diff options
Diffstat (limited to 'kernel/fs/nfs')
89 files changed, 66716 insertions, 0 deletions
diff --git a/kernel/fs/nfs/Kconfig b/kernel/fs/nfs/Kconfig new file mode 100644 index 000000000..f31fd0dd9 --- /dev/null +++ b/kernel/fs/nfs/Kconfig @@ -0,0 +1,202 @@ +config NFS_FS + tristate "NFS client support" + depends on INET && FILE_LOCKING && MULTIUSER + select LOCKD + select SUNRPC + select NFS_ACL_SUPPORT if NFS_V3_ACL + help + Choose Y here if you want to access files residing on other + computers using Sun's Network File System protocol. To compile + this file system support as a module, choose M here: the module + will be called nfs. + + To mount file systems exported by NFS servers, you also need to + install the user space mount.nfs command which can be found in + the Linux nfs-utils package, available from http://linux-nfs.org/. + Information about using the mount command is available in the + mount(8) man page. More detail about the Linux NFS client + implementation is available via the nfs(5) man page. + + Below you can choose which versions of the NFS protocol are + available in the kernel to mount NFS servers. Support for NFS + version 2 (RFC 1094) is always available when NFS_FS is selected. + + To configure a system which mounts its root file system via NFS + at boot time, say Y here, select "Kernel level IP + autoconfiguration" in the NETWORK menu, and select "Root file + system on NFS" below. You cannot compile this file system as a + module in this case. + + If unsure, say N. + +config NFS_V2 + tristate "NFS client support for NFS version 2" + depends on NFS_FS + default y + help + This option enables support for version 2 of the NFS protocol + (RFC 1094) in the kernel's NFS client. + + If unsure, say Y. + +config NFS_V3 + tristate "NFS client support for NFS version 3" + depends on NFS_FS + default y + help + This option enables support for version 3 of the NFS protocol + (RFC 1813) in the kernel's NFS client. + + If unsure, say Y. + +config NFS_V3_ACL + bool "NFS client support for the NFSv3 ACL protocol extension" + depends on NFS_V3 + help + Some NFS servers support an auxiliary NFSv3 ACL protocol that + Sun added to Solaris but never became an official part of the + NFS version 3 protocol. This protocol extension allows + applications on NFS clients to manipulate POSIX Access Control + Lists on files residing on NFS servers. NFS servers enforce + ACLs on local files whether this protocol is available or not. + + Choose Y here if your NFS server supports the Solaris NFSv3 ACL + protocol extension and you want your NFS client to allow + applications to access and modify ACLs on files on the server. + + Most NFS servers don't support the Solaris NFSv3 ACL protocol + extension. You can choose N here or specify the "noacl" mount + option to prevent your NFS client from trying to use the NFSv3 + ACL protocol. + + If unsure, say N. + +config NFS_V4 + tristate "NFS client support for NFS version 4" + depends on NFS_FS + select SUNRPC_GSS + select KEYS + help + This option enables support for version 4 of the NFS protocol + (RFC 3530) in the kernel's NFS client. + + To mount NFS servers using NFSv4, you also need to install user + space programs which can be found in the Linux nfs-utils package, + available from http://linux-nfs.org/. + + If unsure, say Y. + +config NFS_SWAP + bool "Provide swap over NFS support" + default n + depends on NFS_FS + select SUNRPC_SWAP + help + This option enables swapon to work on files located on NFS mounts. + +config NFS_V4_1 + bool "NFS client support for NFSv4.1" + depends on NFS_V4 + select SUNRPC_BACKCHANNEL + help + This option enables support for minor version 1 of the NFSv4 protocol + (RFC 5661) in the kernel's NFS client. + + If unsure, say N. + +config NFS_V4_2 + bool "NFS client support for NFSv4.2" + depends on NFS_V4_1 + help + This option enables support for minor version 2 of the NFSv4 protocol + in the kernel's NFS client. + + If unsure, say N. + +config PNFS_FILE_LAYOUT + tristate + depends on NFS_V4_1 + default NFS_V4 + +config PNFS_BLOCK + tristate + depends on NFS_V4_1 && BLK_DEV_DM + default NFS_V4 + +config PNFS_OBJLAYOUT + tristate + depends on NFS_V4_1 && SCSI_OSD_ULD + default NFS_V4 + +config PNFS_FLEXFILE_LAYOUT + tristate + depends on NFS_V4_1 && NFS_V3 + default m + +config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN + string "NFSv4.1 Implementation ID Domain" + depends on NFS_V4_1 + default "kernel.org" + help + This option defines the domain portion of the implementation ID that + may be sent in the NFS exchange_id operation. The value must be in + the format of a DNS domain name and should be set to the DNS domain + name of the distribution. + If the NFS client is unchanged from the upstream kernel, this + option should be set to the default "kernel.org". + +config NFS_V4_1_MIGRATION + bool "NFSv4.1 client support for migration" + depends on NFS_V4_1 + default n + help + This option makes the NFS client advertise to NFSv4.1 servers that + it can support NFSv4 migration. + + The NFSv4.1 pieces of the Linux NFSv4 migration implementation are + still experimental. If you are not an NFSv4 developer, say N here. + +config NFS_V4_SECURITY_LABEL + bool + depends on NFS_V4_2 && SECURITY + default y + +config ROOT_NFS + bool "Root file system on NFS" + depends on NFS_FS=y && IP_PNP + help + If you want your system to mount its root file system via NFS, + choose Y here. This is common practice for managing systems + without local permanent storage. For details, read + <file:Documentation/filesystems/nfs/nfsroot.txt>. + + Most people say N here. + +config NFS_FSCACHE + bool "Provide NFS client caching support" + depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y + help + Say Y here if you want NFS data to be cached locally on disc through + the general filesystem cache manager + +config NFS_USE_LEGACY_DNS + bool "Use the legacy NFS DNS resolver" + depends on NFS_V4 + help + The kernel now provides a method for translating a host name into an + IP address. Select Y here if you would rather use your own DNS + resolver script. + + If unsure, say N + +config NFS_USE_KERNEL_DNS + bool + depends on NFS_V4 && !NFS_USE_LEGACY_DNS + select DNS_RESOLVER + default y + +config NFS_DEBUG + bool + depends on NFS_FS && SUNRPC_DEBUG + select CRC32 + default y diff --git a/kernel/fs/nfs/Makefile b/kernel/fs/nfs/Makefile new file mode 100644 index 000000000..866441795 --- /dev/null +++ b/kernel/fs/nfs/Makefile @@ -0,0 +1,36 @@ +# +# Makefile for the Linux nfs filesystem routines. +# + +obj-$(CONFIG_NFS_FS) += nfs.o + +CFLAGS_nfstrace.o += -I$(src) +nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ + direct.o pagelist.o read.o symlink.o unlink.o \ + write.o namespace.o mount_clnt.o nfstrace.o +nfs-$(CONFIG_ROOT_NFS) += nfsroot.o +nfs-$(CONFIG_SYSCTL) += sysctl.o +nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o + +obj-$(CONFIG_NFS_V2) += nfsv2.o +nfsv2-y := nfs2super.o proc.o nfs2xdr.o + +obj-$(CONFIG_NFS_V3) += nfsv3.o +nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o +nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o + +obj-$(CONFIG_NFS_V4) += nfsv4.o +CFLAGS_nfs4trace.o += -I$(src) +nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ + delegation.o nfs4idmap.o callback.o callback_xdr.o callback_proc.o \ + nfs4namespace.o nfs4getroot.o nfs4client.o nfs4session.o \ + dns_resolve.o nfs4trace.o +nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o +nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o pnfs_nfs.o +nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o + +obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ +obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/ +obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ +obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ diff --git a/kernel/fs/nfs/blocklayout/Makefile b/kernel/fs/nfs/blocklayout/Makefile new file mode 100644 index 000000000..3ca14c36d --- /dev/null +++ b/kernel/fs/nfs/blocklayout/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for the pNFS block layout driver kernel module +# +obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o + +blocklayoutdriver-y += blocklayout.o dev.o extent_tree.o rpc_pipefs.o diff --git a/kernel/fs/nfs/blocklayout/blocklayout.c b/kernel/fs/nfs/blocklayout/blocklayout.c new file mode 100644 index 000000000..d2554fe14 --- /dev/null +++ b/kernel/fs/nfs/blocklayout/blocklayout.c @@ -0,0 +1,928 @@ +/* + * linux/fs/nfs/blocklayout/blocklayout.c + * + * Module for the NFSv4.1 pNFS block layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/bio.h> /* struct bio */ +#include <linux/prefetch.h> +#include <linux/pagevec.h> + +#include "../pnfs.h" +#include "../nfs4session.h" +#include "../internal.h" +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>"); +MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver"); + +static bool is_hole(struct pnfs_block_extent *be) +{ + switch (be->be_state) { + case PNFS_BLOCK_NONE_DATA: + return true; + case PNFS_BLOCK_INVALID_DATA: + return be->be_tag ? false : true; + default: + return false; + } +} + +/* The data we are handed might be spread across several bios. We need + * to track when the last one is finished. + */ +struct parallel_io { + struct kref refcnt; + void (*pnfs_callback) (void *data); + void *data; +}; + +static inline struct parallel_io *alloc_parallel(void *data) +{ + struct parallel_io *rv; + + rv = kmalloc(sizeof(*rv), GFP_NOFS); + if (rv) { + rv->data = data; + kref_init(&rv->refcnt); + } + return rv; +} + +static inline void get_parallel(struct parallel_io *p) +{ + kref_get(&p->refcnt); +} + +static void destroy_parallel(struct kref *kref) +{ + struct parallel_io *p = container_of(kref, struct parallel_io, refcnt); + + dprintk("%s enter\n", __func__); + p->pnfs_callback(p->data); + kfree(p); +} + +static inline void put_parallel(struct parallel_io *p) +{ + kref_put(&p->refcnt, destroy_parallel); +} + +static struct bio * +bl_submit_bio(int rw, struct bio *bio) +{ + if (bio) { + get_parallel(bio->bi_private); + dprintk("%s submitting %s bio %u@%llu\n", __func__, + rw == READ ? "read" : "write", bio->bi_iter.bi_size, + (unsigned long long)bio->bi_iter.bi_sector); + submit_bio(rw, bio); + } + return NULL; +} + +static struct bio * +bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, + void (*end_io)(struct bio *, int err), struct parallel_io *par) +{ + struct bio *bio; + + npg = min(npg, BIO_MAX_PAGES); + bio = bio_alloc(GFP_NOIO, npg); + if (!bio && (current->flags & PF_MEMALLOC)) { + while (!bio && (npg /= 2)) + bio = bio_alloc(GFP_NOIO, npg); + } + + if (bio) { + bio->bi_iter.bi_sector = disk_sector; + bio->bi_bdev = bdev; + bio->bi_end_io = end_io; + bio->bi_private = par; + } + return bio; +} + +static struct bio * +do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, + struct page *page, struct pnfs_block_dev_map *map, + struct pnfs_block_extent *be, + void (*end_io)(struct bio *, int err), + struct parallel_io *par, unsigned int offset, int *len) +{ + struct pnfs_block_dev *dev = + container_of(be->be_device, struct pnfs_block_dev, node); + u64 disk_addr, end; + + dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__, + npg, rw, (unsigned long long)isect, offset, *len); + + /* translate to device offset */ + isect += be->be_v_offset; + isect -= be->be_f_offset; + + /* translate to physical disk offset */ + disk_addr = (u64)isect << SECTOR_SHIFT; + if (disk_addr < map->start || disk_addr >= map->start + map->len) { + if (!dev->map(dev, disk_addr, map)) + return ERR_PTR(-EIO); + bio = bl_submit_bio(rw, bio); + } + disk_addr += map->disk_offset; + disk_addr -= map->start; + + /* limit length to what the device mapping allows */ + end = disk_addr + *len; + if (end >= map->start + map->len) + *len = map->start + map->len - disk_addr; + +retry: + if (!bio) { + bio = bl_alloc_init_bio(npg, map->bdev, + disk_addr >> SECTOR_SHIFT, end_io, par); + if (!bio) + return ERR_PTR(-ENOMEM); + } + if (bio_add_page(bio, page, *len, offset) < *len) { + bio = bl_submit_bio(rw, bio); + goto retry; + } + return bio; +} + +static void bl_end_io_read(struct bio *bio, int err) +{ + struct parallel_io *par = bio->bi_private; + + if (err) { + struct nfs_pgio_header *header = par->data; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); + } + + bio_put(bio); + put_parallel(par); +} + +static void bl_read_cleanup(struct work_struct *work) +{ + struct rpc_task *task; + struct nfs_pgio_header *hdr; + dprintk("%s enter\n", __func__); + task = container_of(work, struct rpc_task, u.tk_work); + hdr = container_of(task, struct nfs_pgio_header, task); + pnfs_ld_read_done(hdr); +} + +static void +bl_end_par_io_read(void *data) +{ + struct nfs_pgio_header *hdr = data; + + hdr->task.tk_status = hdr->pnfs_error; + INIT_WORK(&hdr->task.u.tk_work, bl_read_cleanup); + schedule_work(&hdr->task.u.tk_work); +} + +static enum pnfs_try_status +bl_read_pagelist(struct nfs_pgio_header *header) +{ + struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg); + struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 }; + struct bio *bio = NULL; + struct pnfs_block_extent be; + sector_t isect, extent_length = 0; + struct parallel_io *par; + loff_t f_offset = header->args.offset; + size_t bytes_left = header->args.count; + unsigned int pg_offset, pg_len; + struct page **pages = header->args.pages; + int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; + const bool is_dio = (header->dreq != NULL); + struct blk_plug plug; + int i; + + dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__, + header->page_array.npages, f_offset, + (unsigned int)header->args.count); + + par = alloc_parallel(header); + if (!par) + return PNFS_NOT_ATTEMPTED; + par->pnfs_callback = bl_end_par_io_read; + + blk_start_plug(&plug); + + isect = (sector_t) (f_offset >> SECTOR_SHIFT); + /* Code assumes extents are page-aligned */ + for (i = pg_index; i < header->page_array.npages; i++) { + if (extent_length <= 0) { + /* We've used up the previous extent */ + bio = bl_submit_bio(READ, bio); + + /* Get the next one */ + if (!ext_tree_lookup(bl, isect, &be, false)) { + header->pnfs_error = -EIO; + goto out; + } + extent_length = be.be_length - (isect - be.be_f_offset); + } + + pg_offset = f_offset & ~PAGE_CACHE_MASK; + if (is_dio) { + if (pg_offset + bytes_left > PAGE_CACHE_SIZE) + pg_len = PAGE_CACHE_SIZE - pg_offset; + else + pg_len = bytes_left; + } else { + BUG_ON(pg_offset != 0); + pg_len = PAGE_CACHE_SIZE; + } + + isect += (pg_offset >> SECTOR_SHIFT); + extent_length -= (pg_offset >> SECTOR_SHIFT); + + if (is_hole(&be)) { + bio = bl_submit_bio(READ, bio); + /* Fill hole w/ zeroes w/o accessing device */ + dprintk("%s Zeroing page for hole\n", __func__); + zero_user_segment(pages[i], pg_offset, pg_len); + + /* invalidate map */ + map.start = NFS4_MAX_UINT64; + } else { + bio = do_add_page_to_bio(bio, + header->page_array.npages - i, + READ, + isect, pages[i], &map, &be, + bl_end_io_read, par, + pg_offset, &pg_len); + if (IS_ERR(bio)) { + header->pnfs_error = PTR_ERR(bio); + bio = NULL; + goto out; + } + } + isect += (pg_len >> SECTOR_SHIFT); + extent_length -= (pg_len >> SECTOR_SHIFT); + f_offset += pg_len; + bytes_left -= pg_len; + } + if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { + header->res.eof = 1; + header->res.count = header->inode->i_size - header->args.offset; + } else { + header->res.count = (isect << SECTOR_SHIFT) - header->args.offset; + } +out: + bl_submit_bio(READ, bio); + blk_finish_plug(&plug); + put_parallel(par); + return PNFS_ATTEMPTED; +} + +static void bl_end_io_write(struct bio *bio, int err) +{ + struct parallel_io *par = bio->bi_private; + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct nfs_pgio_header *header = par->data; + + if (!uptodate) { + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); + } + bio_put(bio); + put_parallel(par); +} + +/* Function scheduled for call during bl_end_par_io_write, + * it marks sectors as written and extends the commitlist. + */ +static void bl_write_cleanup(struct work_struct *work) +{ + struct rpc_task *task = container_of(work, struct rpc_task, u.tk_work); + struct nfs_pgio_header *hdr = + container_of(task, struct nfs_pgio_header, task); + + dprintk("%s enter\n", __func__); + + if (likely(!hdr->pnfs_error)) { + struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg); + u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK; + u64 end = (hdr->args.offset + hdr->args.count + + PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK; + + ext_tree_mark_written(bl, start >> SECTOR_SHIFT, + (end - start) >> SECTOR_SHIFT); + } + + pnfs_ld_write_done(hdr); +} + +/* Called when last of bios associated with a bl_write_pagelist call finishes */ +static void bl_end_par_io_write(void *data) +{ + struct nfs_pgio_header *hdr = data; + + hdr->task.tk_status = hdr->pnfs_error; + hdr->verf.committed = NFS_FILE_SYNC; + INIT_WORK(&hdr->task.u.tk_work, bl_write_cleanup); + schedule_work(&hdr->task.u.tk_work); +} + +static enum pnfs_try_status +bl_write_pagelist(struct nfs_pgio_header *header, int sync) +{ + struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg); + struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 }; + struct bio *bio = NULL; + struct pnfs_block_extent be; + sector_t isect, extent_length = 0; + struct parallel_io *par = NULL; + loff_t offset = header->args.offset; + size_t count = header->args.count; + struct page **pages = header->args.pages; + int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; + unsigned int pg_len; + struct blk_plug plug; + int i; + + dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); + + /* At this point, header->page_aray is a (sequential) list of nfs_pages. + * We want to write each, and if there is an error set pnfs_error + * to have it redone using nfs. + */ + par = alloc_parallel(header); + if (!par) + return PNFS_NOT_ATTEMPTED; + par->pnfs_callback = bl_end_par_io_write; + + blk_start_plug(&plug); + + /* we always write out the whole page */ + offset = offset & (loff_t)PAGE_CACHE_MASK; + isect = offset >> SECTOR_SHIFT; + + for (i = pg_index; i < header->page_array.npages; i++) { + if (extent_length <= 0) { + /* We've used up the previous extent */ + bio = bl_submit_bio(WRITE, bio); + /* Get the next one */ + if (!ext_tree_lookup(bl, isect, &be, true)) { + header->pnfs_error = -EINVAL; + goto out; + } + + extent_length = be.be_length - (isect - be.be_f_offset); + } + + pg_len = PAGE_CACHE_SIZE; + bio = do_add_page_to_bio(bio, header->page_array.npages - i, + WRITE, isect, pages[i], &map, &be, + bl_end_io_write, par, + 0, &pg_len); + if (IS_ERR(bio)) { + header->pnfs_error = PTR_ERR(bio); + bio = NULL; + goto out; + } + + offset += pg_len; + count -= pg_len; + isect += (pg_len >> SECTOR_SHIFT); + extent_length -= (pg_len >> SECTOR_SHIFT); + } + + header->res.count = header->args.count; +out: + bl_submit_bio(WRITE, bio); + blk_finish_plug(&plug); + put_parallel(par); + return PNFS_ATTEMPTED; +} + +static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + int err; + + dprintk("%s enter\n", __func__); + + err = ext_tree_remove(bl, true, 0, LLONG_MAX); + WARN_ON(err); + + kfree(bl); +} + +static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode, + gfp_t gfp_flags) +{ + struct pnfs_block_layout *bl; + + dprintk("%s enter\n", __func__); + bl = kzalloc(sizeof(*bl), gfp_flags); + if (!bl) + return NULL; + + bl->bl_ext_rw = RB_ROOT; + bl->bl_ext_ro = RB_ROOT; + spin_lock_init(&bl->bl_ext_lock); + + return &bl->bl_layout; +} + +static void bl_free_lseg(struct pnfs_layout_segment *lseg) +{ + dprintk("%s enter\n", __func__); + kfree(lseg); +} + +/* Tracks info needed to ensure extents in layout obey constraints of spec */ +struct layout_verification { + u32 mode; /* R or RW */ + u64 start; /* Expected start of next non-COW extent */ + u64 inval; /* Start of INVAL coverage */ + u64 cowread; /* End of COW read coverage */ +}; + +/* Verify the extent meets the layout requirements of the pnfs-block draft, + * section 2.3.1. + */ +static int verify_extent(struct pnfs_block_extent *be, + struct layout_verification *lv) +{ + if (lv->mode == IOMODE_READ) { + if (be->be_state == PNFS_BLOCK_READWRITE_DATA || + be->be_state == PNFS_BLOCK_INVALID_DATA) + return -EIO; + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } + /* lv->mode == IOMODE_RW */ + if (be->be_state == PNFS_BLOCK_READWRITE_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + if (lv->cowread > lv->start) + return -EIO; + lv->start += be->be_length; + lv->inval = lv->start; + return 0; + } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } else if (be->be_state == PNFS_BLOCK_READ_DATA) { + if (be->be_f_offset > lv->start) + return -EIO; + if (be->be_f_offset < lv->inval) + return -EIO; + if (be->be_f_offset < lv->cowread) + return -EIO; + /* It looks like you might want to min this with lv->start, + * but you really don't. + */ + lv->inval = lv->inval + be->be_length; + lv->cowread = be->be_f_offset + be->be_length; + return 0; + } else + return -EIO; +} + +static int decode_sector_number(__be32 **rp, sector_t *sp) +{ + uint64_t s; + + *rp = xdr_decode_hyper(*rp, &s); + if (s & 0x1ff) { + printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__); + return -1; + } + *sp = s >> SECTOR_SHIFT; + return 0; +} + +static int +bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo, + struct layout_verification *lv, struct list_head *extents, + gfp_t gfp_mask) +{ + struct pnfs_block_extent *be; + struct nfs4_deviceid id; + int error; + __be32 *p; + + p = xdr_inline_decode(xdr, 28 + NFS4_DEVICEID4_SIZE); + if (!p) + return -EIO; + + be = kzalloc(sizeof(*be), GFP_NOFS); + if (!be) + return -ENOMEM; + + memcpy(&id, p, NFS4_DEVICEID4_SIZE); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + + error = -EIO; + be->be_device = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id, + lo->plh_lc_cred, gfp_mask); + if (!be->be_device) + goto out_free_be; + + /* + * The next three values are read in as bytes, but stored in the + * extent structure in 512-byte granularity. + */ + if (decode_sector_number(&p, &be->be_f_offset) < 0) + goto out_put_deviceid; + if (decode_sector_number(&p, &be->be_length) < 0) + goto out_put_deviceid; + if (decode_sector_number(&p, &be->be_v_offset) < 0) + goto out_put_deviceid; + be->be_state = be32_to_cpup(p++); + + error = verify_extent(be, lv); + if (error) { + dprintk("%s: extent verification failed\n", __func__); + goto out_put_deviceid; + } + + list_add_tail(&be->be_list, extents); + return 0; + +out_put_deviceid: + nfs4_put_deviceid_node(be->be_device); +out_free_be: + kfree(be); + return error; +} + +static struct pnfs_layout_segment * +bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr, + gfp_t gfp_mask) +{ + struct layout_verification lv = { + .mode = lgr->range.iomode, + .start = lgr->range.offset >> SECTOR_SHIFT, + .inval = lgr->range.offset >> SECTOR_SHIFT, + .cowread = lgr->range.offset >> SECTOR_SHIFT, + }; + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + struct pnfs_layout_segment *lseg; + struct xdr_buf buf; + struct xdr_stream xdr; + struct page *scratch; + int status, i; + uint32_t count; + __be32 *p; + LIST_HEAD(extents); + + dprintk("---> %s\n", __func__); + + lseg = kzalloc(sizeof(*lseg), gfp_mask); + if (!lseg) + return ERR_PTR(-ENOMEM); + + status = -ENOMEM; + scratch = alloc_page(gfp_mask); + if (!scratch) + goto out; + + xdr_init_decode_pages(&xdr, &buf, + lgr->layoutp->pages, lgr->layoutp->len); + xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE); + + status = -EIO; + p = xdr_inline_decode(&xdr, 4); + if (unlikely(!p)) + goto out_free_scratch; + + count = be32_to_cpup(p++); + dprintk("%s: number of extents %d\n", __func__, count); + + /* + * Decode individual extents, putting them in temporary staging area + * until whole layout is decoded to make error recovery easier. + */ + for (i = 0; i < count; i++) { + status = bl_alloc_extent(&xdr, lo, &lv, &extents, gfp_mask); + if (status) + goto process_extents; + } + + if (lgr->range.offset + lgr->range.length != + lv.start << SECTOR_SHIFT) { + dprintk("%s Final length mismatch\n", __func__); + status = -EIO; + goto process_extents; + } + + if (lv.start < lv.cowread) { + dprintk("%s Final uncovered COW extent\n", __func__); + status = -EIO; + } + +process_extents: + while (!list_empty(&extents)) { + struct pnfs_block_extent *be = + list_first_entry(&extents, struct pnfs_block_extent, + be_list); + list_del(&be->be_list); + + if (!status) + status = ext_tree_insert(bl, be); + + if (status) { + nfs4_put_deviceid_node(be->be_device); + kfree(be); + } + } + +out_free_scratch: + __free_page(scratch); +out: + dprintk("%s returns %d\n", __func__, status); + if (status) { + kfree(lseg); + return ERR_PTR(status); + } + return lseg; +} + +static void +bl_return_range(struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(lo); + sector_t offset = range->offset >> SECTOR_SHIFT, end; + + if (range->offset % 8) { + dprintk("%s: offset %lld not block size aligned\n", + __func__, range->offset); + return; + } + + if (range->length != NFS4_MAX_UINT64) { + if (range->length % 8) { + dprintk("%s: length %lld not block size aligned\n", + __func__, range->length); + return; + } + + end = offset + (range->length >> SECTOR_SHIFT); + } else { + end = round_down(NFS4_MAX_UINT64, PAGE_SIZE); + } + + ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end); +} + +static int +bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg) +{ + return ext_tree_prepare_commit(arg); +} + +static void +bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata) +{ + ext_tree_mark_committed(&lcdata->args, lcdata->res.status); +} + +static int +bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) +{ + dprintk("%s enter\n", __func__); + + if (server->pnfs_blksize == 0) { + dprintk("%s Server did not return blksize\n", __func__); + return -EINVAL; + } + if (server->pnfs_blksize > PAGE_SIZE) { + printk(KERN_ERR "%s: pNFS blksize %d not supported.\n", + __func__, server->pnfs_blksize); + return -EINVAL; + } + + return 0; +} + +static bool +is_aligned_req(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req, unsigned int alignment) +{ + /* + * Always accept buffered writes, higher layers take care of the + * right alignment. + */ + if (pgio->pg_dreq == NULL) + return true; + + if (!IS_ALIGNED(req->wb_offset, alignment)) + return false; + + if (IS_ALIGNED(req->wb_bytes, alignment)) + return true; + + if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) { + /* + * If the write goes up to the inode size, just write + * the full page. Data past the inode size is + * guaranteed to be zeroed by the higher level client + * code, and this behaviour is mandated by RFC 5663 + * section 2.3.2. + */ + return true; + } + + return false; +} + +static void +bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + if (!is_aligned_req(pgio, req, SECTOR_SIZE)) { + nfs_pageio_reset_read_mds(pgio); + return; + } + + pnfs_generic_pg_init_read(pgio, req); +} + +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t +bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, + struct nfs_page *req) +{ + if (!is_aligned_req(pgio, req, SECTOR_SIZE)) + return 0; + return pnfs_generic_pg_test(pgio, prev, req); +} + +/* + * Return the number of contiguous bytes for a given inode + * starting at page frame idx. + */ +static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t end; + + /* Optimize common case that writes from 0 to end of file */ + end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); + if (end != inode->i_mapping->nrpages) { + rcu_read_lock(); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); + rcu_read_unlock(); + } + + if (!end) + return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT); + else + return (end - idx) << PAGE_CACHE_SHIFT; +} + +static void +bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + u64 wb_size; + + if (!is_aligned_req(pgio, req, PAGE_SIZE)) { + nfs_pageio_reset_write_mds(pgio); + return; + } + + if (pgio->pg_dreq == NULL) + wb_size = pnfs_num_cont_bytes(pgio->pg_inode, + req->wb_index); + else + wb_size = nfs_dreq_bytes_left(pgio->pg_dreq); + + pnfs_generic_pg_init_write(pgio, req, wb_size); +} + +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t +bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, + struct nfs_page *req) +{ + if (!is_aligned_req(pgio, req, PAGE_SIZE)) + return 0; + return pnfs_generic_pg_test(pgio, prev, req); +} + +static const struct nfs_pageio_ops bl_pg_read_ops = { + .pg_init = bl_pg_init_read, + .pg_test = bl_pg_test_read, + .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static const struct nfs_pageio_ops bl_pg_write_ops = { + .pg_init = bl_pg_init_write, + .pg_test = bl_pg_test_write, + .pg_doio = pnfs_generic_pg_writepages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static struct pnfs_layoutdriver_type blocklayout_type = { + .id = LAYOUT_BLOCK_VOLUME, + .name = "LAYOUT_BLOCK_VOLUME", + .owner = THIS_MODULE, + .flags = PNFS_LAYOUTRET_ON_SETATTR | + PNFS_READ_WHOLE_PAGE, + .read_pagelist = bl_read_pagelist, + .write_pagelist = bl_write_pagelist, + .alloc_layout_hdr = bl_alloc_layout_hdr, + .free_layout_hdr = bl_free_layout_hdr, + .alloc_lseg = bl_alloc_lseg, + .free_lseg = bl_free_lseg, + .return_range = bl_return_range, + .prepare_layoutcommit = bl_prepare_layoutcommit, + .cleanup_layoutcommit = bl_cleanup_layoutcommit, + .set_layoutdriver = bl_set_layoutdriver, + .alloc_deviceid_node = bl_alloc_deviceid_node, + .free_deviceid_node = bl_free_deviceid_node, + .pg_read_ops = &bl_pg_read_ops, + .pg_write_ops = &bl_pg_write_ops, + .sync = pnfs_generic_sync, +}; + +static int __init nfs4blocklayout_init(void) +{ + int ret; + + dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__); + + ret = pnfs_register_layoutdriver(&blocklayout_type); + if (ret) + goto out; + ret = bl_init_pipefs(); + if (ret) + goto out_unregister; + return 0; + +out_unregister: + pnfs_unregister_layoutdriver(&blocklayout_type); +out: + return ret; +} + +static void __exit nfs4blocklayout_exit(void) +{ + dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n", + __func__); + + bl_cleanup_pipefs(); + pnfs_unregister_layoutdriver(&blocklayout_type); +} + +MODULE_ALIAS("nfs-layouttype4-3"); + +module_init(nfs4blocklayout_init); +module_exit(nfs4blocklayout_exit); diff --git a/kernel/fs/nfs/blocklayout/blocklayout.h b/kernel/fs/nfs/blocklayout/blocklayout.h new file mode 100644 index 000000000..92dca9e90 --- /dev/null +++ b/kernel/fs/nfs/blocklayout/blocklayout.h @@ -0,0 +1,204 @@ +/* + * linux/fs/nfs/blocklayout/blocklayout.h + * + * Module for the NFSv4.1 pNFS block layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ +#ifndef FS_NFS_NFS4BLOCKLAYOUT_H +#define FS_NFS_NFS4BLOCKLAYOUT_H + +#include <linux/device-mapper.h> +#include <linux/nfs_fs.h> +#include <linux/sunrpc/rpc_pipe_fs.h> + +#include "../nfs4_fs.h" +#include "../pnfs.h" +#include "../netns.h" + +#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT) +#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT) +#define SECTOR_SIZE (1 << SECTOR_SHIFT) + +struct pnfs_block_dev; + +enum pnfs_block_volume_type { + PNFS_BLOCK_VOLUME_SIMPLE = 0, + PNFS_BLOCK_VOLUME_SLICE = 1, + PNFS_BLOCK_VOLUME_CONCAT = 2, + PNFS_BLOCK_VOLUME_STRIPE = 3, +}; + +#define PNFS_BLOCK_MAX_UUIDS 4 +#define PNFS_BLOCK_MAX_DEVICES 64 + +/* + * Random upper cap for the uuid length to avoid unbounded allocation. + * Not actually limited by the protocol. + */ +#define PNFS_BLOCK_UUID_LEN 128 + + +struct pnfs_block_volume { + enum pnfs_block_volume_type type; + union { + struct { + int len; + int nr_sigs; + struct { + u64 offset; + u32 sig_len; + u8 sig[PNFS_BLOCK_UUID_LEN]; + } sigs[PNFS_BLOCK_MAX_UUIDS]; + } simple; + struct { + u64 start; + u64 len; + u32 volume; + } slice; + struct { + u32 volumes_count; + u32 volumes[PNFS_BLOCK_MAX_DEVICES]; + } concat; + struct { + u64 chunk_size; + u32 volumes_count; + u32 volumes[PNFS_BLOCK_MAX_DEVICES]; + } stripe; + }; +}; + +struct pnfs_block_dev_map { + sector_t start; + sector_t len; + + sector_t disk_offset; + struct block_device *bdev; +}; + +struct pnfs_block_dev { + struct nfs4_deviceid_node node; + + u64 start; + u64 len; + + u32 nr_children; + struct pnfs_block_dev *children; + u64 chunk_size; + + struct block_device *bdev; + u64 disk_offset; + + bool (*map)(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map); +}; + +enum exstate4 { + PNFS_BLOCK_READWRITE_DATA = 0, + PNFS_BLOCK_READ_DATA = 1, + PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */ + PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */ +}; + +/* sector_t fields are all in 512-byte sectors */ +struct pnfs_block_extent { + union { + struct rb_node be_node; + struct list_head be_list; + }; + struct nfs4_deviceid_node *be_device; + sector_t be_f_offset; /* the starting offset in the file */ + sector_t be_length; /* the size of the extent */ + sector_t be_v_offset; /* the starting offset in the volume */ + enum exstate4 be_state; /* the state of this extent */ +#define EXTENT_WRITTEN 1 +#define EXTENT_COMMITTING 2 + unsigned int be_tag; +}; + +/* on the wire size of the extent */ +#define BL_EXTENT_SIZE (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE) + +struct pnfs_block_layout { + struct pnfs_layout_hdr bl_layout; + struct rb_root bl_ext_rw; + struct rb_root bl_ext_ro; + spinlock_t bl_ext_lock; /* Protects list manipulation */ +}; + +static inline struct pnfs_block_layout * +BLK_LO2EXT(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct pnfs_block_layout, bl_layout); +} + +static inline struct pnfs_block_layout * +BLK_LSEG2EXT(struct pnfs_layout_segment *lseg) +{ + return BLK_LO2EXT(lseg->pls_layout); +} + +struct bl_pipe_msg { + struct rpc_pipe_msg msg; + wait_queue_head_t *bl_wq; +}; + +struct bl_msg_hdr { + u8 type; + u16 totallen; /* length of entire message, including hdr itself */ +}; + +#define BL_DEVICE_UMOUNT 0x0 /* Umount--delete devices */ +#define BL_DEVICE_MOUNT 0x1 /* Mount--create devices*/ +#define BL_DEVICE_REQUEST_INIT 0x0 /* Start request */ +#define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */ +#define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */ + +/* dev.c */ +struct nfs4_deviceid_node *bl_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_mask); +void bl_free_deviceid_node(struct nfs4_deviceid_node *d); + +/* extent_tree.c */ +int ext_tree_insert(struct pnfs_block_layout *bl, + struct pnfs_block_extent *new); +int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start, + sector_t end); +int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, + sector_t len); +bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect, + struct pnfs_block_extent *ret, bool rw); +int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg); +void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status); + +/* rpc_pipefs.c */ +dev_t bl_resolve_deviceid(struct nfs_server *server, + struct pnfs_block_volume *b, gfp_t gfp_mask); +int __init bl_init_pipefs(void); +void __exit bl_cleanup_pipefs(void); + +#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */ diff --git a/kernel/fs/nfs/blocklayout/dev.c b/kernel/fs/nfs/blocklayout/dev.c new file mode 100644 index 000000000..e535599a0 --- /dev/null +++ b/kernel/fs/nfs/blocklayout/dev.c @@ -0,0 +1,363 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#include <linux/sunrpc/svc.h> +#include <linux/blkdev.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_xdr.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static void +bl_free_device(struct pnfs_block_dev *dev) +{ + if (dev->nr_children) { + int i; + + for (i = 0; i < dev->nr_children; i++) + bl_free_device(&dev->children[i]); + kfree(dev->children); + } else { + if (dev->bdev) + blkdev_put(dev->bdev, FMODE_READ); + } +} + +void +bl_free_deviceid_node(struct nfs4_deviceid_node *d) +{ + struct pnfs_block_dev *dev = + container_of(d, struct pnfs_block_dev, node); + + bl_free_device(dev); + kfree_rcu(dev, node.rcu); +} + +static int +nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b) +{ + __be32 *p; + int i; + + p = xdr_inline_decode(xdr, 4); + if (!p) + return -EIO; + b->type = be32_to_cpup(p++); + + switch (b->type) { + case PNFS_BLOCK_VOLUME_SIMPLE: + p = xdr_inline_decode(xdr, 4); + if (!p) + return -EIO; + b->simple.nr_sigs = be32_to_cpup(p++); + if (!b->simple.nr_sigs) { + dprintk("no signature\n"); + return -EIO; + } + + b->simple.len = 4 + 4; + for (i = 0; i < b->simple.nr_sigs; i++) { + p = xdr_inline_decode(xdr, 8 + 4); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &b->simple.sigs[i].offset); + b->simple.sigs[i].sig_len = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, b->simple.sigs[i].sig_len); + if (!p) + return -EIO; + memcpy(&b->simple.sigs[i].sig, p, + b->simple.sigs[i].sig_len); + + b->simple.len += 8 + 4 + b->simple.sigs[i].sig_len; + } + break; + case PNFS_BLOCK_VOLUME_SLICE: + p = xdr_inline_decode(xdr, 8 + 8 + 4); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &b->slice.start); + p = xdr_decode_hyper(p, &b->slice.len); + b->slice.volume = be32_to_cpup(p++); + break; + case PNFS_BLOCK_VOLUME_CONCAT: + p = xdr_inline_decode(xdr, 4); + if (!p) + return -EIO; + b->concat.volumes_count = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, b->concat.volumes_count * 4); + if (!p) + return -EIO; + for (i = 0; i < b->concat.volumes_count; i++) + b->concat.volumes[i] = be32_to_cpup(p++); + break; + case PNFS_BLOCK_VOLUME_STRIPE: + p = xdr_inline_decode(xdr, 8 + 4); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &b->stripe.chunk_size); + b->stripe.volumes_count = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, b->stripe.volumes_count * 4); + if (!p) + return -EIO; + for (i = 0; i < b->stripe.volumes_count; i++) + b->stripe.volumes[i] = be32_to_cpup(p++); + break; + default: + dprintk("unknown volume type!\n"); + return -EIO; + } + + return 0; +} + +static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map) +{ + map->start = dev->start; + map->len = dev->len; + map->disk_offset = dev->disk_offset; + map->bdev = dev->bdev; + return true; +} + +static bool bl_map_concat(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map) +{ + int i; + + for (i = 0; i < dev->nr_children; i++) { + struct pnfs_block_dev *child = &dev->children[i]; + + if (child->start > offset || + child->start + child->len <= offset) + continue; + + child->map(child, offset - child->start, map); + return true; + } + + dprintk("%s: ran off loop!\n", __func__); + return false; +} + +static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset, + struct pnfs_block_dev_map *map) +{ + struct pnfs_block_dev *child; + u64 chunk; + u32 chunk_idx; + u64 disk_offset; + + chunk = div_u64(offset, dev->chunk_size); + div_u64_rem(chunk, dev->nr_children, &chunk_idx); + + if (chunk_idx > dev->nr_children) { + dprintk("%s: invalid chunk idx %d (%lld/%lld)\n", + __func__, chunk_idx, offset, dev->chunk_size); + /* error, should not happen */ + return false; + } + + /* truncate offset to the beginning of the stripe */ + offset = chunk * dev->chunk_size; + + /* disk offset of the stripe */ + disk_offset = div_u64(offset, dev->nr_children); + + child = &dev->children[chunk_idx]; + child->map(child, disk_offset, map); + + map->start += offset; + map->disk_offset += disk_offset; + map->len = dev->chunk_size; + return true; +} + +static int +bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask); + + +static int +bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + dev_t dev; + + dev = bl_resolve_deviceid(server, v, gfp_mask); + if (!dev) + return -EIO; + + d->bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + if (IS_ERR(d->bdev)) { + printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n", + MAJOR(dev), MINOR(dev), PTR_ERR(d->bdev)); + return PTR_ERR(d->bdev); + } + + + d->len = i_size_read(d->bdev->bd_inode); + d->map = bl_map_simple; + + printk(KERN_INFO "pNFS: using block device %s\n", + d->bdev->bd_disk->disk_name); + return 0; +} + +static int +bl_parse_slice(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + int ret; + + ret = bl_parse_deviceid(server, d, volumes, v->slice.volume, gfp_mask); + if (ret) + return ret; + + d->disk_offset = v->slice.start; + d->len = v->slice.len; + return 0; +} + +static int +bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + u64 len = 0; + int ret, i; + + d->children = kcalloc(v->concat.volumes_count, + sizeof(struct pnfs_block_dev), GFP_KERNEL); + if (!d->children) + return -ENOMEM; + + for (i = 0; i < v->concat.volumes_count; i++) { + ret = bl_parse_deviceid(server, &d->children[i], + volumes, v->concat.volumes[i], gfp_mask); + if (ret) + return ret; + + d->nr_children++; + d->children[i].start += len; + len += d->children[i].len; + } + + d->len = len; + d->map = bl_map_concat; + return 0; +} + +static int +bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + struct pnfs_block_volume *v = &volumes[idx]; + u64 len = 0; + int ret, i; + + d->children = kcalloc(v->stripe.volumes_count, + sizeof(struct pnfs_block_dev), GFP_KERNEL); + if (!d->children) + return -ENOMEM; + + for (i = 0; i < v->stripe.volumes_count; i++) { + ret = bl_parse_deviceid(server, &d->children[i], + volumes, v->stripe.volumes[i], gfp_mask); + if (ret) + return ret; + + d->nr_children++; + len += d->children[i].len; + } + + d->len = len; + d->chunk_size = v->stripe.chunk_size; + d->map = bl_map_stripe; + return 0; +} + +static int +bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d, + struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) +{ + switch (volumes[idx].type) { + case PNFS_BLOCK_VOLUME_SIMPLE: + return bl_parse_simple(server, d, volumes, idx, gfp_mask); + case PNFS_BLOCK_VOLUME_SLICE: + return bl_parse_slice(server, d, volumes, idx, gfp_mask); + case PNFS_BLOCK_VOLUME_CONCAT: + return bl_parse_concat(server, d, volumes, idx, gfp_mask); + case PNFS_BLOCK_VOLUME_STRIPE: + return bl_parse_stripe(server, d, volumes, idx, gfp_mask); + default: + dprintk("unsupported volume type: %d\n", volumes[idx].type); + return -EIO; + } +} + +struct nfs4_deviceid_node * +bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_mask) +{ + struct nfs4_deviceid_node *node = NULL; + struct pnfs_block_volume *volumes; + struct pnfs_block_dev *top; + struct xdr_stream xdr; + struct xdr_buf buf; + struct page *scratch; + int nr_volumes, ret, i; + __be32 *p; + + scratch = alloc_page(gfp_mask); + if (!scratch) + goto out; + + xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen); + xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (!p) + goto out_free_scratch; + nr_volumes = be32_to_cpup(p++); + + volumes = kcalloc(nr_volumes, sizeof(struct pnfs_block_volume), + gfp_mask); + if (!volumes) + goto out_free_scratch; + + for (i = 0; i < nr_volumes; i++) { + ret = nfs4_block_decode_volume(&xdr, &volumes[i]); + if (ret < 0) + goto out_free_volumes; + } + + top = kzalloc(sizeof(*top), gfp_mask); + if (!top) + goto out_free_volumes; + + ret = bl_parse_deviceid(server, top, volumes, nr_volumes - 1, gfp_mask); + if (ret) { + bl_free_device(top); + kfree(top); + goto out_free_volumes; + } + + node = &top->node; + nfs4_init_deviceid_node(node, server, &pdev->dev_id); + +out_free_volumes: + kfree(volumes); +out_free_scratch: + __free_page(scratch); +out: + return node; +} diff --git a/kernel/fs/nfs/blocklayout/extent_tree.c b/kernel/fs/nfs/blocklayout/extent_tree.c new file mode 100644 index 000000000..31d0b5e53 --- /dev/null +++ b/kernel/fs/nfs/blocklayout/extent_tree.c @@ -0,0 +1,602 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ + +#include <linux/vmalloc.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static inline struct pnfs_block_extent * +ext_node(struct rb_node *node) +{ + return rb_entry(node, struct pnfs_block_extent, be_node); +} + +static struct pnfs_block_extent * +ext_tree_first(struct rb_root *root) +{ + struct rb_node *node = rb_first(root); + return node ? ext_node(node) : NULL; +} + +static struct pnfs_block_extent * +ext_tree_prev(struct pnfs_block_extent *be) +{ + struct rb_node *node = rb_prev(&be->be_node); + return node ? ext_node(node) : NULL; +} + +static struct pnfs_block_extent * +ext_tree_next(struct pnfs_block_extent *be) +{ + struct rb_node *node = rb_next(&be->be_node); + return node ? ext_node(node) : NULL; +} + +static inline sector_t +ext_f_end(struct pnfs_block_extent *be) +{ + return be->be_f_offset + be->be_length; +} + +static struct pnfs_block_extent * +__ext_tree_search(struct rb_root *root, sector_t start) +{ + struct rb_node *node = root->rb_node; + struct pnfs_block_extent *be = NULL; + + while (node) { + be = ext_node(node); + if (start < be->be_f_offset) + node = node->rb_left; + else if (start >= ext_f_end(be)) + node = node->rb_right; + else + return be; + } + + if (be) { + if (start < be->be_f_offset) + return be; + + if (start >= ext_f_end(be)) + return ext_tree_next(be); + } + + return NULL; +} + +static bool +ext_can_merge(struct pnfs_block_extent *be1, struct pnfs_block_extent *be2) +{ + if (be1->be_state != be2->be_state) + return false; + if (be1->be_device != be2->be_device) + return false; + + if (be1->be_f_offset + be1->be_length != be2->be_f_offset) + return false; + + if (be1->be_state != PNFS_BLOCK_NONE_DATA && + (be1->be_v_offset + be1->be_length != be2->be_v_offset)) + return false; + + if (be1->be_state == PNFS_BLOCK_INVALID_DATA && + be1->be_tag != be2->be_tag) + return false; + + return true; +} + +static struct pnfs_block_extent * +ext_try_to_merge_left(struct rb_root *root, struct pnfs_block_extent *be) +{ + struct pnfs_block_extent *left = ext_tree_prev(be); + + if (left && ext_can_merge(left, be)) { + left->be_length += be->be_length; + rb_erase(&be->be_node, root); + nfs4_put_deviceid_node(be->be_device); + kfree(be); + return left; + } + + return be; +} + +static struct pnfs_block_extent * +ext_try_to_merge_right(struct rb_root *root, struct pnfs_block_extent *be) +{ + struct pnfs_block_extent *right = ext_tree_next(be); + + if (right && ext_can_merge(be, right)) { + be->be_length += right->be_length; + rb_erase(&right->be_node, root); + nfs4_put_deviceid_node(right->be_device); + kfree(right); + } + + return be; +} + +static void +__ext_tree_insert(struct rb_root *root, + struct pnfs_block_extent *new, bool merge_ok) +{ + struct rb_node **p = &root->rb_node, *parent = NULL; + struct pnfs_block_extent *be; + + while (*p) { + parent = *p; + be = ext_node(parent); + + if (new->be_f_offset < be->be_f_offset) { + if (merge_ok && ext_can_merge(new, be)) { + be->be_f_offset = new->be_f_offset; + if (be->be_state != PNFS_BLOCK_NONE_DATA) + be->be_v_offset = new->be_v_offset; + be->be_length += new->be_length; + be = ext_try_to_merge_left(root, be); + goto free_new; + } + p = &(*p)->rb_left; + } else if (new->be_f_offset >= ext_f_end(be)) { + if (merge_ok && ext_can_merge(be, new)) { + be->be_length += new->be_length; + be = ext_try_to_merge_right(root, be); + goto free_new; + } + p = &(*p)->rb_right; + } else { + BUG(); + } + } + + rb_link_node(&new->be_node, parent, p); + rb_insert_color(&new->be_node, root); + return; +free_new: + nfs4_put_deviceid_node(new->be_device); + kfree(new); +} + +static int +__ext_tree_remove(struct rb_root *root, sector_t start, sector_t end) +{ + struct pnfs_block_extent *be; + sector_t len1 = 0, len2 = 0; + sector_t orig_v_offset; + sector_t orig_len; + + be = __ext_tree_search(root, start); + if (!be) + return 0; + if (be->be_f_offset >= end) + return 0; + + orig_v_offset = be->be_v_offset; + orig_len = be->be_length; + + if (start > be->be_f_offset) + len1 = start - be->be_f_offset; + if (ext_f_end(be) > end) + len2 = ext_f_end(be) - end; + + if (len2 > 0) { + if (len1 > 0) { + struct pnfs_block_extent *new; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + return -ENOMEM; + + be->be_length = len1; + + new->be_f_offset = end; + if (be->be_state != PNFS_BLOCK_NONE_DATA) { + new->be_v_offset = + orig_v_offset + orig_len - len2; + } + new->be_length = len2; + new->be_state = be->be_state; + new->be_tag = be->be_tag; + new->be_device = nfs4_get_deviceid(be->be_device); + + __ext_tree_insert(root, new, true); + } else { + be->be_f_offset = end; + if (be->be_state != PNFS_BLOCK_NONE_DATA) { + be->be_v_offset = + orig_v_offset + orig_len - len2; + } + be->be_length = len2; + } + } else { + if (len1 > 0) { + be->be_length = len1; + be = ext_tree_next(be); + } + + while (be && ext_f_end(be) <= end) { + struct pnfs_block_extent *next = ext_tree_next(be); + + rb_erase(&be->be_node, root); + nfs4_put_deviceid_node(be->be_device); + kfree(be); + be = next; + } + + if (be && be->be_f_offset < end) { + len1 = ext_f_end(be) - end; + be->be_f_offset = end; + if (be->be_state != PNFS_BLOCK_NONE_DATA) + be->be_v_offset += be->be_length - len1; + be->be_length = len1; + } + } + + return 0; +} + +int +ext_tree_insert(struct pnfs_block_layout *bl, struct pnfs_block_extent *new) +{ + struct pnfs_block_extent *be; + struct rb_root *root; + int err = 0; + + switch (new->be_state) { + case PNFS_BLOCK_READWRITE_DATA: + case PNFS_BLOCK_INVALID_DATA: + root = &bl->bl_ext_rw; + break; + case PNFS_BLOCK_READ_DATA: + case PNFS_BLOCK_NONE_DATA: + root = &bl->bl_ext_ro; + break; + default: + dprintk("invalid extent type\n"); + return -EINVAL; + } + + spin_lock(&bl->bl_ext_lock); +retry: + be = __ext_tree_search(root, new->be_f_offset); + if (!be || be->be_f_offset >= ext_f_end(new)) { + __ext_tree_insert(root, new, true); + } else if (new->be_f_offset >= be->be_f_offset) { + if (ext_f_end(new) <= ext_f_end(be)) { + nfs4_put_deviceid_node(new->be_device); + kfree(new); + } else { + sector_t new_len = ext_f_end(new) - ext_f_end(be); + sector_t diff = new->be_length - new_len; + + new->be_f_offset += diff; + new->be_v_offset += diff; + new->be_length = new_len; + goto retry; + } + } else if (ext_f_end(new) <= ext_f_end(be)) { + new->be_length = be->be_f_offset - new->be_f_offset; + __ext_tree_insert(root, new, true); + } else { + struct pnfs_block_extent *split; + sector_t new_len = ext_f_end(new) - ext_f_end(be); + sector_t diff = new->be_length - new_len; + + split = kmemdup(new, sizeof(*new), GFP_ATOMIC); + if (!split) { + err = -EINVAL; + goto out; + } + + split->be_length = be->be_f_offset - split->be_f_offset; + split->be_device = nfs4_get_deviceid(new->be_device); + __ext_tree_insert(root, split, true); + + new->be_f_offset += diff; + new->be_v_offset += diff; + new->be_length = new_len; + goto retry; + } +out: + spin_unlock(&bl->bl_ext_lock); + return err; +} + +static bool +__ext_tree_lookup(struct rb_root *root, sector_t isect, + struct pnfs_block_extent *ret) +{ + struct rb_node *node; + struct pnfs_block_extent *be; + + node = root->rb_node; + while (node) { + be = ext_node(node); + if (isect < be->be_f_offset) + node = node->rb_left; + else if (isect >= ext_f_end(be)) + node = node->rb_right; + else { + *ret = *be; + return true; + } + } + + return false; +} + +bool +ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect, + struct pnfs_block_extent *ret, bool rw) +{ + bool found = false; + + spin_lock(&bl->bl_ext_lock); + if (!rw) + found = __ext_tree_lookup(&bl->bl_ext_ro, isect, ret); + if (!found) + found = __ext_tree_lookup(&bl->bl_ext_rw, isect, ret); + spin_unlock(&bl->bl_ext_lock); + + return found; +} + +int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, + sector_t start, sector_t end) +{ + int err, err2; + + spin_lock(&bl->bl_ext_lock); + err = __ext_tree_remove(&bl->bl_ext_ro, start, end); + if (rw) { + err2 = __ext_tree_remove(&bl->bl_ext_rw, start, end); + if (!err) + err = err2; + } + spin_unlock(&bl->bl_ext_lock); + + return err; +} + +static int +ext_tree_split(struct rb_root *root, struct pnfs_block_extent *be, + sector_t split) +{ + struct pnfs_block_extent *new; + sector_t orig_len = be->be_length; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + return -ENOMEM; + + be->be_length = split - be->be_f_offset; + + new->be_f_offset = split; + if (be->be_state != PNFS_BLOCK_NONE_DATA) + new->be_v_offset = be->be_v_offset + be->be_length; + new->be_length = orig_len - be->be_length; + new->be_state = be->be_state; + new->be_tag = be->be_tag; + new->be_device = nfs4_get_deviceid(be->be_device); + + __ext_tree_insert(root, new, false); + return 0; +} + +int +ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start, + sector_t len) +{ + struct rb_root *root = &bl->bl_ext_rw; + sector_t end = start + len; + struct pnfs_block_extent *be; + int err = 0; + + spin_lock(&bl->bl_ext_lock); + /* + * First remove all COW extents or holes from written to range. + */ + err = __ext_tree_remove(&bl->bl_ext_ro, start, end); + if (err) + goto out; + + /* + * Then mark all invalid extents in the range as written to. + */ + for (be = __ext_tree_search(root, start); be; be = ext_tree_next(be)) { + if (be->be_f_offset >= end) + break; + + if (be->be_state != PNFS_BLOCK_INVALID_DATA || be->be_tag) + continue; + + if (be->be_f_offset < start) { + struct pnfs_block_extent *left = ext_tree_prev(be); + + if (left && ext_can_merge(left, be)) { + sector_t diff = start - be->be_f_offset; + + left->be_length += diff; + + be->be_f_offset += diff; + be->be_v_offset += diff; + be->be_length -= diff; + } else { + err = ext_tree_split(root, be, start); + if (err) + goto out; + } + } + + if (ext_f_end(be) > end) { + struct pnfs_block_extent *right = ext_tree_next(be); + + if (right && ext_can_merge(be, right)) { + sector_t diff = end - be->be_f_offset; + + be->be_length -= diff; + + right->be_f_offset -= diff; + right->be_v_offset -= diff; + right->be_length += diff; + } else { + err = ext_tree_split(root, be, end); + if (err) + goto out; + } + } + + if (be->be_f_offset >= start && ext_f_end(be) <= end) { + be->be_tag = EXTENT_WRITTEN; + be = ext_try_to_merge_left(root, be); + be = ext_try_to_merge_right(root, be); + } + } +out: + spin_unlock(&bl->bl_ext_lock); + return err; +} + +static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg, + size_t buffer_size) +{ + if (arg->layoutupdate_pages != &arg->layoutupdate_page) { + int nr_pages = DIV_ROUND_UP(buffer_size, PAGE_SIZE), i; + + for (i = 0; i < nr_pages; i++) + put_page(arg->layoutupdate_pages[i]); + kfree(arg->layoutupdate_pages); + } else { + put_page(arg->layoutupdate_page); + } +} + +static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p, + size_t buffer_size, size_t *count) +{ + struct pnfs_block_extent *be; + int ret = 0; + + spin_lock(&bl->bl_ext_lock); + for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) { + if (be->be_state != PNFS_BLOCK_INVALID_DATA || + be->be_tag != EXTENT_WRITTEN) + continue; + + (*count)++; + if (*count * BL_EXTENT_SIZE > buffer_size) { + /* keep counting.. */ + ret = -ENOSPC; + continue; + } + + p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data, + NFS4_DEVICEID4_SIZE); + p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT); + p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT); + p = xdr_encode_hyper(p, 0LL); + *p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA); + + be->be_tag = EXTENT_COMMITTING; + } + spin_unlock(&bl->bl_ext_lock); + + return ret; +} + +int +ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout); + size_t count = 0, buffer_size = PAGE_SIZE; + __be32 *start_p; + int ret; + + dprintk("%s enter\n", __func__); + + arg->layoutupdate_page = alloc_page(GFP_NOFS); + if (!arg->layoutupdate_page) + return -ENOMEM; + start_p = page_address(arg->layoutupdate_page); + arg->layoutupdate_pages = &arg->layoutupdate_page; + +retry: + ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count); + if (unlikely(ret)) { + ext_tree_free_commitdata(arg, buffer_size); + + buffer_size = sizeof(__be32) + BL_EXTENT_SIZE * count; + count = 0; + + arg->layoutupdate_pages = + kcalloc(DIV_ROUND_UP(buffer_size, PAGE_SIZE), + sizeof(struct page *), GFP_NOFS); + if (!arg->layoutupdate_pages) + return -ENOMEM; + + start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL); + if (!start_p) { + kfree(arg->layoutupdate_pages); + return -ENOMEM; + } + + goto retry; + } + + *start_p = cpu_to_be32(count); + arg->layoutupdate_len = sizeof(__be32) + BL_EXTENT_SIZE * count; + + if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) { + __be32 *p = start_p; + int i = 0; + + for (p = start_p; + p < start_p + arg->layoutupdate_len; + p += PAGE_SIZE) { + arg->layoutupdate_pages[i++] = vmalloc_to_page(p); + } + } + + dprintk("%s found %zu ranges\n", __func__, count); + return 0; +} + +void +ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status) +{ + struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout); + struct rb_root *root = &bl->bl_ext_rw; + struct pnfs_block_extent *be; + + dprintk("%s status %d\n", __func__, status); + + ext_tree_free_commitdata(arg, arg->layoutupdate_len); + + spin_lock(&bl->bl_ext_lock); + for (be = ext_tree_first(root); be; be = ext_tree_next(be)) { + if (be->be_state != PNFS_BLOCK_INVALID_DATA || + be->be_tag != EXTENT_COMMITTING) + continue; + + if (status) { + /* + * Mark as written and try again. + * + * XXX: some real error handling here wouldn't hurt.. + */ + be->be_tag = EXTENT_WRITTEN; + } else { + be->be_state = PNFS_BLOCK_READWRITE_DATA; + be->be_tag = 0; + } + + be = ext_try_to_merge_left(root, be); + be = ext_try_to_merge_right(root, be); + } + spin_unlock(&bl->bl_ext_lock); +} diff --git a/kernel/fs/nfs/blocklayout/rpc_pipefs.c b/kernel/fs/nfs/blocklayout/rpc_pipefs.c new file mode 100644 index 000000000..dbe5839cd --- /dev/null +++ b/kernel/fs/nfs/blocklayout/rpc_pipefs.c @@ -0,0 +1,288 @@ +/* + * Copyright (c) 2006,2007 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson <andros@citi.umich.edu> + * Fred Isaman <iisaman@umich.edu> + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ + +#include <linux/module.h> +#include <linux/genhd.h> +#include <linux/blkdev.h> + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static void +nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b) +{ + int i; + + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(b->type); + *p++ = cpu_to_be32(b->simple.nr_sigs); + for (i = 0; i < b->simple.nr_sigs; i++) { + p = xdr_encode_hyper(p, b->simple.sigs[i].offset); + p = xdr_encode_opaque(p, b->simple.sigs[i].sig, + b->simple.sigs[i].sig_len); + } +} + +dev_t +bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, + gfp_t gfp_mask) +{ + struct net *net = server->nfs_client->cl_net; + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct bl_dev_msg *reply = &nn->bl_mount_reply; + struct bl_pipe_msg bl_pipe_msg; + struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; + struct bl_msg_hdr *bl_msg; + DECLARE_WAITQUEUE(wq, current); + dev_t dev = 0; + int rc; + + dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); + + mutex_lock(&nn->bl_mutex); + bl_pipe_msg.bl_wq = &nn->bl_wq; + + b->simple.len += 4; /* single volume */ + if (b->simple.len > PAGE_SIZE) + goto out_unlock; + + memset(msg, 0, sizeof(*msg)); + msg->len = sizeof(*bl_msg) + b->simple.len; + msg->data = kzalloc(msg->len, gfp_mask); + if (!msg->data) + goto out_free_data; + + bl_msg = msg->data; + bl_msg->type = BL_DEVICE_MOUNT, + bl_msg->totallen = b->simple.len; + nfs4_encode_simple(msg->data + sizeof(*bl_msg), b); + + dprintk("%s CALLING USERSPACE DAEMON\n", __func__); + add_wait_queue(&nn->bl_wq, &wq); + rc = rpc_queue_upcall(nn->bl_device_pipe, msg); + if (rc < 0) { + remove_wait_queue(&nn->bl_wq, &wq); + goto out_free_data; + } + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + remove_wait_queue(&nn->bl_wq, &wq); + + if (reply->status != BL_DEVICE_REQUEST_PROC) { + printk(KERN_WARNING "%s failed to decode device: %d\n", + __func__, reply->status); + goto out_free_data; + } + + dev = MKDEV(reply->major, reply->minor); +out_free_data: + kfree(msg->data); +out_unlock: + mutex_unlock(&nn->bl_mutex); + return dev; +} + +static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, + size_t mlen) +{ + struct nfs_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, + nfs_net_id); + + if (mlen != sizeof (struct bl_dev_msg)) + return -EINVAL; + + if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0) + return -EFAULT; + + wake_up(&nn->bl_wq); + + return mlen; +} + +static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) +{ + struct bl_pipe_msg *bl_pipe_msg = + container_of(msg, struct bl_pipe_msg, msg); + + if (msg->errno >= 0) + return; + wake_up(bl_pipe_msg->bl_wq); +} + +static const struct rpc_pipe_ops bl_upcall_ops = { + .upcall = rpc_pipe_generic_upcall, + .downcall = bl_pipe_downcall, + .destroy_msg = bl_pipe_destroy_msg, +}; + +static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb, + struct rpc_pipe *pipe) +{ + struct dentry *dir, *dentry; + + dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME); + if (dir == NULL) + return ERR_PTR(-ENOENT); + dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe); + dput(dir); + return dentry; +} + +static void nfs4blocklayout_unregister_sb(struct super_block *sb, + struct rpc_pipe *pipe) +{ + if (pipe->dentry) + rpc_unlink(pipe->dentry); +} + +static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct super_block *sb = ptr; + struct net *net = sb->s_fs_info; + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct dentry *dentry; + int ret = 0; + + if (!try_module_get(THIS_MODULE)) + return 0; + + if (nn->bl_device_pipe == NULL) { + module_put(THIS_MODULE); + return 0; + } + + switch (event) { + case RPC_PIPEFS_MOUNT: + dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe); + if (IS_ERR(dentry)) { + ret = PTR_ERR(dentry); + break; + } + nn->bl_device_pipe->dentry = dentry; + break; + case RPC_PIPEFS_UMOUNT: + if (nn->bl_device_pipe->dentry) + nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe); + break; + default: + ret = -ENOTSUPP; + break; + } + module_put(THIS_MODULE); + return ret; +} + +static struct notifier_block nfs4blocklayout_block = { + .notifier_call = rpc_pipefs_event, +}; + +static struct dentry *nfs4blocklayout_register_net(struct net *net, + struct rpc_pipe *pipe) +{ + struct super_block *pipefs_sb; + struct dentry *dentry; + + pipefs_sb = rpc_get_sb_net(net); + if (!pipefs_sb) + return NULL; + dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe); + rpc_put_sb_net(net); + return dentry; +} + +static void nfs4blocklayout_unregister_net(struct net *net, + struct rpc_pipe *pipe) +{ + struct super_block *pipefs_sb; + + pipefs_sb = rpc_get_sb_net(net); + if (pipefs_sb) { + nfs4blocklayout_unregister_sb(pipefs_sb, pipe); + rpc_put_sb_net(net); + } +} + +static int nfs4blocklayout_net_init(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct dentry *dentry; + + mutex_init(&nn->bl_mutex); + init_waitqueue_head(&nn->bl_wq); + nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); + if (IS_ERR(nn->bl_device_pipe)) + return PTR_ERR(nn->bl_device_pipe); + dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe); + if (IS_ERR(dentry)) { + rpc_destroy_pipe_data(nn->bl_device_pipe); + return PTR_ERR(dentry); + } + nn->bl_device_pipe->dentry = dentry; + return 0; +} + +static void nfs4blocklayout_net_exit(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + + nfs4blocklayout_unregister_net(net, nn->bl_device_pipe); + rpc_destroy_pipe_data(nn->bl_device_pipe); + nn->bl_device_pipe = NULL; +} + +static struct pernet_operations nfs4blocklayout_net_ops = { + .init = nfs4blocklayout_net_init, + .exit = nfs4blocklayout_net_exit, +}; + +int __init bl_init_pipefs(void) +{ + int ret; + + ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block); + if (ret) + goto out; + ret = register_pernet_subsys(&nfs4blocklayout_net_ops); + if (ret) + goto out_unregister_notifier; + return 0; + +out_unregister_notifier: + rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); +out: + return ret; +} + +void __exit bl_cleanup_pipefs(void) +{ + rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); + unregister_pernet_subsys(&nfs4blocklayout_net_ops); +} diff --git a/kernel/fs/nfs/cache_lib.c b/kernel/fs/nfs/cache_lib.c new file mode 100644 index 000000000..5f7b05372 --- /dev/null +++ b/kernel/fs/nfs/cache_lib.c @@ -0,0 +1,158 @@ +/* + * linux/fs/nfs/cache_lib.c + * + * Helper routines for the NFS client caches + * + * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/kmod.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/slab.h> +#include <linux/sunrpc/cache.h> +#include <linux/sunrpc/rpc_pipe_fs.h> +#include <net/net_namespace.h> + +#include "cache_lib.h" + +#define NFS_CACHE_UPCALL_PATHLEN 256 +#define NFS_CACHE_UPCALL_TIMEOUT 15 + +static char nfs_cache_getent_prog[NFS_CACHE_UPCALL_PATHLEN] = + "/sbin/nfs_cache_getent"; +static unsigned long nfs_cache_getent_timeout = NFS_CACHE_UPCALL_TIMEOUT; + +module_param_string(cache_getent, nfs_cache_getent_prog, + sizeof(nfs_cache_getent_prog), 0600); +MODULE_PARM_DESC(cache_getent, "Path to the client cache upcall program"); +module_param_named(cache_getent_timeout, nfs_cache_getent_timeout, ulong, 0600); +MODULE_PARM_DESC(cache_getent_timeout, "Timeout (in seconds) after which " + "the cache upcall is assumed to have failed"); + +int nfs_cache_upcall(struct cache_detail *cd, char *entry_name) +{ + static char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + char *argv[] = { + nfs_cache_getent_prog, + cd->name, + entry_name, + NULL + }; + int ret = -EACCES; + + if (nfs_cache_getent_prog[0] == '\0') + goto out; + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + /* + * Disable the upcall mechanism if we're getting an ENOENT or + * EACCES error. The admin can re-enable it on the fly by using + * sysfs to set the 'cache_getent' parameter once the problem + * has been fixed. + */ + if (ret == -ENOENT || ret == -EACCES) + nfs_cache_getent_prog[0] = '\0'; +out: + return ret > 0 ? 0 : ret; +} + +/* + * Deferred request handling + */ +void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq) +{ + if (atomic_dec_and_test(&dreq->count)) + kfree(dreq); +} + +static void nfs_dns_cache_revisit(struct cache_deferred_req *d, int toomany) +{ + struct nfs_cache_defer_req *dreq; + + dreq = container_of(d, struct nfs_cache_defer_req, deferred_req); + + complete_all(&dreq->completion); + nfs_cache_defer_req_put(dreq); +} + +static struct cache_deferred_req *nfs_dns_cache_defer(struct cache_req *req) +{ + struct nfs_cache_defer_req *dreq; + + dreq = container_of(req, struct nfs_cache_defer_req, req); + dreq->deferred_req.revisit = nfs_dns_cache_revisit; + atomic_inc(&dreq->count); + + return &dreq->deferred_req; +} + +struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void) +{ + struct nfs_cache_defer_req *dreq; + + dreq = kzalloc(sizeof(*dreq), GFP_KERNEL); + if (dreq) { + init_completion(&dreq->completion); + atomic_set(&dreq->count, 1); + dreq->req.defer = nfs_dns_cache_defer; + } + return dreq; +} + +int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq) +{ + if (wait_for_completion_timeout(&dreq->completion, + nfs_cache_getent_timeout * HZ) == 0) + return -ETIMEDOUT; + return 0; +} + +int nfs_cache_register_sb(struct super_block *sb, struct cache_detail *cd) +{ + int ret; + struct dentry *dir; + + dir = rpc_d_lookup_sb(sb, "cache"); + ret = sunrpc_cache_register_pipefs(dir, cd->name, 0600, cd); + dput(dir); + return ret; +} + +int nfs_cache_register_net(struct net *net, struct cache_detail *cd) +{ + struct super_block *pipefs_sb; + int ret = 0; + + sunrpc_init_cache_detail(cd); + pipefs_sb = rpc_get_sb_net(net); + if (pipefs_sb) { + ret = nfs_cache_register_sb(pipefs_sb, cd); + rpc_put_sb_net(net); + if (ret) + sunrpc_destroy_cache_detail(cd); + } + return ret; +} + +void nfs_cache_unregister_sb(struct super_block *sb, struct cache_detail *cd) +{ + if (cd->u.pipefs.dir) + sunrpc_cache_unregister_pipefs(cd); +} + +void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd) +{ + struct super_block *pipefs_sb; + + pipefs_sb = rpc_get_sb_net(net); + if (pipefs_sb) { + nfs_cache_unregister_sb(pipefs_sb, cd); + rpc_put_sb_net(net); + } + sunrpc_destroy_cache_detail(cd); +} diff --git a/kernel/fs/nfs/cache_lib.h b/kernel/fs/nfs/cache_lib.h new file mode 100644 index 000000000..4116d2c3f --- /dev/null +++ b/kernel/fs/nfs/cache_lib.h @@ -0,0 +1,31 @@ +/* + * Helper routines for the NFS client caches + * + * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com> + */ + +#include <linux/completion.h> +#include <linux/sunrpc/cache.h> +#include <linux/atomic.h> + +/* + * Deferred request handling + */ +struct nfs_cache_defer_req { + struct cache_req req; + struct cache_deferred_req deferred_req; + struct completion completion; + atomic_t count; +}; + +extern int nfs_cache_upcall(struct cache_detail *cd, char *entry_name); +extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void); +extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq); +extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq); + +extern int nfs_cache_register_net(struct net *net, struct cache_detail *cd); +extern void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd); +extern int nfs_cache_register_sb(struct super_block *sb, + struct cache_detail *cd); +extern void nfs_cache_unregister_sb(struct super_block *sb, + struct cache_detail *cd); diff --git a/kernel/fs/nfs/callback.c b/kernel/fs/nfs/callback.c new file mode 100644 index 000000000..8d129bb73 --- /dev/null +++ b/kernel/fs/nfs/callback.c @@ -0,0 +1,499 @@ +/* + * linux/fs/nfs/callback.c + * + * Copyright (C) 2004 Trond Myklebust + * + * NFSv4 callback handling + */ + +#include <linux/completion.h> +#include <linux/ip.h> +#include <linux/module.h> +#include <linux/sunrpc/svc.h> +#include <linux/sunrpc/svcsock.h> +#include <linux/nfs_fs.h> +#include <linux/errno.h> +#include <linux/mutex.h> +#include <linux/freezer.h> +#include <linux/kthread.h> +#include <linux/sunrpc/svcauth_gss.h> +#include <linux/sunrpc/bc_xprt.h> + +#include <net/inet_sock.h> + +#include "nfs4_fs.h" +#include "callback.h" +#include "internal.h" +#include "netns.h" + +#define NFSDBG_FACILITY NFSDBG_CALLBACK + +struct nfs_callback_data { + unsigned int users; + struct svc_serv *serv; + struct svc_rqst *rqst; + struct task_struct *task; +}; + +static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1]; +static DEFINE_MUTEX(nfs_callback_mutex); +static struct svc_program nfs4_callback_program; + +static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) +{ + int ret; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + ret = svc_create_xprt(serv, "tcp", net, PF_INET, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + if (ret <= 0) + goto out_err; + nn->nfs_callback_tcpport = ret; + dprintk("NFS: Callback listener port = %u (af %u, net %p)\n", + nn->nfs_callback_tcpport, PF_INET, net); + + ret = svc_create_xprt(serv, "tcp", net, PF_INET6, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + if (ret > 0) { + nn->nfs_callback_tcpport6 = ret; + dprintk("NFS: Callback listener port = %u (af %u, net %p)\n", + nn->nfs_callback_tcpport6, PF_INET6, net); + } else if (ret != -EAFNOSUPPORT) + goto out_err; + return 0; + +out_err: + return (ret) ? ret : -ENOMEM; +} + +/* + * This is the NFSv4 callback kernel thread. + */ +static int +nfs4_callback_svc(void *vrqstp) +{ + int err; + struct svc_rqst *rqstp = vrqstp; + + set_freezable(); + + while (!kthread_should_stop()) { + /* + * Listen for a request on the socket + */ + err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT); + if (err == -EAGAIN || err == -EINTR) + continue; + svc_process(rqstp); + } + return 0; +} + +/* + * Prepare to bring up the NFSv4 callback service + */ +static struct svc_rqst * +nfs4_callback_up(struct svc_serv *serv) +{ + return svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); +} + +#if defined(CONFIG_NFS_V4_1) +static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net) +{ + /* + * Create an svc_sock for the back channel service that shares the + * fore channel connection. + * Returns the input port (0) and sets the svc_serv bc_xprt on success + */ + return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0, + SVC_SOCK_ANONYMOUS); +} + +/* + * The callback service for NFSv4.1 callbacks + */ +static int +nfs41_callback_svc(void *vrqstp) +{ + struct svc_rqst *rqstp = vrqstp; + struct svc_serv *serv = rqstp->rq_server; + struct rpc_rqst *req; + int error; + DEFINE_WAIT(wq); + + set_freezable(); + + while (!kthread_should_stop()) { + if (try_to_freeze()) + continue; + + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + spin_lock_bh(&serv->sv_cb_lock); + if (!list_empty(&serv->sv_cb_list)) { + req = list_first_entry(&serv->sv_cb_list, + struct rpc_rqst, rq_bc_list); + list_del(&req->rq_bc_list); + spin_unlock_bh(&serv->sv_cb_lock); + finish_wait(&serv->sv_cb_waitq, &wq); + dprintk("Invoking bc_svc_process()\n"); + error = bc_svc_process(serv, req, rqstp); + dprintk("bc_svc_process() returned w/ error code= %d\n", + error); + } else { + spin_unlock_bh(&serv->sv_cb_lock); + schedule(); + finish_wait(&serv->sv_cb_waitq, &wq); + } + flush_signals(current); + } + return 0; +} + +/* + * Bring up the NFSv4.1 callback service + */ +static struct svc_rqst * +nfs41_callback_up(struct svc_serv *serv) +{ + struct svc_rqst *rqstp; + + INIT_LIST_HEAD(&serv->sv_cb_list); + spin_lock_init(&serv->sv_cb_lock); + init_waitqueue_head(&serv->sv_cb_waitq); + rqstp = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); + if (IS_ERR(rqstp)) { + svc_xprt_put(serv->sv_bc_xprt); + serv->sv_bc_xprt = NULL; + } + dprintk("--> %s return %d\n", __func__, PTR_ERR_OR_ZERO(rqstp)); + return rqstp; +} + +static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv, + struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp)) +{ + *rqstpp = nfs41_callback_up(serv); + *callback_svc = nfs41_callback_svc; +} + +static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt, + struct svc_serv *serv) +{ + if (minorversion) + /* + * Save the svc_serv in the transport so that it can + * be referenced when the session backchannel is initialized + */ + xprt->bc_serv = serv; +} +#else +static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net) +{ + return 0; +} + +static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv, + struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp)) +{ + *rqstpp = ERR_PTR(-ENOTSUPP); + *callback_svc = ERR_PTR(-ENOTSUPP); +} + +static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt, + struct svc_serv *serv) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + +static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, + struct svc_serv *serv) +{ + struct svc_rqst *rqstp; + int (*callback_svc)(void *vrqstp); + struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; + int ret; + + nfs_callback_bc_serv(minorversion, xprt, serv); + + if (cb_info->task) + return 0; + + switch (minorversion) { + case 0: + /* v4.0 callback setup */ + rqstp = nfs4_callback_up(serv); + callback_svc = nfs4_callback_svc; + break; + default: + nfs_minorversion_callback_svc_setup(serv, + &rqstp, &callback_svc); + } + + if (IS_ERR(rqstp)) + return PTR_ERR(rqstp); + + svc_sock_update_bufs(serv); + + cb_info->serv = serv; + cb_info->rqst = rqstp; + cb_info->task = kthread_create(callback_svc, cb_info->rqst, + "nfsv4.%u-svc", minorversion); + if (IS_ERR(cb_info->task)) { + ret = PTR_ERR(cb_info->task); + svc_exit_thread(cb_info->rqst); + cb_info->rqst = NULL; + cb_info->task = NULL; + return ret; + } + rqstp->rq_task = cb_info->task; + wake_up_process(cb_info->task); + dprintk("nfs_callback_up: service started\n"); + return 0; +} + +static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + + if (--nn->cb_users[minorversion]) + return; + + dprintk("NFS: destroy per-net callback data; net=%p\n", net); + svc_shutdown_net(serv, net); +} + +static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + int ret; + + if (nn->cb_users[minorversion]++) + return 0; + + dprintk("NFS: create per-net callback data; net=%p\n", net); + + ret = svc_bind(serv, net); + if (ret < 0) { + printk(KERN_WARNING "NFS: bind callback service failed\n"); + goto err_bind; + } + + switch (minorversion) { + case 0: + ret = nfs4_callback_up_net(serv, net); + break; + case 1: + case 2: + ret = nfs41_callback_up_net(serv, net); + break; + default: + printk(KERN_ERR "NFS: unknown callback version: %d\n", + minorversion); + ret = -EINVAL; + break; + } + + if (ret < 0) { + printk(KERN_ERR "NFS: callback service start failed\n"); + goto err_socks; + } + return 0; + +err_socks: + svc_rpcb_cleanup(serv, net); +err_bind: + dprintk("NFS: Couldn't create callback socket: err = %d; " + "net = %p\n", ret, net); + return ret; +} + +static struct svc_serv *nfs_callback_create_svc(int minorversion) +{ + struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; + struct svc_serv *serv; + + /* + * Check whether we're already up and running. + */ + if (cb_info->task) { + /* + * Note: increase service usage, because later in case of error + * svc_destroy() will be called. + */ + svc_get(cb_info->serv); + return cb_info->serv; + } + + /* + * Sanity check: if there's no task, + * we should be the first user ... + */ + if (cb_info->users) + printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n", + cb_info->users); + + serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL); + if (!serv) { + printk(KERN_ERR "nfs_callback_create_svc: create service failed\n"); + return ERR_PTR(-ENOMEM); + } + /* As there is only one thread we need to over-ride the + * default maximum of 80 connections + */ + serv->sv_maxconn = 1024; + dprintk("nfs_callback_create_svc: service created\n"); + return serv; +} + +/* + * Bring up the callback thread if it is not already up. + */ +int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) +{ + struct svc_serv *serv; + struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; + int ret; + struct net *net = xprt->xprt_net; + + mutex_lock(&nfs_callback_mutex); + + serv = nfs_callback_create_svc(minorversion); + if (IS_ERR(serv)) { + ret = PTR_ERR(serv); + goto err_create; + } + + ret = nfs_callback_up_net(minorversion, serv, net); + if (ret < 0) + goto err_net; + + ret = nfs_callback_start_svc(minorversion, xprt, serv); + if (ret < 0) + goto err_start; + + cb_info->users++; + /* + * svc_create creates the svc_serv with sv_nrthreads == 1, and then + * svc_prepare_thread increments that. So we need to call svc_destroy + * on both success and failure so that the refcount is 1 when the + * thread exits. + */ +err_net: + svc_destroy(serv); +err_create: + mutex_unlock(&nfs_callback_mutex); + return ret; + +err_start: + nfs_callback_down_net(minorversion, serv, net); + dprintk("NFS: Couldn't create server thread; err = %d\n", ret); + goto err_net; +} + +/* + * Kill the callback thread if it's no longer being used. + */ +void nfs_callback_down(int minorversion, struct net *net) +{ + struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; + + mutex_lock(&nfs_callback_mutex); + nfs_callback_down_net(minorversion, cb_info->serv, net); + cb_info->users--; + if (cb_info->users == 0 && cb_info->task != NULL) { + kthread_stop(cb_info->task); + dprintk("nfs_callback_down: service stopped\n"); + svc_exit_thread(cb_info->rqst); + dprintk("nfs_callback_down: service destroyed\n"); + cb_info->serv = NULL; + cb_info->rqst = NULL; + cb_info->task = NULL; + } + mutex_unlock(&nfs_callback_mutex); +} + +/* Boolean check of RPC_AUTH_GSS principal */ +int +check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp) +{ + char *p = rqstp->rq_cred.cr_principal; + + if (rqstp->rq_authop->flavour != RPC_AUTH_GSS) + return 1; + + /* No RPC_AUTH_GSS on NFSv4.1 back channel yet */ + if (clp->cl_minorversion != 0) + return 0; + /* + * It might just be a normal user principal, in which case + * userspace won't bother to tell us the name at all. + */ + if (p == NULL) + return 0; + + /* + * Did we get the acceptor from userland during the SETCLIENID + * negotiation? + */ + if (clp->cl_acceptor) + return !strcmp(p, clp->cl_acceptor); + + /* + * Otherwise try to verify it using the cl_hostname. Note that this + * doesn't work if a non-canonical hostname was used in the devname. + */ + + /* Expect a GSS_C_NT_HOSTBASED_NAME like "nfs@serverhostname" */ + + if (memcmp(p, "nfs@", 4) != 0) + return 0; + p += 4; + if (strcmp(p, clp->cl_hostname) != 0) + return 0; + return 1; +} + +/* + * pg_authenticate method for nfsv4 callback threads. + * + * The authflavor has been negotiated, so an incorrect flavor is a server + * bug. Drop packets with incorrect authflavor. + * + * All other checking done after NFS decoding where the nfs_client can be + * found in nfs4_callback_compound + */ +static int nfs_callback_authenticate(struct svc_rqst *rqstp) +{ + switch (rqstp->rq_authop->flavour) { + case RPC_AUTH_NULL: + if (rqstp->rq_proc != CB_NULL) + return SVC_DROP; + break; + case RPC_AUTH_GSS: + /* No RPC_AUTH_GSS support yet in NFSv4.1 */ + if (svc_is_backchannel(rqstp)) + return SVC_DROP; + } + return SVC_OK; +} + +/* + * Define NFS4 callback program + */ +static struct svc_version *nfs4_callback_version[] = { + [1] = &nfs4_callback_version1, + [4] = &nfs4_callback_version4, +}; + +static struct svc_stat nfs4_callback_stats; + +static struct svc_program nfs4_callback_program = { + .pg_prog = NFS4_CALLBACK, /* RPC service number */ + .pg_nvers = ARRAY_SIZE(nfs4_callback_version), /* Number of entries */ + .pg_vers = nfs4_callback_version, /* version table */ + .pg_name = "NFSv4 callback", /* service name */ + .pg_class = "nfs", /* authentication class */ + .pg_stats = &nfs4_callback_stats, + .pg_authenticate = nfs_callback_authenticate, +}; diff --git a/kernel/fs/nfs/callback.h b/kernel/fs/nfs/callback.h new file mode 100644 index 000000000..84326e9fb --- /dev/null +++ b/kernel/fs/nfs/callback.h @@ -0,0 +1,214 @@ +/* + * linux/fs/nfs/callback.h + * + * Copyright (C) 2004 Trond Myklebust + * + * NFSv4 callback definitions + */ +#ifndef __LINUX_FS_NFS_CALLBACK_H +#define __LINUX_FS_NFS_CALLBACK_H +#include <linux/sunrpc/svc.h> + +#define NFS4_CALLBACK 0x40000000 +#define NFS4_CALLBACK_XDRSIZE 2048 +#define NFS4_CALLBACK_BUFSIZE (1024 + NFS4_CALLBACK_XDRSIZE) + +enum nfs4_callback_procnum { + CB_NULL = 0, + CB_COMPOUND = 1, +}; + +enum nfs4_callback_opnum { + OP_CB_GETATTR = 3, + OP_CB_RECALL = 4, +/* Callback operations new to NFSv4.1 */ + OP_CB_LAYOUTRECALL = 5, + OP_CB_NOTIFY = 6, + OP_CB_PUSH_DELEG = 7, + OP_CB_RECALL_ANY = 8, + OP_CB_RECALLABLE_OBJ_AVAIL = 9, + OP_CB_RECALL_SLOT = 10, + OP_CB_SEQUENCE = 11, + OP_CB_WANTS_CANCELLED = 12, + OP_CB_NOTIFY_LOCK = 13, + OP_CB_NOTIFY_DEVICEID = 14, +/* Callback operations new to NFSv4.2 */ + OP_CB_OFFLOAD = 15, + OP_CB_ILLEGAL = 10044, +}; + +struct cb_process_state { + __be32 drc_status; + struct nfs_client *clp; + u32 slotid; + u32 minorversion; + struct net *net; +}; + +struct cb_compound_hdr_arg { + unsigned int taglen; + const char *tag; + unsigned int minorversion; + unsigned int cb_ident; /* v4.0 callback identifier */ + unsigned nops; +}; + +struct cb_compound_hdr_res { + __be32 *status; + unsigned int taglen; + const char *tag; + __be32 *nops; +}; + +struct cb_getattrargs { + struct sockaddr *addr; + struct nfs_fh fh; + uint32_t bitmap[2]; +}; + +struct cb_getattrres { + __be32 status; + uint32_t bitmap[2]; + uint64_t size; + uint64_t change_attr; + struct timespec ctime; + struct timespec mtime; +}; + +struct cb_recallargs { + struct sockaddr *addr; + struct nfs_fh fh; + nfs4_stateid stateid; + uint32_t truncate; +}; + +#if defined(CONFIG_NFS_V4_1) + +struct referring_call { + uint32_t rc_sequenceid; + uint32_t rc_slotid; +}; + +struct referring_call_list { + struct nfs4_sessionid rcl_sessionid; + uint32_t rcl_nrefcalls; + struct referring_call *rcl_refcalls; +}; + +struct cb_sequenceargs { + struct sockaddr *csa_addr; + struct nfs4_sessionid csa_sessionid; + uint32_t csa_sequenceid; + uint32_t csa_slotid; + uint32_t csa_highestslotid; + uint32_t csa_cachethis; + uint32_t csa_nrclists; + struct referring_call_list *csa_rclists; +}; + +struct cb_sequenceres { + __be32 csr_status; + struct nfs4_sessionid csr_sessionid; + uint32_t csr_sequenceid; + uint32_t csr_slotid; + uint32_t csr_highestslotid; + uint32_t csr_target_highestslotid; +}; + +extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, + struct cb_sequenceres *res, + struct cb_process_state *cps); + +extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, + const nfs4_stateid *stateid); + +#define RCA4_TYPE_MASK_RDATA_DLG 0 +#define RCA4_TYPE_MASK_WDATA_DLG 1 +#define RCA4_TYPE_MASK_DIR_DLG 2 +#define RCA4_TYPE_MASK_FILE_LAYOUT 3 +#define RCA4_TYPE_MASK_BLK_LAYOUT 4 +#define RCA4_TYPE_MASK_OBJ_LAYOUT_MIN 8 +#define RCA4_TYPE_MASK_OBJ_LAYOUT_MAX 9 +#define RCA4_TYPE_MASK_OTHER_LAYOUT_MIN 12 +#define RCA4_TYPE_MASK_OTHER_LAYOUT_MAX 15 +#define RCA4_TYPE_MASK_ALL 0xf31f + +struct cb_recallanyargs { + struct sockaddr *craa_addr; + uint32_t craa_objs_to_keep; + uint32_t craa_type_mask; +}; + +extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, + void *dummy, + struct cb_process_state *cps); + +struct cb_recallslotargs { + struct sockaddr *crsa_addr; + uint32_t crsa_target_highest_slotid; +}; +extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, + void *dummy, + struct cb_process_state *cps); + +struct cb_layoutrecallargs { + struct sockaddr *cbl_addr; + uint32_t cbl_recall_type; + uint32_t cbl_layout_type; + uint32_t cbl_layoutchanged; + union { + struct { + struct nfs_fh cbl_fh; + struct pnfs_layout_range cbl_range; + nfs4_stateid cbl_stateid; + }; + struct nfs_fsid cbl_fsid; + }; +}; + +extern __be32 nfs4_callback_layoutrecall( + struct cb_layoutrecallargs *args, + void *dummy, struct cb_process_state *cps); + +struct cb_devicenotifyitem { + uint32_t cbd_notify_type; + uint32_t cbd_layout_type; + struct nfs4_deviceid cbd_dev_id; + uint32_t cbd_immediate; +}; + +struct cb_devicenotifyargs { + int ndevs; + struct cb_devicenotifyitem *devs; +}; + +extern __be32 nfs4_callback_devicenotify( + struct cb_devicenotifyargs *args, + void *dummy, struct cb_process_state *cps); + +#endif /* CONFIG_NFS_V4_1 */ +extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *); +extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, + struct cb_getattrres *res, + struct cb_process_state *cps); +extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, + struct cb_process_state *cps); +#if IS_ENABLED(CONFIG_NFS_V4) +extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); +extern void nfs_callback_down(int minorversion, struct net *net); +extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, + const nfs4_stateid *stateid); +extern int nfs4_set_callback_sessionid(struct nfs_client *clp); +#endif /* CONFIG_NFS_V4 */ +/* + * nfs41: Callbacks are expected to not cause substantial latency, + * so we limit their concurrency to 1 by setting up the maximum number + * of slots for the backchannel. + */ +#define NFS41_BC_MIN_CALLBACKS 1 +#define NFS41_BC_MAX_CALLBACKS 1 + +extern unsigned int nfs_callback_set_tcpport; +extern unsigned short nfs_callback_tcpport; + +#endif /* __LINUX_FS_NFS_CALLBACK_H */ diff --git a/kernel/fs/nfs/callback_proc.c b/kernel/fs/nfs/callback_proc.c new file mode 100644 index 000000000..197806fb8 --- /dev/null +++ b/kernel/fs/nfs/callback_proc.c @@ -0,0 +1,554 @@ +/* + * linux/fs/nfs/callback_proc.c + * + * Copyright (C) 2004 Trond Myklebust + * + * NFSv4 callback procedures + */ +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/slab.h> +#include <linux/rcupdate.h> +#include "nfs4_fs.h" +#include "callback.h" +#include "delegation.h" +#include "internal.h" +#include "pnfs.h" +#include "nfs4session.h" +#include "nfs4trace.h" + +#ifdef NFS_DEBUG +#define NFSDBG_FACILITY NFSDBG_CALLBACK +#endif + +__be32 nfs4_callback_getattr(struct cb_getattrargs *args, + struct cb_getattrres *res, + struct cb_process_state *cps) +{ + struct nfs_delegation *delegation; + struct nfs_inode *nfsi; + struct inode *inode; + + res->status = htonl(NFS4ERR_OP_NOT_IN_SESSION); + if (!cps->clp) /* Always set for v4.0. Set in cb_sequence for v4.1 */ + goto out; + + res->bitmap[0] = res->bitmap[1] = 0; + res->status = htonl(NFS4ERR_BADHANDLE); + + dprintk_rcu("NFS: GETATTR callback request from %s\n", + rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR)); + + inode = nfs_delegation_find_inode(cps->clp, &args->fh); + if (inode == NULL) + goto out; + nfsi = NFS_I(inode); + rcu_read_lock(); + delegation = rcu_dereference(nfsi->delegation); + if (delegation == NULL || (delegation->type & FMODE_WRITE) == 0) + goto out_iput; + res->size = i_size_read(inode); + res->change_attr = delegation->change_attr; + if (nfsi->nrequests != 0) + res->change_attr++; + res->ctime = inode->i_ctime; + res->mtime = inode->i_mtime; + res->bitmap[0] = (FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE) & + args->bitmap[0]; + res->bitmap[1] = (FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY) & + args->bitmap[1]; + res->status = 0; +out_iput: + rcu_read_unlock(); + iput(inode); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(res->status)); + return res->status; +} + +__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, + struct cb_process_state *cps) +{ + struct inode *inode; + __be32 res; + + res = htonl(NFS4ERR_OP_NOT_IN_SESSION); + if (!cps->clp) /* Always set for v4.0. Set in cb_sequence for v4.1 */ + goto out; + + dprintk_rcu("NFS: RECALL callback request from %s\n", + rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR)); + + res = htonl(NFS4ERR_BADHANDLE); + inode = nfs_delegation_find_inode(cps->clp, &args->fh); + if (inode == NULL) + goto out; + /* Set up a helper thread to actually return the delegation */ + switch (nfs_async_inode_return_delegation(inode, &args->stateid)) { + case 0: + res = 0; + break; + case -ENOENT: + res = htonl(NFS4ERR_BAD_STATEID); + break; + default: + res = htonl(NFS4ERR_RESOURCE); + } + trace_nfs4_recall_delegation(inode, -ntohl(res)); + iput(inode); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(res)); + return res; +} + +#if defined(CONFIG_NFS_V4_1) + +/* + * Lookup a layout by filehandle. + * + * Note: gets a refcount on the layout hdr and on its respective inode. + * Caller must put the layout hdr and the inode. + * + * TODO: keep track of all layouts (and delegations) in a hash table + * hashed by filehandle. + */ +static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp, + struct nfs_fh *fh, nfs4_stateid *stateid) +{ + struct nfs_server *server; + struct inode *ino; + struct pnfs_layout_hdr *lo; + + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + list_for_each_entry(lo, &server->layouts, plh_layouts) { + if (!nfs4_stateid_match_other(&lo->plh_stateid, stateid)) + continue; + if (nfs_compare_fh(fh, &NFS_I(lo->plh_inode)->fh)) + continue; + ino = igrab(lo->plh_inode); + if (!ino) + break; + spin_lock(&ino->i_lock); + /* Is this layout in the process of being freed? */ + if (NFS_I(ino)->layout != lo) { + spin_unlock(&ino->i_lock); + iput(ino); + break; + } + pnfs_get_layout_hdr(lo); + spin_unlock(&ino->i_lock); + return lo; + } + } + + return NULL; +} + +static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, + struct nfs_fh *fh, nfs4_stateid *stateid) +{ + struct pnfs_layout_hdr *lo; + + spin_lock(&clp->cl_lock); + rcu_read_lock(); + lo = get_layout_by_fh_locked(clp, fh, stateid); + rcu_read_unlock(); + spin_unlock(&clp->cl_lock); + + return lo; +} + +static u32 initiate_file_draining(struct nfs_client *clp, + struct cb_layoutrecallargs *args) +{ + struct inode *ino; + struct pnfs_layout_hdr *lo; + u32 rv = NFS4ERR_NOMATCHING_LAYOUT; + LIST_HEAD(free_me_list); + + lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid); + if (!lo) + goto out; + + ino = lo->plh_inode; + + spin_lock(&ino->i_lock); + pnfs_set_layout_stateid(lo, &args->cbl_stateid, true); + spin_unlock(&ino->i_lock); + + pnfs_layoutcommit_inode(ino, false); + + spin_lock(&ino->i_lock); + if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || + pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, + &args->cbl_range)) { + rv = NFS4ERR_DELAY; + goto unlock; + } + + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { + NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, + &args->cbl_range); + } +unlock: + spin_unlock(&ino->i_lock); + pnfs_free_lseg_list(&free_me_list); + pnfs_put_layout_hdr(lo); + iput(ino); +out: + return rv; +} + +static u32 initiate_bulk_draining(struct nfs_client *clp, + struct cb_layoutrecallargs *args) +{ + int stat; + + if (args->cbl_recall_type == RETURN_FSID) + stat = pnfs_destroy_layouts_byfsid(clp, &args->cbl_fsid, true); + else + stat = pnfs_destroy_layouts_byclid(clp, true); + if (stat != 0) + return NFS4ERR_DELAY; + return NFS4ERR_NOMATCHING_LAYOUT; +} + +static u32 do_callback_layoutrecall(struct nfs_client *clp, + struct cb_layoutrecallargs *args) +{ + u32 res; + + dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type); + if (args->cbl_recall_type == RETURN_FILE) + res = initiate_file_draining(clp, args); + else + res = initiate_bulk_draining(clp, args); + dprintk("%s returning %i\n", __func__, res); + return res; + +} + +__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args, + void *dummy, struct cb_process_state *cps) +{ + u32 res; + + dprintk("%s: -->\n", __func__); + + if (cps->clp) + res = do_callback_layoutrecall(cps->clp, args); + else + res = NFS4ERR_OP_NOT_IN_SESSION; + + dprintk("%s: exit with status = %d\n", __func__, res); + return cpu_to_be32(res); +} + +static void pnfs_recall_all_layouts(struct nfs_client *clp) +{ + struct cb_layoutrecallargs args; + + /* Pretend we got a CB_LAYOUTRECALL(ALL) */ + memset(&args, 0, sizeof(args)); + args.cbl_recall_type = RETURN_ALL; + /* FIXME we ignore errors, what should we do? */ + do_callback_layoutrecall(clp, &args); +} + +__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args, + void *dummy, struct cb_process_state *cps) +{ + int i; + __be32 res = 0; + struct nfs_client *clp = cps->clp; + struct nfs_server *server = NULL; + + dprintk("%s: -->\n", __func__); + + if (!clp) { + res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION); + goto out; + } + + for (i = 0; i < args->ndevs; i++) { + struct cb_devicenotifyitem *dev = &args->devs[i]; + + if (!server || + server->pnfs_curr_ld->id != dev->cbd_layout_type) { + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + if (server->pnfs_curr_ld && + server->pnfs_curr_ld->id == dev->cbd_layout_type) { + rcu_read_unlock(); + goto found; + } + rcu_read_unlock(); + dprintk("%s: layout type %u not found\n", + __func__, dev->cbd_layout_type); + continue; + } + + found: + nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id); + } + +out: + kfree(args->devs); + dprintk("%s: exit with status = %u\n", + __func__, be32_to_cpu(res)); + return res; +} + +/* + * Validate the sequenceID sent by the server. + * Return success if the sequenceID is one more than what we last saw on + * this slot, accounting for wraparound. Increments the slot's sequence. + * + * We don't yet implement a duplicate request cache, instead we set the + * back channel ca_maxresponsesize_cached to zero. This is OK for now + * since we only currently implement idempotent callbacks anyway. + * + * We have a single slot backchannel at this time, so we don't bother + * checking the used_slots bit array on the table. The lower layer guarantees + * a single outstanding callback request at a time. + */ +static __be32 +validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args) +{ + struct nfs4_slot *slot; + + dprintk("%s enter. slotid %u seqid %u\n", + __func__, args->csa_slotid, args->csa_sequenceid); + + if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS) + return htonl(NFS4ERR_BADSLOT); + + slot = tbl->slots + args->csa_slotid; + dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr); + + /* Normal */ + if (likely(args->csa_sequenceid == slot->seq_nr + 1)) { + slot->seq_nr++; + goto out_ok; + } + + /* Replay */ + if (args->csa_sequenceid == slot->seq_nr) { + dprintk("%s seqid %u is a replay\n", + __func__, args->csa_sequenceid); + /* Signal process_op to set this error on next op */ + if (args->csa_cachethis == 0) + return htonl(NFS4ERR_RETRY_UNCACHED_REP); + + /* The ca_maxresponsesize_cached is 0 with no DRC */ + else if (args->csa_cachethis == 1) + return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE); + } + + /* Wraparound */ + if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) { + slot->seq_nr = 1; + goto out_ok; + } + + /* Misordered request */ + return htonl(NFS4ERR_SEQ_MISORDERED); +out_ok: + tbl->highest_used_slotid = args->csa_slotid; + return htonl(NFS4_OK); +} + +/* + * For each referring call triple, check the session's slot table for + * a match. If the slot is in use and the sequence numbers match, the + * client is still waiting for a response to the original request. + */ +static bool referring_call_exists(struct nfs_client *clp, + uint32_t nrclists, + struct referring_call_list *rclists) +{ + bool status = 0; + int i, j; + struct nfs4_session *session; + struct nfs4_slot_table *tbl; + struct referring_call_list *rclist; + struct referring_call *ref; + + /* + * XXX When client trunking is implemented, this becomes + * a session lookup from within the loop + */ + session = clp->cl_session; + tbl = &session->fc_slot_table; + + for (i = 0; i < nrclists; i++) { + rclist = &rclists[i]; + if (memcmp(session->sess_id.data, + rclist->rcl_sessionid.data, + NFS4_MAX_SESSIONID_LEN) != 0) + continue; + + for (j = 0; j < rclist->rcl_nrefcalls; j++) { + ref = &rclist->rcl_refcalls[j]; + + dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u " + "slotid %u\n", __func__, + ((u32 *)&rclist->rcl_sessionid.data)[0], + ((u32 *)&rclist->rcl_sessionid.data)[1], + ((u32 *)&rclist->rcl_sessionid.data)[2], + ((u32 *)&rclist->rcl_sessionid.data)[3], + ref->rc_sequenceid, ref->rc_slotid); + + spin_lock(&tbl->slot_tbl_lock); + status = (test_bit(ref->rc_slotid, tbl->used_slots) && + tbl->slots[ref->rc_slotid].seq_nr == + ref->rc_sequenceid); + spin_unlock(&tbl->slot_tbl_lock); + if (status) + goto out; + } + } + +out: + return status; +} + +__be32 nfs4_callback_sequence(struct cb_sequenceargs *args, + struct cb_sequenceres *res, + struct cb_process_state *cps) +{ + struct nfs4_slot_table *tbl; + struct nfs_client *clp; + int i; + __be32 status = htonl(NFS4ERR_BADSESSION); + + clp = nfs4_find_client_sessionid(cps->net, args->csa_addr, + &args->csa_sessionid, cps->minorversion); + if (clp == NULL) + goto out; + + if (!(clp->cl_session->flags & SESSION4_BACK_CHAN)) + goto out; + tbl = &clp->cl_session->bc_slot_table; + + spin_lock(&tbl->slot_tbl_lock); + /* state manager is resetting the session */ + if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) { + spin_unlock(&tbl->slot_tbl_lock); + status = htonl(NFS4ERR_DELAY); + /* Return NFS4ERR_BADSESSION if we're draining the session + * in order to reset it. + */ + if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) + status = htonl(NFS4ERR_BADSESSION); + goto out; + } + + status = validate_seqid(&clp->cl_session->bc_slot_table, args); + spin_unlock(&tbl->slot_tbl_lock); + if (status) + goto out; + + cps->slotid = args->csa_slotid; + + /* + * Check for pending referring calls. If a match is found, a + * related callback was received before the response to the original + * call. + */ + if (referring_call_exists(clp, args->csa_nrclists, args->csa_rclists)) { + status = htonl(NFS4ERR_DELAY); + goto out; + } + + memcpy(&res->csr_sessionid, &args->csa_sessionid, + sizeof(res->csr_sessionid)); + res->csr_sequenceid = args->csa_sequenceid; + res->csr_slotid = args->csa_slotid; + res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1; + res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1; + +out: + cps->clp = clp; /* put in nfs4_callback_compound */ + for (i = 0; i < args->csa_nrclists; i++) + kfree(args->csa_rclists[i].rcl_refcalls); + kfree(args->csa_rclists); + + if (status == htonl(NFS4ERR_RETRY_UNCACHED_REP)) { + cps->drc_status = status; + status = 0; + } else + res->csr_status = status; + + trace_nfs4_cb_sequence(args, res, status); + dprintk("%s: exit with status = %d res->csr_status %d\n", __func__, + ntohl(status), ntohl(res->csr_status)); + return status; +} + +static bool +validate_bitmap_values(unsigned long mask) +{ + return (mask & ~RCA4_TYPE_MASK_ALL) == 0; +} + +__be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy, + struct cb_process_state *cps) +{ + __be32 status; + fmode_t flags = 0; + + status = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION); + if (!cps->clp) /* set in cb_sequence */ + goto out; + + dprintk_rcu("NFS: RECALL_ANY callback request from %s\n", + rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR)); + + status = cpu_to_be32(NFS4ERR_INVAL); + if (!validate_bitmap_values(args->craa_type_mask)) + goto out; + + status = cpu_to_be32(NFS4_OK); + if (test_bit(RCA4_TYPE_MASK_RDATA_DLG, (const unsigned long *) + &args->craa_type_mask)) + flags = FMODE_READ; + if (test_bit(RCA4_TYPE_MASK_WDATA_DLG, (const unsigned long *) + &args->craa_type_mask)) + flags |= FMODE_WRITE; + if (test_bit(RCA4_TYPE_MASK_FILE_LAYOUT, (const unsigned long *) + &args->craa_type_mask)) + pnfs_recall_all_layouts(cps->clp); + if (flags) + nfs_expire_unused_delegation_types(cps->clp, flags); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} + +/* Reduce the fore channel's max_slots to the target value */ +__be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy, + struct cb_process_state *cps) +{ + struct nfs4_slot_table *fc_tbl; + __be32 status; + + status = htonl(NFS4ERR_OP_NOT_IN_SESSION); + if (!cps->clp) /* set in cb_sequence */ + goto out; + + dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target highest slotid %u\n", + rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR), + args->crsa_target_highest_slotid); + + fc_tbl = &cps->clp->cl_session->fc_slot_table; + + status = htonl(NFS4_OK); + + nfs41_set_target_slotid(fc_tbl, args->crsa_target_highest_slotid); + nfs41_server_notify_target_slotid_update(cps->clp); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} +#endif /* CONFIG_NFS_V4_1 */ diff --git a/kernel/fs/nfs/callback_xdr.c b/kernel/fs/nfs/callback_xdr.c new file mode 100644 index 000000000..19ca95cdf --- /dev/null +++ b/kernel/fs/nfs/callback_xdr.c @@ -0,0 +1,1033 @@ +/* + * linux/fs/nfs/callback_xdr.c + * + * Copyright (C) 2004 Trond Myklebust + * + * NFSv4 callback encode/decode procedures + */ +#include <linux/kernel.h> +#include <linux/sunrpc/svc.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/ratelimit.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/sunrpc/bc_xprt.h> +#include "nfs4_fs.h" +#include "callback.h" +#include "internal.h" +#include "nfs4session.h" + +#define CB_OP_TAGLEN_MAXSZ (512) +#define CB_OP_HDR_RES_MAXSZ (2 + CB_OP_TAGLEN_MAXSZ) +#define CB_OP_GETATTR_BITMAP_MAXSZ (4) +#define CB_OP_GETATTR_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ + CB_OP_GETATTR_BITMAP_MAXSZ + \ + 2 + 2 + 3 + 3) +#define CB_OP_RECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) + +#if defined(CONFIG_NFS_V4_1) +#define CB_OP_LAYOUTRECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) +#define CB_OP_DEVICENOTIFY_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) +#define CB_OP_SEQUENCE_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ + 4 + 1 + 3) +#define CB_OP_RECALLANY_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) +#define CB_OP_RECALLSLOT_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) +#endif /* CONFIG_NFS_V4_1 */ + +#define NFSDBG_FACILITY NFSDBG_CALLBACK + +/* Internal error code */ +#define NFS4ERR_RESOURCE_HDR 11050 + +typedef __be32 (*callback_process_op_t)(void *, void *, + struct cb_process_state *); +typedef __be32 (*callback_decode_arg_t)(struct svc_rqst *, struct xdr_stream *, void *); +typedef __be32 (*callback_encode_res_t)(struct svc_rqst *, struct xdr_stream *, void *); + + +struct callback_op { + callback_process_op_t process_op; + callback_decode_arg_t decode_args; + callback_encode_res_t encode_res; + long res_maxsize; +}; + +static struct callback_op callback_ops[]; + +static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp) +{ + return htonl(NFS4_OK); +} + +static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +{ + return xdr_argsize_check(rqstp, p); +} + +static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +{ + return xdr_ressize_check(rqstp, p); +} + +static __be32 *read_buf(struct xdr_stream *xdr, int nbytes) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, nbytes); + if (unlikely(p == NULL)) + printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n"); + return p; +} + +static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len, const char **str) +{ + __be32 *p; + + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + *len = ntohl(*p); + + if (*len != 0) { + p = read_buf(xdr, *len); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + *str = (const char *)p; + } else + *str = NULL; + + return 0; +} + +static __be32 decode_fh(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + fh->size = ntohl(*p); + if (fh->size > NFS4_FHSIZE) + return htonl(NFS4ERR_BADHANDLE); + p = read_buf(xdr, fh->size); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + memcpy(&fh->data[0], p, fh->size); + memset(&fh->data[fh->size], 0, sizeof(fh->data) - fh->size); + return 0; +} + +static __be32 decode_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) +{ + __be32 *p; + unsigned int attrlen; + + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + attrlen = ntohl(*p); + p = read_buf(xdr, attrlen << 2); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + if (likely(attrlen > 0)) + bitmap[0] = ntohl(*p++); + if (attrlen > 1) + bitmap[1] = ntohl(*p); + return 0; +} + +static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + __be32 *p; + + p = read_buf(xdr, NFS4_STATEID_SIZE); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + memcpy(stateid, p, NFS4_STATEID_SIZE); + return 0; +} + +static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound_hdr_arg *hdr) +{ + __be32 *p; + __be32 status; + + status = decode_string(xdr, &hdr->taglen, &hdr->tag); + if (unlikely(status != 0)) + return status; + /* We do not like overly long tags! */ + if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) { + printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n", + __func__, hdr->taglen); + return htonl(NFS4ERR_RESOURCE); + } + p = read_buf(xdr, 12); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + hdr->minorversion = ntohl(*p++); + /* Check for minor version support */ + if (hdr->minorversion <= NFS4_MAX_MINOR_VERSION) { + hdr->cb_ident = ntohl(*p++); /* ignored by v4.1 and v4.2 */ + } else { + pr_warn_ratelimited("NFS: %s: NFSv4 server callback with " + "illegal minor version %u!\n", + __func__, hdr->minorversion); + return htonl(NFS4ERR_MINOR_VERS_MISMATCH); + } + hdr->nops = ntohl(*p); + dprintk("%s: minorversion %d nops %d\n", __func__, + hdr->minorversion, hdr->nops); + return 0; +} + +static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op) +{ + __be32 *p; + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE_HDR); + *op = ntohl(*p); + return 0; +} + +static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_getattrargs *args) +{ + __be32 status; + + status = decode_fh(xdr, &args->fh); + if (unlikely(status != 0)) + goto out; + args->addr = svc_addr(rqstp); + status = decode_bitmap(xdr, args->bitmap); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} + +static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallargs *args) +{ + __be32 *p; + __be32 status; + + args->addr = svc_addr(rqstp); + status = decode_stateid(xdr, &args->stateid); + if (unlikely(status != 0)) + goto out; + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_RESOURCE); + goto out; + } + args->truncate = ntohl(*p); + status = decode_fh(xdr, &args->fh); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} + +#if defined(CONFIG_NFS_V4_1) + +static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct cb_layoutrecallargs *args) +{ + __be32 *p; + __be32 status = 0; + uint32_t iomode; + + args->cbl_addr = svc_addr(rqstp); + p = read_buf(xdr, 4 * sizeof(uint32_t)); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_BADXDR); + goto out; + } + + args->cbl_layout_type = ntohl(*p++); + /* Depite the spec's xdr, iomode really belongs in the FILE switch, + * as it is unusable and ignored with the other types. + */ + iomode = ntohl(*p++); + args->cbl_layoutchanged = ntohl(*p++); + args->cbl_recall_type = ntohl(*p++); + + if (args->cbl_recall_type == RETURN_FILE) { + args->cbl_range.iomode = iomode; + status = decode_fh(xdr, &args->cbl_fh); + if (unlikely(status != 0)) + goto out; + + p = read_buf(xdr, 2 * sizeof(uint64_t)); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_BADXDR); + goto out; + } + p = xdr_decode_hyper(p, &args->cbl_range.offset); + p = xdr_decode_hyper(p, &args->cbl_range.length); + status = decode_stateid(xdr, &args->cbl_stateid); + if (unlikely(status != 0)) + goto out; + } else if (args->cbl_recall_type == RETURN_FSID) { + p = read_buf(xdr, 2 * sizeof(uint64_t)); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_BADXDR); + goto out; + } + p = xdr_decode_hyper(p, &args->cbl_fsid.major); + p = xdr_decode_hyper(p, &args->cbl_fsid.minor); + } else if (args->cbl_recall_type != RETURN_ALL) { + status = htonl(NFS4ERR_BADXDR); + goto out; + } + dprintk("%s: ltype 0x%x iomode %d changed %d recall_type %d\n", + __func__, + args->cbl_layout_type, iomode, + args->cbl_layoutchanged, args->cbl_recall_type); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} + +static +__be32 decode_devicenotify_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct cb_devicenotifyargs *args) +{ + __be32 *p; + __be32 status = 0; + u32 tmp; + int n, i; + args->ndevs = 0; + + /* Num of device notifications */ + p = read_buf(xdr, sizeof(uint32_t)); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_BADXDR); + goto out; + } + n = ntohl(*p++); + if (n <= 0) + goto out; + if (n > ULONG_MAX / sizeof(*args->devs)) { + status = htonl(NFS4ERR_BADXDR); + goto out; + } + + args->devs = kmalloc_array(n, sizeof(*args->devs), GFP_KERNEL); + if (!args->devs) { + status = htonl(NFS4ERR_DELAY); + goto out; + } + + /* Decode each dev notification */ + for (i = 0; i < n; i++) { + struct cb_devicenotifyitem *dev = &args->devs[i]; + + p = read_buf(xdr, (4 * sizeof(uint32_t)) + NFS4_DEVICEID4_SIZE); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_BADXDR); + goto err; + } + + tmp = ntohl(*p++); /* bitmap size */ + if (tmp != 1) { + status = htonl(NFS4ERR_INVAL); + goto err; + } + dev->cbd_notify_type = ntohl(*p++); + if (dev->cbd_notify_type != NOTIFY_DEVICEID4_CHANGE && + dev->cbd_notify_type != NOTIFY_DEVICEID4_DELETE) { + status = htonl(NFS4ERR_INVAL); + goto err; + } + + tmp = ntohl(*p++); /* opaque size */ + if (((dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE) && + (tmp != NFS4_DEVICEID4_SIZE + 8)) || + ((dev->cbd_notify_type == NOTIFY_DEVICEID4_DELETE) && + (tmp != NFS4_DEVICEID4_SIZE + 4))) { + status = htonl(NFS4ERR_INVAL); + goto err; + } + dev->cbd_layout_type = ntohl(*p++); + memcpy(dev->cbd_dev_id.data, p, NFS4_DEVICEID4_SIZE); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + + if (dev->cbd_layout_type == NOTIFY_DEVICEID4_CHANGE) { + p = read_buf(xdr, sizeof(uint32_t)); + if (unlikely(p == NULL)) { + status = htonl(NFS4ERR_BADXDR); + goto err; + } + dev->cbd_immediate = ntohl(*p++); + } else { + dev->cbd_immediate = 0; + } + + args->ndevs++; + + dprintk("%s: type %d layout 0x%x immediate %d\n", + __func__, dev->cbd_notify_type, dev->cbd_layout_type, + dev->cbd_immediate); + } +out: + dprintk("%s: status %d ndevs %d\n", + __func__, ntohl(status), args->ndevs); + return status; +err: + kfree(args->devs); + goto out; +} + +static __be32 decode_sessionid(struct xdr_stream *xdr, + struct nfs4_sessionid *sid) +{ + __be32 *p; + int len = NFS4_MAX_SESSIONID_LEN; + + p = read_buf(xdr, len); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + + memcpy(sid->data, p, len); + return 0; +} + +static __be32 decode_rc_list(struct xdr_stream *xdr, + struct referring_call_list *rc_list) +{ + __be32 *p; + int i; + __be32 status; + + status = decode_sessionid(xdr, &rc_list->rcl_sessionid); + if (status) + goto out; + + status = htonl(NFS4ERR_RESOURCE); + p = read_buf(xdr, sizeof(uint32_t)); + if (unlikely(p == NULL)) + goto out; + + rc_list->rcl_nrefcalls = ntohl(*p++); + if (rc_list->rcl_nrefcalls) { + p = read_buf(xdr, + rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t)); + if (unlikely(p == NULL)) + goto out; + rc_list->rcl_refcalls = kmalloc_array(rc_list->rcl_nrefcalls, + sizeof(*rc_list->rcl_refcalls), + GFP_KERNEL); + if (unlikely(rc_list->rcl_refcalls == NULL)) + goto out; + for (i = 0; i < rc_list->rcl_nrefcalls; i++) { + rc_list->rcl_refcalls[i].rc_sequenceid = ntohl(*p++); + rc_list->rcl_refcalls[i].rc_slotid = ntohl(*p++); + } + } + status = 0; + +out: + return status; +} + +static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct cb_sequenceargs *args) +{ + __be32 *p; + int i; + __be32 status; + + status = decode_sessionid(xdr, &args->csa_sessionid); + if (status) + goto out; + + status = htonl(NFS4ERR_RESOURCE); + p = read_buf(xdr, 5 * sizeof(uint32_t)); + if (unlikely(p == NULL)) + goto out; + + args->csa_addr = svc_addr(rqstp); + args->csa_sequenceid = ntohl(*p++); + args->csa_slotid = ntohl(*p++); + args->csa_highestslotid = ntohl(*p++); + args->csa_cachethis = ntohl(*p++); + args->csa_nrclists = ntohl(*p++); + args->csa_rclists = NULL; + if (args->csa_nrclists) { + args->csa_rclists = kmalloc_array(args->csa_nrclists, + sizeof(*args->csa_rclists), + GFP_KERNEL); + if (unlikely(args->csa_rclists == NULL)) + goto out; + + for (i = 0; i < args->csa_nrclists; i++) { + status = decode_rc_list(xdr, &args->csa_rclists[i]); + if (status) { + args->csa_nrclists = i; + goto out_free; + } + } + } + status = 0; + + dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u slotid %u " + "highestslotid %u cachethis %d nrclists %u\n", + __func__, + ((u32 *)&args->csa_sessionid)[0], + ((u32 *)&args->csa_sessionid)[1], + ((u32 *)&args->csa_sessionid)[2], + ((u32 *)&args->csa_sessionid)[3], + args->csa_sequenceid, args->csa_slotid, + args->csa_highestslotid, args->csa_cachethis, + args->csa_nrclists); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; + +out_free: + for (i = 0; i < args->csa_nrclists; i++) + kfree(args->csa_rclists[i].rcl_refcalls); + kfree(args->csa_rclists); + goto out; +} + +static __be32 decode_recallany_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct cb_recallanyargs *args) +{ + uint32_t bitmap[2]; + __be32 *p, status; + + args->craa_addr = svc_addr(rqstp); + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_BADXDR); + args->craa_objs_to_keep = ntohl(*p++); + status = decode_bitmap(xdr, bitmap); + if (unlikely(status)) + return status; + args->craa_type_mask = bitmap[0]; + + return 0; +} + +static __be32 decode_recallslot_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct cb_recallslotargs *args) +{ + __be32 *p; + + args->crsa_addr = svc_addr(rqstp); + p = read_buf(xdr, 4); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_BADXDR); + args->crsa_target_highest_slotid = ntohl(*p++); + return 0; +} + +#endif /* CONFIG_NFS_V4_1 */ + +static __be32 encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4 + len); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + xdr_encode_opaque(p, str, len); + return 0; +} + +#define CB_SUPPORTED_ATTR0 (FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE) +#define CB_SUPPORTED_ATTR1 (FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY) +static __be32 encode_attr_bitmap(struct xdr_stream *xdr, const uint32_t *bitmap, __be32 **savep) +{ + __be32 bm[2]; + __be32 *p; + + bm[0] = htonl(bitmap[0] & CB_SUPPORTED_ATTR0); + bm[1] = htonl(bitmap[1] & CB_SUPPORTED_ATTR1); + if (bm[1] != 0) { + p = xdr_reserve_space(xdr, 16); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + *p++ = htonl(2); + *p++ = bm[0]; + *p++ = bm[1]; + } else if (bm[0] != 0) { + p = xdr_reserve_space(xdr, 12); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + *p++ = htonl(1); + *p++ = bm[0]; + } else { + p = xdr_reserve_space(xdr, 8); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + *p++ = htonl(0); + } + *savep = p; + return 0; +} + +static __be32 encode_attr_change(struct xdr_stream *xdr, const uint32_t *bitmap, uint64_t change) +{ + __be32 *p; + + if (!(bitmap[0] & FATTR4_WORD0_CHANGE)) + return 0; + p = xdr_reserve_space(xdr, 8); + if (unlikely(!p)) + return htonl(NFS4ERR_RESOURCE); + p = xdr_encode_hyper(p, change); + return 0; +} + +static __be32 encode_attr_size(struct xdr_stream *xdr, const uint32_t *bitmap, uint64_t size) +{ + __be32 *p; + + if (!(bitmap[0] & FATTR4_WORD0_SIZE)) + return 0; + p = xdr_reserve_space(xdr, 8); + if (unlikely(!p)) + return htonl(NFS4ERR_RESOURCE); + p = xdr_encode_hyper(p, size); + return 0; +} + +static __be32 encode_attr_time(struct xdr_stream *xdr, const struct timespec *time) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 12); + if (unlikely(!p)) + return htonl(NFS4ERR_RESOURCE); + p = xdr_encode_hyper(p, time->tv_sec); + *p = htonl(time->tv_nsec); + return 0; +} + +static __be32 encode_attr_ctime(struct xdr_stream *xdr, const uint32_t *bitmap, const struct timespec *time) +{ + if (!(bitmap[1] & FATTR4_WORD1_TIME_METADATA)) + return 0; + return encode_attr_time(xdr,time); +} + +static __be32 encode_attr_mtime(struct xdr_stream *xdr, const uint32_t *bitmap, const struct timespec *time) +{ + if (!(bitmap[1] & FATTR4_WORD1_TIME_MODIFY)) + return 0; + return encode_attr_time(xdr,time); +} + +static __be32 encode_compound_hdr_res(struct xdr_stream *xdr, struct cb_compound_hdr_res *hdr) +{ + __be32 status; + + hdr->status = xdr_reserve_space(xdr, 4); + if (unlikely(hdr->status == NULL)) + return htonl(NFS4ERR_RESOURCE); + status = encode_string(xdr, hdr->taglen, hdr->tag); + if (unlikely(status != 0)) + return status; + hdr->nops = xdr_reserve_space(xdr, 4); + if (unlikely(hdr->nops == NULL)) + return htonl(NFS4ERR_RESOURCE); + return 0; +} + +static __be32 encode_op_hdr(struct xdr_stream *xdr, uint32_t op, __be32 res) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 8); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE_HDR); + *p++ = htonl(op); + *p = res; + return 0; +} + +static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, const struct cb_getattrres *res) +{ + __be32 *savep = NULL; + __be32 status = res->status; + + if (unlikely(status != 0)) + goto out; + status = encode_attr_bitmap(xdr, res->bitmap, &savep); + if (unlikely(status != 0)) + goto out; + status = encode_attr_change(xdr, res->bitmap, res->change_attr); + if (unlikely(status != 0)) + goto out; + status = encode_attr_size(xdr, res->bitmap, res->size); + if (unlikely(status != 0)) + goto out; + status = encode_attr_ctime(xdr, res->bitmap, &res->ctime); + if (unlikely(status != 0)) + goto out; + status = encode_attr_mtime(xdr, res->bitmap, &res->mtime); + *savep = htonl((unsigned int)((char *)xdr->p - (char *)(savep+1))); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} + +#if defined(CONFIG_NFS_V4_1) + +static __be32 encode_sessionid(struct xdr_stream *xdr, + const struct nfs4_sessionid *sid) +{ + __be32 *p; + int len = NFS4_MAX_SESSIONID_LEN; + + p = xdr_reserve_space(xdr, len); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + + memcpy(p, sid, len); + return 0; +} + +static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + const struct cb_sequenceres *res) +{ + __be32 *p; + __be32 status = res->csr_status; + + if (unlikely(status != 0)) + goto out; + + encode_sessionid(xdr, &res->csr_sessionid); + + p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t)); + if (unlikely(p == NULL)) + return htonl(NFS4ERR_RESOURCE); + + *p++ = htonl(res->csr_sequenceid); + *p++ = htonl(res->csr_slotid); + *p++ = htonl(res->csr_highestslotid); + *p++ = htonl(res->csr_target_highestslotid); +out: + dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); + return status; +} + +static __be32 +preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op) +{ + if (op_nr == OP_CB_SEQUENCE) { + if (nop != 0) + return htonl(NFS4ERR_SEQUENCE_POS); + } else { + if (nop == 0) + return htonl(NFS4ERR_OP_NOT_IN_SESSION); + } + + switch (op_nr) { + case OP_CB_GETATTR: + case OP_CB_RECALL: + case OP_CB_SEQUENCE: + case OP_CB_RECALL_ANY: + case OP_CB_RECALL_SLOT: + case OP_CB_LAYOUTRECALL: + case OP_CB_NOTIFY_DEVICEID: + *op = &callback_ops[op_nr]; + break; + + case OP_CB_NOTIFY: + case OP_CB_PUSH_DELEG: + case OP_CB_RECALLABLE_OBJ_AVAIL: + case OP_CB_WANTS_CANCELLED: + case OP_CB_NOTIFY_LOCK: + return htonl(NFS4ERR_NOTSUPP); + + default: + return htonl(NFS4ERR_OP_ILLEGAL); + } + + return htonl(NFS_OK); +} + +static void nfs4_callback_free_slot(struct nfs4_session *session) +{ + struct nfs4_slot_table *tbl = &session->bc_slot_table; + + spin_lock(&tbl->slot_tbl_lock); + /* + * Let the state manager know callback processing done. + * A single slot, so highest used slotid is either 0 or -1 + */ + tbl->highest_used_slotid = NFS4_NO_SLOT; + nfs4_slot_tbl_drain_complete(tbl); + spin_unlock(&tbl->slot_tbl_lock); +} + +static void nfs4_cb_free_slot(struct cb_process_state *cps) +{ + if (cps->slotid != NFS4_NO_SLOT) + nfs4_callback_free_slot(cps->clp->cl_session); +} + +#else /* CONFIG_NFS_V4_1 */ + +static __be32 +preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op) +{ + return htonl(NFS4ERR_MINOR_VERS_MISMATCH); +} + +static void nfs4_cb_free_slot(struct cb_process_state *cps) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + +#ifdef CONFIG_NFS_V4_2 +static __be32 +preprocess_nfs42_op(int nop, unsigned int op_nr, struct callback_op **op) +{ + __be32 status = preprocess_nfs41_op(nop, op_nr, op); + if (status != htonl(NFS4ERR_OP_ILLEGAL)) + return status; + + if (op_nr == OP_CB_OFFLOAD) + return htonl(NFS4ERR_NOTSUPP); + return htonl(NFS4ERR_OP_ILLEGAL); +} +#else /* CONFIG_NFS_V4_2 */ +static __be32 +preprocess_nfs42_op(int nop, unsigned int op_nr, struct callback_op **op) +{ + return htonl(NFS4ERR_MINOR_VERS_MISMATCH); +} +#endif /* CONFIG_NFS_V4_2 */ + +static __be32 +preprocess_nfs4_op(unsigned int op_nr, struct callback_op **op) +{ + switch (op_nr) { + case OP_CB_GETATTR: + case OP_CB_RECALL: + *op = &callback_ops[op_nr]; + break; + default: + return htonl(NFS4ERR_OP_ILLEGAL); + } + + return htonl(NFS_OK); +} + +static __be32 process_op(int nop, struct svc_rqst *rqstp, + struct xdr_stream *xdr_in, void *argp, + struct xdr_stream *xdr_out, void *resp, + struct cb_process_state *cps) +{ + struct callback_op *op = &callback_ops[0]; + unsigned int op_nr; + __be32 status; + long maxlen; + __be32 res; + + dprintk("%s: start\n", __func__); + status = decode_op_hdr(xdr_in, &op_nr); + if (unlikely(status)) + return status; + + dprintk("%s: minorversion=%d nop=%d op_nr=%u\n", + __func__, cps->minorversion, nop, op_nr); + + switch (cps->minorversion) { + case 0: + status = preprocess_nfs4_op(op_nr, &op); + break; + case 1: + status = preprocess_nfs41_op(nop, op_nr, &op); + break; + case 2: + status = preprocess_nfs42_op(nop, op_nr, &op); + break; + default: + status = htonl(NFS4ERR_MINOR_VERS_MISMATCH); + } + + if (status == htonl(NFS4ERR_OP_ILLEGAL)) + op_nr = OP_CB_ILLEGAL; + if (status) + goto encode_hdr; + + if (cps->drc_status) { + status = cps->drc_status; + goto encode_hdr; + } + + maxlen = xdr_out->end - xdr_out->p; + if (maxlen > 0 && maxlen < PAGE_SIZE) { + status = op->decode_args(rqstp, xdr_in, argp); + if (likely(status == 0)) + status = op->process_op(argp, resp, cps); + } else + status = htonl(NFS4ERR_RESOURCE); + +encode_hdr: + res = encode_op_hdr(xdr_out, op_nr, status); + if (unlikely(res)) + return res; + if (op->encode_res != NULL && status == 0) + status = op->encode_res(rqstp, xdr_out, resp); + dprintk("%s: done, status = %d\n", __func__, ntohl(status)); + return status; +} + +/* + * Decode, process and encode a COMPOUND + */ +static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp) +{ + struct cb_compound_hdr_arg hdr_arg = { 0 }; + struct cb_compound_hdr_res hdr_res = { NULL }; + struct xdr_stream xdr_in, xdr_out; + __be32 *p, status; + struct cb_process_state cps = { + .drc_status = 0, + .clp = NULL, + .slotid = NFS4_NO_SLOT, + .net = SVC_NET(rqstp), + }; + unsigned int nops = 0; + + dprintk("%s: start\n", __func__); + + xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base); + + p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len); + xdr_init_encode(&xdr_out, &rqstp->rq_res, p); + + status = decode_compound_hdr_arg(&xdr_in, &hdr_arg); + if (status == __constant_htonl(NFS4ERR_RESOURCE)) + return rpc_garbage_args; + + if (hdr_arg.minorversion == 0) { + cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident); + if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp)) + return rpc_drop_reply; + } + + cps.minorversion = hdr_arg.minorversion; + hdr_res.taglen = hdr_arg.taglen; + hdr_res.tag = hdr_arg.tag; + if (encode_compound_hdr_res(&xdr_out, &hdr_res) != 0) + return rpc_system_err; + + while (status == 0 && nops != hdr_arg.nops) { + status = process_op(nops, rqstp, &xdr_in, + argp, &xdr_out, resp, &cps); + nops++; + } + + /* Buffer overflow in decode_ops_hdr or encode_ops_hdr. Return + * resource error in cb_compound status without returning op */ + if (unlikely(status == htonl(NFS4ERR_RESOURCE_HDR))) { + status = htonl(NFS4ERR_RESOURCE); + nops--; + } + + *hdr_res.status = status; + *hdr_res.nops = htonl(nops); + nfs4_cb_free_slot(&cps); + nfs_put_client(cps.clp); + dprintk("%s: done, status = %u\n", __func__, ntohl(status)); + return rpc_success; +} + +/* + * Define NFS4 callback COMPOUND ops. + */ +static struct callback_op callback_ops[] = { + [0] = { + .res_maxsize = CB_OP_HDR_RES_MAXSZ, + }, + [OP_CB_GETATTR] = { + .process_op = (callback_process_op_t)nfs4_callback_getattr, + .decode_args = (callback_decode_arg_t)decode_getattr_args, + .encode_res = (callback_encode_res_t)encode_getattr_res, + .res_maxsize = CB_OP_GETATTR_RES_MAXSZ, + }, + [OP_CB_RECALL] = { + .process_op = (callback_process_op_t)nfs4_callback_recall, + .decode_args = (callback_decode_arg_t)decode_recall_args, + .res_maxsize = CB_OP_RECALL_RES_MAXSZ, + }, +#if defined(CONFIG_NFS_V4_1) + [OP_CB_LAYOUTRECALL] = { + .process_op = (callback_process_op_t)nfs4_callback_layoutrecall, + .decode_args = + (callback_decode_arg_t)decode_layoutrecall_args, + .res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ, + }, + [OP_CB_NOTIFY_DEVICEID] = { + .process_op = (callback_process_op_t)nfs4_callback_devicenotify, + .decode_args = + (callback_decode_arg_t)decode_devicenotify_args, + .res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ, + }, + [OP_CB_SEQUENCE] = { + .process_op = (callback_process_op_t)nfs4_callback_sequence, + .decode_args = (callback_decode_arg_t)decode_cb_sequence_args, + .encode_res = (callback_encode_res_t)encode_cb_sequence_res, + .res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ, + }, + [OP_CB_RECALL_ANY] = { + .process_op = (callback_process_op_t)nfs4_callback_recallany, + .decode_args = (callback_decode_arg_t)decode_recallany_args, + .res_maxsize = CB_OP_RECALLANY_RES_MAXSZ, + }, + [OP_CB_RECALL_SLOT] = { + .process_op = (callback_process_op_t)nfs4_callback_recallslot, + .decode_args = (callback_decode_arg_t)decode_recallslot_args, + .res_maxsize = CB_OP_RECALLSLOT_RES_MAXSZ, + }, +#endif /* CONFIG_NFS_V4_1 */ +}; + +/* + * Define NFS4 callback procedures + */ +static struct svc_procedure nfs4_callback_procedures1[] = { + [CB_NULL] = { + .pc_func = nfs4_callback_null, + .pc_decode = (kxdrproc_t)nfs4_decode_void, + .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_xdrressize = 1, + }, + [CB_COMPOUND] = { + .pc_func = nfs4_callback_compound, + .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_argsize = 256, + .pc_ressize = 256, + .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, + } +}; + +struct svc_version nfs4_callback_version1 = { + .vs_vers = 1, + .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), + .vs_proc = nfs4_callback_procedures1, + .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, + .vs_dispatch = NULL, + .vs_hidden = 1, +}; + +struct svc_version nfs4_callback_version4 = { + .vs_vers = 4, + .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), + .vs_proc = nfs4_callback_procedures1, + .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, + .vs_dispatch = NULL, + .vs_hidden = 1, +}; diff --git a/kernel/fs/nfs/client.c b/kernel/fs/nfs/client.c new file mode 100644 index 000000000..892aefff3 --- /dev/null +++ b/kernel/fs/nfs/client.c @@ -0,0 +1,1472 @@ +/* client.c: NFS client sharing and management code + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/stats.h> +#include <linux/sunrpc/metrics.h> +#include <linux/sunrpc/xprtsock.h> +#include <linux/sunrpc/xprtrdma.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs4_mount.h> +#include <linux/lockd/bind.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/vfs.h> +#include <linux/inet.h> +#include <linux/in6.h> +#include <linux/slab.h> +#include <linux/idr.h> +#include <net/ipv6.h> +#include <linux/nfs_xdr.h> +#include <linux/sunrpc/bc_xprt.h> +#include <linux/nsproxy.h> +#include <linux/pid_namespace.h> + + +#include "nfs4_fs.h" +#include "callback.h" +#include "delegation.h" +#include "iostat.h" +#include "internal.h" +#include "fscache.h" +#include "pnfs.h" +#include "nfs.h" +#include "netns.h" + +#define NFSDBG_FACILITY NFSDBG_CLIENT + +static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq); +static DEFINE_SPINLOCK(nfs_version_lock); +static DEFINE_MUTEX(nfs_version_mutex); +static LIST_HEAD(nfs_versions); + +/* + * RPC cruft for NFS + */ +static const struct rpc_version *nfs_version[5] = { + [2] = NULL, + [3] = NULL, + [4] = NULL, +}; + +const struct rpc_program nfs_program = { + .name = "nfs", + .number = NFS_PROGRAM, + .nrvers = ARRAY_SIZE(nfs_version), + .version = nfs_version, + .stats = &nfs_rpcstat, + .pipe_dir_name = NFS_PIPE_DIRNAME, +}; + +struct rpc_stat nfs_rpcstat = { + .program = &nfs_program +}; + +static struct nfs_subversion *find_nfs_version(unsigned int version) +{ + struct nfs_subversion *nfs; + spin_lock(&nfs_version_lock); + + list_for_each_entry(nfs, &nfs_versions, list) { + if (nfs->rpc_ops->version == version) { + spin_unlock(&nfs_version_lock); + return nfs; + } + } + + spin_unlock(&nfs_version_lock); + return ERR_PTR(-EPROTONOSUPPORT); +} + +struct nfs_subversion *get_nfs_version(unsigned int version) +{ + struct nfs_subversion *nfs = find_nfs_version(version); + + if (IS_ERR(nfs)) { + mutex_lock(&nfs_version_mutex); + request_module("nfsv%d", version); + nfs = find_nfs_version(version); + mutex_unlock(&nfs_version_mutex); + } + + if (!IS_ERR(nfs) && !try_module_get(nfs->owner)) + return ERR_PTR(-EAGAIN); + return nfs; +} + +void put_nfs_version(struct nfs_subversion *nfs) +{ + module_put(nfs->owner); +} + +void register_nfs_version(struct nfs_subversion *nfs) +{ + spin_lock(&nfs_version_lock); + + list_add(&nfs->list, &nfs_versions); + nfs_version[nfs->rpc_ops->version] = nfs->rpc_vers; + + spin_unlock(&nfs_version_lock); +} +EXPORT_SYMBOL_GPL(register_nfs_version); + +void unregister_nfs_version(struct nfs_subversion *nfs) +{ + spin_lock(&nfs_version_lock); + + nfs_version[nfs->rpc_ops->version] = NULL; + list_del(&nfs->list); + + spin_unlock(&nfs_version_lock); +} +EXPORT_SYMBOL_GPL(unregister_nfs_version); + +/* + * Allocate a shared client record + * + * Since these are allocated/deallocated very rarely, we don't + * bother putting them in a slab cache... + */ +struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) +{ + struct nfs_client *clp; + struct rpc_cred *cred; + int err = -ENOMEM; + + if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) + goto error_0; + + clp->cl_nfs_mod = cl_init->nfs_mod; + if (!try_module_get(clp->cl_nfs_mod->owner)) + goto error_dealloc; + + clp->rpc_ops = clp->cl_nfs_mod->rpc_ops; + + atomic_set(&clp->cl_count, 1); + clp->cl_cons_state = NFS_CS_INITING; + + memcpy(&clp->cl_addr, cl_init->addr, cl_init->addrlen); + clp->cl_addrlen = cl_init->addrlen; + + if (cl_init->hostname) { + err = -ENOMEM; + clp->cl_hostname = kstrdup(cl_init->hostname, GFP_KERNEL); + if (!clp->cl_hostname) + goto error_cleanup; + } + + INIT_LIST_HEAD(&clp->cl_superblocks); + clp->cl_rpcclient = ERR_PTR(-EINVAL); + + clp->cl_proto = cl_init->proto; + clp->cl_net = get_net(cl_init->net); + + cred = rpc_lookup_machine_cred("*"); + if (!IS_ERR(cred)) + clp->cl_machine_cred = cred; + nfs_fscache_get_client_cookie(clp); + + return clp; + +error_cleanup: + put_nfs_version(clp->cl_nfs_mod); +error_dealloc: + kfree(clp); +error_0: + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(nfs_alloc_client); + +#if IS_ENABLED(CONFIG_NFS_V4) +void nfs_cleanup_cb_ident_idr(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + + idr_destroy(&nn->cb_ident_idr); +} + +/* nfs_client_lock held */ +static void nfs_cb_idr_remove_locked(struct nfs_client *clp) +{ + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + + if (clp->cl_cb_ident) + idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident); +} + +static void pnfs_init_server(struct nfs_server *server) +{ + rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); +} + +#else +void nfs_cleanup_cb_ident_idr(struct net *net) +{ +} + +static void nfs_cb_idr_remove_locked(struct nfs_client *clp) +{ +} + +static void pnfs_init_server(struct nfs_server *server) +{ +} + +#endif /* CONFIG_NFS_V4 */ + +/* + * Destroy a shared client record + */ +void nfs_free_client(struct nfs_client *clp) +{ + dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version); + + nfs_fscache_release_client_cookie(clp); + + /* -EIO all pending I/O */ + if (!IS_ERR(clp->cl_rpcclient)) + rpc_shutdown_client(clp->cl_rpcclient); + + if (clp->cl_machine_cred != NULL) + put_rpccred(clp->cl_machine_cred); + + put_net(clp->cl_net); + put_nfs_version(clp->cl_nfs_mod); + kfree(clp->cl_hostname); + kfree(clp->cl_acceptor); + kfree(clp); + + dprintk("<-- nfs_free_client()\n"); +} +EXPORT_SYMBOL_GPL(nfs_free_client); + +/* + * Release a reference to a shared client record + */ +void nfs_put_client(struct nfs_client *clp) +{ + struct nfs_net *nn; + + if (!clp) + return; + + dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count)); + nn = net_generic(clp->cl_net, nfs_net_id); + + if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) { + list_del(&clp->cl_share_link); + nfs_cb_idr_remove_locked(clp); + spin_unlock(&nn->nfs_client_lock); + + WARN_ON_ONCE(!list_empty(&clp->cl_superblocks)); + + clp->rpc_ops->free_client(clp); + } +} +EXPORT_SYMBOL_GPL(nfs_put_client); + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +/* + * Test if two ip6 socket addresses refer to the same socket by + * comparing relevant fields. The padding bytes specifically, are not + * compared. sin6_flowinfo is not compared because it only affects QoS + * and sin6_scope_id is only compared if the address is "link local" + * because "link local" addresses need only be unique to a specific + * link. Conversely, ordinary unicast addresses might have different + * sin6_scope_id. + * + * The caller should ensure both socket addresses are AF_INET6. + */ +static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1; + const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2; + + if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) + return 0; + else if (ipv6_addr_type(&sin1->sin6_addr) & IPV6_ADDR_LINKLOCAL) + return sin1->sin6_scope_id == sin2->sin6_scope_id; + + return 1; +} +#else /* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */ +static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + return 0; +} +#endif + +/* + * Test if two ip4 socket addresses refer to the same socket, by + * comparing relevant fields. The padding bytes specifically, are + * not compared. + * + * The caller should ensure both socket addresses are AF_INET. + */ +static int nfs_sockaddr_match_ipaddr4(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sa1; + const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sa2; + + return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; +} + +static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1; + const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2; + + return nfs_sockaddr_match_ipaddr6(sa1, sa2) && + (sin1->sin6_port == sin2->sin6_port); +} + +static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sa1; + const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sa2; + + return nfs_sockaddr_match_ipaddr4(sa1, sa2) && + (sin1->sin_port == sin2->sin_port); +} + +#if defined(CONFIG_NFS_V4_1) +/* + * Test if two socket addresses represent the same actual socket, + * by comparing (only) relevant fields, excluding the port number. + */ +int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + if (sa1->sa_family != sa2->sa_family) + return 0; + + switch (sa1->sa_family) { + case AF_INET: + return nfs_sockaddr_match_ipaddr4(sa1, sa2); + case AF_INET6: + return nfs_sockaddr_match_ipaddr6(sa1, sa2); + } + return 0; +} +EXPORT_SYMBOL_GPL(nfs_sockaddr_match_ipaddr); +#endif /* CONFIG_NFS_V4_1 */ + +/* + * Test if two socket addresses represent the same actual socket, + * by comparing (only) relevant fields, including the port number. + */ +static int nfs_sockaddr_cmp(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + if (sa1->sa_family != sa2->sa_family) + return 0; + + switch (sa1->sa_family) { + case AF_INET: + return nfs_sockaddr_cmp_ip4(sa1, sa2); + case AF_INET6: + return nfs_sockaddr_cmp_ip6(sa1, sa2); + } + return 0; +} + +/* + * Find an nfs_client on the list that matches the initialisation data + * that is supplied. + */ +static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data) +{ + struct nfs_client *clp; + const struct sockaddr *sap = data->addr; + struct nfs_net *nn = net_generic(data->net, nfs_net_id); + + list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { + const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; + /* Don't match clients that failed to initialise properly */ + if (clp->cl_cons_state < 0) + continue; + + /* Different NFS versions cannot share the same nfs_client */ + if (clp->rpc_ops != data->nfs_mod->rpc_ops) + continue; + + if (clp->cl_proto != data->proto) + continue; + /* Match nfsv4 minorversion */ + if (clp->cl_minorversion != data->minorversion) + continue; + /* Match the full socket address */ + if (!nfs_sockaddr_cmp(sap, clap)) + continue; + + atomic_inc(&clp->cl_count); + return clp; + } + return NULL; +} + +static bool nfs_client_init_is_complete(const struct nfs_client *clp) +{ + return clp->cl_cons_state <= NFS_CS_READY; +} + +int nfs_wait_client_init_complete(const struct nfs_client *clp) +{ + return wait_event_killable(nfs_client_active_wq, + nfs_client_init_is_complete(clp)); +} +EXPORT_SYMBOL_GPL(nfs_wait_client_init_complete); + +/* + * Found an existing client. Make sure it's ready before returning. + */ +static struct nfs_client * +nfs_found_client(const struct nfs_client_initdata *cl_init, + struct nfs_client *clp) +{ + int error; + + error = nfs_wait_client_init_complete(clp); + if (error < 0) { + nfs_put_client(clp); + return ERR_PTR(-ERESTARTSYS); + } + + if (clp->cl_cons_state < NFS_CS_READY) { + error = clp->cl_cons_state; + nfs_put_client(clp); + return ERR_PTR(error); + } + + smp_rmb(); + + dprintk("<-- %s found nfs_client %p for %s\n", + __func__, clp, cl_init->hostname ?: ""); + return clp; +} + +/* + * Look up a client by IP address and protocol version + * - creates a new record if one doesn't yet exist + */ +struct nfs_client * +nfs_get_client(const struct nfs_client_initdata *cl_init, + const struct rpc_timeout *timeparms, + const char *ip_addr, + rpc_authflavor_t authflavour) +{ + struct nfs_client *clp, *new = NULL; + struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); + const struct nfs_rpc_ops *rpc_ops = cl_init->nfs_mod->rpc_ops; + + if (cl_init->hostname == NULL) { + WARN_ON(1); + return NULL; + } + + dprintk("--> nfs_get_client(%s,v%u)\n", + cl_init->hostname, rpc_ops->version); + + /* see if the client already exists */ + do { + spin_lock(&nn->nfs_client_lock); + + clp = nfs_match_client(cl_init); + if (clp) { + spin_unlock(&nn->nfs_client_lock); + if (new) + new->rpc_ops->free_client(new); + return nfs_found_client(cl_init, clp); + } + if (new) { + list_add_tail(&new->cl_share_link, + &nn->nfs_client_list); + spin_unlock(&nn->nfs_client_lock); + new->cl_flags = cl_init->init_flags; + return rpc_ops->init_client(new, timeparms, ip_addr); + } + + spin_unlock(&nn->nfs_client_lock); + + new = rpc_ops->alloc_client(cl_init); + } while (!IS_ERR(new)); + + dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n", + cl_init->hostname, PTR_ERR(new)); + return new; +} +EXPORT_SYMBOL_GPL(nfs_get_client); + +/* + * Mark a server as ready or failed + */ +void nfs_mark_client_ready(struct nfs_client *clp, int state) +{ + smp_wmb(); + clp->cl_cons_state = state; + wake_up_all(&nfs_client_active_wq); +} +EXPORT_SYMBOL_GPL(nfs_mark_client_ready); + +/* + * Initialise the timeout values for a connection + */ +void nfs_init_timeout_values(struct rpc_timeout *to, int proto, + unsigned int timeo, unsigned int retrans) +{ + to->to_initval = timeo * HZ / 10; + to->to_retries = retrans; + + switch (proto) { + case XPRT_TRANSPORT_TCP: + case XPRT_TRANSPORT_RDMA: + if (to->to_retries == 0) + to->to_retries = NFS_DEF_TCP_RETRANS; + if (to->to_initval == 0) + to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; + if (to->to_initval > NFS_MAX_TCP_TIMEOUT) + to->to_initval = NFS_MAX_TCP_TIMEOUT; + to->to_increment = to->to_initval; + to->to_maxval = to->to_initval + (to->to_increment * to->to_retries); + if (to->to_maxval > NFS_MAX_TCP_TIMEOUT) + to->to_maxval = NFS_MAX_TCP_TIMEOUT; + if (to->to_maxval < to->to_initval) + to->to_maxval = to->to_initval; + to->to_exponential = 0; + break; + case XPRT_TRANSPORT_UDP: + if (to->to_retries == 0) + to->to_retries = NFS_DEF_UDP_RETRANS; + if (!to->to_initval) + to->to_initval = NFS_DEF_UDP_TIMEO * HZ / 10; + if (to->to_initval > NFS_MAX_UDP_TIMEOUT) + to->to_initval = NFS_MAX_UDP_TIMEOUT; + to->to_maxval = NFS_MAX_UDP_TIMEOUT; + to->to_exponential = 1; + break; + default: + BUG(); + } +} +EXPORT_SYMBOL_GPL(nfs_init_timeout_values); + +/* + * Create an RPC client handle + */ +int nfs_create_rpc_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + rpc_authflavor_t flavor) +{ + struct rpc_clnt *clnt = NULL; + struct rpc_create_args args = { + .net = clp->cl_net, + .protocol = clp->cl_proto, + .address = (struct sockaddr *)&clp->cl_addr, + .addrsize = clp->cl_addrlen, + .timeout = timeparms, + .servername = clp->cl_hostname, + .program = &nfs_program, + .version = clp->rpc_ops->version, + .authflavor = flavor, + }; + + if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_DISCRTRY; + if (test_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT; + if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS; + + if (!IS_ERR(clp->cl_rpcclient)) + return 0; + + clnt = rpc_create(&args); + if (IS_ERR(clnt)) { + dprintk("%s: cannot create RPC client. Error = %ld\n", + __func__, PTR_ERR(clnt)); + return PTR_ERR(clnt); + } + + clp->cl_rpcclient = clnt; + return 0; +} +EXPORT_SYMBOL_GPL(nfs_create_rpc_client); + +/* + * Version 2 or 3 client destruction + */ +static void nfs_destroy_server(struct nfs_server *server) +{ + if (server->nlm_host) + nlmclnt_done(server->nlm_host); +} + +/* + * Version 2 or 3 lockd setup + */ +static int nfs_start_lockd(struct nfs_server *server) +{ + struct nlm_host *host; + struct nfs_client *clp = server->nfs_client; + struct nlmclnt_initdata nlm_init = { + .hostname = clp->cl_hostname, + .address = (struct sockaddr *)&clp->cl_addr, + .addrlen = clp->cl_addrlen, + .nfs_version = clp->rpc_ops->version, + .noresvport = server->flags & NFS_MOUNT_NORESVPORT ? + 1 : 0, + .net = clp->cl_net, + }; + + if (nlm_init.nfs_version > 3) + return 0; + if ((server->flags & NFS_MOUNT_LOCAL_FLOCK) && + (server->flags & NFS_MOUNT_LOCAL_FCNTL)) + return 0; + + switch (clp->cl_proto) { + default: + nlm_init.protocol = IPPROTO_TCP; + break; + case XPRT_TRANSPORT_UDP: + nlm_init.protocol = IPPROTO_UDP; + } + + host = nlmclnt_init(&nlm_init); + if (IS_ERR(host)) + return PTR_ERR(host); + + server->nlm_host = host; + server->destroy = nfs_destroy_server; + return 0; +} + +/* + * Create a general RPC client + */ +int nfs_init_server_rpcclient(struct nfs_server *server, + const struct rpc_timeout *timeo, + rpc_authflavor_t pseudoflavour) +{ + struct nfs_client *clp = server->nfs_client; + + server->client = rpc_clone_client_set_auth(clp->cl_rpcclient, + pseudoflavour); + if (IS_ERR(server->client)) { + dprintk("%s: couldn't create rpc_client!\n", __func__); + return PTR_ERR(server->client); + } + + memcpy(&server->client->cl_timeout_default, + timeo, + sizeof(server->client->cl_timeout_default)); + server->client->cl_timeout = &server->client->cl_timeout_default; + server->client->cl_softrtry = 0; + if (server->flags & NFS_MOUNT_SOFT) + server->client->cl_softrtry = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient); + +/** + * nfs_init_client - Initialise an NFS2 or NFS3 client + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: IP presentation address (not used) + * + * Returns pointer to an NFS client, or an ERR_PTR value. + */ +struct nfs_client *nfs_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr) +{ + int error; + + if (clp->cl_cons_state == NFS_CS_READY) { + /* the client is already initialised */ + dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp); + return clp; + } + + /* + * Create a client RPC handle for doing FSSTAT with UNIX auth only + * - RFC 2623, sec 2.3.2 + */ + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); + if (error < 0) + goto error; + nfs_mark_client_ready(clp, NFS_CS_READY); + return clp; + +error: + nfs_mark_client_ready(clp, error); + nfs_put_client(clp); + dprintk("<-- nfs_init_client() = xerror %d\n", error); + return ERR_PTR(error); +} +EXPORT_SYMBOL_GPL(nfs_init_client); + +/* + * Create a version 2 or 3 client + */ +static int nfs_init_server(struct nfs_server *server, + const struct nfs_parsed_mount_data *data, + struct nfs_subversion *nfs_mod) +{ + struct nfs_client_initdata cl_init = { + .hostname = data->nfs_server.hostname, + .addr = (const struct sockaddr *)&data->nfs_server.address, + .addrlen = data->nfs_server.addrlen, + .nfs_mod = nfs_mod, + .proto = data->nfs_server.protocol, + .net = data->net, + }; + struct rpc_timeout timeparms; + struct nfs_client *clp; + int error; + + dprintk("--> nfs_init_server()\n"); + + nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, + data->timeo, data->retrans); + if (data->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + + /* Allocate or find a client reference we can use */ + clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX); + if (IS_ERR(clp)) { + dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp)); + return PTR_ERR(clp); + } + + server->nfs_client = clp; + + /* Initialise the client representation from the mount data */ + server->flags = data->flags; + server->options = data->options; + server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| + NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; + + if (data->rsize) + server->rsize = nfs_block_size(data->rsize, NULL); + if (data->wsize) + server->wsize = nfs_block_size(data->wsize, NULL); + + server->acregmin = data->acregmin * HZ; + server->acregmax = data->acregmax * HZ; + server->acdirmin = data->acdirmin * HZ; + server->acdirmax = data->acdirmax * HZ; + + /* Start lockd here, before we might error out */ + error = nfs_start_lockd(server); + if (error < 0) + goto error; + + server->port = data->nfs_server.port; + server->auth_info = data->auth_info; + + error = nfs_init_server_rpcclient(server, &timeparms, + data->selected_flavor); + if (error < 0) + goto error; + + /* Preserve the values of mount_server-related mount options */ + if (data->mount_server.addrlen) { + memcpy(&server->mountd_address, &data->mount_server.address, + data->mount_server.addrlen); + server->mountd_addrlen = data->mount_server.addrlen; + } + server->mountd_version = data->mount_server.version; + server->mountd_port = data->mount_server.port; + server->mountd_protocol = data->mount_server.protocol; + + server->namelen = data->namlen; + dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp); + return 0; + +error: + server->nfs_client = NULL; + nfs_put_client(clp); + dprintk("<-- nfs_init_server() = xerror %d\n", error); + return error; +} + +/* + * Load up the server record from information gained in an fsinfo record + */ +static void nfs_server_set_fsinfo(struct nfs_server *server, + struct nfs_fh *mntfh, + struct nfs_fsinfo *fsinfo) +{ + unsigned long max_rpc_payload; + + /* Work out a lot of parameters */ + if (server->rsize == 0) + server->rsize = nfs_block_size(fsinfo->rtpref, NULL); + if (server->wsize == 0) + server->wsize = nfs_block_size(fsinfo->wtpref, NULL); + + if (fsinfo->rtmax >= 512 && server->rsize > fsinfo->rtmax) + server->rsize = nfs_block_size(fsinfo->rtmax, NULL); + if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax) + server->wsize = nfs_block_size(fsinfo->wtmax, NULL); + + max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL); + if (server->rsize > max_rpc_payload) + server->rsize = max_rpc_payload; + if (server->rsize > NFS_MAX_FILE_IO_SIZE) + server->rsize = NFS_MAX_FILE_IO_SIZE; + server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + server->backing_dev_info.name = "nfs"; + server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD; + + if (server->wsize > max_rpc_payload) + server->wsize = max_rpc_payload; + if (server->wsize > NFS_MAX_FILE_IO_SIZE) + server->wsize = NFS_MAX_FILE_IO_SIZE; + server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); + + server->dtsize = nfs_block_size(fsinfo->dtpref, NULL); + if (server->dtsize > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES) + server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES; + if (server->dtsize > server->rsize) + server->dtsize = server->rsize; + + if (server->flags & NFS_MOUNT_NOAC) { + server->acregmin = server->acregmax = 0; + server->acdirmin = server->acdirmax = 0; + } + + server->maxfilesize = fsinfo->maxfilesize; + + server->time_delta = fsinfo->time_delta; + + /* We're airborne Set socket buffersize */ + rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); +} + +/* + * Probe filesystem information, including the FSID on v2/v3 + */ +int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr) +{ + struct nfs_fsinfo fsinfo; + struct nfs_client *clp = server->nfs_client; + int error; + + dprintk("--> nfs_probe_fsinfo()\n"); + + if (clp->rpc_ops->set_capabilities != NULL) { + error = clp->rpc_ops->set_capabilities(server, mntfh); + if (error < 0) + goto out_error; + } + + fsinfo.fattr = fattr; + fsinfo.layouttype = 0; + error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo); + if (error < 0) + goto out_error; + + nfs_server_set_fsinfo(server, mntfh, &fsinfo); + + /* Get some general file system info */ + if (server->namelen == 0) { + struct nfs_pathconf pathinfo; + + pathinfo.fattr = fattr; + nfs_fattr_init(fattr); + + if (clp->rpc_ops->pathconf(server, mntfh, &pathinfo) >= 0) + server->namelen = pathinfo.max_namelen; + } + + dprintk("<-- nfs_probe_fsinfo() = 0\n"); + return 0; + +out_error: + dprintk("nfs_probe_fsinfo: error = %d\n", -error); + return error; +} +EXPORT_SYMBOL_GPL(nfs_probe_fsinfo); + +/* + * Copy useful information when duplicating a server record + */ +void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source) +{ + target->flags = source->flags; + target->rsize = source->rsize; + target->wsize = source->wsize; + target->acregmin = source->acregmin; + target->acregmax = source->acregmax; + target->acdirmin = source->acdirmin; + target->acdirmax = source->acdirmax; + target->caps = source->caps; + target->options = source->options; + target->auth_info = source->auth_info; +} +EXPORT_SYMBOL_GPL(nfs_server_copy_userdata); + +void nfs_server_insert_lists(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + + spin_lock(&nn->nfs_client_lock); + list_add_tail_rcu(&server->client_link, &clp->cl_superblocks); + list_add_tail(&server->master_link, &nn->nfs_volume_list); + clear_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state); + spin_unlock(&nn->nfs_client_lock); + +} +EXPORT_SYMBOL_GPL(nfs_server_insert_lists); + +void nfs_server_remove_lists(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs_net *nn; + + if (clp == NULL) + return; + nn = net_generic(clp->cl_net, nfs_net_id); + spin_lock(&nn->nfs_client_lock); + list_del_rcu(&server->client_link); + if (list_empty(&clp->cl_superblocks)) + set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state); + list_del(&server->master_link); + spin_unlock(&nn->nfs_client_lock); + + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(nfs_server_remove_lists); + +/* + * Allocate and initialise a server record + */ +struct nfs_server *nfs_alloc_server(void) +{ + struct nfs_server *server; + + server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL); + if (!server) + return NULL; + + server->client = server->client_acl = ERR_PTR(-EINVAL); + + /* Zero out the NFS state stuff */ + INIT_LIST_HEAD(&server->client_link); + INIT_LIST_HEAD(&server->master_link); + INIT_LIST_HEAD(&server->delegations); + INIT_LIST_HEAD(&server->layouts); + INIT_LIST_HEAD(&server->state_owners_lru); + + atomic_set(&server->active, 0); + + server->io_stats = nfs_alloc_iostats(); + if (!server->io_stats) { + kfree(server); + return NULL; + } + + if (bdi_init(&server->backing_dev_info)) { + nfs_free_iostats(server->io_stats); + kfree(server); + return NULL; + } + + ida_init(&server->openowner_id); + ida_init(&server->lockowner_id); + pnfs_init_server(server); + + return server; +} +EXPORT_SYMBOL_GPL(nfs_alloc_server); + +/* + * Free up a server record + */ +void nfs_free_server(struct nfs_server *server) +{ + dprintk("--> nfs_free_server()\n"); + + nfs_server_remove_lists(server); + + if (server->destroy != NULL) + server->destroy(server); + + if (!IS_ERR(server->client_acl)) + rpc_shutdown_client(server->client_acl); + if (!IS_ERR(server->client)) + rpc_shutdown_client(server->client); + + nfs_put_client(server->nfs_client); + + ida_destroy(&server->lockowner_id); + ida_destroy(&server->openowner_id); + nfs_free_iostats(server->io_stats); + bdi_destroy(&server->backing_dev_info); + kfree(server); + nfs_release_automount_timer(); + dprintk("<-- nfs_free_server()\n"); +} +EXPORT_SYMBOL_GPL(nfs_free_server); + +/* + * Create a version 2 or 3 volume record + * - keyed on server and FSID + */ +struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct nfs_server *server; + struct nfs_fattr *fattr; + int error; + + server = nfs_alloc_server(); + if (!server) + return ERR_PTR(-ENOMEM); + + error = -ENOMEM; + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + goto error; + + /* Get a client representation */ + error = nfs_init_server(server, mount_info->parsed, nfs_mod); + if (error < 0) + goto error; + + /* Probe the root fh to retrieve its FSID */ + error = nfs_probe_fsinfo(server, mount_info->mntfh, fattr); + if (error < 0) + goto error; + if (server->nfs_client->rpc_ops->version == 3) { + if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN) + server->namelen = NFS3_MAXNAMLEN; + if (!(mount_info->parsed->flags & NFS_MOUNT_NORDIRPLUS)) + server->caps |= NFS_CAP_READDIRPLUS; + } else { + if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) + server->namelen = NFS2_MAXNAMLEN; + } + + if (!(fattr->valid & NFS_ATTR_FATTR)) { + error = nfs_mod->rpc_ops->getattr(server, mount_info->mntfh, fattr, NULL); + if (error < 0) { + dprintk("nfs_create_server: getattr error = %d\n", -error); + goto error; + } + } + memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid)); + + dprintk("Server FSID: %llx:%llx\n", + (unsigned long long) server->fsid.major, + (unsigned long long) server->fsid.minor); + + nfs_server_insert_lists(server); + server->mount_time = jiffies; + nfs_free_fattr(fattr); + return server; + +error: + nfs_free_fattr(fattr); + nfs_free_server(server); + return ERR_PTR(error); +} +EXPORT_SYMBOL_GPL(nfs_create_server); + +/* + * Clone an NFS2, NFS3 or NFS4 server record + */ +struct nfs_server *nfs_clone_server(struct nfs_server *source, + struct nfs_fh *fh, + struct nfs_fattr *fattr, + rpc_authflavor_t flavor) +{ + struct nfs_server *server; + struct nfs_fattr *fattr_fsinfo; + int error; + + dprintk("--> nfs_clone_server(,%llx:%llx,)\n", + (unsigned long long) fattr->fsid.major, + (unsigned long long) fattr->fsid.minor); + + server = nfs_alloc_server(); + if (!server) + return ERR_PTR(-ENOMEM); + + error = -ENOMEM; + fattr_fsinfo = nfs_alloc_fattr(); + if (fattr_fsinfo == NULL) + goto out_free_server; + + /* Copy data from the source */ + server->nfs_client = source->nfs_client; + server->destroy = source->destroy; + atomic_inc(&server->nfs_client->cl_count); + nfs_server_copy_userdata(server, source); + + server->fsid = fattr->fsid; + + error = nfs_init_server_rpcclient(server, + source->client->cl_timeout, + flavor); + if (error < 0) + goto out_free_server; + + /* probe the filesystem info for this server filesystem */ + error = nfs_probe_fsinfo(server, fh, fattr_fsinfo); + if (error < 0) + goto out_free_server; + + if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) + server->namelen = NFS4_MAXNAMLEN; + + dprintk("Cloned FSID: %llx:%llx\n", + (unsigned long long) server->fsid.major, + (unsigned long long) server->fsid.minor); + + error = nfs_start_lockd(server); + if (error < 0) + goto out_free_server; + + nfs_server_insert_lists(server); + server->mount_time = jiffies; + + nfs_free_fattr(fattr_fsinfo); + dprintk("<-- nfs_clone_server() = %p\n", server); + return server; + +out_free_server: + nfs_free_fattr(fattr_fsinfo); + nfs_free_server(server); + dprintk("<-- nfs_clone_server() = error %d\n", error); + return ERR_PTR(error); +} +EXPORT_SYMBOL_GPL(nfs_clone_server); + +void nfs_clients_init(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + + INIT_LIST_HEAD(&nn->nfs_client_list); + INIT_LIST_HEAD(&nn->nfs_volume_list); +#if IS_ENABLED(CONFIG_NFS_V4) + idr_init(&nn->cb_ident_idr); +#endif + spin_lock_init(&nn->nfs_client_lock); + nn->boot_time = CURRENT_TIME; +} + +#ifdef CONFIG_PROC_FS +static struct proc_dir_entry *proc_fs_nfs; + +static int nfs_server_list_open(struct inode *inode, struct file *file); +static void *nfs_server_list_start(struct seq_file *p, loff_t *pos); +static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos); +static void nfs_server_list_stop(struct seq_file *p, void *v); +static int nfs_server_list_show(struct seq_file *m, void *v); + +static const struct seq_operations nfs_server_list_ops = { + .start = nfs_server_list_start, + .next = nfs_server_list_next, + .stop = nfs_server_list_stop, + .show = nfs_server_list_show, +}; + +static const struct file_operations nfs_server_list_fops = { + .open = nfs_server_list_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, + .owner = THIS_MODULE, +}; + +static int nfs_volume_list_open(struct inode *inode, struct file *file); +static void *nfs_volume_list_start(struct seq_file *p, loff_t *pos); +static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos); +static void nfs_volume_list_stop(struct seq_file *p, void *v); +static int nfs_volume_list_show(struct seq_file *m, void *v); + +static const struct seq_operations nfs_volume_list_ops = { + .start = nfs_volume_list_start, + .next = nfs_volume_list_next, + .stop = nfs_volume_list_stop, + .show = nfs_volume_list_show, +}; + +static const struct file_operations nfs_volume_list_fops = { + .open = nfs_volume_list_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, + .owner = THIS_MODULE, +}; + +/* + * open "/proc/fs/nfsfs/servers" which provides a summary of servers with which + * we're dealing + */ +static int nfs_server_list_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &nfs_server_list_ops, + sizeof(struct seq_net_private)); +} + +/* + * set up the iterator to start reading from the server list and return the first item + */ +static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos) + __acquires(&nn->nfs_client_lock) +{ + struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id); + + /* lock the list against modification */ + spin_lock(&nn->nfs_client_lock); + return seq_list_start_head(&nn->nfs_client_list, *_pos); +} + +/* + * move to next server + */ +static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos) +{ + struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id); + + return seq_list_next(v, &nn->nfs_client_list, pos); +} + +/* + * clean up after reading from the transports list + */ +static void nfs_server_list_stop(struct seq_file *p, void *v) + __releases(&nn->nfs_client_lock) +{ + struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id); + + spin_unlock(&nn->nfs_client_lock); +} + +/* + * display a header line followed by a load of call lines + */ +static int nfs_server_list_show(struct seq_file *m, void *v) +{ + struct nfs_client *clp; + struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id); + + /* display header on line 1 */ + if (v == &nn->nfs_client_list) { + seq_puts(m, "NV SERVER PORT USE HOSTNAME\n"); + return 0; + } + + /* display one transport per line on subsequent lines */ + clp = list_entry(v, struct nfs_client, cl_share_link); + + /* Check if the client is initialized */ + if (clp->cl_cons_state != NFS_CS_READY) + return 0; + + rcu_read_lock(); + seq_printf(m, "v%u %s %s %3d %s\n", + clp->rpc_ops->version, + rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR), + rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT), + atomic_read(&clp->cl_count), + clp->cl_hostname); + rcu_read_unlock(); + + return 0; +} + +/* + * open "/proc/fs/nfsfs/volumes" which provides a summary of extant volumes + */ +static int nfs_volume_list_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &nfs_volume_list_ops, + sizeof(struct seq_net_private)); +} + +/* + * set up the iterator to start reading from the volume list and return the first item + */ +static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos) + __acquires(&nn->nfs_client_lock) +{ + struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id); + + /* lock the list against modification */ + spin_lock(&nn->nfs_client_lock); + return seq_list_start_head(&nn->nfs_volume_list, *_pos); +} + +/* + * move to next volume + */ +static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos) +{ + struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id); + + return seq_list_next(v, &nn->nfs_volume_list, pos); +} + +/* + * clean up after reading from the transports list + */ +static void nfs_volume_list_stop(struct seq_file *p, void *v) + __releases(&nn->nfs_client_lock) +{ + struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id); + + spin_unlock(&nn->nfs_client_lock); +} + +/* + * display a header line followed by a load of call lines + */ +static int nfs_volume_list_show(struct seq_file *m, void *v) +{ + struct nfs_server *server; + struct nfs_client *clp; + char dev[8], fsid[17]; + struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id); + + /* display header on line 1 */ + if (v == &nn->nfs_volume_list) { + seq_puts(m, "NV SERVER PORT DEV FSID FSC\n"); + return 0; + } + /* display one transport per line on subsequent lines */ + server = list_entry(v, struct nfs_server, master_link); + clp = server->nfs_client; + + snprintf(dev, 8, "%u:%u", + MAJOR(server->s_dev), MINOR(server->s_dev)); + + snprintf(fsid, 17, "%llx:%llx", + (unsigned long long) server->fsid.major, + (unsigned long long) server->fsid.minor); + + rcu_read_lock(); + seq_printf(m, "v%u %s %s %-7s %-17s %s\n", + clp->rpc_ops->version, + rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR), + rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT), + dev, + fsid, + nfs_server_fscache_state(server)); + rcu_read_unlock(); + + return 0; +} + +int nfs_fs_proc_net_init(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct proc_dir_entry *p; + + nn->proc_nfsfs = proc_net_mkdir(net, "nfsfs", net->proc_net); + if (!nn->proc_nfsfs) + goto error_0; + + /* a file of servers with which we're dealing */ + p = proc_create("servers", S_IFREG|S_IRUGO, + nn->proc_nfsfs, &nfs_server_list_fops); + if (!p) + goto error_1; + + /* a file of volumes that we have mounted */ + p = proc_create("volumes", S_IFREG|S_IRUGO, + nn->proc_nfsfs, &nfs_volume_list_fops); + if (!p) + goto error_1; + return 0; + +error_1: + remove_proc_subtree("nfsfs", net->proc_net); +error_0: + return -ENOMEM; +} + +void nfs_fs_proc_net_exit(struct net *net) +{ + remove_proc_subtree("nfsfs", net->proc_net); +} + +/* + * initialise the /proc/fs/nfsfs/ directory + */ +int __init nfs_fs_proc_init(void) +{ + struct proc_dir_entry *p; + + proc_fs_nfs = proc_mkdir("fs/nfsfs", NULL); + if (!proc_fs_nfs) + goto error_0; + + /* a file of servers with which we're dealing */ + p = proc_symlink("servers", proc_fs_nfs, "../../net/nfsfs/servers"); + if (!p) + goto error_1; + + /* a file of volumes that we have mounted */ + p = proc_symlink("volumes", proc_fs_nfs, "../../net/nfsfs/volumes"); + if (!p) + goto error_2; + return 0; + +error_2: + remove_proc_entry("servers", proc_fs_nfs); +error_1: + remove_proc_entry("fs/nfsfs", NULL); +error_0: + return -ENOMEM; +} + +/* + * clean up the /proc/fs/nfsfs/ directory + */ +void nfs_fs_proc_exit(void) +{ + remove_proc_entry("volumes", proc_fs_nfs); + remove_proc_entry("servers", proc_fs_nfs); + remove_proc_entry("fs/nfsfs", NULL); +} + +#endif /* CONFIG_PROC_FS */ diff --git a/kernel/fs/nfs/delegation.c b/kernel/fs/nfs/delegation.c new file mode 100644 index 000000000..029d688a9 --- /dev/null +++ b/kernel/fs/nfs/delegation.c @@ -0,0 +1,902 @@ +/* + * linux/fs/nfs/delegation.c + * + * Copyright (C) 2004 Trond Myklebust + * + * NFS file delegation management + * + */ +#include <linux/completion.h> +#include <linux/kthread.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_xdr.h> + +#include "nfs4_fs.h" +#include "delegation.h" +#include "internal.h" +#include "nfs4trace.h" + +static void nfs_free_delegation(struct nfs_delegation *delegation) +{ + if (delegation->cred) { + put_rpccred(delegation->cred); + delegation->cred = NULL; + } + kfree_rcu(delegation, rcu); +} + +/** + * nfs_mark_delegation_referenced - set delegation's REFERENCED flag + * @delegation: delegation to process + * + */ +void nfs_mark_delegation_referenced(struct nfs_delegation *delegation) +{ + set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags); +} + +static int +nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark) +{ + struct nfs_delegation *delegation; + int ret = 0; + + flags &= FMODE_READ|FMODE_WRITE; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL && (delegation->type & flags) == flags && + !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + if (mark) + nfs_mark_delegation_referenced(delegation); + ret = 1; + } + rcu_read_unlock(); + return ret; +} +/** + * nfs_have_delegation - check if inode has a delegation, mark it + * NFS_DELEGATION_REFERENCED if there is one. + * @inode: inode to check + * @flags: delegation types to check for + * + * Returns one if inode has the indicated delegation, otherwise zero. + */ +int nfs4_have_delegation(struct inode *inode, fmode_t flags) +{ + return nfs4_do_check_delegation(inode, flags, true); +} + +/* + * nfs4_check_delegation - check if inode has a delegation, do not mark + * NFS_DELEGATION_REFERENCED if it has one. + */ +int nfs4_check_delegation(struct inode *inode, fmode_t flags) +{ + return nfs4_do_check_delegation(inode, flags, false); +} + +static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) +{ + struct inode *inode = state->inode; + struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; + int status = 0; + + if (flctx == NULL) + goto out; + + list = &flctx->flc_posix; + spin_lock(&flctx->flc_lock); +restart: + list_for_each_entry(fl, list, fl_list) { + if (nfs_file_open_context(fl->fl_file) != ctx) + continue; + spin_unlock(&flctx->flc_lock); + status = nfs4_lock_delegation_recall(fl, state, stateid); + if (status < 0) + goto out; + spin_lock(&flctx->flc_lock); + } + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } + spin_unlock(&flctx->flc_lock); +out: + return status; +} + +static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_open_context *ctx; + struct nfs4_state_owner *sp; + struct nfs4_state *state; + unsigned int seq; + int err; + +again: + spin_lock(&inode->i_lock); + list_for_each_entry(ctx, &nfsi->open_files, list) { + state = ctx->state; + if (state == NULL) + continue; + if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) + continue; + if (!nfs4_valid_open_stateid(state)) + continue; + if (!nfs4_stateid_match(&state->stateid, stateid)) + continue; + get_nfs_open_context(ctx); + spin_unlock(&inode->i_lock); + sp = state->owner; + /* Block nfs4_proc_unlck */ + mutex_lock(&sp->so_delegreturn_mutex); + seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); + err = nfs4_open_delegation_recall(ctx, state, stateid); + if (!err) + err = nfs_delegation_claim_locks(ctx, state, stateid); + if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) + err = -EAGAIN; + mutex_unlock(&sp->so_delegreturn_mutex); + put_nfs_open_context(ctx); + if (err != 0) + return err; + goto again; + } + spin_unlock(&inode->i_lock); + return 0; +} + +/** + * nfs_inode_reclaim_delegation - process a delegation reclaim request + * @inode: inode to process + * @cred: credential to use for request + * @res: new delegation state from server + * + */ +void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, + struct nfs_openres *res) +{ + struct nfs_delegation *delegation; + struct rpc_cred *oldcred = NULL; + + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + spin_lock(&delegation->lock); + if (delegation->inode != NULL) { + nfs4_stateid_copy(&delegation->stateid, &res->delegation); + delegation->type = res->delegation_type; + delegation->maxsize = res->maxsize; + oldcred = delegation->cred; + delegation->cred = get_rpccred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, + &delegation->flags); + spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_rpccred(oldcred); + trace_nfs4_reclaim_delegation(inode, res->delegation_type); + } else { + /* We appear to have raced with a delegation return. */ + spin_unlock(&delegation->lock); + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, res); + } + } else { + rcu_read_unlock(); + } +} + +static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) +{ + int res = 0; + + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + res = nfs4_proc_delegreturn(inode, + delegation->cred, + &delegation->stateid, + issync); + nfs_free_delegation(delegation); + return res; +} + +static struct inode *nfs_delegation_grab_inode(struct nfs_delegation *delegation) +{ + struct inode *inode = NULL; + + spin_lock(&delegation->lock); + if (delegation->inode != NULL) + inode = igrab(delegation->inode); + spin_unlock(&delegation->lock); + return inode; +} + +static struct nfs_delegation * +nfs_start_delegation_return_locked(struct nfs_inode *nfsi) +{ + struct nfs_delegation *ret = NULL; + struct nfs_delegation *delegation = rcu_dereference(nfsi->delegation); + + if (delegation == NULL) + goto out; + spin_lock(&delegation->lock); + if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) + ret = delegation; + spin_unlock(&delegation->lock); +out: + return ret; +} + +static struct nfs_delegation * +nfs_start_delegation_return(struct nfs_inode *nfsi) +{ + struct nfs_delegation *delegation; + + rcu_read_lock(); + delegation = nfs_start_delegation_return_locked(nfsi); + rcu_read_unlock(); + return delegation; +} + +static void +nfs_abort_delegation_return(struct nfs_delegation *delegation, + struct nfs_client *clp) +{ + + spin_lock(&delegation->lock); + clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags); + set_bit(NFS_DELEGATION_RETURN, &delegation->flags); + spin_unlock(&delegation->lock); + set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state); +} + +static struct nfs_delegation * +nfs_detach_delegation_locked(struct nfs_inode *nfsi, + struct nfs_delegation *delegation, + struct nfs_client *clp) +{ + struct nfs_delegation *deleg_cur = + rcu_dereference_protected(nfsi->delegation, + lockdep_is_held(&clp->cl_lock)); + + if (deleg_cur == NULL || delegation != deleg_cur) + return NULL; + + spin_lock(&delegation->lock); + set_bit(NFS_DELEGATION_RETURNING, &delegation->flags); + list_del_rcu(&delegation->super_list); + delegation->inode = NULL; + rcu_assign_pointer(nfsi->delegation, NULL); + spin_unlock(&delegation->lock); + return delegation; +} + +static struct nfs_delegation *nfs_detach_delegation(struct nfs_inode *nfsi, + struct nfs_delegation *delegation, + struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + + spin_lock(&clp->cl_lock); + delegation = nfs_detach_delegation_locked(nfsi, delegation, clp); + spin_unlock(&clp->cl_lock); + return delegation; +} + +static struct nfs_delegation * +nfs_inode_detach_delegation(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_delegation *delegation; + + delegation = nfs_start_delegation_return(nfsi); + if (delegation == NULL) + return NULL; + return nfs_detach_delegation(nfsi, delegation, server); +} + +static void +nfs_update_inplace_delegation(struct nfs_delegation *delegation, + const struct nfs_delegation *update) +{ + if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) { + delegation->stateid.seqid = update->stateid.seqid; + smp_wmb(); + delegation->type = update->type; + } +} + +/** + * nfs_inode_set_delegation - set up a delegation on an inode + * @inode: inode to which delegation applies + * @cred: cred to use for subsequent delegation processing + * @res: new delegation state from server + * + * Returns zero on success, or a negative errno value. + */ +int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_delegation *delegation, *old_delegation; + struct nfs_delegation *freeme = NULL; + int status = 0; + + delegation = kmalloc(sizeof(*delegation), GFP_NOFS); + if (delegation == NULL) + return -ENOMEM; + nfs4_stateid_copy(&delegation->stateid, &res->delegation); + delegation->type = res->delegation_type; + delegation->maxsize = res->maxsize; + delegation->change_attr = inode->i_version; + delegation->cred = get_rpccred(cred); + delegation->inode = inode; + delegation->flags = 1<<NFS_DELEGATION_REFERENCED; + spin_lock_init(&delegation->lock); + + spin_lock(&clp->cl_lock); + old_delegation = rcu_dereference_protected(nfsi->delegation, + lockdep_is_held(&clp->cl_lock)); + if (old_delegation != NULL) { + /* Is this an update of the existing delegation? */ + if (nfs4_stateid_match_other(&old_delegation->stateid, + &delegation->stateid)) { + nfs_update_inplace_delegation(old_delegation, + delegation); + goto out; + } + /* + * Deal with broken servers that hand out two + * delegations for the same file. + * Allow for upgrades to a WRITE delegation, but + * nothing else. + */ + dfprintk(FILE, "%s: server %s handed out " + "a duplicate delegation!\n", + __func__, clp->cl_hostname); + if (delegation->type == old_delegation->type || + !(delegation->type & FMODE_WRITE)) { + freeme = delegation; + delegation = NULL; + goto out; + } + if (test_and_set_bit(NFS_DELEGATION_RETURNING, + &old_delegation->flags)) + goto out; + freeme = nfs_detach_delegation_locked(nfsi, + old_delegation, clp); + if (freeme == NULL) + goto out; + } + list_add_tail_rcu(&delegation->super_list, &server->delegations); + rcu_assign_pointer(nfsi->delegation, delegation); + delegation = NULL; + + /* Ensure we revalidate the attributes and page cache! */ + spin_lock(&inode->i_lock); + nfsi->cache_validity |= NFS_INO_REVAL_FORCED; + spin_unlock(&inode->i_lock); + trace_nfs4_set_delegation(inode, res->delegation_type); + +out: + spin_unlock(&clp->cl_lock); + if (delegation != NULL) + nfs_free_delegation(delegation); + if (freeme != NULL) + nfs_do_return_delegation(inode, freeme, 0); + return status; +} + +/* + * Basic procedure for returning a delegation to the server + */ +static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync) +{ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + struct nfs_inode *nfsi = NFS_I(inode); + int err = 0; + + if (delegation == NULL) + return 0; + do { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + break; + err = nfs_delegation_claim_opens(inode, &delegation->stateid); + if (!issync || err != -EAGAIN) + break; + /* + * Guard against state recovery + */ + err = nfs4_wait_clnt_recover(clp); + } while (err == 0); + + if (err) { + nfs_abort_delegation_return(delegation, clp); + goto out; + } + if (!nfs_detach_delegation(nfsi, delegation, NFS_SERVER(inode))) + goto out; + + err = nfs_do_return_delegation(inode, delegation, issync); +out: + return err; +} + +static bool nfs_delegation_need_return(struct nfs_delegation *delegation) +{ + bool ret = false; + + if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) + goto out; + if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags)) + ret = true; + if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) { + struct inode *inode; + + spin_lock(&delegation->lock); + inode = delegation->inode; + if (inode && list_empty(&NFS_I(inode)->open_files)) + ret = true; + spin_unlock(&delegation->lock); + } +out: + return ret; +} + +/** + * nfs_client_return_marked_delegations - return previously marked delegations + * @clp: nfs_client to process + * + * Note that this function is designed to be called by the state + * manager thread. For this reason, it cannot flush the dirty data, + * since that could deadlock in case of a state recovery error. + * + * Returns zero on success, or a negative errno value. + */ +int nfs_client_return_marked_delegations(struct nfs_client *clp) +{ + struct nfs_delegation *delegation; + struct nfs_server *server; + struct inode *inode; + int err = 0; + +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + list_for_each_entry_rcu(delegation, &server->delegations, + super_list) { + if (!nfs_delegation_need_return(delegation)) + continue; + if (!nfs_sb_active(server->super)) + continue; + inode = nfs_delegation_grab_inode(delegation); + if (inode == NULL) { + rcu_read_unlock(); + nfs_sb_deactive(server->super); + goto restart; + } + delegation = nfs_start_delegation_return_locked(NFS_I(inode)); + rcu_read_unlock(); + + err = nfs_end_delegation_return(inode, delegation, 0); + iput(inode); + nfs_sb_deactive(server->super); + if (!err) + goto restart; + set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state); + return err; + } + } + rcu_read_unlock(); + return 0; +} + +/** + * nfs_inode_return_delegation_noreclaim - return delegation, don't reclaim opens + * @inode: inode to process + * + * Does not protect against delegation reclaims, therefore really only safe + * to be called from nfs4_clear_inode(). + */ +void nfs_inode_return_delegation_noreclaim(struct inode *inode) +{ + struct nfs_delegation *delegation; + + delegation = nfs_inode_detach_delegation(inode); + if (delegation != NULL) + nfs_do_return_delegation(inode, delegation, 1); +} + +/** + * nfs_inode_return_delegation - synchronously return a delegation + * @inode: inode to process + * + * This routine will always flush any dirty data to disk on the + * assumption that if we need to return the delegation, then + * we should stop caching. + * + * Returns zero on success, or a negative errno value. + */ +int nfs4_inode_return_delegation(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_delegation *delegation; + int err = 0; + + nfs_wb_all(inode); + delegation = nfs_start_delegation_return(nfsi); + if (delegation != NULL) + err = nfs_end_delegation_return(inode, delegation, 1); + return err; +} + +static void nfs_mark_return_if_closed_delegation(struct nfs_server *server, + struct nfs_delegation *delegation) +{ + set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); + set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); +} + +static void nfs_mark_return_delegation(struct nfs_server *server, + struct nfs_delegation *delegation) +{ + set_bit(NFS_DELEGATION_RETURN, &delegation->flags); + set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); +} + +static bool nfs_server_mark_return_all_delegations(struct nfs_server *server) +{ + struct nfs_delegation *delegation; + bool ret = false; + + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + nfs_mark_return_delegation(server, delegation); + ret = true; + } + return ret; +} + +static void nfs_client_mark_return_all_delegations(struct nfs_client *clp) +{ + struct nfs_server *server; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs_server_mark_return_all_delegations(server); + rcu_read_unlock(); +} + +static void nfs_delegation_run_state_manager(struct nfs_client *clp) +{ + if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) + nfs4_schedule_state_manager(clp); +} + +/** + * nfs_expire_all_delegations + * @clp: client to process + * + */ +void nfs_expire_all_delegations(struct nfs_client *clp) +{ + nfs_client_mark_return_all_delegations(clp); + nfs_delegation_run_state_manager(clp); +} + +/** + * nfs_super_return_all_delegations - return delegations for one superblock + * @sb: sb to process + * + */ +void nfs_server_return_all_delegations(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + bool need_wait; + + if (clp == NULL) + return; + + rcu_read_lock(); + need_wait = nfs_server_mark_return_all_delegations(server); + rcu_read_unlock(); + + if (need_wait) { + nfs4_schedule_state_manager(clp); + nfs4_wait_clnt_recover(clp); + } +} + +static void nfs_mark_return_unused_delegation_types(struct nfs_server *server, + fmode_t flags) +{ + struct nfs_delegation *delegation; + + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE)) + continue; + if (delegation->type & flags) + nfs_mark_return_if_closed_delegation(server, delegation); + } +} + +static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *clp, + fmode_t flags) +{ + struct nfs_server *server; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs_mark_return_unused_delegation_types(server, flags); + rcu_read_unlock(); +} + +static void nfs_revoke_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + nfs_mark_return_delegation(NFS_SERVER(inode), delegation); + } + rcu_read_unlock(); +} + +void nfs_remove_bad_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + + nfs_revoke_delegation(inode); + delegation = nfs_inode_detach_delegation(inode); + if (delegation) { + nfs_inode_find_state_and_recover(inode, &delegation->stateid); + nfs_free_delegation(delegation); + } +} +EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation); + +/** + * nfs_expire_unused_delegation_types + * @clp: client to process + * @flags: delegation types to expire + * + */ +void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags) +{ + nfs_client_mark_return_unused_delegation_types(clp, flags); + nfs_delegation_run_state_manager(clp); +} + +static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server) +{ + struct nfs_delegation *delegation; + + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags)) + continue; + nfs_mark_return_if_closed_delegation(server, delegation); + } +} + +/** + * nfs_expire_unreferenced_delegations - Eliminate unused delegations + * @clp: nfs_client to process + * + */ +void nfs_expire_unreferenced_delegations(struct nfs_client *clp) +{ + struct nfs_server *server; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs_mark_return_unreferenced_delegations(server); + rcu_read_unlock(); + + nfs_delegation_run_state_manager(clp); +} + +/** + * nfs_async_inode_return_delegation - asynchronously return a delegation + * @inode: inode to process + * @stateid: state ID information + * + * Returns zero on success, or a negative errno value. + */ +int nfs_async_inode_return_delegation(struct inode *inode, + const nfs4_stateid *stateid) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + struct nfs_delegation *delegation; + + filemap_flush(inode->i_mapping); + + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation == NULL) + goto out_enoent; + + if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) + goto out_enoent; + nfs_mark_return_delegation(server, delegation); + rcu_read_unlock(); + + nfs_delegation_run_state_manager(clp); + return 0; +out_enoent: + rcu_read_unlock(); + return -ENOENT; +} + +static struct inode * +nfs_delegation_find_inode_server(struct nfs_server *server, + const struct nfs_fh *fhandle) +{ + struct nfs_delegation *delegation; + struct inode *res = NULL; + + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + spin_lock(&delegation->lock); + if (delegation->inode != NULL && + nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) { + res = igrab(delegation->inode); + } + spin_unlock(&delegation->lock); + if (res != NULL) + break; + } + return res; +} + +/** + * nfs_delegation_find_inode - retrieve the inode associated with a delegation + * @clp: client state handle + * @fhandle: filehandle from a delegation recall + * + * Returns pointer to inode matching "fhandle," or NULL if a matching inode + * cannot be found. + */ +struct inode *nfs_delegation_find_inode(struct nfs_client *clp, + const struct nfs_fh *fhandle) +{ + struct nfs_server *server; + struct inode *res = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + res = nfs_delegation_find_inode_server(server, fhandle); + if (res != NULL) + break; + } + rcu_read_unlock(); + return res; +} + +static void nfs_delegation_mark_reclaim_server(struct nfs_server *server) +{ + struct nfs_delegation *delegation; + + list_for_each_entry_rcu(delegation, &server->delegations, super_list) + set_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); +} + +/** + * nfs_delegation_mark_reclaim - mark all delegations as needing to be reclaimed + * @clp: nfs_client to process + * + */ +void nfs_delegation_mark_reclaim(struct nfs_client *clp) +{ + struct nfs_server *server; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs_delegation_mark_reclaim_server(server); + rcu_read_unlock(); +} + +/** + * nfs_delegation_reap_unclaimed - reap unclaimed delegations after reboot recovery is done + * @clp: nfs_client to process + * + */ +void nfs_delegation_reap_unclaimed(struct nfs_client *clp) +{ + struct nfs_delegation *delegation; + struct nfs_server *server; + struct inode *inode; + +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + list_for_each_entry_rcu(delegation, &server->delegations, + super_list) { + if (test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags)) + continue; + if (test_bit(NFS_DELEGATION_NEED_RECLAIM, + &delegation->flags) == 0) + continue; + if (!nfs_sb_active(server->super)) + continue; + inode = nfs_delegation_grab_inode(delegation); + if (inode == NULL) { + rcu_read_unlock(); + nfs_sb_deactive(server->super); + goto restart; + } + delegation = nfs_start_delegation_return_locked(NFS_I(inode)); + rcu_read_unlock(); + if (delegation != NULL) { + delegation = nfs_detach_delegation(NFS_I(inode), + delegation, server); + if (delegation != NULL) + nfs_free_delegation(delegation); + } + iput(inode); + nfs_sb_deactive(server->super); + goto restart; + } + } + rcu_read_unlock(); +} + +/** + * nfs_delegations_present - check for existence of delegations + * @clp: client state handle + * + * Returns one if there are any nfs_delegation structures attached + * to this nfs_client. + */ +int nfs_delegations_present(struct nfs_client *clp) +{ + struct nfs_server *server; + int ret = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + if (!list_empty(&server->delegations)) { + ret = 1; + break; + } + rcu_read_unlock(); + return ret; +} + +/** + * nfs4_copy_delegation_stateid - Copy inode's state ID information + * @dst: stateid data structure to fill in + * @inode: inode to check + * @flags: delegation type requirement + * + * Returns "true" and fills in "dst->data" * if inode had a delegation, + * otherwise "false" is returned. + */ +bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, + fmode_t flags) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_delegation *delegation; + bool ret; + + flags &= FMODE_READ|FMODE_WRITE; + rcu_read_lock(); + delegation = rcu_dereference(nfsi->delegation); + ret = (delegation != NULL && (delegation->type & flags) == flags); + if (ret) { + nfs4_stateid_copy(dst, &delegation->stateid); + nfs_mark_delegation_referenced(delegation); + } + rcu_read_unlock(); + return ret; +} diff --git a/kernel/fs/nfs/delegation.h b/kernel/fs/nfs/delegation.h new file mode 100644 index 000000000..e3c20a3cc --- /dev/null +++ b/kernel/fs/nfs/delegation.h @@ -0,0 +1,73 @@ +/* + * linux/fs/nfs/delegation.h + * + * Copyright (c) Trond Myklebust + * + * Definitions pertaining to NFS delegated files + */ +#ifndef FS_NFS_DELEGATION_H +#define FS_NFS_DELEGATION_H + +#if IS_ENABLED(CONFIG_NFS_V4) +/* + * NFSv4 delegation + */ +struct nfs_delegation { + struct list_head super_list; + struct rpc_cred *cred; + struct inode *inode; + nfs4_stateid stateid; + fmode_t type; + loff_t maxsize; + __u64 change_attr; + unsigned long flags; + spinlock_t lock; + struct rcu_head rcu; +}; + +enum { + NFS_DELEGATION_NEED_RECLAIM = 0, + NFS_DELEGATION_RETURN, + NFS_DELEGATION_RETURN_IF_CLOSED, + NFS_DELEGATION_REFERENCED, + NFS_DELEGATION_RETURNING, + NFS_DELEGATION_REVOKED, +}; + +int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); +void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); +int nfs4_inode_return_delegation(struct inode *inode); +int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid); +void nfs_inode_return_delegation_noreclaim(struct inode *inode); + +struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle); +void nfs_server_return_all_delegations(struct nfs_server *); +void nfs_expire_all_delegations(struct nfs_client *clp); +void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags); +void nfs_expire_unreferenced_delegations(struct nfs_client *clp); +int nfs_client_return_marked_delegations(struct nfs_client *clp); +int nfs_delegations_present(struct nfs_client *clp); +void nfs_remove_bad_delegation(struct inode *inode); + +void nfs_delegation_mark_reclaim(struct nfs_client *clp); +void nfs_delegation_reap_unclaimed(struct nfs_client *clp); + +/* NFSv4 delegation-related procedures */ +int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync); +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid); +int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); +bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags); + +void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); +int nfs4_have_delegation(struct inode *inode, fmode_t flags); +int nfs4_check_delegation(struct inode *inode, fmode_t flags); + +#endif + +static inline int nfs_have_delegated_attributes(struct inode *inode) +{ + return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) && + !(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED); +} + +#endif diff --git a/kernel/fs/nfs/dir.c b/kernel/fs/nfs/dir.c new file mode 100644 index 000000000..b2c8b31b2 --- /dev/null +++ b/kernel/fs/nfs/dir.c @@ -0,0 +1,2520 @@ +/* + * linux/fs/nfs/dir.c + * + * Copyright (C) 1992 Rick Sladkey + * + * nfs directory handling functions + * + * 10 Apr 1996 Added silly rename for unlink --okir + * 28 Sep 1996 Improved directory cache --okir + * 23 Aug 1997 Claus Heine claus@momo.math.rwth-aachen.de + * Re-implemented silly rename for unlink, newly implemented + * silly rename for nfs_rename() following the suggestions + * of Olaf Kirch (okir) found in this file. + * Following Linus comments on my original hack, this version + * depends only on the dcache stuff and doesn't touch the inode + * layer (iput() and friends). + * 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM + */ + +#include <linux/module.h> +#include <linux/time.h> +#include <linux/errno.h> +#include <linux/stat.h> +#include <linux/fcntl.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/pagemap.h> +#include <linux/pagevec.h> +#include <linux/namei.h> +#include <linux/mount.h> +#include <linux/swap.h> +#include <linux/sched.h> +#include <linux/kmemleak.h> +#include <linux/xattr.h> + +#include "delegation.h" +#include "iostat.h" +#include "internal.h" +#include "fscache.h" + +#include "nfstrace.h" + +/* #define NFS_DEBUG_VERBOSE 1 */ + +static int nfs_opendir(struct inode *, struct file *); +static int nfs_closedir(struct inode *, struct file *); +static int nfs_readdir(struct file *, struct dir_context *); +static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); +static loff_t nfs_llseek_dir(struct file *, loff_t, int); +static void nfs_readdir_clear_array(struct page*); + +const struct file_operations nfs_dir_operations = { + .llseek = nfs_llseek_dir, + .read = generic_read_dir, + .iterate = nfs_readdir, + .open = nfs_opendir, + .release = nfs_closedir, + .fsync = nfs_fsync_dir, +}; + +const struct address_space_operations nfs_dir_aops = { + .freepage = nfs_readdir_clear_array, +}; + +static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred) +{ + struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_open_dir_context *ctx; + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (ctx != NULL) { + ctx->duped = 0; + ctx->attr_gencount = nfsi->attr_gencount; + ctx->dir_cookie = 0; + ctx->dup_cookie = 0; + ctx->cred = get_rpccred(cred); + spin_lock(&dir->i_lock); + list_add(&ctx->list, &nfsi->open_files); + spin_unlock(&dir->i_lock); + return ctx; + } + return ERR_PTR(-ENOMEM); +} + +static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx) +{ + spin_lock(&dir->i_lock); + list_del(&ctx->list); + spin_unlock(&dir->i_lock); + put_rpccred(ctx->cred); + kfree(ctx); +} + +/* + * Open file + */ +static int +nfs_opendir(struct inode *inode, struct file *filp) +{ + int res = 0; + struct nfs_open_dir_context *ctx; + struct rpc_cred *cred; + + dfprintk(FILE, "NFS: open dir(%pD2)\n", filp); + + nfs_inc_stats(inode, NFSIOS_VFSOPEN); + + cred = rpc_lookup_cred(); + if (IS_ERR(cred)) + return PTR_ERR(cred); + ctx = alloc_nfs_open_dir_context(inode, cred); + if (IS_ERR(ctx)) { + res = PTR_ERR(ctx); + goto out; + } + filp->private_data = ctx; + if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) { + /* This is a mountpoint, so d_revalidate will never + * have been called, so we need to refresh the + * inode (for close-open consistency) ourselves. + */ + __nfs_revalidate_inode(NFS_SERVER(inode), inode); + } +out: + put_rpccred(cred); + return res; +} + +static int +nfs_closedir(struct inode *inode, struct file *filp) +{ + put_nfs_open_dir_context(file_inode(filp), filp->private_data); + return 0; +} + +struct nfs_cache_array_entry { + u64 cookie; + u64 ino; + struct qstr string; + unsigned char d_type; +}; + +struct nfs_cache_array { + int size; + int eof_index; + u64 last_cookie; + struct nfs_cache_array_entry array[0]; +}; + +typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int); +typedef struct { + struct file *file; + struct page *page; + struct dir_context *ctx; + unsigned long page_index; + u64 *dir_cookie; + u64 last_cookie; + loff_t current_index; + decode_dirent_t decode; + + unsigned long timestamp; + unsigned long gencount; + unsigned int cache_entry_index; + unsigned int plus:1; + unsigned int eof:1; +} nfs_readdir_descriptor_t; + +/* + * The caller is responsible for calling nfs_readdir_release_array(page) + */ +static +struct nfs_cache_array *nfs_readdir_get_array(struct page *page) +{ + void *ptr; + if (page == NULL) + return ERR_PTR(-EIO); + ptr = kmap(page); + if (ptr == NULL) + return ERR_PTR(-ENOMEM); + return ptr; +} + +static +void nfs_readdir_release_array(struct page *page) +{ + kunmap(page); +} + +/* + * we are freeing strings created by nfs_add_to_readdir_array() + */ +static +void nfs_readdir_clear_array(struct page *page) +{ + struct nfs_cache_array *array; + int i; + + array = kmap_atomic(page); + for (i = 0; i < array->size; i++) + kfree(array->array[i].string.name); + kunmap_atomic(array); +} + +/* + * the caller is responsible for freeing qstr.name + * when called by nfs_readdir_add_to_array, the strings will be freed in + * nfs_clear_readdir_array() + */ +static +int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len) +{ + string->len = len; + string->name = kmemdup(name, len, GFP_KERNEL); + if (string->name == NULL) + return -ENOMEM; + /* + * Avoid a kmemleak false positive. The pointer to the name is stored + * in a page cache page which kmemleak does not scan. + */ + kmemleak_not_leak(string->name); + string->hash = full_name_hash(name, len); + return 0; +} + +static +int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) +{ + struct nfs_cache_array *array = nfs_readdir_get_array(page); + struct nfs_cache_array_entry *cache_entry; + int ret; + + if (IS_ERR(array)) + return PTR_ERR(array); + + cache_entry = &array->array[array->size]; + + /* Check that this entry lies within the page bounds */ + ret = -ENOSPC; + if ((char *)&cache_entry[1] - (char *)page_address(page) > PAGE_SIZE) + goto out; + + cache_entry->cookie = entry->prev_cookie; + cache_entry->ino = entry->ino; + cache_entry->d_type = entry->d_type; + ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len); + if (ret) + goto out; + array->last_cookie = entry->cookie; + array->size++; + if (entry->eof != 0) + array->eof_index = array->size; +out: + nfs_readdir_release_array(page); + return ret; +} + +static +int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) +{ + loff_t diff = desc->ctx->pos - desc->current_index; + unsigned int index; + + if (diff < 0) + goto out_eof; + if (diff >= array->size) { + if (array->eof_index >= 0) + goto out_eof; + return -EAGAIN; + } + + index = (unsigned int)diff; + *desc->dir_cookie = array->array[index].cookie; + desc->cache_entry_index = index; + return 0; +out_eof: + desc->eof = 1; + return -EBADCOOKIE; +} + +static bool +nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi) +{ + if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA)) + return false; + smp_rmb(); + return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags); +} + +static +int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) +{ + int i; + loff_t new_pos; + int status = -EAGAIN; + + for (i = 0; i < array->size; i++) { + if (array->array[i].cookie == *desc->dir_cookie) { + struct nfs_inode *nfsi = NFS_I(file_inode(desc->file)); + struct nfs_open_dir_context *ctx = desc->file->private_data; + + new_pos = desc->current_index + i; + if (ctx->attr_gencount != nfsi->attr_gencount || + !nfs_readdir_inode_mapping_valid(nfsi)) { + ctx->duped = 0; + ctx->attr_gencount = nfsi->attr_gencount; + } else if (new_pos < desc->ctx->pos) { + if (ctx->duped > 0 + && ctx->dup_cookie == *desc->dir_cookie) { + if (printk_ratelimit()) { + pr_notice("NFS: directory %pD2 contains a readdir loop." + "Please contact your server vendor. " + "The file: %.*s has duplicate cookie %llu\n", + desc->file, array->array[i].string.len, + array->array[i].string.name, *desc->dir_cookie); + } + status = -ELOOP; + goto out; + } + ctx->dup_cookie = *desc->dir_cookie; + ctx->duped = -1; + } + desc->ctx->pos = new_pos; + desc->cache_entry_index = i; + return 0; + } + } + if (array->eof_index >= 0) { + status = -EBADCOOKIE; + if (*desc->dir_cookie == array->last_cookie) + desc->eof = 1; + } +out: + return status; +} + +static +int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc) +{ + struct nfs_cache_array *array; + int status; + + array = nfs_readdir_get_array(desc->page); + if (IS_ERR(array)) { + status = PTR_ERR(array); + goto out; + } + + if (*desc->dir_cookie == 0) + status = nfs_readdir_search_for_pos(array, desc); + else + status = nfs_readdir_search_for_cookie(array, desc); + + if (status == -EAGAIN) { + desc->last_cookie = array->last_cookie; + desc->current_index += array->size; + desc->page_index++; + } + nfs_readdir_release_array(desc->page); +out: + return status; +} + +/* Fill a page with xdr information before transferring to the cache page */ +static +int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, + struct nfs_entry *entry, struct file *file, struct inode *inode) +{ + struct nfs_open_dir_context *ctx = file->private_data; + struct rpc_cred *cred = ctx->cred; + unsigned long timestamp, gencount; + int error; + + again: + timestamp = jiffies; + gencount = nfs_inc_attr_generation_counter(); + error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages, + NFS_SERVER(inode)->dtsize, desc->plus); + if (error < 0) { + /* We requested READDIRPLUS, but the server doesn't grok it */ + if (error == -ENOTSUPP && desc->plus) { + NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; + clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); + desc->plus = 0; + goto again; + } + goto error; + } + desc->timestamp = timestamp; + desc->gencount = gencount; +error: + return error; +} + +static int xdr_decode(nfs_readdir_descriptor_t *desc, + struct nfs_entry *entry, struct xdr_stream *xdr) +{ + int error; + + error = desc->decode(xdr, entry, desc->plus); + if (error) + return error; + entry->fattr->time_start = desc->timestamp; + entry->fattr->gencount = desc->gencount; + return 0; +} + +/* Match file and dirent using either filehandle or fileid + * Note: caller is responsible for checking the fsid + */ +static +int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) +{ + struct nfs_inode *nfsi; + + if (d_really_is_negative(dentry)) + return 0; + + nfsi = NFS_I(d_inode(dentry)); + if (entry->fattr->fileid == nfsi->fileid) + return 1; + if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0) + return 1; + return 0; +} + +static +bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx) +{ + if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) + return false; + if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags)) + return true; + if (ctx->pos == 0) + return true; + return false; +} + +/* + * This function is called by the lookup code to request the use of + * readdirplus to accelerate any future lookups in the same + * directory. + */ +static +void nfs_advise_use_readdirplus(struct inode *dir) +{ + set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags); +} + +/* + * This function is mainly for use by nfs_getattr(). + * + * If this is an 'ls -l', we want to force use of readdirplus. + * Do this by checking if there is an active file descriptor + * and calling nfs_advise_use_readdirplus, then forcing a + * cache flush. + */ +void nfs_force_use_readdirplus(struct inode *dir) +{ + if (!list_empty(&NFS_I(dir)->open_files)) { + nfs_advise_use_readdirplus(dir); + nfs_zap_mapping(dir, dir->i_mapping); + } +} + +static +void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) +{ + struct qstr filename = QSTR_INIT(entry->name, entry->len); + struct dentry *dentry; + struct dentry *alias; + struct inode *dir = d_inode(parent); + struct inode *inode; + int status; + + if (!(entry->fattr->valid & NFS_ATTR_FATTR_FILEID)) + return; + if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID)) + return; + if (filename.name[0] == '.') { + if (filename.len == 1) + return; + if (filename.len == 2 && filename.name[1] == '.') + return; + } + filename.hash = full_name_hash(filename.name, filename.len); + + dentry = d_lookup(parent, &filename); + if (dentry != NULL) { + /* Is there a mountpoint here? If so, just exit */ + if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid, + &entry->fattr->fsid)) + goto out; + if (nfs_same_file(dentry, entry)) { + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + status = nfs_refresh_inode(d_inode(dentry), entry->fattr); + if (!status) + nfs_setsecurity(d_inode(dentry), entry->fattr, entry->label); + goto out; + } else { + d_invalidate(dentry); + dput(dentry); + } + } + + dentry = d_alloc(parent, &filename); + if (dentry == NULL) + return; + + inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label); + if (IS_ERR(inode)) + goto out; + + alias = d_splice_alias(inode, dentry); + if (IS_ERR(alias)) + goto out; + else if (alias) { + nfs_set_verifier(alias, nfs_save_change_attribute(dir)); + dput(alias); + } else + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + +out: + dput(dentry); +} + +/* Perform conversion from xdr to cache array */ +static +int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, + struct page **xdr_pages, struct page *page, unsigned int buflen) +{ + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + struct nfs_cache_array *array; + unsigned int count = 0; + int status; + + scratch = alloc_page(GFP_KERNEL); + if (scratch == NULL) + return -ENOMEM; + + if (buflen == 0) + goto out_nopages; + + xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + do { + status = xdr_decode(desc, entry, &stream); + if (status != 0) { + if (status == -EAGAIN) + status = 0; + break; + } + + count++; + + if (desc->plus != 0) + nfs_prime_dcache(desc->file->f_path.dentry, entry); + + status = nfs_readdir_add_to_array(entry, page); + if (status != 0) + break; + } while (!entry->eof); + +out_nopages: + if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) { + array = nfs_readdir_get_array(page); + if (!IS_ERR(array)) { + array->eof_index = array->size; + status = 0; + nfs_readdir_release_array(page); + } else + status = PTR_ERR(array); + } + + put_page(scratch); + return status; +} + +static +void nfs_readdir_free_pagearray(struct page **pages, unsigned int npages) +{ + unsigned int i; + for (i = 0; i < npages; i++) + put_page(pages[i]); +} + +static +void nfs_readdir_free_large_page(void *ptr, struct page **pages, + unsigned int npages) +{ + nfs_readdir_free_pagearray(pages, npages); +} + +/* + * nfs_readdir_large_page will allocate pages that must be freed with a call + * to nfs_readdir_free_large_page + */ +static +int nfs_readdir_large_page(struct page **pages, unsigned int npages) +{ + unsigned int i; + + for (i = 0; i < npages; i++) { + struct page *page = alloc_page(GFP_KERNEL); + if (page == NULL) + goto out_freepages; + pages[i] = page; + } + return 0; + +out_freepages: + nfs_readdir_free_pagearray(pages, i); + return -ENOMEM; +} + +static +int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode) +{ + struct page *pages[NFS_MAX_READDIR_PAGES]; + void *pages_ptr = NULL; + struct nfs_entry entry; + struct file *file = desc->file; + struct nfs_cache_array *array; + int status = -ENOMEM; + unsigned int array_size = ARRAY_SIZE(pages); + + entry.prev_cookie = 0; + entry.cookie = desc->last_cookie; + entry.eof = 0; + entry.fh = nfs_alloc_fhandle(); + entry.fattr = nfs_alloc_fattr(); + entry.server = NFS_SERVER(inode); + if (entry.fh == NULL || entry.fattr == NULL) + goto out; + + entry.label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT); + if (IS_ERR(entry.label)) { + status = PTR_ERR(entry.label); + goto out; + } + + array = nfs_readdir_get_array(page); + if (IS_ERR(array)) { + status = PTR_ERR(array); + goto out_label_free; + } + memset(array, 0, sizeof(struct nfs_cache_array)); + array->eof_index = -1; + + status = nfs_readdir_large_page(pages, array_size); + if (status < 0) + goto out_release_array; + do { + unsigned int pglen; + status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode); + + if (status < 0) + break; + pglen = status; + status = nfs_readdir_page_filler(desc, &entry, pages, page, pglen); + if (status < 0) { + if (status == -ENOSPC) + status = 0; + break; + } + } while (array->eof_index < 0); + + nfs_readdir_free_large_page(pages_ptr, pages, array_size); +out_release_array: + nfs_readdir_release_array(page); +out_label_free: + nfs4_label_free(entry.label); +out: + nfs_free_fattr(entry.fattr); + nfs_free_fhandle(entry.fh); + return status; +} + +/* + * Now we cache directories properly, by converting xdr information + * to an array that can be used for lookups later. This results in + * fewer cache pages, since we can store more information on each page. + * We only need to convert from xdr once so future lookups are much simpler + */ +static +int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) +{ + struct inode *inode = file_inode(desc->file); + int ret; + + ret = nfs_readdir_xdr_to_array(desc, page, inode); + if (ret < 0) + goto error; + SetPageUptodate(page); + + if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { + /* Should never happen */ + nfs_zap_mapping(inode, inode->i_mapping); + } + unlock_page(page); + return 0; + error: + unlock_page(page); + return ret; +} + +static +void cache_page_release(nfs_readdir_descriptor_t *desc) +{ + if (!desc->page->mapping) + nfs_readdir_clear_array(desc->page); + page_cache_release(desc->page); + desc->page = NULL; +} + +static +struct page *get_cache_page(nfs_readdir_descriptor_t *desc) +{ + return read_cache_page(file_inode(desc->file)->i_mapping, + desc->page_index, (filler_t *)nfs_readdir_filler, desc); +} + +/* + * Returns 0 if desc->dir_cookie was found on page desc->page_index + */ +static +int find_cache_page(nfs_readdir_descriptor_t *desc) +{ + int res; + + desc->page = get_cache_page(desc); + if (IS_ERR(desc->page)) + return PTR_ERR(desc->page); + + res = nfs_readdir_search_array(desc); + if (res != 0) + cache_page_release(desc); + return res; +} + +/* Search for desc->dir_cookie from the beginning of the page cache */ +static inline +int readdir_search_pagecache(nfs_readdir_descriptor_t *desc) +{ + int res; + + if (desc->page_index == 0) { + desc->current_index = 0; + desc->last_cookie = 0; + } + do { + res = find_cache_page(desc); + } while (res == -EAGAIN); + return res; +} + +/* + * Once we've found the start of the dirent within a page: fill 'er up... + */ +static +int nfs_do_filldir(nfs_readdir_descriptor_t *desc) +{ + struct file *file = desc->file; + int i = 0; + int res = 0; + struct nfs_cache_array *array = NULL; + struct nfs_open_dir_context *ctx = file->private_data; + + array = nfs_readdir_get_array(desc->page); + if (IS_ERR(array)) { + res = PTR_ERR(array); + goto out; + } + + for (i = desc->cache_entry_index; i < array->size; i++) { + struct nfs_cache_array_entry *ent; + + ent = &array->array[i]; + if (!dir_emit(desc->ctx, ent->string.name, ent->string.len, + nfs_compat_user_ino64(ent->ino), ent->d_type)) { + desc->eof = 1; + break; + } + desc->ctx->pos++; + if (i < (array->size-1)) + *desc->dir_cookie = array->array[i+1].cookie; + else + *desc->dir_cookie = array->last_cookie; + if (ctx->duped != 0) + ctx->duped = 1; + } + if (array->eof_index >= 0) + desc->eof = 1; + + nfs_readdir_release_array(desc->page); +out: + cache_page_release(desc); + dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n", + (unsigned long long)*desc->dir_cookie, res); + return res; +} + +/* + * If we cannot find a cookie in our cache, we suspect that this is + * because it points to a deleted file, so we ask the server to return + * whatever it thinks is the next entry. We then feed this to filldir. + * If all goes well, we should then be able to find our way round the + * cache on the next call to readdir_search_pagecache(); + * + * NOTE: we cannot add the anonymous page to the pagecache because + * the data it contains might not be page aligned. Besides, + * we should already have a complete representation of the + * directory in the page cache by the time we get here. + */ +static inline +int uncached_readdir(nfs_readdir_descriptor_t *desc) +{ + struct page *page = NULL; + int status; + struct inode *inode = file_inode(desc->file); + struct nfs_open_dir_context *ctx = desc->file->private_data; + + dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n", + (unsigned long long)*desc->dir_cookie); + + page = alloc_page(GFP_HIGHUSER); + if (!page) { + status = -ENOMEM; + goto out; + } + + desc->page_index = 0; + desc->last_cookie = *desc->dir_cookie; + desc->page = page; + ctx->duped = 0; + + status = nfs_readdir_xdr_to_array(desc, page, inode); + if (status < 0) + goto out_release; + + status = nfs_do_filldir(desc); + + out: + dfprintk(DIRCACHE, "NFS: %s: returns %d\n", + __func__, status); + return status; + out_release: + cache_page_release(desc); + goto out; +} + +static bool nfs_dir_mapping_need_revalidate(struct inode *dir) +{ + struct nfs_inode *nfsi = NFS_I(dir); + + if (nfs_attribute_cache_expired(dir)) + return true; + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + return true; + return false; +} + +/* The file offset position represents the dirent entry number. A + last cookie cache takes care of the common case of reading the + whole directory. + */ +static int nfs_readdir(struct file *file, struct dir_context *ctx) +{ + struct dentry *dentry = file->f_path.dentry; + struct inode *inode = d_inode(dentry); + nfs_readdir_descriptor_t my_desc, + *desc = &my_desc; + struct nfs_open_dir_context *dir_ctx = file->private_data; + int res = 0; + + dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", + file, (long long)ctx->pos); + nfs_inc_stats(inode, NFSIOS_VFSGETDENTS); + + /* + * ctx->pos points to the dirent entry number. + * *desc->dir_cookie has the cookie for the next entry. We have + * to either find the entry with the appropriate number or + * revalidate the cookie. + */ + memset(desc, 0, sizeof(*desc)); + + desc->file = file; + desc->ctx = ctx; + desc->dir_cookie = &dir_ctx->dir_cookie; + desc->decode = NFS_PROTO(inode)->decode_dirent; + desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0; + + nfs_block_sillyrename(dentry); + if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode)) + res = nfs_revalidate_mapping(inode, file->f_mapping); + if (res < 0) + goto out; + + do { + res = readdir_search_pagecache(desc); + + if (res == -EBADCOOKIE) { + res = 0; + /* This means either end of directory */ + if (*desc->dir_cookie && desc->eof == 0) { + /* Or that the server has 'lost' a cookie */ + res = uncached_readdir(desc); + if (res == 0) + continue; + } + break; + } + if (res == -ETOOSMALL && desc->plus) { + clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); + nfs_zap_caches(inode); + desc->page_index = 0; + desc->plus = 0; + desc->eof = 0; + continue; + } + if (res < 0) + break; + + res = nfs_do_filldir(desc); + if (res < 0) + break; + } while (!desc->eof); +out: + nfs_unblock_sillyrename(dentry); + if (res > 0) + res = 0; + dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res); + return res; +} + +static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) +{ + struct inode *inode = file_inode(filp); + struct nfs_open_dir_context *dir_ctx = filp->private_data; + + dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", + filp, offset, whence); + + mutex_lock(&inode->i_mutex); + switch (whence) { + case 1: + offset += filp->f_pos; + case 0: + if (offset >= 0) + break; + default: + offset = -EINVAL; + goto out; + } + if (offset != filp->f_pos) { + filp->f_pos = offset; + dir_ctx->dir_cookie = 0; + dir_ctx->duped = 0; + } +out: + mutex_unlock(&inode->i_mutex); + return offset; +} + +/* + * All directory operations under NFS are synchronous, so fsync() + * is a dummy operation. + */ +static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, + int datasync) +{ + struct inode *inode = file_inode(filp); + + dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync); + + mutex_lock(&inode->i_mutex); + nfs_inc_stats(inode, NFSIOS_VFSFSYNC); + mutex_unlock(&inode->i_mutex); + return 0; +} + +/** + * nfs_force_lookup_revalidate - Mark the directory as having changed + * @dir - pointer to directory inode + * + * This forces the revalidation code in nfs_lookup_revalidate() to do a + * full lookup on all child dentries of 'dir' whenever a change occurs + * on the server that might have invalidated our dcache. + * + * The caller should be holding dir->i_lock + */ +void nfs_force_lookup_revalidate(struct inode *dir) +{ + NFS_I(dir)->cache_change_attribute++; +} +EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate); + +/* + * A check for whether or not the parent directory has changed. + * In the case it has, we assume that the dentries are untrustworthy + * and may need to be looked up again. + * If rcu_walk prevents us from performing a full check, return 0. + */ +static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, + int rcu_walk) +{ + int ret; + + if (IS_ROOT(dentry)) + return 1; + if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) + return 0; + if (!nfs_verify_change_attribute(dir, dentry->d_time)) + return 0; + /* Revalidate nfsi->cache_change_attribute before we declare a match */ + if (rcu_walk) + ret = nfs_revalidate_inode_rcu(NFS_SERVER(dir), dir); + else + ret = nfs_revalidate_inode(NFS_SERVER(dir), dir); + if (ret < 0) + return 0; + if (!nfs_verify_change_attribute(dir, dentry->d_time)) + return 0; + return 1; +} + +/* + * Use intent information to check whether or not we're going to do + * an O_EXCL create using this path component. + */ +static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags) +{ + if (NFS_PROTO(dir)->version == 2) + return 0; + return flags & LOOKUP_EXCL; +} + +/* + * Inode and filehandle revalidation for lookups. + * + * We force revalidation in the cases where the VFS sets LOOKUP_REVAL, + * or if the intent information indicates that we're about to open this + * particular file and the "nocto" mount flag is not set. + * + */ +static +int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) +{ + struct nfs_server *server = NFS_SERVER(inode); + int ret; + + if (IS_AUTOMOUNT(inode)) + return 0; + /* VFS wants an on-the-wire revalidation */ + if (flags & LOOKUP_REVAL) + goto out_force; + /* This is an open(2) */ + if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) + goto out_force; +out: + return (inode->i_nlink == 0) ? -ENOENT : 0; +out_force: + if (flags & LOOKUP_RCU) + return -ECHILD; + ret = __nfs_revalidate_inode(server, inode); + if (ret != 0) + return ret; + goto out; +} + +/* + * We judge how long we want to trust negative + * dentries by looking at the parent inode mtime. + * + * If parent mtime has changed, we revalidate, else we wait for a + * period corresponding to the parent's attribute cache timeout value. + * + * If LOOKUP_RCU prevents us from performing a full check, return 1 + * suggesting a reval is needed. + */ +static inline +int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + /* Don't revalidate a negative dentry if we're creating a new file */ + if (flags & LOOKUP_CREATE) + return 0; + if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) + return 1; + return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU); +} + +/* + * This is called every time the dcache has a lookup hit, + * and we should check whether we can really trust that + * lookup. + * + * NOTE! The hit can be a negative hit too, don't assume + * we have an inode! + * + * If the parent directory is seen to have changed, we throw out the + * cached dentry and do a new lookup. + */ +static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct inode *dir; + struct inode *inode; + struct dentry *parent; + struct nfs_fh *fhandle = NULL; + struct nfs_fattr *fattr = NULL; + struct nfs4_label *label = NULL; + int error; + + if (flags & LOOKUP_RCU) { + parent = ACCESS_ONCE(dentry->d_parent); + dir = d_inode_rcu(parent); + if (!dir) + return -ECHILD; + } else { + parent = dget_parent(dentry); + dir = d_inode(parent); + } + nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE); + inode = d_inode(dentry); + + if (!inode) { + if (nfs_neg_need_reval(dir, dentry, flags)) { + if (flags & LOOKUP_RCU) + return -ECHILD; + goto out_bad; + } + goto out_valid_noent; + } + + if (is_bad_inode(inode)) { + if (flags & LOOKUP_RCU) + return -ECHILD; + dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n", + __func__, dentry); + goto out_bad; + } + + if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) + goto out_set_verifier; + + /* Force a full look up iff the parent directory has changed */ + if (!nfs_is_exclusive_create(dir, flags) && + nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { + + if (nfs_lookup_verify_inode(inode, flags)) { + if (flags & LOOKUP_RCU) + return -ECHILD; + goto out_zap_parent; + } + goto out_valid; + } + + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (NFS_STALE(inode)) + goto out_bad; + + error = -ENOMEM; + fhandle = nfs_alloc_fhandle(); + fattr = nfs_alloc_fattr(); + if (fhandle == NULL || fattr == NULL) + goto out_error; + + label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT); + if (IS_ERR(label)) + goto out_error; + + trace_nfs_lookup_revalidate_enter(dir, dentry, flags); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); + if (error) + goto out_bad; + if (nfs_compare_fh(NFS_FH(inode), fhandle)) + goto out_bad; + if ((error = nfs_refresh_inode(inode, fattr)) != 0) + goto out_bad; + + nfs_setsecurity(inode, fattr, label); + + nfs_free_fattr(fattr); + nfs_free_fhandle(fhandle); + nfs4_label_free(label); + +out_set_verifier: + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + out_valid: + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + out_valid_noent: + if (flags & LOOKUP_RCU) { + if (parent != ACCESS_ONCE(dentry->d_parent)) + return -ECHILD; + } else + dput(parent); + dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n", + __func__, dentry); + return 1; +out_zap_parent: + nfs_zap_caches(dir); + out_bad: + WARN_ON(flags & LOOKUP_RCU); + nfs_free_fattr(fattr); + nfs_free_fhandle(fhandle); + nfs4_label_free(label); + nfs_mark_for_revalidate(dir); + if (inode && S_ISDIR(inode->i_mode)) { + /* Purge readdir caches. */ + nfs_zap_caches(inode); + /* + * We can't d_drop the root of a disconnected tree: + * its d_hash is on the s_anon list and d_drop() would hide + * it from shrink_dcache_for_unmount(), leading to busy + * inodes on unmount and further oopses. + */ + if (IS_ROOT(dentry)) + goto out_valid; + } + dput(parent); + dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n", + __func__, dentry); + return 0; +out_error: + WARN_ON(flags & LOOKUP_RCU); + nfs_free_fattr(fattr); + nfs_free_fhandle(fhandle); + nfs4_label_free(label); + dput(parent); + dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n", + __func__, dentry, error); + return error; +} + +/* + * A weaker form of d_revalidate for revalidating just the d_inode(dentry) + * when we don't really care about the dentry name. This is called when a + * pathwalk ends on a dentry that was not found via a normal lookup in the + * parent dir (e.g.: ".", "..", procfs symlinks or mountpoint traversals). + * + * In this situation, we just want to verify that the inode itself is OK + * since the dentry might have changed on the server. + */ +static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags) +{ + int error; + struct inode *inode = d_inode(dentry); + + /* + * I believe we can only get a negative dentry here in the case of a + * procfs-style symlink. Just assume it's correct for now, but we may + * eventually need to do something more here. + */ + if (!inode) { + dfprintk(LOOKUPCACHE, "%s: %pd2 has negative inode\n", + __func__, dentry); + return 1; + } + + if (is_bad_inode(inode)) { + dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n", + __func__, dentry); + return 0; + } + + error = nfs_revalidate_inode(NFS_SERVER(inode), inode); + dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n", + __func__, inode->i_ino, error ? "invalid" : "valid"); + return !error; +} + +/* + * This is called from dput() when d_count is going to 0. + */ +static int nfs_dentry_delete(const struct dentry *dentry) +{ + dfprintk(VFS, "NFS: dentry_delete(%pd2, %x)\n", + dentry, dentry->d_flags); + + /* Unhash any dentry with a stale inode */ + if (d_really_is_positive(dentry) && NFS_STALE(d_inode(dentry))) + return 1; + + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + /* Unhash it, so that ->d_iput() would be called */ + return 1; + } + if (!(dentry->d_sb->s_flags & MS_ACTIVE)) { + /* Unhash it, so that ancestors of killed async unlink + * files will be cleaned up during umount */ + return 1; + } + return 0; + +} + +/* Ensure that we revalidate inode->i_nlink */ +static void nfs_drop_nlink(struct inode *inode) +{ + spin_lock(&inode->i_lock); + /* drop the inode if we're reasonably sure this is the last link */ + if (inode->i_nlink == 1) + clear_nlink(inode); + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR; + spin_unlock(&inode->i_lock); +} + +/* + * Called when the dentry loses inode. + * We use it to clean up silly-renamed files. + */ +static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) +{ + if (S_ISDIR(inode->i_mode)) + /* drop any readdir cache as it could easily be old */ + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA; + + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + nfs_complete_unlink(dentry, inode); + nfs_drop_nlink(inode); + } + iput(inode); +} + +static void nfs_d_release(struct dentry *dentry) +{ + /* free cached devname value, if it survived that far */ + if (unlikely(dentry->d_fsdata)) { + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + WARN_ON(1); + else + kfree(dentry->d_fsdata); + } +} + +const struct dentry_operations nfs_dentry_operations = { + .d_revalidate = nfs_lookup_revalidate, + .d_weak_revalidate = nfs_weak_revalidate, + .d_delete = nfs_dentry_delete, + .d_iput = nfs_dentry_iput, + .d_automount = nfs_d_automount, + .d_release = nfs_d_release, +}; +EXPORT_SYMBOL_GPL(nfs_dentry_operations); + +struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) +{ + struct dentry *res; + struct dentry *parent; + struct inode *inode = NULL; + struct nfs_fh *fhandle = NULL; + struct nfs_fattr *fattr = NULL; + struct nfs4_label *label = NULL; + int error; + + dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry); + nfs_inc_stats(dir, NFSIOS_VFSLOOKUP); + + res = ERR_PTR(-ENAMETOOLONG); + if (dentry->d_name.len > NFS_SERVER(dir)->namelen) + goto out; + + /* + * If we're doing an exclusive create, optimize away the lookup + * but don't hash the dentry. + */ + if (nfs_is_exclusive_create(dir, flags)) { + d_instantiate(dentry, NULL); + res = NULL; + goto out; + } + + res = ERR_PTR(-ENOMEM); + fhandle = nfs_alloc_fhandle(); + fattr = nfs_alloc_fattr(); + if (fhandle == NULL || fattr == NULL) + goto out; + + label = nfs4_label_alloc(NFS_SERVER(dir), GFP_NOWAIT); + if (IS_ERR(label)) + goto out; + + parent = dentry->d_parent; + /* Protect against concurrent sillydeletes */ + trace_nfs_lookup_enter(dir, dentry, flags); + nfs_block_sillyrename(parent); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + if (error == -ENOENT) + goto no_entry; + if (error < 0) { + res = ERR_PTR(error); + goto out_unblock_sillyrename; + } + inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); + res = ERR_CAST(inode); + if (IS_ERR(res)) + goto out_unblock_sillyrename; + + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + +no_entry: + res = d_splice_alias(inode, dentry); + if (res != NULL) { + if (IS_ERR(res)) + goto out_unblock_sillyrename; + dentry = res; + } + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); +out_unblock_sillyrename: + nfs_unblock_sillyrename(parent); + trace_nfs_lookup_exit(dir, dentry, flags, error); + nfs4_label_free(label); +out: + nfs_free_fattr(fattr); + nfs_free_fhandle(fhandle); + return res; +} +EXPORT_SYMBOL_GPL(nfs_lookup); + +#if IS_ENABLED(CONFIG_NFS_V4) +static int nfs4_lookup_revalidate(struct dentry *, unsigned int); + +const struct dentry_operations nfs4_dentry_operations = { + .d_revalidate = nfs4_lookup_revalidate, + .d_delete = nfs_dentry_delete, + .d_iput = nfs_dentry_iput, + .d_automount = nfs_d_automount, + .d_release = nfs_d_release, +}; +EXPORT_SYMBOL_GPL(nfs4_dentry_operations); + +static fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + +static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags) +{ + return alloc_nfs_open_context(dentry, flags_to_mode(open_flags)); +} + +static int do_open(struct inode *inode, struct file *filp) +{ + nfs_fscache_open_file(inode, filp); + return 0; +} + +static int nfs_finish_open(struct nfs_open_context *ctx, + struct dentry *dentry, + struct file *file, unsigned open_flags, + int *opened) +{ + int err; + + if ((open_flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + *opened |= FILE_CREATED; + + err = finish_open(file, dentry, do_open, opened); + if (err) + goto out; + nfs_file_set_open_context(file, ctx); + +out: + return err; +} + +int nfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned open_flags, + umode_t mode, int *opened) +{ + struct nfs_open_context *ctx; + struct dentry *res; + struct iattr attr = { .ia_valid = ATTR_OPEN }; + struct inode *inode; + unsigned int lookup_flags = 0; + int err; + + /* Expect a negative dentry */ + BUG_ON(d_inode(dentry)); + + dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n", + dir->i_sb->s_id, dir->i_ino, dentry); + + err = nfs_check_flags(open_flags); + if (err) + return err; + + /* NFS only supports OPEN on regular files */ + if ((open_flags & O_DIRECTORY)) { + if (!d_unhashed(dentry)) { + /* + * Hashed negative dentry with O_DIRECTORY: dentry was + * revalidated and is fine, no need to perform lookup + * again + */ + return -ENOENT; + } + lookup_flags = LOOKUP_OPEN|LOOKUP_DIRECTORY; + goto no_open; + } + + if (dentry->d_name.len > NFS_SERVER(dir)->namelen) + return -ENAMETOOLONG; + + if (open_flags & O_CREAT) { + attr.ia_valid |= ATTR_MODE; + attr.ia_mode = mode & ~current_umask(); + } + if (open_flags & O_TRUNC) { + attr.ia_valid |= ATTR_SIZE; + attr.ia_size = 0; + } + + ctx = create_nfs_open_context(dentry, open_flags); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + + trace_nfs_atomic_open_enter(dir, ctx, open_flags); + nfs_block_sillyrename(dentry->d_parent); + inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened); + nfs_unblock_sillyrename(dentry->d_parent); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); + put_nfs_open_context(ctx); + switch (err) { + case -ENOENT: + d_drop(dentry); + d_add(dentry, NULL); + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + break; + case -EISDIR: + case -ENOTDIR: + goto no_open; + case -ELOOP: + if (!(open_flags & O_NOFOLLOW)) + goto no_open; + break; + /* case -EINVAL: */ + default: + break; + } + goto out; + } + + err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened); + trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); + put_nfs_open_context(ctx); +out: + return err; + +no_open: + res = nfs_lookup(dir, dentry, lookup_flags); + err = PTR_ERR(res); + if (IS_ERR(res)) + goto out; + + return finish_no_open(file, res); +} +EXPORT_SYMBOL_GPL(nfs_atomic_open); + +static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct inode *inode; + int ret = 0; + + if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) + goto no_open; + if (d_mountpoint(dentry)) + goto no_open; + if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1) + goto no_open; + + inode = d_inode(dentry); + + /* We can't create new files in nfs_open_revalidate(), so we + * optimize away revalidation of negative dentries. + */ + if (inode == NULL) { + struct dentry *parent; + struct inode *dir; + + if (flags & LOOKUP_RCU) { + parent = ACCESS_ONCE(dentry->d_parent); + dir = d_inode_rcu(parent); + if (!dir) + return -ECHILD; + } else { + parent = dget_parent(dentry); + dir = d_inode(parent); + } + if (!nfs_neg_need_reval(dir, dentry, flags)) + ret = 1; + else if (flags & LOOKUP_RCU) + ret = -ECHILD; + if (!(flags & LOOKUP_RCU)) + dput(parent); + else if (parent != ACCESS_ONCE(dentry->d_parent)) + return -ECHILD; + goto out; + } + + /* NFS only supports OPEN on regular files */ + if (!S_ISREG(inode->i_mode)) + goto no_open; + /* We cannot do exclusive creation on a positive dentry */ + if (flags & LOOKUP_EXCL) + goto no_open; + + /* Let f_op->open() actually open (and revalidate) the file */ + ret = 1; + +out: + return ret; + +no_open: + return nfs_lookup_revalidate(dentry, flags); +} + +#endif /* CONFIG_NFSV4 */ + +/* + * Code common to create, mkdir, and mknod. + */ +int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + struct dentry *parent = dget_parent(dentry); + struct inode *dir = d_inode(parent); + struct inode *inode; + int error = -EACCES; + + d_drop(dentry); + + /* We may have been initialized further down */ + if (d_really_is_positive(dentry)) + goto out; + if (fhandle->size == 0) { + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, NULL); + if (error) + goto out_error; + } + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + if (!(fattr->valid & NFS_ATTR_FATTR)) { + struct nfs_server *server = NFS_SB(dentry->d_sb); + error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr, NULL); + if (error < 0) + goto out_error; + } + inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); + error = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out_error; + d_add(dentry, inode); +out: + dput(parent); + return 0; +out_error: + nfs_mark_for_revalidate(dir); + dput(parent); + return error; +} +EXPORT_SYMBOL_GPL(nfs_instantiate); + +/* + * Following a failed create operation, we drop the dentry rather + * than retain a negative dentry. This avoids a problem in the event + * that the operation succeeded on the server, but an error in the + * reply path made it appear to have failed. + */ +int nfs_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool excl) +{ + struct iattr attr; + int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT; + int error; + + dfprintk(VFS, "NFS: create(%s/%lu), %pd\n", + dir->i_sb->s_id, dir->i_ino, dentry); + + attr.ia_mode = mode; + attr.ia_valid = ATTR_MODE; + + trace_nfs_create_enter(dir, dentry, open_flags); + error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); + trace_nfs_create_exit(dir, dentry, open_flags, error); + if (error != 0) + goto out_err; + return 0; +out_err: + d_drop(dentry); + return error; +} +EXPORT_SYMBOL_GPL(nfs_create); + +/* + * See comments for nfs_proc_create regarding failed operations. + */ +int +nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) +{ + struct iattr attr; + int status; + + dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n", + dir->i_sb->s_id, dir->i_ino, dentry); + + if (!new_valid_dev(rdev)) + return -EINVAL; + + attr.ia_mode = mode; + attr.ia_valid = ATTR_MODE; + + trace_nfs_mknod_enter(dir, dentry); + status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev); + trace_nfs_mknod_exit(dir, dentry, status); + if (status != 0) + goto out_err; + return 0; +out_err: + d_drop(dentry); + return status; +} +EXPORT_SYMBOL_GPL(nfs_mknod); + +/* + * See comments for nfs_proc_create regarding failed operations. + */ +int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct iattr attr; + int error; + + dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n", + dir->i_sb->s_id, dir->i_ino, dentry); + + attr.ia_valid = ATTR_MODE; + attr.ia_mode = mode | S_IFDIR; + + trace_nfs_mkdir_enter(dir, dentry); + error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr); + trace_nfs_mkdir_exit(dir, dentry, error); + if (error != 0) + goto out_err; + return 0; +out_err: + d_drop(dentry); + return error; +} +EXPORT_SYMBOL_GPL(nfs_mkdir); + +static void nfs_dentry_handle_enoent(struct dentry *dentry) +{ + if (d_really_is_positive(dentry) && !d_unhashed(dentry)) + d_delete(dentry); +} + +int nfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + int error; + + dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n", + dir->i_sb->s_id, dir->i_ino, dentry); + + trace_nfs_rmdir_enter(dir, dentry); + if (d_really_is_positive(dentry)) { + nfs_wait_on_sillyrename(dentry); + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + /* Ensure the VFS deletes this inode */ + switch (error) { + case 0: + clear_nlink(d_inode(dentry)); + break; + case -ENOENT: + nfs_dentry_handle_enoent(dentry); + } + } else + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + trace_nfs_rmdir_exit(dir, dentry, error); + + return error; +} +EXPORT_SYMBOL_GPL(nfs_rmdir); + +/* + * Remove a file after making sure there are no pending writes, + * and after checking that the file has only one user. + * + * We invalidate the attribute cache and free the inode prior to the operation + * to avoid possible races if the server reuses the inode. + */ +static int nfs_safe_remove(struct dentry *dentry) +{ + struct inode *dir = d_inode(dentry->d_parent); + struct inode *inode = d_inode(dentry); + int error = -EBUSY; + + dfprintk(VFS, "NFS: safe_remove(%pd2)\n", dentry); + + /* If the dentry was sillyrenamed, we simply call d_delete() */ + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + error = 0; + goto out; + } + + trace_nfs_remove_enter(dir, dentry); + if (inode != NULL) { + NFS_PROTO(inode)->return_delegation(inode); + error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); + if (error == 0) + nfs_drop_nlink(inode); + } else + error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); + if (error == -ENOENT) + nfs_dentry_handle_enoent(dentry); + trace_nfs_remove_exit(dir, dentry, error); +out: + return error; +} + +/* We do silly rename. In case sillyrename() returns -EBUSY, the inode + * belongs to an active ".nfs..." file and we return -EBUSY. + * + * If sillyrename() returns 0, we do nothing, otherwise we unlink. + */ +int nfs_unlink(struct inode *dir, struct dentry *dentry) +{ + int error; + int need_rehash = 0; + + dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id, + dir->i_ino, dentry); + + trace_nfs_unlink_enter(dir, dentry); + spin_lock(&dentry->d_lock); + if (d_count(dentry) > 1) { + spin_unlock(&dentry->d_lock); + /* Start asynchronous writeout of the inode */ + write_inode_now(d_inode(dentry), 0); + error = nfs_sillyrename(dir, dentry); + goto out; + } + if (!d_unhashed(dentry)) { + __d_drop(dentry); + need_rehash = 1; + } + spin_unlock(&dentry->d_lock); + error = nfs_safe_remove(dentry); + if (!error || error == -ENOENT) { + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + } else if (need_rehash) + d_rehash(dentry); +out: + trace_nfs_unlink_exit(dir, dentry, error); + return error; +} +EXPORT_SYMBOL_GPL(nfs_unlink); + +/* + * To create a symbolic link, most file systems instantiate a new inode, + * add a page to it containing the path, then write it out to the disk + * using prepare_write/commit_write. + * + * Unfortunately the NFS client can't create the in-core inode first + * because it needs a file handle to create an in-core inode (see + * fs/nfs/inode.c:nfs_fhget). We only have a file handle *after* the + * symlink request has completed on the server. + * + * So instead we allocate a raw page, copy the symname into it, then do + * the SYMLINK request with the page as the buffer. If it succeeds, we + * now have a new file handle and can instantiate an in-core NFS inode + * and move the raw page into its mapping. + */ +int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ + struct page *page; + char *kaddr; + struct iattr attr; + unsigned int pathlen = strlen(symname); + int error; + + dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id, + dir->i_ino, dentry, symname); + + if (pathlen > PAGE_SIZE) + return -ENAMETOOLONG; + + attr.ia_mode = S_IFLNK | S_IRWXUGO; + attr.ia_valid = ATTR_MODE; + + page = alloc_page(GFP_HIGHUSER); + if (!page) + return -ENOMEM; + + kaddr = kmap_atomic(page); + memcpy(kaddr, symname, pathlen); + if (pathlen < PAGE_SIZE) + memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen); + kunmap_atomic(kaddr); + + trace_nfs_symlink_enter(dir, dentry); + error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr); + trace_nfs_symlink_exit(dir, dentry, error); + if (error != 0) { + dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n", + dir->i_sb->s_id, dir->i_ino, + dentry, symname, error); + d_drop(dentry); + __free_page(page); + return error; + } + + /* + * No big deal if we can't add this page to the page cache here. + * READLINK will get the missing page from the server if needed. + */ + if (!add_to_page_cache_lru(page, d_inode(dentry)->i_mapping, 0, + GFP_KERNEL)) { + SetPageUptodate(page); + unlock_page(page); + /* + * add_to_page_cache_lru() grabs an extra page refcount. + * Drop it here to avoid leaking this page later. + */ + page_cache_release(page); + } else + __free_page(page); + + return 0; +} +EXPORT_SYMBOL_GPL(nfs_symlink); + +int +nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(old_dentry); + int error; + + dfprintk(VFS, "NFS: link(%pd2 -> %pd2)\n", + old_dentry, dentry); + + trace_nfs_link_enter(inode, dir, dentry); + NFS_PROTO(inode)->return_delegation(inode); + + d_drop(dentry); + error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); + if (error == 0) { + ihold(inode); + d_add(dentry, inode); + } + trace_nfs_link_exit(inode, dir, dentry, error); + return error; +} +EXPORT_SYMBOL_GPL(nfs_link); + +/* + * RENAME + * FIXME: Some nfsds, like the Linux user space nfsd, may generate a + * different file handle for the same inode after a rename (e.g. when + * moving to a different directory). A fail-safe method to do so would + * be to look up old_dir/old_name, create a link to new_dir/new_name and + * rename the old file using the sillyrename stuff. This way, the original + * file in old_dir will go away when the last process iput()s the inode. + * + * FIXED. + * + * It actually works quite well. One needs to have the possibility for + * at least one ".nfs..." file in each directory the file ever gets + * moved or linked to which happens automagically with the new + * implementation that only depends on the dcache stuff instead of + * using the inode layer + * + * Unfortunately, things are a little more complicated than indicated + * above. For a cross-directory move, we want to make sure we can get + * rid of the old inode after the operation. This means there must be + * no pending writes (if it's a file), and the use count must be 1. + * If these conditions are met, we can drop the dentries before doing + * the rename. + */ +int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct inode *old_inode = d_inode(old_dentry); + struct inode *new_inode = d_inode(new_dentry); + struct dentry *dentry = NULL, *rehash = NULL; + struct rpc_task *task; + int error = -EBUSY; + + dfprintk(VFS, "NFS: rename(%pd2 -> %pd2, ct=%d)\n", + old_dentry, new_dentry, + d_count(new_dentry)); + + trace_nfs_rename_enter(old_dir, old_dentry, new_dir, new_dentry); + /* + * For non-directories, check whether the target is busy and if so, + * make a copy of the dentry and then do a silly-rename. If the + * silly-rename succeeds, the copied dentry is hashed and becomes + * the new target. + */ + if (new_inode && !S_ISDIR(new_inode->i_mode)) { + /* + * To prevent any new references to the target during the + * rename, we unhash the dentry in advance. + */ + if (!d_unhashed(new_dentry)) { + d_drop(new_dentry); + rehash = new_dentry; + } + + if (d_count(new_dentry) > 2) { + int err; + + /* copy the target dentry's name */ + dentry = d_alloc(new_dentry->d_parent, + &new_dentry->d_name); + if (!dentry) + goto out; + + /* silly-rename the existing target ... */ + err = nfs_sillyrename(new_dir, new_dentry); + if (err) + goto out; + + new_dentry = dentry; + rehash = NULL; + new_inode = NULL; + } + } + + NFS_PROTO(old_inode)->return_delegation(old_inode); + if (new_inode != NULL) + NFS_PROTO(new_inode)->return_delegation(new_inode); + + task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); + if (IS_ERR(task)) { + error = PTR_ERR(task); + goto out; + } + + error = rpc_wait_for_completion_task(task); + if (error == 0) + error = task->tk_status; + rpc_put_task(task); + nfs_mark_for_revalidate(old_inode); +out: + if (rehash) + d_rehash(rehash); + trace_nfs_rename_exit(old_dir, old_dentry, + new_dir, new_dentry, error); + if (!error) { + if (new_inode != NULL) + nfs_drop_nlink(new_inode); + d_move(old_dentry, new_dentry); + nfs_set_verifier(new_dentry, + nfs_save_change_attribute(new_dir)); + } else if (error == -ENOENT) + nfs_dentry_handle_enoent(old_dentry); + + /* new dentry created? */ + if (dentry) + dput(dentry); + return error; +} +EXPORT_SYMBOL_GPL(nfs_rename); + +static DEFINE_SPINLOCK(nfs_access_lru_lock); +static LIST_HEAD(nfs_access_lru_list); +static atomic_long_t nfs_access_nr_entries; + +static unsigned long nfs_access_max_cachesize = ULONG_MAX; +module_param(nfs_access_max_cachesize, ulong, 0644); +MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache length"); + +static void nfs_access_free_entry(struct nfs_access_entry *entry) +{ + put_rpccred(entry->cred); + kfree_rcu(entry, rcu_head); + smp_mb__before_atomic(); + atomic_long_dec(&nfs_access_nr_entries); + smp_mb__after_atomic(); +} + +static void nfs_access_free_list(struct list_head *head) +{ + struct nfs_access_entry *cache; + + while (!list_empty(head)) { + cache = list_entry(head->next, struct nfs_access_entry, lru); + list_del(&cache->lru); + nfs_access_free_entry(cache); + } +} + +static unsigned long +nfs_do_access_cache_scan(unsigned int nr_to_scan) +{ + LIST_HEAD(head); + struct nfs_inode *nfsi, *next; + struct nfs_access_entry *cache; + long freed = 0; + + spin_lock(&nfs_access_lru_lock); + list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) { + struct inode *inode; + + if (nr_to_scan-- == 0) + break; + inode = &nfsi->vfs_inode; + spin_lock(&inode->i_lock); + if (list_empty(&nfsi->access_cache_entry_lru)) + goto remove_lru_entry; + cache = list_entry(nfsi->access_cache_entry_lru.next, + struct nfs_access_entry, lru); + list_move(&cache->lru, &head); + rb_erase(&cache->rb_node, &nfsi->access_cache); + freed++; + if (!list_empty(&nfsi->access_cache_entry_lru)) + list_move_tail(&nfsi->access_cache_inode_lru, + &nfs_access_lru_list); + else { +remove_lru_entry: + list_del_init(&nfsi->access_cache_inode_lru); + smp_mb__before_atomic(); + clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags); + smp_mb__after_atomic(); + } + spin_unlock(&inode->i_lock); + } + spin_unlock(&nfs_access_lru_lock); + nfs_access_free_list(&head); + return freed; +} + +unsigned long +nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + int nr_to_scan = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; + + if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) + return SHRINK_STOP; + return nfs_do_access_cache_scan(nr_to_scan); +} + + +unsigned long +nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries)); +} + +static void +nfs_access_cache_enforce_limit(void) +{ + long nr_entries = atomic_long_read(&nfs_access_nr_entries); + unsigned long diff; + unsigned int nr_to_scan; + + if (nr_entries < 0 || nr_entries <= nfs_access_max_cachesize) + return; + nr_to_scan = 100; + diff = nr_entries - nfs_access_max_cachesize; + if (diff < nr_to_scan) + nr_to_scan = diff; + nfs_do_access_cache_scan(nr_to_scan); +} + +static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head) +{ + struct rb_root *root_node = &nfsi->access_cache; + struct rb_node *n; + struct nfs_access_entry *entry; + + /* Unhook entries from the cache */ + while ((n = rb_first(root_node)) != NULL) { + entry = rb_entry(n, struct nfs_access_entry, rb_node); + rb_erase(n, root_node); + list_move(&entry->lru, head); + } + nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS; +} + +void nfs_access_zap_cache(struct inode *inode) +{ + LIST_HEAD(head); + + if (test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags) == 0) + return; + /* Remove from global LRU init */ + spin_lock(&nfs_access_lru_lock); + if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) + list_del_init(&NFS_I(inode)->access_cache_inode_lru); + + spin_lock(&inode->i_lock); + __nfs_access_zap_cache(NFS_I(inode), &head); + spin_unlock(&inode->i_lock); + spin_unlock(&nfs_access_lru_lock); + nfs_access_free_list(&head); +} +EXPORT_SYMBOL_GPL(nfs_access_zap_cache); + +static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred) +{ + struct rb_node *n = NFS_I(inode)->access_cache.rb_node; + struct nfs_access_entry *entry; + + while (n != NULL) { + entry = rb_entry(n, struct nfs_access_entry, rb_node); + + if (cred < entry->cred) + n = n->rb_left; + else if (cred > entry->cred) + n = n->rb_right; + else + return entry; + } + return NULL; +} + +static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_access_entry *cache; + int err = -ENOENT; + + spin_lock(&inode->i_lock); + if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS) + goto out_zap; + cache = nfs_access_search_rbtree(inode, cred); + if (cache == NULL) + goto out; + if (!nfs_have_delegated_attributes(inode) && + !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo)) + goto out_stale; + res->jiffies = cache->jiffies; + res->cred = cache->cred; + res->mask = cache->mask; + list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); + err = 0; +out: + spin_unlock(&inode->i_lock); + return err; +out_stale: + rb_erase(&cache->rb_node, &nfsi->access_cache); + list_del(&cache->lru); + spin_unlock(&inode->i_lock); + nfs_access_free_entry(cache); + return -ENOENT; +out_zap: + spin_unlock(&inode->i_lock); + nfs_access_zap_cache(inode); + return -ENOENT; +} + +static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res) +{ + /* Only check the most recently returned cache entry, + * but do it without locking. + */ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_access_entry *cache; + int err = -ECHILD; + struct list_head *lh; + + rcu_read_lock(); + if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS) + goto out; + lh = rcu_dereference(nfsi->access_cache_entry_lru.prev); + cache = list_entry(lh, struct nfs_access_entry, lru); + if (lh == &nfsi->access_cache_entry_lru || + cred != cache->cred) + cache = NULL; + if (cache == NULL) + goto out; + if (!nfs_have_delegated_attributes(inode) && + !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo)) + goto out; + res->jiffies = cache->jiffies; + res->cred = cache->cred; + res->mask = cache->mask; + err = 0; +out: + rcu_read_unlock(); + return err; +} + +static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct rb_root *root_node = &nfsi->access_cache; + struct rb_node **p = &root_node->rb_node; + struct rb_node *parent = NULL; + struct nfs_access_entry *entry; + + spin_lock(&inode->i_lock); + while (*p != NULL) { + parent = *p; + entry = rb_entry(parent, struct nfs_access_entry, rb_node); + + if (set->cred < entry->cred) + p = &parent->rb_left; + else if (set->cred > entry->cred) + p = &parent->rb_right; + else + goto found; + } + rb_link_node(&set->rb_node, parent, p); + rb_insert_color(&set->rb_node, root_node); + list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); + spin_unlock(&inode->i_lock); + return; +found: + rb_replace_node(parent, &set->rb_node, root_node); + list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); + list_del(&entry->lru); + spin_unlock(&inode->i_lock); + nfs_access_free_entry(entry); +} + +void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) +{ + struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); + if (cache == NULL) + return; + RB_CLEAR_NODE(&cache->rb_node); + cache->jiffies = set->jiffies; + cache->cred = get_rpccred(set->cred); + cache->mask = set->mask; + + /* The above field assignments must be visible + * before this item appears on the lru. We cannot easily + * use rcu_assign_pointer, so just force the memory barrier. + */ + smp_wmb(); + nfs_access_add_rbtree(inode, cache); + + /* Update accounting */ + smp_mb__before_atomic(); + atomic_long_inc(&nfs_access_nr_entries); + smp_mb__after_atomic(); + + /* Add inode to global LRU list */ + if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) { + spin_lock(&nfs_access_lru_lock); + if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) + list_add_tail(&NFS_I(inode)->access_cache_inode_lru, + &nfs_access_lru_list); + spin_unlock(&nfs_access_lru_lock); + } + nfs_access_cache_enforce_limit(); +} +EXPORT_SYMBOL_GPL(nfs_access_add_cache); + +void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result) +{ + entry->mask = 0; + if (access_result & NFS4_ACCESS_READ) + entry->mask |= MAY_READ; + if (access_result & + (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE)) + entry->mask |= MAY_WRITE; + if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE)) + entry->mask |= MAY_EXEC; +} +EXPORT_SYMBOL_GPL(nfs_access_set_mask); + +static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) +{ + struct nfs_access_entry cache; + int status; + + trace_nfs_access_enter(inode); + + status = nfs_access_get_cached_rcu(inode, cred, &cache); + if (status != 0) + status = nfs_access_get_cached(inode, cred, &cache); + if (status == 0) + goto out_cached; + + status = -ECHILD; + if (mask & MAY_NOT_BLOCK) + goto out; + + /* Be clever: ask server to check for all possible rights */ + cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ; + cache.cred = cred; + cache.jiffies = jiffies; + status = NFS_PROTO(inode)->access(inode, &cache); + if (status != 0) { + if (status == -ESTALE) { + nfs_zap_caches(inode); + if (!S_ISDIR(inode->i_mode)) + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + } + goto out; + } + nfs_access_add_cache(inode, &cache); +out_cached: + if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) + status = -EACCES; +out: + trace_nfs_access_exit(inode, status); + return status; +} + +static int nfs_open_permission_mask(int openflags) +{ + int mask = 0; + + if (openflags & __FMODE_EXEC) { + /* ONLY check exec rights */ + mask = MAY_EXEC; + } else { + if ((openflags & O_ACCMODE) != O_WRONLY) + mask |= MAY_READ; + if ((openflags & O_ACCMODE) != O_RDONLY) + mask |= MAY_WRITE; + } + + return mask; +} + +int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) +{ + return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags)); +} +EXPORT_SYMBOL_GPL(nfs_may_open); + +int nfs_permission(struct inode *inode, int mask) +{ + struct rpc_cred *cred; + int res = 0; + + nfs_inc_stats(inode, NFSIOS_VFSACCESS); + + if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) + goto out; + /* Is this sys_access() ? */ + if (mask & (MAY_ACCESS | MAY_CHDIR)) + goto force_lookup; + + switch (inode->i_mode & S_IFMT) { + case S_IFLNK: + goto out; + case S_IFREG: + break; + case S_IFDIR: + /* + * Optimize away all write operations, since the server + * will check permissions when we perform the op. + */ + if ((mask & MAY_WRITE) && !(mask & MAY_READ)) + goto out; + } + +force_lookup: + if (!NFS_PROTO(inode)->access) + goto out_notsup; + + /* Always try fast lookups first */ + rcu_read_lock(); + cred = rpc_lookup_cred_nonblock(); + if (!IS_ERR(cred)) + res = nfs_do_access(inode, cred, mask|MAY_NOT_BLOCK); + else + res = PTR_ERR(cred); + rcu_read_unlock(); + if (res == -ECHILD && !(mask & MAY_NOT_BLOCK)) { + /* Fast lookup failed, try the slow way */ + cred = rpc_lookup_cred(); + if (!IS_ERR(cred)) { + res = nfs_do_access(inode, cred, mask); + put_rpccred(cred); + } else + res = PTR_ERR(cred); + } +out: + if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) + res = -EACCES; + + dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", + inode->i_sb->s_id, inode->i_ino, mask, res); + return res; +out_notsup: + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + + res = nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (res == 0) + res = generic_permission(inode, mask); + goto out; +} +EXPORT_SYMBOL_GPL(nfs_permission); + +/* + * Local variables: + * version-control: t + * kept-new-versions: 5 + * End: + */ diff --git a/kernel/fs/nfs/direct.c b/kernel/fs/nfs/direct.c new file mode 100644 index 000000000..38678d9a5 --- /dev/null +++ b/kernel/fs/nfs/direct.c @@ -0,0 +1,1066 @@ +/* + * linux/fs/nfs/direct.c + * + * Copyright (C) 2003 by Chuck Lever <cel@netapp.com> + * + * High-performance uncached I/O for the Linux NFS client + * + * There are important applications whose performance or correctness + * depends on uncached access to file data. Database clusters + * (multiple copies of the same instance running on separate hosts) + * implement their own cache coherency protocol that subsumes file + * system cache protocols. Applications that process datasets + * considerably larger than the client's memory do not always benefit + * from a local cache. A streaming video server, for instance, has no + * need to cache the contents of a file. + * + * When an application requests uncached I/O, all read and write requests + * are made directly to the server; data stored or fetched via these + * requests is not cached in the Linux page cache. The client does not + * correct unaligned requests from applications. All requested bytes are + * held on permanent storage before a direct write system call returns to + * an application. + * + * Solaris implements an uncached I/O facility called directio() that + * is used for backups and sequential I/O to very large files. Solaris + * also supports uncaching whole NFS partitions with "-o forcedirectio," + * an undocumented mount option. + * + * Designed by Jeff Kimmel, Chuck Lever, and Trond Myklebust, with + * help from Andrew Morton. + * + * 18 Dec 2001 Initial implementation for 2.4 --cel + * 08 Jul 2002 Version for 2.4.19, with bug fixes --trondmy + * 08 Jun 2003 Port to 2.5 APIs --cel + * 31 Mar 2004 Handle direct I/O without VFS support --cel + * 15 Sep 2004 Parallel async reads --cel + * 04 May 2005 support O_DIRECT with aio --cel + * + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/file.h> +#include <linux/pagemap.h> +#include <linux/kref.h> +#include <linux/slab.h> +#include <linux/task_io_accounting_ops.h> +#include <linux/module.h> + +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/sunrpc/clnt.h> + +#include <asm/uaccess.h> +#include <linux/atomic.h> + +#include "internal.h" +#include "iostat.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +static struct kmem_cache *nfs_direct_cachep; + +/* + * This represents a set of asynchronous requests that we're waiting on + */ +struct nfs_direct_mirror { + ssize_t count; +}; + +struct nfs_direct_req { + struct kref kref; /* release manager */ + + /* I/O parameters */ + struct nfs_open_context *ctx; /* file open context info */ + struct nfs_lock_context *l_ctx; /* Lock context info */ + struct kiocb * iocb; /* controlling i/o request */ + struct inode * inode; /* target file of i/o */ + + /* completion state */ + atomic_t io_count; /* i/os we're waiting for */ + spinlock_t lock; /* protect completion state */ + + struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX]; + int mirror_count; + + ssize_t count, /* bytes actually processed */ + bytes_left, /* bytes left to be sent */ + io_start, /* start of IO */ + error; /* any reported error */ + struct completion completion; /* wait for i/o completion */ + + /* commit state */ + struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ + struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ + struct work_struct work; + int flags; +#define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ +#define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ + struct nfs_writeverf verf; /* unstable write verifier */ +}; + +static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops; +static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops; +static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode); +static void nfs_direct_write_schedule_work(struct work_struct *work); + +static inline void get_dreq(struct nfs_direct_req *dreq) +{ + atomic_inc(&dreq->io_count); +} + +static inline int put_dreq(struct nfs_direct_req *dreq) +{ + return atomic_dec_and_test(&dreq->io_count); +} + +void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq) +{ + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; +} +EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes); + +static void +nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) +{ + int i; + ssize_t count; + + if (dreq->mirror_count == 1) { + dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes; + dreq->count += hdr->good_bytes; + } else { + /* mirrored writes */ + count = dreq->mirrors[hdr->pgio_mirror_idx].count; + if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) { + count = hdr->io_start + hdr->good_bytes - dreq->io_start; + dreq->mirrors[hdr->pgio_mirror_idx].count = count; + } + /* update the dreq->count by finding the minimum agreed count from all + * mirrors */ + count = dreq->mirrors[0].count; + + for (i = 1; i < dreq->mirror_count; i++) + count = min(count, dreq->mirrors[i].count); + + dreq->count = count; + } +} + +/* + * nfs_direct_select_verf - select the right verifier + * @dreq - direct request possibly spanning multiple servers + * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs + * @commit_idx - commit bucket index for the DS + * + * returns the correct verifier to use given the role of the server + */ +static struct nfs_writeverf * +nfs_direct_select_verf(struct nfs_direct_req *dreq, + struct nfs_client *ds_clp, + int commit_idx) +{ + struct nfs_writeverf *verfp = &dreq->verf; + +#ifdef CONFIG_NFS_V4_1 + if (ds_clp) { + /* pNFS is in use, use the DS verf */ + if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets) + verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf; + else + WARN_ON_ONCE(1); + } +#endif + return verfp; +} + + +/* + * nfs_direct_set_hdr_verf - set the write/commit verifier + * @dreq - direct request possibly spanning multiple servers + * @hdr - pageio header to validate against previously seen verfs + * + * Set the server's (MDS or DS) "seen" verifier + */ +static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq, + struct nfs_pgio_header *hdr) +{ + struct nfs_writeverf *verfp; + + verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx); + WARN_ON_ONCE(verfp->committed >= 0); + memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); + WARN_ON_ONCE(verfp->committed < 0); +} + +/* + * nfs_direct_cmp_hdr_verf - compare verifier for pgio header + * @dreq - direct request possibly spanning multiple servers + * @hdr - pageio header to validate against previously seen verf + * + * set the server's "seen" verf if not initialized. + * returns result of comparison between @hdr->verf and the "seen" + * verf of the server used by @hdr (DS or MDS) + */ +static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq, + struct nfs_pgio_header *hdr) +{ + struct nfs_writeverf *verfp; + + verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx); + if (verfp->committed < 0) { + nfs_direct_set_hdr_verf(dreq, hdr); + return 0; + } + return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); +} + +/* + * nfs_direct_cmp_commit_data_verf - compare verifier for commit data + * @dreq - direct request possibly spanning multiple servers + * @data - commit data to validate against previously seen verf + * + * returns result of comparison between @data->verf and the verf of + * the server used by @data (DS or MDS) + */ +static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, + struct nfs_commit_data *data) +{ + struct nfs_writeverf *verfp; + + verfp = nfs_direct_select_verf(dreq, data->ds_clp, + data->ds_commit_index); + + /* verifier not set so always fail */ + if (verfp->committed < 0) + return 1; + + return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf)); +} + +/** + * nfs_direct_IO - NFS address space operation for direct I/O + * @iocb: target I/O control block + * @iov: array of vectors that define I/O buffer + * @pos: offset in file to begin the operation + * @nr_segs: size of iovec array + * + * The presence of this routine in the address space ops vector means + * the NFS client supports direct I/O. However, for most direct IO, we + * shunt off direct read and write requests before the VFS gets them, + * so this method is only ever called for swap. + */ +ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +{ + struct inode *inode = iocb->ki_filp->f_mapping->host; + + /* we only support swap file calling nfs_direct_IO */ + if (!IS_SWAPFILE(inode)) + return 0; + + VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); + + if (iov_iter_rw(iter) == READ) + return nfs_file_direct_read(iocb, iter, pos); + return nfs_file_direct_write(iocb, iter); +} + +static void nfs_direct_release_pages(struct page **pages, unsigned int npages) +{ + unsigned int i; + for (i = 0; i < npages; i++) + page_cache_release(pages[i]); +} + +void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, + struct nfs_direct_req *dreq) +{ + cinfo->lock = &dreq->inode->i_lock; + cinfo->mds = &dreq->mds_cinfo; + cinfo->ds = &dreq->ds_cinfo; + cinfo->dreq = dreq; + cinfo->completion_ops = &nfs_direct_commit_completion_ops; +} + +static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq, + struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + int mirror_count = 1; + + if (pgio->pg_ops->pg_get_mirror_count) + mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + + dreq->mirror_count = mirror_count; +} + +static inline struct nfs_direct_req *nfs_direct_req_alloc(void) +{ + struct nfs_direct_req *dreq; + + dreq = kmem_cache_zalloc(nfs_direct_cachep, GFP_KERNEL); + if (!dreq) + return NULL; + + kref_init(&dreq->kref); + kref_get(&dreq->kref); + init_completion(&dreq->completion); + INIT_LIST_HEAD(&dreq->mds_cinfo.list); + dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */ + INIT_WORK(&dreq->work, nfs_direct_write_schedule_work); + dreq->mirror_count = 1; + spin_lock_init(&dreq->lock); + + return dreq; +} + +static void nfs_direct_req_free(struct kref *kref) +{ + struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); + + nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo); + if (dreq->l_ctx != NULL) + nfs_put_lock_context(dreq->l_ctx); + if (dreq->ctx != NULL) + put_nfs_open_context(dreq->ctx); + kmem_cache_free(nfs_direct_cachep, dreq); +} + +static void nfs_direct_req_release(struct nfs_direct_req *dreq) +{ + kref_put(&dreq->kref, nfs_direct_req_free); +} + +ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq) +{ + return dreq->bytes_left; +} +EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left); + +/* + * Collects and returns the final error value/byte-count. + */ +static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq) +{ + ssize_t result = -EIOCBQUEUED; + + /* Async requests don't wait here */ + if (dreq->iocb) + goto out; + + result = wait_for_completion_killable(&dreq->completion); + + if (!result) + result = dreq->error; + if (!result) + result = dreq->count; + +out: + return (ssize_t) result; +} + +/* + * Synchronous I/O uses a stack-allocated iocb. Thus we can't trust + * the iocb is still valid here if this is a synchronous request. + */ +static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write) +{ + struct inode *inode = dreq->inode; + + if (dreq->iocb && write) { + loff_t pos = dreq->iocb->ki_pos + dreq->count; + + spin_lock(&inode->i_lock); + if (i_size_read(inode) < pos) + i_size_write(inode, pos); + spin_unlock(&inode->i_lock); + } + + if (write) + nfs_zap_mapping(inode, inode->i_mapping); + + inode_dio_end(inode); + + if (dreq->iocb) { + long res = (long) dreq->error; + if (!res) + res = (long) dreq->count; + dreq->iocb->ki_complete(dreq->iocb, res, 0); + } + + complete_all(&dreq->completion); + + nfs_direct_req_release(dreq); +} + +static void nfs_direct_readpage_release(struct nfs_page *req) +{ + dprintk("NFS: direct read done (%s/%llu %d@%lld)\n", + d_inode(req->wb_context->dentry)->i_sb->s_id, + (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)), + req->wb_bytes, + (long long)req_offset(req)); + nfs_release_request(req); +} + +static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) +{ + unsigned long bytes = 0; + struct nfs_direct_req *dreq = hdr->dreq; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out_put; + + spin_lock(&dreq->lock); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) + dreq->error = hdr->error; + else + nfs_direct_good_bytes(dreq, hdr); + + spin_unlock(&dreq->lock); + + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + if (!PageCompound(page) && bytes < hdr->good_bytes) + set_page_dirty(page); + bytes += req->wb_bytes; + nfs_list_remove_request(req); + nfs_direct_readpage_release(req); + } +out_put: + if (put_dreq(dreq)) + nfs_direct_complete(dreq, false); + hdr->release(hdr); +} + +static void nfs_read_sync_pgio_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_release_request(req); + } +} + +static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr) +{ + get_dreq(hdr->dreq); +} + +static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { + .error_cleanup = nfs_read_sync_pgio_error, + .init_hdr = nfs_direct_pgio_init, + .completion = nfs_direct_read_completion, +}; + +/* + * For each rsize'd chunk of the user's buffer, dispatch an NFS READ + * operation. If nfs_readdata_alloc() or get_user_pages() fails, + * bail and stop sending more reads. Read length accounting is + * handled automatically by nfs_direct_read_result(). Otherwise, if + * no requests have been sent, just return an error. + */ + +static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, + struct iov_iter *iter, + loff_t pos) +{ + struct nfs_pageio_descriptor desc; + struct inode *inode = dreq->inode; + ssize_t result = -EINVAL; + size_t requested_bytes = 0; + size_t rsize = max_t(size_t, NFS_SERVER(inode)->rsize, PAGE_SIZE); + + nfs_pageio_init_read(&desc, dreq->inode, false, + &nfs_direct_read_completion_ops); + get_dreq(dreq); + desc.pg_dreq = dreq; + inode_dio_begin(inode); + + while (iov_iter_count(iter)) { + struct page **pagevec; + size_t bytes; + size_t pgbase; + unsigned npages, i; + + result = iov_iter_get_pages_alloc(iter, &pagevec, + rsize, &pgbase); + if (result < 0) + break; + + bytes = result; + iov_iter_advance(iter, bytes); + npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); + /* XXX do we need to do the eof zeroing found in async_filler? */ + req = nfs_create_request(dreq->ctx, pagevec[i], NULL, + pgbase, req_len); + if (IS_ERR(req)) { + result = PTR_ERR(req); + break; + } + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(&desc, req)) { + result = desc.pg_error; + nfs_release_request(req); + break; + } + pgbase = 0; + bytes -= req_len; + requested_bytes += req_len; + pos += req_len; + dreq->bytes_left -= req_len; + } + nfs_direct_release_pages(pagevec, npages); + kvfree(pagevec); + if (result < 0) + break; + } + + nfs_pageio_complete(&desc); + + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + inode_dio_end(inode); + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + + if (put_dreq(dreq)) + nfs_direct_complete(dreq, false); + return 0; +} + +/** + * nfs_file_direct_read - file direct read operation for NFS files + * @iocb: target I/O control block + * @iter: vector of user buffers into which to read data + * @pos: byte offset in file where reading starts + * + * We use this function for direct reads instead of calling + * generic_file_aio_read() in order to avoid gfar's check to see if + * the request starts before the end of the file. For that check + * to work, we must generate a GETATTR before each direct read, and + * even then there is a window between the GETATTR and the subsequent + * READ where the file size could change. Our preference is simply + * to do all reads the application wants, and the server will take + * care of managing the end of file boundary. + * + * This function also eliminates unnecessarily updating the file's + * atime locally, as the NFS server sets the file's atime, and this + * client must read the updated atime from the server back into its + * cache. + */ +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, + loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + struct nfs_direct_req *dreq; + struct nfs_lock_context *l_ctx; + ssize_t result = -EINVAL; + size_t count = iov_iter_count(iter); + nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); + + dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", + file, count, (long long) pos); + + result = 0; + if (!count) + goto out; + + mutex_lock(&inode->i_mutex); + result = nfs_sync_mapping(mapping); + if (result) + goto out_unlock; + + task_io_account_read(count); + + result = -ENOMEM; + dreq = nfs_direct_req_alloc(); + if (dreq == NULL) + goto out_unlock; + + dreq->inode = inode; + dreq->bytes_left = count; + dreq->io_start = pos; + dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); + l_ctx = nfs_get_lock_context(dreq->ctx); + if (IS_ERR(l_ctx)) { + result = PTR_ERR(l_ctx); + goto out_release; + } + dreq->l_ctx = l_ctx; + if (!is_sync_kiocb(iocb)) + dreq->iocb = iocb; + + NFS_I(inode)->read_io += count; + result = nfs_direct_read_schedule_iovec(dreq, iter, pos); + + mutex_unlock(&inode->i_mutex); + + if (!result) { + result = nfs_direct_wait(dreq); + if (result > 0) + iocb->ki_pos = pos + result; + } + + nfs_direct_req_release(dreq); + return result; + +out_release: + nfs_direct_req_release(dreq); +out_unlock: + mutex_unlock(&inode->i_mutex); +out: + return result; +} + +static void +nfs_direct_write_scan_commit_list(struct inode *inode, + struct list_head *list, + struct nfs_commit_info *cinfo) +{ + spin_lock(cinfo->lock); +#ifdef CONFIG_NFS_V4_1 + if (cinfo->ds != NULL && cinfo->ds->nwritten != 0) + NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo); +#endif + nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0); + spin_unlock(cinfo->lock); +} + +static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) +{ + struct nfs_pageio_descriptor desc; + struct nfs_page *req, *tmp; + LIST_HEAD(reqs); + struct nfs_commit_info cinfo; + LIST_HEAD(failed); + int i; + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); + + dreq->count = 0; + for (i = 0; i < dreq->mirror_count; i++) + dreq->mirrors[i].count = 0; + get_dreq(dreq); + + nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false, + &nfs_direct_write_completion_ops); + desc.pg_dreq = dreq; + + req = nfs_list_entry(reqs.next); + nfs_direct_setup_mirroring(dreq, &desc, req); + + list_for_each_entry_safe(req, tmp, &reqs, wb_list) { + if (!nfs_pageio_add_request(&desc, req)) { + nfs_list_remove_request(req); + nfs_list_add_request(req, &failed); + spin_lock(cinfo.lock); + dreq->flags = 0; + dreq->error = -EIO; + spin_unlock(cinfo.lock); + } + nfs_release_request(req); + } + nfs_pageio_complete(&desc); + + while (!list_empty(&failed)) { + req = nfs_list_entry(failed.next); + nfs_list_remove_request(req); + nfs_unlock_and_release_request(req); + } + + if (put_dreq(dreq)) + nfs_direct_write_complete(dreq, dreq->inode); +} + +static void nfs_direct_commit_complete(struct nfs_commit_data *data) +{ + struct nfs_direct_req *dreq = data->dreq; + struct nfs_commit_info cinfo; + struct nfs_page *req; + int status = data->task.tk_status; + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + if (status < 0) { + dprintk("NFS: %5u commit failed with error %d.\n", + data->task.tk_pid, status); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + } else if (nfs_direct_cmp_commit_data_verf(dreq, data)) { + dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + } + + dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status); + while (!list_empty(&data->pages)) { + req = nfs_list_entry(data->pages.next); + nfs_list_remove_request(req); + if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) { + /* Note the rewrite will go through mds */ + nfs_mark_request_commit(req, NULL, &cinfo, 0); + } else + nfs_release_request(req); + nfs_unlock_and_release_request(req); + } + + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + nfs_direct_write_complete(dreq, data->inode); +} + +static void nfs_direct_error_cleanup(struct nfs_inode *nfsi) +{ + /* There is no lock to clear */ +} + +static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = { + .completion = nfs_direct_commit_complete, + .error_cleanup = nfs_direct_error_cleanup, +}; + +static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) +{ + int res; + struct nfs_commit_info cinfo; + LIST_HEAD(mds_list); + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_scan_commit(dreq->inode, &mds_list, &cinfo); + res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); + if (res < 0) /* res == -ENOMEM */ + nfs_direct_write_reschedule(dreq); +} + +static void nfs_direct_write_schedule_work(struct work_struct *work) +{ + struct nfs_direct_req *dreq = container_of(work, struct nfs_direct_req, work); + int flags = dreq->flags; + + dreq->flags = 0; + switch (flags) { + case NFS_ODIRECT_DO_COMMIT: + nfs_direct_commit_schedule(dreq); + break; + case NFS_ODIRECT_RESCHED_WRITES: + nfs_direct_write_reschedule(dreq); + break; + default: + nfs_direct_complete(dreq, true); + } +} + +static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode) +{ + schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */ +} + +static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) +{ + struct nfs_direct_req *dreq = hdr->dreq; + struct nfs_commit_info cinfo; + bool request_commit = false; + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out_put; + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + + spin_lock(&dreq->lock); + + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + dreq->flags = 0; + dreq->error = hdr->error; + } + if (dreq->error == 0) { + nfs_direct_good_bytes(dreq, hdr); + if (nfs_write_need_commit(hdr)) { + if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) + request_commit = true; + else if (dreq->flags == 0) { + nfs_direct_set_hdr_verf(dreq, hdr); + request_commit = true; + dreq->flags = NFS_ODIRECT_DO_COMMIT; + } else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) { + request_commit = true; + if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr)) + dreq->flags = + NFS_ODIRECT_RESCHED_WRITES; + } + } + } + spin_unlock(&dreq->lock); + + while (!list_empty(&hdr->pages)) { + + req = nfs_list_entry(hdr->pages.next); + nfs_list_remove_request(req); + if (request_commit) { + kref_get(&req->wb_kref); + nfs_mark_request_commit(req, hdr->lseg, &cinfo, + hdr->ds_commit_idx); + } + nfs_unlock_and_release_request(req); + } + +out_put: + if (put_dreq(dreq)) + nfs_direct_write_complete(dreq, hdr->inode); + hdr->release(hdr); +} + +static void nfs_write_sync_pgio_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_unlock_and_release_request(req); + } +} + +static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { + .error_cleanup = nfs_write_sync_pgio_error, + .init_hdr = nfs_direct_pgio_init, + .completion = nfs_direct_write_completion, +}; + + +/* + * NB: Return the value of the first error return code. Subsequent + * errors after the first one are ignored. + */ +/* + * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE + * operation. If nfs_writedata_alloc() or get_user_pages() fails, + * bail and stop sending more writes. Write length accounting is + * handled automatically by nfs_direct_write_result(). Otherwise, if + * no requests have been sent, just return an error. + */ +static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, + struct iov_iter *iter, + loff_t pos) +{ + struct nfs_pageio_descriptor desc; + struct inode *inode = dreq->inode; + ssize_t result = 0; + size_t requested_bytes = 0; + size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); + + nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false, + &nfs_direct_write_completion_ops); + desc.pg_dreq = dreq; + get_dreq(dreq); + inode_dio_begin(inode); + + NFS_I(inode)->write_io += iov_iter_count(iter); + while (iov_iter_count(iter)) { + struct page **pagevec; + size_t bytes; + size_t pgbase; + unsigned npages, i; + + result = iov_iter_get_pages_alloc(iter, &pagevec, + wsize, &pgbase); + if (result < 0) + break; + + bytes = result; + iov_iter_advance(iter, bytes); + npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); + + req = nfs_create_request(dreq->ctx, pagevec[i], NULL, + pgbase, req_len); + if (IS_ERR(req)) { + result = PTR_ERR(req); + break; + } + + nfs_direct_setup_mirroring(dreq, &desc, req); + + nfs_lock_request(req); + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(&desc, req)) { + result = desc.pg_error; + nfs_unlock_and_release_request(req); + break; + } + pgbase = 0; + bytes -= req_len; + requested_bytes += req_len; + pos += req_len; + dreq->bytes_left -= req_len; + } + nfs_direct_release_pages(pagevec, npages); + kvfree(pagevec); + if (result < 0) + break; + } + nfs_pageio_complete(&desc); + + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + inode_dio_end(inode); + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + + if (put_dreq(dreq)) + nfs_direct_write_complete(dreq, dreq->inode); + return 0; +} + +/** + * nfs_file_direct_write - file direct write operation for NFS files + * @iocb: target I/O control block + * @iter: vector of user buffers from which to write data + * @pos: byte offset in file where writing starts + * + * We use this function for direct writes instead of calling + * generic_file_aio_write() in order to avoid taking the inode + * semaphore and updating the i_size. The NFS server will set + * the new i_size and this client must read the updated size + * back into its cache. We let the server do generic write + * parameter checking and report problems. + * + * We eliminate local atime updates, see direct read above. + * + * We avoid unnecessary page cache invalidations for normal cached + * readers of this file. + * + * Note that O_APPEND is not supported for NFS direct writes, as there + * is no atomic O_APPEND write facility in the NFS protocol. + */ +ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) +{ + ssize_t result = -EINVAL; + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + struct nfs_direct_req *dreq; + struct nfs_lock_context *l_ctx; + loff_t pos, end; + + dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n", + file, iov_iter_count(iter), (long long) iocb->ki_pos); + + nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, + iov_iter_count(iter)); + + pos = iocb->ki_pos; + end = (pos + iov_iter_count(iter) - 1) >> PAGE_CACHE_SHIFT; + + mutex_lock(&inode->i_mutex); + + result = nfs_sync_mapping(mapping); + if (result) + goto out_unlock; + + if (mapping->nrpages) { + result = invalidate_inode_pages2_range(mapping, + pos >> PAGE_CACHE_SHIFT, end); + if (result) + goto out_unlock; + } + + task_io_account_write(iov_iter_count(iter)); + + result = -ENOMEM; + dreq = nfs_direct_req_alloc(); + if (!dreq) + goto out_unlock; + + dreq->inode = inode; + dreq->bytes_left = iov_iter_count(iter); + dreq->io_start = pos; + dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); + l_ctx = nfs_get_lock_context(dreq->ctx); + if (IS_ERR(l_ctx)) { + result = PTR_ERR(l_ctx); + goto out_release; + } + dreq->l_ctx = l_ctx; + if (!is_sync_kiocb(iocb)) + dreq->iocb = iocb; + + result = nfs_direct_write_schedule_iovec(dreq, iter, pos); + + if (mapping->nrpages) { + invalidate_inode_pages2_range(mapping, + pos >> PAGE_CACHE_SHIFT, end); + } + + mutex_unlock(&inode->i_mutex); + + if (!result) { + result = nfs_direct_wait(dreq); + if (result > 0) { + struct inode *inode = mapping->host; + + iocb->ki_pos = pos + result; + spin_lock(&inode->i_lock); + if (i_size_read(inode) < iocb->ki_pos) + i_size_write(inode, iocb->ki_pos); + spin_unlock(&inode->i_lock); + generic_write_sync(file, pos, result); + } + } + nfs_direct_req_release(dreq); + return result; + +out_release: + nfs_direct_req_release(dreq); +out_unlock: + mutex_unlock(&inode->i_mutex); + return result; +} + +/** + * nfs_init_directcache - create a slab cache for nfs_direct_req structures + * + */ +int __init nfs_init_directcache(void) +{ + nfs_direct_cachep = kmem_cache_create("nfs_direct_cache", + sizeof(struct nfs_direct_req), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD), + NULL); + if (nfs_direct_cachep == NULL) + return -ENOMEM; + + return 0; +} + +/** + * nfs_destroy_directcache - destroy the slab cache for nfs_direct_req structures + * + */ +void nfs_destroy_directcache(void) +{ + kmem_cache_destroy(nfs_direct_cachep); +} diff --git a/kernel/fs/nfs/dns_resolve.c b/kernel/fs/nfs/dns_resolve.c new file mode 100644 index 000000000..d25f10fb4 --- /dev/null +++ b/kernel/fs/nfs/dns_resolve.c @@ -0,0 +1,470 @@ +/* + * linux/fs/nfs/dns_resolve.c + * + * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com> + * + * Resolves DNS hostnames into valid ip addresses + */ + +#ifdef CONFIG_NFS_USE_KERNEL_DNS + +#include <linux/module.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> +#include <linux/dns_resolver.h> +#include "dns_resolve.h" + +ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, + struct sockaddr *sa, size_t salen) +{ + ssize_t ret; + char *ip_addr = NULL; + int ip_len; + + ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL); + if (ip_len > 0) + ret = rpc_pton(net, ip_addr, ip_len, sa, salen); + else + ret = -ESRCH; + kfree(ip_addr); + return ret; +} + +#else + +#include <linux/module.h> +#include <linux/hash.h> +#include <linux/string.h> +#include <linux/kmod.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/socket.h> +#include <linux/seq_file.h> +#include <linux/inet.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> +#include <linux/sunrpc/cache.h> +#include <linux/sunrpc/svcauth.h> +#include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/nfs_fs.h> + +#include "nfs4_fs.h" +#include "dns_resolve.h" +#include "cache_lib.h" +#include "netns.h" + +#define NFS_DNS_HASHBITS 4 +#define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS) + +struct nfs_dns_ent { + struct cache_head h; + + char *hostname; + size_t namelen; + + struct sockaddr_storage addr; + size_t addrlen; +}; + + +static void nfs_dns_ent_update(struct cache_head *cnew, + struct cache_head *ckey) +{ + struct nfs_dns_ent *new; + struct nfs_dns_ent *key; + + new = container_of(cnew, struct nfs_dns_ent, h); + key = container_of(ckey, struct nfs_dns_ent, h); + + memcpy(&new->addr, &key->addr, key->addrlen); + new->addrlen = key->addrlen; +} + +static void nfs_dns_ent_init(struct cache_head *cnew, + struct cache_head *ckey) +{ + struct nfs_dns_ent *new; + struct nfs_dns_ent *key; + + new = container_of(cnew, struct nfs_dns_ent, h); + key = container_of(ckey, struct nfs_dns_ent, h); + + kfree(new->hostname); + new->hostname = kstrndup(key->hostname, key->namelen, GFP_KERNEL); + if (new->hostname) { + new->namelen = key->namelen; + nfs_dns_ent_update(cnew, ckey); + } else { + new->namelen = 0; + new->addrlen = 0; + } +} + +static void nfs_dns_ent_put(struct kref *ref) +{ + struct nfs_dns_ent *item; + + item = container_of(ref, struct nfs_dns_ent, h.ref); + kfree(item->hostname); + kfree(item); +} + +static struct cache_head *nfs_dns_ent_alloc(void) +{ + struct nfs_dns_ent *item = kmalloc(sizeof(*item), GFP_KERNEL); + + if (item != NULL) { + item->hostname = NULL; + item->namelen = 0; + item->addrlen = 0; + return &item->h; + } + return NULL; +}; + +static unsigned int nfs_dns_hash(const struct nfs_dns_ent *key) +{ + return hash_str(key->hostname, NFS_DNS_HASHBITS); +} + +static void nfs_dns_request(struct cache_detail *cd, + struct cache_head *ch, + char **bpp, int *blen) +{ + struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h); + + qword_add(bpp, blen, key->hostname); + (*bpp)[-1] = '\n'; +} + +static int nfs_dns_upcall(struct cache_detail *cd, + struct cache_head *ch) +{ + struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h); + int ret; + + ret = nfs_cache_upcall(cd, key->hostname); + if (ret) + ret = sunrpc_cache_pipe_upcall(cd, ch); + return ret; +} + +static int nfs_dns_match(struct cache_head *ca, + struct cache_head *cb) +{ + struct nfs_dns_ent *a; + struct nfs_dns_ent *b; + + a = container_of(ca, struct nfs_dns_ent, h); + b = container_of(cb, struct nfs_dns_ent, h); + + if (a->namelen == 0 || a->namelen != b->namelen) + return 0; + return memcmp(a->hostname, b->hostname, a->namelen) == 0; +} + +static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd, + struct cache_head *h) +{ + struct nfs_dns_ent *item; + long ttl; + + if (h == NULL) { + seq_puts(m, "# ip address hostname ttl\n"); + return 0; + } + item = container_of(h, struct nfs_dns_ent, h); + ttl = item->h.expiry_time - seconds_since_boot(); + if (ttl < 0) + ttl = 0; + + if (!test_bit(CACHE_NEGATIVE, &h->flags)) { + char buf[INET6_ADDRSTRLEN+IPV6_SCOPE_ID_LEN+1]; + + rpc_ntop((struct sockaddr *)&item->addr, buf, sizeof(buf)); + seq_printf(m, "%15s ", buf); + } else + seq_puts(m, "<none> "); + seq_printf(m, "%15s %ld\n", item->hostname, ttl); + return 0; +} + +static struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd, + struct nfs_dns_ent *key) +{ + struct cache_head *ch; + + ch = sunrpc_cache_lookup(cd, + &key->h, + nfs_dns_hash(key)); + if (!ch) + return NULL; + return container_of(ch, struct nfs_dns_ent, h); +} + +static struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd, + struct nfs_dns_ent *new, + struct nfs_dns_ent *key) +{ + struct cache_head *ch; + + ch = sunrpc_cache_update(cd, + &new->h, &key->h, + nfs_dns_hash(key)); + if (!ch) + return NULL; + return container_of(ch, struct nfs_dns_ent, h); +} + +static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) +{ + char buf1[NFS_DNS_HOSTNAME_MAXLEN+1]; + struct nfs_dns_ent key, *item; + unsigned int ttl; + ssize_t len; + int ret = -EINVAL; + + if (buf[buflen-1] != '\n') + goto out; + buf[buflen-1] = '\0'; + + len = qword_get(&buf, buf1, sizeof(buf1)); + if (len <= 0) + goto out; + key.addrlen = rpc_pton(cd->net, buf1, len, + (struct sockaddr *)&key.addr, + sizeof(key.addr)); + + len = qword_get(&buf, buf1, sizeof(buf1)); + if (len <= 0) + goto out; + + key.hostname = buf1; + key.namelen = len; + memset(&key.h, 0, sizeof(key.h)); + + if (get_uint(&buf, &ttl) < 0) + goto out; + if (ttl == 0) + goto out; + key.h.expiry_time = ttl + seconds_since_boot(); + + ret = -ENOMEM; + item = nfs_dns_lookup(cd, &key); + if (item == NULL) + goto out; + + if (key.addrlen == 0) + set_bit(CACHE_NEGATIVE, &key.h.flags); + + item = nfs_dns_update(cd, &key, item); + if (item == NULL) + goto out; + + ret = 0; + cache_put(&item->h, cd); +out: + return ret; +} + +static int do_cache_lookup(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item, + struct nfs_cache_defer_req *dreq) +{ + int ret = -ENOMEM; + + *item = nfs_dns_lookup(cd, key); + if (*item) { + ret = cache_check(cd, &(*item)->h, &dreq->req); + if (ret) + *item = NULL; + } + return ret; +} + +static int do_cache_lookup_nowait(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item) +{ + int ret = -ENOMEM; + + *item = nfs_dns_lookup(cd, key); + if (!*item) + goto out_err; + ret = -ETIMEDOUT; + if (!test_bit(CACHE_VALID, &(*item)->h.flags) + || (*item)->h.expiry_time < seconds_since_boot() + || cd->flush_time > (*item)->h.last_refresh) + goto out_put; + ret = -ENOENT; + if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags)) + goto out_put; + return 0; +out_put: + cache_put(&(*item)->h, cd); +out_err: + *item = NULL; + return ret; +} + +static int do_cache_lookup_wait(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item) +{ + struct nfs_cache_defer_req *dreq; + int ret = -ENOMEM; + + dreq = nfs_cache_defer_req_alloc(); + if (!dreq) + goto out; + ret = do_cache_lookup(cd, key, item, dreq); + if (ret == -EAGAIN) { + ret = nfs_cache_wait_for_upcall(dreq); + if (!ret) + ret = do_cache_lookup_nowait(cd, key, item); + } + nfs_cache_defer_req_put(dreq); +out: + return ret; +} + +ssize_t nfs_dns_resolve_name(struct net *net, char *name, + size_t namelen, struct sockaddr *sa, size_t salen) +{ + struct nfs_dns_ent key = { + .hostname = name, + .namelen = namelen, + }; + struct nfs_dns_ent *item = NULL; + ssize_t ret; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + ret = do_cache_lookup_wait(nn->nfs_dns_resolve, &key, &item); + if (ret == 0) { + if (salen >= item->addrlen) { + memcpy(sa, &item->addr, item->addrlen); + ret = item->addrlen; + } else + ret = -EOVERFLOW; + cache_put(&item->h, nn->nfs_dns_resolve); + } else if (ret == -ENOENT) + ret = -ESRCH; + return ret; +} + +static struct cache_detail nfs_dns_resolve_template = { + .owner = THIS_MODULE, + .hash_size = NFS_DNS_HASHTBL_SIZE, + .name = "dns_resolve", + .cache_put = nfs_dns_ent_put, + .cache_upcall = nfs_dns_upcall, + .cache_request = nfs_dns_request, + .cache_parse = nfs_dns_parse, + .cache_show = nfs_dns_show, + .match = nfs_dns_match, + .init = nfs_dns_ent_init, + .update = nfs_dns_ent_update, + .alloc = nfs_dns_ent_alloc, +}; + + +int nfs_dns_resolver_cache_init(struct net *net) +{ + int err; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + nn->nfs_dns_resolve = cache_create_net(&nfs_dns_resolve_template, net); + if (IS_ERR(nn->nfs_dns_resolve)) + return PTR_ERR(nn->nfs_dns_resolve); + + err = nfs_cache_register_net(net, nn->nfs_dns_resolve); + if (err) + goto err_reg; + return 0; + +err_reg: + cache_destroy_net(nn->nfs_dns_resolve, net); + return err; +} + +void nfs_dns_resolver_cache_destroy(struct net *net) +{ + struct nfs_net *nn = net_generic(net, nfs_net_id); + + nfs_cache_unregister_net(net, nn->nfs_dns_resolve); + cache_destroy_net(nn->nfs_dns_resolve, net); +} + +static int nfs4_dns_net_init(struct net *net) +{ + return nfs_dns_resolver_cache_init(net); +} + +static void nfs4_dns_net_exit(struct net *net) +{ + nfs_dns_resolver_cache_destroy(net); +} + +static struct pernet_operations nfs4_dns_resolver_ops = { + .init = nfs4_dns_net_init, + .exit = nfs4_dns_net_exit, +}; + +static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct super_block *sb = ptr; + struct net *net = sb->s_fs_info; + struct nfs_net *nn = net_generic(net, nfs_net_id); + struct cache_detail *cd = nn->nfs_dns_resolve; + int ret = 0; + + if (cd == NULL) + return 0; + + if (!try_module_get(THIS_MODULE)) + return 0; + + switch (event) { + case RPC_PIPEFS_MOUNT: + ret = nfs_cache_register_sb(sb, cd); + break; + case RPC_PIPEFS_UMOUNT: + nfs_cache_unregister_sb(sb, cd); + break; + default: + ret = -ENOTSUPP; + break; + } + module_put(THIS_MODULE); + return ret; +} + +static struct notifier_block nfs_dns_resolver_block = { + .notifier_call = rpc_pipefs_event, +}; + +int nfs_dns_resolver_init(void) +{ + int err; + + err = register_pernet_subsys(&nfs4_dns_resolver_ops); + if (err < 0) + goto out; + err = rpc_pipefs_notifier_register(&nfs_dns_resolver_block); + if (err < 0) + goto out1; + return 0; +out1: + unregister_pernet_subsys(&nfs4_dns_resolver_ops); +out: + return err; +} + +void nfs_dns_resolver_destroy(void) +{ + rpc_pipefs_notifier_unregister(&nfs_dns_resolver_block); + unregister_pernet_subsys(&nfs4_dns_resolver_ops); +} +#endif diff --git a/kernel/fs/nfs/dns_resolve.h b/kernel/fs/nfs/dns_resolve.h new file mode 100644 index 000000000..2e4f596d2 --- /dev/null +++ b/kernel/fs/nfs/dns_resolve.h @@ -0,0 +1,36 @@ +/* + * Resolve DNS hostnames into valid ip addresses + */ +#ifndef __LINUX_FS_NFS_DNS_RESOLVE_H +#define __LINUX_FS_NFS_DNS_RESOLVE_H + +#define NFS_DNS_HOSTNAME_MAXLEN (128) + + +#ifdef CONFIG_NFS_USE_KERNEL_DNS +static inline int nfs_dns_resolver_init(void) +{ + return 0; +} + +static inline void nfs_dns_resolver_destroy(void) +{} + +static inline int nfs_dns_resolver_cache_init(struct net *net) +{ + return 0; +} + +static inline void nfs_dns_resolver_cache_destroy(struct net *net) +{} +#else +extern int nfs_dns_resolver_init(void); +extern void nfs_dns_resolver_destroy(void); +extern int nfs_dns_resolver_cache_init(struct net *net); +extern void nfs_dns_resolver_cache_destroy(struct net *net); +#endif + +extern ssize_t nfs_dns_resolve_name(struct net *net, char *name, + size_t namelen, struct sockaddr *sa, size_t salen); + +#endif diff --git a/kernel/fs/nfs/file.c b/kernel/fs/nfs/file.c new file mode 100644 index 000000000..8b8d83a52 --- /dev/null +++ b/kernel/fs/nfs/file.c @@ -0,0 +1,947 @@ +/* + * linux/fs/nfs/file.c + * + * Copyright (C) 1992 Rick Sladkey + * + * Changes Copyright (C) 1994 by Florian La Roche + * - Do not copy data too often around in the kernel. + * - In nfs_file_read the return value of kmalloc wasn't checked. + * - Put in a better version of read look-ahead buffering. Original idea + * and implementation by Wai S Kok elekokws@ee.nus.sg. + * + * Expire cache on write to a file by Wai S Kok (Oct 1994). + * + * Total rewrite of read side for new NFS buffer cache.. Linus. + * + * nfs regular file handling functions + */ + +#include <linux/module.h> +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fcntl.h> +#include <linux/stat.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/gfp.h> +#include <linux/swap.h> + +#include <asm/uaccess.h> + +#include "delegation.h" +#include "internal.h" +#include "iostat.h" +#include "fscache.h" +#include "pnfs.h" + +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_FILE + +static const struct vm_operations_struct nfs_file_vm_ops; + +/* Hack for future NFS swap support */ +#ifndef IS_SWAPFILE +# define IS_SWAPFILE(inode) (0) +#endif + +int nfs_check_flags(int flags) +{ + if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT)) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_GPL(nfs_check_flags); + +/* + * Open file + */ +static int +nfs_file_open(struct inode *inode, struct file *filp) +{ + int res; + + dprintk("NFS: open file(%pD2)\n", filp); + + nfs_inc_stats(inode, NFSIOS_VFSOPEN); + res = nfs_check_flags(filp->f_flags); + if (res) + return res; + + res = nfs_open(inode, filp); + return res; +} + +int +nfs_file_release(struct inode *inode, struct file *filp) +{ + dprintk("NFS: release(%pD2)\n", filp); + + nfs_inc_stats(inode, NFSIOS_VFSRELEASE); + return nfs_release(inode, filp); +} +EXPORT_SYMBOL_GPL(nfs_file_release); + +/** + * nfs_revalidate_size - Revalidate the file size + * @inode - pointer to inode struct + * @file - pointer to struct file + * + * Revalidates the file length. This is basically a wrapper around + * nfs_revalidate_inode() that takes into account the fact that we may + * have cached writes (in which case we don't care about the server's + * idea of what the file length is), or O_DIRECT (in which case we + * shouldn't trust the cache). + */ +static int nfs_revalidate_file_size(struct inode *inode, struct file *filp) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_inode *nfsi = NFS_I(inode); + + if (nfs_have_delegated_attributes(inode)) + goto out_noreval; + + if (filp->f_flags & O_DIRECT) + goto force_reval; + if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) + goto force_reval; + if (nfs_attribute_timeout(inode)) + goto force_reval; +out_noreval: + return 0; +force_reval: + return __nfs_revalidate_inode(server, inode); +} + +loff_t nfs_file_llseek(struct file *filp, loff_t offset, int whence) +{ + dprintk("NFS: llseek file(%pD2, %lld, %d)\n", + filp, offset, whence); + + /* + * whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate + * the cached file length + */ + if (whence != SEEK_SET && whence != SEEK_CUR) { + struct inode *inode = filp->f_mapping->host; + + int retval = nfs_revalidate_file_size(inode, filp); + if (retval < 0) + return (loff_t)retval; + } + + return generic_file_llseek(filp, offset, whence); +} +EXPORT_SYMBOL_GPL(nfs_file_llseek); + +/* + * Flush all dirty pages, and check for write errors. + */ +int +nfs_file_flush(struct file *file, fl_owner_t id) +{ + struct inode *inode = file_inode(file); + + dprintk("NFS: flush(%pD2)\n", file); + + nfs_inc_stats(inode, NFSIOS_VFSFLUSH); + if ((file->f_mode & FMODE_WRITE) == 0) + return 0; + + /* + * If we're holding a write delegation, then just start the i/o + * but don't wait for completion (or send a commit). + */ + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) + return filemap_fdatawrite(file->f_mapping); + + /* Flush writes to the server and return any errors */ + return vfs_fsync(file, 0); +} +EXPORT_SYMBOL_GPL(nfs_file_flush); + +ssize_t +nfs_file_read(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + ssize_t result; + + if (iocb->ki_flags & IOCB_DIRECT) + return nfs_file_direct_read(iocb, to, iocb->ki_pos); + + dprintk("NFS: read(%pD2, %zu@%lu)\n", + iocb->ki_filp, + iov_iter_count(to), (unsigned long) iocb->ki_pos); + + result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping); + if (!result) { + result = generic_file_read_iter(iocb, to); + if (result > 0) + nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result); + } + return result; +} +EXPORT_SYMBOL_GPL(nfs_file_read); + +ssize_t +nfs_file_splice_read(struct file *filp, loff_t *ppos, + struct pipe_inode_info *pipe, size_t count, + unsigned int flags) +{ + struct inode *inode = file_inode(filp); + ssize_t res; + + dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n", + filp, (unsigned long) count, (unsigned long long) *ppos); + + res = nfs_revalidate_mapping_protected(inode, filp->f_mapping); + if (!res) { + res = generic_file_splice_read(filp, ppos, pipe, count, flags); + if (res > 0) + nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res); + } + return res; +} +EXPORT_SYMBOL_GPL(nfs_file_splice_read); + +int +nfs_file_mmap(struct file * file, struct vm_area_struct * vma) +{ + struct inode *inode = file_inode(file); + int status; + + dprintk("NFS: mmap(%pD2)\n", file); + + /* Note: generic_file_mmap() returns ENOSYS on nommu systems + * so we call that before revalidating the mapping + */ + status = generic_file_mmap(file, vma); + if (!status) { + vma->vm_ops = &nfs_file_vm_ops; + status = nfs_revalidate_mapping(inode, file->f_mapping); + } + return status; +} +EXPORT_SYMBOL_GPL(nfs_file_mmap); + +/* + * Flush any dirty pages for this process, and check for write errors. + * The return status from this call provides a reliable indication of + * whether any write errors occurred for this process. + * + * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to + * disk, but it retrieves and clears ctx->error after synching, despite + * the two being set at the same time in nfs_context_set_write_error(). + * This is because the former is used to notify the _next_ call to + * nfs_file_write() that a write error occurred, and hence cause it to + * fall back to doing a synchronous write. + */ +int +nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync) +{ + struct nfs_open_context *ctx = nfs_file_open_context(file); + struct inode *inode = file_inode(file); + int have_error, do_resend, status; + int ret = 0; + + dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync); + + nfs_inc_stats(inode, NFSIOS_VFSFSYNC); + do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); + have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); + status = nfs_commit_inode(inode, FLUSH_SYNC); + have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); + if (have_error) { + ret = xchg(&ctx->error, 0); + if (ret) + goto out; + } + if (status < 0) { + ret = status; + goto out; + } + do_resend |= test_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); + if (do_resend) + ret = -EAGAIN; +out: + return ret; +} +EXPORT_SYMBOL_GPL(nfs_file_fsync_commit); + +static int +nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + int ret; + struct inode *inode = file_inode(file); + + trace_nfs_fsync_enter(inode); + + nfs_inode_dio_wait(inode); + do { + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret != 0) + break; + mutex_lock(&inode->i_mutex); + ret = nfs_file_fsync_commit(file, start, end, datasync); + mutex_unlock(&inode->i_mutex); + /* + * If nfs_file_fsync_commit detected a server reboot, then + * resend all dirty pages that might have been covered by + * the NFS_CONTEXT_RESEND_WRITES flag + */ + start = 0; + end = LLONG_MAX; + } while (ret == -EAGAIN); + + trace_nfs_fsync_exit(inode, ret); + return ret; +} + +/* + * Decide whether a read/modify/write cycle may be more efficient + * then a modify/write/read cycle when writing to a page in the + * page cache. + * + * The modify/write/read cycle may occur if a page is read before + * being completely filled by the writer. In this situation, the + * page must be completely written to stable storage on the server + * before it can be refilled by reading in the page from the server. + * This can lead to expensive, small, FILE_SYNC mode writes being + * done. + * + * It may be more efficient to read the page first if the file is + * open for reading in addition to writing, the page is not marked + * as Uptodate, it is not dirty or waiting to be committed, + * indicating that it was previously allocated and then modified, + * that there were valid bytes of data in that range of the file, + * and that the new data won't completely replace the old data in + * that range of the file. + */ +static int nfs_want_read_modify_write(struct file *file, struct page *page, + loff_t pos, unsigned len) +{ + unsigned int pglen = nfs_page_length(page); + unsigned int offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned int end = offset + len; + + if (pnfs_ld_read_whole_page(file->f_mapping->host)) { + if (!PageUptodate(page)) + return 1; + return 0; + } + + if ((file->f_mode & FMODE_READ) && /* open for read? */ + !PageUptodate(page) && /* Uptodate? */ + !PagePrivate(page) && /* i/o request already? */ + pglen && /* valid bytes of file? */ + (end < pglen || offset)) /* replace all valid bytes? */ + return 1; + return 0; +} + +/* + * This does the "real" work of the write. We must allocate and lock the + * page to be sent back to the generic routine, which then copies the + * data from user space. + * + * If the writer ends up delaying the write, the writer needs to + * increment the page use counts until he is done with the page. + */ +static int nfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + int ret; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + struct page *page; + int once_thru = 0; + + dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n", + file, mapping->host->i_ino, len, (long long) pos); + +start: + /* + * Prevent starvation issues if someone is doing a consistency + * sync-to-disk + */ + ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (ret) + return ret; + /* + * Wait for O_DIRECT to complete + */ + nfs_inode_dio_wait(mapping->host); + + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + *pagep = page; + + ret = nfs_flush_incompatible(file, page); + if (ret) { + unlock_page(page); + page_cache_release(page); + } else if (!once_thru && + nfs_want_read_modify_write(file, page, pos, len)) { + once_thru = 1; + ret = nfs_readpage(file, page); + page_cache_release(page); + if (!ret) + goto start; + } + return ret; +} + +static int nfs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + unsigned offset = pos & (PAGE_CACHE_SIZE - 1); + struct nfs_open_context *ctx = nfs_file_open_context(file); + int status; + + dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n", + file, mapping->host->i_ino, len, (long long) pos); + + /* + * Zero any uninitialised parts of the page, and then mark the page + * as up to date if it turns out that we're extending the file. + */ + if (!PageUptodate(page)) { + unsigned pglen = nfs_page_length(page); + unsigned end = offset + len; + + if (pglen == 0) { + zero_user_segments(page, 0, offset, + end, PAGE_CACHE_SIZE); + SetPageUptodate(page); + } else if (end >= pglen) { + zero_user_segment(page, end, PAGE_CACHE_SIZE); + if (offset == 0) + SetPageUptodate(page); + } else + zero_user_segment(page, pglen, PAGE_CACHE_SIZE); + } + + status = nfs_updatepage(file, page, offset, copied); + + unlock_page(page); + page_cache_release(page); + + if (status < 0) + return status; + NFS_I(mapping->host)->write_io += copied; + + if (nfs_ctx_key_to_expire(ctx)) { + status = nfs_wb_all(mapping->host); + if (status < 0) + return status; + } + + return copied; +} + +/* + * Partially or wholly invalidate a page + * - Release the private state associated with a page if undergoing complete + * page invalidation + * - Called if either PG_private or PG_fscache is set on the page + * - Caller holds page lock + */ +static void nfs_invalidate_page(struct page *page, unsigned int offset, + unsigned int length) +{ + dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %u, %u)\n", + page, offset, length); + + if (offset != 0 || length < PAGE_CACHE_SIZE) + return; + /* Cancel any unstarted writes on this page */ + nfs_wb_page_cancel(page_file_mapping(page)->host, page); + + nfs_fscache_invalidate_page(page, page->mapping->host); +} + +/* + * Attempt to release the private state associated with a page + * - Called if either PG_private or PG_fscache is set on the page + * - Caller holds page lock + * - Return true (may release page) or false (may not) + */ +static int nfs_release_page(struct page *page, gfp_t gfp) +{ + struct address_space *mapping = page->mapping; + + dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); + + /* Always try to initiate a 'commit' if relevant, but only + * wait for it if __GFP_WAIT is set. Even then, only wait 1 + * second and only if the 'bdi' is not congested. + * Waiting indefinitely can cause deadlocks when the NFS + * server is on this machine, when a new TCP connection is + * needed and in other rare cases. There is no particular + * need to wait extensively here. A short wait has the + * benefit that someone else can worry about the freezer. + */ + if (mapping) { + struct nfs_server *nfss = NFS_SERVER(mapping->host); + nfs_commit_inode(mapping->host, 0); + if ((gfp & __GFP_WAIT) && + !bdi_write_congested(&nfss->backing_dev_info)) { + wait_on_page_bit_killable_timeout(page, PG_private, + HZ); + if (PagePrivate(page)) + set_bdi_congested(&nfss->backing_dev_info, + BLK_RW_ASYNC); + } + } + /* If PagePrivate() is set, then the page is not freeable */ + if (PagePrivate(page)) + return 0; + return nfs_fscache_release_page(page, gfp); +} + +static void nfs_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct nfs_inode *nfsi; + struct address_space *mapping = page_file_mapping(page); + + if (!mapping || PageSwapCache(page)) + return; + + /* + * Check if an unstable page is currently being committed and + * if so, have the VM treat it as if the page is under writeback + * so it will not block due to pages that will shortly be freeable. + */ + nfsi = NFS_I(mapping->host); + if (test_bit(NFS_INO_COMMIT, &nfsi->flags)) { + *writeback = true; + return; + } + + /* + * If PagePrivate() is set, then the page is not freeable and as the + * inode is not being committed, it's not going to be cleaned in the + * near future so treat it as dirty + */ + if (PagePrivate(page)) + *dirty = true; +} + +/* + * Attempt to clear the private state associated with a page when an error + * occurs that requires the cached contents of an inode to be written back or + * destroyed + * - Called if either PG_private or fscache is set on the page + * - Caller holds page lock + * - Return 0 if successful, -error otherwise + */ +static int nfs_launder_page(struct page *page) +{ + struct inode *inode = page_file_mapping(page)->host; + struct nfs_inode *nfsi = NFS_I(inode); + + dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n", + inode->i_ino, (long long)page_offset(page)); + + nfs_fscache_wait_on_page_write(nfsi, page); + return nfs_wb_page(inode, page); +} + +#ifdef CONFIG_NFS_SWAP +static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, + sector_t *span) +{ + int ret; + struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); + + *span = sis->pages; + + rcu_read_lock(); + ret = xs_swapper(rcu_dereference(clnt->cl_xprt), 1); + rcu_read_unlock(); + + return ret; +} + +static void nfs_swap_deactivate(struct file *file) +{ + struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); + + rcu_read_lock(); + xs_swapper(rcu_dereference(clnt->cl_xprt), 0); + rcu_read_unlock(); +} +#endif + +const struct address_space_operations nfs_file_aops = { + .readpage = nfs_readpage, + .readpages = nfs_readpages, + .set_page_dirty = __set_page_dirty_nobuffers, + .writepage = nfs_writepage, + .writepages = nfs_writepages, + .write_begin = nfs_write_begin, + .write_end = nfs_write_end, + .invalidatepage = nfs_invalidate_page, + .releasepage = nfs_release_page, + .direct_IO = nfs_direct_IO, + .migratepage = nfs_migrate_page, + .launder_page = nfs_launder_page, + .is_dirty_writeback = nfs_check_dirty_writeback, + .error_remove_page = generic_error_remove_page, +#ifdef CONFIG_NFS_SWAP + .swap_activate = nfs_swap_activate, + .swap_deactivate = nfs_swap_deactivate, +#endif +}; + +/* + * Notification that a PTE pointing to an NFS page is about to be made + * writable, implying that someone is about to modify the page through a + * shared-writable mapping + */ +static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct file *filp = vma->vm_file; + struct inode *inode = file_inode(filp); + unsigned pagelen; + int ret = VM_FAULT_NOPAGE; + struct address_space *mapping; + + dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n", + filp, filp->f_mapping->host->i_ino, + (long long)page_offset(page)); + + /* make sure the cache has finished storing the page */ + nfs_fscache_wait_on_page_write(NFS_I(inode), page); + + wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING, + nfs_wait_bit_killable, TASK_KILLABLE); + + lock_page(page); + mapping = page_file_mapping(page); + if (mapping != inode->i_mapping) + goto out_unlock; + + wait_on_page_writeback(page); + + pagelen = nfs_page_length(page); + if (pagelen == 0) + goto out_unlock; + + ret = VM_FAULT_LOCKED; + if (nfs_flush_incompatible(filp, page) == 0 && + nfs_updatepage(filp, page, 0, pagelen) == 0) + goto out; + + ret = VM_FAULT_SIGBUS; +out_unlock: + unlock_page(page); +out: + return ret; +} + +static const struct vm_operations_struct nfs_file_vm_ops = { + .fault = filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = nfs_vm_page_mkwrite, +}; + +static int nfs_need_sync_write(struct file *filp, struct inode *inode) +{ + struct nfs_open_context *ctx; + + if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC)) + return 1; + ctx = nfs_file_open_context(filp); + if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) || + nfs_ctx_key_to_expire(ctx)) + return 1; + return 0; +} + +ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + unsigned long written = 0; + ssize_t result; + size_t count = iov_iter_count(from); + + result = nfs_key_timeout_notify(file, inode); + if (result) + return result; + + if (iocb->ki_flags & IOCB_DIRECT) { + result = generic_write_checks(iocb, from); + if (result <= 0) + return result; + return nfs_file_direct_write(iocb, from); + } + + dprintk("NFS: write(%pD2, %zu@%Ld)\n", + file, count, (long long) iocb->ki_pos); + + result = -EBUSY; + if (IS_SWAPFILE(inode)) + goto out_swapfile; + /* + * O_APPEND implies that we must revalidate the file length. + */ + if (iocb->ki_flags & IOCB_APPEND) { + result = nfs_revalidate_file_size(inode, file); + if (result) + goto out; + } + + result = count; + if (!count) + goto out; + + result = generic_file_write_iter(iocb, from); + if (result > 0) + written = result; + + /* Return error values for O_DSYNC and IS_SYNC() */ + if (result >= 0 && nfs_need_sync_write(file, inode)) { + int err = vfs_fsync(file, 0); + if (err < 0) + result = err; + } + if (result > 0) + nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written); +out: + return result; + +out_swapfile: + printk(KERN_INFO "NFS: attempt to write to active swap file!\n"); + goto out; +} +EXPORT_SYMBOL_GPL(nfs_file_write); + +static int +do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) +{ + struct inode *inode = filp->f_mapping->host; + int status = 0; + unsigned int saved_type = fl->fl_type; + + /* Try local locking first */ + posix_test_lock(filp, fl); + if (fl->fl_type != F_UNLCK) { + /* found a conflict */ + goto out; + } + fl->fl_type = saved_type; + + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) + goto out_noconflict; + + if (is_local) + goto out_noconflict; + + status = NFS_PROTO(inode)->lock(filp, cmd, fl); +out: + return status; +out_noconflict: + fl->fl_type = F_UNLCK; + goto out; +} + +static int do_vfs_lock(struct file *file, struct file_lock *fl) +{ + int res = 0; + switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { + case FL_POSIX: + res = posix_lock_file_wait(file, fl); + break; + case FL_FLOCK: + res = flock_lock_file_wait(file, fl); + break; + default: + BUG(); + } + return res; +} + +static int +do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) +{ + struct inode *inode = filp->f_mapping->host; + struct nfs_lock_context *l_ctx; + int status; + + /* + * Flush all pending writes before doing anything + * with locks.. + */ + vfs_fsync(filp, 0); + + l_ctx = nfs_get_lock_context(nfs_file_open_context(filp)); + if (!IS_ERR(l_ctx)) { + status = nfs_iocounter_wait(&l_ctx->io_count); + nfs_put_lock_context(l_ctx); + if (status < 0) + return status; + } + + /* NOTE: special case + * If we're signalled while cleaning up locks on process exit, we + * still need to complete the unlock. + */ + /* + * Use local locking if mounted with "-onolock" or with appropriate + * "-olocal_lock=" + */ + if (!is_local) + status = NFS_PROTO(inode)->lock(filp, cmd, fl); + else + status = do_vfs_lock(filp, fl); + return status; +} + +static int +is_time_granular(struct timespec *ts) { + return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000)); +} + +static int +do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) +{ + struct inode *inode = filp->f_mapping->host; + int status; + + /* + * Flush all pending writes before doing anything + * with locks.. + */ + status = nfs_sync_mapping(filp->f_mapping); + if (status != 0) + goto out; + + /* + * Use local locking if mounted with "-onolock" or with appropriate + * "-olocal_lock=" + */ + if (!is_local) + status = NFS_PROTO(inode)->lock(filp, cmd, fl); + else + status = do_vfs_lock(filp, fl); + if (status < 0) + goto out; + + /* + * Revalidate the cache if the server has time stamps granular + * enough to detect subsecond changes. Otherwise, clear the + * cache to prevent missing any changes. + * + * This makes locking act as a cache coherency point. + */ + nfs_sync_mapping(filp->f_mapping); + if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) { + if (is_time_granular(&NFS_SERVER(inode)->time_delta)) + __nfs_revalidate_inode(NFS_SERVER(inode), inode); + else + nfs_zap_caches(inode); + } +out: + return status; +} + +/* + * Lock a (portion of) a file + */ +int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = filp->f_mapping->host; + int ret = -ENOLCK; + int is_local = 0; + + dprintk("NFS: lock(%pD2, t=%x, fl=%x, r=%lld:%lld)\n", + filp, fl->fl_type, fl->fl_flags, + (long long)fl->fl_start, (long long)fl->fl_end); + + nfs_inc_stats(inode, NFSIOS_VFSLOCK); + + /* No mandatory locks over NFS */ + if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) + goto out_err; + + if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL) + is_local = 1; + + if (NFS_PROTO(inode)->lock_check_bounds != NULL) { + ret = NFS_PROTO(inode)->lock_check_bounds(fl); + if (ret < 0) + goto out_err; + } + + if (IS_GETLK(cmd)) + ret = do_getlk(filp, cmd, fl, is_local); + else if (fl->fl_type == F_UNLCK) + ret = do_unlk(filp, cmd, fl, is_local); + else + ret = do_setlk(filp, cmd, fl, is_local); +out_err: + return ret; +} +EXPORT_SYMBOL_GPL(nfs_lock); + +/* + * Lock a (portion of) a file + */ +int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = filp->f_mapping->host; + int is_local = 0; + + dprintk("NFS: flock(%pD2, t=%x, fl=%x)\n", + filp, fl->fl_type, fl->fl_flags); + + if (!(fl->fl_flags & FL_FLOCK)) + return -ENOLCK; + + /* + * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of + * any standard. In principle we might be able to support LOCK_MAND + * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the + * NFS code is not set up for it. + */ + if (fl->fl_type & LOCK_MAND) + return -EINVAL; + + if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK) + is_local = 1; + + /* We're simulating flock() locks using posix locks on the server */ + if (fl->fl_type == F_UNLCK) + return do_unlk(filp, cmd, fl, is_local); + return do_setlk(filp, cmd, fl, is_local); +} +EXPORT_SYMBOL_GPL(nfs_flock); + +const struct file_operations nfs_file_operations = { + .llseek = nfs_file_llseek, + .read_iter = nfs_file_read, + .write_iter = nfs_file_write, + .mmap = nfs_file_mmap, + .open = nfs_file_open, + .flush = nfs_file_flush, + .release = nfs_file_release, + .fsync = nfs_file_fsync, + .lock = nfs_lock, + .flock = nfs_flock, + .splice_read = nfs_file_splice_read, + .splice_write = iter_file_splice_write, + .check_flags = nfs_check_flags, + .setlease = simple_nosetlease, +}; +EXPORT_SYMBOL_GPL(nfs_file_operations); diff --git a/kernel/fs/nfs/filelayout/Makefile b/kernel/fs/nfs/filelayout/Makefile new file mode 100644 index 000000000..8516cdffb --- /dev/null +++ b/kernel/fs/nfs/filelayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Files Layout Driver kernel module +# +obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o +nfs_layout_nfsv41_files-y := filelayout.o filelayoutdev.o diff --git a/kernel/fs/nfs/filelayout/filelayout.c b/kernel/fs/nfs/filelayout/filelayout.c new file mode 100644 index 000000000..a46bf6de9 --- /dev/null +++ b/kernel/fs/nfs/filelayout/filelayout.c @@ -0,0 +1,1162 @@ +/* + * Module for the pnfs nfs4 file layout driver. + * Defines all I/O and Policy interface operations, plus code + * to register itself with the pNFS client. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/module.h> + +#include <linux/sunrpc/metrics.h> + +#include "../nfs4session.h" +#include "../internal.h" +#include "../delegation.h" +#include "filelayout.h" +#include "../nfs4trace.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>"); +MODULE_DESCRIPTION("The NFSv4 file layout driver"); + +#define FILELAYOUT_POLL_RETRY_MAX (15*HZ) + +static loff_t +filelayout_get_dense_offset(struct nfs4_filelayout_segment *flseg, + loff_t offset) +{ + u32 stripe_width = flseg->stripe_unit * flseg->dsaddr->stripe_count; + u64 stripe_no; + u32 rem; + + offset -= flseg->pattern_offset; + stripe_no = div_u64(offset, stripe_width); + div_u64_rem(offset, flseg->stripe_unit, &rem); + + return stripe_no * flseg->stripe_unit + rem; +} + +/* This function is used by the layout driver to calculate the + * offset of the file on the dserver based on whether the + * layout type is STRIPE_DENSE or STRIPE_SPARSE + */ +static loff_t +filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + + switch (flseg->stripe_type) { + case STRIPE_SPARSE: + return offset; + + case STRIPE_DENSE: + return filelayout_get_dense_offset(flseg, offset); + } + + BUG(); +} + +static void filelayout_reset_write(struct nfs_pgio_header *hdr) +{ + struct rpc_task *task = &hdr->task; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_write_done_resend_to_mds(hdr); + } +} + +static void filelayout_reset_read(struct nfs_pgio_header *hdr) +{ + struct rpc_task *task = &hdr->task; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_read_done_resend_to_mds(hdr); + } +} + +static int filelayout_async_handle_error(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_hdr *lo = lseg->pls_layout; + struct inode *inode = lo->plh_inode; + struct nfs_server *mds_server = NFS_SERVER(inode); + struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); + struct nfs_client *mds_client = mds_server->nfs_client; + struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; + + if (task->tk_status >= 0) + return 0; + + switch (task->tk_status) { + /* MDS state errors */ + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OPENMODE: + if (state == NULL) + break; + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + goto wait_on_recovery; + case -NFS4ERR_EXPIRED: + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + } + nfs4_schedule_lease_recovery(mds_client); + goto wait_on_recovery; + /* DS session errors */ + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + dprintk("%s ERROR %d, Reset session. Exchangeid " + "flags 0x%x\n", __func__, task->tk_status, + clp->cl_exchange_flags); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + break; + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + rpc_delay(task, FILELAYOUT_POLL_RETRY_MAX); + break; + case -NFS4ERR_RETRY_UNCACHED_REP: + break; + /* Invalidate Layout errors */ + case -NFS4ERR_PNFS_NO_LAYOUT: + case -ESTALE: /* mapped NFS4ERR_STALE */ + case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ + case -EISDIR: /* mapped NFS4ERR_ISDIR */ + case -NFS4ERR_FHEXPIRED: + case -NFS4ERR_WRONG_TYPE: + dprintk("%s Invalid layout error %d\n", __func__, + task->tk_status); + /* + * Destroy layout so new i/o will get a new layout. + * Layout will not be destroyed until all current lseg + * references are put. Mark layout as invalid to resend failed + * i/o and all i/o waiting on the slot table to the MDS until + * layout is destroyed and a new valid layout is obtained. + */ + pnfs_destroy_layout(NFS_I(inode)); + rpc_wake_up(&tbl->slot_tbl_waitq); + goto reset; + /* RPC connection errors */ + case -ECONNREFUSED: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EIO: + case -ETIMEDOUT: + case -EPIPE: + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + pnfs_error_mark_layout_for_return(inode, lseg); + rpc_wake_up(&tbl->slot_tbl_waitq); + /* fall through */ + default: +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, + task->tk_status); + return -NFS4ERR_RESET_TO_MDS; + } +out: + task->tk_status = 0; + return -EAGAIN; +out_bad_stateid: + task->tk_status = -EIO; + return 0; +wait_on_recovery: + rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) + rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); + goto out; +} + +/* NFS_PROTO call done callback routines */ + +static int filelayout_read_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + int err; + + trace_nfs4_pnfs_read(hdr, task->tk_status); + err = filelayout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg); + + switch (err) { + case -NFS4ERR_RESET_TO_MDS: + filelayout_reset_read(hdr); + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + return 0; +} + +/* + * We reference the rpc_cred of the first WRITE that triggers the need for + * a LAYOUTCOMMIT, and use it to send the layoutcommit compound. + * rfc5661 is not clear about which credential should be used. + */ +static void +filelayout_set_layoutcommit(struct nfs_pgio_header *hdr) +{ + + if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds || + hdr->res.verf->committed != NFS_DATA_SYNC) + return; + + pnfs_set_layoutcommit(hdr->inode, hdr->lseg, + hdr->mds_offset + hdr->res.count); + dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); +} + +bool +filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node) +{ + return filelayout_test_devid_invalid(node) || + nfs4_test_deviceid_unavailable(node); +} + +static bool +filelayout_reset_to_mds(struct pnfs_layout_segment *lseg) +{ + struct nfs4_deviceid_node *node = FILELAYOUT_DEVID_NODE(lseg); + + return filelayout_test_devid_unavailable(node); +} + +/* + * Call ops for the async read/write cases + * In the case of dense layouts, the offset needs to be reset to its + * original value. + */ +static void filelayout_read_prepare(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return; + } + if (filelayout_reset_to_mds(hdr->lseg)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + filelayout_reset_read(hdr); + rpc_exit(task, 0); + return; + } + hdr->pgio_done_cb = filelayout_read_done_cb; + + if (nfs41_setup_sequence(hdr->ds_clp->cl_session, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_READ) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void filelayout_read_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs41_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, data); +} + +static void filelayout_read_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics); +} + +static int filelayout_write_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + int err; + + trace_nfs4_pnfs_write(hdr, task->tk_status); + err = filelayout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg); + + switch (err) { + case -NFS4ERR_RESET_TO_MDS: + filelayout_reset_write(hdr); + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + filelayout_set_layoutcommit(hdr); + return 0; +} + +static int filelayout_commit_done_cb(struct rpc_task *task, + struct nfs_commit_data *data) +{ + int err; + + trace_nfs4_pnfs_commit_ds(data, task->tk_status); + err = filelayout_async_handle_error(task, NULL, data->ds_clp, + data->lseg); + + switch (err) { + case -NFS4ERR_RESET_TO_MDS: + pnfs_generic_prepare_to_resend_writes(data); + return -EAGAIN; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (data->verf.committed == NFS_UNSTABLE) + pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb); + + return 0; +} + +static void filelayout_write_prepare(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return; + } + if (filelayout_reset_to_mds(hdr->lseg)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + filelayout_reset_write(hdr); + rpc_exit(task, 0); + return; + } + if (nfs41_setup_sequence(hdr->ds_clp->cl_session, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_WRITE) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void filelayout_write_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs41_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, data); +} + +static void filelayout_write_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics); +} + +static void filelayout_commit_prepare(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + nfs41_setup_sequence(wdata->ds_clp->cl_session, + &wdata->args.seq_args, + &wdata->res.seq_res, + task); +} + +static void filelayout_commit_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *cdata = data; + + rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics); +} + +static const struct rpc_call_ops filelayout_read_call_ops = { + .rpc_call_prepare = filelayout_read_prepare, + .rpc_call_done = filelayout_read_call_done, + .rpc_count_stats = filelayout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops filelayout_write_call_ops = { + .rpc_call_prepare = filelayout_write_prepare, + .rpc_call_done = filelayout_write_call_done, + .rpc_count_stats = filelayout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops filelayout_commit_call_ops = { + .rpc_call_prepare = filelayout_commit_prepare, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = filelayout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static enum pnfs_try_status +filelayout_read_pagelist(struct nfs_pgio_header *hdr) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + loff_t offset = hdr->args.offset; + u32 j, idx; + struct nfs_fh *fh; + + dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", + __func__, hdr->inode->i_ino, + hdr->args.pgbase, (size_t)hdr->args.count, offset); + + /* Retrieve the correct rpc_client for the byte range */ + j = nfs4_fl_calc_j_index(lseg, offset); + idx = nfs4_fl_calc_ds_index(lseg, j); + ds = nfs4_fl_prepare_ds(lseg, idx); + if (!ds) + return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + + dprintk("%s USE DS: %s cl_count %d\n", __func__, + ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); + + /* No multipath support. Use first DS */ + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + hdr->ds_commit_idx = idx; + fh = nfs4_fl_select_ds_fh(lseg, j); + if (fh) + hdr->args.fh = fh; + + hdr->args.offset = filelayout_get_dserver_offset(lseg, offset); + hdr->mds_offset = offset; + + /* Perform an asynchronous read to ds */ + nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, + NFS_PROTO(hdr->inode), &filelayout_read_call_ops, + 0, RPC_TASK_SOFTCONN); + return PNFS_ATTEMPTED; +} + +/* Perform async writes. */ +static enum pnfs_try_status +filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + loff_t offset = hdr->args.offset; + u32 j, idx; + struct nfs_fh *fh; + + /* Retrieve the correct rpc_client for the byte range */ + j = nfs4_fl_calc_j_index(lseg, offset); + idx = nfs4_fl_calc_ds_index(lseg, j); + ds = nfs4_fl_prepare_ds(lseg, idx); + if (!ds) + return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + + dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n", + __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count, + offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); + + hdr->pgio_done_cb = filelayout_write_done_cb; + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + hdr->ds_commit_idx = idx; + fh = nfs4_fl_select_ds_fh(lseg, j); + if (fh) + hdr->args.fh = fh; + hdr->args.offset = filelayout_get_dserver_offset(lseg, offset); + + /* Perform an asynchronous write */ + nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, + NFS_PROTO(hdr->inode), &filelayout_write_call_ops, + sync, RPC_TASK_SOFTCONN); + return PNFS_ATTEMPTED; +} + +/* + * filelayout_check_layout() + * + * Make sure layout segment parameters are sane WRT the device. + * At this point no generic layer initialization of the lseg has occurred, + * and nothing has been added to the layout_hdr cache. + * + */ +static int +filelayout_check_layout(struct pnfs_layout_hdr *lo, + struct nfs4_filelayout_segment *fl, + struct nfs4_layoutget_res *lgr, + struct nfs4_deviceid *id, + gfp_t gfp_flags) +{ + struct nfs4_deviceid_node *d; + struct nfs4_file_layout_dsaddr *dsaddr; + int status = -EINVAL; + + dprintk("--> %s\n", __func__); + + /* FIXME: remove this check when layout segment support is added */ + if (lgr->range.offset != 0 || + lgr->range.length != NFS4_MAX_UINT64) { + dprintk("%s Only whole file layouts supported. Use MDS i/o\n", + __func__); + goto out; + } + + if (fl->pattern_offset > lgr->range.offset) { + dprintk("%s pattern_offset %lld too large\n", + __func__, fl->pattern_offset); + goto out; + } + + if (!fl->stripe_unit) { + dprintk("%s Invalid stripe unit (%u)\n", + __func__, fl->stripe_unit); + goto out; + } + + /* find and reference the deviceid */ + d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id, + lo->plh_lc_cred, gfp_flags); + if (d == NULL) + goto out; + + dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node); + /* Found deviceid is unavailable */ + if (filelayout_test_devid_unavailable(&dsaddr->id_node)) + goto out_put; + + fl->dsaddr = dsaddr; + + if (fl->first_stripe_index >= dsaddr->stripe_count) { + dprintk("%s Bad first_stripe_index %u\n", + __func__, fl->first_stripe_index); + goto out_put; + } + + if ((fl->stripe_type == STRIPE_SPARSE && + fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) || + (fl->stripe_type == STRIPE_DENSE && + fl->num_fh != dsaddr->stripe_count)) { + dprintk("%s num_fh %u not valid for given packing\n", + __func__, fl->num_fh); + goto out_put; + } + + status = 0; +out: + dprintk("--> %s returns %d\n", __func__, status); + return status; +out_put: + nfs4_fl_put_deviceid(dsaddr); + goto out; +} + +static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl) +{ + int i; + + for (i = 0; i < fl->num_fh; i++) { + if (!fl->fh_array[i]) + break; + kfree(fl->fh_array[i]); + } + kfree(fl->fh_array); + fl->fh_array = NULL; +} + +static void +_filelayout_free_lseg(struct nfs4_filelayout_segment *fl) +{ + filelayout_free_fh_array(fl); + kfree(fl); +} + +static int +filelayout_decode_layout(struct pnfs_layout_hdr *flo, + struct nfs4_filelayout_segment *fl, + struct nfs4_layoutget_res *lgr, + struct nfs4_deviceid *id, + gfp_t gfp_flags) +{ + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + __be32 *p; + uint32_t nfl_util; + int i; + + dprintk("%s: set_layout_map Begin\n", __func__); + + scratch = alloc_page(gfp_flags); + if (!scratch) + return -ENOMEM; + + xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8), + * num_fh (4) */ + p = xdr_inline_decode(&stream, NFS4_DEVICEID4_SIZE + 20); + if (unlikely(!p)) + goto out_err; + + memcpy(id, p, sizeof(*id)); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + nfs4_print_deviceid(id); + + nfl_util = be32_to_cpup(p++); + if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS) + fl->commit_through_mds = 1; + if (nfl_util & NFL4_UFLG_DENSE) + fl->stripe_type = STRIPE_DENSE; + else + fl->stripe_type = STRIPE_SPARSE; + fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK; + + fl->first_stripe_index = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &fl->pattern_offset); + fl->num_fh = be32_to_cpup(p++); + + dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n", + __func__, nfl_util, fl->num_fh, fl->first_stripe_index, + fl->pattern_offset); + + /* Note that a zero value for num_fh is legal for STRIPE_SPARSE. + * Futher checking is done in filelayout_check_layout */ + if (fl->num_fh > + max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT)) + goto out_err; + + if (fl->num_fh > 0) { + fl->fh_array = kcalloc(fl->num_fh, sizeof(fl->fh_array[0]), + gfp_flags); + if (!fl->fh_array) + goto out_err; + } + + for (i = 0; i < fl->num_fh; i++) { + /* Do we want to use a mempool here? */ + fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags); + if (!fl->fh_array[i]) + goto out_err_free; + + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free; + fl->fh_array[i]->size = be32_to_cpup(p++); + if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { + printk(KERN_ERR "NFS: Too big fh %d received %d\n", + i, fl->fh_array[i]->size); + goto out_err_free; + } + + p = xdr_inline_decode(&stream, fl->fh_array[i]->size); + if (unlikely(!p)) + goto out_err_free; + memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); + dprintk("DEBUG: %s: fh len %d\n", __func__, + fl->fh_array[i]->size); + } + + __free_page(scratch); + return 0; + +out_err_free: + filelayout_free_fh_array(fl); +out_err: + __free_page(scratch); + return -EIO; +} + +static void +filelayout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + + dprintk("--> %s\n", __func__); + nfs4_fl_put_deviceid(fl->dsaddr); + /* This assumes a single RW lseg */ + if (lseg->pls_range.iomode == IOMODE_RW) { + struct nfs4_filelayout *flo; + + flo = FILELAYOUT_FROM_HDR(lseg->pls_layout); + flo->commit_info.nbuckets = 0; + kfree(flo->commit_info.buckets); + flo->commit_info.buckets = NULL; + } + _filelayout_free_lseg(fl); +} + +static int +filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + gfp_t gfp_flags) +{ + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + struct pnfs_commit_bucket *buckets; + int size, i; + + if (fl->commit_through_mds) + return 0; + + size = (fl->stripe_type == STRIPE_SPARSE) ? + fl->dsaddr->ds_num : fl->dsaddr->stripe_count; + + if (cinfo->ds->nbuckets >= size) { + /* This assumes there is only one IOMODE_RW lseg. What + * we really want to do is have a layout_hdr level + * dictionary of <multipath_list4, fh> keys, each + * associated with a struct list_head, populated by calls + * to filelayout_write_pagelist(). + * */ + return 0; + } + + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), + gfp_flags); + if (!buckets) + return -ENOMEM; + for (i = 0; i < size; i++) { + INIT_LIST_HEAD(&buckets[i].written); + INIT_LIST_HEAD(&buckets[i].committing); + /* mark direct verifier as unset */ + buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; + } + + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets >= size) + goto out; + for (i = 0; i < cinfo->ds->nbuckets; i++) { + list_splice(&cinfo->ds->buckets[i].written, + &buckets[i].written); + list_splice(&cinfo->ds->buckets[i].committing, + &buckets[i].committing); + buckets[i].direct_verf.committed = + cinfo->ds->buckets[i].direct_verf.committed; + buckets[i].wlseg = cinfo->ds->buckets[i].wlseg; + buckets[i].clseg = cinfo->ds->buckets[i].clseg; + } + swap(cinfo->ds->buckets, buckets); + cinfo->ds->nbuckets = size; +out: + spin_unlock(cinfo->lock); + kfree(buckets); + return 0; +} + +static struct pnfs_layout_segment * +filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) +{ + struct nfs4_filelayout_segment *fl; + int rc; + struct nfs4_deviceid id; + + dprintk("--> %s\n", __func__); + fl = kzalloc(sizeof(*fl), gfp_flags); + if (!fl) + return NULL; + + rc = filelayout_decode_layout(layoutid, fl, lgr, &id, gfp_flags); + if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id, gfp_flags)) { + _filelayout_free_lseg(fl); + return NULL; + } + return &fl->generic_hdr; +} + +/* + * filelayout_pg_test(). Called by nfs_can_coalesce_requests() + * + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t +filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, + struct nfs_page *req) +{ + unsigned int size; + u64 p_stripe, r_stripe; + u32 stripe_offset; + u64 segment_offset = pgio->pg_lseg->pls_range.offset; + u32 stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit; + + /* calls nfs_generic_pg_test */ + size = pnfs_generic_pg_test(pgio, prev, req); + if (!size) + return 0; + + /* see if req and prev are in the same stripe */ + if (prev) { + p_stripe = (u64)req_offset(prev) - segment_offset; + r_stripe = (u64)req_offset(req) - segment_offset; + do_div(p_stripe, stripe_unit); + do_div(r_stripe, stripe_unit); + + if (p_stripe != r_stripe) + return 0; + } + + /* calculate remaining bytes in the current stripe */ + div_u64_rem((u64)req_offset(req) - segment_offset, + stripe_unit, + &stripe_offset); + WARN_ON_ONCE(stripe_offset > stripe_unit); + if (stripe_offset >= stripe_unit) + return 0; + return min(stripe_unit - (unsigned int)stripe_offset, size); +} + +static void +filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_READ, + GFP_KERNEL); + /* If no lseg, fall back to read through mds */ + if (pgio->pg_lseg == NULL) + nfs_pageio_reset_read_mds(pgio); +} + +static void +filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs_commit_info cinfo; + int status; + + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + /* If no lseg, fall back to write through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); + if (status < 0) { + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + goto out_mds; + } + return; +out_mds: + nfs_pageio_reset_write_mds(pgio); +} + +static const struct nfs_pageio_ops filelayout_pg_read_ops = { + .pg_init = filelayout_pg_init_read, + .pg_test = filelayout_pg_test, + .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static const struct nfs_pageio_ops filelayout_pg_write_ops = { + .pg_init = filelayout_pg_init_write, + .pg_test = filelayout_pg_test, + .pg_doio = pnfs_generic_pg_writepages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) +{ + if (fl->stripe_type == STRIPE_SPARSE) + return nfs4_fl_calc_ds_index(&fl->generic_hdr, j); + else + return j; +} + +static void +filelayout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) + +{ + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + u32 i, j; + + if (fl->commit_through_mds) { + nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); + } else { + /* Note that we are calling nfs4_fl_calc_j_index on each page + * that ends up being committed to a data server. An attractive + * alternative is to add a field to nfs_write_data and nfs_page + * to store the value calculated in filelayout_write_pagelist + * and just use that here. + */ + j = nfs4_fl_calc_j_index(lseg, req_offset(req)); + i = select_bucket_index(fl, j); + pnfs_layout_mark_request_commit(req, lseg, cinfo, i); + } +} + +static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + + if (flseg->stripe_type == STRIPE_SPARSE) + return i; + else + return nfs4_fl_calc_ds_index(lseg, i); +} + +static struct nfs_fh * +select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + + if (flseg->stripe_type == STRIPE_SPARSE) { + if (flseg->num_fh == 1) + i = 0; + else if (flseg->num_fh == 0) + /* Use the MDS OPEN fh set in nfs_read_rpcsetup */ + return NULL; + } + return flseg->fh_array[i]; +} + +static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) +{ + struct pnfs_layout_segment *lseg = data->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + u32 idx; + struct nfs_fh *fh; + + idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); + ds = nfs4_fl_prepare_ds(lseg, idx); + if (!ds) + goto out_err; + + ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, data->inode); + if (IS_ERR(ds_clnt)) + goto out_err; + + dprintk("%s ino %lu, how %d cl_count %d\n", __func__, + data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count)); + data->commit_done_cb = filelayout_commit_done_cb; + atomic_inc(&ds->ds_clp->cl_count); + data->ds_clp = ds->ds_clp; + fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); + if (fh) + data->args.fh = fh; + return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode), + &filelayout_commit_call_ops, how, + RPC_TASK_SOFTCONN); +out_err: + pnfs_generic_prepare_to_resend_writes(data); + pnfs_generic_commit_release(data); + return -EAGAIN; +} + +/* filelayout_search_commit_reqs - Search lists in @cinfo for the head reqest + * for @page + * @cinfo - commit info for current inode + * @page - page to search for matching head request + * + * Returns a the head request if one is found, otherwise returns NULL. + */ +static struct nfs_page * +filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page) +{ + struct nfs_page *freq, *t; + struct pnfs_commit_bucket *b; + int i; + + /* Linearly search the commit lists for each bucket until a matching + * request is found */ + for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { + list_for_each_entry_safe(freq, t, &b->written, wb_list) { + if (freq->wb_page == page) + return freq->wb_head; + } + list_for_each_entry_safe(freq, t, &b->committing, wb_list) { + if (freq->wb_page == page) + return freq->wb_head; + } + } + + return NULL; +} + +static int +filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how, struct nfs_commit_info *cinfo) +{ + return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo, + filelayout_initiate_commit); +} + +static struct nfs4_deviceid_node * +filelayout_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_flags) +{ + struct nfs4_file_layout_dsaddr *dsaddr; + + dsaddr = nfs4_fl_alloc_deviceid_node(server, pdev, gfp_flags); + if (!dsaddr) + return NULL; + return &dsaddr->id_node; +} + +static void +filelayout_free_deviceid_node(struct nfs4_deviceid_node *d) +{ + nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node)); +} + +static struct pnfs_layout_hdr * +filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) +{ + struct nfs4_filelayout *flo; + + flo = kzalloc(sizeof(*flo), gfp_flags); + return flo != NULL ? &flo->generic_hdr : NULL; +} + +static void +filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + kfree(FILELAYOUT_FROM_HDR(lo)); +} + +static struct pnfs_ds_commit_info * +filelayout_get_ds_info(struct inode *inode) +{ + struct pnfs_layout_hdr *layout = NFS_I(inode)->layout; + + if (layout == NULL) + return NULL; + else + return &FILELAYOUT_FROM_HDR(layout)->commit_info; +} + +static struct pnfs_layoutdriver_type filelayout_type = { + .id = LAYOUT_NFSV4_1_FILES, + .name = "LAYOUT_NFSV4_1_FILES", + .owner = THIS_MODULE, + .alloc_layout_hdr = filelayout_alloc_layout_hdr, + .free_layout_hdr = filelayout_free_layout_hdr, + .alloc_lseg = filelayout_alloc_lseg, + .free_lseg = filelayout_free_lseg, + .pg_read_ops = &filelayout_pg_read_ops, + .pg_write_ops = &filelayout_pg_write_ops, + .get_ds_info = &filelayout_get_ds_info, + .mark_request_commit = filelayout_mark_request_commit, + .clear_request_commit = pnfs_generic_clear_request_commit, + .scan_commit_lists = pnfs_generic_scan_commit_lists, + .recover_commit_reqs = pnfs_generic_recover_commit_reqs, + .search_commit_reqs = filelayout_search_commit_reqs, + .commit_pagelist = filelayout_commit_pagelist, + .read_pagelist = filelayout_read_pagelist, + .write_pagelist = filelayout_write_pagelist, + .alloc_deviceid_node = filelayout_alloc_deviceid_node, + .free_deviceid_node = filelayout_free_deviceid_node, + .sync = pnfs_nfs_generic_sync, +}; + +static int __init nfs4filelayout_init(void) +{ + printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n", + __func__); + return pnfs_register_layoutdriver(&filelayout_type); +} + +static void __exit nfs4filelayout_exit(void) +{ + printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n", + __func__); + pnfs_unregister_layoutdriver(&filelayout_type); +} + +MODULE_ALIAS("nfs-layouttype4-1"); + +module_init(nfs4filelayout_init); +module_exit(nfs4filelayout_exit); diff --git a/kernel/fs/nfs/filelayout/filelayout.h b/kernel/fs/nfs/filelayout/filelayout.h new file mode 100644 index 000000000..2896cb833 --- /dev/null +++ b/kernel/fs/nfs/filelayout/filelayout.h @@ -0,0 +1,117 @@ +/* + * NFSv4 file layout driver data structures. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#ifndef FS_NFS_NFS4FILELAYOUT_H +#define FS_NFS_NFS4FILELAYOUT_H + +#include "../pnfs.h" + +/* + * Field testing shows we need to support up to 4096 stripe indices. + * We store each index as a u8 (u32 on the wire) to keep the memory footprint + * reasonable. This in turn means we support a maximum of 256 + * RFC 5661 multipath_list4 structures. + */ +#define NFS4_PNFS_MAX_STRIPE_CNT 4096 +#define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */ + +enum stripetype4 { + STRIPE_SPARSE = 1, + STRIPE_DENSE = 2 +}; + +struct nfs4_file_layout_dsaddr { + struct nfs4_deviceid_node id_node; + u32 stripe_count; + u8 *stripe_indices; + u32 ds_num; + struct nfs4_pnfs_ds *ds_list[1]; +}; + +struct nfs4_filelayout_segment { + struct pnfs_layout_segment generic_hdr; + u32 stripe_type; + u32 commit_through_mds; + u32 stripe_unit; + u32 first_stripe_index; + u64 pattern_offset; + struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ + unsigned int num_fh; + struct nfs_fh **fh_array; +}; + +struct nfs4_filelayout { + struct pnfs_layout_hdr generic_hdr; + struct pnfs_ds_commit_info commit_info; +}; + +static inline struct nfs4_filelayout * +FILELAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct nfs4_filelayout, generic_hdr); +} + +static inline struct nfs4_filelayout_segment * +FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, + struct nfs4_filelayout_segment, + generic_hdr); +} + +static inline struct nfs4_deviceid_node * +FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg) +{ + return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node; +} + +static inline bool +filelayout_test_devid_invalid(struct nfs4_deviceid_node *node) +{ + return test_bit(NFS_DEVICEID_INVALID, &node->flags); +} + +extern bool +filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node); + +extern struct nfs_fh * +nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j); + +u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset); +u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j); +struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, + u32 ds_idx); + +extern struct nfs4_file_layout_dsaddr * +nfs4_fl_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_flags); +extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr); +extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr); + +#endif /* FS_NFS_NFS4FILELAYOUT_H */ diff --git a/kernel/fs/nfs/filelayout/filelayoutdev.c b/kernel/fs/nfs/filelayout/filelayoutdev.c new file mode 100644 index 000000000..4946ef40b --- /dev/null +++ b/kernel/fs/nfs/filelayout/filelayoutdev.c @@ -0,0 +1,299 @@ +/* + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * Garth Goodson <Garth.Goodson@netapp.com> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include <linux/vmalloc.h> +#include <linux/module.h> + +#include "../internal.h" +#include "../nfs4session.h" +#include "filelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; +static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; + +void +nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) +{ + struct nfs4_pnfs_ds *ds; + int i; + + nfs4_print_deviceid(&dsaddr->id_node.deviceid); + + for (i = 0; i < dsaddr->ds_num; i++) { + ds = dsaddr->ds_list[i]; + if (ds != NULL) + nfs4_pnfs_ds_put(ds); + } + kfree(dsaddr->stripe_indices); + kfree_rcu(dsaddr, id_node.rcu); +} + +/* Decode opaque device data and return the result */ +struct nfs4_file_layout_dsaddr * +nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags) +{ + int i; + u32 cnt, num; + u8 *indexp; + __be32 *p; + u8 *stripe_indices; + u8 max_stripe_index; + struct nfs4_file_layout_dsaddr *dsaddr = NULL; + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + struct list_head dsaddrs; + struct nfs4_pnfs_ds_addr *da; + + /* set up xdr stream */ + scratch = alloc_page(gfp_flags); + if (!scratch) + goto out_err; + + xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* Get the stripe count (number of stripe index) */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_scratch; + + cnt = be32_to_cpup(p); + dprintk("%s stripe count %d\n", __func__, cnt); + if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) { + printk(KERN_WARNING "NFS: %s: stripe count %d greater than " + "supported maximum %d\n", __func__, + cnt, NFS4_PNFS_MAX_STRIPE_CNT); + goto out_err_free_scratch; + } + + /* read stripe indices */ + stripe_indices = kcalloc(cnt, sizeof(u8), gfp_flags); + if (!stripe_indices) + goto out_err_free_scratch; + + p = xdr_inline_decode(&stream, cnt << 2); + if (unlikely(!p)) + goto out_err_free_stripe_indices; + + indexp = &stripe_indices[0]; + max_stripe_index = 0; + for (i = 0; i < cnt; i++) { + *indexp = be32_to_cpup(p++); + max_stripe_index = max(max_stripe_index, *indexp); + indexp++; + } + + /* Check the multipath list count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_stripe_indices; + + num = be32_to_cpup(p); + dprintk("%s ds_num %u\n", __func__, num); + if (num > NFS4_PNFS_MAX_MULTI_CNT) { + printk(KERN_WARNING "NFS: %s: multipath count %d greater than " + "supported maximum %d\n", __func__, + num, NFS4_PNFS_MAX_MULTI_CNT); + goto out_err_free_stripe_indices; + } + + /* validate stripe indices are all < num */ + if (max_stripe_index >= num) { + printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n", + __func__, max_stripe_index, num); + goto out_err_free_stripe_indices; + } + + dsaddr = kzalloc(sizeof(*dsaddr) + + (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), + gfp_flags); + if (!dsaddr) + goto out_err_free_stripe_indices; + + dsaddr->stripe_count = cnt; + dsaddr->stripe_indices = stripe_indices; + stripe_indices = NULL; + dsaddr->ds_num = num; + nfs4_init_deviceid_node(&dsaddr->id_node, server, &pdev->dev_id); + + INIT_LIST_HEAD(&dsaddrs); + + for (i = 0; i < dsaddr->ds_num; i++) { + int j; + u32 mp_count; + + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_deviceid; + + mp_count = be32_to_cpup(p); /* multipath count */ + for (j = 0; j < mp_count; j++) { + da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, + &stream, gfp_flags); + if (da) + list_add_tail(&da->da_node, &dsaddrs); + } + if (list_empty(&dsaddrs)) { + dprintk("%s: no suitable DS addresses found\n", + __func__); + goto out_err_free_deviceid; + } + + dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + if (!dsaddr->ds_list[i]) + goto out_err_drain_dsaddrs; + + /* If DS was already in cache, free ds addrs */ + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, + struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + } + + __free_page(scratch); + return dsaddr; + +out_err_drain_dsaddrs: + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } +out_err_free_deviceid: + nfs4_fl_free_deviceid(dsaddr); + /* stripe_indicies was part of dsaddr */ + goto out_err_free_scratch; +out_err_free_stripe_indices: + kfree(stripe_indices); +out_err_free_scratch: + __free_page(scratch); +out_err: + dprintk("%s ERROR: returning NULL\n", __func__); + return NULL; +} + +void +nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) +{ + nfs4_put_deviceid_node(&dsaddr->id_node); +} + +/* + * Want res = (offset - layout->pattern_offset)/ layout->stripe_unit + * Then: ((res + fsi) % dsaddr->stripe_count) + */ +u32 +nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + u64 tmp; + + tmp = offset - flseg->pattern_offset; + do_div(tmp, flseg->stripe_unit); + tmp += flseg->first_stripe_index; + return do_div(tmp, flseg->dsaddr->stripe_count); +} + +u32 +nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j) +{ + return FILELAYOUT_LSEG(lseg)->dsaddr->stripe_indices[j]; +} + +struct nfs_fh * +nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + u32 i; + + if (flseg->stripe_type == STRIPE_SPARSE) { + if (flseg->num_fh == 1) + i = 0; + else if (flseg->num_fh == 0) + /* Use the MDS OPEN fh set in nfs_read_rpcsetup */ + return NULL; + else + i = nfs4_fl_calc_ds_index(lseg, j); + } else + i = j; + return flseg->fh_array[i]; +} + +/* Upon return, either ds is connected, or ds is NULL */ +struct nfs4_pnfs_ds * +nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) +{ + struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr; + struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx]; + struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); + struct nfs4_pnfs_ds *ret = ds; + struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); + + if (ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", + __func__, ds_idx); + pnfs_generic_mark_devid_invalid(devid); + goto out; + } + smp_rmb(); + if (ds->ds_clp) + goto out_test_devid; + + nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + dataserver_retrans, 4, + s->nfs_client->cl_minorversion, + s->nfs_client->cl_rpcclient->cl_auth->au_flavor); + +out_test_devid: + if (filelayout_test_devid_unavailable(devid)) + ret = NULL; +out: + return ret; +} + +module_param(dataserver_retrans, uint, 0644); +MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client " + "retries a request before it attempts further " + " recovery action."); +module_param(dataserver_timeo, uint, 0644); +MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the " + "NFSv4.1 client waits for a response from a " + " data server before it retries an NFS request."); diff --git a/kernel/fs/nfs/flexfilelayout/Makefile b/kernel/fs/nfs/flexfilelayout/Makefile new file mode 100644 index 000000000..1d2c9f6bb --- /dev/null +++ b/kernel/fs/nfs/flexfilelayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Flexfile Layout Driver kernel module +# +obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o +nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o diff --git a/kernel/fs/nfs/flexfilelayout/flexfilelayout.c b/kernel/fs/nfs/flexfilelayout/flexfilelayout.c new file mode 100644 index 000000000..7d05089e5 --- /dev/null +++ b/kernel/fs/nfs/flexfilelayout/flexfilelayout.c @@ -0,0 +1,1535 @@ +/* + * Module for pnfs flexfile layout driver. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng <bergwolf@primarydata.com> + */ + +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/module.h> + +#include <linux/sunrpc/metrics.h> + +#include "flexfilelayout.h" +#include "../nfs4session.h" +#include "../nfs4idmap.h" +#include "../internal.h" +#include "../delegation.h" +#include "../nfs4trace.h" +#include "../iostat.h" +#include "../nfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ) + +static struct pnfs_layout_hdr * +ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) +{ + struct nfs4_flexfile_layout *ffl; + + ffl = kzalloc(sizeof(*ffl), gfp_flags); + if (ffl) { + INIT_LIST_HEAD(&ffl->error_list); + return &ffl->generic_hdr; + } else + return NULL; +} + +static void +ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct nfs4_ff_layout_ds_err *err, *n; + + list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list, + list) { + list_del(&err->list); + kfree(err); + } + kfree(FF_LAYOUT_FROM_HDR(lo)); +} + +static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE); + if (unlikely(p == NULL)) + return -ENOBUFS; + memcpy(stateid, p, NFS4_STATEID_SIZE); + dprintk("%s: stateid id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); + return 0; +} + +static int decode_deviceid(struct xdr_stream *xdr, struct nfs4_deviceid *devid) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE); + if (unlikely(!p)) + return -ENOBUFS; + memcpy(devid, p, NFS4_DEVICEID4_SIZE); + nfs4_print_deviceid(devid); + return 0; +} + +static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -ENOBUFS; + fh->size = be32_to_cpup(p++); + if (fh->size > sizeof(struct nfs_fh)) { + printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n", + fh->size); + return -EOVERFLOW; + } + /* fh.data */ + p = xdr_inline_decode(xdr, fh->size); + if (unlikely(!p)) + return -ENOBUFS; + memcpy(&fh->data, p, fh->size); + dprintk("%s: fh len %d\n", __func__, fh->size); + + return 0; +} + +/* + * Currently only stringified uids and gids are accepted. + * I.e., kerberos is not supported to the DSes, so no pricipals. + * + * That means that one common function will suffice, but when + * principals are added, this should be split to accomodate + * calls to both nfs_map_name_to_uid() and nfs_map_group_to_gid(). + */ +static int +decode_name(struct xdr_stream *xdr, u32 *id) +{ + __be32 *p; + int len; + + /* opaque_length(4)*/ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -ENOBUFS; + len = be32_to_cpup(p++); + if (len < 0) + return -EINVAL; + + dprintk("%s: len %u\n", __func__, len); + + /* opaque body */ + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return -ENOBUFS; + + if (!nfs_map_string_to_numeric((char *)p, len, id)) + return -EINVAL; + + return 0; +} + +static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls) +{ + int i; + + if (fls->mirror_array) { + for (i = 0; i < fls->mirror_array_cnt; i++) { + /* normally mirror_ds is freed in + * .free_deviceid_node but we still do it here + * for .alloc_lseg error path */ + if (fls->mirror_array[i]) { + kfree(fls->mirror_array[i]->fh_versions); + nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds); + kfree(fls->mirror_array[i]); + } + } + kfree(fls->mirror_array); + fls->mirror_array = NULL; + } +} + +static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr) +{ + int ret = 0; + + dprintk("--> %s\n", __func__); + + /* FIXME: remove this check when layout segment support is added */ + if (lgr->range.offset != 0 || + lgr->range.length != NFS4_MAX_UINT64) { + dprintk("%s Only whole file layouts supported. Use MDS i/o\n", + __func__); + ret = -EINVAL; + } + + dprintk("--> %s returns %d\n", __func__, ret); + return ret; +} + +static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls) +{ + if (fls) { + ff_layout_free_mirror_array(fls); + kfree(fls); + } +} + +static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls) +{ + struct nfs4_ff_layout_mirror *tmp; + int i, j; + + for (i = 0; i < fls->mirror_array_cnt - 1; i++) { + for (j = i + 1; j < fls->mirror_array_cnt; j++) + if (fls->mirror_array[i]->efficiency < + fls->mirror_array[j]->efficiency) { + tmp = fls->mirror_array[i]; + fls->mirror_array[i] = fls->mirror_array[j]; + fls->mirror_array[j] = tmp; + } + } +} + +static struct pnfs_layout_segment * +ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) +{ + struct pnfs_layout_segment *ret; + struct nfs4_ff_layout_segment *fls = NULL; + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + u64 stripe_unit; + u32 mirror_array_cnt; + __be32 *p; + int i, rc; + + dprintk("--> %s\n", __func__); + scratch = alloc_page(gfp_flags); + if (!scratch) + return ERR_PTR(-ENOMEM); + + xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, + lgr->layoutp->len); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* stripe unit and mirror_array_cnt */ + rc = -EIO; + p = xdr_inline_decode(&stream, 8 + 4); + if (!p) + goto out_err_free; + + p = xdr_decode_hyper(p, &stripe_unit); + mirror_array_cnt = be32_to_cpup(p++); + dprintk("%s: stripe_unit=%llu mirror_array_cnt=%u\n", __func__, + stripe_unit, mirror_array_cnt); + + if (mirror_array_cnt > NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT || + mirror_array_cnt == 0) + goto out_err_free; + + rc = -ENOMEM; + fls = kzalloc(sizeof(*fls), gfp_flags); + if (!fls) + goto out_err_free; + + fls->mirror_array_cnt = mirror_array_cnt; + fls->stripe_unit = stripe_unit; + fls->mirror_array = kcalloc(fls->mirror_array_cnt, + sizeof(fls->mirror_array[0]), gfp_flags); + if (fls->mirror_array == NULL) + goto out_err_free; + + for (i = 0; i < fls->mirror_array_cnt; i++) { + struct nfs4_deviceid devid; + struct nfs4_deviceid_node *idnode; + u32 ds_count; + u32 fh_count; + int j; + + rc = -EIO; + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + ds_count = be32_to_cpup(p); + + /* FIXME: allow for striping? */ + if (ds_count != 1) + goto out_err_free; + + fls->mirror_array[i] = + kzalloc(sizeof(struct nfs4_ff_layout_mirror), + gfp_flags); + if (fls->mirror_array[i] == NULL) { + rc = -ENOMEM; + goto out_err_free; + } + + spin_lock_init(&fls->mirror_array[i]->lock); + fls->mirror_array[i]->ds_count = ds_count; + + /* deviceid */ + rc = decode_deviceid(&stream, &devid); + if (rc) + goto out_err_free; + + idnode = nfs4_find_get_deviceid(NFS_SERVER(lh->plh_inode), + &devid, lh->plh_lc_cred, + gfp_flags); + /* + * upon success, mirror_ds is allocated by previous + * getdeviceinfo, or newly by .alloc_deviceid_node + * nfs4_find_get_deviceid failure is indeed getdeviceinfo falure + */ + if (idnode) + fls->mirror_array[i]->mirror_ds = + FF_LAYOUT_MIRROR_DS(idnode); + else + goto out_err_free; + + /* efficiency */ + rc = -EIO; + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + fls->mirror_array[i]->efficiency = be32_to_cpup(p); + + /* stateid */ + rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid); + if (rc) + goto out_err_free; + + /* fh */ + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + fh_count = be32_to_cpup(p); + + fls->mirror_array[i]->fh_versions = + kzalloc(fh_count * sizeof(struct nfs_fh), + gfp_flags); + if (fls->mirror_array[i]->fh_versions == NULL) { + rc = -ENOMEM; + goto out_err_free; + } + + for (j = 0; j < fh_count; j++) { + rc = decode_nfs_fh(&stream, + &fls->mirror_array[i]->fh_versions[j]); + if (rc) + goto out_err_free; + } + + fls->mirror_array[i]->fh_versions_cnt = fh_count; + + /* user */ + rc = decode_name(&stream, &fls->mirror_array[i]->uid); + if (rc) + goto out_err_free; + + /* group */ + rc = decode_name(&stream, &fls->mirror_array[i]->gid); + if (rc) + goto out_err_free; + + dprintk("%s: uid %d gid %d\n", __func__, + fls->mirror_array[i]->uid, + fls->mirror_array[i]->gid); + } + + ff_layout_sort_mirrors(fls); + rc = ff_layout_check_layout(lgr); + if (rc) + goto out_err_free; + + ret = &fls->generic_hdr; + dprintk("<-- %s (success)\n", __func__); +out_free_page: + __free_page(scratch); + return ret; +out_err_free: + _ff_layout_free_lseg(fls); + ret = ERR_PTR(rc); + dprintk("<-- %s (%d)\n", __func__, rc); + goto out_free_page; +} + +static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &layout->plh_segs, pls_list) + if (lseg->pls_range.iomode == IOMODE_RW) + return true; + + return false; +} + +static void +ff_layout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); + int i; + + dprintk("--> %s\n", __func__); + + for (i = 0; i < fls->mirror_array_cnt; i++) { + if (fls->mirror_array[i]) { + nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds); + fls->mirror_array[i]->mirror_ds = NULL; + if (fls->mirror_array[i]->cred) { + put_rpccred(fls->mirror_array[i]->cred); + fls->mirror_array[i]->cred = NULL; + } + } + } + + if (lseg->pls_range.iomode == IOMODE_RW) { + struct nfs4_flexfile_layout *ffl; + struct inode *inode; + + ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout); + inode = ffl->generic_hdr.plh_inode; + spin_lock(&inode->i_lock); + if (!ff_layout_has_rw_segments(lseg->pls_layout)) { + ffl->commit_info.nbuckets = 0; + kfree(ffl->commit_info.buckets); + ffl->commit_info.buckets = NULL; + } + spin_unlock(&inode->i_lock); + } + _ff_layout_free_lseg(fls); +} + +/* Return 1 until we have multiple lsegs support */ +static int +ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls) +{ + return 1; +} + +static int +ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + gfp_t gfp_flags) +{ + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); + struct pnfs_commit_bucket *buckets; + int size; + + if (cinfo->ds->nbuckets != 0) { + /* This assumes there is only one RW lseg per file. + * To support multiple lseg per file, we need to + * change struct pnfs_commit_bucket to allow dynamic + * increasing nbuckets. + */ + return 0; + } + + size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg); + + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), + gfp_flags); + if (!buckets) + return -ENOMEM; + else { + int i; + + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets != 0) + kfree(buckets); + else { + cinfo->ds->buckets = buckets; + cinfo->ds->nbuckets = size; + for (i = 0; i < size; i++) { + INIT_LIST_HEAD(&buckets[i].written); + INIT_LIST_HEAD(&buckets[i].committing); + /* mark direct verifier as unset */ + buckets[i].direct_verf.committed = + NFS_INVALID_STABLE_HOW; + } + } + spin_unlock(cinfo->lock); + return 0; + } +} + +static struct nfs4_pnfs_ds * +ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio, + int *best_idx) +{ + struct nfs4_ff_layout_segment *fls; + struct nfs4_pnfs_ds *ds; + int idx; + + fls = FF_LAYOUT_LSEG(pgio->pg_lseg); + /* mirrors are sorted by efficiency */ + for (idx = 0; idx < fls->mirror_array_cnt; idx++) { + ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false); + if (ds) { + *best_idx = idx; + return ds; + } + } + + return NULL; +} + +static void +ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs_pgio_mirror *pgm; + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_pnfs_ds *ds; + int ds_idx; + + /* Use full layout for now */ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_READ, + GFP_KERNEL); + /* If no lseg, fall back to read through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + + ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx); + if (!ds) + goto out_mds; + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + + pgio->pg_mirror_idx = ds_idx; + + /* read always uses only one mirror - idx 0 for pgio layer */ + pgm = &pgio->pg_mirrors[0]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; + + return; +out_mds: + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_read_mds(pgio); +} + +static void +ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs4_ff_layout_mirror *mirror; + struct nfs_pgio_mirror *pgm; + struct nfs_commit_info cinfo; + struct nfs4_pnfs_ds *ds; + int i; + int status; + + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + /* If no lseg, fall back to write through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); + if (status < 0) + goto out_mds; + + /* Use a direct mapping of ds_idx to pgio mirror_idx */ + if (WARN_ON_ONCE(pgio->pg_mirror_count != + FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))) + goto out_mds; + + for (i = 0; i < pgio->pg_mirror_count; i++) { + ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true); + if (!ds) + goto out_mds; + pgm = &pgio->pg_mirrors[i]; + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize; + } + + return; + +out_mds: + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_write_mds(pgio); +} + +static unsigned int +ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + if (pgio->pg_lseg) + return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg); + + /* no lseg means that pnfs is not in use, so no mirroring here */ + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_write_mds(pgio); + return 1; +} + +static const struct nfs_pageio_ops ff_layout_pg_read_ops = { + .pg_init = ff_layout_pg_init_read, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static const struct nfs_pageio_ops ff_layout_pg_write_ops = { + .pg_init = ff_layout_pg_init_write, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_writepages, + .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) +{ + struct rpc_task *task = &hdr->task; + + pnfs_layoutcommit_inode(hdr->inode, false); + + if (retry_pnfs) { + dprintk("%s Reset task %5u for i/o through pNFS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + if (!hdr->dreq) { + struct nfs_open_context *ctx; + + ctx = nfs_list_entry(hdr->pages.next)->wb_context; + set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); + hdr->completion_ops->error_cleanup(&hdr->pages); + } else { + nfs_direct_set_resched_writes(hdr->dreq); + /* fake unstable write to let common nfs resend pages */ + hdr->verf.committed = NFS_UNSTABLE; + hdr->good_bytes = 0; + } + return; + } + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_write_done_resend_to_mds(hdr); + } +} + +static void ff_layout_reset_read(struct nfs_pgio_header *hdr) +{ + struct rpc_task *task = &hdr->task; + + pnfs_layoutcommit_inode(hdr->inode, false); + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_read_done_resend_to_mds(hdr); + } +} + +static int ff_layout_async_handle_error_v4(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg, + int idx) +{ + struct pnfs_layout_hdr *lo = lseg->pls_layout; + struct inode *inode = lo->plh_inode; + struct nfs_server *mds_server = NFS_SERVER(inode); + + struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + struct nfs_client *mds_client = mds_server->nfs_client; + struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; + + if (task->tk_status >= 0) + return 0; + + switch (task->tk_status) { + /* MDS state errors */ + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + if (state == NULL) + break; + nfs_remove_bad_delegation(state->inode); + case -NFS4ERR_OPENMODE: + if (state == NULL) + break; + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + goto wait_on_recovery; + case -NFS4ERR_EXPIRED: + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + } + nfs4_schedule_lease_recovery(mds_client); + goto wait_on_recovery; + /* DS session errors */ + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + dprintk("%s ERROR %d, Reset session. Exchangeid " + "flags 0x%x\n", __func__, task->tk_status, + clp->cl_exchange_flags); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + break; + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX); + break; + case -NFS4ERR_RETRY_UNCACHED_REP: + break; + /* Invalidate Layout errors */ + case -NFS4ERR_PNFS_NO_LAYOUT: + case -ESTALE: /* mapped NFS4ERR_STALE */ + case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ + case -EISDIR: /* mapped NFS4ERR_ISDIR */ + case -NFS4ERR_FHEXPIRED: + case -NFS4ERR_WRONG_TYPE: + dprintk("%s Invalid layout error %d\n", __func__, + task->tk_status); + /* + * Destroy layout so new i/o will get a new layout. + * Layout will not be destroyed until all current lseg + * references are put. Mark layout as invalid to resend failed + * i/o and all i/o waiting on the slot table to the MDS until + * layout is destroyed and a new valid layout is obtained. + */ + pnfs_destroy_layout(NFS_I(inode)); + rpc_wake_up(&tbl->slot_tbl_waitq); + goto reset; + /* RPC connection errors */ + case -ECONNREFUSED: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EIO: + case -ETIMEDOUT: + case -EPIPE: + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + rpc_wake_up(&tbl->slot_tbl_waitq); + /* fall through */ + default: + if (ff_layout_has_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, + task->tk_status); + return -NFS4ERR_RESET_TO_MDS; + } +out: + task->tk_status = 0; + return -EAGAIN; +out_bad_stateid: + task->tk_status = -EIO; + return 0; +wait_on_recovery: + rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) + rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); + goto out; +} + +/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ +static int ff_layout_async_handle_error_v3(struct rpc_task *task, + struct pnfs_layout_segment *lseg, + int idx) +{ + struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + + if (task->tk_status >= 0) + return 0; + + if (task->tk_status != -EJUKEBOX) { + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + if (ff_layout_has_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; + else + return -NFS4ERR_RESET_TO_MDS; + } + + if (task->tk_status == -EJUKEBOX) + nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); + task->tk_status = 0; + rpc_restart_call(task); + rpc_delay(task, NFS_JUKEBOX_RETRY_TIME); + return -EAGAIN; +} + +static int ff_layout_async_handle_error(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg, + int idx) +{ + int vers = clp->cl_nfs_mod->rpc_vers->number; + + switch (vers) { + case 3: + return ff_layout_async_handle_error_v3(task, lseg, idx); + case 4: + return ff_layout_async_handle_error_v4(task, state, clp, + lseg, idx); + default: + /* should never happen */ + WARN_ON_ONCE(1); + return 0; + } +} + +static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, + int idx, u64 offset, u64 length, + u32 status, int opnum) +{ + struct nfs4_ff_layout_mirror *mirror; + int err; + + mirror = FF_LAYOUT_COMP(lseg, idx); + err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, offset, length, status, opnum, + GFP_NOIO); + dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status); +} + +/* NFS_PROTO call done callback routines */ + +static int ff_layout_read_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_read(hdr, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status) + hdr->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && hdr->res.op_status) + ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, + hdr->args.offset, hdr->args.count, + hdr->res.op_status, OP_READ); + err = ff_layout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg, + hdr->pgio_mirror_idx); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &hdr->lseg->pls_layout->plh_flags); + pnfs_read_resend_pnfs(hdr); + return task->tk_status; + case -NFS4ERR_RESET_TO_MDS: + inode = hdr->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, hdr->lseg); + ff_layout_reset_read(hdr); + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + return 0; +} + +/* + * We reference the rpc_cred of the first WRITE that triggers the need for + * a LAYOUTCOMMIT, and use it to send the layoutcommit compound. + * rfc5661 is not clear about which credential should be used. + * + * Flexlayout client should treat DS replied FILE_SYNC as DATA_SYNC, so + * to follow http://www.rfc-editor.org/errata_search.php?rfc=5661&eid=2751 + * we always send layoutcommit after DS writes. + */ +static void +ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr) +{ + pnfs_set_layoutcommit(hdr->inode, hdr->lseg, + hdr->mds_offset + hdr->res.count); + dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); +} + +static bool +ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) +{ + /* No mirroring for now */ + struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx); + + return ff_layout_test_devid_unavailable(node); +} + +static int ff_layout_read_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return -EIO; + } + if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + if (ff_layout_has_available_ds(hdr->lseg)) + pnfs_read_resend_pnfs(hdr); + else + ff_layout_reset_read(hdr); + rpc_exit(task, 0); + return -EAGAIN; + } + hdr->pgio_done_cb = ff_layout_read_done_cb; + + return 0; +} + +/* + * Call ops for the async read/write cases + * In the case of dense layouts, the offset needs to be reset to its + * original value. + */ +static void ff_layout_read_prepare_v3(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_read_prepare_common(task, hdr)) + return; + + rpc_call_start(task); +} + +static int ff_layout_setup_sequence(struct nfs_client *ds_clp, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + if (ds_clp->cl_session) + return nfs41_setup_sequence(ds_clp->cl_session, + args, + res, + task); + return nfs40_setup_sequence(ds_clp->cl_slot_tbl, + args, + res, + task); +} + +static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_read_prepare_common(task, hdr)) + return; + + if (ff_layout_setup_sequence(hdr->ds_clp, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_READ) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void ff_layout_read_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs4_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, hdr); +} + +static void ff_layout_read_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]); +} + +static int ff_layout_write_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_write(hdr, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status) + hdr->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && hdr->res.op_status) + ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, + hdr->args.offset, hdr->args.count, + hdr->res.op_status, OP_WRITE); + err = ff_layout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg, + hdr->pgio_mirror_idx); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + case -NFS4ERR_RESET_TO_MDS: + inode = hdr->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, hdr->lseg); + if (err == -NFS4ERR_RESET_TO_PNFS) { + pnfs_set_retry_layoutget(hdr->lseg->pls_layout); + ff_layout_reset_write(hdr, true); + } else { + pnfs_clear_retry_layoutget(hdr->lseg->pls_layout); + ff_layout_reset_write(hdr, false); + } + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (hdr->res.verf->committed == NFS_FILE_SYNC || + hdr->res.verf->committed == NFS_DATA_SYNC) + ff_layout_set_layoutcommit(hdr); + + return 0; +} + +static int ff_layout_commit_done_cb(struct rpc_task *task, + struct nfs_commit_data *data) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_commit_ds(data, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !data->res.op_status) + data->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && data->res.op_status) + ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index, + data->args.offset, data->args.count, + data->res.op_status, OP_COMMIT); + err = ff_layout_async_handle_error(task, NULL, data->ds_clp, + data->lseg, data->ds_commit_index); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + case -NFS4ERR_RESET_TO_MDS: + inode = data->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, data->lseg); + if (err == -NFS4ERR_RESET_TO_PNFS) + pnfs_set_retry_layoutget(data->lseg->pls_layout); + else + pnfs_clear_retry_layoutget(data->lseg->pls_layout); + pnfs_generic_prepare_to_resend_writes(data); + return -EAGAIN; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (data->verf.committed == NFS_UNSTABLE) + pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb); + + return 0; +} + +static int ff_layout_write_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return -EIO; + } + + if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) { + bool retry_pnfs; + + retry_pnfs = ff_layout_has_available_ds(hdr->lseg); + dprintk("%s task %u reset io to %s\n", __func__, + task->tk_pid, retry_pnfs ? "pNFS" : "MDS"); + ff_layout_reset_write(hdr, retry_pnfs); + rpc_exit(task, 0); + return -EAGAIN; + } + + return 0; +} + +static void ff_layout_write_prepare_v3(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_write_prepare_common(task, hdr)) + return; + + rpc_call_start(task); +} + +static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_write_prepare_common(task, hdr)) + return; + + if (ff_layout_setup_sequence(hdr->ds_clp, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_WRITE) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void ff_layout_write_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs4_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, hdr); +} + +static void ff_layout_write_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]); +} + +static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) +{ + rpc_call_start(task); +} + +static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + ff_layout_setup_sequence(wdata->ds_clp, + &wdata->args.seq_args, + &wdata->res.seq_res, + task); +} + +static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *cdata = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]); +} + +static const struct rpc_call_ops ff_layout_read_call_ops_v3 = { + .rpc_call_prepare = ff_layout_read_prepare_v3, + .rpc_call_done = ff_layout_read_call_done, + .rpc_count_stats = ff_layout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_read_call_ops_v4 = { + .rpc_call_prepare = ff_layout_read_prepare_v4, + .rpc_call_done = ff_layout_read_call_done, + .rpc_count_stats = ff_layout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_write_call_ops_v3 = { + .rpc_call_prepare = ff_layout_write_prepare_v3, + .rpc_call_done = ff_layout_write_call_done, + .rpc_count_stats = ff_layout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_write_call_ops_v4 = { + .rpc_call_prepare = ff_layout_write_prepare_v4, + .rpc_call_done = ff_layout_write_call_done, + .rpc_count_stats = ff_layout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = { + .rpc_call_prepare = ff_layout_commit_prepare_v3, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = ff_layout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = { + .rpc_call_prepare = ff_layout_commit_prepare_v4, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = ff_layout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static enum pnfs_try_status +ff_layout_read_pagelist(struct nfs_pgio_header *hdr) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + loff_t offset = hdr->args.offset; + u32 idx = hdr->pgio_mirror_idx; + int vers; + struct nfs_fh *fh; + + dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", + __func__, hdr->inode->i_ino, + hdr->args.pgbase, (size_t)hdr->args.count, offset); + + ds = nfs4_ff_layout_prepare_ds(lseg, idx, false); + if (!ds) + goto out_failed; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + hdr->inode); + if (IS_ERR(ds_clnt)) + goto out_failed; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred); + if (IS_ERR(ds_cred)) + goto out_failed; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__, + ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers); + + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + fh = nfs4_ff_layout_select_ds_fh(lseg, idx); + if (fh) + hdr->args.fh = fh; + + /* + * Note that if we ever decide to split across DSes, + * then we may need to handle dense-like offsets. + */ + hdr->args.offset = offset; + hdr->mds_offset = offset; + + /* Perform an asynchronous read to ds */ + nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_read_call_ops_v3 : + &ff_layout_read_call_ops_v4, + 0, RPC_TASK_SOFTCONN); + + return PNFS_ATTEMPTED; + +out_failed: + if (ff_layout_has_available_ds(lseg)) + return PNFS_TRY_AGAIN; + return PNFS_NOT_ATTEMPTED; +} + +/* Perform async writes. */ +static enum pnfs_try_status +ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + loff_t offset = hdr->args.offset; + int vers; + struct nfs_fh *fh; + int idx = hdr->pgio_mirror_idx; + + ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); + if (!ds) + return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred); + if (IS_ERR(ds_cred)) + return PNFS_NOT_ATTEMPTED; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n", + __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count, + offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), + vers); + + hdr->pgio_done_cb = ff_layout_write_done_cb; + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + hdr->ds_commit_idx = idx; + fh = nfs4_ff_layout_select_ds_fh(lseg, idx); + if (fh) + hdr->args.fh = fh; + + /* + * Note that if we ever decide to split across DSes, + * then we may need to handle dense-like offsets. + */ + hdr->args.offset = offset; + + /* Perform an asynchronous write */ + nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_write_call_ops_v3 : + &ff_layout_write_call_ops_v4, + sync, RPC_TASK_SOFTCONN); + return PNFS_ATTEMPTED; +} + +static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + return i; +} + +static struct nfs_fh * +select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg); + + /* FIXME: Assume that there is only one NFS version available + * for the DS. + */ + return &flseg->mirror_array[i]->fh_versions[0]; +} + +static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) +{ + struct pnfs_layout_segment *lseg = data->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + u32 idx; + int vers; + struct nfs_fh *fh; + + idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); + ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); + if (!ds) + goto out_err; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + data->inode); + if (IS_ERR(ds_clnt)) + goto out_err; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred); + if (IS_ERR(ds_cred)) + goto out_err; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__, + data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count), + vers); + data->commit_done_cb = ff_layout_commit_done_cb; + data->cred = ds_cred; + atomic_inc(&ds->ds_clp->cl_count); + data->ds_clp = ds->ds_clp; + fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); + if (fh) + data->args.fh = fh; + return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_commit_call_ops_v3 : + &ff_layout_commit_call_ops_v4, + how, RPC_TASK_SOFTCONN); +out_err: + pnfs_generic_prepare_to_resend_writes(data); + pnfs_generic_commit_release(data); + return -EAGAIN; +} + +static int +ff_layout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how, struct nfs_commit_info *cinfo) +{ + return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo, + ff_layout_initiate_commit); +} + +static struct pnfs_ds_commit_info * +ff_layout_get_ds_info(struct inode *inode) +{ + struct pnfs_layout_hdr *layout = NFS_I(inode)->layout; + + if (layout == NULL) + return NULL; + + return &FF_LAYOUT_FROM_HDR(layout)->commit_info; +} + +static void +ff_layout_free_deviceid_node(struct nfs4_deviceid_node *d) +{ + nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds, + id_node)); +} + +static int ff_layout_encode_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct pnfs_layout_hdr *hdr = &flo->generic_hdr; + __be32 *start; + int count = 0, ret = 0; + + start = xdr_reserve_space(xdr, 4); + if (unlikely(!start)) + return -E2BIG; + + /* This assume we always return _ALL_ layouts */ + spin_lock(&hdr->plh_inode->i_lock); + ret = ff_layout_encode_ds_ioerr(flo, xdr, &count, &args->range); + spin_unlock(&hdr->plh_inode->i_lock); + + *start = cpu_to_be32(count); + + return ret; +} + +/* report nothing for now */ +static void ff_layout_encode_iostats(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + if (likely(p)) + *p = cpu_to_be32(0); +} + +static struct nfs4_deviceid_node * +ff_layout_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_flags) +{ + struct nfs4_ff_layout_ds *dsaddr; + + dsaddr = nfs4_ff_alloc_deviceid_node(server, pdev, gfp_flags); + if (!dsaddr) + return NULL; + return &dsaddr->id_node; +} + +static void +ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct nfs4_flexfile_layout *flo = FF_LAYOUT_FROM_HDR(lo); + __be32 *start; + + dprintk("%s: Begin\n", __func__); + start = xdr_reserve_space(xdr, 4); + BUG_ON(!start); + + if (ff_layout_encode_ioerr(flo, xdr, args)) + goto out; + + ff_layout_encode_iostats(flo, xdr, args); +out: + *start = cpu_to_be32((xdr->p - start - 1) * 4); + dprintk("%s: Return\n", __func__); +} + +static struct pnfs_layoutdriver_type flexfilelayout_type = { + .id = LAYOUT_FLEX_FILES, + .name = "LAYOUT_FLEX_FILES", + .owner = THIS_MODULE, + .alloc_layout_hdr = ff_layout_alloc_layout_hdr, + .free_layout_hdr = ff_layout_free_layout_hdr, + .alloc_lseg = ff_layout_alloc_lseg, + .free_lseg = ff_layout_free_lseg, + .pg_read_ops = &ff_layout_pg_read_ops, + .pg_write_ops = &ff_layout_pg_write_ops, + .get_ds_info = ff_layout_get_ds_info, + .free_deviceid_node = ff_layout_free_deviceid_node, + .mark_request_commit = pnfs_layout_mark_request_commit, + .clear_request_commit = pnfs_generic_clear_request_commit, + .scan_commit_lists = pnfs_generic_scan_commit_lists, + .recover_commit_reqs = pnfs_generic_recover_commit_reqs, + .commit_pagelist = ff_layout_commit_pagelist, + .read_pagelist = ff_layout_read_pagelist, + .write_pagelist = ff_layout_write_pagelist, + .alloc_deviceid_node = ff_layout_alloc_deviceid_node, + .encode_layoutreturn = ff_layout_encode_layoutreturn, + .sync = pnfs_nfs_generic_sync, +}; + +static int __init nfs4flexfilelayout_init(void) +{ + printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n", + __func__); + return pnfs_register_layoutdriver(&flexfilelayout_type); +} + +static void __exit nfs4flexfilelayout_exit(void) +{ + printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n", + __func__); + pnfs_unregister_layoutdriver(&flexfilelayout_type); +} + +MODULE_ALIAS("nfs-layouttype4-4"); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("The NFSv4 flexfile layout driver"); + +module_init(nfs4flexfilelayout_init); +module_exit(nfs4flexfilelayout_exit); diff --git a/kernel/fs/nfs/flexfilelayout/flexfilelayout.h b/kernel/fs/nfs/flexfilelayout/flexfilelayout.h new file mode 100644 index 000000000..070f20445 --- /dev/null +++ b/kernel/fs/nfs/flexfilelayout/flexfilelayout.h @@ -0,0 +1,155 @@ +/* + * NFSv4 flexfile layout driver data structures. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng <bergwolf@primarydata.com> + */ + +#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H +#define FS_NFS_NFS4FLEXFILELAYOUT_H + +#include "../pnfs.h" + +/* XXX: Let's filter out insanely large mirror count for now to avoid oom + * due to network error etc. */ +#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096 + +struct nfs4_ff_ds_version { + u32 version; + u32 minor_version; + u32 rsize; + u32 wsize; + bool tightly_coupled; +}; + +/* chained in global deviceid hlist */ +struct nfs4_ff_layout_ds { + struct nfs4_deviceid_node id_node; + u32 ds_versions_cnt; + struct nfs4_ff_ds_version *ds_versions; + struct nfs4_pnfs_ds *ds; +}; + +struct nfs4_ff_layout_ds_err { + struct list_head list; /* linked in mirror error_list */ + u64 offset; + u64 length; + int status; + enum nfs_opnum4 opnum; + nfs4_stateid stateid; + struct nfs4_deviceid deviceid; +}; + +struct nfs4_ff_layout_mirror { + u32 ds_count; + u32 efficiency; + struct nfs4_ff_layout_ds *mirror_ds; + u32 fh_versions_cnt; + struct nfs_fh *fh_versions; + nfs4_stateid stateid; + struct nfs4_string user_name; + struct nfs4_string group_name; + u32 uid; + u32 gid; + struct rpc_cred *cred; + spinlock_t lock; +}; + +struct nfs4_ff_layout_segment { + struct pnfs_layout_segment generic_hdr; + u64 stripe_unit; + u32 mirror_array_cnt; + struct nfs4_ff_layout_mirror **mirror_array; +}; + +struct nfs4_flexfile_layout { + struct pnfs_layout_hdr generic_hdr; + struct pnfs_ds_commit_info commit_info; + struct list_head error_list; /* nfs4_ff_layout_ds_err */ +}; + +static inline struct nfs4_flexfile_layout * +FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct nfs4_flexfile_layout, generic_hdr); +} + +static inline struct nfs4_ff_layout_segment * +FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, + struct nfs4_ff_layout_segment, + generic_hdr); +} + +static inline struct nfs4_deviceid_node * +FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx) +{ + if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt || + FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL || + FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL) + return NULL; + return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node; +} + +static inline struct nfs4_ff_layout_ds * +FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node) +{ + return container_of(node, struct nfs4_ff_layout_ds, id_node); +} + +static inline struct nfs4_ff_layout_mirror * +FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx) +{ + if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt) + return NULL; + return FF_LAYOUT_LSEG(lseg)->mirror_array[idx]; +} + +static inline u32 +FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg) +{ + return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt; +} + +static inline bool +ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) +{ + return nfs4_test_deviceid_unavailable(node); +} + +static inline int +nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx) +{ + return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version; +} + +struct nfs4_ff_layout_ds * +nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags); +void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds); +void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds); +int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_mirror *mirror, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + gfp_t gfp_flags); +int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, int *count, + const struct pnfs_layout_range *range); +struct nfs_fh * +nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx); + +struct nfs4_pnfs_ds * +nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, + bool fail_return); + +struct rpc_clnt * +nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, + u32 ds_idx, + struct nfs_client *ds_clp, + struct inode *inode); +struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, + u32 ds_idx, struct rpc_cred *mdscred); +bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg); +#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */ diff --git a/kernel/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/kernel/fs/nfs/flexfilelayout/flexfilelayoutdev.c new file mode 100644 index 000000000..77a2d026a --- /dev/null +++ b/kernel/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -0,0 +1,552 @@ +/* + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng <bergwolf@primarydata.com> + */ + +#include <linux/nfs_fs.h> +#include <linux/vmalloc.h> +#include <linux/module.h> +#include <linux/sunrpc/addr.h> + +#include "../internal.h" +#include "../nfs4session.h" +#include "flexfilelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; +static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; + +void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds) +{ + if (mirror_ds) + nfs4_put_deviceid_node(&mirror_ds->id_node); +} + +void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) +{ + nfs4_print_deviceid(&mirror_ds->id_node.deviceid); + nfs4_pnfs_ds_put(mirror_ds->ds); + kfree_rcu(mirror_ds, id_node.rcu); +} + +/* Decode opaque device data and construct new_ds using it */ +struct nfs4_ff_layout_ds * +nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags) +{ + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + struct list_head dsaddrs; + struct nfs4_pnfs_ds_addr *da; + struct nfs4_ff_layout_ds *new_ds = NULL; + struct nfs4_ff_ds_version *ds_versions = NULL; + u32 mp_count; + u32 version_count; + __be32 *p; + int i, ret = -ENOMEM; + + /* set up xdr stream */ + scratch = alloc_page(gfp_flags); + if (!scratch) + goto out_err; + + new_ds = kzalloc(sizeof(struct nfs4_ff_layout_ds), gfp_flags); + if (!new_ds) + goto out_scratch; + + nfs4_init_deviceid_node(&new_ds->id_node, + server, + &pdev->dev_id); + INIT_LIST_HEAD(&dsaddrs); + + xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* multipath count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + mp_count = be32_to_cpup(p); + dprintk("%s: multipath ds count %d\n", __func__, mp_count); + + for (i = 0; i < mp_count; i++) { + /* multipath ds */ + da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, + &stream, gfp_flags); + if (da) + list_add_tail(&da->da_node, &dsaddrs); + } + if (list_empty(&dsaddrs)) { + dprintk("%s: no suitable DS addresses found\n", + __func__); + ret = -ENOMEDIUM; + goto out_err_drain_dsaddrs; + } + + /* version count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + version_count = be32_to_cpup(p); + dprintk("%s: version count %d\n", __func__, version_count); + + ds_versions = kzalloc(version_count * sizeof(struct nfs4_ff_ds_version), + gfp_flags); + if (!ds_versions) + goto out_scratch; + + for (i = 0; i < version_count; i++) { + /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + + * tightly_coupled(4) */ + p = xdr_inline_decode(&stream, 20); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + ds_versions[i].version = be32_to_cpup(p++); + ds_versions[i].minor_version = be32_to_cpup(p++); + ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].tightly_coupled = be32_to_cpup(p); + + if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE) + ds_versions[i].rsize = NFS_MAX_FILE_IO_SIZE; + if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE) + ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE; + + if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) { + dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__, + i, ds_versions[i].version, + ds_versions[i].minor_version); + ret = -EPROTONOSUPPORT; + goto out_err_drain_dsaddrs; + } + + dprintk("%s: [%d] vers %u minor_ver %u rsize %u wsize %u coupled %d\n", + __func__, i, ds_versions[i].version, + ds_versions[i].minor_version, + ds_versions[i].rsize, + ds_versions[i].wsize, + ds_versions[i].tightly_coupled); + } + + new_ds->ds_versions = ds_versions; + new_ds->ds_versions_cnt = version_count; + + new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + if (!new_ds->ds) + goto out_err_drain_dsaddrs; + + /* If DS was already in cache, free ds addrs */ + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, + struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + __free_page(scratch); + return new_ds; + +out_err_drain_dsaddrs: + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + kfree(ds_versions); +out_scratch: + __free_page(scratch); +out_err: + kfree(new_ds); + + dprintk("%s ERROR: returning %d\n", __func__, ret); + return NULL; +} + +static u64 +end_offset(u64 start, u64 len) +{ + u64 end; + + end = start + len; + return end >= start ? end : NFS4_MAX_UINT64; +} + +static void extend_ds_error(struct nfs4_ff_layout_ds_err *err, + u64 offset, u64 length) +{ + u64 end; + + end = max_t(u64, end_offset(err->offset, err->length), + end_offset(offset, length)); + err->offset = min_t(u64, err->offset, offset); + err->length = end - err->offset; +} + +static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + nfs4_stateid *stateid, + struct nfs4_deviceid *deviceid) +{ + return err->status == status && err->opnum == opnum && + nfs4_stateid_match(&err->stateid, stateid) && + !memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) && + end_offset(err->offset, err->length) >= offset && + err->offset <= end_offset(offset, length); +} + +static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old, + struct nfs4_ff_layout_ds_err *new) +{ + if (!ds_error_can_merge(old, new->offset, new->length, new->status, + new->opnum, &new->stateid, &new->deviceid)) + return false; + + extend_ds_error(old, new->offset, new->length); + return true; +} + +static bool +ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_ds_err *dserr) +{ + struct nfs4_ff_layout_ds_err *err; + + list_for_each_entry(err, &flo->error_list, list) { + if (merge_ds_error(err, dserr)) { + return true; + } + } + + list_add(&dserr->list, &flo->error_list); + return false; +} + +static bool +ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + nfs4_stateid *stateid, struct nfs4_deviceid *deviceid) +{ + bool found = false; + struct nfs4_ff_layout_ds_err *err; + + list_for_each_entry(err, &flo->error_list, list) { + if (ds_error_can_merge(err, offset, length, status, opnum, + stateid, deviceid)) { + found = true; + extend_ds_error(err, offset, length); + break; + } + } + + return found; +} + +int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_mirror *mirror, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + gfp_t gfp_flags) +{ + struct nfs4_ff_layout_ds_err *dserr; + bool needfree; + + if (status == 0) + return 0; + + if (mirror->mirror_ds == NULL) + return -EINVAL; + + spin_lock(&flo->generic_hdr.plh_inode->i_lock); + if (ff_layout_update_ds_error(flo, offset, length, status, opnum, + &mirror->stateid, + &mirror->mirror_ds->id_node.deviceid)) { + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + return 0; + } + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + dserr = kmalloc(sizeof(*dserr), gfp_flags); + if (!dserr) + return -ENOMEM; + + INIT_LIST_HEAD(&dserr->list); + dserr->offset = offset; + dserr->length = length; + dserr->status = status; + dserr->opnum = opnum; + nfs4_stateid_copy(&dserr->stateid, &mirror->stateid); + memcpy(&dserr->deviceid, &mirror->mirror_ds->id_node.deviceid, + NFS4_DEVICEID4_SIZE); + + spin_lock(&flo->generic_hdr.plh_inode->i_lock); + needfree = ff_layout_add_ds_error_locked(flo, dserr); + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + if (needfree) + kfree(dserr); + + return 0; +} + +/* currently we only support AUTH_NONE and AUTH_SYS */ +static rpc_authflavor_t +nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror) +{ + if (mirror->uid == (u32)-1) + return RPC_AUTH_NULL; + return RPC_AUTH_UNIX; +} + +/* fetch cred for NFSv3 DS */ +static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror, + struct nfs4_pnfs_ds *ds) +{ + if (ds->ds_clp && !mirror->cred && + mirror->mirror_ds->ds_versions[0].version == 3) { + struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth; + struct rpc_cred *cred; + struct auth_cred acred = { + .uid = make_kuid(&init_user_ns, mirror->uid), + .gid = make_kgid(&init_user_ns, mirror->gid), + }; + + /* AUTH_NULL ignores acred */ + cred = auth->au_ops->lookup_cred(auth, &acred, 0); + if (IS_ERR(cred)) { + dprintk("%s: lookup_cred failed with %ld\n", + __func__, PTR_ERR(cred)); + return PTR_ERR(cred); + } else { + mirror->cred = cred; + } + } + return 0; +} + +struct nfs_fh * +nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx); + struct nfs_fh *fh = NULL; + struct nfs4_deviceid_node *devid; + + if (mirror == NULL || mirror->mirror_ds == NULL || + mirror->mirror_ds->ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for mirror offset index %d\n", + __func__, mirror_idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + pnfs_generic_mark_devid_invalid(devid); + } + goto out; + } + + /* FIXME: For now assume there is only 1 version available for the DS */ + fh = &mirror->fh_versions[0]; +out: + return fh; +} + +/* Upon return, either ds is connected, or ds is NULL */ +struct nfs4_pnfs_ds * +nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, + bool fail_return) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + struct nfs4_pnfs_ds *ds = NULL; + struct nfs4_deviceid_node *devid; + struct inode *ino = lseg->pls_layout->plh_inode; + struct nfs_server *s = NFS_SERVER(ino); + unsigned int max_payload; + rpc_authflavor_t flavor; + + if (mirror == NULL || mirror->mirror_ds == NULL || + mirror->mirror_ds->ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", + __func__, ds_idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + pnfs_generic_mark_devid_invalid(devid); + } + goto out; + } + + devid = &mirror->mirror_ds->id_node; + if (ff_layout_test_devid_unavailable(devid)) + goto out; + + ds = mirror->mirror_ds->ds; + /* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */ + smp_rmb(); + if (ds->ds_clp) + goto out; + + flavor = nfs4_ff_layout_choose_authflavor(mirror); + + /* FIXME: For now we assume the server sent only one version of NFS + * to use for the DS. + */ + nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + dataserver_retrans, + mirror->mirror_ds->ds_versions[0].version, + mirror->mirror_ds->ds_versions[0].minor_version, + flavor); + + /* connect success, check rsize/wsize limit */ + if (ds->ds_clp) { + max_payload = + nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient), + NULL); + if (mirror->mirror_ds->ds_versions[0].rsize > max_payload) + mirror->mirror_ds->ds_versions[0].rsize = max_payload; + if (mirror->mirror_ds->ds_versions[0].wsize > max_payload) + mirror->mirror_ds->ds_versions[0].wsize = max_payload; + } else { + ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, lseg->pls_range.offset, + lseg->pls_range.length, NFS4ERR_NXIO, + OP_ILLEGAL, GFP_NOIO); + if (fail_return) { + pnfs_error_mark_layout_for_return(ino, lseg); + if (ff_layout_has_available_ds(lseg)) + pnfs_set_retry_layoutget(lseg->pls_layout); + else + pnfs_clear_retry_layoutget(lseg->pls_layout); + + } else { + if (ff_layout_has_available_ds(lseg)) + set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lseg->pls_layout->plh_flags); + else { + pnfs_error_mark_layout_for_return(ino, lseg); + pnfs_clear_retry_layoutget(lseg->pls_layout); + } + } + } + + if (ff_layout_update_mirror_cred(mirror, ds)) + ds = NULL; +out: + return ds; +} + +struct rpc_cred * +ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct rpc_cred *mdscred) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + struct rpc_cred *cred = ERR_PTR(-EINVAL); + + if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true)) + goto out; + + if (mirror && mirror->cred) + cred = mirror->cred; + else + cred = mdscred; +out: + return cred; +} + +/** +* Find or create a DS rpc client with th MDS server rpc client auth flavor +* in the nfs_client cl_ds_clients list. +*/ +struct rpc_clnt * +nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct nfs_client *ds_clp, struct inode *inode) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + + switch (mirror->mirror_ds->ds_versions[0].version) { + case 3: + /* For NFSv3 DS, flavor is set when creating DS connections */ + return ds_clp->cl_rpcclient; + case 4: + return nfs4_find_or_create_ds_client(ds_clp, inode); + default: + BUG(); + } +} + +static bool is_range_intersecting(u64 offset1, u64 length1, + u64 offset2, u64 length2) +{ + u64 end1 = end_offset(offset1, length1); + u64 end2 = end_offset(offset2, length2); + + return (end1 == NFS4_MAX_UINT64 || end1 > offset2) && + (end2 == NFS4_MAX_UINT64 || end2 > offset1); +} + +/* called with inode i_lock held */ +int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, int *count, + const struct pnfs_layout_range *range) +{ + struct nfs4_ff_layout_ds_err *err, *n; + __be32 *p; + + list_for_each_entry_safe(err, n, &flo->error_list, list) { + if (!is_range_intersecting(err->offset, err->length, + range->offset, range->length)) + continue; + /* offset(8) + length(8) + stateid(NFS4_STATEID_SIZE) + * + deviceid(NFS4_DEVICEID4_SIZE) + status(4) + opnum(4) + */ + p = xdr_reserve_space(xdr, + 24 + NFS4_STATEID_SIZE + NFS4_DEVICEID4_SIZE); + if (unlikely(!p)) + return -ENOBUFS; + p = xdr_encode_hyper(p, err->offset); + p = xdr_encode_hyper(p, err->length); + p = xdr_encode_opaque_fixed(p, &err->stateid, + NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, &err->deviceid, + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(err->status); + *p++ = cpu_to_be32(err->opnum); + *count += 1; + list_del(&err->list); + dprintk("%s: offset %llu length %llu status %d op %d count %d\n", + __func__, err->offset, err->length, err->status, + err->opnum, *count); + kfree(err); + } + + return 0; +} + +bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_deviceid_node *devid; + int idx; + + for (idx = 0; idx < FF_LAYOUT_MIRROR_COUNT(lseg); idx++) { + mirror = FF_LAYOUT_COMP(lseg, idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + if (!ff_layout_test_devid_unavailable(devid)) + return true; + } + } + + return false; +} + +module_param(dataserver_retrans, uint, 0644); +MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client " + "retries a request before it attempts further " + " recovery action."); +module_param(dataserver_timeo, uint, 0644); +MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the " + "NFSv4.1 client waits for a response from a " + " data server before it retries an NFS request."); diff --git a/kernel/fs/nfs/fscache-index.c b/kernel/fs/nfs/fscache-index.c new file mode 100644 index 000000000..777b05506 --- /dev/null +++ b/kernel/fs/nfs/fscache-index.c @@ -0,0 +1,336 @@ +/* NFS FS-Cache index structure definition + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_fs_sb.h> +#include <linux/in6.h> + +#include "internal.h" +#include "fscache.h" + +#define NFSDBG_FACILITY NFSDBG_FSCACHE + +/* + * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks + * the cookie for the top-level index object for NFS into here. The top-level + * index can than have other cache objects inserted into it. + */ +struct fscache_netfs nfs_fscache_netfs = { + .name = "nfs", + .version = 0, +}; + +/* + * Register NFS for caching + */ +int nfs_fscache_register(void) +{ + return fscache_register_netfs(&nfs_fscache_netfs); +} + +/* + * Unregister NFS for caching + */ +void nfs_fscache_unregister(void) +{ + fscache_unregister_netfs(&nfs_fscache_netfs); +} + +/* + * Layout of the key for an NFS server cache object. + */ +struct nfs_server_key { + uint16_t nfsversion; /* NFS protocol version */ + uint16_t family; /* address family */ + uint16_t port; /* IP port */ + union { + struct in_addr ipv4_addr; /* IPv4 address */ + struct in6_addr ipv6_addr; /* IPv6 address */ + } addr[0]; +}; + +/* + * Generate a key to describe a server in the main NFS index + * - We return the length of the key, or 0 if we can't generate one + */ +static uint16_t nfs_server_get_key(const void *cookie_netfs_data, + void *buffer, uint16_t bufmax) +{ + const struct nfs_client *clp = cookie_netfs_data; + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr; + const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr; + struct nfs_server_key *key = buffer; + uint16_t len = sizeof(struct nfs_server_key); + + memset(key, 0, len); + key->nfsversion = clp->rpc_ops->version; + key->family = clp->cl_addr.ss_family; + + switch (clp->cl_addr.ss_family) { + case AF_INET: + key->port = sin->sin_port; + key->addr[0].ipv4_addr = sin->sin_addr; + len += sizeof(key->addr[0].ipv4_addr); + break; + + case AF_INET6: + key->port = sin6->sin6_port; + key->addr[0].ipv6_addr = sin6->sin6_addr; + len += sizeof(key->addr[0].ipv6_addr); + break; + + default: + printk(KERN_WARNING "NFS: Unknown network family '%d'\n", + clp->cl_addr.ss_family); + len = 0; + break; + } + + return len; +} + +/* + * Define the server object for FS-Cache. This is used to describe a server + * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and + * server address parameters. + */ +const struct fscache_cookie_def nfs_fscache_server_index_def = { + .name = "NFS.server", + .type = FSCACHE_COOKIE_TYPE_INDEX, + .get_key = nfs_server_get_key, +}; + +/* + * Generate a key to describe a superblock key in the main NFS index + */ +static uint16_t nfs_super_get_key(const void *cookie_netfs_data, + void *buffer, uint16_t bufmax) +{ + const struct nfs_fscache_key *key; + const struct nfs_server *nfss = cookie_netfs_data; + uint16_t len; + + key = nfss->fscache_key; + len = sizeof(key->key) + key->key.uniq_len; + if (len > bufmax) { + len = 0; + } else { + memcpy(buffer, &key->key, sizeof(key->key)); + memcpy(buffer + sizeof(key->key), + key->key.uniquifier, key->key.uniq_len); + } + + return len; +} + +/* + * Define the superblock object for FS-Cache. This is used to describe a + * superblock object to fscache_acquire_cookie(). It is keyed by all the NFS + * parameters that might cause a separate superblock. + */ +const struct fscache_cookie_def nfs_fscache_super_index_def = { + .name = "NFS.super", + .type = FSCACHE_COOKIE_TYPE_INDEX, + .get_key = nfs_super_get_key, +}; + +/* + * Definition of the auxiliary data attached to NFS inode storage objects + * within the cache. + * + * The contents of this struct are recorded in the on-disk local cache in the + * auxiliary data attached to the data storage object backing an inode. This + * permits coherency to be managed when a new inode binds to an already extant + * cache object. + */ +struct nfs_fscache_inode_auxdata { + struct timespec mtime; + struct timespec ctime; + loff_t size; + u64 change_attr; +}; + +/* + * Generate a key to describe an NFS inode in an NFS server's index + */ +static uint16_t nfs_fscache_inode_get_key(const void *cookie_netfs_data, + void *buffer, uint16_t bufmax) +{ + const struct nfs_inode *nfsi = cookie_netfs_data; + uint16_t nsize; + + /* use the inode's NFS filehandle as the key */ + nsize = nfsi->fh.size; + memcpy(buffer, nfsi->fh.data, nsize); + return nsize; +} + +/* + * Get certain file attributes from the netfs data + * - This function can be absent for an index + * - Not permitted to return an error + * - The netfs data from the cookie being used as the source is presented + */ +static void nfs_fscache_inode_get_attr(const void *cookie_netfs_data, + uint64_t *size) +{ + const struct nfs_inode *nfsi = cookie_netfs_data; + + *size = nfsi->vfs_inode.i_size; +} + +/* + * Get the auxiliary data from netfs data + * - This function can be absent if the index carries no state data + * - Should store the auxiliary data in the buffer + * - Should return the amount of amount stored + * - Not permitted to return an error + * - The netfs data from the cookie being used as the source is presented + */ +static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data, + void *buffer, uint16_t bufmax) +{ + struct nfs_fscache_inode_auxdata auxdata; + const struct nfs_inode *nfsi = cookie_netfs_data; + + memset(&auxdata, 0, sizeof(auxdata)); + auxdata.size = nfsi->vfs_inode.i_size; + auxdata.mtime = nfsi->vfs_inode.i_mtime; + auxdata.ctime = nfsi->vfs_inode.i_ctime; + + if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) + auxdata.change_attr = nfsi->vfs_inode.i_version; + + if (bufmax > sizeof(auxdata)) + bufmax = sizeof(auxdata); + + memcpy(buffer, &auxdata, bufmax); + return bufmax; +} + +/* + * Consult the netfs about the state of an object + * - This function can be absent if the index carries no state data + * - The netfs data from the cookie being used as the target is + * presented, as is the auxiliary data + */ +static +enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, + const void *data, + uint16_t datalen) +{ + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = cookie_netfs_data; + + if (datalen != sizeof(auxdata)) + return FSCACHE_CHECKAUX_OBSOLETE; + + memset(&auxdata, 0, sizeof(auxdata)); + auxdata.size = nfsi->vfs_inode.i_size; + auxdata.mtime = nfsi->vfs_inode.i_mtime; + auxdata.ctime = nfsi->vfs_inode.i_ctime; + + if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) + auxdata.change_attr = nfsi->vfs_inode.i_version; + + if (memcmp(data, &auxdata, datalen) != 0) + return FSCACHE_CHECKAUX_OBSOLETE; + + return FSCACHE_CHECKAUX_OKAY; +} + +/* + * Indication from FS-Cache that the cookie is no longer cached + * - This function is called when the backing store currently caching a cookie + * is removed + * - The netfs should use this to clean up any markers indicating cached pages + * - This is mandatory for any object that may have data + */ +static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data) +{ + struct nfs_inode *nfsi = cookie_netfs_data; + struct pagevec pvec; + pgoff_t first; + int loop, nr_pages; + + pagevec_init(&pvec, 0); + first = 0; + + dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi); + + for (;;) { + /* grab a bunch of pages to unmark */ + nr_pages = pagevec_lookup(&pvec, + nfsi->vfs_inode.i_mapping, + first, + PAGEVEC_SIZE - pagevec_count(&pvec)); + if (!nr_pages) + break; + + for (loop = 0; loop < nr_pages; loop++) + ClearPageFsCache(pvec.pages[loop]); + + first = pvec.pages[nr_pages - 1]->index + 1; + + pvec.nr = nr_pages; + pagevec_release(&pvec); + cond_resched(); + } +} + +/* + * Get an extra reference on a read context. + * - This function can be absent if the completion function doesn't require a + * context. + * - The read context is passed back to NFS in the event that a data read on the + * cache fails with EIO - in which case the server must be contacted to + * retrieve the data, which requires the read context for security. + */ +static void nfs_fh_get_context(void *cookie_netfs_data, void *context) +{ + get_nfs_open_context(context); +} + +/* + * Release an extra reference on a read context. + * - This function can be absent if the completion function doesn't require a + * context. + */ +static void nfs_fh_put_context(void *cookie_netfs_data, void *context) +{ + if (context) + put_nfs_open_context(context); +} + +/* + * Define the inode object for FS-Cache. This is used to describe an inode + * object to fscache_acquire_cookie(). It is keyed by the NFS file handle for + * an inode. + * + * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime + * held in the cache auxiliary data for the data storage object with those in + * the inode struct in memory. + */ +const struct fscache_cookie_def nfs_fscache_inode_object_def = { + .name = "NFS.fh", + .type = FSCACHE_COOKIE_TYPE_DATAFILE, + .get_key = nfs_fscache_inode_get_key, + .get_attr = nfs_fscache_inode_get_attr, + .get_aux = nfs_fscache_inode_get_aux, + .check_aux = nfs_fscache_inode_check_aux, + .now_uncached = nfs_fscache_inode_now_uncached, + .get_context = nfs_fh_get_context, + .put_context = nfs_fh_put_context, +}; diff --git a/kernel/fs/nfs/fscache.c b/kernel/fs/nfs/fscache.c new file mode 100644 index 000000000..d63bea8bb --- /dev/null +++ b/kernel/fs/nfs/fscache.c @@ -0,0 +1,439 @@ +/* NFS filesystem cache interface + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_fs_sb.h> +#include <linux/in6.h> +#include <linux/seq_file.h> +#include <linux/slab.h> + +#include "internal.h" +#include "iostat.h" +#include "fscache.h" + +#define NFSDBG_FACILITY NFSDBG_FSCACHE + +static struct rb_root nfs_fscache_keys = RB_ROOT; +static DEFINE_SPINLOCK(nfs_fscache_keys_lock); + +/* + * Get the per-client index cookie for an NFS client if the appropriate mount + * flag was set + * - We always try and get an index cookie for the client, but get filehandle + * cookies on a per-superblock basis, depending on the mount flags + */ +void nfs_fscache_get_client_cookie(struct nfs_client *clp) +{ + /* create a cache index for looking up filehandles */ + clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index, + &nfs_fscache_server_index_def, + clp, true); + dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n", + clp, clp->fscache); +} + +/* + * Dispose of a per-client cookie + */ +void nfs_fscache_release_client_cookie(struct nfs_client *clp) +{ + dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n", + clp, clp->fscache); + + fscache_relinquish_cookie(clp->fscache, 0); + clp->fscache = NULL; +} + +/* + * Get the cache cookie for an NFS superblock. We have to handle + * uniquification here because the cache doesn't do it for us. + * + * The default uniquifier is just an empty string, but it may be overridden + * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent + * superblock across an automount point of some nature. + */ +void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) +{ + struct nfs_fscache_key *key, *xkey; + struct nfs_server *nfss = NFS_SB(sb); + struct rb_node **p, *parent; + int diff; + + if (!uniq) { + uniq = ""; + ulen = 1; + } + + key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL); + if (!key) + return; + + key->nfs_client = nfss->nfs_client; + key->key.super.s_flags = sb->s_flags & NFS_MS_MASK; + key->key.nfs_server.flags = nfss->flags; + key->key.nfs_server.rsize = nfss->rsize; + key->key.nfs_server.wsize = nfss->wsize; + key->key.nfs_server.acregmin = nfss->acregmin; + key->key.nfs_server.acregmax = nfss->acregmax; + key->key.nfs_server.acdirmin = nfss->acdirmin; + key->key.nfs_server.acdirmax = nfss->acdirmax; + key->key.nfs_server.fsid = nfss->fsid; + key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor; + + key->key.uniq_len = ulen; + memcpy(key->key.uniquifier, uniq, ulen); + + spin_lock(&nfs_fscache_keys_lock); + p = &nfs_fscache_keys.rb_node; + parent = NULL; + while (*p) { + parent = *p; + xkey = rb_entry(parent, struct nfs_fscache_key, node); + + if (key->nfs_client < xkey->nfs_client) + goto go_left; + if (key->nfs_client > xkey->nfs_client) + goto go_right; + + diff = memcmp(&key->key, &xkey->key, sizeof(key->key)); + if (diff < 0) + goto go_left; + if (diff > 0) + goto go_right; + + if (key->key.uniq_len == 0) + goto non_unique; + diff = memcmp(key->key.uniquifier, + xkey->key.uniquifier, + key->key.uniq_len); + if (diff < 0) + goto go_left; + if (diff > 0) + goto go_right; + goto non_unique; + + go_left: + p = &(*p)->rb_left; + continue; + go_right: + p = &(*p)->rb_right; + } + + rb_link_node(&key->node, parent, p); + rb_insert_color(&key->node, &nfs_fscache_keys); + spin_unlock(&nfs_fscache_keys_lock); + nfss->fscache_key = key; + + /* create a cache index for looking up filehandles */ + nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache, + &nfs_fscache_super_index_def, + nfss, true); + dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", + nfss, nfss->fscache); + return; + +non_unique: + spin_unlock(&nfs_fscache_keys_lock); + kfree(key); + nfss->fscache_key = NULL; + nfss->fscache = NULL; + printk(KERN_WARNING "NFS:" + " Cache request denied due to non-unique superblock keys\n"); +} + +/* + * release a per-superblock cookie + */ +void nfs_fscache_release_super_cookie(struct super_block *sb) +{ + struct nfs_server *nfss = NFS_SB(sb); + + dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n", + nfss, nfss->fscache); + + fscache_relinquish_cookie(nfss->fscache, 0); + nfss->fscache = NULL; + + if (nfss->fscache_key) { + spin_lock(&nfs_fscache_keys_lock); + rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys); + spin_unlock(&nfs_fscache_keys_lock); + kfree(nfss->fscache_key); + nfss->fscache_key = NULL; + } +} + +/* + * Initialise the per-inode cache cookie pointer for an NFS inode. + */ +void nfs_fscache_init_inode(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + nfsi->fscache = NULL; + if (!S_ISREG(inode->i_mode)) + return; + nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, + &nfs_fscache_inode_object_def, + nfsi, false); +} + +/* + * Release a per-inode cookie. + */ +void nfs_fscache_clear_inode(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct fscache_cookie *cookie = nfs_i_fscache(inode); + + dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); + + fscache_relinquish_cookie(cookie, false); + nfsi->fscache = NULL; +} + +static bool nfs_fscache_can_enable(void *data) +{ + struct inode *inode = data; + + return !inode_is_open_for_write(inode); +} + +/* + * Enable or disable caching for a file that is being opened as appropriate. + * The cookie is allocated when the inode is initialised, but is not enabled at + * that time. Enablement is deferred to file-open time to avoid stat() and + * access() thrashing the cache. + * + * For now, with NFS, only regular files that are open read-only will be able + * to use the cache. + * + * We enable the cache for an inode if we open it read-only and it isn't + * currently open for writing. We disable the cache if the inode is open + * write-only. + * + * The caller uses the file struct to pin i_writecount on the inode before + * calling us when a file is opened for writing, so we can make use of that. + * + * Note that this may be invoked multiple times in parallel by parallel + * nfs_open() functions. + */ +void nfs_fscache_open_file(struct inode *inode, struct file *filp) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct fscache_cookie *cookie = nfs_i_fscache(inode); + + if (!fscache_cookie_valid(cookie)) + return; + + if (inode_is_open_for_write(inode)) { + dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); + clear_bit(NFS_INO_FSCACHE, &nfsi->flags); + fscache_disable_cookie(cookie, true); + fscache_uncache_all_inode_pages(cookie, inode); + } else { + dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi); + fscache_enable_cookie(cookie, nfs_fscache_can_enable, inode); + if (fscache_cookie_enabled(cookie)) + set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); + } +} +EXPORT_SYMBOL_GPL(nfs_fscache_open_file); + +/* + * Release the caching state associated with a page, if the page isn't busy + * interacting with the cache. + * - Returns true (can release page) or false (page busy). + */ +int nfs_fscache_release_page(struct page *page, gfp_t gfp) +{ + if (PageFsCache(page)) { + struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host); + + BUG_ON(!cookie); + dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", + cookie, page, NFS_I(page->mapping->host)); + + if (!fscache_maybe_release_page(cookie, page, gfp)) + return 0; + + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); + } + + return 1; +} + +/* + * Release the caching state associated with a page if undergoing complete page + * invalidation. + */ +void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) +{ + struct fscache_cookie *cookie = nfs_i_fscache(inode); + + BUG_ON(!cookie); + + dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n", + cookie, page, NFS_I(inode)); + + fscache_wait_on_page_write(cookie, page); + + BUG_ON(!PageLocked(page)); + fscache_uncache_page(cookie, page); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); +} + +/* + * Handle completion of a page being read from the cache. + * - Called in process (keventd) context. + */ +static void nfs_readpage_from_fscache_complete(struct page *page, + void *context, + int error) +{ + dfprintk(FSCACHE, + "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n", + page, context, error); + + /* if the read completes with an error, we just unlock the page and let + * the VM reissue the readpage */ + if (!error) { + SetPageUptodate(page); + unlock_page(page); + } else { + error = nfs_readpage_async(context, page->mapping->host, page); + if (error) + unlock_page(page); + } +} + +/* + * Retrieve a page from fscache + */ +int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, + struct inode *inode, struct page *page) +{ + int ret; + + dfprintk(FSCACHE, + "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", + nfs_i_fscache(inode), page, page->index, page->flags, inode); + + ret = fscache_read_or_alloc_page(nfs_i_fscache(inode), + page, + nfs_readpage_from_fscache_complete, + ctx, + GFP_KERNEL); + + switch (ret) { + case 0: /* read BIO submitted (page in fscache) */ + dfprintk(FSCACHE, + "NFS: readpage_from_fscache: BIO submitted\n"); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); + return ret; + + case -ENOBUFS: /* inode not in cache */ + case -ENODATA: /* page not in cache */ + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); + dfprintk(FSCACHE, + "NFS: readpage_from_fscache %d\n", ret); + return 1; + + default: + dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); + } + return ret; +} + +/* + * Retrieve a set of pages from fscache + */ +int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, + struct inode *inode, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages) +{ + unsigned npages = *nr_pages; + int ret; + + dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", + nfs_i_fscache(inode), npages, inode); + + ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode), + mapping, pages, nr_pages, + nfs_readpage_from_fscache_complete, + ctx, + mapping_gfp_mask(mapping)); + if (*nr_pages < npages) + nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, + npages); + if (*nr_pages > 0) + nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, + *nr_pages); + + switch (ret) { + case 0: /* read submitted to the cache for all pages */ + BUG_ON(!list_empty(pages)); + BUG_ON(*nr_pages != 0); + dfprintk(FSCACHE, + "NFS: nfs_getpages_from_fscache: submitted\n"); + + return ret; + + case -ENOBUFS: /* some pages aren't cached and can't be */ + case -ENODATA: /* some pages aren't cached */ + dfprintk(FSCACHE, + "NFS: nfs_getpages_from_fscache: no page: %d\n", ret); + return 1; + + default: + dfprintk(FSCACHE, + "NFS: nfs_getpages_from_fscache: ret %d\n", ret); + } + + return ret; +} + +/* + * Store a newly fetched page in fscache + * - PG_fscache must be set on the page + */ +void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) +{ + int ret; + + dfprintk(FSCACHE, + "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", + nfs_i_fscache(inode), page, page->index, page->flags, sync); + + ret = fscache_write_page(nfs_i_fscache(inode), page, GFP_KERNEL); + dfprintk(FSCACHE, + "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", + page, page->index, page->flags, ret); + + if (ret != 0) { + fscache_uncache_page(nfs_i_fscache(inode), page); + nfs_inc_fscache_stats(inode, + NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); + } else { + nfs_inc_fscache_stats(inode, + NFSIOS_FSCACHE_PAGES_WRITTEN_OK); + } +} diff --git a/kernel/fs/nfs/fscache.h b/kernel/fs/nfs/fscache.h new file mode 100644 index 000000000..d7fe3e799 --- /dev/null +++ b/kernel/fs/nfs/fscache.h @@ -0,0 +1,229 @@ +/* NFS filesystem cache interface definitions + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _NFS_FSCACHE_H +#define _NFS_FSCACHE_H + +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs4_mount.h> +#include <linux/fscache.h> + +#ifdef CONFIG_NFS_FSCACHE + +/* + * set of NFS FS-Cache objects that form a superblock key + */ +struct nfs_fscache_key { + struct rb_node node; + struct nfs_client *nfs_client; /* the server */ + + /* the elements of the unique key - as used by nfs_compare_super() and + * nfs_compare_mount_options() to distinguish superblocks */ + struct { + struct { + unsigned long s_flags; /* various flags + * (& NFS_MS_MASK) */ + } super; + + struct { + struct nfs_fsid fsid; + int flags; + unsigned int rsize; /* read size */ + unsigned int wsize; /* write size */ + unsigned int acregmin; /* attr cache timeouts */ + unsigned int acregmax; + unsigned int acdirmin; + unsigned int acdirmax; + } nfs_server; + + struct { + rpc_authflavor_t au_flavor; + } rpc_auth; + + /* uniquifier - can be used if nfs_server.flags includes + * NFS_MOUNT_UNSHARED */ + u8 uniq_len; + char uniquifier[0]; + } key; +}; + +/* + * fscache-index.c + */ +extern struct fscache_netfs nfs_fscache_netfs; +extern const struct fscache_cookie_def nfs_fscache_server_index_def; +extern const struct fscache_cookie_def nfs_fscache_super_index_def; +extern const struct fscache_cookie_def nfs_fscache_inode_object_def; + +extern int nfs_fscache_register(void); +extern void nfs_fscache_unregister(void); + +/* + * fscache.c + */ +extern void nfs_fscache_get_client_cookie(struct nfs_client *); +extern void nfs_fscache_release_client_cookie(struct nfs_client *); + +extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int); +extern void nfs_fscache_release_super_cookie(struct super_block *); + +extern void nfs_fscache_init_inode(struct inode *); +extern void nfs_fscache_clear_inode(struct inode *); +extern void nfs_fscache_open_file(struct inode *, struct file *); + +extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); +extern int nfs_fscache_release_page(struct page *, gfp_t); + +extern int __nfs_readpage_from_fscache(struct nfs_open_context *, + struct inode *, struct page *); +extern int __nfs_readpages_from_fscache(struct nfs_open_context *, + struct inode *, struct address_space *, + struct list_head *, unsigned *); +extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); + +/* + * wait for a page to complete writing to the cache + */ +static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, + struct page *page) +{ + if (PageFsCache(page)) + fscache_wait_on_page_write(nfsi->fscache, page); +} + +/* + * release the caching state associated with a page if undergoing complete page + * invalidation + */ +static inline void nfs_fscache_invalidate_page(struct page *page, + struct inode *inode) +{ + if (PageFsCache(page)) + __nfs_fscache_invalidate_page(page, inode); +} + +/* + * Retrieve a page from an inode data storage object. + */ +static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, + struct inode *inode, + struct page *page) +{ + if (NFS_I(inode)->fscache) + return __nfs_readpage_from_fscache(ctx, inode, page); + return -ENOBUFS; +} + +/* + * Retrieve a set of pages from an inode data storage object. + */ +static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, + struct inode *inode, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages) +{ + if (NFS_I(inode)->fscache) + return __nfs_readpages_from_fscache(ctx, inode, mapping, pages, + nr_pages); + return -ENOBUFS; +} + +/* + * Store a page newly fetched from the server in an inode data storage object + * in the cache. + */ +static inline void nfs_readpage_to_fscache(struct inode *inode, + struct page *page, + int sync) +{ + if (PageFsCache(page)) + __nfs_readpage_to_fscache(inode, page, sync); +} + +/* + * Invalidate the contents of fscache for this inode. This will not sleep. + */ +static inline void nfs_fscache_invalidate(struct inode *inode) +{ + fscache_invalidate(NFS_I(inode)->fscache); +} + +/* + * Wait for an object to finish being invalidated. + */ +static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) +{ + fscache_wait_on_invalidate(NFS_I(inode)->fscache); +} + +/* + * indicate the client caching state as readable text + */ +static inline const char *nfs_server_fscache_state(struct nfs_server *server) +{ + if (server->fscache && (server->options & NFS_OPTION_FSCACHE)) + return "yes"; + return "no "; +} + +#else /* CONFIG_NFS_FSCACHE */ +static inline int nfs_fscache_register(void) { return 0; } +static inline void nfs_fscache_unregister(void) {} + +static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {} +static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {} + +static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} + +static inline void nfs_fscache_init_inode(struct inode *inode) {} +static inline void nfs_fscache_clear_inode(struct inode *inode) {} +static inline void nfs_fscache_open_file(struct inode *inode, + struct file *filp) {} + +static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) +{ + return 1; /* True: may release page */ +} +static inline void nfs_fscache_invalidate_page(struct page *page, + struct inode *inode) {} +static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, + struct page *page) {} + +static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, + struct inode *inode, + struct page *page) +{ + return -ENOBUFS; +} +static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, + struct inode *inode, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages) +{ + return -ENOBUFS; +} +static inline void nfs_readpage_to_fscache(struct inode *inode, + struct page *page, int sync) {} + + +static inline void nfs_fscache_invalidate(struct inode *inode) {} +static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {} + +static inline const char *nfs_server_fscache_state(struct nfs_server *server) +{ + return "no "; +} + +#endif /* CONFIG_NFS_FSCACHE */ +#endif /* _NFS_FSCACHE_H */ diff --git a/kernel/fs/nfs/getroot.c b/kernel/fs/nfs/getroot.c new file mode 100644 index 000000000..a608ffd28 --- /dev/null +++ b/kernel/fs/nfs/getroot.c @@ -0,0 +1,133 @@ +/* getroot.c: get the root dentry for an NFS mount + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/init.h> + +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/stats.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/lockd/bind.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/vfs.h> +#include <linux/namei.h> +#include <linux/security.h> + +#include <asm/uaccess.h> + +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_CLIENT + +/* + * Set the superblock root dentry. + * Note that this function frees the inode in case of error. + */ +static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *inode) +{ + /* The mntroot acts as the dummy root dentry for this superblock */ + if (sb->s_root == NULL) { + sb->s_root = d_make_root(inode); + if (sb->s_root == NULL) + return -ENOMEM; + ihold(inode); + /* + * Ensure that this dentry is invisible to d_find_alias(). + * Otherwise, it may be spliced into the tree by + * d_splice_alias if a parent directory from the same + * filesystem gets mounted at a later time. + * This again causes shrink_dcache_for_umount_subtree() to + * Oops, since the test for IS_ROOT() will fail. + */ + spin_lock(&d_inode(sb->s_root)->i_lock); + spin_lock(&sb->s_root->d_lock); + hlist_del_init(&sb->s_root->d_u.d_alias); + spin_unlock(&sb->s_root->d_lock); + spin_unlock(&d_inode(sb->s_root)->i_lock); + } + return 0; +} + +/* + * get an NFS2/NFS3 root dentry from the root filehandle + */ +struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh, + const char *devname) +{ + struct nfs_server *server = NFS_SB(sb); + struct nfs_fsinfo fsinfo; + struct dentry *ret; + struct inode *inode; + void *name = kstrdup(devname, GFP_KERNEL); + int error; + + if (!name) + return ERR_PTR(-ENOMEM); + + /* get the actual root for this mount */ + fsinfo.fattr = nfs_alloc_fattr(); + if (fsinfo.fattr == NULL) { + kfree(name); + return ERR_PTR(-ENOMEM); + } + + error = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo); + if (error < 0) { + dprintk("nfs_get_root: getattr error = %d\n", -error); + ret = ERR_PTR(error); + goto out; + } + + inode = nfs_fhget(sb, mntfh, fsinfo.fattr, NULL); + if (IS_ERR(inode)) { + dprintk("nfs_get_root: get root inode failed\n"); + ret = ERR_CAST(inode); + goto out; + } + + error = nfs_superblock_set_dummy_root(sb, inode); + if (error != 0) { + ret = ERR_PTR(error); + goto out; + } + + /* root dentries normally start off anonymous and get spliced in later + * if the dentry tree reaches them; however if the dentry already + * exists, we'll pick it up at this point and use it as the root + */ + ret = d_obtain_root(inode); + if (IS_ERR(ret)) { + dprintk("nfs_get_root: get root dentry failed\n"); + goto out; + } + + security_d_instantiate(ret, inode); + spin_lock(&ret->d_lock); + if (IS_ROOT(ret) && !ret->d_fsdata && + !(ret->d_flags & DCACHE_NFSFS_RENAMED)) { + ret->d_fsdata = name; + name = NULL; + } + spin_unlock(&ret->d_lock); +out: + kfree(name); + nfs_free_fattr(fsinfo.fattr); + return ret; +} diff --git a/kernel/fs/nfs/inode.c b/kernel/fs/nfs/inode.c new file mode 100644 index 000000000..f734562c6 --- /dev/null +++ b/kernel/fs/nfs/inode.c @@ -0,0 +1,2066 @@ +/* + * linux/fs/nfs/inode.c + * + * Copyright (C) 1992 Rick Sladkey + * + * nfs inode and superblock handling functions + * + * Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some + * experimental NFS changes. Modularisation taken straight from SYS5 fs. + * + * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. + * J.S.Peatfield@damtp.cam.ac.uk + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/stats.h> +#include <linux/sunrpc/metrics.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs4_mount.h> +#include <linux/lockd/bind.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/vfs.h> +#include <linux/inet.h> +#include <linux/nfs_xdr.h> +#include <linux/slab.h> +#include <linux/compat.h> +#include <linux/freezer.h> + +#include <asm/uaccess.h> + +#include "nfs4_fs.h" +#include "callback.h" +#include "delegation.h" +#include "iostat.h" +#include "internal.h" +#include "fscache.h" +#include "pnfs.h" +#include "nfs.h" +#include "netns.h" + +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +#define NFS_64_BIT_INODE_NUMBERS_ENABLED 1 + +/* Default is to see 64-bit inode numbers */ +static bool enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED; + +static void nfs_invalidate_inode(struct inode *); +static int nfs_update_inode(struct inode *, struct nfs_fattr *); + +static struct kmem_cache * nfs_inode_cachep; + +static inline unsigned long +nfs_fattr_to_ino_t(struct nfs_fattr *fattr) +{ + return nfs_fileid_to_ino_t(fattr->fileid); +} + +/** + * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks + * @word: long word containing the bit lock + */ +int nfs_wait_bit_killable(struct wait_bit_key *key) +{ + if (fatal_signal_pending(current)) + return -ERESTARTSYS; + freezable_schedule_unsafe(); + return 0; +} +EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); + +/** + * nfs_compat_user_ino64 - returns the user-visible inode number + * @fileid: 64-bit fileid + * + * This function returns a 32-bit inode number if the boot parameter + * nfs.enable_ino64 is zero. + */ +u64 nfs_compat_user_ino64(u64 fileid) +{ +#ifdef CONFIG_COMPAT + compat_ulong_t ino; +#else + unsigned long ino; +#endif + + if (enable_ino64) + return fileid; + ino = fileid; + if (sizeof(ino) < sizeof(fileid)) + ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8; + return ino; +} + +int nfs_drop_inode(struct inode *inode) +{ + return NFS_STALE(inode) || generic_drop_inode(inode); +} +EXPORT_SYMBOL_GPL(nfs_drop_inode); + +void nfs_clear_inode(struct inode *inode) +{ + /* + * The following should never happen... + */ + WARN_ON_ONCE(nfs_have_writebacks(inode)); + WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files)); + nfs_zap_acl_cache(inode); + nfs_access_zap_cache(inode); + nfs_fscache_clear_inode(inode); +} +EXPORT_SYMBOL_GPL(nfs_clear_inode); + +void nfs_evict_inode(struct inode *inode) +{ + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); + nfs_clear_inode(inode); +} + +int nfs_sync_inode(struct inode *inode) +{ + nfs_inode_dio_wait(inode); + return nfs_wb_all(inode); +} +EXPORT_SYMBOL_GPL(nfs_sync_inode); + +/** + * nfs_sync_mapping - helper to flush all mmapped dirty data to disk + */ +int nfs_sync_mapping(struct address_space *mapping) +{ + int ret = 0; + + if (mapping->nrpages != 0) { + unmap_mapping_range(mapping, 0, 0, 0); + ret = nfs_wb_all(mapping->host); + } + return ret; +} + +static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + if (inode->i_mapping->nrpages == 0) + flags &= ~NFS_INO_INVALID_DATA; + nfsi->cache_validity |= flags; + if (flags & NFS_INO_INVALID_DATA) + nfs_fscache_invalidate(inode); +} + +/* + * Invalidate the local caches + */ +static void nfs_zap_caches_locked(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + int mode = inode->i_mode; + + nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); + + nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); + nfsi->attrtimeo_timestamp = jiffies; + + memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf)); + if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_PAGECACHE); + } else + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_PAGECACHE); + nfs_zap_label_cache_locked(nfsi); +} + +void nfs_zap_caches(struct inode *inode) +{ + spin_lock(&inode->i_lock); + nfs_zap_caches_locked(inode); + spin_unlock(&inode->i_lock); +} + +void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) +{ + if (mapping->nrpages != 0) { + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); + spin_unlock(&inode->i_lock); + } +} + +void nfs_zap_acl_cache(struct inode *inode) +{ + void (*clear_acl_cache)(struct inode *); + + clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache; + if (clear_acl_cache != NULL) + clear_acl_cache(inode); + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL; + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); + +void nfs_invalidate_atime(struct inode *inode) +{ + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL_GPL(nfs_invalidate_atime); + +/* + * Invalidate, but do not unhash, the inode. + * NB: must be called with inode->i_lock held! + */ +static void nfs_invalidate_inode(struct inode *inode) +{ + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + nfs_zap_caches_locked(inode); +} + +struct nfs_find_desc { + struct nfs_fh *fh; + struct nfs_fattr *fattr; +}; + +/* + * In NFSv3 we can have 64bit inode numbers. In order to support + * this, and re-exported directories (also seen in NFSv2) + * we are forced to allow 2 different inodes to have the same + * i_ino. + */ +static int +nfs_find_actor(struct inode *inode, void *opaque) +{ + struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque; + struct nfs_fh *fh = desc->fh; + struct nfs_fattr *fattr = desc->fattr; + + if (NFS_FILEID(inode) != fattr->fileid) + return 0; + if ((S_IFMT & inode->i_mode) != (S_IFMT & fattr->mode)) + return 0; + if (nfs_compare_fh(NFS_FH(inode), fh)) + return 0; + if (is_bad_inode(inode) || NFS_STALE(inode)) + return 0; + return 1; +} + +static int +nfs_init_locked(struct inode *inode, void *opaque) +{ + struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque; + struct nfs_fattr *fattr = desc->fattr; + + set_nfs_fileid(inode, fattr->fileid); + nfs_copy_fh(NFS_FH(inode), desc->fh); + return 0; +} + +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +static void nfs_clear_label_invalid(struct inode *inode) +{ + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; + spin_unlock(&inode->i_lock); +} + +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + int error; + + if (label == NULL) + return; + + if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { + error = security_inode_notifysecctx(inode, label->label, + label->len); + if (error) + printk(KERN_ERR "%s() %s %d " + "security_inode_notifysecctx() %d\n", + __func__, + (char *)label->label, + label->len, error); + nfs_clear_label_invalid(inode); + } +} + +struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) +{ + struct nfs4_label *label = NULL; + int minor_version = server->nfs_client->cl_minorversion; + + if (minor_version < 2) + return label; + + if (!(server->caps & NFS_CAP_SECURITY_LABEL)) + return label; + + label = kzalloc(sizeof(struct nfs4_label), flags); + if (label == NULL) + return ERR_PTR(-ENOMEM); + + label->label = kzalloc(NFS4_MAXLABELLEN, flags); + if (label->label == NULL) { + kfree(label); + return ERR_PTR(-ENOMEM); + } + label->len = NFS4_MAXLABELLEN; + + return label; +} +EXPORT_SYMBOL_GPL(nfs4_label_alloc); +#else +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ +} +#endif +EXPORT_SYMBOL_GPL(nfs_setsecurity); + +/* + * This is our front-end to iget that looks up inodes by file handle + * instead of inode number. + */ +struct inode * +nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs_find_desc desc = { + .fh = fh, + .fattr = fattr + }; + struct inode *inode = ERR_PTR(-ENOENT); + unsigned long hash; + + nfs_attr_check_mountpoint(sb, fattr); + + if (nfs_attr_use_mounted_on_fileid(fattr)) + fattr->fileid = fattr->mounted_on_fileid; + else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) + goto out_no_inode; + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) + goto out_no_inode; + + hash = nfs_fattr_to_ino_t(fattr); + + inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc); + if (inode == NULL) { + inode = ERR_PTR(-ENOMEM); + goto out_no_inode; + } + + if (inode->i_state & I_NEW) { + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long now = jiffies; + + /* We set i_ino for the few things that still rely on it, + * such as stat(2) */ + inode->i_ino = hash; + + /* We can't support update_atime(), since the server will reset it */ + inode->i_flags |= S_NOATIME|S_NOCMTIME; + inode->i_mode = fattr->mode; + if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 + && nfs_server_capable(inode, NFS_CAP_MODE)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + /* Why so? Because we want revalidate for devices/FIFOs, and + * that's precisely what we have in nfs_file_inode_operations. + */ + inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops; + if (S_ISREG(inode->i_mode)) { + inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; + inode->i_data.a_ops = &nfs_file_aops; + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; + inode->i_fop = &nfs_dir_operations; + inode->i_data.a_ops = &nfs_dir_aops; + /* Deal with crossing mountpoints */ + if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || + fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) + inode->i_op = &nfs_referral_inode_operations; + else + inode->i_op = &nfs_mountpoint_inode_operations; + inode->i_fop = NULL; + inode->i_flags |= S_AUTOMOUNT; + } + } else if (S_ISLNK(inode->i_mode)) + inode->i_op = &nfs_symlink_inode_operations; + else + init_special_inode(inode, inode->i_mode, fattr->rdev); + + memset(&inode->i_atime, 0, sizeof(inode->i_atime)); + memset(&inode->i_mtime, 0, sizeof(inode->i_mtime)); + memset(&inode->i_ctime, 0, sizeof(inode->i_ctime)); + inode->i_version = 0; + inode->i_size = 0; + clear_nlink(inode); + inode->i_uid = make_kuid(&init_user_ns, -2); + inode->i_gid = make_kgid(&init_user_ns, -2); + inode->i_blocks = 0; + memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + nfsi->write_io = 0; + nfsi->read_io = 0; + + nfsi->read_cache_jiffies = fattr->time_start; + nfsi->attr_gencount = fattr->gencount; + if (fattr->valid & NFS_ATTR_FATTR_ATIME) + inode->i_atime = fattr->atime; + else if (nfs_server_capable(inode, NFS_CAP_ATIME)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_MTIME) + inode->i_mtime = fattr->mtime; + else if (nfs_server_capable(inode, NFS_CAP_MTIME)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_CTIME) + inode->i_ctime = fattr->ctime; + else if (nfs_server_capable(inode, NFS_CAP_CTIME)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_CHANGE) + inode->i_version = fattr->change_attr; + else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_SIZE) + inode->i_size = nfs_size_to_loff_t(fattr->size); + else + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE); + if (fattr->valid & NFS_ATTR_FATTR_NLINK) + set_nlink(inode, fattr->nlink); + else if (nfs_server_capable(inode, NFS_CAP_NLINK)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_OWNER) + inode->i_uid = fattr->uid; + else if (nfs_server_capable(inode, NFS_CAP_OWNER)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_GROUP) + inode->i_gid = fattr->gid; + else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + inode->i_blocks = fattr->du.nfs2.blocks; + if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { + /* + * report the blocks in 512byte units + */ + inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); + } + + nfs_setsecurity(inode, fattr, label); + + nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); + nfsi->attrtimeo_timestamp = now; + nfsi->access_cache = RB_ROOT; + + nfs_fscache_init_inode(inode); + + unlock_new_inode(inode); + } else + nfs_refresh_inode(inode, fattr); + dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), + nfs_display_fhandle_hash(fh), + atomic_read(&inode->i_count)); + +out: + return inode; + +out_no_inode: + dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode)); + goto out; +} +EXPORT_SYMBOL_GPL(nfs_fhget); + +#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) + +int +nfs_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = d_inode(dentry); + struct nfs_fattr *fattr; + int error = -ENOMEM; + + nfs_inc_stats(inode, NFSIOS_VFSSETATTR); + + /* skip mode change if it's just for clearing setuid/setgid */ + if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + + if (attr->ia_valid & ATTR_SIZE) { + loff_t i_size; + + BUG_ON(!S_ISREG(inode->i_mode)); + + i_size = i_size_read(inode); + if (attr->ia_size == i_size) + attr->ia_valid &= ~ATTR_SIZE; + else if (attr->ia_size < i_size && IS_SWAPFILE(inode)) + return -ETXTBSY; + } + + /* Optimization: if the end result is no change, don't RPC */ + attr->ia_valid &= NFS_VALID_ATTRS; + if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0) + return 0; + + trace_nfs_setattr_enter(inode); + + /* Write all dirty data */ + if (S_ISREG(inode->i_mode)) + nfs_sync_inode(inode); + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + goto out; + /* + * Return any delegations if we're going to change ACLs + */ + if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) + NFS_PROTO(inode)->return_delegation(inode); + error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); + if (error == 0) + error = nfs_refresh_inode(inode, fattr); + nfs_free_fattr(fattr); +out: + trace_nfs_setattr_exit(inode, error); + return error; +} +EXPORT_SYMBOL_GPL(nfs_setattr); + +/** + * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall + * @inode: inode of the file used + * @offset: file offset to start truncating + * + * This is a copy of the common vmtruncate, but with the locking + * corrected to take into account the fact that NFS requires + * inode->i_size to be updated under the inode->i_lock. + * Note: must be called with inode->i_lock held! + */ +static int nfs_vmtruncate(struct inode * inode, loff_t offset) +{ + int err; + + err = inode_newsize_ok(inode, offset); + if (err) + goto out; + + i_size_write(inode, offset); + /* Optimisation */ + if (offset == 0) + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA; + + spin_unlock(&inode->i_lock); + truncate_pagecache(inode, offset); + spin_lock(&inode->i_lock); +out: + return err; +} + +/** + * nfs_setattr_update_inode - Update inode metadata after a setattr call. + * @inode: pointer to struct inode + * @attr: pointer to struct iattr + * + * Note: we do this in the *proc.c in order to ensure that + * it works for things like exclusive creates too. + */ +void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, + struct nfs_fattr *fattr) +{ + /* Barrier: bump the attribute generation count. */ + nfs_fattr_set_barrier(fattr); + + spin_lock(&inode->i_lock); + NFS_I(inode)->attr_gencount = fattr->gencount; + if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) { + if ((attr->ia_valid & ATTR_MODE) != 0) { + int mode = attr->ia_mode & S_IALLUGO; + mode |= inode->i_mode & ~S_IALLUGO; + inode->i_mode = mode; + } + if ((attr->ia_valid & ATTR_UID) != 0) + inode->i_uid = attr->ia_uid; + if ((attr->ia_valid & ATTR_GID) != 0) + inode->i_gid = attr->ia_gid; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL); + } + if ((attr->ia_valid & ATTR_SIZE) != 0) { + nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC); + nfs_vmtruncate(inode, attr->ia_size); + } + nfs_update_inode(inode, fattr); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); + +static void nfs_request_parent_use_readdirplus(struct dentry *dentry) +{ + struct dentry *parent; + + parent = dget_parent(dentry); + nfs_force_use_readdirplus(d_inode(parent)); + dput(parent); +} + +static bool nfs_need_revalidate_inode(struct inode *inode) +{ + if (NFS_I(inode)->cache_validity & + (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) + return true; + if (nfs_attribute_cache_expired(inode)) + return true; + return false; +} + +int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = d_inode(dentry); + int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; + int err = 0; + + trace_nfs_getattr_enter(inode); + /* Flush out writes to the server in order to update c/mtime. */ + if (S_ISREG(inode->i_mode)) { + mutex_lock(&inode->i_mutex); + err = nfs_sync_inode(inode); + mutex_unlock(&inode->i_mutex); + if (err) + goto out; + } + + /* + * We may force a getattr if the user cares about atime. + * + * Note that we only have to check the vfsmount flags here: + * - NFS always sets S_NOATIME by so checking it would give a + * bogus result + * - NFS never sets MS_NOATIME or MS_NODIRATIME so there is + * no point in checking those. + */ + if ((mnt->mnt_flags & MNT_NOATIME) || + ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))) + need_atime = 0; + + if (need_atime || nfs_need_revalidate_inode(inode)) { + struct nfs_server *server = NFS_SERVER(inode); + + if (server->caps & NFS_CAP_READDIRPLUS) + nfs_request_parent_use_readdirplus(dentry); + err = __nfs_revalidate_inode(server, inode); + } + if (!err) { + generic_fillattr(inode, stat); + stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); + } +out: + trace_nfs_getattr_exit(inode, err); + return err; +} +EXPORT_SYMBOL_GPL(nfs_getattr); + +static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) +{ + atomic_set(&l_ctx->count, 1); + l_ctx->lockowner.l_owner = current->files; + l_ctx->lockowner.l_pid = current->tgid; + INIT_LIST_HEAD(&l_ctx->list); + nfs_iocounter_init(&l_ctx->io_count); +} + +static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) +{ + struct nfs_lock_context *head = &ctx->lock_context; + struct nfs_lock_context *pos = head; + + do { + if (pos->lockowner.l_owner != current->files) + continue; + if (pos->lockowner.l_pid != current->tgid) + continue; + atomic_inc(&pos->count); + return pos; + } while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head); + return NULL; +} + +struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) +{ + struct nfs_lock_context *res, *new = NULL; + struct inode *inode = d_inode(ctx->dentry); + + spin_lock(&inode->i_lock); + res = __nfs_find_lock_context(ctx); + if (res == NULL) { + spin_unlock(&inode->i_lock); + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (new == NULL) + return ERR_PTR(-ENOMEM); + nfs_init_lock_context(new); + spin_lock(&inode->i_lock); + res = __nfs_find_lock_context(ctx); + if (res == NULL) { + list_add_tail(&new->list, &ctx->lock_context.list); + new->open_context = ctx; + res = new; + new = NULL; + } + } + spin_unlock(&inode->i_lock); + kfree(new); + return res; +} +EXPORT_SYMBOL_GPL(nfs_get_lock_context); + +void nfs_put_lock_context(struct nfs_lock_context *l_ctx) +{ + struct nfs_open_context *ctx = l_ctx->open_context; + struct inode *inode = d_inode(ctx->dentry); + + if (!atomic_dec_and_lock(&l_ctx->count, &inode->i_lock)) + return; + list_del(&l_ctx->list); + spin_unlock(&inode->i_lock); + kfree(l_ctx); +} +EXPORT_SYMBOL_GPL(nfs_put_lock_context); + +/** + * nfs_close_context - Common close_context() routine NFSv2/v3 + * @ctx: pointer to context + * @is_sync: is this a synchronous close + * + * always ensure that the attributes are up to date if we're mounted + * with close-to-open semantics + */ +void nfs_close_context(struct nfs_open_context *ctx, int is_sync) +{ + struct inode *inode; + struct nfs_server *server; + + if (!(ctx->mode & FMODE_WRITE)) + return; + if (!is_sync) + return; + inode = d_inode(ctx->dentry); + if (!list_empty(&NFS_I(inode)->open_files)) + return; + server = NFS_SERVER(inode); + if (server->flags & NFS_MOUNT_NOCTO) + return; + nfs_revalidate_inode(server, inode); +} +EXPORT_SYMBOL_GPL(nfs_close_context); + +struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode) +{ + struct nfs_open_context *ctx; + struct rpc_cred *cred = rpc_lookup_cred(); + if (IS_ERR(cred)) + return ERR_CAST(cred); + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + put_rpccred(cred); + return ERR_PTR(-ENOMEM); + } + nfs_sb_active(dentry->d_sb); + ctx->dentry = dget(dentry); + ctx->cred = cred; + ctx->state = NULL; + ctx->mode = f_mode; + ctx->flags = 0; + ctx->error = 0; + nfs_init_lock_context(&ctx->lock_context); + ctx->lock_context.open_context = ctx; + INIT_LIST_HEAD(&ctx->list); + ctx->mdsthreshold = NULL; + return ctx; +} +EXPORT_SYMBOL_GPL(alloc_nfs_open_context); + +struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) +{ + if (ctx != NULL) + atomic_inc(&ctx->lock_context.count); + return ctx; +} +EXPORT_SYMBOL_GPL(get_nfs_open_context); + +static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) +{ + struct inode *inode = d_inode(ctx->dentry); + struct super_block *sb = ctx->dentry->d_sb; + + if (!list_empty(&ctx->list)) { + if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock)) + return; + list_del(&ctx->list); + spin_unlock(&inode->i_lock); + } else if (!atomic_dec_and_test(&ctx->lock_context.count)) + return; + if (inode != NULL) + NFS_PROTO(inode)->close_context(ctx, is_sync); + if (ctx->cred != NULL) + put_rpccred(ctx->cred); + dput(ctx->dentry); + nfs_sb_deactive(sb); + kfree(ctx->mdsthreshold); + kfree(ctx); +} + +void put_nfs_open_context(struct nfs_open_context *ctx) +{ + __put_nfs_open_context(ctx, 0); +} +EXPORT_SYMBOL_GPL(put_nfs_open_context); + +/* + * Ensure that mmap has a recent RPC credential for use when writing out + * shared pages + */ +void nfs_inode_attach_open_context(struct nfs_open_context *ctx) +{ + struct inode *inode = d_inode(ctx->dentry); + struct nfs_inode *nfsi = NFS_I(inode); + + spin_lock(&inode->i_lock); + list_add(&ctx->list, &nfsi->open_files); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); + +void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) +{ + filp->private_data = get_nfs_open_context(ctx); + if (list_empty(&ctx->list)) + nfs_inode_attach_open_context(ctx); +} +EXPORT_SYMBOL_GPL(nfs_file_set_open_context); + +/* + * Given an inode, search for an open context with the desired characteristics + */ +struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_open_context *pos, *ctx = NULL; + + spin_lock(&inode->i_lock); + list_for_each_entry(pos, &nfsi->open_files, list) { + if (cred != NULL && pos->cred != cred) + continue; + if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) + continue; + ctx = get_nfs_open_context(pos); + break; + } + spin_unlock(&inode->i_lock); + return ctx; +} + +static void nfs_file_clear_open_context(struct file *filp) +{ + struct nfs_open_context *ctx = nfs_file_open_context(filp); + + if (ctx) { + struct inode *inode = d_inode(ctx->dentry); + + filp->private_data = NULL; + spin_lock(&inode->i_lock); + list_move_tail(&ctx->list, &NFS_I(inode)->open_files); + spin_unlock(&inode->i_lock); + __put_nfs_open_context(ctx, filp->f_flags & O_DIRECT ? 0 : 1); + } +} + +/* + * These allocate and release file read/write context information. + */ +int nfs_open(struct inode *inode, struct file *filp) +{ + struct nfs_open_context *ctx; + + ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + nfs_file_set_open_context(filp, ctx); + put_nfs_open_context(ctx); + nfs_fscache_open_file(inode, filp); + return 0; +} + +int nfs_release(struct inode *inode, struct file *filp) +{ + nfs_file_clear_open_context(filp); + return 0; +} + +/* + * This function is called whenever some part of NFS notices that + * the cached attributes have to be refreshed. + */ +int +__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) +{ + int status = -ESTALE; + struct nfs4_label *label = NULL; + struct nfs_fattr *fattr = NULL; + struct nfs_inode *nfsi = NFS_I(inode); + + dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n", + inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); + + trace_nfs_revalidate_inode_enter(inode); + + if (is_bad_inode(inode)) + goto out; + if (NFS_STALE(inode)) + goto out; + + status = -ENOMEM; + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + goto out; + + nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); + + label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); + if (IS_ERR(label)) { + status = PTR_ERR(label); + goto out; + } + + status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, label); + if (status != 0) { + dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), status); + if (status == -ESTALE) { + nfs_zap_caches(inode); + if (!S_ISDIR(inode->i_mode)) + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + } + goto err_out; + } + + status = nfs_refresh_inode(inode, fattr); + if (status) { + dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), status); + goto err_out; + } + + if (nfsi->cache_validity & NFS_INO_INVALID_ACL) + nfs_zap_acl_cache(inode); + + nfs_setsecurity(inode, fattr, label); + + dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode)); + +err_out: + nfs4_label_free(label); +out: + nfs_free_fattr(fattr); + trace_nfs_revalidate_inode_exit(inode, status); + return status; +} + +int nfs_attribute_timeout(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); +} + +int nfs_attribute_cache_expired(struct inode *inode) +{ + if (nfs_have_delegated_attributes(inode)) + return 0; + return nfs_attribute_timeout(inode); +} + +/** + * nfs_revalidate_inode - Revalidate the inode attributes + * @server - pointer to nfs_server struct + * @inode - pointer to inode struct + * + * Updates inode attribute information by retrieving the data from the server. + */ +int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) +{ + if (!nfs_need_revalidate_inode(inode)) + return NFS_STALE(inode) ? -ESTALE : 0; + return __nfs_revalidate_inode(server, inode); +} +EXPORT_SYMBOL_GPL(nfs_revalidate_inode); + +int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode) +{ + if (!(NFS_I(inode)->cache_validity & + (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) + && !nfs_attribute_cache_expired(inode)) + return NFS_STALE(inode) ? -ESTALE : 0; + return -ECHILD; +} + +static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) +{ + struct nfs_inode *nfsi = NFS_I(inode); + int ret; + + if (mapping->nrpages != 0) { + if (S_ISREG(inode->i_mode)) { + unmap_mapping_range(mapping, 0, 0, 0); + ret = nfs_sync_mapping(mapping); + if (ret < 0) + return ret; + } + ret = invalidate_inode_pages2(mapping); + if (ret < 0) + return ret; + } + if (S_ISDIR(inode->i_mode)) { + spin_lock(&inode->i_lock); + memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + spin_unlock(&inode->i_lock); + } + nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); + nfs_fscache_wait_on_invalidate(inode); + + dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode)); + return 0; +} + +static bool nfs_mapping_need_revalidate_inode(struct inode *inode) +{ + if (nfs_have_delegated_attributes(inode)) + return false; + return (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE) + || nfs_attribute_timeout(inode) + || NFS_STALE(inode); +} + +/** + * __nfs_revalidate_mapping - Revalidate the pagecache + * @inode - pointer to host inode + * @mapping - pointer to mapping + * @may_lock - take inode->i_mutex? + */ +static int __nfs_revalidate_mapping(struct inode *inode, + struct address_space *mapping, + bool may_lock) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + /* swapfiles are not supposed to be shared. */ + if (IS_SWAPFILE(inode)) + goto out; + + if (nfs_mapping_need_revalidate_inode(inode)) { + ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (ret < 0) + goto out; + } + + /* + * We must clear NFS_INO_INVALID_DATA first to ensure that + * invalidations that come in while we're shooting down the mappings + * are respected. But, that leaves a race window where one revalidator + * can clear the flag, and then another checks it before the mapping + * gets invalidated. Fix that by serializing access to this part of + * the function. + * + * At the same time, we need to allow other tasks to see whether we + * might be in the middle of invalidating the pages, so we only set + * the bit lock here if it looks like we're going to be doing that. + */ + for (;;) { + ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (ret) + goto out; + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock)) { + spin_unlock(&inode->i_lock); + continue; + } + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + break; + spin_unlock(&inode->i_lock); + goto out; + } + + set_bit(NFS_INO_INVALIDATING, bitlock); + smp_wmb(); + nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; + spin_unlock(&inode->i_lock); + trace_nfs_invalidate_mapping_enter(inode); + if (may_lock) { + mutex_lock(&inode->i_mutex); + ret = nfs_invalidate_mapping(inode, mapping); + mutex_unlock(&inode->i_mutex); + } else + ret = nfs_invalidate_mapping(inode, mapping); + trace_nfs_invalidate_mapping_exit(inode, ret); + + clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_INO_INVALIDATING); +out: + return ret; +} + +/** + * nfs_revalidate_mapping - Revalidate the pagecache + * @inode - pointer to host inode + * @mapping - pointer to mapping + */ +int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) +{ + return __nfs_revalidate_mapping(inode, mapping, false); +} + +/** + * nfs_revalidate_mapping_protected - Revalidate the pagecache + * @inode - pointer to host inode + * @mapping - pointer to mapping + * + * Differs from nfs_revalidate_mapping() in that it grabs the inode->i_mutex + * while invalidating the mapping. + */ +int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping) +{ + return __nfs_revalidate_mapping(inode, mapping, true); +} + +static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long ret = 0; + + if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) + && (fattr->valid & NFS_ATTR_FATTR_CHANGE) + && inode->i_version == fattr->pre_change_attr) { + inode->i_version = fattr->change_attr; + if (S_ISDIR(inode->i_mode)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); + ret |= NFS_INO_INVALID_ATTR; + } + /* If we have atomic WCC data, we may update some attributes */ + if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) + && (fattr->valid & NFS_ATTR_FATTR_CTIME) + && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) { + memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); + ret |= NFS_INO_INVALID_ATTR; + } + + if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) + && (fattr->valid & NFS_ATTR_FATTR_MTIME) + && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) { + memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); + if (S_ISDIR(inode->i_mode)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); + ret |= NFS_INO_INVALID_ATTR; + } + if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) + && (fattr->valid & NFS_ATTR_FATTR_SIZE) + && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) + && nfsi->nrequests == 0) { + i_size_write(inode, nfs_size_to_loff_t(fattr->size)); + ret |= NFS_INO_INVALID_ATTR; + } + + return ret; +} + +/** + * nfs_check_inode_attributes - verify consistency of the inode attribute cache + * @inode - pointer to inode + * @fattr - updated attributes + * + * Verifies the attribute cache. If we have just changed the attributes, + * so that fattr carries weak cache consistency data, then it may + * also update the ctime/mtime/change_attribute. + */ +static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr) +{ + struct nfs_inode *nfsi = NFS_I(inode); + loff_t cur_size, new_isize; + unsigned long invalid = 0; + + + if (nfs_have_delegated_attributes(inode)) + return 0; + /* Has the inode gone and changed behind our back? */ + if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) + return -EIO; + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) + return -EIO; + + if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && + inode->i_version != fattr->change_attr) + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; + + /* Verify a few of the more important attributes */ + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime)) + invalid |= NFS_INO_INVALID_ATTR; + + if (fattr->valid & NFS_ATTR_FATTR_SIZE) { + cur_size = i_size_read(inode); + new_isize = nfs_size_to_loff_t(fattr->size); + if (cur_size != new_isize && nfsi->nrequests == 0) + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; + } + + /* Have any file permissions changed? */ + if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) + invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; + if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid)) + invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; + if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid)) + invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; + + /* Has the link count changed? */ + if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) + invalid |= NFS_INO_INVALID_ATTR; + + if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime)) + invalid |= NFS_INO_INVALID_ATIME; + + if (invalid != 0) + nfs_set_cache_invalid(inode, invalid); + + nfsi->read_cache_jiffies = fattr->time_start; + return 0; +} + +static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr) +{ + if (!(fattr->valid & NFS_ATTR_FATTR_CTIME)) + return 0; + return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0; +} + +static atomic_long_t nfs_attr_generation_counter; + +static unsigned long nfs_read_attr_generation_counter(void) +{ + return atomic_long_read(&nfs_attr_generation_counter); +} + +unsigned long nfs_inc_attr_generation_counter(void) +{ + return atomic_long_inc_return(&nfs_attr_generation_counter); +} +EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter); + +void nfs_fattr_init(struct nfs_fattr *fattr) +{ + fattr->valid = 0; + fattr->time_start = jiffies; + fattr->gencount = nfs_inc_attr_generation_counter(); + fattr->owner_name = NULL; + fattr->group_name = NULL; +} +EXPORT_SYMBOL_GPL(nfs_fattr_init); + +/** + * nfs_fattr_set_barrier + * @fattr: attributes + * + * Used to set a barrier after an attribute was updated. This + * barrier ensures that older attributes from RPC calls that may + * have raced with our update cannot clobber these new values. + * Note that you are still responsible for ensuring that other + * operations which change the attribute on the server do not + * collide. + */ +void nfs_fattr_set_barrier(struct nfs_fattr *fattr) +{ + fattr->gencount = nfs_inc_attr_generation_counter(); +} + +struct nfs_fattr *nfs_alloc_fattr(void) +{ + struct nfs_fattr *fattr; + + fattr = kmalloc(sizeof(*fattr), GFP_NOFS); + if (fattr != NULL) + nfs_fattr_init(fattr); + return fattr; +} +EXPORT_SYMBOL_GPL(nfs_alloc_fattr); + +struct nfs_fh *nfs_alloc_fhandle(void) +{ + struct nfs_fh *fh; + + fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS); + if (fh != NULL) + fh->size = 0; + return fh; +} +EXPORT_SYMBOL_GPL(nfs_alloc_fhandle); + +#ifdef NFS_DEBUG +/* + * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle + * in the same way that wireshark does + * + * @fh: file handle + * + * For debugging only. + */ +u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) +{ + /* wireshark uses 32-bit AUTODIN crc and does a bitwise + * not on the result */ + return nfs_fhandle_hash(fh); +} +EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); + +/* + * _nfs_display_fhandle - display an NFS file handle on the console + * + * @fh: file handle to display + * @caption: display caption + * + * For debugging only. + */ +void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) +{ + unsigned short i; + + if (fh == NULL || fh->size == 0) { + printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh); + return; + } + + printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n", + caption, fh, fh->size, _nfs_display_fhandle_hash(fh)); + for (i = 0; i < fh->size; i += 16) { + __be32 *pos = (__be32 *)&fh->data[i]; + + switch ((fh->size - i - 1) >> 2) { + case 0: + printk(KERN_DEFAULT " %08x\n", + be32_to_cpup(pos)); + break; + case 1: + printk(KERN_DEFAULT " %08x %08x\n", + be32_to_cpup(pos), be32_to_cpup(pos + 1)); + break; + case 2: + printk(KERN_DEFAULT " %08x %08x %08x\n", + be32_to_cpup(pos), be32_to_cpup(pos + 1), + be32_to_cpup(pos + 2)); + break; + default: + printk(KERN_DEFAULT " %08x %08x %08x %08x\n", + be32_to_cpup(pos), be32_to_cpup(pos + 1), + be32_to_cpup(pos + 2), be32_to_cpup(pos + 3)); + } + } +} +EXPORT_SYMBOL_GPL(_nfs_display_fhandle); +#endif + +/** + * nfs_inode_attrs_need_update - check if the inode attributes need updating + * @inode - pointer to inode + * @fattr - attributes + * + * Attempt to divine whether or not an RPC call reply carrying stale + * attributes got scheduled after another call carrying updated ones. + * + * To do so, the function first assumes that a more recent ctime means + * that the attributes in fattr are newer, however it also attempt to + * catch the case where ctime either didn't change, or went backwards + * (if someone reset the clock on the server) by looking at whether + * or not this RPC call was started after the inode was last updated. + * Note also the check for wraparound of 'attr_gencount' + * + * The function returns 'true' if it thinks the attributes in 'fattr' are + * more recent than the ones cached in the inode. + * + */ +static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr) +{ + const struct nfs_inode *nfsi = NFS_I(inode); + + return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 || + nfs_ctime_need_update(inode, fattr) || + ((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0); +} + +/* + * Don't trust the change_attribute, mtime, ctime or size if + * a pnfs LAYOUTCOMMIT is outstanding + */ +static void nfs_inode_attrs_handle_layoutcommit(struct inode *inode, + struct nfs_fattr *fattr) +{ + if (pnfs_layoutcommit_outstanding(inode)) + fattr->valid &= ~(NFS_ATTR_FATTR_CHANGE | + NFS_ATTR_FATTR_MTIME | + NFS_ATTR_FATTR_CTIME | + NFS_ATTR_FATTR_SIZE); +} + +static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) +{ + int ret; + + trace_nfs_refresh_inode_enter(inode); + + nfs_inode_attrs_handle_layoutcommit(inode, fattr); + + if (nfs_inode_attrs_need_update(inode, fattr)) + ret = nfs_update_inode(inode, fattr); + else + ret = nfs_check_inode_attributes(inode, fattr); + + trace_nfs_refresh_inode_exit(inode, ret); + return ret; +} + +/** + * nfs_refresh_inode - try to update the inode attribute cache + * @inode - pointer to inode + * @fattr - updated attributes + * + * Check that an RPC call that returned attributes has not overlapped with + * other recent updates of the inode metadata, then decide whether it is + * safe to do a full update of the inode attributes, or whether just to + * call nfs_check_inode_attributes. + */ +int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) +{ + int status; + + if ((fattr->valid & NFS_ATTR_FATTR) == 0) + return 0; + spin_lock(&inode->i_lock); + status = nfs_refresh_inode_locked(inode, fattr); + spin_unlock(&inode->i_lock); + + return status; +} +EXPORT_SYMBOL_GPL(nfs_refresh_inode); + +static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr) +{ + unsigned long invalid = NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; + + if (S_ISDIR(inode->i_mode)) + invalid |= NFS_INO_INVALID_DATA; + nfs_set_cache_invalid(inode, invalid); + if ((fattr->valid & NFS_ATTR_FATTR) == 0) + return 0; + return nfs_refresh_inode_locked(inode, fattr); +} + +/** + * nfs_post_op_update_inode - try to update the inode attribute cache + * @inode - pointer to inode + * @fattr - updated attributes + * + * After an operation that has changed the inode metadata, mark the + * attribute cache as being invalid, then try to update it. + * + * NB: if the server didn't return any post op attributes, this + * function will force the retrieval of attributes before the next + * NFS request. Thus it should be used only for operations that + * are expected to change one or more attributes, to avoid + * unnecessary NFS requests and trips through nfs_update_inode(). + */ +int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) +{ + int status; + + spin_lock(&inode->i_lock); + nfs_fattr_set_barrier(fattr); + status = nfs_post_op_update_inode_locked(inode, fattr); + spin_unlock(&inode->i_lock); + + return status; +} +EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); + +/** + * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache + * @inode - pointer to inode + * @fattr - updated attributes + * + * After an operation that has changed the inode metadata, mark the + * attribute cache as being invalid, then try to update it. Fake up + * weak cache consistency data, if none exist. + * + * This function is mainly designed to be used by the ->write_done() functions. + */ +int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr) +{ + int status; + + /* Don't do a WCC update if these attributes are already stale */ + if ((fattr->valid & NFS_ATTR_FATTR) == 0 || + !nfs_inode_attrs_need_update(inode, fattr)) { + fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE + | NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PREMTIME + | NFS_ATTR_FATTR_PRECTIME); + goto out_noforce; + } + if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { + fattr->pre_change_attr = inode->i_version; + fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; + } + if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { + memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime)); + fattr->valid |= NFS_ATTR_FATTR_PRECTIME; + } + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { + memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime)); + fattr->valid |= NFS_ATTR_FATTR_PREMTIME; + } + if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) { + fattr->pre_size = i_size_read(inode); + fattr->valid |= NFS_ATTR_FATTR_PRESIZE; + } +out_noforce: + status = nfs_post_op_update_inode_locked(inode, fattr); + return status; +} + +/** + * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache + * @inode - pointer to inode + * @fattr - updated attributes + * + * After an operation that has changed the inode metadata, mark the + * attribute cache as being invalid, then try to update it. Fake up + * weak cache consistency data, if none exist. + * + * This function is mainly designed to be used by the ->write_done() functions. + */ +int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr) +{ + int status; + + spin_lock(&inode->i_lock); + nfs_fattr_set_barrier(fattr); + status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr); + spin_unlock(&inode->i_lock); + return status; +} +EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc); + + +static inline bool nfs_fileid_valid(struct nfs_inode *nfsi, + struct nfs_fattr *fattr) +{ + bool ret1 = true, ret2 = true; + + if (fattr->valid & NFS_ATTR_FATTR_FILEID) + ret1 = (nfsi->fileid == fattr->fileid); + if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) + ret2 = (nfsi->fileid == fattr->mounted_on_fileid); + return ret1 || ret2; +} + +/* + * Many nfs protocol calls return the new file attributes after + * an operation. Here we update the inode to reflect the state + * of the server's inode. + * + * This is a bit tricky because we have to make sure all dirty pages + * have been sent off to the server before calling invalidate_inode_pages. + * To make sure no other process adds more write requests while we try + * our best to flush them, we make them sleep during the attribute refresh. + * + * A very similar scenario holds for the dir cache. + */ +static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) +{ + struct nfs_server *server; + struct nfs_inode *nfsi = NFS_I(inode); + loff_t cur_isize, new_isize; + unsigned long invalid = 0; + unsigned long now = jiffies; + unsigned long save_cache_validity; + + dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", + __func__, inode->i_sb->s_id, inode->i_ino, + nfs_display_fhandle_hash(NFS_FH(inode)), + atomic_read(&inode->i_count), fattr->valid); + + if (!nfs_fileid_valid(nfsi, fattr)) { + printk(KERN_ERR "NFS: server %s error: fileid changed\n" + "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", + NFS_SERVER(inode)->nfs_client->cl_hostname, + inode->i_sb->s_id, (long long)nfsi->fileid, + (long long)fattr->fileid); + goto out_err; + } + + /* + * Make sure the inode's type hasn't changed. + */ + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) { + /* + * Big trouble! The inode has become a different object. + */ + printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n", + __func__, inode->i_ino, inode->i_mode, fattr->mode); + goto out_err; + } + + server = NFS_SERVER(inode); + /* Update the fsid? */ + if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) && + !nfs_fsid_equal(&server->fsid, &fattr->fsid) && + !IS_AUTOMOUNT(inode)) + server->fsid = fattr->fsid; + + /* + * Update the read time so we don't revalidate too often. + */ + nfsi->read_cache_jiffies = fattr->time_start; + + save_cache_validity = nfsi->cache_validity; + nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ATIME + | NFS_INO_REVAL_FORCED + | NFS_INO_REVAL_PAGECACHE); + + /* Do atomic weak cache consistency updates */ + invalid |= nfs_wcc_update_inode(inode, fattr); + + /* More cache consistency checks */ + if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { + if (inode->i_version != fattr->change_attr) { + dprintk("NFS: change_attr change on server for file %s/%ld\n", + inode->i_sb->s_id, inode->i_ino); + invalid |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_PAGECACHE; + if (S_ISDIR(inode->i_mode)) + nfs_force_lookup_revalidate(inode); + inode->i_version = fattr->change_attr; + } + } else if (server->caps & NFS_CAP_CHANGE_ATTR) + nfsi->cache_validity |= save_cache_validity; + + if (fattr->valid & NFS_ATTR_FATTR_MTIME) { + memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); + } else if (server->caps & NFS_CAP_MTIME) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_FORCED); + + if (fattr->valid & NFS_ATTR_FATTR_CTIME) { + memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); + } else if (server->caps & NFS_CAP_CTIME) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_FORCED); + + /* Check if our cached file size is stale */ + if (fattr->valid & NFS_ATTR_FATTR_SIZE) { + new_isize = nfs_size_to_loff_t(fattr->size); + cur_isize = i_size_read(inode); + if (new_isize != cur_isize) { + /* Do we perhaps have any outstanding writes, or has + * the file grown beyond our last write? */ + if ((nfsi->nrequests == 0) || new_isize > cur_isize) { + i_size_write(inode, new_isize); + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; + invalid &= ~NFS_INO_REVAL_PAGECACHE; + } + dprintk("NFS: isize change on server for file %s/%ld " + "(%Ld to %Ld)\n", + inode->i_sb->s_id, + inode->i_ino, + (long long)cur_isize, + (long long)new_isize); + } + } else + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_REVAL_FORCED); + + + if (fattr->valid & NFS_ATTR_FATTR_ATIME) + memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); + else if (server->caps & NFS_CAP_ATIME) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATIME + | NFS_INO_REVAL_FORCED); + + if (fattr->valid & NFS_ATTR_FATTR_MODE) { + if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { + umode_t newmode = inode->i_mode & S_IFMT; + newmode |= fattr->mode & S_IALLUGO; + inode->i_mode = newmode; + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + } + } else if (server->caps & NFS_CAP_MODE) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + + if (fattr->valid & NFS_ATTR_FATTR_OWNER) { + if (!uid_eq(inode->i_uid, fattr->uid)) { + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + inode->i_uid = fattr->uid; + } + } else if (server->caps & NFS_CAP_OWNER) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + + if (fattr->valid & NFS_ATTR_FATTR_GROUP) { + if (!gid_eq(inode->i_gid, fattr->gid)) { + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + inode->i_gid = fattr->gid; + } + } else if (server->caps & NFS_CAP_OWNER_GROUP) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + + if (fattr->valid & NFS_ATTR_FATTR_NLINK) { + if (inode->i_nlink != fattr->nlink) { + invalid |= NFS_INO_INVALID_ATTR; + if (S_ISDIR(inode->i_mode)) + invalid |= NFS_INO_INVALID_DATA; + set_nlink(inode, fattr->nlink); + } + } else if (server->caps & NFS_CAP_NLINK) + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_FORCED); + + if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { + /* + * report the blocks in 512byte units + */ + inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); + } + if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + inode->i_blocks = fattr->du.nfs2.blocks; + + /* Update attrtimeo value if we're out of the unstable period */ + if (invalid & NFS_INO_INVALID_ATTR) { + nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); + nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); + nfsi->attrtimeo_timestamp = now; + /* Set barrier to be more recent than all outstanding updates */ + nfsi->attr_gencount = nfs_inc_attr_generation_counter(); + } else { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + nfsi->attrtimeo_timestamp = now; + } + /* Set the barrier to be more recent than this fattr */ + if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0) + nfsi->attr_gencount = fattr->gencount; + } + invalid &= ~NFS_INO_INVALID_ATTR; + /* Don't invalidate the data if we were to blame */ + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) + || S_ISLNK(inode->i_mode))) + invalid &= ~NFS_INO_INVALID_DATA; + if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) || + (save_cache_validity & NFS_INO_REVAL_FORCED)) + nfs_set_cache_invalid(inode, invalid); + + return 0; + out_err: + /* + * No need to worry about unhashing the dentry, as the + * lookup validation will know that the inode is bad. + * (But we fall through to invalidate the caches.) + */ + nfs_invalidate_inode(inode); + return -ESTALE; +} + +struct inode *nfs_alloc_inode(struct super_block *sb) +{ + struct nfs_inode *nfsi; + nfsi = kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL); + if (!nfsi) + return NULL; + nfsi->flags = 0UL; + nfsi->cache_validity = 0UL; +#if IS_ENABLED(CONFIG_NFS_V4) + nfsi->nfs4_acl = NULL; +#endif /* CONFIG_NFS_V4 */ + return &nfsi->vfs_inode; +} +EXPORT_SYMBOL_GPL(nfs_alloc_inode); + +static void nfs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); +} + +void nfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, nfs_i_callback); +} +EXPORT_SYMBOL_GPL(nfs_destroy_inode); + +static inline void nfs4_init_once(struct nfs_inode *nfsi) +{ +#if IS_ENABLED(CONFIG_NFS_V4) + INIT_LIST_HEAD(&nfsi->open_states); + nfsi->delegation = NULL; + init_rwsem(&nfsi->rwsem); + nfsi->layout = NULL; +#endif +} + +static void init_once(void *foo) +{ + struct nfs_inode *nfsi = (struct nfs_inode *) foo; + + inode_init_once(&nfsi->vfs_inode); + INIT_LIST_HEAD(&nfsi->open_files); + INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); + INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); + INIT_LIST_HEAD(&nfsi->commit_info.list); + nfsi->nrequests = 0; + nfsi->commit_info.ncommit = 0; + atomic_set(&nfsi->commit_info.rpcs_out, 0); + atomic_set(&nfsi->silly_count, 1); + INIT_HLIST_HEAD(&nfsi->silly_list); + init_waitqueue_head(&nfsi->waitqueue); + nfs4_init_once(nfsi); +} + +static int __init nfs_init_inodecache(void) +{ + nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", + sizeof(struct nfs_inode), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD), + init_once); + if (nfs_inode_cachep == NULL) + return -ENOMEM; + + return 0; +} + +static void nfs_destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(nfs_inode_cachep); +} + +struct workqueue_struct *nfsiod_workqueue; +EXPORT_SYMBOL_GPL(nfsiod_workqueue); + +/* + * start up the nfsiod workqueue + */ +static int nfsiod_start(void) +{ + struct workqueue_struct *wq; + dprintk("RPC: creating workqueue nfsiod\n"); + wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM, 0); + if (wq == NULL) + return -ENOMEM; + nfsiod_workqueue = wq; + return 0; +} + +/* + * Destroy the nfsiod workqueue + */ +static void nfsiod_stop(void) +{ + struct workqueue_struct *wq; + + wq = nfsiod_workqueue; + if (wq == NULL) + return; + nfsiod_workqueue = NULL; + destroy_workqueue(wq); +} + +int nfs_net_id; +EXPORT_SYMBOL_GPL(nfs_net_id); + +static int nfs_net_init(struct net *net) +{ + nfs_clients_init(net); + return nfs_fs_proc_net_init(net); +} + +static void nfs_net_exit(struct net *net) +{ + nfs_fs_proc_net_exit(net); + nfs_cleanup_cb_ident_idr(net); +} + +static struct pernet_operations nfs_net_ops = { + .init = nfs_net_init, + .exit = nfs_net_exit, + .id = &nfs_net_id, + .size = sizeof(struct nfs_net), +}; + +/* + * Initialize NFS + */ +static int __init init_nfs_fs(void) +{ + int err; + + err = register_pernet_subsys(&nfs_net_ops); + if (err < 0) + goto out9; + + err = nfs_fscache_register(); + if (err < 0) + goto out8; + + err = nfsiod_start(); + if (err) + goto out7; + + err = nfs_fs_proc_init(); + if (err) + goto out6; + + err = nfs_init_nfspagecache(); + if (err) + goto out5; + + err = nfs_init_inodecache(); + if (err) + goto out4; + + err = nfs_init_readpagecache(); + if (err) + goto out3; + + err = nfs_init_writepagecache(); + if (err) + goto out2; + + err = nfs_init_directcache(); + if (err) + goto out1; + +#ifdef CONFIG_PROC_FS + rpc_proc_register(&init_net, &nfs_rpcstat); +#endif + if ((err = register_nfs_fs()) != 0) + goto out0; + + return 0; +out0: +#ifdef CONFIG_PROC_FS + rpc_proc_unregister(&init_net, "nfs"); +#endif + nfs_destroy_directcache(); +out1: + nfs_destroy_writepagecache(); +out2: + nfs_destroy_readpagecache(); +out3: + nfs_destroy_inodecache(); +out4: + nfs_destroy_nfspagecache(); +out5: + nfs_fs_proc_exit(); +out6: + nfsiod_stop(); +out7: + nfs_fscache_unregister(); +out8: + unregister_pernet_subsys(&nfs_net_ops); +out9: + return err; +} + +static void __exit exit_nfs_fs(void) +{ + nfs_destroy_directcache(); + nfs_destroy_writepagecache(); + nfs_destroy_readpagecache(); + nfs_destroy_inodecache(); + nfs_destroy_nfspagecache(); + nfs_fscache_unregister(); + unregister_pernet_subsys(&nfs_net_ops); +#ifdef CONFIG_PROC_FS + rpc_proc_unregister(&init_net, "nfs"); +#endif + unregister_nfs_fs(); + nfs_fs_proc_exit(); + nfsiod_stop(); +} + +/* Not quite true; I just maintain it */ +MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); +MODULE_LICENSE("GPL"); +module_param(enable_ino64, bool, 0644); + +module_init(init_nfs_fs) +module_exit(exit_nfs_fs) diff --git a/kernel/fs/nfs/internal.h b/kernel/fs/nfs/internal.h new file mode 100644 index 000000000..9e6475bc5 --- /dev/null +++ b/kernel/fs/nfs/internal.h @@ -0,0 +1,683 @@ +/* + * NFS internal definitions + */ + +#include "nfs4_fs.h" +#include <linux/mount.h> +#include <linux/security.h> +#include <linux/crc32.h> +#include <linux/nfs_page.h> + +#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) + +struct nfs_string; + +/* Maximum number of readahead requests + * FIXME: this should really be a sysctl so that users may tune it to suit + * their needs. People that do NFS over a slow network, might for + * instance want to reduce it to something closer to 1 for improved + * interactive response. + */ +#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1) + +static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) +{ + if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) + fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; +} + +static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) +{ + if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || + (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && + ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) + return 0; + return 1; +} + +struct nfs_clone_mount { + const struct super_block *sb; + const struct dentry *dentry; + struct nfs_fh *fh; + struct nfs_fattr *fattr; + char *hostname; + char *mnt_path; + struct sockaddr *addr; + size_t addrlen; + rpc_authflavor_t authflavor; +}; + +/* + * Note: RFC 1813 doesn't limit the number of auth flavors that + * a server can return, so make something up. + */ +#define NFS_MAX_SECFLAVORS (12) + +/* + * Value used if the user did not specify a port value. + */ +#define NFS_UNSPEC_PORT (-1) + +/* + * Maximum number of pages that readdir can use for creating + * a vmapped array of pages. + */ +#define NFS_MAX_READDIR_PAGES 8 + +struct nfs_client_initdata { + unsigned long init_flags; + const char *hostname; + const struct sockaddr *addr; + size_t addrlen; + struct nfs_subversion *nfs_mod; + int proto; + u32 minorversion; + struct net *net; +}; + +/* + * In-kernel mount arguments + */ +struct nfs_parsed_mount_data { + int flags; + unsigned int rsize, wsize; + unsigned int timeo, retrans; + unsigned int acregmin, acregmax, + acdirmin, acdirmax; + unsigned int namlen; + unsigned int options; + unsigned int bsize; + struct nfs_auth_info auth_info; + rpc_authflavor_t selected_flavor; + char *client_address; + unsigned int version; + unsigned int minorversion; + char *fscache_uniq; + bool need_mount; + + struct { + struct sockaddr_storage address; + size_t addrlen; + char *hostname; + u32 version; + int port; + unsigned short protocol; + } mount_server; + + struct { + struct sockaddr_storage address; + size_t addrlen; + char *hostname; + char *export_path; + int port; + unsigned short protocol; + } nfs_server; + + struct security_mnt_opts lsm_opts; + struct net *net; +}; + +/* mount_clnt.c */ +struct nfs_mount_request { + struct sockaddr *sap; + size_t salen; + char *hostname; + char *dirpath; + u32 version; + unsigned short protocol; + struct nfs_fh *fh; + int noresvport; + unsigned int *auth_flav_len; + rpc_authflavor_t *auth_flavs; + struct net *net; +}; + +struct nfs_mount_info { + void (*fill_super)(struct super_block *, struct nfs_mount_info *); + int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *); + struct nfs_parsed_mount_data *parsed; + struct nfs_clone_mount *cloned; + struct nfs_fh *mntfh; +}; + +extern int nfs_mount(struct nfs_mount_request *info); +extern void nfs_umount(const struct nfs_mount_request *info); + +/* client.c */ +extern const struct rpc_program nfs_program; +extern void nfs_clients_init(struct net *net); +extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); +int nfs_create_rpc_client(struct nfs_client *, const struct rpc_timeout *, rpc_authflavor_t); +struct nfs_client *nfs_get_client(const struct nfs_client_initdata *, + const struct rpc_timeout *, const char *, + rpc_authflavor_t); +int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); +void nfs_server_insert_lists(struct nfs_server *); +void nfs_server_remove_lists(struct nfs_server *); +void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int); +int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, + rpc_authflavor_t); +struct nfs_server *nfs_alloc_server(void); +void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); + +extern void nfs_cleanup_cb_ident_idr(struct net *); +extern void nfs_put_client(struct nfs_client *); +extern void nfs_free_client(struct nfs_client *); +extern struct nfs_client *nfs4_find_client_ident(struct net *, int); +extern struct nfs_client * +nfs4_find_client_sessionid(struct net *, const struct sockaddr *, + struct nfs4_sessionid *, u32); +extern struct nfs_server *nfs_create_server(struct nfs_mount_info *, + struct nfs_subversion *); +extern struct nfs_server *nfs4_create_server( + struct nfs_mount_info *, + struct nfs_subversion *); +extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, + struct nfs_fh *); +extern int nfs4_update_server(struct nfs_server *server, const char *hostname, + struct sockaddr *sap, size_t salen, + struct net *net); +extern void nfs_free_server(struct nfs_server *server); +extern struct nfs_server *nfs_clone_server(struct nfs_server *, + struct nfs_fh *, + struct nfs_fattr *, + rpc_authflavor_t); +extern int nfs_wait_client_init_complete(const struct nfs_client *clp); +extern void nfs_mark_client_ready(struct nfs_client *clp, int state); +extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, + const struct sockaddr *ds_addr, + int ds_addrlen, int ds_proto, + unsigned int ds_timeo, + unsigned int ds_retrans, + u32 minor_version, + rpc_authflavor_t au_flavor); +extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, + struct inode *); +extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, + unsigned int ds_retrans, rpc_authflavor_t au_flavor); +#ifdef CONFIG_PROC_FS +extern int __init nfs_fs_proc_init(void); +extern void nfs_fs_proc_exit(void); +extern int nfs_fs_proc_net_init(struct net *net); +extern void nfs_fs_proc_net_exit(struct net *net); +#else +static inline int nfs_fs_proc_net_init(struct net *net) +{ + return 0; +} +static inline void nfs_fs_proc_net_exit(struct net *net) +{ +} +static inline int nfs_fs_proc_init(void) +{ + return 0; +} +static inline void nfs_fs_proc_exit(void) +{ +} +#endif + +#ifdef CONFIG_NFS_V4_1 +int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *); +#endif + +/* callback_xdr.c */ +extern struct svc_version nfs4_callback_version1; +extern struct svc_version nfs4_callback_version4; + +struct nfs_pageio_descriptor; +/* pagelist.c */ +extern int __init nfs_init_nfspagecache(void); +extern void nfs_destroy_nfspagecache(void); +extern int __init nfs_init_readpagecache(void); +extern void nfs_destroy_readpagecache(void); +extern int __init nfs_init_writepagecache(void); +extern void nfs_destroy_writepagecache(void); + +extern int __init nfs_init_directcache(void); +extern void nfs_destroy_directcache(void); +extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)); +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); +int nfs_iocounter_wait(struct nfs_io_counter *c); + +extern const struct nfs_pageio_ops nfs_pgio_rw_ops; +struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); +void nfs_pgio_header_free(struct nfs_pgio_header *); +void nfs_pgio_data_destroy(struct nfs_pgio_header *); +int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); +int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, + struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, + const struct rpc_call_ops *call_ops, int how, int flags); +void nfs_free_request(struct nfs_page *req); +struct nfs_pgio_mirror * +nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); + +static inline void nfs_iocounter_init(struct nfs_io_counter *c) +{ + c->flags = 0; + atomic_set(&c->io_count, 0); +} + +static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc) +{ + WARN_ON_ONCE(desc->pg_mirror_count < 1); + return desc->pg_mirror_count > 1; +} + +/* nfs2xdr.c */ +extern struct rpc_procinfo nfs_procedures[]; +extern int nfs2_decode_dirent(struct xdr_stream *, + struct nfs_entry *, int); + +/* nfs3xdr.c */ +extern struct rpc_procinfo nfs3_procedures[]; +extern int nfs3_decode_dirent(struct xdr_stream *, + struct nfs_entry *, int); + +/* nfs4xdr.c */ +#if IS_ENABLED(CONFIG_NFS_V4) +extern int nfs4_decode_dirent(struct xdr_stream *, + struct nfs_entry *, int); +#endif +#ifdef CONFIG_NFS_V4_1 +extern const u32 nfs41_maxread_overhead; +extern const u32 nfs41_maxwrite_overhead; +extern const u32 nfs41_maxgetdevinfo_overhead; +#endif + +/* nfs4proc.c */ +#if IS_ENABLED(CONFIG_NFS_V4) +extern struct rpc_procinfo nfs4_procedures[]; +#endif + +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); +static inline void nfs4_label_free(struct nfs4_label *label) +{ + if (label) { + kfree(label->label); + kfree(label); + } + return; +} + +static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) +{ + if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) + nfsi->cache_validity |= NFS_INO_INVALID_LABEL; +} +#else +static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } +static inline void nfs4_label_free(void *label) {} +static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) +{ +} +#endif /* CONFIG_NFS_V4_SECURITY_LABEL */ + +/* proc.c */ +void nfs_close_context(struct nfs_open_context *ctx, int is_sync); +extern struct nfs_client *nfs_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr); + +/* dir.c */ +extern void nfs_force_use_readdirplus(struct inode *dir); +extern unsigned long nfs_access_cache_count(struct shrinker *shrink, + struct shrink_control *sc); +extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, + struct shrink_control *sc); +struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +int nfs_create(struct inode *, struct dentry *, umode_t, bool); +int nfs_mkdir(struct inode *, struct dentry *, umode_t); +int nfs_rmdir(struct inode *, struct dentry *); +int nfs_unlink(struct inode *, struct dentry *); +int nfs_symlink(struct inode *, struct dentry *, const char *); +int nfs_link(struct dentry *, struct inode *, struct dentry *); +int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); +int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); + +/* file.c */ +int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int); +loff_t nfs_file_llseek(struct file *, loff_t, int); +int nfs_file_flush(struct file *, fl_owner_t); +ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); +ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, + size_t, unsigned int); +int nfs_file_mmap(struct file *, struct vm_area_struct *); +ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); +int nfs_file_release(struct inode *, struct file *); +int nfs_lock(struct file *, int, struct file_lock *); +int nfs_flock(struct file *, int, struct file_lock *); +int nfs_check_flags(int); + +/* inode.c */ +extern struct workqueue_struct *nfsiod_workqueue; +extern struct inode *nfs_alloc_inode(struct super_block *sb); +extern void nfs_destroy_inode(struct inode *); +extern int nfs_write_inode(struct inode *, struct writeback_control *); +extern int nfs_drop_inode(struct inode *); +extern void nfs_clear_inode(struct inode *); +extern void nfs_evict_inode(struct inode *); +void nfs_zap_acl_cache(struct inode *inode); +extern int nfs_wait_bit_killable(struct wait_bit_key *key); + +/* super.c */ +extern const struct super_operations nfs_sops; +extern struct file_system_type nfs_fs_type; +extern struct file_system_type nfs_xdev_fs_type; +#if IS_ENABLED(CONFIG_NFS_V4) +extern struct file_system_type nfs4_xdev_fs_type; +extern struct file_system_type nfs4_referral_fs_type; +#endif +bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); +struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *, + struct nfs_subversion *); +void nfs_initialise_sb(struct super_block *); +int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); +int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); +struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *, + struct nfs_mount_info *, struct nfs_subversion *); +struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *); +struct dentry * nfs_xdev_mount_common(struct file_system_type *, int, + const char *, struct nfs_mount_info *); +void nfs_kill_super(struct super_block *); +void nfs_fill_super(struct super_block *, struct nfs_mount_info *); + +extern struct rpc_stat nfs_rpcstat; + +extern int __init register_nfs_fs(void); +extern void __exit unregister_nfs_fs(void); +extern bool nfs_sb_active(struct super_block *sb); +extern void nfs_sb_deactive(struct super_block *sb); + +/* namespace.c */ +#define NFS_PATH_CANONICAL 1 +extern char *nfs_path(char **p, struct dentry *dentry, + char *buffer, ssize_t buflen, unsigned flags); +extern struct vfsmount *nfs_d_automount(struct path *path); +struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); +struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *, + struct nfs_fattr *, rpc_authflavor_t); + +/* getroot.c */ +extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, + const char *); +#if IS_ENABLED(CONFIG_NFS_V4) +extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, + const char *); + +extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); +#endif + +struct nfs_pgio_completion_ops; +/* read.c */ +extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, bool force_mds, + const struct nfs_pgio_completion_ops *compl_ops); +extern void nfs_read_prepare(struct rpc_task *task, void *calldata); +extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); + +/* super.c */ +void nfs_clone_super(struct super_block *, struct nfs_mount_info *); +void nfs_umount_begin(struct super_block *); +int nfs_statfs(struct dentry *, struct kstatfs *); +int nfs_show_options(struct seq_file *, struct dentry *); +int nfs_show_devname(struct seq_file *, struct dentry *); +int nfs_show_path(struct seq_file *, struct dentry *); +int nfs_show_stats(struct seq_file *, struct dentry *); +int nfs_remount(struct super_block *sb, int *flags, char *raw_data); + +/* write.c */ +extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, + struct inode *inode, int ioflags, bool force_mds, + const struct nfs_pgio_completion_ops *compl_ops); +extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); +extern void nfs_commit_free(struct nfs_commit_data *p); +extern void nfs_write_prepare(struct rpc_task *task, void *calldata); +extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); +extern int nfs_initiate_commit(struct rpc_clnt *clnt, + struct nfs_commit_data *data, + const struct nfs_rpc_ops *nfs_ops, + const struct rpc_call_ops *call_ops, + int how, int flags); +extern void nfs_init_commit(struct nfs_commit_data *data, + struct list_head *head, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); +int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max); +unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); +int nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo); +void nfs_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); +int nfs_write_need_commit(struct nfs_pgio_header *); +void nfs_writeback_update_inode(struct nfs_pgio_header *hdr); +int nfs_generic_commit_list(struct inode *inode, struct list_head *head, + int how, struct nfs_commit_info *cinfo); +void nfs_retry_commit(struct list_head *page_list, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); +void nfs_commitdata_release(struct nfs_commit_data *data); +void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo); +void nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo); +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq); +int nfs_key_timeout_notify(struct file *filp, struct inode *inode); +bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx); +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); + +#ifdef CONFIG_MIGRATION +extern int nfs_migrate_page(struct address_space *, + struct page *, struct page *, enum migrate_mode); +#else +#define nfs_migrate_page NULL +#endif + +/* unlink.c */ +extern struct rpc_task * +nfs_async_rename(struct inode *old_dir, struct inode *new_dir, + struct dentry *old_dentry, struct dentry *new_dentry, + void (*complete)(struct rpc_task *, struct nfs_renamedata *)); +extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); + +/* direct.c */ +void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, + struct nfs_direct_req *dreq); +static inline void nfs_inode_dio_wait(struct inode *inode) +{ + inode_dio_wait(inode); +} +extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); +extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq); + +/* nfs4proc.c */ +extern void __nfs4_read_done_cb(struct nfs_pgio_header *); +extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr); +extern int nfs40_walk_client_list(struct nfs_client *clp, + struct nfs_client **result, + struct rpc_cred *cred); +extern int nfs41_walk_client_list(struct nfs_client *clp, + struct nfs_client **result, + struct rpc_cred *cred); + +static inline struct inode *nfs_igrab_and_active(struct inode *inode) +{ + inode = igrab(inode); + if (inode != NULL && !nfs_sb_active(inode->i_sb)) { + iput(inode); + inode = NULL; + } + return inode; +} + +static inline void nfs_iput_and_deactive(struct inode *inode) +{ + if (inode != NULL) { + struct super_block *sb = inode->i_sb; + + iput(inode); + nfs_sb_deactive(sb); + } +} + +/* + * Determine the device name as a string + */ +static inline char *nfs_devname(struct dentry *dentry, + char *buffer, ssize_t buflen) +{ + char *dummy; + return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); +} + +/* + * Determine the actual block size (and log2 thereof) + */ +static inline +unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) +{ + /* make sure blocksize is a power of two */ + if ((bsize & (bsize - 1)) || nrbitsp) { + unsigned char nrbits; + + for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--) + ; + bsize = 1 << nrbits; + if (nrbitsp) + *nrbitsp = nrbits; + } + + return bsize; +} + +/* + * Calculate the number of 512byte blocks used. + */ +static inline blkcnt_t nfs_calc_block_size(u64 tsize) +{ + blkcnt_t used = (tsize + 511) >> 9; + return (used > ULONG_MAX) ? ULONG_MAX : used; +} + +/* + * Compute and set NFS server blocksize + */ +static inline +unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) +{ + if (bsize < NFS_MIN_FILE_IO_SIZE) + bsize = NFS_DEF_FILE_IO_SIZE; + else if (bsize >= NFS_MAX_FILE_IO_SIZE) + bsize = NFS_MAX_FILE_IO_SIZE; + + return nfs_block_bits(bsize, nrbitsp); +} + +/* + * Determine the maximum file size for a superblock + */ +static inline +void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) +{ + sb->s_maxbytes = (loff_t)maxfilesize; + if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) + sb->s_maxbytes = MAX_LFS_FILESIZE; +} + +/* + * Record the page as unstable and mark its inode as dirty. + */ +static inline +void nfs_mark_page_unstable(struct page *page) +{ + struct inode *inode = page_file_mapping(page)->host; + + inc_zone_page_state(page, NR_UNSTABLE_NFS); + inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE); + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); +} + +/* + * Determine the number of bytes of data the page contains + */ +static inline +unsigned int nfs_page_length(struct page *page) +{ + loff_t i_size = i_size_read(page_file_mapping(page)->host); + + if (i_size > 0) { + pgoff_t page_index = page_file_index(page); + pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; + if (page_index < end_index) + return PAGE_CACHE_SIZE; + if (page_index == end_index) + return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1; + } + return 0; +} + +/* + * Convert a umode to a dirent->d_type + */ +static inline +unsigned char nfs_umode_to_dtype(umode_t mode) +{ + return (mode >> 12) & 15; +} + +/* + * Determine the number of pages in an array of length 'len' and + * with a base offset of 'base' + */ +static inline +unsigned int nfs_page_array_len(unsigned int base, size_t len) +{ + return ((unsigned long)len + (unsigned long)base + + PAGE_SIZE - 1) >> PAGE_SHIFT; +} + +/* + * Convert a struct timespec into a 64-bit change attribute + * + * This does approximately the same thing as timespec_to_ns(), + * but for calculation efficiency, we multiply the seconds by + * 1024*1024*1024. + */ +static inline +u64 nfs_timespec_to_change_attr(const struct timespec *ts) +{ + return ((u64)ts->tv_sec << 30) + ts->tv_nsec; +} + +#ifdef CONFIG_CRC32 +/** + * nfs_fhandle_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); +} +#else +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return 0; +} +#endif diff --git a/kernel/fs/nfs/iostat.h b/kernel/fs/nfs/iostat.h new file mode 100644 index 000000000..0cb806fbd --- /dev/null +++ b/kernel/fs/nfs/iostat.h @@ -0,0 +1,76 @@ +/* + * linux/fs/nfs/iostat.h + * + * Declarations for NFS client per-mount statistics + * + * Copyright (C) 2005, 2006 Chuck Lever <cel@netapp.com> + * + */ + +#ifndef _NFS_IOSTAT +#define _NFS_IOSTAT + +#include <linux/percpu.h> +#include <linux/cache.h> +#include <linux/nfs_iostat.h> + +struct nfs_iostats { + unsigned long long bytes[__NFSIOS_BYTESMAX]; +#ifdef CONFIG_NFS_FSCACHE + unsigned long long fscache[__NFSIOS_FSCACHEMAX]; +#endif + unsigned long events[__NFSIOS_COUNTSMAX]; +} ____cacheline_aligned; + +static inline void nfs_inc_server_stats(const struct nfs_server *server, + enum nfs_stat_eventcounters stat) +{ + this_cpu_inc(server->io_stats->events[stat]); +} + +static inline void nfs_inc_stats(const struct inode *inode, + enum nfs_stat_eventcounters stat) +{ + nfs_inc_server_stats(NFS_SERVER(inode), stat); +} + +static inline void nfs_add_server_stats(const struct nfs_server *server, + enum nfs_stat_bytecounters stat, + long addend) +{ + this_cpu_add(server->io_stats->bytes[stat], addend); +} + +static inline void nfs_add_stats(const struct inode *inode, + enum nfs_stat_bytecounters stat, + long addend) +{ + nfs_add_server_stats(NFS_SERVER(inode), stat, addend); +} + +#ifdef CONFIG_NFS_FSCACHE +static inline void nfs_add_fscache_stats(struct inode *inode, + enum nfs_stat_fscachecounters stat, + long addend) +{ + this_cpu_add(NFS_SERVER(inode)->io_stats->fscache[stat], addend); +} +static inline void nfs_inc_fscache_stats(struct inode *inode, + enum nfs_stat_fscachecounters stat) +{ + this_cpu_inc(NFS_SERVER(inode)->io_stats->fscache[stat]); +} +#endif + +static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void) +{ + return alloc_percpu(struct nfs_iostats); +} + +static inline void nfs_free_iostats(struct nfs_iostats __percpu *stats) +{ + if (stats != NULL) + free_percpu(stats); +} + +#endif /* _NFS_IOSTAT */ diff --git a/kernel/fs/nfs/mount_clnt.c b/kernel/fs/nfs/mount_clnt.c new file mode 100644 index 000000000..99a45283b --- /dev/null +++ b/kernel/fs/nfs/mount_clnt.c @@ -0,0 +1,535 @@ +/* + * In-kernel MOUNT protocol client + * + * Copyright (C) 1997, Olaf Kirch <okir@monad.swb.de> + */ + +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/uio.h> +#include <linux/net.h> +#include <linux/in.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/sched.h> +#include <linux/nfs_fs.h> +#include "internal.h" + +#ifdef NFS_DEBUG +# define NFSDBG_FACILITY NFSDBG_MOUNT +#endif + +/* + * Defined by RFC 1094, section A.3; and RFC 1813, section 5.1.4 + */ +#define MNTPATHLEN (1024) + +/* + * XDR data type sizes + */ +#define encode_dirpath_sz (1 + XDR_QUADLEN(MNTPATHLEN)) +#define MNT_status_sz (1) +#define MNT_fhs_status_sz (1) +#define MNT_fhandle_sz XDR_QUADLEN(NFS2_FHSIZE) +#define MNT_fhandle3_sz (1 + XDR_QUADLEN(NFS3_FHSIZE)) +#define MNT_authflav3_sz (1 + NFS_MAX_SECFLAVORS) + +/* + * XDR argument and result sizes + */ +#define MNT_enc_dirpath_sz encode_dirpath_sz +#define MNT_dec_mountres_sz (MNT_status_sz + MNT_fhandle_sz) +#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandle_sz + \ + MNT_authflav3_sz) + +/* + * Defined by RFC 1094, section A.5 + */ +enum { + MOUNTPROC_NULL = 0, + MOUNTPROC_MNT = 1, + MOUNTPROC_DUMP = 2, + MOUNTPROC_UMNT = 3, + MOUNTPROC_UMNTALL = 4, + MOUNTPROC_EXPORT = 5, +}; + +/* + * Defined by RFC 1813, section 5.2 + */ +enum { + MOUNTPROC3_NULL = 0, + MOUNTPROC3_MNT = 1, + MOUNTPROC3_DUMP = 2, + MOUNTPROC3_UMNT = 3, + MOUNTPROC3_UMNTALL = 4, + MOUNTPROC3_EXPORT = 5, +}; + +static const struct rpc_program mnt_program; + +/* + * Defined by OpenGroup XNFS Version 3W, chapter 8 + */ +enum mountstat { + MNT_OK = 0, + MNT_EPERM = 1, + MNT_ENOENT = 2, + MNT_EACCES = 13, + MNT_EINVAL = 22, +}; + +static struct { + u32 status; + int errno; +} mnt_errtbl[] = { + { .status = MNT_OK, .errno = 0, }, + { .status = MNT_EPERM, .errno = -EPERM, }, + { .status = MNT_ENOENT, .errno = -ENOENT, }, + { .status = MNT_EACCES, .errno = -EACCES, }, + { .status = MNT_EINVAL, .errno = -EINVAL, }, +}; + +/* + * Defined by RFC 1813, section 5.1.5 + */ +enum mountstat3 { + MNT3_OK = 0, /* no error */ + MNT3ERR_PERM = 1, /* Not owner */ + MNT3ERR_NOENT = 2, /* No such file or directory */ + MNT3ERR_IO = 5, /* I/O error */ + MNT3ERR_ACCES = 13, /* Permission denied */ + MNT3ERR_NOTDIR = 20, /* Not a directory */ + MNT3ERR_INVAL = 22, /* Invalid argument */ + MNT3ERR_NAMETOOLONG = 63, /* Filename too long */ + MNT3ERR_NOTSUPP = 10004, /* Operation not supported */ + MNT3ERR_SERVERFAULT = 10006, /* A failure on the server */ +}; + +static struct { + u32 status; + int errno; +} mnt3_errtbl[] = { + { .status = MNT3_OK, .errno = 0, }, + { .status = MNT3ERR_PERM, .errno = -EPERM, }, + { .status = MNT3ERR_NOENT, .errno = -ENOENT, }, + { .status = MNT3ERR_IO, .errno = -EIO, }, + { .status = MNT3ERR_ACCES, .errno = -EACCES, }, + { .status = MNT3ERR_NOTDIR, .errno = -ENOTDIR, }, + { .status = MNT3ERR_INVAL, .errno = -EINVAL, }, + { .status = MNT3ERR_NAMETOOLONG, .errno = -ENAMETOOLONG, }, + { .status = MNT3ERR_NOTSUPP, .errno = -ENOTSUPP, }, + { .status = MNT3ERR_SERVERFAULT, .errno = -EREMOTEIO, }, +}; + +struct mountres { + int errno; + struct nfs_fh *fh; + unsigned int *auth_count; + rpc_authflavor_t *auth_flavors; +}; + +struct mnt_fhstatus { + u32 status; + struct nfs_fh *fh; +}; + +/** + * nfs_mount - Obtain an NFS file handle for the given host and path + * @info: pointer to mount request arguments + * + * Uses default timeout parameters specified by underlying transport. On + * successful return, the auth_flavs list and auth_flav_len will be populated + * with the list from the server or a faked-up list if the server didn't + * provide one. + */ +int nfs_mount(struct nfs_mount_request *info) +{ + struct mountres result = { + .fh = info->fh, + .auth_count = info->auth_flav_len, + .auth_flavors = info->auth_flavs, + }; + struct rpc_message msg = { + .rpc_argp = info->dirpath, + .rpc_resp = &result, + }; + struct rpc_create_args args = { + .net = info->net, + .protocol = info->protocol, + .address = info->sap, + .addrsize = info->salen, + .servername = info->hostname, + .program = &mnt_program, + .version = info->version, + .authflavor = RPC_AUTH_UNIX, + }; + struct rpc_clnt *mnt_clnt; + int status; + + dprintk("NFS: sending MNT request for %s:%s\n", + (info->hostname ? info->hostname : "server"), + info->dirpath); + + if (strlen(info->dirpath) > MNTPATHLEN) + return -ENAMETOOLONG; + + if (info->noresvport) + args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + + mnt_clnt = rpc_create(&args); + if (IS_ERR(mnt_clnt)) + goto out_clnt_err; + + if (info->version == NFS_MNT3_VERSION) + msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC3_MNT]; + else + msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT]; + + status = rpc_call_sync(mnt_clnt, &msg, RPC_TASK_SOFT|RPC_TASK_TIMEOUT); + rpc_shutdown_client(mnt_clnt); + + if (status < 0) + goto out_call_err; + if (result.errno != 0) + goto out_mnt_err; + + dprintk("NFS: MNT request succeeded\n"); + status = 0; + + /* + * If the server didn't provide a flavor list, allow the + * client to try any flavor. + */ + if (info->version != NFS_MNT3_VERSION || *info->auth_flav_len == 0) { + dprintk("NFS: Faking up auth_flavs list\n"); + info->auth_flavs[0] = RPC_AUTH_NULL; + *info->auth_flav_len = 1; + } +out: + return status; + +out_clnt_err: + status = PTR_ERR(mnt_clnt); + dprintk("NFS: failed to create MNT RPC client, status=%d\n", status); + goto out; + +out_call_err: + dprintk("NFS: MNT request failed, status=%d\n", status); + goto out; + +out_mnt_err: + dprintk("NFS: MNT server returned result %d\n", result.errno); + status = result.errno; + goto out; +} + +/** + * nfs_umount - Notify a server that we have unmounted this export + * @info: pointer to umount request arguments + * + * MOUNTPROC_UMNT is advisory, so we set a short timeout, and always + * use UDP. + */ +void nfs_umount(const struct nfs_mount_request *info) +{ + static const struct rpc_timeout nfs_umnt_timeout = { + .to_initval = 1 * HZ, + .to_maxval = 3 * HZ, + .to_retries = 2, + }; + struct rpc_create_args args = { + .net = info->net, + .protocol = IPPROTO_UDP, + .address = info->sap, + .addrsize = info->salen, + .timeout = &nfs_umnt_timeout, + .servername = info->hostname, + .program = &mnt_program, + .version = info->version, + .authflavor = RPC_AUTH_UNIX, + .flags = RPC_CLNT_CREATE_NOPING, + }; + struct rpc_message msg = { + .rpc_argp = info->dirpath, + }; + struct rpc_clnt *clnt; + int status; + + if (strlen(info->dirpath) > MNTPATHLEN) + return; + + if (info->noresvport) + args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + + clnt = rpc_create(&args); + if (IS_ERR(clnt)) + goto out_clnt_err; + + dprintk("NFS: sending UMNT request for %s:%s\n", + (info->hostname ? info->hostname : "server"), info->dirpath); + + if (info->version == NFS_MNT3_VERSION) + msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC3_UMNT]; + else + msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC_UMNT]; + + status = rpc_call_sync(clnt, &msg, 0); + rpc_shutdown_client(clnt); + + if (unlikely(status < 0)) + goto out_call_err; + + return; + +out_clnt_err: + dprintk("NFS: failed to create UMNT RPC client, status=%ld\n", + PTR_ERR(clnt)); + return; + +out_call_err: + dprintk("NFS: UMNT request failed, status=%d\n", status); +} + +/* + * XDR encode/decode functions for MOUNT + */ + +static void encode_mntdirpath(struct xdr_stream *xdr, const char *pathname) +{ + const u32 pathname_len = strlen(pathname); + __be32 *p; + + p = xdr_reserve_space(xdr, 4 + pathname_len); + xdr_encode_opaque(p, pathname, pathname_len); +} + +static void mnt_xdr_enc_dirpath(struct rpc_rqst *req, struct xdr_stream *xdr, + const char *dirpath) +{ + encode_mntdirpath(xdr, dirpath); +} + +/* + * RFC 1094: "A non-zero status indicates some sort of error. In this + * case, the status is a UNIX error number." This can be problematic + * if the server and client use different errno values for the same + * error. + * + * However, the OpenGroup XNFS spec provides a simple mapping that is + * independent of local errno values on the server and the client. + */ +static int decode_status(struct xdr_stream *xdr, struct mountres *res) +{ + unsigned int i; + u32 status; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + return -EIO; + status = be32_to_cpup(p); + + for (i = 0; i < ARRAY_SIZE(mnt_errtbl); i++) { + if (mnt_errtbl[i].status == status) { + res->errno = mnt_errtbl[i].errno; + return 0; + } + } + + dprintk("NFS: unrecognized MNT status code: %u\n", status); + res->errno = -EACCES; + return 0; +} + +static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res) +{ + struct nfs_fh *fh = res->fh; + __be32 *p; + + p = xdr_inline_decode(xdr, NFS2_FHSIZE); + if (unlikely(p == NULL)) + return -EIO; + + fh->size = NFS2_FHSIZE; + memcpy(fh->data, p, NFS2_FHSIZE); + return 0; +} + +static int mnt_xdr_dec_mountres(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct mountres *res) +{ + int status; + + status = decode_status(xdr, res); + if (unlikely(status != 0 || res->errno != 0)) + return status; + return decode_fhandle(xdr, res); +} + +static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res) +{ + unsigned int i; + u32 status; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + return -EIO; + status = be32_to_cpup(p); + + for (i = 0; i < ARRAY_SIZE(mnt3_errtbl); i++) { + if (mnt3_errtbl[i].status == status) { + res->errno = mnt3_errtbl[i].errno; + return 0; + } + } + + dprintk("NFS: unrecognized MNT3 status code: %u\n", status); + res->errno = -EACCES; + return 0; +} + +static int decode_fhandle3(struct xdr_stream *xdr, struct mountres *res) +{ + struct nfs_fh *fh = res->fh; + u32 size; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + return -EIO; + + size = be32_to_cpup(p); + if (size > NFS3_FHSIZE || size == 0) + return -EIO; + + p = xdr_inline_decode(xdr, size); + if (unlikely(p == NULL)) + return -EIO; + + fh->size = size; + memcpy(fh->data, p, size); + return 0; +} + +static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res) +{ + rpc_authflavor_t *flavors = res->auth_flavors; + unsigned int *count = res->auth_count; + u32 entries, i; + __be32 *p; + + if (*count == 0) + return 0; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + return -EIO; + entries = be32_to_cpup(p); + dprintk("NFS: received %u auth flavors\n", entries); + if (entries > NFS_MAX_SECFLAVORS) + entries = NFS_MAX_SECFLAVORS; + + p = xdr_inline_decode(xdr, 4 * entries); + if (unlikely(p == NULL)) + return -EIO; + + if (entries > *count) + entries = *count; + + for (i = 0; i < entries; i++) { + flavors[i] = be32_to_cpup(p++); + dprintk("NFS: auth flavor[%u]: %d\n", i, flavors[i]); + } + *count = i; + + return 0; +} + +static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct mountres *res) +{ + int status; + + status = decode_fhs_status(xdr, res); + if (unlikely(status != 0 || res->errno != 0)) + return status; + status = decode_fhandle3(xdr, res); + if (unlikely(status != 0)) { + res->errno = -EBADHANDLE; + return 0; + } + return decode_auth_flavors(xdr, res); +} + +static struct rpc_procinfo mnt_procedures[] = { + [MOUNTPROC_MNT] = { + .p_proc = MOUNTPROC_MNT, + .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres, + .p_arglen = MNT_enc_dirpath_sz, + .p_replen = MNT_dec_mountres_sz, + .p_statidx = MOUNTPROC_MNT, + .p_name = "MOUNT", + }, + [MOUNTPROC_UMNT] = { + .p_proc = MOUNTPROC_UMNT, + .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_arglen = MNT_enc_dirpath_sz, + .p_statidx = MOUNTPROC_UMNT, + .p_name = "UMOUNT", + }, +}; + +static struct rpc_procinfo mnt3_procedures[] = { + [MOUNTPROC3_MNT] = { + .p_proc = MOUNTPROC3_MNT, + .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres3, + .p_arglen = MNT_enc_dirpath_sz, + .p_replen = MNT_dec_mountres3_sz, + .p_statidx = MOUNTPROC3_MNT, + .p_name = "MOUNT", + }, + [MOUNTPROC3_UMNT] = { + .p_proc = MOUNTPROC3_UMNT, + .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_arglen = MNT_enc_dirpath_sz, + .p_statidx = MOUNTPROC3_UMNT, + .p_name = "UMOUNT", + }, +}; + + +static const struct rpc_version mnt_version1 = { + .number = 1, + .nrprocs = ARRAY_SIZE(mnt_procedures), + .procs = mnt_procedures, +}; + +static const struct rpc_version mnt_version3 = { + .number = 3, + .nrprocs = ARRAY_SIZE(mnt3_procedures), + .procs = mnt3_procedures, +}; + +static const struct rpc_version *mnt_version[] = { + NULL, + &mnt_version1, + NULL, + &mnt_version3, +}; + +static struct rpc_stat mnt_stats; + +static const struct rpc_program mnt_program = { + .name = "mount", + .number = NFS_MNT_PROGRAM, + .nrvers = ARRAY_SIZE(mnt_version), + .version = mnt_version, + .stats = &mnt_stats, +}; diff --git a/kernel/fs/nfs/namespace.c b/kernel/fs/nfs/namespace.c new file mode 100644 index 000000000..c8162c660 --- /dev/null +++ b/kernel/fs/nfs/namespace.c @@ -0,0 +1,289 @@ +/* + * linux/fs/nfs/namespace.c + * + * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com> + * - Modified by David Howells <dhowells@redhat.com> + * + * NFS namespace + */ + +#include <linux/module.h> +#include <linux/dcache.h> +#include <linux/gfp.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/nfs_fs.h> +#include <linux/string.h> +#include <linux/sunrpc/clnt.h> +#include <linux/vfs.h> +#include <linux/sunrpc/gss_api.h> +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +static void nfs_expire_automounts(struct work_struct *work); + +static LIST_HEAD(nfs_automount_list); +static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts); +int nfs_mountpoint_expiry_timeout = 500 * HZ; + +/* + * nfs_path - reconstruct the path given an arbitrary dentry + * @base - used to return pointer to the end of devname part of path + * @dentry - pointer to dentry + * @buffer - result buffer + * @buflen - length of buffer + * @flags - options (see below) + * + * Helper function for constructing the server pathname + * by arbitrary hashed dentry. + * + * This is mainly for use in figuring out the path on the + * server side when automounting on top of an existing partition + * and in generating /proc/mounts and friends. + * + * Supported flags: + * NFS_PATH_CANONICAL: ensure there is exactly one slash after + * the original device (export) name + * (if unset, the original name is returned verbatim) + */ +char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, + unsigned flags) +{ + char *end; + int namelen; + unsigned seq; + const char *base; + +rename_retry: + end = buffer+buflen; + *--end = '\0'; + buflen--; + + seq = read_seqbegin(&rename_lock); + rcu_read_lock(); + while (1) { + spin_lock(&dentry->d_lock); + if (IS_ROOT(dentry)) + break; + namelen = dentry->d_name.len; + buflen -= namelen + 1; + if (buflen < 0) + goto Elong_unlock; + end -= namelen; + memcpy(end, dentry->d_name.name, namelen); + *--end = '/'; + spin_unlock(&dentry->d_lock); + dentry = dentry->d_parent; + } + if (read_seqretry(&rename_lock, seq)) { + spin_unlock(&dentry->d_lock); + rcu_read_unlock(); + goto rename_retry; + } + if ((flags & NFS_PATH_CANONICAL) && *end != '/') { + if (--buflen < 0) { + spin_unlock(&dentry->d_lock); + rcu_read_unlock(); + goto Elong; + } + *--end = '/'; + } + *p = end; + base = dentry->d_fsdata; + if (!base) { + spin_unlock(&dentry->d_lock); + rcu_read_unlock(); + WARN_ON(1); + return end; + } + namelen = strlen(base); + if (flags & NFS_PATH_CANONICAL) { + /* Strip off excess slashes in base string */ + while (namelen > 0 && base[namelen - 1] == '/') + namelen--; + } + buflen -= namelen; + if (buflen < 0) { + spin_unlock(&dentry->d_lock); + rcu_read_unlock(); + goto Elong; + } + end -= namelen; + memcpy(end, base, namelen); + spin_unlock(&dentry->d_lock); + rcu_read_unlock(); + return end; +Elong_unlock: + spin_unlock(&dentry->d_lock); + rcu_read_unlock(); + if (read_seqretry(&rename_lock, seq)) + goto rename_retry; +Elong: + return ERR_PTR(-ENAMETOOLONG); +} +EXPORT_SYMBOL_GPL(nfs_path); + +/* + * nfs_d_automount - Handle crossing a mountpoint on the server + * @path - The mountpoint + * + * When we encounter a mountpoint on the server, we want to set up + * a mountpoint on the client too, to prevent inode numbers from + * colliding, and to allow "df" to work properly. + * On NFSv4, we also want to allow for the fact that different + * filesystems may be migrated to different servers in a failover + * situation, and that different filesystems may want to use + * different security flavours. + */ +struct vfsmount *nfs_d_automount(struct path *path) +{ + struct vfsmount *mnt; + struct nfs_server *server = NFS_SERVER(d_inode(path->dentry)); + struct nfs_fh *fh = NULL; + struct nfs_fattr *fattr = NULL; + + dprintk("--> nfs_d_automount()\n"); + + mnt = ERR_PTR(-ESTALE); + if (IS_ROOT(path->dentry)) + goto out_nofree; + + mnt = ERR_PTR(-ENOMEM); + fh = nfs_alloc_fhandle(); + fattr = nfs_alloc_fattr(); + if (fh == NULL || fattr == NULL) + goto out; + + dprintk("%s: enter\n", __func__); + + mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr); + if (IS_ERR(mnt)) + goto out; + + dprintk("%s: done, success\n", __func__); + mntget(mnt); /* prevent immediate expiration */ + mnt_set_expiry(mnt, &nfs_automount_list); + schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout); + +out: + nfs_free_fattr(fattr); + nfs_free_fhandle(fh); +out_nofree: + if (IS_ERR(mnt)) + dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt)); + else + dprintk("<-- %s() = %p\n", __func__, mnt); + return mnt; +} + +static int +nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + if (NFS_FH(d_inode(dentry))->size != 0) + return nfs_getattr(mnt, dentry, stat); + generic_fillattr(d_inode(dentry), stat); + return 0; +} + +static int +nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr) +{ + if (NFS_FH(d_inode(dentry))->size != 0) + return nfs_setattr(dentry, attr); + return -EACCES; +} + +const struct inode_operations nfs_mountpoint_inode_operations = { + .getattr = nfs_getattr, + .setattr = nfs_setattr, +}; + +const struct inode_operations nfs_referral_inode_operations = { + .getattr = nfs_namespace_getattr, + .setattr = nfs_namespace_setattr, +}; + +static void nfs_expire_automounts(struct work_struct *work) +{ + struct list_head *list = &nfs_automount_list; + + mark_mounts_for_expiry(list); + if (!list_empty(list)) + schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout); +} + +void nfs_release_automount_timer(void) +{ + if (list_empty(&nfs_automount_list)) + cancel_delayed_work(&nfs_automount_task); +} + +/* + * Clone a mountpoint of the appropriate type + */ +static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, + const char *devname, + struct nfs_clone_mount *mountdata) +{ + return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata); +} + +/** + * nfs_do_submount - set up mountpoint when crossing a filesystem boundary + * @dentry - parent directory + * @fh - filehandle for new root dentry + * @fattr - attributes for new root inode + * @authflavor - security flavor to use when performing the mount + * + */ +struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, + struct nfs_fattr *fattr, rpc_authflavor_t authflavor) +{ + struct nfs_clone_mount mountdata = { + .sb = dentry->d_sb, + .dentry = dentry, + .fh = fh, + .fattr = fattr, + .authflavor = authflavor, + }; + struct vfsmount *mnt = ERR_PTR(-ENOMEM); + char *page = (char *) __get_free_page(GFP_USER); + char *devname; + + dprintk("--> nfs_do_submount()\n"); + + dprintk("%s: submounting on %pd2\n", __func__, + dentry); + if (page == NULL) + goto out; + devname = nfs_devname(dentry, page, PAGE_SIZE); + mnt = (struct vfsmount *)devname; + if (IS_ERR(devname)) + goto free_page; + mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata); +free_page: + free_page((unsigned long)page); +out: + dprintk("%s: done\n", __func__); + + dprintk("<-- nfs_do_submount() = %p\n", mnt); + return mnt; +} +EXPORT_SYMBOL_GPL(nfs_do_submount); + +struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + int err; + struct dentry *parent = dget_parent(dentry); + + /* Look it up again to get its attributes */ + err = server->nfs_client->rpc_ops->lookup(d_inode(parent), &dentry->d_name, fh, fattr, NULL); + dput(parent); + if (err != 0) + return ERR_PTR(err); + + return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor); +} +EXPORT_SYMBOL_GPL(nfs_submount); diff --git a/kernel/fs/nfs/netns.h b/kernel/fs/nfs/netns.h new file mode 100644 index 000000000..f0e06e4ac --- /dev/null +++ b/kernel/fs/nfs/netns.h @@ -0,0 +1,40 @@ +/* + * NFS-private data for each "struct net". Accessed with net_generic(). + */ + +#ifndef __NFS_NETNS_H__ +#define __NFS_NETNS_H__ + +#include <linux/nfs4.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> + +struct bl_dev_msg { + int32_t status; + uint32_t major, minor; +}; + +struct nfs_net { + struct cache_detail *nfs_dns_resolve; + struct rpc_pipe *bl_device_pipe; + struct bl_dev_msg bl_mount_reply; + wait_queue_head_t bl_wq; + struct mutex bl_mutex; + struct list_head nfs_client_list; + struct list_head nfs_volume_list; +#if IS_ENABLED(CONFIG_NFS_V4) + struct idr cb_ident_idr; /* Protected by nfs_client_lock */ + unsigned short nfs_callback_tcpport; + unsigned short nfs_callback_tcpport6; + int cb_users[NFS4_MAX_MINOR_VERSION + 1]; +#endif + spinlock_t nfs_client_lock; + struct timespec boot_time; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc_nfsfs; +#endif +}; + +extern int nfs_net_id; + +#endif diff --git a/kernel/fs/nfs/nfs.h b/kernel/fs/nfs/nfs.h new file mode 100644 index 000000000..43679df56 --- /dev/null +++ b/kernel/fs/nfs/nfs.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2012 Netapp, Inc. All rights reserved. + * + * Function and structures exported by the NFS module + * for use by NFS version-specific modules. + */ +#ifndef __LINUX_INTERNAL_NFS_H +#define __LINUX_INTERNAL_NFS_H + +#include <linux/fs.h> +#include <linux/sunrpc/sched.h> +#include <linux/nfs_xdr.h> + +struct nfs_subversion { + struct module *owner; /* THIS_MODULE pointer */ + struct file_system_type *nfs_fs; /* NFS filesystem type */ + const struct rpc_version *rpc_vers; /* NFS version information */ + const struct nfs_rpc_ops *rpc_ops; /* NFS operations */ + const struct super_operations *sops; /* NFS Super operations */ + const struct xattr_handler **xattr; /* NFS xattr handlers */ + struct list_head list; /* List of NFS versions */ +}; + +struct nfs_subversion *get_nfs_version(unsigned int); +void put_nfs_version(struct nfs_subversion *); +void register_nfs_version(struct nfs_subversion *); +void unregister_nfs_version(struct nfs_subversion *); + +#endif /* __LINUX_INTERNAL_NFS_H */ diff --git a/kernel/fs/nfs/nfs2super.c b/kernel/fs/nfs/nfs2super.c new file mode 100644 index 000000000..0a9782c91 --- /dev/null +++ b/kernel/fs/nfs/nfs2super.c @@ -0,0 +1,31 @@ +/* + * Copyright (c) 2012 Netapp, Inc. All rights reserved. + */ +#include <linux/module.h> +#include <linux/nfs_fs.h> +#include "internal.h" +#include "nfs.h" + +static struct nfs_subversion nfs_v2 = { + .owner = THIS_MODULE, + .nfs_fs = &nfs_fs_type, + .rpc_vers = &nfs_version2, + .rpc_ops = &nfs_v2_clientops, + .sops = &nfs_sops, +}; + +static int __init init_nfs_v2(void) +{ + register_nfs_version(&nfs_v2); + return 0; +} + +static void __exit exit_nfs_v2(void) +{ + unregister_nfs_version(&nfs_v2); +} + +MODULE_LICENSE("GPL"); + +module_init(init_nfs_v2); +module_exit(exit_nfs_v2); diff --git a/kernel/fs/nfs/nfs2xdr.c b/kernel/fs/nfs/nfs2xdr.c new file mode 100644 index 000000000..b4e03ed85 --- /dev/null +++ b/kernel/fs/nfs/nfs2xdr.c @@ -0,0 +1,1151 @@ +/* + * linux/fs/nfs/nfs2xdr.c + * + * XDR functions to encode/decode NFS RPC arguments and results. + * + * Copyright (C) 1992, 1993, 1994 Rick Sladkey + * Copyright (C) 1996 Olaf Kirch + * 04 Aug 1998 Ion Badulescu <ionut@cs.columbia.edu> + * FIFO's need special handling in NFSv2 + */ + +#include <linux/param.h> +#include <linux/time.h> +#include <linux/mm.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/pagemap.h> +#include <linux/proc_fs.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs2.h> +#include <linux/nfs_fs.h> +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_XDR + +/* Mapping from NFS error code to "errno" error code. */ +#define errno_NFSERR_IO EIO + +/* + * Declare the space requirements for NFS arguments and replies as + * number of 32bit-words + */ +#define NFS_fhandle_sz (8) +#define NFS_sattr_sz (8) +#define NFS_filename_sz (1+(NFS2_MAXNAMLEN>>2)) +#define NFS_path_sz (1+(NFS2_MAXPATHLEN>>2)) +#define NFS_fattr_sz (17) +#define NFS_info_sz (5) +#define NFS_entry_sz (NFS_filename_sz+3) + +#define NFS_diropargs_sz (NFS_fhandle_sz+NFS_filename_sz) +#define NFS_removeargs_sz (NFS_fhandle_sz+NFS_filename_sz) +#define NFS_sattrargs_sz (NFS_fhandle_sz+NFS_sattr_sz) +#define NFS_readlinkargs_sz (NFS_fhandle_sz) +#define NFS_readargs_sz (NFS_fhandle_sz+3) +#define NFS_writeargs_sz (NFS_fhandle_sz+4) +#define NFS_createargs_sz (NFS_diropargs_sz+NFS_sattr_sz) +#define NFS_renameargs_sz (NFS_diropargs_sz+NFS_diropargs_sz) +#define NFS_linkargs_sz (NFS_fhandle_sz+NFS_diropargs_sz) +#define NFS_symlinkargs_sz (NFS_diropargs_sz+1+NFS_sattr_sz) +#define NFS_readdirargs_sz (NFS_fhandle_sz+2) + +#define NFS_attrstat_sz (1+NFS_fattr_sz) +#define NFS_diropres_sz (1+NFS_fhandle_sz+NFS_fattr_sz) +#define NFS_readlinkres_sz (2) +#define NFS_readres_sz (1+NFS_fattr_sz+1) +#define NFS_writeres_sz (NFS_attrstat_sz) +#define NFS_stat_sz (1) +#define NFS_readdirres_sz (1) +#define NFS_statfsres_sz (1+NFS_info_sz) + +static int nfs_stat_to_errno(enum nfs_stat); + +/* + * While encoding arguments, set up the reply buffer in advance to + * receive reply data directly into the page cache. + */ +static void prepare_reply_buffer(struct rpc_rqst *req, struct page **pages, + unsigned int base, unsigned int len, + unsigned int bufsize) +{ + struct rpc_auth *auth = req->rq_cred->cr_auth; + unsigned int replen; + + replen = RPC_REPHDRSIZE + auth->au_rslack + bufsize; + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, pages, base, len); +} + +/* + * Handle decode buffer overflows out-of-line. + */ +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("NFS: %s prematurely hit the end of our receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); +} + + +/* + * Encode/decode NFSv2 basic data types + * + * Basic NFSv2 data types are defined in section 2.3 of RFC 1094: + * "NFS: Network File System Protocol Specification". + * + * Not all basic data types have their own encoding and decoding + * functions. For run-time efficiency, some data types are encoded + * or decoded inline. + */ + +/* + * typedef opaque nfsdata<>; + */ +static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_pgio_res *result) +{ + u32 recvd, count; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + count = be32_to_cpup(p); + recvd = xdr_read_pages(xdr, count); + if (unlikely(count > recvd)) + goto out_cheating; +out: + result->eof = 0; /* NFSv2 does not pass EOF flag on the wire. */ + result->count = count; + return count; +out_cheating: + dprintk("NFS: server cheating in read result: " + "count %u > recvd %u\n", count, recvd); + count = recvd; + goto out; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * enum stat { + * NFS_OK = 0, + * NFSERR_PERM = 1, + * NFSERR_NOENT = 2, + * NFSERR_IO = 5, + * NFSERR_NXIO = 6, + * NFSERR_ACCES = 13, + * NFSERR_EXIST = 17, + * NFSERR_NODEV = 19, + * NFSERR_NOTDIR = 20, + * NFSERR_ISDIR = 21, + * NFSERR_FBIG = 27, + * NFSERR_NOSPC = 28, + * NFSERR_ROFS = 30, + * NFSERR_NAMETOOLONG = 63, + * NFSERR_NOTEMPTY = 66, + * NFSERR_DQUOT = 69, + * NFSERR_STALE = 70, + * NFSERR_WFLUSH = 99 + * }; + */ +static int decode_stat(struct xdr_stream *xdr, enum nfs_stat *status) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + *status = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * 2.3.2. ftype + * + * enum ftype { + * NFNON = 0, + * NFREG = 1, + * NFDIR = 2, + * NFBLK = 3, + * NFCHR = 4, + * NFLNK = 5 + * }; + * + */ +static __be32 *xdr_decode_ftype(__be32 *p, u32 *type) +{ + *type = be32_to_cpup(p++); + if (unlikely(*type > NF2FIFO)) + *type = NFBAD; + return p; +} + +/* + * 2.3.3. fhandle + * + * typedef opaque fhandle[FHSIZE]; + */ +static void encode_fhandle(struct xdr_stream *xdr, const struct nfs_fh *fh) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, NFS2_FHSIZE); + memcpy(p, fh->data, NFS2_FHSIZE); +} + +static int decode_fhandle(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS2_FHSIZE); + if (unlikely(p == NULL)) + goto out_overflow; + fh->size = NFS2_FHSIZE; + memcpy(fh->data, p, NFS2_FHSIZE); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * 2.3.4. timeval + * + * struct timeval { + * unsigned int seconds; + * unsigned int useconds; + * }; + */ +static __be32 *xdr_encode_time(__be32 *p, const struct timespec *timep) +{ + *p++ = cpu_to_be32(timep->tv_sec); + if (timep->tv_nsec != 0) + *p++ = cpu_to_be32(timep->tv_nsec / NSEC_PER_USEC); + else + *p++ = cpu_to_be32(0); + return p; +} + +/* + * Passing the invalid value useconds=1000000 is a Sun convention for + * "set to current server time". It's needed to make permissions checks + * for the "touch" program across v2 mounts to Solaris and Irix servers + * work correctly. See description of sattr in section 6.1 of "NFS + * Illustrated" by Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5. + */ +static __be32 *xdr_encode_current_server_time(__be32 *p, + const struct timespec *timep) +{ + *p++ = cpu_to_be32(timep->tv_sec); + *p++ = cpu_to_be32(1000000); + return p; +} + +static __be32 *xdr_decode_time(__be32 *p, struct timespec *timep) +{ + timep->tv_sec = be32_to_cpup(p++); + timep->tv_nsec = be32_to_cpup(p++) * NSEC_PER_USEC; + return p; +} + +/* + * 2.3.5. fattr + * + * struct fattr { + * ftype type; + * unsigned int mode; + * unsigned int nlink; + * unsigned int uid; + * unsigned int gid; + * unsigned int size; + * unsigned int blocksize; + * unsigned int rdev; + * unsigned int blocks; + * unsigned int fsid; + * unsigned int fileid; + * timeval atime; + * timeval mtime; + * timeval ctime; + * }; + * + */ +static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + u32 rdev, type; + __be32 *p; + + p = xdr_inline_decode(xdr, NFS_fattr_sz << 2); + if (unlikely(p == NULL)) + goto out_overflow; + + fattr->valid |= NFS_ATTR_FATTR_V2; + + p = xdr_decode_ftype(p, &type); + + fattr->mode = be32_to_cpup(p++); + fattr->nlink = be32_to_cpup(p++); + fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++)); + if (!uid_valid(fattr->uid)) + goto out_uid; + fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++)); + if (!gid_valid(fattr->gid)) + goto out_gid; + + fattr->size = be32_to_cpup(p++); + fattr->du.nfs2.blocksize = be32_to_cpup(p++); + + rdev = be32_to_cpup(p++); + fattr->rdev = new_decode_dev(rdev); + if (type == (u32)NFCHR && rdev == (u32)NFS2_FIFO_DEV) { + fattr->mode = (fattr->mode & ~S_IFMT) | S_IFIFO; + fattr->rdev = 0; + } + + fattr->du.nfs2.blocks = be32_to_cpup(p++); + fattr->fsid.major = be32_to_cpup(p++); + fattr->fsid.minor = 0; + fattr->fileid = be32_to_cpup(p++); + + p = xdr_decode_time(p, &fattr->atime); + p = xdr_decode_time(p, &fattr->mtime); + xdr_decode_time(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + + return 0; +out_uid: + dprintk("NFS: returned invalid uid\n"); + return -EINVAL; +out_gid: + dprintk("NFS: returned invalid gid\n"); + return -EINVAL; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * 2.3.6. sattr + * + * struct sattr { + * unsigned int mode; + * unsigned int uid; + * unsigned int gid; + * unsigned int size; + * timeval atime; + * timeval mtime; + * }; + */ + +#define NFS2_SATTR_NOT_SET (0xffffffff) + +static __be32 *xdr_time_not_set(__be32 *p) +{ + *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); + *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); + return p; +} + +static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, NFS_sattr_sz << 2); + + if (attr->ia_valid & ATTR_MODE) + *p++ = cpu_to_be32(attr->ia_mode); + else + *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); + if (attr->ia_valid & ATTR_UID) + *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid)); + else + *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); + if (attr->ia_valid & ATTR_GID) + *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid)); + else + *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); + if (attr->ia_valid & ATTR_SIZE) + *p++ = cpu_to_be32((u32)attr->ia_size); + else + *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); + + if (attr->ia_valid & ATTR_ATIME_SET) + p = xdr_encode_time(p, &attr->ia_atime); + else if (attr->ia_valid & ATTR_ATIME) + p = xdr_encode_current_server_time(p, &attr->ia_atime); + else + p = xdr_time_not_set(p); + if (attr->ia_valid & ATTR_MTIME_SET) + xdr_encode_time(p, &attr->ia_mtime); + else if (attr->ia_valid & ATTR_MTIME) + xdr_encode_current_server_time(p, &attr->ia_mtime); + else + xdr_time_not_set(p); +} + +/* + * 2.3.7. filename + * + * typedef string filename<MAXNAMLEN>; + */ +static void encode_filename(struct xdr_stream *xdr, + const char *name, u32 length) +{ + __be32 *p; + + WARN_ON_ONCE(length > NFS2_MAXNAMLEN); + p = xdr_reserve_space(xdr, 4 + length); + xdr_encode_opaque(p, name, length); +} + +static int decode_filename_inline(struct xdr_stream *xdr, + const char **name, u32 *length) +{ + __be32 *p; + u32 count; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + count = be32_to_cpup(p); + if (count > NFS3_MAXNAMLEN) + goto out_nametoolong; + p = xdr_inline_decode(xdr, count); + if (unlikely(p == NULL)) + goto out_overflow; + *name = (const char *)p; + *length = count; + return 0; +out_nametoolong: + dprintk("NFS: returned filename too long: %u\n", count); + return -ENAMETOOLONG; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * 2.3.8. path + * + * typedef string path<MAXPATHLEN>; + */ +static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + *p = cpu_to_be32(length); + xdr_write_pages(xdr, pages, 0, length); +} + +static int decode_path(struct xdr_stream *xdr) +{ + u32 length, recvd; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + length = be32_to_cpup(p); + if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN)) + goto out_size; + recvd = xdr_read_pages(xdr, length); + if (unlikely(length > recvd)) + goto out_cheating; + xdr_terminate_string(xdr->buf, length); + return 0; +out_size: + dprintk("NFS: returned pathname too long: %u\n", length); + return -ENAMETOOLONG; +out_cheating: + dprintk("NFS: server cheating in pathname result: " + "length %u > received %u\n", length, recvd); + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * 2.3.9. attrstat + * + * union attrstat switch (stat status) { + * case NFS_OK: + * fattr attributes; + * default: + * void; + * }; + */ +static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result, + __u32 *op_status) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + if (op_status) + *op_status = status; + if (status != NFS_OK) + goto out_default; + error = decode_fattr(xdr, result); +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + +/* + * 2.3.10. diropargs + * + * struct diropargs { + * fhandle dir; + * filename name; + * }; + */ +static void encode_diropargs(struct xdr_stream *xdr, const struct nfs_fh *fh, + const char *name, u32 length) +{ + encode_fhandle(xdr, fh); + encode_filename(xdr, name, length); +} + +/* + * 2.3.11. diropres + * + * union diropres switch (stat status) { + * case NFS_OK: + * struct { + * fhandle file; + * fattr attributes; + * } diropok; + * default: + * void; + * }; + */ +static int decode_diropok(struct xdr_stream *xdr, struct nfs_diropok *result) +{ + int error; + + error = decode_fhandle(xdr, result->fh); + if (unlikely(error)) + goto out; + error = decode_fattr(xdr, result->fattr); +out: + return error; +} + +static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS_OK) + goto out_default; + error = decode_diropok(xdr, result); +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + + +/* + * NFSv2 XDR encode functions + * + * NFSv2 argument types are defined in section 2.2 of RFC 1094: + * "NFS: Network File System Protocol Specification". + */ + +static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_fh *fh) +{ + encode_fhandle(xdr, fh); +} + +/* + * 2.2.3. sattrargs + * + * struct sattrargs { + * fhandle file; + * sattr attributes; + * }; + */ +static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_sattrargs *args) +{ + encode_fhandle(xdr, args->fh); + encode_sattr(xdr, args->sattr); +} + +static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_diropargs *args) +{ + encode_diropargs(xdr, args->fh, args->name, args->len); +} + +static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_readlinkargs *args) +{ + encode_fhandle(xdr, args->fh); + prepare_reply_buffer(req, args->pages, args->pgbase, + args->pglen, NFS_readlinkres_sz); +} + +/* + * 2.2.7. readargs + * + * struct readargs { + * fhandle file; + * unsigned offset; + * unsigned count; + * unsigned totalcount; + * }; + */ +static void encode_readargs(struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + u32 offset = args->offset; + u32 count = args->count; + __be32 *p; + + encode_fhandle(xdr, args->fh); + + p = xdr_reserve_space(xdr, 4 + 4 + 4); + *p++ = cpu_to_be32(offset); + *p++ = cpu_to_be32(count); + *p = cpu_to_be32(count); +} + +static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + encode_readargs(xdr, args); + prepare_reply_buffer(req, args->pages, args->pgbase, + args->count, NFS_readres_sz); + req->rq_rcv_buf.flags |= XDRBUF_READ; +} + +/* + * 2.2.9. writeargs + * + * struct writeargs { + * fhandle file; + * unsigned beginoffset; + * unsigned offset; + * unsigned totalcount; + * nfsdata data; + * }; + */ +static void encode_writeargs(struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + u32 offset = args->offset; + u32 count = args->count; + __be32 *p; + + encode_fhandle(xdr, args->fh); + + p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4); + *p++ = cpu_to_be32(offset); + *p++ = cpu_to_be32(offset); + *p++ = cpu_to_be32(count); + + /* nfsdata */ + *p = cpu_to_be32(count); + xdr_write_pages(xdr, args->pages, args->pgbase, count); +} + +static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + encode_writeargs(xdr, args); + xdr->buf->flags |= XDRBUF_WRITE; +} + +/* + * 2.2.10. createargs + * + * struct createargs { + * diropargs where; + * sattr attributes; + * }; + */ +static void nfs2_xdr_enc_createargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_createargs *args) +{ + encode_diropargs(xdr, args->fh, args->name, args->len); + encode_sattr(xdr, args->sattr); +} + +static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_removeargs *args) +{ + encode_diropargs(xdr, args->fh, args->name.name, args->name.len); +} + +/* + * 2.2.12. renameargs + * + * struct renameargs { + * diropargs from; + * diropargs to; + * }; + */ +static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_renameargs *args) +{ + const struct qstr *old = args->old_name; + const struct qstr *new = args->new_name; + + encode_diropargs(xdr, args->old_dir, old->name, old->len); + encode_diropargs(xdr, args->new_dir, new->name, new->len); +} + +/* + * 2.2.13. linkargs + * + * struct linkargs { + * fhandle from; + * diropargs to; + * }; + */ +static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_linkargs *args) +{ + encode_fhandle(xdr, args->fromfh); + encode_diropargs(xdr, args->tofh, args->toname, args->tolen); +} + +/* + * 2.2.14. symlinkargs + * + * struct symlinkargs { + * diropargs from; + * path to; + * sattr attributes; + * }; + */ +static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_symlinkargs *args) +{ + encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen); + encode_path(xdr, args->pages, args->pathlen); + encode_sattr(xdr, args->sattr); +} + +/* + * 2.2.17. readdirargs + * + * struct readdirargs { + * fhandle dir; + * nfscookie cookie; + * unsigned count; + * }; + */ +static void encode_readdirargs(struct xdr_stream *xdr, + const struct nfs_readdirargs *args) +{ + __be32 *p; + + encode_fhandle(xdr, args->fh); + + p = xdr_reserve_space(xdr, 4 + 4); + *p++ = cpu_to_be32(args->cookie); + *p = cpu_to_be32(args->count); +} + +static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_readdirargs *args) +{ + encode_readdirargs(xdr, args); + prepare_reply_buffer(req, args->pages, 0, + args->count, NFS_readdirres_sz); +} + +/* + * NFSv2 XDR decode functions + * + * NFSv2 result types are defined in section 2.2 of RFC 1094: + * "NFS: Network File System Protocol Specification". + */ + +static int nfs2_xdr_dec_stat(struct rpc_rqst *req, struct xdr_stream *xdr, + void *__unused) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS_OK) + goto out_default; +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + +static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_fattr *result) +{ + return decode_attrstat(xdr, result, NULL); +} + +static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_diropok *result) +{ + return decode_diropres(xdr, result); +} + +/* + * 2.2.6. readlinkres + * + * union readlinkres switch (stat status) { + * case NFS_OK: + * path data; + * default: + * void; + * }; + */ +static int nfs2_xdr_dec_readlinkres(struct rpc_rqst *req, + struct xdr_stream *xdr, void *__unused) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS_OK) + goto out_default; + error = decode_path(xdr); +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + +/* + * 2.2.7. readres + * + * union readres switch (stat status) { + * case NFS_OK: + * fattr attributes; + * nfsdata data; + * default: + * void; + * }; + */ +static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_pgio_res *result) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + result->op_status = status; + if (status != NFS_OK) + goto out_default; + error = decode_fattr(xdr, result->fattr); + if (unlikely(error)) + goto out; + error = decode_nfsdata(xdr, result); +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + +static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_pgio_res *result) +{ + /* All NFSv2 writes are "file sync" writes */ + result->verf->committed = NFS_FILE_SYNC; + return decode_attrstat(xdr, result->fattr, &result->op_status); +} + +/** + * nfs2_decode_dirent - Decode a single NFSv2 directory entry stored in + * the local page cache. + * @xdr: XDR stream where entry resides + * @entry: buffer to fill in with entry data + * @plus: boolean indicating whether this should be a readdirplus entry + * + * Returns zero if successful, otherwise a negative errno value is + * returned. + * + * This function is not invoked during READDIR reply decoding, but + * rather whenever an application invokes the getdents(2) system call + * on a directory already in our cache. + * + * 2.2.17. entry + * + * struct entry { + * unsigned fileid; + * filename name; + * nfscookie cookie; + * entry *nextentry; + * }; + */ +int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, + int plus) +{ + __be32 *p; + int error; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p++ == xdr_zero) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p++ == xdr_zero) + return -EAGAIN; + entry->eof = 1; + return -EBADCOOKIE; + } + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + entry->ino = be32_to_cpup(p); + + error = decode_filename_inline(xdr, &entry->name, &entry->len); + if (unlikely(error)) + return error; + + /* + * The type (size and byte order) of nfscookie isn't defined in + * RFC 1094. This implementation assumes that it's an XDR uint32. + */ + entry->prev_cookie = entry->cookie; + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + entry->cookie = be32_to_cpup(p); + + entry->d_type = DT_UNKNOWN; + + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EAGAIN; +} + +/* + * 2.2.17. readdirres + * + * union readdirres switch (stat status) { + * case NFS_OK: + * struct { + * entry *entries; + * bool eof; + * } readdirok; + * default: + * void; + * }; + * + * Read the directory contents into the page cache, but don't + * touch them. The actual decoding is done by nfs2_decode_dirent() + * during subsequent nfs_readdir() calls. + */ +static int decode_readdirok(struct xdr_stream *xdr) +{ + return xdr_read_pages(xdr, xdr->buf->page_len); +} + +static int nfs2_xdr_dec_readdirres(struct rpc_rqst *req, + struct xdr_stream *xdr, void *__unused) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS_OK) + goto out_default; + error = decode_readdirok(xdr); +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + +/* + * 2.2.18. statfsres + * + * union statfsres (stat status) { + * case NFS_OK: + * struct { + * unsigned tsize; + * unsigned bsize; + * unsigned blocks; + * unsigned bfree; + * unsigned bavail; + * } info; + * default: + * void; + * }; + */ +static int decode_info(struct xdr_stream *xdr, struct nfs2_fsstat *result) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS_info_sz << 2); + if (unlikely(p == NULL)) + goto out_overflow; + result->tsize = be32_to_cpup(p++); + result->bsize = be32_to_cpup(p++); + result->blocks = be32_to_cpup(p++); + result->bfree = be32_to_cpup(p++); + result->bavail = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs2_fsstat *result) +{ + enum nfs_stat status; + int error; + + error = decode_stat(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS_OK) + goto out_default; + error = decode_info(xdr, result); +out: + return error; +out_default: + return nfs_stat_to_errno(status); +} + + +/* + * We need to translate between nfs status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs_errtbl[] = { + { NFS_OK, 0 }, + { NFSERR_PERM, -EPERM }, + { NFSERR_NOENT, -ENOENT }, + { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_NXIO, -ENXIO }, +/* { NFSERR_EAGAIN, -EAGAIN }, */ + { NFSERR_ACCES, -EACCES }, + { NFSERR_EXIST, -EEXIST }, + { NFSERR_XDEV, -EXDEV }, + { NFSERR_NODEV, -ENODEV }, + { NFSERR_NOTDIR, -ENOTDIR }, + { NFSERR_ISDIR, -EISDIR }, + { NFSERR_INVAL, -EINVAL }, + { NFSERR_FBIG, -EFBIG }, + { NFSERR_NOSPC, -ENOSPC }, + { NFSERR_ROFS, -EROFS }, + { NFSERR_MLINK, -EMLINK }, + { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFSERR_NOTEMPTY, -ENOTEMPTY }, + { NFSERR_DQUOT, -EDQUOT }, + { NFSERR_STALE, -ESTALE }, + { NFSERR_REMOTE, -EREMOTE }, +#ifdef EWFLUSH + { NFSERR_WFLUSH, -EWFLUSH }, +#endif + { NFSERR_BADHANDLE, -EBADHANDLE }, + { NFSERR_NOT_SYNC, -ENOTSYNC }, + { NFSERR_BAD_COOKIE, -EBADCOOKIE }, + { NFSERR_NOTSUPP, -ENOTSUPP }, + { NFSERR_TOOSMALL, -ETOOSMALL }, + { NFSERR_SERVERFAULT, -EREMOTEIO }, + { NFSERR_BADTYPE, -EBADTYPE }, + { NFSERR_JUKEBOX, -EJUKEBOX }, + { -1, -EIO } +}; + +/** + * nfs_stat_to_errno - convert an NFS status code to a local errno + * @status: NFS status code to convert + * + * Returns a local errno value, or -EIO if the NFS status code is + * not recognized. This function is used jointly by NFSv2 and NFSv3. + */ +static int nfs_stat_to_errno(enum nfs_stat status) +{ + int i; + + for (i = 0; nfs_errtbl[i].stat != -1; i++) { + if (nfs_errtbl[i].stat == (int)status) + return nfs_errtbl[i].errno; + } + dprintk("NFS: Unrecognized nfs status value: %u\n", status); + return nfs_errtbl[i].errno; +} + +#define PROC(proc, argtype, restype, timer) \ +[NFSPROC_##proc] = { \ + .p_proc = NFSPROC_##proc, \ + .p_encode = (kxdreproc_t)nfs2_xdr_enc_##argtype, \ + .p_decode = (kxdrdproc_t)nfs2_xdr_dec_##restype, \ + .p_arglen = NFS_##argtype##_sz, \ + .p_replen = NFS_##restype##_sz, \ + .p_timer = timer, \ + .p_statidx = NFSPROC_##proc, \ + .p_name = #proc, \ + } +struct rpc_procinfo nfs_procedures[] = { + PROC(GETATTR, fhandle, attrstat, 1), + PROC(SETATTR, sattrargs, attrstat, 0), + PROC(LOOKUP, diropargs, diropres, 2), + PROC(READLINK, readlinkargs, readlinkres, 3), + PROC(READ, readargs, readres, 3), + PROC(WRITE, writeargs, writeres, 4), + PROC(CREATE, createargs, diropres, 0), + PROC(REMOVE, removeargs, stat, 0), + PROC(RENAME, renameargs, stat, 0), + PROC(LINK, linkargs, stat, 0), + PROC(SYMLINK, symlinkargs, stat, 0), + PROC(MKDIR, createargs, diropres, 0), + PROC(RMDIR, diropargs, stat, 0), + PROC(READDIR, readdirargs, readdirres, 3), + PROC(STATFS, fhandle, statfsres, 0), +}; + +const struct rpc_version nfs_version2 = { + .number = 2, + .nrprocs = ARRAY_SIZE(nfs_procedures), + .procs = nfs_procedures +}; diff --git a/kernel/fs/nfs/nfs3_fs.h b/kernel/fs/nfs/nfs3_fs.h new file mode 100644 index 000000000..e134d6548 --- /dev/null +++ b/kernel/fs/nfs/nfs3_fs.h @@ -0,0 +1,36 @@ +/* + * Copyright (C) 2014 Anna Schumaker. + * + * NFSv3-specific filesystem definitions and declarations + */ +#ifndef __LINUX_FS_NFS_NFS3_FS_H +#define __LINUX_FS_NFS_NFS3_FS_H + +/* + * nfs3acl.c + */ +#ifdef CONFIG_NFS_V3_ACL +extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type); +extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl); +extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t); +extern const struct xattr_handler *nfs3_xattr_handlers[]; +#else +static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) +{ + return 0; +} +#define nfs3_listxattr NULL +#endif /* CONFIG_NFS_V3_ACL */ + +/* nfs3client.c */ +struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *); +struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *, + struct nfs_fattr *, rpc_authflavor_t); + +/* nfs3super.c */ +extern struct nfs_subversion nfs_v3; + +#endif /* __LINUX_FS_NFS_NFS3_FS_H */ diff --git a/kernel/fs/nfs/nfs3acl.c b/kernel/fs/nfs/nfs3acl.c new file mode 100644 index 000000000..1ebe2fc7c --- /dev/null +++ b/kernel/fs/nfs/nfs3acl.c @@ -0,0 +1,296 @@ +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/nfs.h> +#include <linux/nfs3.h> +#include <linux/nfs_fs.h> +#include <linux/posix_acl_xattr.h> +#include <linux/nfsacl.h> + +#include "internal.h" +#include "nfs3_fs.h" + +#define NFSDBG_FACILITY NFSDBG_PROC + +struct posix_acl *nfs3_get_acl(struct inode *inode, int type) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct page *pages[NFSACL_MAXPAGES] = { }; + struct nfs3_getaclargs args = { + .fh = NFS_FH(inode), + /* The xdr layer may allocate pages here. */ + .pages = pages, + }; + struct nfs3_getaclres res = { + NULL, + }; + struct rpc_message msg = { + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status, count; + + if (!nfs_server_capable(inode, NFS_CAP_ACLS)) + return ERR_PTR(-EOPNOTSUPP); + + status = nfs_revalidate_inode(server, inode); + if (status < 0) + return ERR_PTR(status); + + /* + * Only get the access acl when explicitly requested: We don't + * need it for access decisions, and only some applications use + * it. Applications which request the access acl first are not + * penalized from this optimization. + */ + if (type == ACL_TYPE_ACCESS) + args.mask |= NFS_ACLCNT|NFS_ACL; + if (S_ISDIR(inode->i_mode)) + args.mask |= NFS_DFACLCNT|NFS_DFACL; + if (args.mask == 0) + return NULL; + + dprintk("NFS call getacl\n"); + msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_GETACL]; + res.fattr = nfs_alloc_fattr(); + if (res.fattr == NULL) + return ERR_PTR(-ENOMEM); + + status = rpc_call_sync(server->client_acl, &msg, 0); + dprintk("NFS reply getacl: %d\n", status); + + /* pages may have been allocated at the xdr layer. */ + for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++) + __free_page(args.pages[count]); + + switch (status) { + case 0: + status = nfs_refresh_inode(inode, res.fattr); + break; + case -EPFNOSUPPORT: + case -EPROTONOSUPPORT: + dprintk("NFS_V3_ACL extension not supported; disabling\n"); + server->caps &= ~NFS_CAP_ACLS; + case -ENOTSUPP: + status = -EOPNOTSUPP; + default: + goto getout; + } + if ((args.mask & res.mask) != args.mask) { + status = -EIO; + goto getout; + } + + if (res.acl_access != NULL) { + if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) || + res.acl_access->a_count == 0) { + posix_acl_release(res.acl_access); + res.acl_access = NULL; + } + } + + if (res.mask & NFS_ACL) + set_cached_acl(inode, ACL_TYPE_ACCESS, res.acl_access); + else + forget_cached_acl(inode, ACL_TYPE_ACCESS); + + if (res.mask & NFS_DFACL) + set_cached_acl(inode, ACL_TYPE_DEFAULT, res.acl_default); + else + forget_cached_acl(inode, ACL_TYPE_DEFAULT); + + nfs_free_fattr(res.fattr); + if (type == ACL_TYPE_ACCESS) { + posix_acl_release(res.acl_default); + return res.acl_access; + } else { + posix_acl_release(res.acl_access); + return res.acl_default; + } + +getout: + posix_acl_release(res.acl_access); + posix_acl_release(res.acl_default); + nfs_free_fattr(res.fattr); + return ERR_PTR(status); +} + +static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_fattr *fattr; + struct page *pages[NFSACL_MAXPAGES]; + struct nfs3_setaclargs args = { + .inode = inode, + .mask = NFS_ACL, + .acl_access = acl, + .pages = pages, + }; + struct rpc_message msg = { + .rpc_argp = &args, + .rpc_resp = &fattr, + }; + int status = 0; + + if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL)) + goto out; + + status = -EOPNOTSUPP; + if (!nfs_server_capable(inode, NFS_CAP_ACLS)) + goto out; + + /* We are doing this here because XDR marshalling does not + * return any results, it BUGs. */ + status = -ENOSPC; + if (acl != NULL && acl->a_count > NFS_ACL_MAX_ENTRIES) + goto out; + if (dfacl != NULL && dfacl->a_count > NFS_ACL_MAX_ENTRIES) + goto out; + if (S_ISDIR(inode->i_mode)) { + args.mask |= NFS_DFACL; + args.acl_default = dfacl; + args.len = nfsacl_size(acl, dfacl); + } else + args.len = nfsacl_size(acl, NULL); + + if (args.len > NFS_ACL_INLINE_BUFSIZE) { + unsigned int npages = 1 + ((args.len - 1) >> PAGE_SHIFT); + + status = -ENOMEM; + do { + args.pages[args.npages] = alloc_page(GFP_KERNEL); + if (args.pages[args.npages] == NULL) + goto out_freepages; + args.npages++; + } while (args.npages < npages); + } + + dprintk("NFS call setacl\n"); + status = -ENOMEM; + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + goto out_freepages; + + msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_SETACL]; + msg.rpc_resp = fattr; + status = rpc_call_sync(server->client_acl, &msg, 0); + nfs_access_zap_cache(inode); + nfs_zap_acl_cache(inode); + dprintk("NFS reply setacl: %d\n", status); + + switch (status) { + case 0: + status = nfs_refresh_inode(inode, fattr); + set_cached_acl(inode, ACL_TYPE_ACCESS, acl); + set_cached_acl(inode, ACL_TYPE_DEFAULT, dfacl); + break; + case -EPFNOSUPPORT: + case -EPROTONOSUPPORT: + dprintk("NFS_V3_ACL SETACL RPC not supported" + "(will not retry)\n"); + server->caps &= ~NFS_CAP_ACLS; + case -ENOTSUPP: + status = -EOPNOTSUPP; + } + nfs_free_fattr(fattr); +out_freepages: + while (args.npages != 0) { + args.npages--; + __free_page(args.pages[args.npages]); + } +out: + return status; +} + +int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) +{ + int ret; + ret = __nfs3_proc_setacls(inode, acl, dfacl); + return (ret == -EOPNOTSUPP) ? 0 : ret; + +} + +int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + struct posix_acl *alloc = NULL, *dfacl = NULL; + int status; + + if (S_ISDIR(inode->i_mode)) { + switch(type) { + case ACL_TYPE_ACCESS: + alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT); + if (IS_ERR(alloc)) + goto fail; + break; + + case ACL_TYPE_DEFAULT: + dfacl = acl; + alloc = acl = get_acl(inode, ACL_TYPE_ACCESS); + if (IS_ERR(alloc)) + goto fail; + break; + } + } + + if (acl == NULL) { + alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL); + if (IS_ERR(alloc)) + goto fail; + } + status = __nfs3_proc_setacls(inode, acl, dfacl); + posix_acl_release(alloc); + return status; + +fail: + return PTR_ERR(alloc); +} + +const struct xattr_handler *nfs3_xattr_handlers[] = { + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, + NULL, +}; + +static int +nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data, + size_t size, ssize_t *result) +{ + struct posix_acl *acl; + char *p = data + *result; + + acl = get_acl(inode, type); + if (IS_ERR_OR_NULL(acl)) + return 0; + + posix_acl_release(acl); + + *result += strlen(name); + *result += 1; + if (!size) + return 0; + if (*result > size) + return -ERANGE; + + strcpy(p, name); + return 0; +} + +ssize_t +nfs3_listxattr(struct dentry *dentry, char *data, size_t size) +{ + struct inode *inode = d_inode(dentry); + ssize_t result = 0; + int error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, + POSIX_ACL_XATTR_ACCESS, data, size, &result); + if (error) + return error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, + POSIX_ACL_XATTR_DEFAULT, data, size, &result); + if (error) + return error; + return result; +} diff --git a/kernel/fs/nfs/nfs3client.c b/kernel/fs/nfs/nfs3client.c new file mode 100644 index 000000000..9e9fa347a --- /dev/null +++ b/kernel/fs/nfs/nfs3client.c @@ -0,0 +1,107 @@ +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/sunrpc/addr.h> +#include "internal.h" +#include "nfs3_fs.h" + +#ifdef CONFIG_NFS_V3_ACL +static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program }; +static const struct rpc_version *nfsacl_version[] = { + [3] = &nfsacl_version3, +}; + +const struct rpc_program nfsacl_program = { + .name = "nfsacl", + .number = NFS_ACL_PROGRAM, + .nrvers = ARRAY_SIZE(nfsacl_version), + .version = nfsacl_version, + .stats = &nfsacl_rpcstat, +}; + +/* + * Initialise an NFSv3 ACL client connection + */ +static void nfs_init_server_aclclient(struct nfs_server *server) +{ + if (server->flags & NFS_MOUNT_NOACL) + goto out_noacl; + + server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3); + if (IS_ERR(server->client_acl)) + goto out_noacl; + + /* No errors! Assume that Sun nfsacls are supported */ + server->caps |= NFS_CAP_ACLS; + return; + +out_noacl: + server->caps &= ~NFS_CAP_ACLS; +} +#else +static inline void nfs_init_server_aclclient(struct nfs_server *server) +{ + server->flags &= ~NFS_MOUNT_NOACL; + server->caps &= ~NFS_CAP_ACLS; +} +#endif + +struct nfs_server *nfs3_create_server(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct nfs_server *server = nfs_create_server(mount_info, nfs_mod); + /* Create a client RPC handle for the NFS v3 ACL management interface */ + if (!IS_ERR(server)) + nfs_init_server_aclclient(server); + return server; +} + +struct nfs_server *nfs3_clone_server(struct nfs_server *source, + struct nfs_fh *fh, + struct nfs_fattr *fattr, + rpc_authflavor_t flavor) +{ + struct nfs_server *server = nfs_clone_server(source, fh, fattr, flavor); + if (!IS_ERR(server) && !IS_ERR(source->client_acl)) + nfs_init_server_aclclient(server); + return server; +} + +/* + * Set up a pNFS Data Server client over NFSv3. + * + * Return any existing nfs_client that matches server address,port,version + * and minorversion. + * + * For a new nfs_client, use a soft mount (default), a low retrans and a + * low timeout interval so that if a connection is lost, we retry through + * the MDS. + */ +struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, + rpc_authflavor_t au_flavor) +{ + struct nfs_client_initdata cl_init = { + .addr = ds_addr, + .addrlen = ds_addrlen, + .nfs_mod = &nfs_v3, + .proto = ds_proto, + .net = mds_clp->cl_net, + }; + struct rpc_timeout ds_timeout; + struct nfs_client *clp; + char buf[INET6_ADDRSTRLEN + 1]; + + /* fake a hostname because lockd wants it */ + if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + return ERR_PTR(-EINVAL); + cl_init.hostname = buf; + + /* Use the MDS nfs_client cl_ipaddr. */ + nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); + clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, + au_flavor); + + return clp; +} +EXPORT_SYMBOL_GPL(nfs3_set_ds_client); diff --git a/kernel/fs/nfs/nfs3proc.c b/kernel/fs/nfs/nfs3proc.c new file mode 100644 index 000000000..cb28cceef --- /dev/null +++ b/kernel/fs/nfs/nfs3proc.c @@ -0,0 +1,974 @@ +/* + * linux/fs/nfs/nfs3proc.c + * + * Client-side NFSv3 procedures stubs. + * + * Copyright (C) 1997, Olaf Kirch + */ + +#include <linux/mm.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/sunrpc/clnt.h> +#include <linux/slab.h> +#include <linux/nfs.h> +#include <linux/nfs3.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/lockd/bind.h> +#include <linux/nfs_mount.h> +#include <linux/freezer.h> +#include <linux/xattr.h> + +#include "iostat.h" +#include "internal.h" +#include "nfs3_fs.h" + +#define NFSDBG_FACILITY NFSDBG_PROC + +/* A wrapper to handle the EJUKEBOX error messages */ +static int +nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) +{ + int res; + do { + res = rpc_call_sync(clnt, msg, flags); + if (res != -EJUKEBOX) + break; + freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME); + res = -ERESTARTSYS; + } while (!fatal_signal_pending(current)); + return res; +} + +#define rpc_call_sync(clnt, msg, flags) nfs3_rpc_wrapper(clnt, msg, flags) + +static int +nfs3_async_handle_jukebox(struct rpc_task *task, struct inode *inode) +{ + if (task->tk_status != -EJUKEBOX) + return 0; + if (task->tk_status == -EJUKEBOX) + nfs_inc_stats(inode, NFSIOS_DELAY); + task->tk_status = 0; + rpc_restart_call(task); + rpc_delay(task, NFS_JUKEBOX_RETRY_TIME); + return 1; +} + +static int +do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_FSINFO], + .rpc_argp = fhandle, + .rpc_resp = info, + }; + int status; + + dprintk("%s: call fsinfo\n", __func__); + nfs_fattr_init(info->fattr); + status = rpc_call_sync(client, &msg, 0); + dprintk("%s: reply fsinfo: %d\n", __func__, status); + if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) { + msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; + msg.rpc_resp = info->fattr; + status = rpc_call_sync(client, &msg, 0); + dprintk("%s: reply getattr: %d\n", __func__, status); + } + return status; +} + +/* + * Bare-bones access to getattr: this is for nfs_get_root/nfs_get_sb + */ +static int +nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + int status; + + status = do_proc_get_root(server->client, fhandle, info); + if (status && server->nfs_client->cl_rpcclient != server->client) + status = do_proc_get_root(server->nfs_client->cl_rpcclient, fhandle, info); + return status; +} + +/* + * One function for each procedure in the NFS protocol. + */ +static int +nfs3_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR], + .rpc_argp = fhandle, + .rpc_resp = fattr, + }; + int status; + + dprintk("NFS call getattr\n"); + nfs_fattr_init(fattr); + status = rpc_call_sync(server->client, &msg, 0); + dprintk("NFS reply getattr: %d\n", status); + return status; +} + +static int +nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, + struct iattr *sattr) +{ + struct inode *inode = d_inode(dentry); + struct nfs3_sattrargs arg = { + .fh = NFS_FH(inode), + .sattr = sattr, + }; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_SETATTR], + .rpc_argp = &arg, + .rpc_resp = fattr, + }; + int status; + + dprintk("NFS call setattr\n"); + if (sattr->ia_valid & ATTR_FILE) + msg.rpc_cred = nfs_file_cred(sattr->ia_file); + nfs_fattr_init(fattr); + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + if (status == 0) + nfs_setattr_update_inode(inode, sattr, fattr); + dprintk("NFS reply setattr: %d\n", status); + return status; +} + +static int +nfs3_proc_lookup(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + struct nfs3_diropargs arg = { + .fh = NFS_FH(dir), + .name = name->name, + .len = name->len + }; + struct nfs3_diropres res = { + .fh = fhandle, + .fattr = fattr + }; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_LOOKUP], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int status; + + dprintk("NFS call lookup %s\n", name->name); + res.dir_attr = nfs_alloc_fattr(); + if (res.dir_attr == NULL) + return -ENOMEM; + + nfs_fattr_init(fattr); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_refresh_inode(dir, res.dir_attr); + if (status >= 0 && !(fattr->valid & NFS_ATTR_FATTR)) { + msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; + msg.rpc_argp = fhandle; + msg.rpc_resp = fattr; + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + } + nfs_free_fattr(res.dir_attr); + dprintk("NFS reply lookup: %d\n", status); + return status; +} + +static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) +{ + struct nfs3_accessargs arg = { + .fh = NFS_FH(inode), + }; + struct nfs3_accessres res; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS], + .rpc_argp = &arg, + .rpc_resp = &res, + .rpc_cred = entry->cred, + }; + int mode = entry->mask; + int status = -ENOMEM; + + dprintk("NFS call access\n"); + + if (mode & MAY_READ) + arg.access |= NFS3_ACCESS_READ; + if (S_ISDIR(inode->i_mode)) { + if (mode & MAY_WRITE) + arg.access |= NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE; + if (mode & MAY_EXEC) + arg.access |= NFS3_ACCESS_LOOKUP; + } else { + if (mode & MAY_WRITE) + arg.access |= NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND; + if (mode & MAY_EXEC) + arg.access |= NFS3_ACCESS_EXECUTE; + } + + res.fattr = nfs_alloc_fattr(); + if (res.fattr == NULL) + goto out; + + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + nfs_refresh_inode(inode, res.fattr); + if (status == 0) { + entry->mask = 0; + if (res.access & NFS3_ACCESS_READ) + entry->mask |= MAY_READ; + if (res.access & (NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE)) + entry->mask |= MAY_WRITE; + if (res.access & (NFS3_ACCESS_LOOKUP|NFS3_ACCESS_EXECUTE)) + entry->mask |= MAY_EXEC; + } + nfs_free_fattr(res.fattr); +out: + dprintk("NFS reply access: %d\n", status); + return status; +} + +static int nfs3_proc_readlink(struct inode *inode, struct page *page, + unsigned int pgbase, unsigned int pglen) +{ + struct nfs_fattr *fattr; + struct nfs3_readlinkargs args = { + .fh = NFS_FH(inode), + .pgbase = pgbase, + .pglen = pglen, + .pages = &page + }; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_READLINK], + .rpc_argp = &args, + }; + int status = -ENOMEM; + + dprintk("NFS call readlink\n"); + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + goto out; + msg.rpc_resp = fattr; + + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + nfs_refresh_inode(inode, fattr); + nfs_free_fattr(fattr); +out: + dprintk("NFS reply readlink: %d\n", status); + return status; +} + +struct nfs3_createdata { + struct rpc_message msg; + union { + struct nfs3_createargs create; + struct nfs3_mkdirargs mkdir; + struct nfs3_symlinkargs symlink; + struct nfs3_mknodargs mknod; + } arg; + struct nfs3_diropres res; + struct nfs_fh fh; + struct nfs_fattr fattr; + struct nfs_fattr dir_attr; +}; + +static struct nfs3_createdata *nfs3_alloc_createdata(void) +{ + struct nfs3_createdata *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data != NULL) { + data->msg.rpc_argp = &data->arg; + data->msg.rpc_resp = &data->res; + data->res.fh = &data->fh; + data->res.fattr = &data->fattr; + data->res.dir_attr = &data->dir_attr; + nfs_fattr_init(data->res.fattr); + nfs_fattr_init(data->res.dir_attr); + } + return data; +} + +static int nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data) +{ + int status; + + status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0); + nfs_post_op_update_inode(dir, data->res.dir_attr); + if (status == 0) + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + return status; +} + +static void nfs3_free_createdata(struct nfs3_createdata *data) +{ + kfree(data); +} + +/* + * Create a regular file. + */ +static int +nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, + int flags) +{ + struct posix_acl *default_acl, *acl; + struct nfs3_createdata *data; + int status = -ENOMEM; + + dprintk("NFS call create %pd\n", dentry); + + data = nfs3_alloc_createdata(); + if (data == NULL) + goto out; + + data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_CREATE]; + data->arg.create.fh = NFS_FH(dir); + data->arg.create.name = dentry->d_name.name; + data->arg.create.len = dentry->d_name.len; + data->arg.create.sattr = sattr; + + data->arg.create.createmode = NFS3_CREATE_UNCHECKED; + if (flags & O_EXCL) { + data->arg.create.createmode = NFS3_CREATE_EXCLUSIVE; + data->arg.create.verifier[0] = cpu_to_be32(jiffies); + data->arg.create.verifier[1] = cpu_to_be32(current->pid); + } + + status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl); + if (status) + goto out; + + for (;;) { + status = nfs3_do_create(dir, dentry, data); + + if (status != -ENOTSUPP) + break; + /* If the server doesn't support the exclusive creation + * semantics, try again with simple 'guarded' mode. */ + switch (data->arg.create.createmode) { + case NFS3_CREATE_EXCLUSIVE: + data->arg.create.createmode = NFS3_CREATE_GUARDED; + break; + + case NFS3_CREATE_GUARDED: + data->arg.create.createmode = NFS3_CREATE_UNCHECKED; + break; + + case NFS3_CREATE_UNCHECKED: + goto out; + } + nfs_fattr_init(data->res.dir_attr); + nfs_fattr_init(data->res.fattr); + } + + if (status != 0) + goto out_release_acls; + + /* When we created the file with exclusive semantics, make + * sure we set the attributes afterwards. */ + if (data->arg.create.createmode == NFS3_CREATE_EXCLUSIVE) { + dprintk("NFS call setattr (post-create)\n"); + + if (!(sattr->ia_valid & ATTR_ATIME_SET)) + sattr->ia_valid |= ATTR_ATIME; + if (!(sattr->ia_valid & ATTR_MTIME_SET)) + sattr->ia_valid |= ATTR_MTIME; + + /* Note: we could use a guarded setattr here, but I'm + * not sure this buys us anything (and I'd have + * to revamp the NFSv3 XDR code) */ + status = nfs3_proc_setattr(dentry, data->res.fattr, sattr); + nfs_post_op_update_inode(d_inode(dentry), data->res.fattr); + dprintk("NFS reply setattr (post-create): %d\n", status); + if (status != 0) + goto out_release_acls; + } + + status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); + +out_release_acls: + posix_acl_release(acl); + posix_acl_release(default_acl); +out: + nfs3_free_createdata(data); + dprintk("NFS reply create: %d\n", status); + return status; +} + +static int +nfs3_proc_remove(struct inode *dir, struct qstr *name) +{ + struct nfs_removeargs arg = { + .fh = NFS_FH(dir), + .name = *name, + }; + struct nfs_removeres res; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int status = -ENOMEM; + + dprintk("NFS call remove %s\n", name->name); + res.dir_attr = nfs_alloc_fattr(); + if (res.dir_attr == NULL) + goto out; + + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_post_op_update_inode(dir, res.dir_attr); + nfs_free_fattr(res.dir_attr); +out: + dprintk("NFS reply remove: %d\n", status); + return status; +} + +static void +nfs3_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) +{ + msg->rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE]; +} + +static void nfs3_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) +{ + rpc_call_start(task); +} + +static int +nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir) +{ + struct nfs_removeres *res; + if (nfs3_async_handle_jukebox(task, dir)) + return 0; + res = task->tk_msg.rpc_resp; + nfs_post_op_update_inode(dir, res->dir_attr); + return 1; +} + +static void +nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir) +{ + msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME]; +} + +static void nfs3_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data) +{ + rpc_call_start(task); +} + +static int +nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir, + struct inode *new_dir) +{ + struct nfs_renameres *res; + + if (nfs3_async_handle_jukebox(task, old_dir)) + return 0; + res = task->tk_msg.rpc_resp; + + nfs_post_op_update_inode(old_dir, res->old_fattr); + nfs_post_op_update_inode(new_dir, res->new_fattr); + return 1; +} + +static int +nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name) +{ + struct nfs3_linkargs arg = { + .fromfh = NFS_FH(inode), + .tofh = NFS_FH(dir), + .toname = name->name, + .tolen = name->len + }; + struct nfs3_linkres res; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_LINK], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int status = -ENOMEM; + + dprintk("NFS call link %s\n", name->name); + res.fattr = nfs_alloc_fattr(); + res.dir_attr = nfs_alloc_fattr(); + if (res.fattr == NULL || res.dir_attr == NULL) + goto out; + + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + nfs_post_op_update_inode(dir, res.dir_attr); + nfs_post_op_update_inode(inode, res.fattr); +out: + nfs_free_fattr(res.dir_attr); + nfs_free_fattr(res.fattr); + dprintk("NFS reply link: %d\n", status); + return status; +} + +static int +nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, + unsigned int len, struct iattr *sattr) +{ + struct nfs3_createdata *data; + int status = -ENOMEM; + + if (len > NFS3_MAXPATHLEN) + return -ENAMETOOLONG; + + dprintk("NFS call symlink %pd\n", dentry); + + data = nfs3_alloc_createdata(); + if (data == NULL) + goto out; + data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_SYMLINK]; + data->arg.symlink.fromfh = NFS_FH(dir); + data->arg.symlink.fromname = dentry->d_name.name; + data->arg.symlink.fromlen = dentry->d_name.len; + data->arg.symlink.pages = &page; + data->arg.symlink.pathlen = len; + data->arg.symlink.sattr = sattr; + + status = nfs3_do_create(dir, dentry, data); + + nfs3_free_createdata(data); +out: + dprintk("NFS reply symlink: %d\n", status); + return status; +} + +static int +nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) +{ + struct posix_acl *default_acl, *acl; + struct nfs3_createdata *data; + int status = -ENOMEM; + + dprintk("NFS call mkdir %pd\n", dentry); + + data = nfs3_alloc_createdata(); + if (data == NULL) + goto out; + + status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl); + if (status) + goto out; + + data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKDIR]; + data->arg.mkdir.fh = NFS_FH(dir); + data->arg.mkdir.name = dentry->d_name.name; + data->arg.mkdir.len = dentry->d_name.len; + data->arg.mkdir.sattr = sattr; + + status = nfs3_do_create(dir, dentry, data); + if (status != 0) + goto out_release_acls; + + status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); + +out_release_acls: + posix_acl_release(acl); + posix_acl_release(default_acl); +out: + nfs3_free_createdata(data); + dprintk("NFS reply mkdir: %d\n", status); + return status; +} + +static int +nfs3_proc_rmdir(struct inode *dir, struct qstr *name) +{ + struct nfs_fattr *dir_attr; + struct nfs3_diropargs arg = { + .fh = NFS_FH(dir), + .name = name->name, + .len = name->len + }; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_RMDIR], + .rpc_argp = &arg, + }; + int status = -ENOMEM; + + dprintk("NFS call rmdir %s\n", name->name); + dir_attr = nfs_alloc_fattr(); + if (dir_attr == NULL) + goto out; + + msg.rpc_resp = dir_attr; + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_post_op_update_inode(dir, dir_attr); + nfs_free_fattr(dir_attr); +out: + dprintk("NFS reply rmdir: %d\n", status); + return status; +} + +/* + * The READDIR implementation is somewhat hackish - we pass the user buffer + * to the encode function, which installs it in the receive iovec. + * The decode function itself doesn't perform any decoding, it just makes + * sure the reply is syntactically correct. + * + * Also note that this implementation handles both plain readdir and + * readdirplus. + */ +static int +nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, + u64 cookie, struct page **pages, unsigned int count, int plus) +{ + struct inode *dir = d_inode(dentry); + __be32 *verf = NFS_I(dir)->cookieverf; + struct nfs3_readdirargs arg = { + .fh = NFS_FH(dir), + .cookie = cookie, + .verf = {verf[0], verf[1]}, + .plus = plus, + .count = count, + .pages = pages + }; + struct nfs3_readdirres res = { + .verf = verf, + .plus = plus + }; + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_READDIR], + .rpc_argp = &arg, + .rpc_resp = &res, + .rpc_cred = cred + }; + int status = -ENOMEM; + + if (plus) + msg.rpc_proc = &nfs3_procedures[NFS3PROC_READDIRPLUS]; + + dprintk("NFS call readdir%s %d\n", + plus? "plus" : "", (unsigned int) cookie); + + res.dir_attr = nfs_alloc_fattr(); + if (res.dir_attr == NULL) + goto out; + + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + + nfs_invalidate_atime(dir); + nfs_refresh_inode(dir, res.dir_attr); + + nfs_free_fattr(res.dir_attr); +out: + dprintk("NFS reply readdir%s: %d\n", + plus? "plus" : "", status); + return status; +} + +static int +nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, + dev_t rdev) +{ + struct posix_acl *default_acl, *acl; + struct nfs3_createdata *data; + int status = -ENOMEM; + + dprintk("NFS call mknod %pd %u:%u\n", dentry, + MAJOR(rdev), MINOR(rdev)); + + data = nfs3_alloc_createdata(); + if (data == NULL) + goto out; + + status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl); + if (status) + goto out; + + data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKNOD]; + data->arg.mknod.fh = NFS_FH(dir); + data->arg.mknod.name = dentry->d_name.name; + data->arg.mknod.len = dentry->d_name.len; + data->arg.mknod.sattr = sattr; + data->arg.mknod.rdev = rdev; + + switch (sattr->ia_mode & S_IFMT) { + case S_IFBLK: + data->arg.mknod.type = NF3BLK; + break; + case S_IFCHR: + data->arg.mknod.type = NF3CHR; + break; + case S_IFIFO: + data->arg.mknod.type = NF3FIFO; + break; + case S_IFSOCK: + data->arg.mknod.type = NF3SOCK; + break; + default: + status = -EINVAL; + goto out; + } + + status = nfs3_do_create(dir, dentry, data); + if (status != 0) + goto out_release_acls; + + status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); + +out_release_acls: + posix_acl_release(acl); + posix_acl_release(default_acl); +out: + nfs3_free_createdata(data); + dprintk("NFS reply mknod: %d\n", status); + return status; +} + +static int +nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsstat *stat) +{ + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_FSSTAT], + .rpc_argp = fhandle, + .rpc_resp = stat, + }; + int status; + + dprintk("NFS call fsstat\n"); + nfs_fattr_init(stat->fattr); + status = rpc_call_sync(server->client, &msg, 0); + dprintk("NFS reply fsstat: %d\n", status); + return status; +} + +static int +do_proc_fsinfo(struct rpc_clnt *client, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_FSINFO], + .rpc_argp = fhandle, + .rpc_resp = info, + }; + int status; + + dprintk("NFS call fsinfo\n"); + nfs_fattr_init(info->fattr); + status = rpc_call_sync(client, &msg, 0); + dprintk("NFS reply fsinfo: %d\n", status); + return status; +} + +/* + * Bare-bones access to fsinfo: this is for nfs_get_root/nfs_get_sb via + * nfs_create_server + */ +static int +nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + int status; + + status = do_proc_fsinfo(server->client, fhandle, info); + if (status && server->nfs_client->cl_rpcclient != server->client) + status = do_proc_fsinfo(server->nfs_client->cl_rpcclient, fhandle, info); + return status; +} + +static int +nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_pathconf *info) +{ + struct rpc_message msg = { + .rpc_proc = &nfs3_procedures[NFS3PROC_PATHCONF], + .rpc_argp = fhandle, + .rpc_resp = info, + }; + int status; + + dprintk("NFS call pathconf\n"); + nfs_fattr_init(info->fattr); + status = rpc_call_sync(server->client, &msg, 0); + dprintk("NFS reply pathconf: %d\n", status); + return status; +} + +static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + struct inode *inode = hdr->inode; + + if (hdr->pgio_done_cb != NULL) + return hdr->pgio_done_cb(task, hdr); + + if (nfs3_async_handle_jukebox(task, inode)) + return -EAGAIN; + + nfs_invalidate_atime(inode); + nfs_refresh_inode(inode, &hdr->fattr); + return 0; +} + +static void nfs3_proc_read_setup(struct nfs_pgio_header *hdr, + struct rpc_message *msg) +{ + msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ]; +} + +static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + rpc_call_start(task); + return 0; +} + +static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + struct inode *inode = hdr->inode; + + if (hdr->pgio_done_cb != NULL) + return hdr->pgio_done_cb(task, hdr); + + if (nfs3_async_handle_jukebox(task, inode)) + return -EAGAIN; + if (task->tk_status >= 0) + nfs_writeback_update_inode(hdr); + return 0; +} + +static void nfs3_proc_write_setup(struct nfs_pgio_header *hdr, + struct rpc_message *msg) +{ + msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE]; +} + +static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) +{ + rpc_call_start(task); +} + +static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data) +{ + if (data->commit_done_cb != NULL) + return data->commit_done_cb(task, data); + + if (nfs3_async_handle_jukebox(task, data->inode)) + return -EAGAIN; + nfs_refresh_inode(data->inode, data->res.fattr); + return 0; +} + +static void nfs3_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg) +{ + msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT]; +} + +static int +nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = file_inode(filp); + + return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl); +} + +static int nfs3_have_delegation(struct inode *inode, fmode_t flags) +{ + return 0; +} + +static int nfs3_return_delegation(struct inode *inode) +{ + nfs_wb_all(inode); + return 0; +} + +static const struct inode_operations nfs3_dir_inode_operations = { + .create = nfs_create, + .lookup = nfs_lookup, + .link = nfs_link, + .unlink = nfs_unlink, + .symlink = nfs_symlink, + .mkdir = nfs_mkdir, + .rmdir = nfs_rmdir, + .mknod = nfs_mknod, + .rename = nfs_rename, + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +#ifdef CONFIG_NFS_V3_ACL + .listxattr = nfs3_listxattr, + .getxattr = generic_getxattr, + .setxattr = generic_setxattr, + .removexattr = generic_removexattr, + .get_acl = nfs3_get_acl, + .set_acl = nfs3_set_acl, +#endif +}; + +static const struct inode_operations nfs3_file_inode_operations = { + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +#ifdef CONFIG_NFS_V3_ACL + .listxattr = nfs3_listxattr, + .getxattr = generic_getxattr, + .setxattr = generic_setxattr, + .removexattr = generic_removexattr, + .get_acl = nfs3_get_acl, + .set_acl = nfs3_set_acl, +#endif +}; + +const struct nfs_rpc_ops nfs_v3_clientops = { + .version = 3, /* protocol version */ + .dentry_ops = &nfs_dentry_operations, + .dir_inode_ops = &nfs3_dir_inode_operations, + .file_inode_ops = &nfs3_file_inode_operations, + .file_ops = &nfs_file_operations, + .getroot = nfs3_proc_get_root, + .submount = nfs_submount, + .try_mount = nfs_try_mount, + .getattr = nfs3_proc_getattr, + .setattr = nfs3_proc_setattr, + .lookup = nfs3_proc_lookup, + .access = nfs3_proc_access, + .readlink = nfs3_proc_readlink, + .create = nfs3_proc_create, + .remove = nfs3_proc_remove, + .unlink_setup = nfs3_proc_unlink_setup, + .unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare, + .unlink_done = nfs3_proc_unlink_done, + .rename_setup = nfs3_proc_rename_setup, + .rename_rpc_prepare = nfs3_proc_rename_rpc_prepare, + .rename_done = nfs3_proc_rename_done, + .link = nfs3_proc_link, + .symlink = nfs3_proc_symlink, + .mkdir = nfs3_proc_mkdir, + .rmdir = nfs3_proc_rmdir, + .readdir = nfs3_proc_readdir, + .mknod = nfs3_proc_mknod, + .statfs = nfs3_proc_statfs, + .fsinfo = nfs3_proc_fsinfo, + .pathconf = nfs3_proc_pathconf, + .decode_dirent = nfs3_decode_dirent, + .pgio_rpc_prepare = nfs3_proc_pgio_rpc_prepare, + .read_setup = nfs3_proc_read_setup, + .read_done = nfs3_read_done, + .write_setup = nfs3_proc_write_setup, + .write_done = nfs3_write_done, + .commit_setup = nfs3_proc_commit_setup, + .commit_rpc_prepare = nfs3_proc_commit_rpc_prepare, + .commit_done = nfs3_commit_done, + .lock = nfs3_proc_lock, + .clear_acl_cache = forget_all_cached_acls, + .close_context = nfs_close_context, + .have_delegation = nfs3_have_delegation, + .return_delegation = nfs3_return_delegation, + .alloc_client = nfs_alloc_client, + .init_client = nfs_init_client, + .free_client = nfs_free_client, + .create_server = nfs3_create_server, + .clone_server = nfs3_clone_server, +}; diff --git a/kernel/fs/nfs/nfs3super.c b/kernel/fs/nfs/nfs3super.c new file mode 100644 index 000000000..5c4394e46 --- /dev/null +++ b/kernel/fs/nfs/nfs3super.c @@ -0,0 +1,35 @@ +/* + * Copyright (c) 2012 Netapp, Inc. All rights reserved. + */ +#include <linux/module.h> +#include <linux/nfs_fs.h> +#include "internal.h" +#include "nfs3_fs.h" +#include "nfs.h" + +struct nfs_subversion nfs_v3 = { + .owner = THIS_MODULE, + .nfs_fs = &nfs_fs_type, + .rpc_vers = &nfs_version3, + .rpc_ops = &nfs_v3_clientops, + .sops = &nfs_sops, +#ifdef CONFIG_NFS_V3_ACL + .xattr = nfs3_xattr_handlers, +#endif +}; + +static int __init init_nfs_v3(void) +{ + register_nfs_version(&nfs_v3); + return 0; +} + +static void __exit exit_nfs_v3(void) +{ + unregister_nfs_version(&nfs_v3); +} + +MODULE_LICENSE("GPL"); + +module_init(init_nfs_v3); +module_exit(exit_nfs_v3); diff --git a/kernel/fs/nfs/nfs3xdr.c b/kernel/fs/nfs/nfs3xdr.c new file mode 100644 index 000000000..53852a4bd --- /dev/null +++ b/kernel/fs/nfs/nfs3xdr.c @@ -0,0 +1,2564 @@ +/* + * linux/fs/nfs/nfs3xdr.c + * + * XDR functions to encode/decode NFSv3 RPC arguments and results. + * + * Copyright (C) 1996, 1997 Olaf Kirch + */ + +#include <linux/param.h> +#include <linux/time.h> +#include <linux/mm.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/pagemap.h> +#include <linux/proc_fs.h> +#include <linux/kdev_t.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs3.h> +#include <linux/nfs_fs.h> +#include <linux/nfsacl.h> +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_XDR + +/* Mapping from NFS error code to "errno" error code. */ +#define errno_NFSERR_IO EIO + +/* + * Declare the space requirements for NFS arguments and replies as + * number of 32bit-words + */ +#define NFS3_fhandle_sz (1+16) +#define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */ +#define NFS3_sattr_sz (15) +#define NFS3_filename_sz (1+(NFS3_MAXNAMLEN>>2)) +#define NFS3_path_sz (1+(NFS3_MAXPATHLEN>>2)) +#define NFS3_fattr_sz (21) +#define NFS3_cookieverf_sz (NFS3_COOKIEVERFSIZE>>2) +#define NFS3_wcc_attr_sz (6) +#define NFS3_pre_op_attr_sz (1+NFS3_wcc_attr_sz) +#define NFS3_post_op_attr_sz (1+NFS3_fattr_sz) +#define NFS3_wcc_data_sz (NFS3_pre_op_attr_sz+NFS3_post_op_attr_sz) +#define NFS3_diropargs_sz (NFS3_fh_sz+NFS3_filename_sz) + +#define NFS3_getattrargs_sz (NFS3_fh_sz) +#define NFS3_setattrargs_sz (NFS3_fh_sz+NFS3_sattr_sz+3) +#define NFS3_lookupargs_sz (NFS3_fh_sz+NFS3_filename_sz) +#define NFS3_accessargs_sz (NFS3_fh_sz+1) +#define NFS3_readlinkargs_sz (NFS3_fh_sz) +#define NFS3_readargs_sz (NFS3_fh_sz+3) +#define NFS3_writeargs_sz (NFS3_fh_sz+5) +#define NFS3_createargs_sz (NFS3_diropargs_sz+NFS3_sattr_sz) +#define NFS3_mkdirargs_sz (NFS3_diropargs_sz+NFS3_sattr_sz) +#define NFS3_symlinkargs_sz (NFS3_diropargs_sz+1+NFS3_sattr_sz) +#define NFS3_mknodargs_sz (NFS3_diropargs_sz+2+NFS3_sattr_sz) +#define NFS3_removeargs_sz (NFS3_fh_sz+NFS3_filename_sz) +#define NFS3_renameargs_sz (NFS3_diropargs_sz+NFS3_diropargs_sz) +#define NFS3_linkargs_sz (NFS3_fh_sz+NFS3_diropargs_sz) +#define NFS3_readdirargs_sz (NFS3_fh_sz+NFS3_cookieverf_sz+3) +#define NFS3_readdirplusargs_sz (NFS3_fh_sz+NFS3_cookieverf_sz+4) +#define NFS3_commitargs_sz (NFS3_fh_sz+3) + +#define NFS3_getattrres_sz (1+NFS3_fattr_sz) +#define NFS3_setattrres_sz (1+NFS3_wcc_data_sz) +#define NFS3_removeres_sz (NFS3_setattrres_sz) +#define NFS3_lookupres_sz (1+NFS3_fh_sz+(2 * NFS3_post_op_attr_sz)) +#define NFS3_accessres_sz (1+NFS3_post_op_attr_sz+1) +#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1) +#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3) +#define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4) +#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) +#define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz)) +#define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) +#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2) +#define NFS3_fsstatres_sz (1+NFS3_post_op_attr_sz+13) +#define NFS3_fsinfores_sz (1+NFS3_post_op_attr_sz+12) +#define NFS3_pathconfres_sz (1+NFS3_post_op_attr_sz+6) +#define NFS3_commitres_sz (1+NFS3_wcc_data_sz+2) + +#define ACL3_getaclargs_sz (NFS3_fh_sz+1) +#define ACL3_setaclargs_sz (NFS3_fh_sz+1+ \ + XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)) +#define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+ \ + XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)) +#define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz) + +static int nfs3_stat_to_errno(enum nfs_stat); + +/* + * Map file type to S_IFMT bits + */ +static const umode_t nfs_type2fmt[] = { + [NF3BAD] = 0, + [NF3REG] = S_IFREG, + [NF3DIR] = S_IFDIR, + [NF3BLK] = S_IFBLK, + [NF3CHR] = S_IFCHR, + [NF3LNK] = S_IFLNK, + [NF3SOCK] = S_IFSOCK, + [NF3FIFO] = S_IFIFO, +}; + +/* + * While encoding arguments, set up the reply buffer in advance to + * receive reply data directly into the page cache. + */ +static void prepare_reply_buffer(struct rpc_rqst *req, struct page **pages, + unsigned int base, unsigned int len, + unsigned int bufsize) +{ + struct rpc_auth *auth = req->rq_cred->cr_auth; + unsigned int replen; + + replen = RPC_REPHDRSIZE + auth->au_rslack + bufsize; + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, pages, base, len); +} + +/* + * Handle decode buffer overflows out-of-line. + */ +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("NFS: %s prematurely hit the end of our receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); +} + + +/* + * Encode/decode NFSv3 basic data types + * + * Basic NFSv3 data types are defined in section 2.5 of RFC 1813: + * "NFS Version 3 Protocol Specification". + * + * Not all basic data types have their own encoding and decoding + * functions. For run-time efficiency, some data types are encoded + * or decoded inline. + */ + +static void encode_uint32(struct xdr_stream *xdr, u32 value) +{ + __be32 *p = xdr_reserve_space(xdr, 4); + *p = cpu_to_be32(value); +} + +static int decode_uint32(struct xdr_stream *xdr, u32 *value) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + *value = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_uint64(struct xdr_stream *xdr, u64 *value) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(p == NULL)) + goto out_overflow; + xdr_decode_hyper(p, value); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * fileid3 + * + * typedef uint64 fileid3; + */ +static __be32 *xdr_decode_fileid3(__be32 *p, u64 *fileid) +{ + return xdr_decode_hyper(p, fileid); +} + +static int decode_fileid3(struct xdr_stream *xdr, u64 *fileid) +{ + return decode_uint64(xdr, fileid); +} + +/* + * filename3 + * + * typedef string filename3<>; + */ +static void encode_filename3(struct xdr_stream *xdr, + const char *name, u32 length) +{ + __be32 *p; + + WARN_ON_ONCE(length > NFS3_MAXNAMLEN); + p = xdr_reserve_space(xdr, 4 + length); + xdr_encode_opaque(p, name, length); +} + +static int decode_inline_filename3(struct xdr_stream *xdr, + const char **name, u32 *length) +{ + __be32 *p; + u32 count; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + count = be32_to_cpup(p); + if (count > NFS3_MAXNAMLEN) + goto out_nametoolong; + p = xdr_inline_decode(xdr, count); + if (unlikely(p == NULL)) + goto out_overflow; + *name = (const char *)p; + *length = count; + return 0; + +out_nametoolong: + dprintk("NFS: returned filename too long: %u\n", count); + return -ENAMETOOLONG; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * nfspath3 + * + * typedef string nfspath3<>; + */ +static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages, + const u32 length) +{ + encode_uint32(xdr, length); + xdr_write_pages(xdr, pages, 0, length); +} + +static int decode_nfspath3(struct xdr_stream *xdr) +{ + u32 recvd, count; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + count = be32_to_cpup(p); + if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN)) + goto out_nametoolong; + recvd = xdr_read_pages(xdr, count); + if (unlikely(count > recvd)) + goto out_cheating; + xdr_terminate_string(xdr->buf, count); + return 0; + +out_nametoolong: + dprintk("NFS: returned pathname too long: %u\n", count); + return -ENAMETOOLONG; +out_cheating: + dprintk("NFS: server cheating in pathname result: " + "count %u > recvd %u\n", count, recvd); + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * cookie3 + * + * typedef uint64 cookie3 + */ +static __be32 *xdr_encode_cookie3(__be32 *p, u64 cookie) +{ + return xdr_encode_hyper(p, cookie); +} + +static int decode_cookie3(struct xdr_stream *xdr, u64 *cookie) +{ + return decode_uint64(xdr, cookie); +} + +/* + * cookieverf3 + * + * typedef opaque cookieverf3[NFS3_COOKIEVERFSIZE]; + */ +static __be32 *xdr_encode_cookieverf3(__be32 *p, const __be32 *verifier) +{ + memcpy(p, verifier, NFS3_COOKIEVERFSIZE); + return p + XDR_QUADLEN(NFS3_COOKIEVERFSIZE); +} + +static int decode_cookieverf3(struct xdr_stream *xdr, __be32 *verifier) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); + if (unlikely(p == NULL)) + goto out_overflow; + memcpy(verifier, p, NFS3_COOKIEVERFSIZE); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * createverf3 + * + * typedef opaque createverf3[NFS3_CREATEVERFSIZE]; + */ +static void encode_createverf3(struct xdr_stream *xdr, const __be32 *verifier) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, NFS3_CREATEVERFSIZE); + memcpy(p, verifier, NFS3_CREATEVERFSIZE); +} + +static int decode_writeverf3(struct xdr_stream *xdr, struct nfs_write_verifier *verifier) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE); + if (unlikely(p == NULL)) + goto out_overflow; + memcpy(verifier->data, p, NFS3_WRITEVERFSIZE); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * size3 + * + * typedef uint64 size3; + */ +static __be32 *xdr_decode_size3(__be32 *p, u64 *size) +{ + return xdr_decode_hyper(p, size); +} + +/* + * nfsstat3 + * + * enum nfsstat3 { + * NFS3_OK = 0, + * ... + * } + */ +#define NFS3_OK NFS_OK + +static int decode_nfsstat3(struct xdr_stream *xdr, enum nfs_stat *status) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + *status = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * ftype3 + * + * enum ftype3 { + * NF3REG = 1, + * NF3DIR = 2, + * NF3BLK = 3, + * NF3CHR = 4, + * NF3LNK = 5, + * NF3SOCK = 6, + * NF3FIFO = 7 + * }; + */ +static void encode_ftype3(struct xdr_stream *xdr, const u32 type) +{ + encode_uint32(xdr, type); +} + +static __be32 *xdr_decode_ftype3(__be32 *p, umode_t *mode) +{ + u32 type; + + type = be32_to_cpup(p++); + if (type > NF3FIFO) + type = NF3NON; + *mode = nfs_type2fmt[type]; + return p; +} + +/* + * specdata3 + * + * struct specdata3 { + * uint32 specdata1; + * uint32 specdata2; + * }; + */ +static void encode_specdata3(struct xdr_stream *xdr, const dev_t rdev) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 8); + *p++ = cpu_to_be32(MAJOR(rdev)); + *p = cpu_to_be32(MINOR(rdev)); +} + +static __be32 *xdr_decode_specdata3(__be32 *p, dev_t *rdev) +{ + unsigned int major, minor; + + major = be32_to_cpup(p++); + minor = be32_to_cpup(p++); + *rdev = MKDEV(major, minor); + if (MAJOR(*rdev) != major || MINOR(*rdev) != minor) + *rdev = 0; + return p; +} + +/* + * nfs_fh3 + * + * struct nfs_fh3 { + * opaque data<NFS3_FHSIZE>; + * }; + */ +static void encode_nfs_fh3(struct xdr_stream *xdr, const struct nfs_fh *fh) +{ + __be32 *p; + + WARN_ON_ONCE(fh->size > NFS3_FHSIZE); + p = xdr_reserve_space(xdr, 4 + fh->size); + xdr_encode_opaque(p, fh->data, fh->size); +} + +static int decode_nfs_fh3(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + u32 length; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + length = be32_to_cpup(p++); + if (unlikely(length > NFS3_FHSIZE)) + goto out_toobig; + p = xdr_inline_decode(xdr, length); + if (unlikely(p == NULL)) + goto out_overflow; + fh->size = length; + memcpy(fh->data, p, length); + return 0; +out_toobig: + dprintk("NFS: file handle size (%u) too big\n", length); + return -E2BIG; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static void zero_nfs_fh3(struct nfs_fh *fh) +{ + memset(fh, 0, sizeof(*fh)); +} + +/* + * nfstime3 + * + * struct nfstime3 { + * uint32 seconds; + * uint32 nseconds; + * }; + */ +static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep) +{ + *p++ = cpu_to_be32(timep->tv_sec); + *p++ = cpu_to_be32(timep->tv_nsec); + return p; +} + +static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep) +{ + timep->tv_sec = be32_to_cpup(p++); + timep->tv_nsec = be32_to_cpup(p++); + return p; +} + +/* + * sattr3 + * + * enum time_how { + * DONT_CHANGE = 0, + * SET_TO_SERVER_TIME = 1, + * SET_TO_CLIENT_TIME = 2 + * }; + * + * union set_mode3 switch (bool set_it) { + * case TRUE: + * mode3 mode; + * default: + * void; + * }; + * + * union set_uid3 switch (bool set_it) { + * case TRUE: + * uid3 uid; + * default: + * void; + * }; + * + * union set_gid3 switch (bool set_it) { + * case TRUE: + * gid3 gid; + * default: + * void; + * }; + * + * union set_size3 switch (bool set_it) { + * case TRUE: + * size3 size; + * default: + * void; + * }; + * + * union set_atime switch (time_how set_it) { + * case SET_TO_CLIENT_TIME: + * nfstime3 atime; + * default: + * void; + * }; + * + * union set_mtime switch (time_how set_it) { + * case SET_TO_CLIENT_TIME: + * nfstime3 mtime; + * default: + * void; + * }; + * + * struct sattr3 { + * set_mode3 mode; + * set_uid3 uid; + * set_gid3 gid; + * set_size3 size; + * set_atime atime; + * set_mtime mtime; + * }; + */ +static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) +{ + u32 nbytes; + __be32 *p; + + /* + * In order to make only a single xdr_reserve_space() call, + * pre-compute the total number of bytes to be reserved. + * Six boolean values, one for each set_foo field, are always + * present in the encoded result, so start there. + */ + nbytes = 6 * 4; + if (attr->ia_valid & ATTR_MODE) + nbytes += 4; + if (attr->ia_valid & ATTR_UID) + nbytes += 4; + if (attr->ia_valid & ATTR_GID) + nbytes += 4; + if (attr->ia_valid & ATTR_SIZE) + nbytes += 8; + if (attr->ia_valid & ATTR_ATIME_SET) + nbytes += 8; + if (attr->ia_valid & ATTR_MTIME_SET) + nbytes += 8; + p = xdr_reserve_space(xdr, nbytes); + + if (attr->ia_valid & ATTR_MODE) { + *p++ = xdr_one; + *p++ = cpu_to_be32(attr->ia_mode & S_IALLUGO); + } else + *p++ = xdr_zero; + + if (attr->ia_valid & ATTR_UID) { + *p++ = xdr_one; + *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid)); + } else + *p++ = xdr_zero; + + if (attr->ia_valid & ATTR_GID) { + *p++ = xdr_one; + *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid)); + } else + *p++ = xdr_zero; + + if (attr->ia_valid & ATTR_SIZE) { + *p++ = xdr_one; + p = xdr_encode_hyper(p, (u64)attr->ia_size); + } else + *p++ = xdr_zero; + + if (attr->ia_valid & ATTR_ATIME_SET) { + *p++ = xdr_two; + p = xdr_encode_nfstime3(p, &attr->ia_atime); + } else if (attr->ia_valid & ATTR_ATIME) { + *p++ = xdr_one; + } else + *p++ = xdr_zero; + + if (attr->ia_valid & ATTR_MTIME_SET) { + *p++ = xdr_two; + xdr_encode_nfstime3(p, &attr->ia_mtime); + } else if (attr->ia_valid & ATTR_MTIME) { + *p = xdr_one; + } else + *p = xdr_zero; +} + +/* + * fattr3 + * + * struct fattr3 { + * ftype3 type; + * mode3 mode; + * uint32 nlink; + * uid3 uid; + * gid3 gid; + * size3 size; + * size3 used; + * specdata3 rdev; + * uint64 fsid; + * fileid3 fileid; + * nfstime3 atime; + * nfstime3 mtime; + * nfstime3 ctime; + * }; + */ +static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + umode_t fmode; + __be32 *p; + + p = xdr_inline_decode(xdr, NFS3_fattr_sz << 2); + if (unlikely(p == NULL)) + goto out_overflow; + + p = xdr_decode_ftype3(p, &fmode); + + fattr->mode = (be32_to_cpup(p++) & ~S_IFMT) | fmode; + fattr->nlink = be32_to_cpup(p++); + fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++)); + if (!uid_valid(fattr->uid)) + goto out_uid; + fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++)); + if (!gid_valid(fattr->gid)) + goto out_gid; + + p = xdr_decode_size3(p, &fattr->size); + p = xdr_decode_size3(p, &fattr->du.nfs3.used); + p = xdr_decode_specdata3(p, &fattr->rdev); + + p = xdr_decode_hyper(p, &fattr->fsid.major); + fattr->fsid.minor = 0; + + p = xdr_decode_fileid3(p, &fattr->fileid); + p = xdr_decode_nfstime3(p, &fattr->atime); + p = xdr_decode_nfstime3(p, &fattr->mtime); + xdr_decode_nfstime3(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + + fattr->valid |= NFS_ATTR_FATTR_V3; + return 0; +out_uid: + dprintk("NFS: returned invalid uid\n"); + return -EINVAL; +out_gid: + dprintk("NFS: returned invalid gid\n"); + return -EINVAL; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * post_op_attr + * + * union post_op_attr switch (bool attributes_follow) { + * case TRUE: + * fattr3 attributes; + * case FALSE: + * void; + * }; + */ +static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p != xdr_zero) + return decode_fattr3(xdr, fattr); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * wcc_attr + * struct wcc_attr { + * size3 size; + * nfstime3 mtime; + * nfstime3 ctime; + * }; + */ +static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS3_wcc_attr_sz << 2); + if (unlikely(p == NULL)) + goto out_overflow; + + fattr->valid |= NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PRECHANGE + | NFS_ATTR_FATTR_PREMTIME + | NFS_ATTR_FATTR_PRECTIME; + + p = xdr_decode_size3(p, &fattr->pre_size); + p = xdr_decode_nfstime3(p, &fattr->pre_mtime); + xdr_decode_nfstime3(p, &fattr->pre_ctime); + fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime); + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * pre_op_attr + * union pre_op_attr switch (bool attributes_follow) { + * case TRUE: + * wcc_attr attributes; + * case FALSE: + * void; + * }; + * + * wcc_data + * + * struct wcc_data { + * pre_op_attr before; + * post_op_attr after; + * }; + */ +static int decode_pre_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p != xdr_zero) + return decode_wcc_attr(xdr, fattr); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_wcc_data(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + int error; + + error = decode_pre_op_attr(xdr, fattr); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, fattr); +out: + return error; +} + +/* + * post_op_fh3 + * + * union post_op_fh3 switch (bool handle_follows) { + * case TRUE: + * nfs_fh3 handle; + * case FALSE: + * void; + * }; + */ +static int decode_post_op_fh3(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p != xdr_zero) + return decode_nfs_fh3(xdr, fh); + zero_nfs_fh3(fh); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * diropargs3 + * + * struct diropargs3 { + * nfs_fh3 dir; + * filename3 name; + * }; + */ +static void encode_diropargs3(struct xdr_stream *xdr, const struct nfs_fh *fh, + const char *name, u32 length) +{ + encode_nfs_fh3(xdr, fh); + encode_filename3(xdr, name, length); +} + + +/* + * NFSv3 XDR encode functions + * + * NFSv3 argument types are defined in section 3.3 of RFC 1813: + * "NFS Version 3 Protocol Specification". + */ + +/* + * 3.3.1 GETATTR3args + * + * struct GETATTR3args { + * nfs_fh3 object; + * }; + */ +static void nfs3_xdr_enc_getattr3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_fh *fh) +{ + encode_nfs_fh3(xdr, fh); +} + +/* + * 3.3.2 SETATTR3args + * + * union sattrguard3 switch (bool check) { + * case TRUE: + * nfstime3 obj_ctime; + * case FALSE: + * void; + * }; + * + * struct SETATTR3args { + * nfs_fh3 object; + * sattr3 new_attributes; + * sattrguard3 guard; + * }; + */ +static void encode_sattrguard3(struct xdr_stream *xdr, + const struct nfs3_sattrargs *args) +{ + __be32 *p; + + if (args->guard) { + p = xdr_reserve_space(xdr, 4 + 8); + *p++ = xdr_one; + xdr_encode_nfstime3(p, &args->guardtime); + } else { + p = xdr_reserve_space(xdr, 4); + *p = xdr_zero; + } +} + +static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_sattrargs *args) +{ + encode_nfs_fh3(xdr, args->fh); + encode_sattr3(xdr, args->sattr); + encode_sattrguard3(xdr, args); +} + +/* + * 3.3.3 LOOKUP3args + * + * struct LOOKUP3args { + * diropargs3 what; + * }; + */ +static void nfs3_xdr_enc_lookup3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_diropargs *args) +{ + encode_diropargs3(xdr, args->fh, args->name, args->len); +} + +/* + * 3.3.4 ACCESS3args + * + * struct ACCESS3args { + * nfs_fh3 object; + * uint32 access; + * }; + */ +static void encode_access3args(struct xdr_stream *xdr, + const struct nfs3_accessargs *args) +{ + encode_nfs_fh3(xdr, args->fh); + encode_uint32(xdr, args->access); +} + +static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_accessargs *args) +{ + encode_access3args(xdr, args); +} + +/* + * 3.3.5 READLINK3args + * + * struct READLINK3args { + * nfs_fh3 symlink; + * }; + */ +static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_readlinkargs *args) +{ + encode_nfs_fh3(xdr, args->fh); + prepare_reply_buffer(req, args->pages, args->pgbase, + args->pglen, NFS3_readlinkres_sz); +} + +/* + * 3.3.6 READ3args + * + * struct READ3args { + * nfs_fh3 file; + * offset3 offset; + * count3 count; + * }; + */ +static void encode_read3args(struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + __be32 *p; + + encode_nfs_fh3(xdr, args->fh); + + p = xdr_reserve_space(xdr, 8 + 4); + p = xdr_encode_hyper(p, args->offset); + *p = cpu_to_be32(args->count); +} + +static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + encode_read3args(xdr, args); + prepare_reply_buffer(req, args->pages, args->pgbase, + args->count, NFS3_readres_sz); + req->rq_rcv_buf.flags |= XDRBUF_READ; +} + +/* + * 3.3.7 WRITE3args + * + * enum stable_how { + * UNSTABLE = 0, + * DATA_SYNC = 1, + * FILE_SYNC = 2 + * }; + * + * struct WRITE3args { + * nfs_fh3 file; + * offset3 offset; + * count3 count; + * stable_how stable; + * opaque data<>; + * }; + */ +static void encode_write3args(struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + __be32 *p; + + encode_nfs_fh3(xdr, args->fh); + + p = xdr_reserve_space(xdr, 8 + 4 + 4 + 4); + p = xdr_encode_hyper(p, args->offset); + *p++ = cpu_to_be32(args->count); + *p++ = cpu_to_be32(args->stable); + *p = cpu_to_be32(args->count); + xdr_write_pages(xdr, args->pages, args->pgbase, args->count); +} + +static void nfs3_xdr_enc_write3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_pgio_args *args) +{ + encode_write3args(xdr, args); + xdr->buf->flags |= XDRBUF_WRITE; +} + +/* + * 3.3.8 CREATE3args + * + * enum createmode3 { + * UNCHECKED = 0, + * GUARDED = 1, + * EXCLUSIVE = 2 + * }; + * + * union createhow3 switch (createmode3 mode) { + * case UNCHECKED: + * case GUARDED: + * sattr3 obj_attributes; + * case EXCLUSIVE: + * createverf3 verf; + * }; + * + * struct CREATE3args { + * diropargs3 where; + * createhow3 how; + * }; + */ +static void encode_createhow3(struct xdr_stream *xdr, + const struct nfs3_createargs *args) +{ + encode_uint32(xdr, args->createmode); + switch (args->createmode) { + case NFS3_CREATE_UNCHECKED: + case NFS3_CREATE_GUARDED: + encode_sattr3(xdr, args->sattr); + break; + case NFS3_CREATE_EXCLUSIVE: + encode_createverf3(xdr, args->verifier); + break; + default: + BUG(); + } +} + +static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_createargs *args) +{ + encode_diropargs3(xdr, args->fh, args->name, args->len); + encode_createhow3(xdr, args); +} + +/* + * 3.3.9 MKDIR3args + * + * struct MKDIR3args { + * diropargs3 where; + * sattr3 attributes; + * }; + */ +static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_mkdirargs *args) +{ + encode_diropargs3(xdr, args->fh, args->name, args->len); + encode_sattr3(xdr, args->sattr); +} + +/* + * 3.3.10 SYMLINK3args + * + * struct symlinkdata3 { + * sattr3 symlink_attributes; + * nfspath3 symlink_data; + * }; + * + * struct SYMLINK3args { + * diropargs3 where; + * symlinkdata3 symlink; + * }; + */ +static void encode_symlinkdata3(struct xdr_stream *xdr, + const struct nfs3_symlinkargs *args) +{ + encode_sattr3(xdr, args->sattr); + encode_nfspath3(xdr, args->pages, args->pathlen); +} + +static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_symlinkargs *args) +{ + encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen); + encode_symlinkdata3(xdr, args); +} + +/* + * 3.3.11 MKNOD3args + * + * struct devicedata3 { + * sattr3 dev_attributes; + * specdata3 spec; + * }; + * + * union mknoddata3 switch (ftype3 type) { + * case NF3CHR: + * case NF3BLK: + * devicedata3 device; + * case NF3SOCK: + * case NF3FIFO: + * sattr3 pipe_attributes; + * default: + * void; + * }; + * + * struct MKNOD3args { + * diropargs3 where; + * mknoddata3 what; + * }; + */ +static void encode_devicedata3(struct xdr_stream *xdr, + const struct nfs3_mknodargs *args) +{ + encode_sattr3(xdr, args->sattr); + encode_specdata3(xdr, args->rdev); +} + +static void encode_mknoddata3(struct xdr_stream *xdr, + const struct nfs3_mknodargs *args) +{ + encode_ftype3(xdr, args->type); + switch (args->type) { + case NF3CHR: + case NF3BLK: + encode_devicedata3(xdr, args); + break; + case NF3SOCK: + case NF3FIFO: + encode_sattr3(xdr, args->sattr); + break; + case NF3REG: + case NF3DIR: + break; + default: + BUG(); + } +} + +static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_mknodargs *args) +{ + encode_diropargs3(xdr, args->fh, args->name, args->len); + encode_mknoddata3(xdr, args); +} + +/* + * 3.3.12 REMOVE3args + * + * struct REMOVE3args { + * diropargs3 object; + * }; + */ +static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_removeargs *args) +{ + encode_diropargs3(xdr, args->fh, args->name.name, args->name.len); +} + +/* + * 3.3.14 RENAME3args + * + * struct RENAME3args { + * diropargs3 from; + * diropargs3 to; + * }; + */ +static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_renameargs *args) +{ + const struct qstr *old = args->old_name; + const struct qstr *new = args->new_name; + + encode_diropargs3(xdr, args->old_dir, old->name, old->len); + encode_diropargs3(xdr, args->new_dir, new->name, new->len); +} + +/* + * 3.3.15 LINK3args + * + * struct LINK3args { + * nfs_fh3 file; + * diropargs3 link; + * }; + */ +static void nfs3_xdr_enc_link3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_linkargs *args) +{ + encode_nfs_fh3(xdr, args->fromfh); + encode_diropargs3(xdr, args->tofh, args->toname, args->tolen); +} + +/* + * 3.3.16 READDIR3args + * + * struct READDIR3args { + * nfs_fh3 dir; + * cookie3 cookie; + * cookieverf3 cookieverf; + * count3 count; + * }; + */ +static void encode_readdir3args(struct xdr_stream *xdr, + const struct nfs3_readdirargs *args) +{ + __be32 *p; + + encode_nfs_fh3(xdr, args->fh); + + p = xdr_reserve_space(xdr, 8 + NFS3_COOKIEVERFSIZE + 4); + p = xdr_encode_cookie3(p, args->cookie); + p = xdr_encode_cookieverf3(p, args->verf); + *p = cpu_to_be32(args->count); +} + +static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_readdirargs *args) +{ + encode_readdir3args(xdr, args); + prepare_reply_buffer(req, args->pages, 0, + args->count, NFS3_readdirres_sz); +} + +/* + * 3.3.17 READDIRPLUS3args + * + * struct READDIRPLUS3args { + * nfs_fh3 dir; + * cookie3 cookie; + * cookieverf3 cookieverf; + * count3 dircount; + * count3 maxcount; + * }; + */ +static void encode_readdirplus3args(struct xdr_stream *xdr, + const struct nfs3_readdirargs *args) +{ + __be32 *p; + + encode_nfs_fh3(xdr, args->fh); + + p = xdr_reserve_space(xdr, 8 + NFS3_COOKIEVERFSIZE + 4 + 4); + p = xdr_encode_cookie3(p, args->cookie); + p = xdr_encode_cookieverf3(p, args->verf); + + /* + * readdirplus: need dircount + buffer size. + * We just make sure we make dircount big enough + */ + *p++ = cpu_to_be32(args->count >> 3); + + *p = cpu_to_be32(args->count); +} + +static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_readdirargs *args) +{ + encode_readdirplus3args(xdr, args); + prepare_reply_buffer(req, args->pages, 0, + args->count, NFS3_readdirres_sz); +} + +/* + * 3.3.21 COMMIT3args + * + * struct COMMIT3args { + * nfs_fh3 file; + * offset3 offset; + * count3 count; + * }; + */ +static void encode_commit3args(struct xdr_stream *xdr, + const struct nfs_commitargs *args) +{ + __be32 *p; + + encode_nfs_fh3(xdr, args->fh); + + p = xdr_reserve_space(xdr, 8 + 4); + p = xdr_encode_hyper(p, args->offset); + *p = cpu_to_be32(args->count); +} + +static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs_commitargs *args) +{ + encode_commit3args(xdr, args); +} + +#ifdef CONFIG_NFS_V3_ACL + +static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_getaclargs *args) +{ + encode_nfs_fh3(xdr, args->fh); + encode_uint32(xdr, args->mask); + if (args->mask & (NFS_ACL | NFS_DFACL)) + prepare_reply_buffer(req, args->pages, 0, + NFSACL_MAXPAGES << PAGE_SHIFT, + ACL3_getaclres_sz); +} + +static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs3_setaclargs *args) +{ + unsigned int base; + int error; + + encode_nfs_fh3(xdr, NFS_FH(args->inode)); + encode_uint32(xdr, args->mask); + + base = req->rq_slen; + if (args->npages != 0) + xdr_write_pages(xdr, args->pages, 0, args->len); + else + xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE); + + error = nfsacl_encode(xdr->buf, base, args->inode, + (args->mask & NFS_ACL) ? + args->acl_access : NULL, 1, 0); + /* FIXME: this is just broken */ + BUG_ON(error < 0); + error = nfsacl_encode(xdr->buf, base + error, args->inode, + (args->mask & NFS_DFACL) ? + args->acl_default : NULL, 1, + NFS_ACL_DEFAULT); + BUG_ON(error < 0); +} + +#endif /* CONFIG_NFS_V3_ACL */ + +/* + * NFSv3 XDR decode functions + * + * NFSv3 result types are defined in section 3.3 of RFC 1813: + * "NFS Version 3 Protocol Specification". + */ + +/* + * 3.3.1 GETATTR3res + * + * struct GETATTR3resok { + * fattr3 obj_attributes; + * }; + * + * union GETATTR3res switch (nfsstat3 status) { + * case NFS3_OK: + * GETATTR3resok resok; + * default: + * void; + * }; + */ +static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_fattr *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_fattr3(xdr, result); +out: + return error; +out_default: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.2 SETATTR3res + * + * struct SETATTR3resok { + * wcc_data obj_wcc; + * }; + * + * struct SETATTR3resfail { + * wcc_data obj_wcc; + * }; + * + * union SETATTR3res switch (nfsstat3 status) { + * case NFS3_OK: + * SETATTR3resok resok; + * default: + * SETATTR3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_fattr *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.3 LOOKUP3res + * + * struct LOOKUP3resok { + * nfs_fh3 object; + * post_op_attr obj_attributes; + * post_op_attr dir_attributes; + * }; + * + * struct LOOKUP3resfail { + * post_op_attr dir_attributes; + * }; + * + * union LOOKUP3res switch (nfsstat3 status) { + * case NFS3_OK: + * LOOKUP3resok resok; + * default: + * LOOKUP3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs3_diropres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_nfs_fh3(xdr, result->fh); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->dir_attr); +out: + return error; +out_default: + error = decode_post_op_attr(xdr, result->dir_attr); + if (unlikely(error)) + goto out; + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.4 ACCESS3res + * + * struct ACCESS3resok { + * post_op_attr obj_attributes; + * uint32 access; + * }; + * + * struct ACCESS3resfail { + * post_op_attr obj_attributes; + * }; + * + * union ACCESS3res switch (nfsstat3 status) { + * case NFS3_OK: + * ACCESS3resok resok; + * default: + * ACCESS3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs3_accessres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_uint32(xdr, &result->access); +out: + return error; +out_default: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.5 READLINK3res + * + * struct READLINK3resok { + * post_op_attr symlink_attributes; + * nfspath3 data; + * }; + * + * struct READLINK3resfail { + * post_op_attr symlink_attributes; + * }; + * + * union READLINK3res switch (nfsstat3 status) { + * case NFS3_OK: + * READLINK3resok resok; + * default: + * READLINK3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_fattr *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_nfspath3(xdr); +out: + return error; +out_default: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.6 READ3res + * + * struct READ3resok { + * post_op_attr file_attributes; + * count3 count; + * bool eof; + * opaque data<>; + * }; + * + * struct READ3resfail { + * post_op_attr file_attributes; + * }; + * + * union READ3res switch (nfsstat3 status) { + * case NFS3_OK: + * READ3resok resok; + * default: + * READ3resfail resfail; + * }; + */ +static int decode_read3resok(struct xdr_stream *xdr, + struct nfs_pgio_res *result) +{ + u32 eof, count, ocount, recvd; + __be32 *p; + + p = xdr_inline_decode(xdr, 4 + 4 + 4); + if (unlikely(p == NULL)) + goto out_overflow; + count = be32_to_cpup(p++); + eof = be32_to_cpup(p++); + ocount = be32_to_cpup(p++); + if (unlikely(ocount != count)) + goto out_mismatch; + recvd = xdr_read_pages(xdr, count); + if (unlikely(count > recvd)) + goto out_cheating; +out: + result->eof = eof; + result->count = count; + return count; +out_mismatch: + dprintk("NFS: READ count doesn't match length of opaque: " + "count %u != ocount %u\n", count, ocount); + return -EIO; +out_cheating: + dprintk("NFS: server cheating in read result: " + "count %u > recvd %u\n", count, recvd); + count = recvd; + eof = 0; + goto out; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_pgio_res *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + result->op_status = status; + if (status != NFS3_OK) + goto out_status; + error = decode_read3resok(xdr, result); +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.7 WRITE3res + * + * enum stable_how { + * UNSTABLE = 0, + * DATA_SYNC = 1, + * FILE_SYNC = 2 + * }; + * + * struct WRITE3resok { + * wcc_data file_wcc; + * count3 count; + * stable_how committed; + * writeverf3 verf; + * }; + * + * struct WRITE3resfail { + * wcc_data file_wcc; + * }; + * + * union WRITE3res switch (nfsstat3 status) { + * case NFS3_OK: + * WRITE3resok resok; + * default: + * WRITE3resfail resfail; + * }; + */ +static int decode_write3resok(struct xdr_stream *xdr, + struct nfs_pgio_res *result) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4 + 4); + if (unlikely(p == NULL)) + goto out_overflow; + result->count = be32_to_cpup(p++); + result->verf->committed = be32_to_cpup(p++); + if (unlikely(result->verf->committed > NFS_FILE_SYNC)) + goto out_badvalue; + if (decode_writeverf3(xdr, &result->verf->verifier)) + goto out_eio; + return result->count; +out_badvalue: + dprintk("NFS: bad stable_how value: %u\n", result->verf->committed); + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); +out_eio: + return -EIO; +} + +static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_pgio_res *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result->fattr); + if (unlikely(error)) + goto out; + result->op_status = status; + if (status != NFS3_OK) + goto out_status; + error = decode_write3resok(xdr, result); +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.8 CREATE3res + * + * struct CREATE3resok { + * post_op_fh3 obj; + * post_op_attr obj_attributes; + * wcc_data dir_wcc; + * }; + * + * struct CREATE3resfail { + * wcc_data dir_wcc; + * }; + * + * union CREATE3res switch (nfsstat3 status) { + * case NFS3_OK: + * CREATE3resok resok; + * default: + * CREATE3resfail resfail; + * }; + */ +static int decode_create3resok(struct xdr_stream *xdr, + struct nfs3_diropres *result) +{ + int error; + + error = decode_post_op_fh3(xdr, result->fh); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + /* The server isn't required to return a file handle. + * If it didn't, force the client to perform a LOOKUP + * to determine the correct file handle and attribute + * values for the new object. */ + if (result->fh->size == 0) + result->fattr->valid = 0; + error = decode_wcc_data(xdr, result->dir_attr); +out: + return error; +} + +static int nfs3_xdr_dec_create3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs3_diropres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_create3resok(xdr, result); +out: + return error; +out_default: + error = decode_wcc_data(xdr, result->dir_attr); + if (unlikely(error)) + goto out; + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.12 REMOVE3res + * + * struct REMOVE3resok { + * wcc_data dir_wcc; + * }; + * + * struct REMOVE3resfail { + * wcc_data dir_wcc; + * }; + * + * union REMOVE3res switch (nfsstat3 status) { + * case NFS3_OK: + * REMOVE3resok resok; + * default: + * REMOVE3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_removeres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result->dir_attr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.14 RENAME3res + * + * struct RENAME3resok { + * wcc_data fromdir_wcc; + * wcc_data todir_wcc; + * }; + * + * struct RENAME3resfail { + * wcc_data fromdir_wcc; + * wcc_data todir_wcc; + * }; + * + * union RENAME3res switch (nfsstat3 status) { + * case NFS3_OK: + * RENAME3resok resok; + * default: + * RENAME3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_renameres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result->old_fattr); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result->new_fattr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.15 LINK3res + * + * struct LINK3resok { + * post_op_attr file_attributes; + * wcc_data linkdir_wcc; + * }; + * + * struct LINK3resfail { + * post_op_attr file_attributes; + * wcc_data linkdir_wcc; + * }; + * + * union LINK3res switch (nfsstat3 status) { + * case NFS3_OK: + * LINK3resok resok; + * default: + * LINK3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs3_linkres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result->dir_attr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/** + * nfs3_decode_dirent - Decode a single NFSv3 directory entry stored in + * the local page cache + * @xdr: XDR stream where entry resides + * @entry: buffer to fill in with entry data + * @plus: boolean indicating whether this should be a readdirplus entry + * + * Returns zero if successful, otherwise a negative errno value is + * returned. + * + * This function is not invoked during READDIR reply decoding, but + * rather whenever an application invokes the getdents(2) system call + * on a directory already in our cache. + * + * 3.3.16 entry3 + * + * struct entry3 { + * fileid3 fileid; + * filename3 name; + * cookie3 cookie; + * fhandle3 filehandle; + * post_op_attr3 attributes; + * entry3 *nextentry; + * }; + * + * 3.3.17 entryplus3 + * struct entryplus3 { + * fileid3 fileid; + * filename3 name; + * cookie3 cookie; + * post_op_attr name_attributes; + * post_op_fh3 name_handle; + * entryplus3 *nextentry; + * }; + */ +int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, + int plus) +{ + struct nfs_entry old = *entry; + __be32 *p; + int error; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p == xdr_zero) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p == xdr_zero) + return -EAGAIN; + entry->eof = 1; + return -EBADCOOKIE; + } + + error = decode_fileid3(xdr, &entry->ino); + if (unlikely(error)) + return error; + + error = decode_inline_filename3(xdr, &entry->name, &entry->len); + if (unlikely(error)) + return error; + + entry->prev_cookie = entry->cookie; + error = decode_cookie3(xdr, &entry->cookie); + if (unlikely(error)) + return error; + + entry->d_type = DT_UNKNOWN; + + if (plus) { + entry->fattr->valid = 0; + error = decode_post_op_attr(xdr, entry->fattr); + if (unlikely(error)) + return error; + if (entry->fattr->valid & NFS_ATTR_FATTR_V3) + entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); + + if (entry->fattr->fileid != entry->ino) { + entry->fattr->mounted_on_fileid = entry->ino; + entry->fattr->valid |= NFS_ATTR_FATTR_MOUNTED_ON_FILEID; + } + + /* In fact, a post_op_fh3: */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(p == NULL)) + goto out_overflow; + if (*p != xdr_zero) { + error = decode_nfs_fh3(xdr, entry->fh); + if (unlikely(error)) { + if (error == -E2BIG) + goto out_truncated; + return error; + } + } else + zero_nfs_fh3(entry->fh); + } + + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EAGAIN; +out_truncated: + dprintk("NFS: directory entry contains invalid file handle\n"); + *entry = old; + return -EAGAIN; +} + +/* + * 3.3.16 READDIR3res + * + * struct dirlist3 { + * entry3 *entries; + * bool eof; + * }; + * + * struct READDIR3resok { + * post_op_attr dir_attributes; + * cookieverf3 cookieverf; + * dirlist3 reply; + * }; + * + * struct READDIR3resfail { + * post_op_attr dir_attributes; + * }; + * + * union READDIR3res switch (nfsstat3 status) { + * case NFS3_OK: + * READDIR3resok resok; + * default: + * READDIR3resfail resfail; + * }; + * + * Read the directory contents into the page cache, but otherwise + * don't touch them. The actual decoding is done by nfs3_decode_entry() + * during subsequent nfs_readdir() calls. + */ +static int decode_dirlist3(struct xdr_stream *xdr) +{ + return xdr_read_pages(xdr, xdr->buf->page_len); +} + +static int decode_readdir3resok(struct xdr_stream *xdr, + struct nfs3_readdirres *result) +{ + int error; + + error = decode_post_op_attr(xdr, result->dir_attr); + if (unlikely(error)) + goto out; + /* XXX: do we need to check if result->verf != NULL ? */ + error = decode_cookieverf3(xdr, result->verf); + if (unlikely(error)) + goto out; + error = decode_dirlist3(xdr); +out: + return error; +} + +static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs3_readdirres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_readdir3resok(xdr, result); +out: + return error; +out_default: + error = decode_post_op_attr(xdr, result->dir_attr); + if (unlikely(error)) + goto out; + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.18 FSSTAT3res + * + * struct FSSTAT3resok { + * post_op_attr obj_attributes; + * size3 tbytes; + * size3 fbytes; + * size3 abytes; + * size3 tfiles; + * size3 ffiles; + * size3 afiles; + * uint32 invarsec; + * }; + * + * struct FSSTAT3resfail { + * post_op_attr obj_attributes; + * }; + * + * union FSSTAT3res switch (nfsstat3 status) { + * case NFS3_OK: + * FSSTAT3resok resok; + * default: + * FSSTAT3resfail resfail; + * }; + */ +static int decode_fsstat3resok(struct xdr_stream *xdr, + struct nfs_fsstat *result) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 8 * 6 + 4); + if (unlikely(p == NULL)) + goto out_overflow; + p = xdr_decode_size3(p, &result->tbytes); + p = xdr_decode_size3(p, &result->fbytes); + p = xdr_decode_size3(p, &result->abytes); + p = xdr_decode_size3(p, &result->tfiles); + p = xdr_decode_size3(p, &result->ffiles); + xdr_decode_size3(p, &result->afiles); + /* ignore invarsec */ + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_fsstat *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; + error = decode_fsstat3resok(xdr, result); +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.19 FSINFO3res + * + * struct FSINFO3resok { + * post_op_attr obj_attributes; + * uint32 rtmax; + * uint32 rtpref; + * uint32 rtmult; + * uint32 wtmax; + * uint32 wtpref; + * uint32 wtmult; + * uint32 dtpref; + * size3 maxfilesize; + * nfstime3 time_delta; + * uint32 properties; + * }; + * + * struct FSINFO3resfail { + * post_op_attr obj_attributes; + * }; + * + * union FSINFO3res switch (nfsstat3 status) { + * case NFS3_OK: + * FSINFO3resok resok; + * default: + * FSINFO3resfail resfail; + * }; + */ +static int decode_fsinfo3resok(struct xdr_stream *xdr, + struct nfs_fsinfo *result) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4 * 7 + 8 + 8 + 4); + if (unlikely(p == NULL)) + goto out_overflow; + result->rtmax = be32_to_cpup(p++); + result->rtpref = be32_to_cpup(p++); + result->rtmult = be32_to_cpup(p++); + result->wtmax = be32_to_cpup(p++); + result->wtpref = be32_to_cpup(p++); + result->wtmult = be32_to_cpup(p++); + result->dtpref = be32_to_cpup(p++); + p = xdr_decode_size3(p, &result->maxfilesize); + xdr_decode_nfstime3(p, &result->time_delta); + + /* ignore properties */ + result->lease_time = 0; + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_fsinfo *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; + error = decode_fsinfo3resok(xdr, result); +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.20 PATHCONF3res + * + * struct PATHCONF3resok { + * post_op_attr obj_attributes; + * uint32 linkmax; + * uint32 name_max; + * bool no_trunc; + * bool chown_restricted; + * bool case_insensitive; + * bool case_preserving; + * }; + * + * struct PATHCONF3resfail { + * post_op_attr obj_attributes; + * }; + * + * union PATHCONF3res switch (nfsstat3 status) { + * case NFS3_OK: + * PATHCONF3resok resok; + * default: + * PATHCONF3resfail resfail; + * }; + */ +static int decode_pathconf3resok(struct xdr_stream *xdr, + struct nfs_pathconf *result) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4 * 6); + if (unlikely(p == NULL)) + goto out_overflow; + result->max_link = be32_to_cpup(p++); + result->max_namelen = be32_to_cpup(p); + /* ignore remaining fields */ + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_pathconf *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_status; + error = decode_pathconf3resok(xdr, result); +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +/* + * 3.3.21 COMMIT3res + * + * struct COMMIT3resok { + * wcc_data file_wcc; + * writeverf3 verf; + * }; + * + * struct COMMIT3resfail { + * wcc_data file_wcc; + * }; + * + * union COMMIT3res switch (nfsstat3 status) { + * case NFS3_OK: + * COMMIT3resok resok; + * default: + * COMMIT3resfail resfail; + * }; + */ +static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_commitres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + error = decode_wcc_data(xdr, result->fattr); + if (unlikely(error)) + goto out; + result->op_status = status; + if (status != NFS3_OK) + goto out_status; + error = decode_writeverf3(xdr, &result->verf->verifier); +out: + return error; +out_status: + return nfs3_stat_to_errno(status); +} + +#ifdef CONFIG_NFS_V3_ACL + +static inline int decode_getacl3resok(struct xdr_stream *xdr, + struct nfs3_getaclres *result) +{ + struct posix_acl **acl; + unsigned int *aclcnt; + size_t hdrlen; + int error; + + error = decode_post_op_attr(xdr, result->fattr); + if (unlikely(error)) + goto out; + error = decode_uint32(xdr, &result->mask); + if (unlikely(error)) + goto out; + error = -EINVAL; + if (result->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT)) + goto out; + + hdrlen = xdr_stream_pos(xdr); + + acl = NULL; + if (result->mask & NFS_ACL) + acl = &result->acl_access; + aclcnt = NULL; + if (result->mask & NFS_ACLCNT) + aclcnt = &result->acl_access_count; + error = nfsacl_decode(xdr->buf, hdrlen, aclcnt, acl); + if (unlikely(error <= 0)) + goto out; + + acl = NULL; + if (result->mask & NFS_DFACL) + acl = &result->acl_default; + aclcnt = NULL; + if (result->mask & NFS_DFACLCNT) + aclcnt = &result->acl_default_count; + error = nfsacl_decode(xdr->buf, hdrlen + error, aclcnt, acl); + if (unlikely(error <= 0)) + return error; + error = 0; +out: + return error; +} + +static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs3_getaclres *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_getacl3resok(xdr, result); +out: + return error; +out_default: + return nfs3_stat_to_errno(status); +} + +static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_fattr *result) +{ + enum nfs_stat status; + int error; + + error = decode_nfsstat3(xdr, &status); + if (unlikely(error)) + goto out; + if (status != NFS3_OK) + goto out_default; + error = decode_post_op_attr(xdr, result); +out: + return error; +out_default: + return nfs3_stat_to_errno(status); +} + +#endif /* CONFIG_NFS_V3_ACL */ + + +/* + * We need to translate between nfs status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs_errtbl[] = { + { NFS_OK, 0 }, + { NFSERR_PERM, -EPERM }, + { NFSERR_NOENT, -ENOENT }, + { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_NXIO, -ENXIO }, +/* { NFSERR_EAGAIN, -EAGAIN }, */ + { NFSERR_ACCES, -EACCES }, + { NFSERR_EXIST, -EEXIST }, + { NFSERR_XDEV, -EXDEV }, + { NFSERR_NODEV, -ENODEV }, + { NFSERR_NOTDIR, -ENOTDIR }, + { NFSERR_ISDIR, -EISDIR }, + { NFSERR_INVAL, -EINVAL }, + { NFSERR_FBIG, -EFBIG }, + { NFSERR_NOSPC, -ENOSPC }, + { NFSERR_ROFS, -EROFS }, + { NFSERR_MLINK, -EMLINK }, + { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFSERR_NOTEMPTY, -ENOTEMPTY }, + { NFSERR_DQUOT, -EDQUOT }, + { NFSERR_STALE, -ESTALE }, + { NFSERR_REMOTE, -EREMOTE }, +#ifdef EWFLUSH + { NFSERR_WFLUSH, -EWFLUSH }, +#endif + { NFSERR_BADHANDLE, -EBADHANDLE }, + { NFSERR_NOT_SYNC, -ENOTSYNC }, + { NFSERR_BAD_COOKIE, -EBADCOOKIE }, + { NFSERR_NOTSUPP, -ENOTSUPP }, + { NFSERR_TOOSMALL, -ETOOSMALL }, + { NFSERR_SERVERFAULT, -EREMOTEIO }, + { NFSERR_BADTYPE, -EBADTYPE }, + { NFSERR_JUKEBOX, -EJUKEBOX }, + { -1, -EIO } +}; + +/** + * nfs3_stat_to_errno - convert an NFS status code to a local errno + * @status: NFS status code to convert + * + * Returns a local errno value, or -EIO if the NFS status code is + * not recognized. This function is used jointly by NFSv2 and NFSv3. + */ +static int nfs3_stat_to_errno(enum nfs_stat status) +{ + int i; + + for (i = 0; nfs_errtbl[i].stat != -1; i++) { + if (nfs_errtbl[i].stat == (int)status) + return nfs_errtbl[i].errno; + } + dprintk("NFS: Unrecognized nfs status value: %u\n", status); + return nfs_errtbl[i].errno; +} + + +#define PROC(proc, argtype, restype, timer) \ +[NFS3PROC_##proc] = { \ + .p_proc = NFS3PROC_##proc, \ + .p_encode = (kxdreproc_t)nfs3_xdr_enc_##argtype##3args, \ + .p_decode = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res, \ + .p_arglen = NFS3_##argtype##args_sz, \ + .p_replen = NFS3_##restype##res_sz, \ + .p_timer = timer, \ + .p_statidx = NFS3PROC_##proc, \ + .p_name = #proc, \ + } + +struct rpc_procinfo nfs3_procedures[] = { + PROC(GETATTR, getattr, getattr, 1), + PROC(SETATTR, setattr, setattr, 0), + PROC(LOOKUP, lookup, lookup, 2), + PROC(ACCESS, access, access, 1), + PROC(READLINK, readlink, readlink, 3), + PROC(READ, read, read, 3), + PROC(WRITE, write, write, 4), + PROC(CREATE, create, create, 0), + PROC(MKDIR, mkdir, create, 0), + PROC(SYMLINK, symlink, create, 0), + PROC(MKNOD, mknod, create, 0), + PROC(REMOVE, remove, remove, 0), + PROC(RMDIR, lookup, setattr, 0), + PROC(RENAME, rename, rename, 0), + PROC(LINK, link, link, 0), + PROC(READDIR, readdir, readdir, 3), + PROC(READDIRPLUS, readdirplus, readdir, 3), + PROC(FSSTAT, getattr, fsstat, 0), + PROC(FSINFO, getattr, fsinfo, 0), + PROC(PATHCONF, getattr, pathconf, 0), + PROC(COMMIT, commit, commit, 5), +}; + +const struct rpc_version nfs_version3 = { + .number = 3, + .nrprocs = ARRAY_SIZE(nfs3_procedures), + .procs = nfs3_procedures +}; + +#ifdef CONFIG_NFS_V3_ACL +static struct rpc_procinfo nfs3_acl_procedures[] = { + [ACLPROC3_GETACL] = { + .p_proc = ACLPROC3_GETACL, + .p_encode = (kxdreproc_t)nfs3_xdr_enc_getacl3args, + .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res, + .p_arglen = ACL3_getaclargs_sz, + .p_replen = ACL3_getaclres_sz, + .p_timer = 1, + .p_name = "GETACL", + }, + [ACLPROC3_SETACL] = { + .p_proc = ACLPROC3_SETACL, + .p_encode = (kxdreproc_t)nfs3_xdr_enc_setacl3args, + .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res, + .p_arglen = ACL3_setaclargs_sz, + .p_replen = ACL3_setaclres_sz, + .p_timer = 0, + .p_name = "SETACL", + }, +}; + +const struct rpc_version nfsacl_version3 = { + .number = 3, + .nrprocs = sizeof(nfs3_acl_procedures)/ + sizeof(nfs3_acl_procedures[0]), + .procs = nfs3_acl_procedures, +}; +#endif /* CONFIG_NFS_V3_ACL */ diff --git a/kernel/fs/nfs/nfs42.h b/kernel/fs/nfs/nfs42.h new file mode 100644 index 000000000..7afb8947d --- /dev/null +++ b/kernel/fs/nfs/nfs42.h @@ -0,0 +1,16 @@ +/* + * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com> + */ + +#ifndef __LINUX_FS_NFS_NFS4_2_H +#define __LINUX_FS_NFS_NFS4_2_H + +/* nfs4.2proc.c */ +int nfs42_proc_allocate(struct file *, loff_t, loff_t); +int nfs42_proc_deallocate(struct file *, loff_t, loff_t); +loff_t nfs42_proc_llseek(struct file *, loff_t, int); + +/* nfs4.2xdr.h */ +extern struct rpc_procinfo nfs4_2_procedures[]; + +#endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/kernel/fs/nfs/nfs42proc.c b/kernel/fs/nfs/nfs42proc.c new file mode 100644 index 000000000..3a9e75235 --- /dev/null +++ b/kernel/fs/nfs/nfs42proc.c @@ -0,0 +1,167 @@ +/* + * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com> + */ +#include <linux/fs.h> +#include <linux/sunrpc/sched.h> +#include <linux/nfs.h> +#include <linux/nfs3.h> +#include <linux/nfs4.h> +#include <linux/nfs_xdr.h> +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" +#include "nfs42.h" + +static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, + fmode_t fmode) +{ + struct nfs_open_context *open; + struct nfs_lock_context *lock; + int ret; + + open = get_nfs_open_context(nfs_file_open_context(file)); + lock = nfs_get_lock_context(open); + if (IS_ERR(lock)) { + put_nfs_open_context(open); + return PTR_ERR(lock); + } + + ret = nfs4_set_rw_stateid(dst, open, lock, fmode); + + nfs_put_lock_context(lock); + put_nfs_open_context(open); + return ret; +} + +static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, + loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + struct nfs_server *server = NFS_SERVER(inode); + struct nfs42_falloc_args args = { + .falloc_fh = NFS_FH(inode), + .falloc_offset = offset, + .falloc_length = len, + .falloc_bitmask = server->cache_consistency_bitmask, + }; + struct nfs42_falloc_res res = { + .falloc_server = server, + }; + int status; + + msg->rpc_argp = &args; + msg->rpc_resp = &res; + + status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + if (status) + return status; + + res.falloc_fattr = nfs_alloc_fattr(); + if (!res.falloc_fattr) + return -ENOMEM; + + status = nfs4_call_sync(server->client, server, msg, + &args.seq_args, &res.seq_res, 0); + if (status == 0) + status = nfs_post_op_update_inode(inode, res.falloc_fattr); + + kfree(res.falloc_fattr); + return status; +} + +static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, + loff_t offset, loff_t len) +{ + struct nfs_server *server = NFS_SERVER(file_inode(filep)); + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs42_proc_fallocate(msg, filep, offset, len); + if (err == -ENOTSUPP) + return -EOPNOTSUPP; + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; +} + +int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], + }; + struct inode *inode = file_inode(filep); + int err; + + if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) + return -EOPNOTSUPP; + + mutex_lock(&inode->i_mutex); + + err = nfs42_proc_fallocate(&msg, filep, offset, len); + if (err == -EOPNOTSUPP) + NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE; + + mutex_unlock(&inode->i_mutex); + return err; +} + +int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DEALLOCATE], + }; + struct inode *inode = file_inode(filep); + int err; + + if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) + return -EOPNOTSUPP; + + nfs_wb_all(inode); + mutex_lock(&inode->i_mutex); + + err = nfs42_proc_fallocate(&msg, filep, offset, len); + if (err == 0) + truncate_pagecache_range(inode, offset, (offset + len) -1); + if (err == -EOPNOTSUPP) + NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE; + + mutex_unlock(&inode->i_mutex); + return err; +} + +loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +{ + struct inode *inode = file_inode(filep); + struct nfs42_seek_args args = { + .sa_fh = NFS_FH(inode), + .sa_offset = offset, + .sa_what = (whence == SEEK_HOLE) ? + NFS4_CONTENT_HOLE : NFS4_CONTENT_DATA, + }; + struct nfs42_seek_res res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEEK], + .rpc_argp = &args, + .rpc_resp = &res, + }; + struct nfs_server *server = NFS_SERVER(inode); + int status; + + if (!nfs_server_capable(inode, NFS_CAP_SEEK)) + return -ENOTSUPP; + + status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); + if (status) + return status; + + nfs_wb_all(inode); + status = nfs4_call_sync(server->client, server, &msg, + &args.seq_args, &res.seq_res, 0); + if (status == -ENOTSUPP) + server->caps &= ~NFS_CAP_SEEK; + if (status) + return status; + + return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); +} diff --git a/kernel/fs/nfs/nfs42xdr.c b/kernel/fs/nfs/nfs42xdr.c new file mode 100644 index 000000000..1a25b2724 --- /dev/null +++ b/kernel/fs/nfs/nfs42xdr.c @@ -0,0 +1,249 @@ +/* + * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com> + */ +#ifndef __LINUX_FS_NFS_NFS4_2XDR_H +#define __LINUX_FS_NFS_NFS4_2XDR_H + +#define encode_fallocate_maxsz (encode_stateid_maxsz + \ + 2 /* offset */ + \ + 2 /* length */) +#define encode_allocate_maxsz (op_encode_hdr_maxsz + \ + encode_fallocate_maxsz) +#define decode_allocate_maxsz (op_decode_hdr_maxsz) +#define encode_deallocate_maxsz (op_encode_hdr_maxsz + \ + encode_fallocate_maxsz) +#define decode_deallocate_maxsz (op_decode_hdr_maxsz) +#define encode_seek_maxsz (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + \ + 2 /* offset */ + \ + 1 /* whence */) +#define decode_seek_maxsz (op_decode_hdr_maxsz + \ + 1 /* eof */ + \ + 1 /* whence */ + \ + 2 /* offset */ + \ + 2 /* length */) + +#define NFS4_enc_allocate_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_allocate_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_allocate_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_allocate_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_deallocate_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_deallocate_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_deallocate_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_seek_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_seek_maxsz) +#define NFS4_dec_seek_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_seek_maxsz) + + +static void encode_fallocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + encode_nfs4_stateid(xdr, &args->falloc_stateid); + encode_uint64(xdr, args->falloc_offset); + encode_uint64(xdr, args->falloc_length); +} + +static void encode_allocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr); + encode_fallocate(xdr, args); +} + +static void encode_deallocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr); + encode_fallocate(xdr, args); +} + +static void encode_seek(struct xdr_stream *xdr, + struct nfs42_seek_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->sa_stateid); + encode_uint64(xdr, args->sa_offset); + encode_uint32(xdr, args->sa_what); +} + +/* + * Encode ALLOCATE request + */ +static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->falloc_fh, &hdr); + encode_allocate(xdr, args, &hdr); + encode_getfattr(xdr, args->falloc_bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode DEALLOCATE request + */ +static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->falloc_fh, &hdr); + encode_deallocate(xdr, args, &hdr); + encode_getfattr(xdr, args->falloc_bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode SEEK request + */ +static void nfs4_xdr_enc_seek(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_seek_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->sa_fh, &hdr); + encode_seek(xdr, args, &hdr); + encode_nops(&hdr); +} + +static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) +{ + return decode_op_hdr(xdr, OP_ALLOCATE); +} + +static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) +{ + return decode_op_hdr(xdr, OP_DEALLOCATE); +} + +static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res) +{ + int status; + __be32 *p; + + status = decode_op_hdr(xdr, OP_SEEK); + if (status) + return status; + + p = xdr_inline_decode(xdr, 4 + 8); + if (unlikely(!p)) + goto out_overflow; + + res->sr_eof = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &res->sr_offset); + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * Decode ALLOCATE request + */ +static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_falloc_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_allocate(xdr, res); + if (status) + goto out; + decode_getfattr(xdr, res->falloc_fattr, res->falloc_server); +out: + return status; +} + +/* + * Decode DEALLOCATE request + */ +static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_falloc_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_deallocate(xdr, res); + if (status) + goto out; + decode_getfattr(xdr, res->falloc_fattr, res->falloc_server); +out: + return status; +} + +/* + * Decode SEEK request + */ +static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_seek_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_seek(xdr, res); +out: + return status; +} +#endif /* __LINUX_FS_NFS_NFS4_2XDR_H */ diff --git a/kernel/fs/nfs/nfs4_fs.h b/kernel/fs/nfs/nfs4_fs.h new file mode 100644 index 000000000..fdef424b0 --- /dev/null +++ b/kernel/fs/nfs/nfs4_fs.h @@ -0,0 +1,529 @@ +/* + * linux/fs/nfs/nfs4_fs.h + * + * Copyright (C) 2005 Trond Myklebust + * + * NFSv4-specific filesystem definitions and declarations + */ + +#ifndef __LINUX_FS_NFS_NFS4_FS_H +#define __LINUX_FS_NFS_NFS4_FS_H + +#if defined(CONFIG_NFS_V4_2) +#define NFS4_MAX_MINOR_VERSION 2 +#elif defined(CONFIG_NFS_V4_1) +#define NFS4_MAX_MINOR_VERSION 1 +#else +#define NFS4_MAX_MINOR_VERSION 0 +#endif + +#if IS_ENABLED(CONFIG_NFS_V4) + +#define NFS4_MAX_LOOP_ON_RECOVER (10) + +#include <linux/seqlock.h> + +struct idmap; + +enum nfs4_client_state { + NFS4CLNT_MANAGER_RUNNING = 0, + NFS4CLNT_CHECK_LEASE, + NFS4CLNT_LEASE_EXPIRED, + NFS4CLNT_RECLAIM_REBOOT, + NFS4CLNT_RECLAIM_NOGRACE, + NFS4CLNT_DELEGRETURN, + NFS4CLNT_SESSION_RESET, + NFS4CLNT_LEASE_CONFIRM, + NFS4CLNT_SERVER_SCOPE_MISMATCH, + NFS4CLNT_PURGE_STATE, + NFS4CLNT_BIND_CONN_TO_SESSION, + NFS4CLNT_MOVED, + NFS4CLNT_LEASE_MOVED, +}; + +#define NFS4_RENEW_TIMEOUT 0x01 +#define NFS4_RENEW_DELEGATION_CB 0x02 + +struct nfs_seqid_counter; +struct nfs4_minor_version_ops { + u32 minor_version; + unsigned init_caps; + + int (*init_client)(struct nfs_client *); + void (*shutdown_client)(struct nfs_client *); + bool (*match_stateid)(const nfs4_stateid *, + const nfs4_stateid *); + int (*find_root_sec)(struct nfs_server *, struct nfs_fh *, + struct nfs_fsinfo *); + void (*free_lock_state)(struct nfs_server *, + struct nfs4_lock_state *); + struct nfs_seqid * + (*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + const struct rpc_call_ops *call_sync_ops; + const struct nfs4_state_recovery_ops *reboot_recovery_ops; + const struct nfs4_state_recovery_ops *nograce_recovery_ops; + const struct nfs4_state_maintenance_ops *state_renewal_ops; + const struct nfs4_mig_recovery_ops *mig_recovery_ops; +}; + +#define NFS_SEQID_CONFIRMED 1 +struct nfs_seqid_counter { + ktime_t create_time; + int owner_id; + int flags; + u32 counter; + spinlock_t lock; /* Protects the list */ + struct list_head list; /* Defines sequence of RPC calls */ + struct rpc_wait_queue wait; /* RPC call delay queue */ +}; + +struct nfs_seqid { + struct nfs_seqid_counter *sequence; + struct list_head list; + struct rpc_task *task; +}; + +static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status) +{ + if (seqid_mutating_err(-status)) + seqid->flags |= NFS_SEQID_CONFIRMED; +} + +/* + * NFS4 state_owners and lock_owners are simply labels for ordered + * sequences of RPC calls. Their sole purpose is to provide once-only + * semantics by allowing the server to identify replayed requests. + */ +struct nfs4_state_owner { + struct nfs_server *so_server; + struct list_head so_lru; + unsigned long so_expires; + struct rb_node so_server_node; + + struct rpc_cred *so_cred; /* Associated cred */ + + spinlock_t so_lock; + atomic_t so_count; + unsigned long so_flags; + struct list_head so_states; + struct nfs_seqid_counter so_seqid; + seqcount_t so_reclaim_seqcount; + struct mutex so_delegreturn_mutex; +}; + +enum { + NFS_OWNER_RECLAIM_REBOOT, + NFS_OWNER_RECLAIM_NOGRACE +}; + +#define NFS_LOCK_NEW 0 +#define NFS_LOCK_RECLAIM 1 +#define NFS_LOCK_EXPIRED 2 + +/* + * struct nfs4_state maintains the client-side state for a given + * (state_owner,inode) tuple (OPEN) or state_owner (LOCK). + * + * OPEN: + * In order to know when to OPEN_DOWNGRADE or CLOSE the state on the server, + * we need to know how many files are open for reading or writing on a + * given inode. This information too is stored here. + * + * LOCK: one nfs4_state (LOCK) to hold the lock stateid nfs4_state(OPEN) + */ + +struct nfs4_lock_state { + struct list_head ls_locks; /* Other lock stateids */ + struct nfs4_state * ls_state; /* Pointer to open state */ +#define NFS_LOCK_INITIALIZED 0 +#define NFS_LOCK_LOST 1 + unsigned long ls_flags; + struct nfs_seqid_counter ls_seqid; + nfs4_stateid ls_stateid; + atomic_t ls_count; + fl_owner_t ls_owner; +}; + +/* bits for nfs4_state->flags */ +enum { + LK_STATE_IN_USE, + NFS_DELEGATED_STATE, /* Current stateid is delegation */ + NFS_OPEN_STATE, /* OPEN stateid is set */ + NFS_O_RDONLY_STATE, /* OPEN stateid has read-only state */ + NFS_O_WRONLY_STATE, /* OPEN stateid has write-only state */ + NFS_O_RDWR_STATE, /* OPEN stateid has read/write state */ + NFS_STATE_RECLAIM_REBOOT, /* OPEN stateid server rebooted */ + NFS_STATE_RECLAIM_NOGRACE, /* OPEN stateid needs to recover state */ + NFS_STATE_POSIX_LOCKS, /* Posix locks are supported */ + NFS_STATE_RECOVERY_FAILED, /* OPEN stateid state recovery failed */ +}; + +struct nfs4_state { + struct list_head open_states; /* List of states for the same state_owner */ + struct list_head inode_states; /* List of states for the same inode */ + struct list_head lock_states; /* List of subservient lock stateids */ + + struct nfs4_state_owner *owner; /* Pointer to the open owner */ + struct inode *inode; /* Pointer to the inode */ + + unsigned long flags; /* Do we hold any locks? */ + spinlock_t state_lock; /* Protects the lock_states list */ + + seqlock_t seqlock; /* Protects the stateid/open_stateid */ + nfs4_stateid stateid; /* Current stateid: may be delegation */ + nfs4_stateid open_stateid; /* OPEN stateid */ + + /* The following 3 fields are protected by owner->so_lock */ + unsigned int n_rdonly; /* Number of read-only references */ + unsigned int n_wronly; /* Number of write-only references */ + unsigned int n_rdwr; /* Number of read/write references */ + fmode_t state; /* State on the server (R,W, or RW) */ + atomic_t count; +}; + + +struct nfs4_exception { + long timeout; + int retry; + struct nfs4_state *state; + struct inode *inode; +}; + +struct nfs4_state_recovery_ops { + int owner_flag_bit; + int state_flag_bit; + int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *); + int (*recover_lock)(struct nfs4_state *, struct file_lock *); + int (*establish_clid)(struct nfs_client *, struct rpc_cred *); + int (*reclaim_complete)(struct nfs_client *, struct rpc_cred *); + int (*detect_trunking)(struct nfs_client *, struct nfs_client **, + struct rpc_cred *); +}; + +struct nfs4_state_maintenance_ops { + int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *, unsigned); + struct rpc_cred * (*get_state_renewal_cred_locked)(struct nfs_client *); + int (*renew_lease)(struct nfs_client *, struct rpc_cred *); +}; + +struct nfs4_mig_recovery_ops { + int (*get_locations)(struct inode *, struct nfs4_fs_locations *, + struct page *, struct rpc_cred *); + int (*fsid_present)(struct inode *, struct rpc_cred *); +}; + +extern const struct dentry_operations nfs4_dentry_operations; + +/* dir.c */ +int nfs_atomic_open(struct inode *, struct dentry *, struct file *, + unsigned, umode_t, int *); + +/* super.c */ +extern struct file_system_type nfs4_fs_type; + +/* nfs4namespace.c */ +struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, struct qstr *); +struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); +int nfs4_replace_transport(struct nfs_server *server, + const struct nfs4_fs_locations *locations); + +/* nfs4proc.c */ +extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); +extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *, + struct rpc_message *, struct nfs4_sequence_args *, + struct nfs4_sequence_res *, int); +extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); +extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); +extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool); +extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred); +extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); +extern int nfs4_destroy_clientid(struct nfs_client *clp); +extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); +extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); +extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); +extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); +extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, + struct nfs4_fs_locations *, struct page *); +extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, + struct page *page, struct rpc_cred *); +extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *); +extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *, + struct nfs_fh *, struct nfs_fattr *); +extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); +extern const struct xattr_handler *nfs4_xattr_handlers[]; +extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, + const struct nfs_open_context *ctx, + const struct nfs_lock_context *l_ctx, + fmode_t fmode); + +#if defined(CONFIG_NFS_V4_1) +static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server) +{ + return server->nfs_client->cl_session; +} + +extern int nfs41_setup_sequence(struct nfs4_session *session, + struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, + struct rpc_task *task); +extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *); +extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *); +extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *); +extern int nfs4_proc_get_lease_time(struct nfs_client *clp, + struct nfs_fsinfo *fsinfo); +extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, + bool sync); + +static inline bool +is_ds_only_client(struct nfs_client *clp) +{ + return (clp->cl_exchange_flags & EXCHGID4_FLAG_MASK_PNFS) == + EXCHGID4_FLAG_USE_PNFS_DS; +} + +static inline bool +is_ds_client(struct nfs_client *clp) +{ + return clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_DS; +} + +static inline bool +_nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, + struct rpc_clnt **clntp, struct rpc_message *msg) +{ + struct rpc_cred *newcred = NULL; + rpc_authflavor_t flavor; + + if (test_bit(sp4_mode, &clp->cl_sp4_flags)) { + spin_lock(&clp->cl_lock); + if (clp->cl_machine_cred != NULL) + /* don't call get_rpccred on the machine cred - + * a reference will be held for life of clp */ + newcred = clp->cl_machine_cred; + spin_unlock(&clp->cl_lock); + msg->rpc_cred = newcred; + + flavor = clp->cl_rpcclient->cl_auth->au_flavor; + WARN_ON_ONCE(flavor != RPC_AUTH_GSS_KRB5I && + flavor != RPC_AUTH_GSS_KRB5P); + *clntp = clp->cl_rpcclient; + + return true; + } + return false; +} + +/* + * Function responsible for determining if an rpc_message should use the + * machine cred under SP4_MACH_CRED and if so switching the credential and + * authflavor (using the nfs_client's rpc_clnt which will be krb5i/p). + * Should be called before rpc_call_sync/rpc_call_async. + */ +static inline void +nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, + struct rpc_clnt **clntp, struct rpc_message *msg) +{ + _nfs4_state_protect(clp, sp4_mode, clntp, msg); +} + +/* + * Special wrapper to nfs4_state_protect for write. + * If WRITE can use machine cred but COMMIT cannot, make sure all writes + * that use machine cred use NFS_FILE_SYNC. + */ +static inline void +nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp, + struct rpc_message *msg, struct nfs_pgio_header *hdr) +{ + if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) && + !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags)) + hdr->args.stable = NFS_FILE_SYNC; +} +#else /* CONFIG_NFS_v4_1 */ +static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server) +{ + return NULL; +} + +static inline bool +is_ds_only_client(struct nfs_client *clp) +{ + return false; +} + +static inline bool +is_ds_client(struct nfs_client *clp) +{ + return false; +} + +static inline void +nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags, + struct rpc_clnt **clntp, struct rpc_message *msg) +{ +} + +static inline void +nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp, + struct rpc_message *msg, struct nfs_pgio_header *hdr) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + +extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[]; + +extern const u32 nfs4_fattr_bitmap[3]; +extern const u32 nfs4_statfs_bitmap[3]; +extern const u32 nfs4_pathconf_bitmap[3]; +extern const u32 nfs4_fsinfo_bitmap[3]; +extern const u32 nfs4_fs_locations_bitmap[3]; + +void nfs40_shutdown_client(struct nfs_client *); +void nfs41_shutdown_client(struct nfs_client *); +int nfs40_init_client(struct nfs_client *); +int nfs41_init_client(struct nfs_client *); +void nfs4_free_client(struct nfs_client *); + +struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *); + +/* nfs4renewd.c */ +extern void nfs4_schedule_state_renewal(struct nfs_client *); +extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); +extern void nfs4_kill_renewd(struct nfs_client *); +extern void nfs4_renew_state(struct work_struct *); + +/* nfs4state.c */ +struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp); +struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp); +struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp); +int nfs4_discover_server_trunking(struct nfs_client *clp, + struct nfs_client **); +int nfs40_discover_server_trunking(struct nfs_client *clp, + struct nfs_client **, struct rpc_cred *); +#if defined(CONFIG_NFS_V4_1) +int nfs41_discover_server_trunking(struct nfs_client *clp, + struct nfs_client **, struct rpc_cred *); +extern void nfs4_schedule_session_recovery(struct nfs4_session *, int); +extern void nfs41_server_notify_target_slotid_update(struct nfs_client *clp); +extern void nfs41_server_notify_highest_slotid_update(struct nfs_client *clp); + +#else +static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + +extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t); +extern void nfs4_put_state_owner(struct nfs4_state_owner *); +extern void nfs4_purge_state_owners(struct nfs_server *); +extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); +extern void nfs4_put_open_state(struct nfs4_state *); +extern void nfs4_close_state(struct nfs4_state *, fmode_t); +extern void nfs4_close_sync(struct nfs4_state *, fmode_t); +extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t); +extern void nfs_inode_find_state_and_recover(struct inode *inode, + const nfs4_stateid *stateid); +extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *, struct nfs4_state *); +extern void nfs4_schedule_lease_recovery(struct nfs_client *); +extern int nfs4_wait_clnt_recover(struct nfs_client *clp); +extern int nfs4_client_recover_expired_lease(struct nfs_client *clp); +extern void nfs4_schedule_state_manager(struct nfs_client *); +extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp); +extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); +extern int nfs4_schedule_migration_recovery(const struct nfs_server *); +extern void nfs4_schedule_lease_moved_recovery(struct nfs_client *); +extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); +extern void nfs41_handle_server_scope(struct nfs_client *, + struct nfs41_server_scope **); +extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); +extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); +extern int nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *, + fmode_t, const struct nfs_lockowner *); + +extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask); +extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task); +extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid); +extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid); +extern void nfs_release_seqid(struct nfs_seqid *seqid); +extern void nfs_free_seqid(struct nfs_seqid *seqid); +extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task); +extern int nfs4_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res); + +extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp); + +extern const nfs4_stateid zero_stateid; + +/* nfs4super.c */ +struct nfs_mount_info; +extern struct nfs_subversion nfs_v4; +struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *); +extern bool nfs4_disable_idmapping; +extern unsigned short max_session_slots; +extern unsigned short send_implementation_id; +extern bool recover_lost_locks; + +#define NFS4_CLIENT_ID_UNIQ_LEN (64) +extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN]; + +/* nfs4sysctl.c */ +#ifdef CONFIG_SYSCTL +int nfs4_register_sysctl(void); +void nfs4_unregister_sysctl(void); +#else +static inline int nfs4_register_sysctl(void) +{ + return 0; +} + +static inline void nfs4_unregister_sysctl(void) +{ +} +#endif + +/* nfs4xdr.c */ +extern struct rpc_procinfo nfs4_procedures[]; + +struct nfs4_mount_data; + +/* callback_xdr.c */ +extern struct svc_version nfs4_callback_version1; +extern struct svc_version nfs4_callback_version4; + +static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src) +{ + return memcmp(dst, src, sizeof(*dst)) == 0; +} + +static inline bool nfs4_stateid_match_other(const nfs4_stateid *dst, const nfs4_stateid *src) +{ + return memcmp(dst->other, src->other, NFS4_STATEID_OTHER_SIZE) == 0; +} + +static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stateid *s2) +{ + return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0; +} + +static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state) +{ + return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0; +} + +#else + +#define nfs4_close_state(a, b) do { } while (0) +#define nfs4_close_sync(a, b) do { } while (0) +#define nfs4_state_protect(a, b, c, d) do { } while (0) +#define nfs4_state_protect_write(a, b, c, d) do { } while (0) + +#endif /* CONFIG_NFS_V4 */ +#endif /* __LINUX_FS_NFS_NFS4_FS.H */ diff --git a/kernel/fs/nfs/nfs4client.c b/kernel/fs/nfs/nfs4client.c new file mode 100644 index 000000000..e42be52a8 --- /dev/null +++ b/kernel/fs/nfs/nfs4client.c @@ -0,0 +1,1232 @@ +/* + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#include <linux/module.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/sunrpc/addr.h> +#include <linux/sunrpc/auth.h> +#include <linux/sunrpc/xprt.h> +#include <linux/sunrpc/bc_xprt.h> +#include <linux/sunrpc/rpc_pipe_fs.h> +#include "internal.h" +#include "callback.h" +#include "delegation.h" +#include "nfs4session.h" +#include "nfs4idmap.h" +#include "pnfs.h" +#include "netns.h" + +#define NFSDBG_FACILITY NFSDBG_CLIENT + +/* + * Get a unique NFSv4.0 callback identifier which will be used + * by the V4.0 callback service to lookup the nfs_client struct + */ +static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) +{ + int ret = 0; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + + if (clp->rpc_ops->version != 4 || minorversion != 0) + return ret; + idr_preload(GFP_KERNEL); + spin_lock(&nn->nfs_client_lock); + ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT); + if (ret >= 0) + clp->cl_cb_ident = ret; + spin_unlock(&nn->nfs_client_lock); + idr_preload_end(); + return ret < 0 ? ret : 0; +} + +#ifdef CONFIG_NFS_V4_1 +/** + * Per auth flavor data server rpc clients + */ +struct nfs4_ds_server { + struct list_head list; /* ds_clp->cl_ds_clients */ + struct rpc_clnt *rpc_clnt; +}; + +/** + * Common lookup case for DS I/O + */ +static struct nfs4_ds_server * +nfs4_find_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor) +{ + struct nfs4_ds_server *dss; + + rcu_read_lock(); + list_for_each_entry_rcu(dss, &ds_clp->cl_ds_clients, list) { + if (dss->rpc_clnt->cl_auth->au_flavor != flavor) + continue; + goto out; + } + dss = NULL; +out: + rcu_read_unlock(); + return dss; +} + +static struct nfs4_ds_server * +nfs4_add_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor, + struct nfs4_ds_server *new) +{ + struct nfs4_ds_server *dss; + + spin_lock(&ds_clp->cl_lock); + list_for_each_entry(dss, &ds_clp->cl_ds_clients, list) { + if (dss->rpc_clnt->cl_auth->au_flavor != flavor) + continue; + goto out; + } + if (new) + list_add_rcu(&new->list, &ds_clp->cl_ds_clients); + dss = new; +out: + spin_unlock(&ds_clp->cl_lock); /* need some lock to protect list */ + return dss; +} + +static struct nfs4_ds_server * +nfs4_alloc_ds_server(struct nfs_client *ds_clp, rpc_authflavor_t flavor) +{ + struct nfs4_ds_server *dss; + + dss = kmalloc(sizeof(*dss), GFP_NOFS); + if (dss == NULL) + return ERR_PTR(-ENOMEM); + + dss->rpc_clnt = rpc_clone_client_set_auth(ds_clp->cl_rpcclient, flavor); + if (IS_ERR(dss->rpc_clnt)) { + int err = PTR_ERR(dss->rpc_clnt); + kfree (dss); + return ERR_PTR(err); + } + INIT_LIST_HEAD(&dss->list); + + return dss; +} + +static void +nfs4_free_ds_server(struct nfs4_ds_server *dss) +{ + rpc_release_client(dss->rpc_clnt); + kfree(dss); +} + +/** +* Find or create a DS rpc client with th MDS server rpc client auth flavor +* in the nfs_client cl_ds_clients list. +*/ +struct rpc_clnt * +nfs4_find_or_create_ds_client(struct nfs_client *ds_clp, struct inode *inode) +{ + struct nfs4_ds_server *dss, *new; + rpc_authflavor_t flavor = NFS_SERVER(inode)->client->cl_auth->au_flavor; + + dss = nfs4_find_ds_client(ds_clp, flavor); + if (dss != NULL) + goto out; + new = nfs4_alloc_ds_server(ds_clp, flavor); + if (IS_ERR(new)) + return ERR_CAST(new); + dss = nfs4_add_ds_client(ds_clp, flavor, new); + if (dss != new) + nfs4_free_ds_server(new); +out: + return dss->rpc_clnt; +} +EXPORT_SYMBOL_GPL(nfs4_find_or_create_ds_client); + +static void +nfs4_shutdown_ds_clients(struct nfs_client *clp) +{ + struct nfs4_ds_server *dss; + LIST_HEAD(shutdown_list); + + while (!list_empty(&clp->cl_ds_clients)) { + dss = list_entry(clp->cl_ds_clients.next, + struct nfs4_ds_server, list); + list_del(&dss->list); + rpc_shutdown_client(dss->rpc_clnt); + kfree (dss); + } +} + +void nfs41_shutdown_client(struct nfs_client *clp) +{ + if (nfs4_has_session(clp)) { + nfs4_shutdown_ds_clients(clp); + nfs4_destroy_session(clp->cl_session); + nfs4_destroy_clientid(clp); + } + +} +#endif /* CONFIG_NFS_V4_1 */ + +void nfs40_shutdown_client(struct nfs_client *clp) +{ + if (clp->cl_slot_tbl) { + nfs4_shutdown_slot_table(clp->cl_slot_tbl); + kfree(clp->cl_slot_tbl); + } +} + +struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) +{ + int err; + struct nfs_client *clp = nfs_alloc_client(cl_init); + if (IS_ERR(clp)) + return clp; + + err = nfs_get_cb_ident_idr(clp, cl_init->minorversion); + if (err) + goto error; + + if (cl_init->minorversion > NFS4_MAX_MINOR_VERSION) { + err = -EINVAL; + goto error; + } + + spin_lock_init(&clp->cl_lock); + INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); + INIT_LIST_HEAD(&clp->cl_ds_clients); + rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); + clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; + clp->cl_minorversion = cl_init->minorversion; + clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; + clp->cl_mig_gen = 1; + return clp; + +error: + nfs_free_client(clp); + return ERR_PTR(err); +} + +/* + * Destroy the NFS4 callback service + */ +static void nfs4_destroy_callback(struct nfs_client *clp) +{ + if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state)) + nfs_callback_down(clp->cl_mvops->minor_version, clp->cl_net); +} + +static void nfs4_shutdown_client(struct nfs_client *clp) +{ + if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state)) + nfs4_kill_renewd(clp); + clp->cl_mvops->shutdown_client(clp); + nfs4_destroy_callback(clp); + if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state)) + nfs_idmap_delete(clp); + + rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverowner); + kfree(clp->cl_serverscope); + kfree(clp->cl_implid); + kfree(clp->cl_owner_id); +} + +void nfs4_free_client(struct nfs_client *clp) +{ + nfs4_shutdown_client(clp); + nfs_free_client(clp); +} + +/* + * Initialize the NFS4 callback service + */ +static int nfs4_init_callback(struct nfs_client *clp) +{ + struct rpc_xprt *xprt; + int error; + + xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); + + if (nfs4_has_session(clp)) { + error = xprt_setup_backchannel(xprt, NFS41_BC_MIN_CALLBACKS); + if (error < 0) + return error; + } + + error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); + if (error < 0) { + dprintk("%s: failed to start callback. Error = %d\n", + __func__, error); + return error; + } + __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); + + return 0; +} + +/** + * nfs40_init_client - nfs_client initialization tasks for NFSv4.0 + * @clp - nfs_client to initialize + * + * Returns zero on success, or a negative errno if some error occurred. + */ +int nfs40_init_client(struct nfs_client *clp) +{ + struct nfs4_slot_table *tbl; + int ret; + + tbl = kzalloc(sizeof(*tbl), GFP_NOFS); + if (tbl == NULL) + return -ENOMEM; + + ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, + "NFSv4.0 transport Slot table"); + if (ret) { + kfree(tbl); + return ret; + } + + clp->cl_slot_tbl = tbl; + return 0; +} + +#if defined(CONFIG_NFS_V4_1) + +/** + * nfs41_init_client - nfs_client initialization tasks for NFSv4.1+ + * @clp - nfs_client to initialize + * + * Returns zero on success, or a negative errno if some error occurred. + */ +int nfs41_init_client(struct nfs_client *clp) +{ + struct nfs4_session *session = NULL; + + /* + * Create the session and mark it expired. + * When a SEQUENCE operation encounters the expired session + * it will do session recovery to initialize it. + */ + session = nfs4_alloc_session(clp); + if (!session) + return -ENOMEM; + + clp->cl_session = session; + + /* + * The create session reply races with the server back + * channel probe. Mark the client NFS_CS_SESSION_INITING + * so that the client back channel can find the + * nfs_client struct + */ + nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING); + return 0; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/* + * Initialize the minor version specific parts of an NFS4 client record + */ +static int nfs4_init_client_minor_version(struct nfs_client *clp) +{ + int ret; + + ret = clp->cl_mvops->init_client(clp); + if (ret) + return ret; + return nfs4_init_callback(clp); +} + +/** + * nfs4_init_client - Initialise an NFS4 client record + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: callback IP address in presentation format + * @authflavor: authentication flavor for underlying RPC transport + * + * Returns pointer to an NFS client, or an ERR_PTR value. + */ +struct nfs_client *nfs4_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr) +{ + char buf[INET6_ADDRSTRLEN + 1]; + struct nfs_client *old; + int error; + + if (clp->cl_cons_state == NFS_CS_READY) { + /* the client is initialised already */ + dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp); + return clp; + } + + /* Check NFS protocol revision and initialize RPC op vector */ + clp->rpc_ops = &nfs_v4_clientops; + + if (clp->cl_minorversion != 0) + __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I); + if (error == -EINVAL) + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); + if (error < 0) + goto error; + + /* If no clientaddr= option was specified, find a usable cb address */ + if (ip_addr == NULL) { + struct sockaddr_storage cb_addr; + struct sockaddr *sap = (struct sockaddr *)&cb_addr; + + error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); + if (error < 0) + goto error; + error = rpc_ntop(sap, buf, sizeof(buf)); + if (error < 0) + goto error; + ip_addr = (const char *)buf; + } + strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); + + error = nfs_idmap_new(clp); + if (error < 0) { + dprintk("%s: failed to create idmapper. Error = %d\n", + __func__, error); + goto error; + } + __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); + + error = nfs4_init_client_minor_version(clp); + if (error < 0) + goto error; + + if (!nfs4_has_session(clp)) + nfs_mark_client_ready(clp, NFS_CS_READY); + + error = nfs4_discover_server_trunking(clp, &old); + if (error < 0) + goto error; + + if (clp != old) + clp->cl_preserve_clid = true; + nfs_put_client(clp); + return old; + +error: + nfs_mark_client_ready(clp, error); + nfs_put_client(clp); + dprintk("<-- nfs4_init_client() = xerror %d\n", error); + return ERR_PTR(error); +} + +/* + * SETCLIENTID just did a callback update with the callback ident in + * "drop," but server trunking discovery claims "drop" and "keep" are + * actually the same server. Swap the callback IDs so that "keep" + * will continue to use the callback ident the server now knows about, + * and so that "keep"'s original callback ident is destroyed when + * "drop" is freed. + */ +static void nfs4_swap_callback_idents(struct nfs_client *keep, + struct nfs_client *drop) +{ + struct nfs_net *nn = net_generic(keep->cl_net, nfs_net_id); + unsigned int save = keep->cl_cb_ident; + + if (keep->cl_cb_ident == drop->cl_cb_ident) + return; + + dprintk("%s: keeping callback ident %u and dropping ident %u\n", + __func__, keep->cl_cb_ident, drop->cl_cb_ident); + + spin_lock(&nn->nfs_client_lock); + + idr_replace(&nn->cb_ident_idr, keep, drop->cl_cb_ident); + keep->cl_cb_ident = drop->cl_cb_ident; + + idr_replace(&nn->cb_ident_idr, drop, save); + drop->cl_cb_ident = save; + + spin_unlock(&nn->nfs_client_lock); +} + +static bool nfs4_match_client_owner_id(const struct nfs_client *clp1, + const struct nfs_client *clp2) +{ + if (clp1->cl_owner_id == NULL || clp2->cl_owner_id == NULL) + return true; + return strcmp(clp1->cl_owner_id, clp2->cl_owner_id) == 0; +} + +/** + * nfs40_walk_client_list - Find server that recognizes a client ID + * + * @new: nfs_client with client ID to test + * @result: OUT: found nfs_client, or new + * @cred: credential to use for trunking test + * + * Returns zero, a negative errno, or a negative NFS4ERR status. + * If zero is returned, an nfs_client pointer is planted in "result." + * + * NB: nfs40_walk_client_list() relies on the new nfs_client being + * the last nfs_client on the list. + */ +int nfs40_walk_client_list(struct nfs_client *new, + struct nfs_client **result, + struct rpc_cred *cred) +{ + struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); + struct nfs_client *pos, *prev = NULL; + struct nfs4_setclientid_res clid = { + .clientid = new->cl_clientid, + .confirm = new->cl_confirm, + }; + int status = -NFS4ERR_STALE_CLIENTID; + + spin_lock(&nn->nfs_client_lock); + list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + + /* If "pos" isn't marked ready, we can't trust the + * remaining fields in "pos" */ + if (pos->cl_cons_state > NFS_CS_READY) { + atomic_inc(&pos->cl_count); + spin_unlock(&nn->nfs_client_lock); + + nfs_put_client(prev); + prev = pos; + + status = nfs_wait_client_init_complete(pos); + if (status < 0) + goto out; + status = -NFS4ERR_STALE_CLIENTID; + spin_lock(&nn->nfs_client_lock); + } + if (pos->cl_cons_state != NFS_CS_READY) + continue; + + if (pos->cl_clientid != new->cl_clientid) + continue; + + if (!nfs4_match_client_owner_id(pos, new)) + continue; + + atomic_inc(&pos->cl_count); + spin_unlock(&nn->nfs_client_lock); + + nfs_put_client(prev); + prev = pos; + + status = nfs4_proc_setclientid_confirm(pos, &clid, cred); + switch (status) { + case -NFS4ERR_STALE_CLIENTID: + break; + case 0: + nfs4_swap_callback_idents(pos, new); + + prev = NULL; + *result = pos; + dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n", + __func__, pos, atomic_read(&pos->cl_count)); + goto out; + case -ERESTARTSYS: + case -ETIMEDOUT: + /* The callback path may have been inadvertently + * changed. Schedule recovery! + */ + nfs4_schedule_path_down_recovery(pos); + default: + goto out; + } + + spin_lock(&nn->nfs_client_lock); + } + spin_unlock(&nn->nfs_client_lock); + + /* No match found. The server lost our clientid */ +out: + nfs_put_client(prev); + dprintk("NFS: <-- %s status = %d\n", __func__, status); + return status; +} + +#ifdef CONFIG_NFS_V4_1 +/* + * Returns true if the client IDs match + */ +static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b) +{ + if (a->cl_clientid != b->cl_clientid) { + dprintk("NFS: --> %s client ID %llx does not match %llx\n", + __func__, a->cl_clientid, b->cl_clientid); + return false; + } + dprintk("NFS: --> %s client ID %llx matches %llx\n", + __func__, a->cl_clientid, b->cl_clientid); + return true; +} + +/* + * Returns true if the server major ids match + */ +static bool +nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b) +{ + struct nfs41_server_owner *o1 = a->cl_serverowner; + struct nfs41_server_owner *o2 = b->cl_serverowner; + + if (o1->major_id_sz != o2->major_id_sz) + goto out_major_mismatch; + if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0) + goto out_major_mismatch; + + dprintk("NFS: --> %s server owners match\n", __func__); + return true; + +out_major_mismatch: + dprintk("NFS: --> %s server owner major IDs do not match\n", + __func__); + return false; +} + +/** + * nfs41_walk_client_list - Find nfs_client that matches a client/server owner + * + * @new: nfs_client with client ID to test + * @result: OUT: found nfs_client, or new + * @cred: credential to use for trunking test + * + * Returns zero, a negative errno, or a negative NFS4ERR status. + * If zero is returned, an nfs_client pointer is planted in "result." + * + * NB: nfs41_walk_client_list() relies on the new nfs_client being + * the last nfs_client on the list. + */ +int nfs41_walk_client_list(struct nfs_client *new, + struct nfs_client **result, + struct rpc_cred *cred) +{ + struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); + struct nfs_client *pos, *prev = NULL; + int status = -NFS4ERR_STALE_CLIENTID; + + spin_lock(&nn->nfs_client_lock); + list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos == new) + goto found; + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + + /* If "pos" isn't marked ready, we can't trust the + * remaining fields in "pos", especially the client + * ID and serverowner fields. Wait for CREATE_SESSION + * to finish. */ + if (pos->cl_cons_state > NFS_CS_READY) { + atomic_inc(&pos->cl_count); + spin_unlock(&nn->nfs_client_lock); + + nfs_put_client(prev); + prev = pos; + + status = nfs_wait_client_init_complete(pos); + spin_lock(&nn->nfs_client_lock); + if (status < 0) + break; + status = -NFS4ERR_STALE_CLIENTID; + } + if (pos->cl_cons_state != NFS_CS_READY) + continue; + + if (!nfs4_match_clientids(pos, new)) + continue; + + /* + * Note that session trunking is just a special subcase of + * client id trunking. In either case, we want to fall back + * to using the existing nfs_client. + */ + if (!nfs4_check_clientid_trunking(pos, new)) + continue; + + /* Unlike NFSv4.0, we know that NFSv4.1 always uses the + * uniform string, however someone might switch the + * uniquifier string on us. + */ + if (!nfs4_match_client_owner_id(pos, new)) + continue; +found: + atomic_inc(&pos->cl_count); + *result = pos; + status = 0; + dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n", + __func__, pos, atomic_read(&pos->cl_count)); + break; + } + + /* No matching nfs_client found. */ + spin_unlock(&nn->nfs_client_lock); + dprintk("NFS: <-- %s status = %d\n", __func__, status); + nfs_put_client(prev); + return status; +} +#endif /* CONFIG_NFS_V4_1 */ + +static void nfs4_destroy_server(struct nfs_server *server) +{ + nfs_server_return_all_delegations(server); + unset_pnfs_layoutdriver(server); + nfs4_purge_state_owners(server); +} + +/* + * NFSv4.0 callback thread helper + * + * Find a client by callback identifier + */ +struct nfs_client * +nfs4_find_client_ident(struct net *net, int cb_ident) +{ + struct nfs_client *clp; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + spin_lock(&nn->nfs_client_lock); + clp = idr_find(&nn->cb_ident_idr, cb_ident); + if (clp) + atomic_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + return clp; +} + +#if defined(CONFIG_NFS_V4_1) +/* Common match routine for v4.0 and v4.1 callback services */ +static bool nfs4_cb_match_client(const struct sockaddr *addr, + struct nfs_client *clp, u32 minorversion) +{ + struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; + + /* Don't match clients that failed to initialise */ + if (!(clp->cl_cons_state == NFS_CS_READY || + clp->cl_cons_state == NFS_CS_SESSION_INITING)) + return false; + + smp_rmb(); + + /* Match the version and minorversion */ + if (clp->rpc_ops->version != 4 || + clp->cl_minorversion != minorversion) + return false; + + /* Match only the IP address, not the port number */ + if (!nfs_sockaddr_match_ipaddr(addr, clap)) + return false; + + return true; +} + +/* + * NFSv4.1 callback thread helper + * For CB_COMPOUND calls, find a client by IP address, protocol version, + * minorversion, and sessionID + * + * Returns NULL if no such client + */ +struct nfs_client * +nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, + struct nfs4_sessionid *sid, u32 minorversion) +{ + struct nfs_client *clp; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + spin_lock(&nn->nfs_client_lock); + list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { + if (nfs4_cb_match_client(addr, clp, minorversion) == false) + continue; + + if (!nfs4_has_session(clp)) + continue; + + /* Match sessionid*/ + if (memcmp(clp->cl_session->sess_id.data, + sid->data, NFS4_MAX_SESSIONID_LEN) != 0) + continue; + + atomic_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + return clp; + } + spin_unlock(&nn->nfs_client_lock); + return NULL; +} + +#else /* CONFIG_NFS_V4_1 */ + +struct nfs_client * +nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, + struct nfs4_sessionid *sid, u32 minorversion) +{ + return NULL; +} +#endif /* CONFIG_NFS_V4_1 */ + +/* + * Set up an NFS4 client + */ +static int nfs4_set_client(struct nfs_server *server, + const char *hostname, + const struct sockaddr *addr, + const size_t addrlen, + const char *ip_addr, + rpc_authflavor_t authflavour, + int proto, const struct rpc_timeout *timeparms, + u32 minorversion, struct net *net) +{ + struct nfs_client_initdata cl_init = { + .hostname = hostname, + .addr = addr, + .addrlen = addrlen, + .nfs_mod = &nfs_v4, + .proto = proto, + .minorversion = minorversion, + .net = net, + }; + struct nfs_client *clp; + int error; + + dprintk("--> nfs4_set_client()\n"); + + if (server->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + if (server->options & NFS_OPTION_MIGRATION) + set_bit(NFS_CS_MIGRATION, &cl_init.init_flags); + + /* Allocate or find a client reference we can use */ + clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour); + if (IS_ERR(clp)) { + error = PTR_ERR(clp); + goto error; + } + + /* + * Query for the lease time on clientid setup or renewal + * + * Note that this will be set on nfs_clients that were created + * only for the DS role and did not set this bit, but now will + * serve a dual role. + */ + set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state); + + server->nfs_client = clp; + dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp); + return 0; +error: + dprintk("<-- nfs4_set_client() = xerror %d\n", error); + return error; +} + +/* + * Set up a pNFS Data Server client. + * + * Return any existing nfs_client that matches server address,port,version + * and minorversion. + * + * For a new nfs_client, use a soft mount (default), a low retrans and a + * low timeout interval so that if a connection is lost, we retry through + * the MDS. + */ +struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, + u32 minor_version, rpc_authflavor_t au_flavor) +{ + struct nfs_client_initdata cl_init = { + .addr = ds_addr, + .addrlen = ds_addrlen, + .nfs_mod = &nfs_v4, + .proto = ds_proto, + .minorversion = minor_version, + .net = mds_clp->cl_net, + }; + struct rpc_timeout ds_timeout; + struct nfs_client *clp; + char buf[INET6_ADDRSTRLEN + 1]; + + if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + return ERR_PTR(-EINVAL); + cl_init.hostname = buf; + + /* + * Set an authflavor equual to the MDS value. Use the MDS nfs_client + * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS + * (section 13.1 RFC 5661). + */ + nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); + clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, + au_flavor); + + dprintk("<-- %s %p\n", __func__, clp); + return clp; +} +EXPORT_SYMBOL_GPL(nfs4_set_ds_client); + +/* + * Session has been established, and the client marked ready. + * Set the mount rsize and wsize with negotiated fore channel + * attributes which will be bound checked in nfs_server_set_fsinfo. + */ +static void nfs4_session_set_rwsize(struct nfs_server *server) +{ +#ifdef CONFIG_NFS_V4_1 + struct nfs4_session *sess; + u32 server_resp_sz; + u32 server_rqst_sz; + + if (!nfs4_has_session(server->nfs_client)) + return; + sess = server->nfs_client->cl_session; + server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead; + server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead; + + if (server->rsize > server_resp_sz) + server->rsize = server_resp_sz; + if (server->wsize > server_rqst_sz) + server->wsize = server_rqst_sz; +#endif /* CONFIG_NFS_V4_1 */ +} + +static int nfs4_server_common_setup(struct nfs_server *server, + struct nfs_fh *mntfh, bool auth_probe) +{ + struct nfs_fattr *fattr; + int error; + + /* data servers support only a subset of NFSv4.1 */ + if (is_ds_only_client(server->nfs_client)) + return -EPROTONOSUPPORT; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + return -ENOMEM; + + /* We must ensure the session is initialised first */ + error = nfs4_init_session(server->nfs_client); + if (error < 0) + goto out; + + /* Set the basic capabilities */ + server->caps |= server->nfs_client->cl_mvops->init_caps; + if (server->flags & NFS_MOUNT_NORDIRPLUS) + server->caps &= ~NFS_CAP_READDIRPLUS; + /* + * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower + * authentication. + */ + if (nfs4_disable_idmapping && + server->client->cl_auth->au_flavor == RPC_AUTH_UNIX) + server->caps |= NFS_CAP_UIDGID_NOMAP; + + + /* Probe the root fh to retrieve its FSID and filehandle */ + error = nfs4_get_rootfh(server, mntfh, auth_probe); + if (error < 0) + goto out; + + dprintk("Server FSID: %llx:%llx\n", + (unsigned long long) server->fsid.major, + (unsigned long long) server->fsid.minor); + nfs_display_fhandle(mntfh, "Pseudo-fs root FH"); + + nfs4_session_set_rwsize(server); + + error = nfs_probe_fsinfo(server, mntfh, fattr); + if (error < 0) + goto out; + + if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) + server->namelen = NFS4_MAXNAMLEN; + + nfs_server_insert_lists(server); + server->mount_time = jiffies; + server->destroy = nfs4_destroy_server; +out: + nfs_free_fattr(fattr); + return error; +} + +/* + * Create a version 4 volume record + */ +static int nfs4_init_server(struct nfs_server *server, + struct nfs_parsed_mount_data *data) +{ + struct rpc_timeout timeparms; + int error; + + dprintk("--> nfs4_init_server()\n"); + + nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, + data->timeo, data->retrans); + + /* Initialise the client representation from the mount data */ + server->flags = data->flags; + server->options = data->options; + server->auth_info = data->auth_info; + + /* Use the first specified auth flavor. If this flavor isn't + * allowed by the server, use the SECINFO path to try the + * other specified flavors */ + if (data->auth_info.flavor_len >= 1) + data->selected_flavor = data->auth_info.flavors[0]; + else + data->selected_flavor = RPC_AUTH_UNIX; + + /* Get a client record */ + error = nfs4_set_client(server, + data->nfs_server.hostname, + (const struct sockaddr *)&data->nfs_server.address, + data->nfs_server.addrlen, + data->client_address, + data->selected_flavor, + data->nfs_server.protocol, + &timeparms, + data->minorversion, + data->net); + if (error < 0) + goto error; + + if (data->rsize) + server->rsize = nfs_block_size(data->rsize, NULL); + if (data->wsize) + server->wsize = nfs_block_size(data->wsize, NULL); + + server->acregmin = data->acregmin * HZ; + server->acregmax = data->acregmax * HZ; + server->acdirmin = data->acdirmin * HZ; + server->acdirmax = data->acdirmax * HZ; + + server->port = data->nfs_server.port; + + error = nfs_init_server_rpcclient(server, &timeparms, + data->selected_flavor); + +error: + /* Done */ + dprintk("<-- nfs4_init_server() = %d\n", error); + return error; +} + +/* + * Create a version 4 volume record + * - keyed on server and FSID + */ +/*struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data, + struct nfs_fh *mntfh)*/ +struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct nfs_server *server; + bool auth_probe; + int error; + + dprintk("--> nfs4_create_server()\n"); + + server = nfs_alloc_server(); + if (!server) + return ERR_PTR(-ENOMEM); + + auth_probe = mount_info->parsed->auth_info.flavor_len < 1; + + /* set up the general RPC client */ + error = nfs4_init_server(server, mount_info->parsed); + if (error < 0) + goto error; + + error = nfs4_server_common_setup(server, mount_info->mntfh, auth_probe); + if (error < 0) + goto error; + + dprintk("<-- nfs4_create_server() = %p\n", server); + return server; + +error: + nfs_free_server(server); + dprintk("<-- nfs4_create_server() = error %d\n", error); + return ERR_PTR(error); +} + +/* + * Create an NFS4 referral server record + */ +struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, + struct nfs_fh *mntfh) +{ + struct nfs_client *parent_client; + struct nfs_server *server, *parent_server; + bool auth_probe; + int error; + + dprintk("--> nfs4_create_referral_server()\n"); + + server = nfs_alloc_server(); + if (!server) + return ERR_PTR(-ENOMEM); + + parent_server = NFS_SB(data->sb); + parent_client = parent_server->nfs_client; + + /* Initialise the client representation from the parent server */ + nfs_server_copy_userdata(server, parent_server); + + /* Get a client representation. + * Note: NFSv4 always uses TCP, */ + error = nfs4_set_client(server, data->hostname, + data->addr, + data->addrlen, + parent_client->cl_ipaddr, + data->authflavor, + rpc_protocol(parent_server->client), + parent_server->client->cl_timeout, + parent_client->cl_mvops->minor_version, + parent_client->cl_net); + if (error < 0) + goto error; + + error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor); + if (error < 0) + goto error; + + auth_probe = parent_server->auth_info.flavor_len < 1; + + error = nfs4_server_common_setup(server, mntfh, auth_probe); + if (error < 0) + goto error; + + dprintk("<-- nfs_create_referral_server() = %p\n", server); + return server; + +error: + nfs_free_server(server); + dprintk("<-- nfs4_create_referral_server() = error %d\n", error); + return ERR_PTR(error); +} + +/* + * Grab the destination's particulars, including lease expiry time. + * + * Returns zero if probe succeeded and retrieved FSID matches the FSID + * we have cached. + */ +static int nfs_probe_destination(struct nfs_server *server) +{ + struct inode *inode = d_inode(server->super->s_root); + struct nfs_fattr *fattr; + int error; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + return -ENOMEM; + + /* Sanity: the probe won't work if the destination server + * does not recognize the migrated FH. */ + error = nfs_probe_fsinfo(server, NFS_FH(inode), fattr); + + nfs_free_fattr(fattr); + return error; +} + +/** + * nfs4_update_server - Move an nfs_server to a different nfs_client + * + * @server: represents FSID to be moved + * @hostname: new end-point's hostname + * @sap: new end-point's socket address + * @salen: size of "sap" + * @net: net namespace + * + * The nfs_server must be quiescent before this function is invoked. + * Either its session is drained (NFSv4.1+), or its transport is + * plugged and drained (NFSv4.0). + * + * Returns zero on success, or a negative errno value. + */ +int nfs4_update_server(struct nfs_server *server, const char *hostname, + struct sockaddr *sap, size_t salen, struct net *net) +{ + struct nfs_client *clp = server->nfs_client; + struct rpc_clnt *clnt = server->client; + struct xprt_create xargs = { + .ident = clp->cl_proto, + .net = net, + .dstaddr = sap, + .addrlen = salen, + .servername = hostname, + }; + char buf[INET6_ADDRSTRLEN + 1]; + struct sockaddr_storage address; + struct sockaddr *localaddr = (struct sockaddr *)&address; + int error; + + dprintk("--> %s: move FSID %llx:%llx to \"%s\")\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + hostname); + + error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout); + if (error != 0) { + dprintk("<-- %s(): rpc_switch_client_transport returned %d\n", + __func__, error); + goto out; + } + + error = rpc_localaddr(clnt, localaddr, sizeof(address)); + if (error != 0) { + dprintk("<-- %s(): rpc_localaddr returned %d\n", + __func__, error); + goto out; + } + + error = -EAFNOSUPPORT; + if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0) { + dprintk("<-- %s(): rpc_ntop returned %d\n", + __func__, error); + goto out; + } + + nfs_server_remove_lists(server); + error = nfs4_set_client(server, hostname, sap, salen, buf, + clp->cl_rpcclient->cl_auth->au_flavor, + clp->cl_proto, clnt->cl_timeout, + clp->cl_minorversion, net); + nfs_put_client(clp); + if (error != 0) { + nfs_server_insert_lists(server); + dprintk("<-- %s(): nfs4_set_client returned %d\n", + __func__, error); + goto out; + } + + if (server->nfs_client->cl_hostname == NULL) + server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + nfs_server_insert_lists(server); + + error = nfs_probe_destination(server); + if (error < 0) + goto out; + + dprintk("<-- %s() succeeded\n", __func__); + +out: + return error; +} diff --git a/kernel/fs/nfs/nfs4file.c b/kernel/fs/nfs/nfs4file.c new file mode 100644 index 000000000..f58c17b3b --- /dev/null +++ b/kernel/fs/nfs/nfs4file.c @@ -0,0 +1,189 @@ +/* + * linux/fs/nfs/file.c + * + * Copyright (C) 1992 Rick Sladkey + */ +#include <linux/fs.h> +#include <linux/falloc.h> +#include <linux/nfs_fs.h> +#include "internal.h" +#include "fscache.h" +#include "pnfs.h" + +#include "nfstrace.h" + +#ifdef CONFIG_NFS_V4_2 +#include "nfs42.h" +#endif + +#define NFSDBG_FACILITY NFSDBG_FILE + +static int +nfs4_file_open(struct inode *inode, struct file *filp) +{ + struct nfs_open_context *ctx; + struct dentry *dentry = filp->f_path.dentry; + struct dentry *parent = NULL; + struct inode *dir; + unsigned openflags = filp->f_flags; + struct iattr attr; + int opened = 0; + int err; + + /* + * If no cached dentry exists or if it's negative, NFSv4 handled the + * opens in ->lookup() or ->create(). + * + * We only get this far for a cached positive dentry. We skipped + * revalidation, so handle it here by dropping the dentry and returning + * -EOPENSTALE. The VFS will retry the lookup/create/open. + */ + + dprintk("NFS: open file(%pd2)\n", dentry); + + if ((openflags & O_ACCMODE) == 3) + openflags--; + + /* We can't create new files here */ + openflags &= ~(O_CREAT|O_EXCL); + + parent = dget_parent(dentry); + dir = d_inode(parent); + + ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + + attr.ia_valid = ATTR_OPEN; + if (openflags & O_TRUNC) { + attr.ia_valid |= ATTR_SIZE; + attr.ia_size = 0; + nfs_sync_inode(inode); + } + + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, &opened); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + switch (err) { + case -EPERM: + case -EACCES: + case -EDQUOT: + case -ENOSPC: + case -EROFS: + goto out_put_ctx; + default: + goto out_drop; + } + } + if (inode != d_inode(dentry)) + goto out_drop; + + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + nfs_file_set_open_context(filp, ctx); + nfs_fscache_open_file(inode, filp); + err = 0; + +out_put_ctx: + put_nfs_open_context(ctx); +out: + dput(parent); + return err; + +out_drop: + d_drop(dentry); + err = -EOPENSTALE; + goto out_put_ctx; +} + +static int +nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + int ret; + struct inode *inode = file_inode(file); + + trace_nfs_fsync_enter(inode); + + nfs_inode_dio_wait(inode); + do { + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret != 0) + break; + mutex_lock(&inode->i_mutex); + ret = nfs_file_fsync_commit(file, start, end, datasync); + if (!ret) + ret = pnfs_sync_inode(inode, !!datasync); + mutex_unlock(&inode->i_mutex); + /* + * If nfs_file_fsync_commit detected a server reboot, then + * resend all dirty pages that might have been covered by + * the NFS_CONTEXT_RESEND_WRITES flag + */ + start = 0; + end = LLONG_MAX; + } while (ret == -EAGAIN); + + trace_nfs_fsync_exit(inode, ret); + return ret; +} + +#ifdef CONFIG_NFS_V4_2 +static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) +{ + loff_t ret; + + switch (whence) { + case SEEK_HOLE: + case SEEK_DATA: + ret = nfs42_proc_llseek(filep, offset, whence); + if (ret != -ENOTSUPP) + return ret; + default: + return nfs_file_llseek(filep, offset, whence); + } +} + +static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + long ret; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE))) + return -EOPNOTSUPP; + + ret = inode_newsize_ok(inode, offset + len); + if (ret < 0) + return ret; + + if (mode & FALLOC_FL_PUNCH_HOLE) + return nfs42_proc_deallocate(filep, offset, len); + return nfs42_proc_allocate(filep, offset, len); +} +#endif /* CONFIG_NFS_V4_2 */ + +const struct file_operations nfs4_file_operations = { +#ifdef CONFIG_NFS_V4_2 + .llseek = nfs4_file_llseek, +#else + .llseek = nfs_file_llseek, +#endif + .read_iter = nfs_file_read, + .write_iter = nfs_file_write, + .mmap = nfs_file_mmap, + .open = nfs4_file_open, + .flush = nfs_file_flush, + .release = nfs_file_release, + .fsync = nfs4_file_fsync, + .lock = nfs_lock, + .flock = nfs_flock, + .splice_read = nfs_file_splice_read, + .splice_write = iter_file_splice_write, +#ifdef CONFIG_NFS_V4_2 + .fallocate = nfs42_fallocate, +#endif /* CONFIG_NFS_V4_2 */ + .check_flags = nfs_check_flags, + .setlease = simple_nosetlease, +}; diff --git a/kernel/fs/nfs/nfs4getroot.c b/kernel/fs/nfs/nfs4getroot.c new file mode 100644 index 000000000..c0b3a16b4 --- /dev/null +++ b/kernel/fs/nfs/nfs4getroot.c @@ -0,0 +1,50 @@ +/* +* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. +* Written by David Howells (dhowells@redhat.com) +*/ + +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_CLIENT + +int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_probe) +{ + struct nfs_fsinfo fsinfo; + int ret = -ENOMEM; + + dprintk("--> nfs4_get_rootfh()\n"); + + fsinfo.fattr = nfs_alloc_fattr(); + if (fsinfo.fattr == NULL) + goto out; + + /* Start by getting the root filehandle from the server */ + ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo, auth_probe); + if (ret < 0) { + dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret); + goto out; + } + + if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE) + || !S_ISDIR(fsinfo.fattr->mode)) { + printk(KERN_ERR "nfs4_get_rootfh:" + " getroot encountered non-directory\n"); + ret = -ENOTDIR; + goto out; + } + + if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { + printk(KERN_ERR "nfs4_get_rootfh:" + " getroot obtained referral\n"); + ret = -EREMOTE; + goto out; + } + + memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid)); +out: + nfs_free_fattr(fsinfo.fattr); + dprintk("<-- nfs4_get_rootfh() = %d\n", ret); + return ret; +} diff --git a/kernel/fs/nfs/nfs4idmap.c b/kernel/fs/nfs/nfs4idmap.c new file mode 100644 index 000000000..2e1737c40 --- /dev/null +++ b/kernel/fs/nfs/nfs4idmap.c @@ -0,0 +1,792 @@ +/* + * fs/nfs/idmap.c + * + * UID and GID to name mapping for clients. + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Marius Aamodt Eriksen <marius@umich.edu> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#include <linux/types.h> +#include <linux/parser.h> +#include <linux/fs.h> +#include <net/net_namespace.h> +#include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_fs_sb.h> +#include <linux/key.h> +#include <linux/keyctl.h> +#include <linux/key-type.h> +#include <keys/user-type.h> +#include <linux/module.h> + +#include "internal.h" +#include "netns.h" +#include "nfs4idmap.h" +#include "nfs4trace.h" + +#define NFS_UINT_MAXLEN 11 + +static const struct cred *id_resolver_cache; +static struct key_type key_type_id_resolver_legacy; + +struct idmap_legacy_upcalldata { + struct rpc_pipe_msg pipe_msg; + struct idmap_msg idmap_msg; + struct key_construction *key_cons; + struct idmap *idmap; +}; + +struct idmap { + struct rpc_pipe_dir_object idmap_pdo; + struct rpc_pipe *idmap_pipe; + struct idmap_legacy_upcalldata *idmap_upcall_data; + struct mutex idmap_mutex; +}; + +/** + * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields + * @fattr: fully initialised struct nfs_fattr + * @owner_name: owner name string cache + * @group_name: group name string cache + */ +void nfs_fattr_init_names(struct nfs_fattr *fattr, + struct nfs4_string *owner_name, + struct nfs4_string *group_name) +{ + fattr->owner_name = owner_name; + fattr->group_name = group_name; +} + +static void nfs_fattr_free_owner_name(struct nfs_fattr *fattr) +{ + fattr->valid &= ~NFS_ATTR_FATTR_OWNER_NAME; + kfree(fattr->owner_name->data); +} + +static void nfs_fattr_free_group_name(struct nfs_fattr *fattr) +{ + fattr->valid &= ~NFS_ATTR_FATTR_GROUP_NAME; + kfree(fattr->group_name->data); +} + +static bool nfs_fattr_map_owner_name(struct nfs_server *server, struct nfs_fattr *fattr) +{ + struct nfs4_string *owner = fattr->owner_name; + kuid_t uid; + + if (!(fattr->valid & NFS_ATTR_FATTR_OWNER_NAME)) + return false; + if (nfs_map_name_to_uid(server, owner->data, owner->len, &uid) == 0) { + fattr->uid = uid; + fattr->valid |= NFS_ATTR_FATTR_OWNER; + } + return true; +} + +static bool nfs_fattr_map_group_name(struct nfs_server *server, struct nfs_fattr *fattr) +{ + struct nfs4_string *group = fattr->group_name; + kgid_t gid; + + if (!(fattr->valid & NFS_ATTR_FATTR_GROUP_NAME)) + return false; + if (nfs_map_group_to_gid(server, group->data, group->len, &gid) == 0) { + fattr->gid = gid; + fattr->valid |= NFS_ATTR_FATTR_GROUP; + } + return true; +} + +/** + * nfs_fattr_free_names - free up the NFSv4 owner and group strings + * @fattr: a fully initialised nfs_fattr structure + */ +void nfs_fattr_free_names(struct nfs_fattr *fattr) +{ + if (fattr->valid & NFS_ATTR_FATTR_OWNER_NAME) + nfs_fattr_free_owner_name(fattr); + if (fattr->valid & NFS_ATTR_FATTR_GROUP_NAME) + nfs_fattr_free_group_name(fattr); +} + +/** + * nfs_fattr_map_and_free_names - map owner/group strings into uid/gid and free + * @server: pointer to the filesystem nfs_server structure + * @fattr: a fully initialised nfs_fattr structure + * + * This helper maps the cached NFSv4 owner/group strings in fattr into + * their numeric uid/gid equivalents, and then frees the cached strings. + */ +void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *fattr) +{ + if (nfs_fattr_map_owner_name(server, fattr)) + nfs_fattr_free_owner_name(fattr); + if (nfs_fattr_map_group_name(server, fattr)) + nfs_fattr_free_group_name(fattr); +} + +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res) +{ + unsigned long val; + char buf[16]; + + if (memchr(name, '@', namelen) != NULL || namelen >= sizeof(buf)) + return 0; + memcpy(buf, name, namelen); + buf[namelen] = '\0'; + if (kstrtoul(buf, 0, &val) != 0) + return 0; + *res = val; + return 1; +} +EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric); + +static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen) +{ + return snprintf(buf, buflen, "%u", id); +} + +static struct key_type key_type_id_resolver = { + .name = "id_resolver", + .preparse = user_preparse, + .free_preparse = user_free_preparse, + .instantiate = generic_key_instantiate, + .revoke = user_revoke, + .destroy = user_destroy, + .describe = user_describe, + .read = user_read, +}; + +static int nfs_idmap_init_keyring(void) +{ + struct cred *cred; + struct key *keyring; + int ret = 0; + + printk(KERN_NOTICE "NFS: Registering the %s key type\n", + key_type_id_resolver.name); + + cred = prepare_kernel_cred(NULL); + if (!cred) + return -ENOMEM; + + keyring = keyring_alloc(".id_resolver", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA, NULL); + if (IS_ERR(keyring)) { + ret = PTR_ERR(keyring); + goto failed_put_cred; + } + + ret = register_key_type(&key_type_id_resolver); + if (ret < 0) + goto failed_put_key; + + ret = register_key_type(&key_type_id_resolver_legacy); + if (ret < 0) + goto failed_reg_legacy; + + set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags); + cred->thread_keyring = keyring; + cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; + id_resolver_cache = cred; + return 0; + +failed_reg_legacy: + unregister_key_type(&key_type_id_resolver); +failed_put_key: + key_put(keyring); +failed_put_cred: + put_cred(cred); + return ret; +} + +static void nfs_idmap_quit_keyring(void) +{ + key_revoke(id_resolver_cache->thread_keyring); + unregister_key_type(&key_type_id_resolver); + unregister_key_type(&key_type_id_resolver_legacy); + put_cred(id_resolver_cache); +} + +/* + * Assemble the description to pass to request_key() + * This function will allocate a new string and update dest to point + * at it. The caller is responsible for freeing dest. + * + * On error 0 is returned. Otherwise, the length of dest is returned. + */ +static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen, + const char *type, size_t typelen, char **desc) +{ + char *cp; + size_t desclen = typelen + namelen + 2; + + *desc = kmalloc(desclen, GFP_KERNEL); + if (!*desc) + return -ENOMEM; + + cp = *desc; + memcpy(cp, type, typelen); + cp += typelen; + *cp++ = ':'; + + memcpy(cp, name, namelen); + cp += namelen; + *cp = '\0'; + return desclen; +} + +static struct key *nfs_idmap_request_key(const char *name, size_t namelen, + const char *type, struct idmap *idmap) +{ + char *desc; + struct key *rkey; + ssize_t ret; + + ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); + if (ret <= 0) + return ERR_PTR(ret); + + rkey = request_key(&key_type_id_resolver, desc, ""); + if (IS_ERR(rkey)) { + mutex_lock(&idmap->idmap_mutex); + rkey = request_key_with_auxdata(&key_type_id_resolver_legacy, + desc, "", 0, idmap); + mutex_unlock(&idmap->idmap_mutex); + } + if (!IS_ERR(rkey)) + set_bit(KEY_FLAG_ROOT_CAN_INVAL, &rkey->flags); + + kfree(desc); + return rkey; +} + +static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, + const char *type, void *data, + size_t data_size, struct idmap *idmap) +{ + const struct cred *saved_cred; + struct key *rkey; + struct user_key_payload *payload; + ssize_t ret; + + saved_cred = override_creds(id_resolver_cache); + rkey = nfs_idmap_request_key(name, namelen, type, idmap); + revert_creds(saved_cred); + + if (IS_ERR(rkey)) { + ret = PTR_ERR(rkey); + goto out; + } + + rcu_read_lock(); + rkey->perm |= KEY_USR_VIEW; + + ret = key_validate(rkey); + if (ret < 0) + goto out_up; + + payload = rcu_dereference(rkey->payload.rcudata); + if (IS_ERR_OR_NULL(payload)) { + ret = PTR_ERR(payload); + goto out_up; + } + + ret = payload->datalen; + if (ret > 0 && ret <= data_size) + memcpy(data, payload->data, ret); + else + ret = -EINVAL; + +out_up: + rcu_read_unlock(); + key_put(rkey); +out: + return ret; +} + +/* ID -> Name */ +static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, + size_t buflen, struct idmap *idmap) +{ + char id_str[NFS_UINT_MAXLEN]; + int id_len; + ssize_t ret; + + id_len = snprintf(id_str, sizeof(id_str), "%u", id); + ret = nfs_idmap_get_key(id_str, id_len, type, buf, buflen, idmap); + if (ret < 0) + return -EINVAL; + return ret; +} + +/* Name -> ID */ +static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *type, + __u32 *id, struct idmap *idmap) +{ + char id_str[NFS_UINT_MAXLEN]; + long id_long; + ssize_t data_size; + int ret = 0; + + data_size = nfs_idmap_get_key(name, namelen, type, id_str, NFS_UINT_MAXLEN, idmap); + if (data_size <= 0) { + ret = -EINVAL; + } else { + ret = kstrtol(id_str, 10, &id_long); + *id = (__u32)id_long; + } + return ret; +} + +/* idmap classic begins here */ + +enum { + Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err +}; + +static const match_table_t nfs_idmap_tokens = { + { Opt_find_uid, "uid:%s" }, + { Opt_find_gid, "gid:%s" }, + { Opt_find_user, "user:%s" }, + { Opt_find_group, "group:%s" }, + { Opt_find_err, NULL } +}; + +static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); +static ssize_t idmap_pipe_downcall(struct file *, const char __user *, + size_t); +static void idmap_release_pipe(struct inode *); +static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); + +static const struct rpc_pipe_ops idmap_upcall_ops = { + .upcall = rpc_pipe_generic_upcall, + .downcall = idmap_pipe_downcall, + .release_pipe = idmap_release_pipe, + .destroy_msg = idmap_pipe_destroy_msg, +}; + +static struct key_type key_type_id_resolver_legacy = { + .name = "id_legacy", + .preparse = user_preparse, + .free_preparse = user_free_preparse, + .instantiate = generic_key_instantiate, + .revoke = user_revoke, + .destroy = user_destroy, + .describe = user_describe, + .read = user_read, + .request_key = nfs_idmap_legacy_upcall, +}; + +static void nfs_idmap_pipe_destroy(struct dentry *dir, + struct rpc_pipe_dir_object *pdo) +{ + struct idmap *idmap = pdo->pdo_data; + struct rpc_pipe *pipe = idmap->idmap_pipe; + + if (pipe->dentry) { + rpc_unlink(pipe->dentry); + pipe->dentry = NULL; + } +} + +static int nfs_idmap_pipe_create(struct dentry *dir, + struct rpc_pipe_dir_object *pdo) +{ + struct idmap *idmap = pdo->pdo_data; + struct rpc_pipe *pipe = idmap->idmap_pipe; + struct dentry *dentry; + + dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + pipe->dentry = dentry; + return 0; +} + +static const struct rpc_pipe_dir_object_ops nfs_idmap_pipe_dir_object_ops = { + .create = nfs_idmap_pipe_create, + .destroy = nfs_idmap_pipe_destroy, +}; + +int +nfs_idmap_new(struct nfs_client *clp) +{ + struct idmap *idmap; + struct rpc_pipe *pipe; + int error; + + idmap = kzalloc(sizeof(*idmap), GFP_KERNEL); + if (idmap == NULL) + return -ENOMEM; + + rpc_init_pipe_dir_object(&idmap->idmap_pdo, + &nfs_idmap_pipe_dir_object_ops, + idmap); + + pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0); + if (IS_ERR(pipe)) { + error = PTR_ERR(pipe); + goto err; + } + idmap->idmap_pipe = pipe; + mutex_init(&idmap->idmap_mutex); + + error = rpc_add_pipe_dir_object(clp->cl_net, + &clp->cl_rpcclient->cl_pipedir_objects, + &idmap->idmap_pdo); + if (error) + goto err_destroy_pipe; + + clp->cl_idmap = idmap; + return 0; +err_destroy_pipe: + rpc_destroy_pipe_data(idmap->idmap_pipe); +err: + kfree(idmap); + return error; +} + +void +nfs_idmap_delete(struct nfs_client *clp) +{ + struct idmap *idmap = clp->cl_idmap; + + if (!idmap) + return; + clp->cl_idmap = NULL; + rpc_remove_pipe_dir_object(clp->cl_net, + &clp->cl_rpcclient->cl_pipedir_objects, + &idmap->idmap_pdo); + rpc_destroy_pipe_data(idmap->idmap_pipe); + kfree(idmap); +} + +int nfs_idmap_init(void) +{ + int ret; + ret = nfs_idmap_init_keyring(); + if (ret != 0) + goto out; +out: + return ret; +} + +void nfs_idmap_quit(void) +{ + nfs_idmap_quit_keyring(); +} + +static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, + struct idmap_msg *im, + struct rpc_pipe_msg *msg) +{ + substring_t substr; + int token, ret; + + im->im_type = IDMAP_TYPE_GROUP; + token = match_token(desc, nfs_idmap_tokens, &substr); + + switch (token) { + case Opt_find_uid: + im->im_type = IDMAP_TYPE_USER; + case Opt_find_gid: + im->im_conv = IDMAP_CONV_NAMETOID; + ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ); + break; + + case Opt_find_user: + im->im_type = IDMAP_TYPE_USER; + case Opt_find_group: + im->im_conv = IDMAP_CONV_IDTONAME; + ret = match_int(&substr, &im->im_id); + break; + + default: + ret = -EINVAL; + goto out; + } + + msg->data = im; + msg->len = sizeof(struct idmap_msg); + +out: + return ret; +} + +static bool +nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, + struct idmap_legacy_upcalldata *data) +{ + if (idmap->idmap_upcall_data != NULL) { + WARN_ON_ONCE(1); + return false; + } + idmap->idmap_upcall_data = data; + return true; +} + +static void +nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) +{ + struct key_construction *cons = idmap->idmap_upcall_data->key_cons; + + kfree(idmap->idmap_upcall_data); + idmap->idmap_upcall_data = NULL; + complete_request_key(cons, ret); +} + +static void +nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) +{ + if (idmap->idmap_upcall_data != NULL) + nfs_idmap_complete_pipe_upcall_locked(idmap, ret); +} + +static int nfs_idmap_legacy_upcall(struct key_construction *cons, + const char *op, + void *aux) +{ + struct idmap_legacy_upcalldata *data; + struct rpc_pipe_msg *msg; + struct idmap_msg *im; + struct idmap *idmap = (struct idmap *)aux; + struct key *key = cons->key; + int ret = -ENOMEM; + + /* msg and im are freed in idmap_pipe_destroy_msg */ + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out1; + + msg = &data->pipe_msg; + im = &data->idmap_msg; + data->idmap = idmap; + data->key_cons = cons; + + ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); + if (ret < 0) + goto out2; + + ret = -EAGAIN; + if (!nfs_idmap_prepare_pipe_upcall(idmap, data)) + goto out2; + + ret = rpc_queue_upcall(idmap->idmap_pipe, msg); + if (ret < 0) + nfs_idmap_abort_pipe_upcall(idmap, ret); + + return ret; +out2: + kfree(data); +out1: + complete_request_key(cons, ret); + return ret; +} + +static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data, size_t datalen) +{ + return key_instantiate_and_link(key, data, datalen, + id_resolver_cache->thread_keyring, + authkey); +} + +static int nfs_idmap_read_and_verify_message(struct idmap_msg *im, + struct idmap_msg *upcall, + struct key *key, struct key *authkey) +{ + char id_str[NFS_UINT_MAXLEN]; + size_t len; + int ret = -ENOKEY; + + /* ret = -ENOKEY */ + if (upcall->im_type != im->im_type || upcall->im_conv != im->im_conv) + goto out; + switch (im->im_conv) { + case IDMAP_CONV_NAMETOID: + if (strcmp(upcall->im_name, im->im_name) != 0) + break; + /* Note: here we store the NUL terminator too */ + len = sprintf(id_str, "%d", im->im_id) + 1; + ret = nfs_idmap_instantiate(key, authkey, id_str, len); + break; + case IDMAP_CONV_IDTONAME: + if (upcall->im_id != im->im_id) + break; + len = strlen(im->im_name); + ret = nfs_idmap_instantiate(key, authkey, im->im_name, len); + break; + default: + ret = -EINVAL; + } +out: + return ret; +} + +static ssize_t +idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) +{ + struct rpc_inode *rpci = RPC_I(file_inode(filp)); + struct idmap *idmap = (struct idmap *)rpci->private; + struct key_construction *cons; + struct idmap_msg im; + size_t namelen_in; + int ret = -ENOKEY; + + /* If instantiation is successful, anyone waiting for key construction + * will have been woken up and someone else may now have used + * idmap_key_cons - so after this point we may no longer touch it. + */ + if (idmap->idmap_upcall_data == NULL) + goto out_noupcall; + + cons = idmap->idmap_upcall_data->key_cons; + + if (mlen != sizeof(im)) { + ret = -ENOSPC; + goto out; + } + + if (copy_from_user(&im, src, mlen) != 0) { + ret = -EFAULT; + goto out; + } + + if (!(im.im_status & IDMAP_STATUS_SUCCESS)) { + ret = -ENOKEY; + goto out; + } + + namelen_in = strnlen(im.im_name, IDMAP_NAMESZ); + if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) { + ret = -EINVAL; + goto out; +} + + ret = nfs_idmap_read_and_verify_message(&im, + &idmap->idmap_upcall_data->idmap_msg, + cons->key, cons->authkey); + if (ret >= 0) { + key_set_timeout(cons->key, nfs_idmap_cache_timeout); + ret = mlen; + } + +out: + nfs_idmap_complete_pipe_upcall_locked(idmap, ret); +out_noupcall: + return ret; +} + +static void +idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) +{ + struct idmap_legacy_upcalldata *data = container_of(msg, + struct idmap_legacy_upcalldata, + pipe_msg); + struct idmap *idmap = data->idmap; + + if (msg->errno) + nfs_idmap_abort_pipe_upcall(idmap, msg->errno); +} + +static void +idmap_release_pipe(struct inode *inode) +{ + struct rpc_inode *rpci = RPC_I(inode); + struct idmap *idmap = (struct idmap *)rpci->private; + + nfs_idmap_abort_pipe_upcall(idmap, -EPIPE); +} + +int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid) +{ + struct idmap *idmap = server->nfs_client->cl_idmap; + __u32 id = -1; + int ret = 0; + + if (!nfs_map_string_to_numeric(name, namelen, &id)) + ret = nfs_idmap_lookup_id(name, namelen, "uid", &id, idmap); + if (ret == 0) { + *uid = make_kuid(&init_user_ns, id); + if (!uid_valid(*uid)) + ret = -ERANGE; + } + trace_nfs4_map_name_to_uid(name, namelen, id, ret); + return ret; +} + +int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, kgid_t *gid) +{ + struct idmap *idmap = server->nfs_client->cl_idmap; + __u32 id = -1; + int ret = 0; + + if (!nfs_map_string_to_numeric(name, namelen, &id)) + ret = nfs_idmap_lookup_id(name, namelen, "gid", &id, idmap); + if (ret == 0) { + *gid = make_kgid(&init_user_ns, id); + if (!gid_valid(*gid)) + ret = -ERANGE; + } + trace_nfs4_map_group_to_gid(name, namelen, id, ret); + return ret; +} + +int nfs_map_uid_to_name(const struct nfs_server *server, kuid_t uid, char *buf, size_t buflen) +{ + struct idmap *idmap = server->nfs_client->cl_idmap; + int ret = -EINVAL; + __u32 id; + + id = from_kuid(&init_user_ns, uid); + if (!(server->caps & NFS_CAP_UIDGID_NOMAP)) + ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap); + if (ret < 0) + ret = nfs_map_numeric_to_string(id, buf, buflen); + trace_nfs4_map_uid_to_name(buf, ret, id, ret); + return ret; +} +int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, size_t buflen) +{ + struct idmap *idmap = server->nfs_client->cl_idmap; + int ret = -EINVAL; + __u32 id; + + id = from_kgid(&init_user_ns, gid); + if (!(server->caps & NFS_CAP_UIDGID_NOMAP)) + ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap); + if (ret < 0) + ret = nfs_map_numeric_to_string(id, buf, buflen); + trace_nfs4_map_gid_to_group(buf, ret, id, ret); + return ret; +} diff --git a/kernel/fs/nfs/nfs4idmap.h b/kernel/fs/nfs/nfs4idmap.h new file mode 100644 index 000000000..de44d7330 --- /dev/null +++ b/kernel/fs/nfs/nfs4idmap.h @@ -0,0 +1,68 @@ +/* + * fs/nfs/nfs4idmap.h + * + * UID and GID to name mapping for clients. + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Marius Aamodt Eriksen <marius@umich.edu> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef NFS_IDMAP_H +#define NFS_IDMAP_H + +#include <linux/uidgid.h> +#include <uapi/linux/nfs_idmap.h> + + +/* Forward declaration to make this header independent of others */ +struct nfs_client; +struct nfs_server; +struct nfs_fattr; +struct nfs4_string; + +int nfs_idmap_init(void); +void nfs_idmap_quit(void); +int nfs_idmap_new(struct nfs_client *); +void nfs_idmap_delete(struct nfs_client *); + +void nfs_fattr_init_names(struct nfs_fattr *fattr, + struct nfs4_string *owner_name, + struct nfs4_string *group_name); +void nfs_fattr_free_names(struct nfs_fattr *); +void nfs_fattr_map_and_free_names(struct nfs_server *, struct nfs_fattr *); + +int nfs_map_name_to_uid(const struct nfs_server *, const char *, size_t, kuid_t *); +int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t *); +int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t); +int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t); + +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res); + +extern unsigned int nfs_idmap_cache_timeout; +#endif /* NFS_IDMAP_H */ diff --git a/kernel/fs/nfs/nfs4namespace.c b/kernel/fs/nfs/nfs4namespace.c new file mode 100644 index 000000000..f59267237 --- /dev/null +++ b/kernel/fs/nfs/nfs4namespace.c @@ -0,0 +1,523 @@ +/* + * linux/fs/nfs/nfs4namespace.c + * + * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com> + * - Modified by David Howells <dhowells@redhat.com> + * + * NFSv4 namespace + */ + +#include <linux/dcache.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> +#include <linux/vfs.h> +#include <linux/inet.h> +#include "internal.h" +#include "nfs4_fs.h" +#include "dns_resolve.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +/* + * Convert the NFSv4 pathname components into a standard posix path. + * + * Note that the resulting string will be placed at the end of the buffer + */ +static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname, + char *buffer, ssize_t buflen) +{ + char *end = buffer + buflen; + int n; + + *--end = '\0'; + buflen--; + + n = pathname->ncomponents; + while (--n >= 0) { + const struct nfs4_string *component = &pathname->components[n]; + buflen -= component->len + 1; + if (buflen < 0) + goto Elong; + end -= component->len; + memcpy(end, component->data, component->len); + *--end = '/'; + } + return end; +Elong: + return ERR_PTR(-ENAMETOOLONG); +} + +/* + * return the path component of "<server>:<path>" + * nfspath - the "<server>:<path>" string + * end - one past the last char that could contain "<server>:" + * returns NULL on failure + */ +static char *nfs_path_component(const char *nfspath, const char *end) +{ + char *p; + + if (*nfspath == '[') { + /* parse [] escaped IPv6 addrs */ + p = strchr(nfspath, ']'); + if (p != NULL && ++p < end && *p == ':') + return p + 1; + } else { + /* otherwise split on first colon */ + p = strchr(nfspath, ':'); + if (p != NULL && p < end) + return p + 1; + } + return NULL; +} + +/* + * Determine the mount path as a string + */ +static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) +{ + char *limit; + char *path = nfs_path(&limit, dentry, buffer, buflen, + NFS_PATH_CANONICAL); + if (!IS_ERR(path)) { + char *path_component = nfs_path_component(path, limit); + if (path_component) + return path_component; + } + return path; +} + +/* + * Check that fs_locations::fs_root [RFC3530 6.3] is a prefix for what we + * believe to be the server path to this dentry + */ +static int nfs4_validate_fspath(struct dentry *dentry, + const struct nfs4_fs_locations *locations, + char *page, char *page2) +{ + const char *path, *fs_path; + + path = nfs4_path(dentry, page, PAGE_SIZE); + if (IS_ERR(path)) + return PTR_ERR(path); + + fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE); + if (IS_ERR(fs_path)) + return PTR_ERR(fs_path); + + if (strncmp(path, fs_path, strlen(fs_path)) != 0) { + dprintk("%s: path %s does not begin with fsroot %s\n", + __func__, path, fs_path); + return -ENOENT; + } + + return 0; +} + +static size_t nfs_parse_server_name(char *string, size_t len, + struct sockaddr *sa, size_t salen, struct net *net) +{ + ssize_t ret; + + ret = rpc_pton(net, string, len, sa, salen); + if (ret == 0) { + ret = nfs_dns_resolve_name(net, string, len, sa, salen); + if (ret < 0) + ret = 0; + } + return ret; +} + +/** + * nfs_find_best_sec - Find a security mechanism supported locally + * @server: NFS server struct + * @flavors: List of security tuples returned by SECINFO procedure + * + * Return an rpc client that uses the first security mechanism in + * "flavors" that is locally supported. The "flavors" array + * is searched in the order returned from the server, per RFC 3530 + * recommendation and each flavor is checked for membership in the + * sec= mount option list if it exists. + * + * Return -EPERM if no matching flavor is found in the array. + * + * Please call rpc_shutdown_client() when you are done with this rpc client. + * + */ +static struct rpc_clnt *nfs_find_best_sec(struct rpc_clnt *clnt, + struct nfs_server *server, + struct nfs4_secinfo_flavors *flavors) +{ + rpc_authflavor_t pflavor; + struct nfs4_secinfo4 *secinfo; + unsigned int i; + + for (i = 0; i < flavors->num_flavors; i++) { + secinfo = &flavors->flavors[i]; + + switch (secinfo->flavor) { + case RPC_AUTH_NULL: + case RPC_AUTH_UNIX: + case RPC_AUTH_GSS: + pflavor = rpcauth_get_pseudoflavor(secinfo->flavor, + &secinfo->flavor_info); + /* does the pseudoflavor match a sec= mount opt? */ + if (pflavor != RPC_AUTH_MAXFLAVOR && + nfs_auth_info_match(&server->auth_info, pflavor)) { + struct rpc_clnt *new; + struct rpc_cred *cred; + + /* Cloning creates an rpc_auth for the flavor */ + new = rpc_clone_client_set_auth(clnt, pflavor); + if (IS_ERR(new)) + continue; + /** + * Check that the user actually can use the + * flavor. This is mostly for RPC_AUTH_GSS + * where cr_init obtains a gss context + */ + cred = rpcauth_lookupcred(new->cl_auth, 0); + if (IS_ERR(cred)) { + rpc_shutdown_client(new); + continue; + } + put_rpccred(cred); + return new; + } + } + } + return ERR_PTR(-EPERM); +} + +/** + * nfs4_negotiate_security - in response to an NFS4ERR_WRONGSEC on lookup, + * return an rpc_clnt that uses the best available security flavor with + * respect to the secinfo flavor list and the sec= mount options. + * + * @clnt: RPC client to clone + * @inode: directory inode + * @name: lookup name + * + * Please call rpc_shutdown_client() when you are done with this rpc client. + */ +struct rpc_clnt * +nfs4_negotiate_security(struct rpc_clnt *clnt, struct inode *inode, + struct qstr *name) +{ + struct page *page; + struct nfs4_secinfo_flavors *flavors; + struct rpc_clnt *new; + int err; + + page = alloc_page(GFP_KERNEL); + if (!page) + return ERR_PTR(-ENOMEM); + + flavors = page_address(page); + + err = nfs4_proc_secinfo(inode, name, flavors); + if (err < 0) { + new = ERR_PTR(err); + goto out; + } + + new = nfs_find_best_sec(clnt, NFS_SERVER(inode), flavors); + +out: + put_page(page); + return new; +} + +static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, + char *page, char *page2, + const struct nfs4_fs_location *location) +{ + const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client); + struct vfsmount *mnt = ERR_PTR(-ENOENT); + char *mnt_path; + unsigned int maxbuflen; + unsigned int s; + + mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE); + if (IS_ERR(mnt_path)) + return ERR_CAST(mnt_path); + mountdata->mnt_path = mnt_path; + maxbuflen = mnt_path - 1 - page2; + + mountdata->addr = kmalloc(addr_bufsize, GFP_KERNEL); + if (mountdata->addr == NULL) + return ERR_PTR(-ENOMEM); + + for (s = 0; s < location->nservers; s++) { + const struct nfs4_string *buf = &location->servers[s]; + + if (buf->len <= 0 || buf->len >= maxbuflen) + continue; + + if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len)) + continue; + + mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len, + mountdata->addr, addr_bufsize, net); + if (mountdata->addrlen == 0) + continue; + + rpc_set_port(mountdata->addr, NFS_PORT); + + memcpy(page2, buf->data, buf->len); + page2[buf->len] = '\0'; + mountdata->hostname = page2; + + snprintf(page, PAGE_SIZE, "%s:%s", + mountdata->hostname, + mountdata->mnt_path); + + mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata); + if (!IS_ERR(mnt)) + break; + } + kfree(mountdata->addr); + return mnt; +} + +/** + * nfs_follow_referral - set up mountpoint when hitting a referral on moved error + * @dentry - parent directory + * @locations - array of NFSv4 server location information + * + */ +static struct vfsmount *nfs_follow_referral(struct dentry *dentry, + const struct nfs4_fs_locations *locations) +{ + struct vfsmount *mnt = ERR_PTR(-ENOENT); + struct nfs_clone_mount mountdata = { + .sb = dentry->d_sb, + .dentry = dentry, + .authflavor = NFS_SB(dentry->d_sb)->client->cl_auth->au_flavor, + }; + char *page = NULL, *page2 = NULL; + int loc, error; + + if (locations == NULL || locations->nlocations <= 0) + goto out; + + dprintk("%s: referral at %pd2\n", __func__, dentry); + + page = (char *) __get_free_page(GFP_USER); + if (!page) + goto out; + + page2 = (char *) __get_free_page(GFP_USER); + if (!page2) + goto out; + + /* Ensure fs path is a prefix of current dentry path */ + error = nfs4_validate_fspath(dentry, locations, page, page2); + if (error < 0) { + mnt = ERR_PTR(error); + goto out; + } + + for (loc = 0; loc < locations->nlocations; loc++) { + const struct nfs4_fs_location *location = &locations->locations[loc]; + + if (location == NULL || location->nservers <= 0 || + location->rootpath.ncomponents == 0) + continue; + + mnt = try_location(&mountdata, page, page2, location); + if (!IS_ERR(mnt)) + break; + } + +out: + free_page((unsigned long) page); + free_page((unsigned long) page2); + dprintk("%s: done\n", __func__); + return mnt; +} + +/* + * nfs_do_refmount - handle crossing a referral on server + * @dentry - dentry of referral + * + */ +static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) +{ + struct vfsmount *mnt = ERR_PTR(-ENOMEM); + struct dentry *parent; + struct nfs4_fs_locations *fs_locations = NULL; + struct page *page; + int err; + + /* BUG_ON(IS_ROOT(dentry)); */ + dprintk("%s: enter\n", __func__); + + page = alloc_page(GFP_KERNEL); + if (page == NULL) + goto out; + + fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (fs_locations == NULL) + goto out_free; + + /* Get locations */ + mnt = ERR_PTR(-ENOENT); + + parent = dget_parent(dentry); + dprintk("%s: getting locations for %pd2\n", + __func__, dentry); + + err = nfs4_proc_fs_locations(client, d_inode(parent), &dentry->d_name, fs_locations, page); + dput(parent); + if (err != 0 || + fs_locations->nlocations <= 0 || + fs_locations->fs_path.ncomponents <= 0) + goto out_free; + + mnt = nfs_follow_referral(dentry, fs_locations); +out_free: + __free_page(page); + kfree(fs_locations); +out: + dprintk("%s: done\n", __func__); + return mnt; +} + +struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + rpc_authflavor_t flavor = server->client->cl_auth->au_flavor; + struct dentry *parent = dget_parent(dentry); + struct inode *dir = d_inode(parent); + struct qstr *name = &dentry->d_name; + struct rpc_clnt *client; + struct vfsmount *mnt; + + /* Look it up again to get its attributes and sec flavor */ + client = nfs4_proc_lookup_mountpoint(dir, name, fh, fattr); + dput(parent); + if (IS_ERR(client)) + return ERR_CAST(client); + + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { + mnt = nfs_do_refmount(client, dentry); + goto out; + } + + if (client->cl_auth->au_flavor != flavor) + flavor = client->cl_auth->au_flavor; + mnt = nfs_do_submount(dentry, fh, fattr, flavor); +out: + rpc_shutdown_client(client); + return mnt; +} + +/* + * Try one location from the fs_locations array. + * + * Returns zero on success, or a negative errno value. + */ +static int nfs4_try_replacing_one_location(struct nfs_server *server, + char *page, char *page2, + const struct nfs4_fs_location *location) +{ + const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct net *net = rpc_net_ns(server->client); + struct sockaddr *sap; + unsigned int s; + size_t salen; + int error; + + sap = kmalloc(addr_bufsize, GFP_KERNEL); + if (sap == NULL) + return -ENOMEM; + + error = -ENOENT; + for (s = 0; s < location->nservers; s++) { + const struct nfs4_string *buf = &location->servers[s]; + char *hostname; + + if (buf->len <= 0 || buf->len > PAGE_SIZE) + continue; + + if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len) != NULL) + continue; + + salen = nfs_parse_server_name(buf->data, buf->len, + sap, addr_bufsize, net); + if (salen == 0) + continue; + rpc_set_port(sap, NFS_PORT); + + error = -ENOMEM; + hostname = kstrndup(buf->data, buf->len, GFP_KERNEL); + if (hostname == NULL) + break; + + error = nfs4_update_server(server, hostname, sap, salen, net); + kfree(hostname); + if (error == 0) + break; + } + + kfree(sap); + return error; +} + +/** + * nfs4_replace_transport - set up transport to destination server + * + * @server: export being migrated + * @locations: fs_locations array + * + * Returns zero on success, or a negative errno value. + * + * The client tries all the entries in the "locations" array, in the + * order returned by the server, until one works or the end of the + * array is reached. + */ +int nfs4_replace_transport(struct nfs_server *server, + const struct nfs4_fs_locations *locations) +{ + char *page = NULL, *page2 = NULL; + int loc, error; + + error = -ENOENT; + if (locations == NULL || locations->nlocations <= 0) + goto out; + + error = -ENOMEM; + page = (char *) __get_free_page(GFP_USER); + if (!page) + goto out; + page2 = (char *) __get_free_page(GFP_USER); + if (!page2) + goto out; + + for (loc = 0; loc < locations->nlocations; loc++) { + const struct nfs4_fs_location *location = + &locations->locations[loc]; + + if (location == NULL || location->nservers <= 0 || + location->rootpath.ncomponents == 0) + continue; + + error = nfs4_try_replacing_one_location(server, page, + page2, location); + if (error == 0) + break; + } + +out: + free_page((unsigned long)page); + free_page((unsigned long)page2); + return error; +} diff --git a/kernel/fs/nfs/nfs4proc.c b/kernel/fs/nfs/nfs4proc.c new file mode 100644 index 000000000..55e1e3af2 --- /dev/null +++ b/kernel/fs/nfs/nfs4proc.c @@ -0,0 +1,8687 @@ +/* + * fs/nfs/nfs4proc.c + * + * Client-side procedure declarations for NFSv4. + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Kendrick Smith <kmsmith@umich.edu> + * Andy Adamson <andros@umich.edu> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/mm.h> +#include <linux/delay.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/string.h> +#include <linux/ratelimit.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/nfs_mount.h> +#include <linux/namei.h> +#include <linux/mount.h> +#include <linux/module.h> +#include <linux/xattr.h> +#include <linux/utsname.h> +#include <linux/freezer.h> + +#include "nfs4_fs.h" +#include "delegation.h" +#include "internal.h" +#include "iostat.h" +#include "callback.h" +#include "pnfs.h" +#include "netns.h" +#include "nfs4idmap.h" +#include "nfs4session.h" +#include "fscache.h" + +#include "nfs4trace.h" + +#define NFSDBG_FACILITY NFSDBG_PROC + +#define NFS4_POLL_RETRY_MIN (HZ/10) +#define NFS4_POLL_RETRY_MAX (15*HZ) + +struct nfs4_opendata; +static int _nfs4_proc_open(struct nfs4_opendata *data); +static int _nfs4_recover_proc_open(struct nfs4_opendata *data); +static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); +static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *); +static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); +static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label); +static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label); +static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, + struct nfs_fattr *fattr, struct iattr *sattr, + struct nfs4_state *state, struct nfs4_label *ilabel, + struct nfs4_label *olabel); +#ifdef CONFIG_NFS_V4_1 +static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *, + struct rpc_cred *); +static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *, + struct rpc_cred *); +#endif + +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +static inline struct nfs4_label * +nfs4_label_init_security(struct inode *dir, struct dentry *dentry, + struct iattr *sattr, struct nfs4_label *label) +{ + int err; + + if (label == NULL) + return NULL; + + if (nfs_server_capable(dir, NFS_CAP_SECURITY_LABEL) == 0) + return NULL; + + err = security_dentry_init_security(dentry, sattr->ia_mode, + &dentry->d_name, (void **)&label->label, &label->len); + if (err == 0) + return label; + + return NULL; +} +static inline void +nfs4_label_release_security(struct nfs4_label *label) +{ + if (label) + security_release_secctx(label->label, label->len); +} +static inline u32 *nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label) +{ + if (label) + return server->attr_bitmask; + + return server->attr_bitmask_nl; +} +#else +static inline struct nfs4_label * +nfs4_label_init_security(struct inode *dir, struct dentry *dentry, + struct iattr *sattr, struct nfs4_label *l) +{ return NULL; } +static inline void +nfs4_label_release_security(struct nfs4_label *label) +{ return; } +static inline u32 * +nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label) +{ return server->attr_bitmask; } +#endif + +/* Prevent leaks of NFSv4 errors into userland */ +static int nfs4_map_errors(int err) +{ + if (err >= -1000) + return err; + switch (err) { + case -NFS4ERR_RESOURCE: + case -NFS4ERR_LAYOUTTRYLATER: + case -NFS4ERR_RECALLCONFLICT: + return -EREMOTEIO; + case -NFS4ERR_WRONGSEC: + case -NFS4ERR_WRONG_CRED: + return -EPERM; + case -NFS4ERR_BADOWNER: + case -NFS4ERR_BADNAME: + return -EINVAL; + case -NFS4ERR_SHARE_DENIED: + return -EACCES; + case -NFS4ERR_MINOR_VERS_MISMATCH: + return -EPROTONOSUPPORT; + case -NFS4ERR_FILE_OPEN: + return -EBUSY; + default: + dprintk("%s could not handle NFSv4 error %d\n", + __func__, -err); + break; + } + return -EIO; +} + +/* + * This is our standard bitmap for GETATTR requests. + */ +const u32 nfs4_fattr_bitmap[3] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_SIZE + | FATTR4_WORD0_FSID + | FATTR4_WORD0_FILEID, + FATTR4_WORD1_MODE + | FATTR4_WORD1_NUMLINKS + | FATTR4_WORD1_OWNER + | FATTR4_WORD1_OWNER_GROUP + | FATTR4_WORD1_RAWDEV + | FATTR4_WORD1_SPACE_USED + | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_METADATA + | FATTR4_WORD1_TIME_MODIFY + | FATTR4_WORD1_MOUNTED_ON_FILEID, +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + FATTR4_WORD2_SECURITY_LABEL +#endif +}; + +static const u32 nfs4_pnfs_open_bitmap[3] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_SIZE + | FATTR4_WORD0_FSID + | FATTR4_WORD0_FILEID, + FATTR4_WORD1_MODE + | FATTR4_WORD1_NUMLINKS + | FATTR4_WORD1_OWNER + | FATTR4_WORD1_OWNER_GROUP + | FATTR4_WORD1_RAWDEV + | FATTR4_WORD1_SPACE_USED + | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_METADATA + | FATTR4_WORD1_TIME_MODIFY, + FATTR4_WORD2_MDSTHRESHOLD +}; + +static const u32 nfs4_open_noattr_bitmap[3] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_FILEID, +}; + +const u32 nfs4_statfs_bitmap[3] = { + FATTR4_WORD0_FILES_AVAIL + | FATTR4_WORD0_FILES_FREE + | FATTR4_WORD0_FILES_TOTAL, + FATTR4_WORD1_SPACE_AVAIL + | FATTR4_WORD1_SPACE_FREE + | FATTR4_WORD1_SPACE_TOTAL +}; + +const u32 nfs4_pathconf_bitmap[3] = { + FATTR4_WORD0_MAXLINK + | FATTR4_WORD0_MAXNAME, + 0 +}; + +const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE + | FATTR4_WORD0_MAXREAD + | FATTR4_WORD0_MAXWRITE + | FATTR4_WORD0_LEASE_TIME, + FATTR4_WORD1_TIME_DELTA + | FATTR4_WORD1_FS_LAYOUT_TYPES, + FATTR4_WORD2_LAYOUT_BLKSIZE +}; + +const u32 nfs4_fs_locations_bitmap[3] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_SIZE + | FATTR4_WORD0_FSID + | FATTR4_WORD0_FILEID + | FATTR4_WORD0_FS_LOCATIONS, + FATTR4_WORD1_MODE + | FATTR4_WORD1_NUMLINKS + | FATTR4_WORD1_OWNER + | FATTR4_WORD1_OWNER_GROUP + | FATTR4_WORD1_RAWDEV + | FATTR4_WORD1_SPACE_USED + | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_METADATA + | FATTR4_WORD1_TIME_MODIFY + | FATTR4_WORD1_MOUNTED_ON_FILEID, +}; + +static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry, + struct nfs4_readdir_arg *readdir) +{ + __be32 *start, *p; + + if (cookie > 2) { + readdir->cookie = cookie; + memcpy(&readdir->verifier, verifier, sizeof(readdir->verifier)); + return; + } + + readdir->cookie = 0; + memset(&readdir->verifier, 0, sizeof(readdir->verifier)); + if (cookie == 2) + return; + + /* + * NFSv4 servers do not return entries for '.' and '..' + * Therefore, we fake these entries here. We let '.' + * have cookie 0 and '..' have cookie 1. Note that + * when talking to the server, we always send cookie 0 + * instead of 1 or 2. + */ + start = p = kmap_atomic(*readdir->pages); + + if (cookie == 0) { + *p++ = xdr_one; /* next */ + *p++ = xdr_zero; /* cookie, first word */ + *p++ = xdr_one; /* cookie, second word */ + *p++ = xdr_one; /* entry len */ + memcpy(p, ".\0\0\0", 4); /* entry */ + p++; + *p++ = xdr_one; /* bitmap length */ + *p++ = htonl(FATTR4_WORD0_FILEID); /* bitmap */ + *p++ = htonl(8); /* attribute buffer length */ + p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry))); + } + + *p++ = xdr_one; /* next */ + *p++ = xdr_zero; /* cookie, first word */ + *p++ = xdr_two; /* cookie, second word */ + *p++ = xdr_two; /* entry len */ + memcpy(p, "..\0\0", 4); /* entry */ + p++; + *p++ = xdr_one; /* bitmap length */ + *p++ = htonl(FATTR4_WORD0_FILEID); /* bitmap */ + *p++ = htonl(8); /* attribute buffer length */ + p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry->d_parent))); + + readdir->pgbase = (char *)p - (char *)start; + readdir->count -= readdir->pgbase; + kunmap_atomic(start); +} + +static long nfs4_update_delay(long *timeout) +{ + long ret; + if (!timeout) + return NFS4_POLL_RETRY_MAX; + if (*timeout <= 0) + *timeout = NFS4_POLL_RETRY_MIN; + if (*timeout > NFS4_POLL_RETRY_MAX) + *timeout = NFS4_POLL_RETRY_MAX; + ret = *timeout; + *timeout <<= 1; + return ret; +} + +static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) +{ + int res = 0; + + might_sleep(); + + freezable_schedule_timeout_killable_unsafe( + nfs4_update_delay(timeout)); + if (fatal_signal_pending(current)) + res = -ERESTARTSYS; + return res; +} + +/* This is the error handling routine for processes that are allowed + * to sleep. + */ +int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_state *state = exception->state; + struct inode *inode = exception->inode; + int ret = errorcode; + + exception->retry = 0; + switch(errorcode) { + case 0: + return 0; + case -NFS4ERR_OPENMODE: + if (inode && nfs4_have_delegation(inode, FMODE_READ)) { + nfs4_inode_return_delegation(inode); + exception->retry = 1; + return 0; + } + if (state == NULL) + break; + ret = nfs4_schedule_stateid_recovery(server, state); + if (ret < 0) + break; + goto wait_on_recovery; + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + if (state == NULL) + break; + ret = nfs4_schedule_stateid_recovery(server, state); + if (ret < 0) + break; + goto wait_on_recovery; + case -NFS4ERR_EXPIRED: + if (state != NULL) { + ret = nfs4_schedule_stateid_recovery(server, state); + if (ret < 0) + break; + } + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_STALE_CLIENTID: + nfs4_schedule_lease_recovery(clp); + goto wait_on_recovery; + case -NFS4ERR_MOVED: + ret = nfs4_schedule_migration_recovery(server); + if (ret < 0) + break; + goto wait_on_recovery; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + goto wait_on_recovery; +#if defined(CONFIG_NFS_V4_1) + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + dprintk("%s ERROR: %d Reset session\n", __func__, + errorcode); + nfs4_schedule_session_recovery(clp->cl_session, errorcode); + goto wait_on_recovery; +#endif /* defined(CONFIG_NFS_V4_1) */ + case -NFS4ERR_FILE_OPEN: + if (exception->timeout > HZ) { + /* We have retried a decent amount, time to + * fail + */ + ret = -EBUSY; + break; + } + case -NFS4ERR_GRACE: + case -NFS4ERR_DELAY: + ret = nfs4_delay(server->client, &exception->timeout); + if (ret != 0) + break; + case -NFS4ERR_RETRY_UNCACHED_REP: + case -NFS4ERR_OLD_STATEID: + exception->retry = 1; + break; + case -NFS4ERR_BADOWNER: + /* The following works around a Linux server bug! */ + case -NFS4ERR_BADNAME: + if (server->caps & NFS_CAP_UIDGID_NOMAP) { + server->caps &= ~NFS_CAP_UIDGID_NOMAP; + exception->retry = 1; + printk(KERN_WARNING "NFS: v4 server %s " + "does not accept raw " + "uid/gids. " + "Reenabling the idmapper.\n", + server->nfs_client->cl_hostname); + } + } + /* We failed to handle the error */ + return nfs4_map_errors(ret); +wait_on_recovery: + ret = nfs4_wait_clnt_recover(clp); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -EIO; + if (ret == 0) + exception->retry = 1; + return ret; +} + +/* + * Return 'true' if 'clp' is using an rpc_client that is integrity protected + * or 'false' otherwise. + */ +static bool _nfs4_is_integrity_protected(struct nfs_client *clp) +{ + rpc_authflavor_t flavor = clp->cl_rpcclient->cl_auth->au_flavor; + + if (flavor == RPC_AUTH_GSS_KRB5I || + flavor == RPC_AUTH_GSS_KRB5P) + return true; + + return false; +} + +static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp) +{ + spin_lock(&clp->cl_lock); + if (time_before(clp->cl_last_renewal,timestamp)) + clp->cl_last_renewal = timestamp; + spin_unlock(&clp->cl_lock); +} + +static void renew_lease(const struct nfs_server *server, unsigned long timestamp) +{ + do_renew_lease(server->nfs_client, timestamp); +} + +struct nfs4_call_sync_data { + const struct nfs_server *seq_server; + struct nfs4_sequence_args *seq_args; + struct nfs4_sequence_res *seq_res; +}; + +static void nfs4_init_sequence(struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, int cache_reply) +{ + args->sa_slot = NULL; + args->sa_cache_this = cache_reply; + args->sa_privileged = 0; + + res->sr_slot = NULL; +} + +static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args) +{ + args->sa_privileged = 1; +} + +int nfs40_setup_sequence(struct nfs4_slot_table *tbl, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + struct nfs4_slot *slot; + + /* slot already allocated? */ + if (res->sr_slot != NULL) + goto out_start; + + spin_lock(&tbl->slot_tbl_lock); + if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged) + goto out_sleep; + + slot = nfs4_alloc_slot(tbl); + if (IS_ERR(slot)) { + if (slot == ERR_PTR(-ENOMEM)) + task->tk_timeout = HZ >> 2; + goto out_sleep; + } + spin_unlock(&tbl->slot_tbl_lock); + + args->sa_slot = slot; + res->sr_slot = slot; + +out_start: + rpc_call_start(task); + return 0; + +out_sleep: + if (args->sa_privileged) + rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task, + NULL, RPC_PRIORITY_PRIVILEGED); + else + rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL); + spin_unlock(&tbl->slot_tbl_lock); + return -EAGAIN; +} +EXPORT_SYMBOL_GPL(nfs40_setup_sequence); + +static int nfs40_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res) +{ + struct nfs4_slot *slot = res->sr_slot; + struct nfs4_slot_table *tbl; + + if (slot == NULL) + goto out; + + tbl = slot->table; + spin_lock(&tbl->slot_tbl_lock); + if (!nfs41_wake_and_assign_slot(tbl, slot)) + nfs4_free_slot(tbl, slot); + spin_unlock(&tbl->slot_tbl_lock); + + res->sr_slot = NULL; +out: + return 1; +} + +#if defined(CONFIG_NFS_V4_1) + +static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) +{ + struct nfs4_session *session; + struct nfs4_slot_table *tbl; + struct nfs4_slot *slot = res->sr_slot; + bool send_new_highest_used_slotid = false; + + tbl = slot->table; + session = tbl->session; + + spin_lock(&tbl->slot_tbl_lock); + /* Be nice to the server: try to ensure that the last transmitted + * value for highest_user_slotid <= target_highest_slotid + */ + if (tbl->highest_used_slotid > tbl->target_highest_slotid) + send_new_highest_used_slotid = true; + + if (nfs41_wake_and_assign_slot(tbl, slot)) { + send_new_highest_used_slotid = false; + goto out_unlock; + } + nfs4_free_slot(tbl, slot); + + if (tbl->highest_used_slotid != NFS4_NO_SLOT) + send_new_highest_used_slotid = false; +out_unlock: + spin_unlock(&tbl->slot_tbl_lock); + res->sr_slot = NULL; + if (send_new_highest_used_slotid) + nfs41_server_notify_highest_slotid_update(session->clp); +} + +int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) +{ + struct nfs4_session *session; + struct nfs4_slot *slot = res->sr_slot; + struct nfs_client *clp; + bool interrupted = false; + int ret = 1; + + if (slot == NULL) + goto out_noaction; + /* don't increment the sequence number if the task wasn't sent */ + if (!RPC_WAS_SENT(task)) + goto out; + + session = slot->table->session; + + if (slot->interrupted) { + slot->interrupted = 0; + interrupted = true; + } + + trace_nfs4_sequence_done(session, res); + /* Check the SEQUENCE operation status */ + switch (res->sr_status) { + case 0: + /* Update the slot's sequence and clientid lease timer */ + ++slot->seq_nr; + clp = session->clp; + do_renew_lease(clp, res->sr_timestamp); + /* Check sequence flags */ + if (res->sr_status_flags != 0) + nfs4_schedule_lease_recovery(clp); + nfs41_update_target_slotid(slot->table, slot, res); + break; + case 1: + /* + * sr_status remains 1 if an RPC level error occurred. + * The server may or may not have processed the sequence + * operation.. + * Mark the slot as having hosted an interrupted RPC call. + */ + slot->interrupted = 1; + goto out; + case -NFS4ERR_DELAY: + /* The server detected a resend of the RPC call and + * returned NFS4ERR_DELAY as per Section 2.10.6.2 + * of RFC5661. + */ + dprintk("%s: slot=%u seq=%u: Operation in progress\n", + __func__, + slot->slot_nr, + slot->seq_nr); + goto out_retry; + case -NFS4ERR_BADSLOT: + /* + * The slot id we used was probably retired. Try again + * using a different slot id. + */ + goto retry_nowait; + case -NFS4ERR_SEQ_MISORDERED: + /* + * Was the last operation on this sequence interrupted? + * If so, retry after bumping the sequence number. + */ + if (interrupted) { + ++slot->seq_nr; + goto retry_nowait; + } + /* + * Could this slot have been previously retired? + * If so, then the server may be expecting seq_nr = 1! + */ + if (slot->seq_nr != 1) { + slot->seq_nr = 1; + goto retry_nowait; + } + break; + case -NFS4ERR_SEQ_FALSE_RETRY: + ++slot->seq_nr; + goto retry_nowait; + default: + /* Just update the slot sequence no. */ + ++slot->seq_nr; + } +out: + /* The session may be reset by one of the error handlers. */ + dprintk("%s: Error %d free the slot \n", __func__, res->sr_status); + nfs41_sequence_free_slot(res); +out_noaction: + return ret; +retry_nowait: + if (rpc_restart_call_prepare(task)) { + task->tk_status = 0; + ret = 0; + } + goto out; +out_retry: + if (!rpc_restart_call(task)) + goto out; + rpc_delay(task, NFS4_POLL_RETRY_MAX); + return 0; +} +EXPORT_SYMBOL_GPL(nfs41_sequence_done); + +int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) +{ + if (res->sr_slot == NULL) + return 1; + if (!res->sr_slot->table->session) + return nfs40_sequence_done(task, res); + return nfs41_sequence_done(task, res); +} +EXPORT_SYMBOL_GPL(nfs4_sequence_done); + +int nfs41_setup_sequence(struct nfs4_session *session, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + struct nfs4_slot *slot; + struct nfs4_slot_table *tbl; + + dprintk("--> %s\n", __func__); + /* slot already allocated? */ + if (res->sr_slot != NULL) + goto out_success; + + tbl = &session->fc_slot_table; + + task->tk_timeout = 0; + + spin_lock(&tbl->slot_tbl_lock); + if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state) && + !args->sa_privileged) { + /* The state manager will wait until the slot table is empty */ + dprintk("%s session is draining\n", __func__); + goto out_sleep; + } + + slot = nfs4_alloc_slot(tbl); + if (IS_ERR(slot)) { + /* If out of memory, try again in 1/4 second */ + if (slot == ERR_PTR(-ENOMEM)) + task->tk_timeout = HZ >> 2; + dprintk("<-- %s: no free slots\n", __func__); + goto out_sleep; + } + spin_unlock(&tbl->slot_tbl_lock); + + args->sa_slot = slot; + + dprintk("<-- %s slotid=%u seqid=%u\n", __func__, + slot->slot_nr, slot->seq_nr); + + res->sr_slot = slot; + res->sr_timestamp = jiffies; + res->sr_status_flags = 0; + /* + * sr_status is only set in decode_sequence, and so will remain + * set to 1 if an rpc level failure occurs. + */ + res->sr_status = 1; + trace_nfs4_setup_sequence(session, args); +out_success: + rpc_call_start(task); + return 0; +out_sleep: + /* Privileged tasks are queued with top priority */ + if (args->sa_privileged) + rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task, + NULL, RPC_PRIORITY_PRIVILEGED); + else + rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL); + spin_unlock(&tbl->slot_tbl_lock); + return -EAGAIN; +} +EXPORT_SYMBOL_GPL(nfs41_setup_sequence); + +static int nfs4_setup_sequence(const struct nfs_server *server, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + struct nfs4_session *session = nfs4_get_session(server); + int ret = 0; + + if (!session) + return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl, + args, res, task); + + dprintk("--> %s clp %p session %p sr_slot %u\n", + __func__, session->clp, session, res->sr_slot ? + res->sr_slot->slot_nr : NFS4_NO_SLOT); + + ret = nfs41_setup_sequence(session, args, res, task); + + dprintk("<-- %s status=%d\n", __func__, ret); + return ret; +} + +static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + struct nfs4_session *session = nfs4_get_session(data->seq_server); + + dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server); + + nfs41_setup_sequence(session, data->seq_args, data->seq_res, task); +} + +static void nfs41_call_sync_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + + nfs41_sequence_done(task, data->seq_res); +} + +static const struct rpc_call_ops nfs41_call_sync_ops = { + .rpc_call_prepare = nfs41_call_sync_prepare, + .rpc_call_done = nfs41_call_sync_done, +}; + +#else /* !CONFIG_NFS_V4_1 */ + +static int nfs4_setup_sequence(const struct nfs_server *server, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl, + args, res, task); +} + +int nfs4_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res) +{ + return nfs40_sequence_done(task, res); +} +EXPORT_SYMBOL_GPL(nfs4_sequence_done); + +#endif /* !CONFIG_NFS_V4_1 */ + +static void nfs40_call_sync_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_setup_sequence(data->seq_server, + data->seq_args, data->seq_res, task); +} + +static void nfs40_call_sync_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_sequence_done(task, data->seq_res); +} + +static const struct rpc_call_ops nfs40_call_sync_ops = { + .rpc_call_prepare = nfs40_call_sync_prepare, + .rpc_call_done = nfs40_call_sync_done, +}; + +static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, + struct nfs_server *server, + struct rpc_message *msg, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res) +{ + int ret; + struct rpc_task *task; + struct nfs_client *clp = server->nfs_client; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = args, + .seq_res = res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = clnt, + .rpc_message = msg, + .callback_ops = clp->cl_mvops->call_sync_ops, + .callback_data = &data + }; + + task = rpc_run_task(&task_setup); + if (IS_ERR(task)) + ret = PTR_ERR(task); + else { + ret = task->tk_status; + rpc_put_task(task); + } + return ret; +} + +int nfs4_call_sync(struct rpc_clnt *clnt, + struct nfs_server *server, + struct rpc_message *msg, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + int cache_reply) +{ + nfs4_init_sequence(args, res, cache_reply); + return nfs4_call_sync_sequence(clnt, server, msg, args, res); +} + +static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) +{ + struct nfs_inode *nfsi = NFS_I(dir); + + spin_lock(&dir->i_lock); + nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; + if (!cinfo->atomic || cinfo->before != dir->i_version) + nfs_force_lookup_revalidate(dir); + dir->i_version = cinfo->after; + nfsi->attr_gencount = nfs_inc_attr_generation_counter(); + nfs_fscache_invalidate(dir); + spin_unlock(&dir->i_lock); +} + +struct nfs4_opendata { + struct kref kref; + struct nfs_openargs o_arg; + struct nfs_openres o_res; + struct nfs_open_confirmargs c_arg; + struct nfs_open_confirmres c_res; + struct nfs4_string owner_name; + struct nfs4_string group_name; + struct nfs_fattr f_attr; + struct nfs4_label *f_label; + struct dentry *dir; + struct dentry *dentry; + struct nfs4_state_owner *owner; + struct nfs4_state *state; + struct iattr attrs; + unsigned long timestamp; + unsigned int rpc_done : 1; + unsigned int file_created : 1; + unsigned int is_recover : 1; + int rpc_status; + int cancelled; +}; + +static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, + int err, struct nfs4_exception *exception) +{ + if (err != -EINVAL) + return false; + if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1)) + return false; + server->caps &= ~NFS_CAP_ATOMIC_OPEN_V1; + exception->retry = 1; + return true; +} + +static u32 +nfs4_map_atomic_open_share(struct nfs_server *server, + fmode_t fmode, int openflags) +{ + u32 res = 0; + + switch (fmode & (FMODE_READ | FMODE_WRITE)) { + case FMODE_READ: + res = NFS4_SHARE_ACCESS_READ; + break; + case FMODE_WRITE: + res = NFS4_SHARE_ACCESS_WRITE; + break; + case FMODE_READ|FMODE_WRITE: + res = NFS4_SHARE_ACCESS_BOTH; + } + if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1)) + goto out; + /* Want no delegation if we're using O_DIRECT */ + if (openflags & O_DIRECT) + res |= NFS4_SHARE_WANT_NO_DELEG; +out: + return res; +} + +static enum open_claim_type4 +nfs4_map_atomic_open_claim(struct nfs_server *server, + enum open_claim_type4 claim) +{ + if (server->caps & NFS_CAP_ATOMIC_OPEN_V1) + return claim; + switch (claim) { + default: + return claim; + case NFS4_OPEN_CLAIM_FH: + return NFS4_OPEN_CLAIM_NULL; + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + return NFS4_OPEN_CLAIM_DELEGATE_CUR; + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + return NFS4_OPEN_CLAIM_DELEGATE_PREV; + } +} + +static void nfs4_init_opendata_res(struct nfs4_opendata *p) +{ + p->o_res.f_attr = &p->f_attr; + p->o_res.f_label = p->f_label; + p->o_res.seqid = p->o_arg.seqid; + p->c_res.seqid = p->c_arg.seqid; + p->o_res.server = p->o_arg.server; + p->o_res.access_request = p->o_arg.access; + nfs_fattr_init(&p->f_attr); + nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name); +} + +static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, + struct nfs4_state_owner *sp, fmode_t fmode, int flags, + const struct iattr *attrs, + struct nfs4_label *label, + enum open_claim_type4 claim, + gfp_t gfp_mask) +{ + struct dentry *parent = dget_parent(dentry); + struct inode *dir = d_inode(parent); + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + struct nfs4_opendata *p; + + p = kzalloc(sizeof(*p), gfp_mask); + if (p == NULL) + goto err; + + p->f_label = nfs4_label_alloc(server, gfp_mask); + if (IS_ERR(p->f_label)) + goto err_free_p; + + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; + p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask); + if (IS_ERR(p->o_arg.seqid)) + goto err_free_label; + nfs_sb_active(dentry->d_sb); + p->dentry = dget(dentry); + p->dir = parent; + p->owner = sp; + atomic_inc(&sp->so_count); + p->o_arg.open_flags = flags; + p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); + p->o_arg.share_access = nfs4_map_atomic_open_share(server, + fmode, flags); + /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS + * will return permission denied for all bits until close */ + if (!(flags & O_EXCL)) { + /* ask server to check for all possible rights as results + * are cached */ + p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY | + NFS4_ACCESS_EXTEND | NFS4_ACCESS_EXECUTE; + } + p->o_arg.clientid = server->nfs_client->cl_clientid; + p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time); + p->o_arg.id.uniquifier = sp->so_seqid.owner_id; + p->o_arg.name = &dentry->d_name; + p->o_arg.server = server; + p->o_arg.bitmask = nfs4_bitmask(server, label); + p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; + p->o_arg.label = label; + p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim); + switch (p->o_arg.claim) { + case NFS4_OPEN_CLAIM_NULL: + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + p->o_arg.fh = NFS_FH(dir); + break; + case NFS4_OPEN_CLAIM_PREVIOUS: + case NFS4_OPEN_CLAIM_FH: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + p->o_arg.fh = NFS_FH(d_inode(dentry)); + } + if (attrs != NULL && attrs->ia_valid != 0) { + __u32 verf[2]; + + p->o_arg.u.attrs = &p->attrs; + memcpy(&p->attrs, attrs, sizeof(p->attrs)); + + verf[0] = jiffies; + verf[1] = current->pid; + memcpy(p->o_arg.u.verifier.data, verf, + sizeof(p->o_arg.u.verifier.data)); + } + p->c_arg.fh = &p->o_res.fh; + p->c_arg.stateid = &p->o_res.stateid; + p->c_arg.seqid = p->o_arg.seqid; + nfs4_init_opendata_res(p); + kref_init(&p->kref); + return p; + +err_free_label: + nfs4_label_free(p->f_label); +err_free_p: + kfree(p); +err: + dput(parent); + return NULL; +} + +static void nfs4_opendata_free(struct kref *kref) +{ + struct nfs4_opendata *p = container_of(kref, + struct nfs4_opendata, kref); + struct super_block *sb = p->dentry->d_sb; + + nfs_free_seqid(p->o_arg.seqid); + if (p->state != NULL) + nfs4_put_open_state(p->state); + nfs4_put_state_owner(p->owner); + + nfs4_label_free(p->f_label); + + dput(p->dir); + dput(p->dentry); + nfs_sb_deactive(sb); + nfs_fattr_free_names(&p->f_attr); + kfree(p->f_attr.mdsthreshold); + kfree(p); +} + +static void nfs4_opendata_put(struct nfs4_opendata *p) +{ + if (p != NULL) + kref_put(&p->kref, nfs4_opendata_free); +} + +static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task) +{ + int ret; + + ret = rpc_wait_for_completion_task(task); + return ret; +} + +static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode) +{ + int ret = 0; + + if (open_mode & (O_EXCL|O_TRUNC)) + goto out; + switch (mode & (FMODE_READ|FMODE_WRITE)) { + case FMODE_READ: + ret |= test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0 + && state->n_rdonly != 0; + break; + case FMODE_WRITE: + ret |= test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0 + && state->n_wronly != 0; + break; + case FMODE_READ|FMODE_WRITE: + ret |= test_bit(NFS_O_RDWR_STATE, &state->flags) != 0 + && state->n_rdwr != 0; + } +out: + return ret; +} + +static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode) +{ + if (delegation == NULL) + return 0; + if ((delegation->type & fmode) != fmode) + return 0; + if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) + return 0; + nfs_mark_delegation_referenced(delegation); + return 1; +} + +static void update_open_stateflags(struct nfs4_state *state, fmode_t fmode) +{ + switch (fmode) { + case FMODE_WRITE: + state->n_wronly++; + break; + case FMODE_READ: + state->n_rdonly++; + break; + case FMODE_READ|FMODE_WRITE: + state->n_rdwr++; + } + nfs4_state_set_mode_locked(state, state->state | fmode); +} + +static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state) +{ + struct nfs_client *clp = state->owner->so_server->nfs_client; + bool need_recover = false; + + if (test_and_clear_bit(NFS_O_RDONLY_STATE, &state->flags) && state->n_rdonly) + need_recover = true; + if (test_and_clear_bit(NFS_O_WRONLY_STATE, &state->flags) && state->n_wronly) + need_recover = true; + if (test_and_clear_bit(NFS_O_RDWR_STATE, &state->flags) && state->n_rdwr) + need_recover = true; + if (need_recover) + nfs4_state_mark_reclaim_nograce(clp, state); +} + +static bool nfs_need_update_open_stateid(struct nfs4_state *state, + nfs4_stateid *stateid) +{ + if (test_and_set_bit(NFS_OPEN_STATE, &state->flags) == 0) + return true; + if (!nfs4_stateid_match_other(stateid, &state->open_stateid)) { + nfs_test_and_clear_all_open_stateid(state); + return true; + } + if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) + return true; + return false; +} + +static void nfs_resync_open_stateid_locked(struct nfs4_state *state) +{ + if (state->n_wronly) + set_bit(NFS_O_WRONLY_STATE, &state->flags); + if (state->n_rdonly) + set_bit(NFS_O_RDONLY_STATE, &state->flags); + if (state->n_rdwr) + set_bit(NFS_O_RDWR_STATE, &state->flags); +} + +static void nfs_clear_open_stateid_locked(struct nfs4_state *state, + nfs4_stateid *stateid, fmode_t fmode) +{ + clear_bit(NFS_O_RDWR_STATE, &state->flags); + switch (fmode & (FMODE_READ|FMODE_WRITE)) { + case FMODE_WRITE: + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + break; + case FMODE_READ: + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + break; + case 0: + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); + } + if (stateid == NULL) + return; + /* Handle races with OPEN */ + if (!nfs4_stateid_match_other(stateid, &state->open_stateid) || + !nfs4_stateid_is_newer(stateid, &state->open_stateid)) { + nfs_resync_open_stateid_locked(state); + return; + } + if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) + nfs4_stateid_copy(&state->stateid, stateid); + nfs4_stateid_copy(&state->open_stateid, stateid); +} + +static void nfs_clear_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode) +{ + write_seqlock(&state->seqlock); + nfs_clear_open_stateid_locked(state, stateid, fmode); + write_sequnlock(&state->seqlock); + if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags)) + nfs4_schedule_state_manager(state->owner->so_server->nfs_client); +} + +static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode) +{ + switch (fmode) { + case FMODE_READ: + set_bit(NFS_O_RDONLY_STATE, &state->flags); + break; + case FMODE_WRITE: + set_bit(NFS_O_WRONLY_STATE, &state->flags); + break; + case FMODE_READ|FMODE_WRITE: + set_bit(NFS_O_RDWR_STATE, &state->flags); + } + if (!nfs_need_update_open_stateid(state, stateid)) + return; + if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) + nfs4_stateid_copy(&state->stateid, stateid); + nfs4_stateid_copy(&state->open_stateid, stateid); +} + +static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, const nfs4_stateid *deleg_stateid, fmode_t fmode) +{ + /* + * Protect the call to nfs4_state_set_mode_locked and + * serialise the stateid update + */ + write_seqlock(&state->seqlock); + if (deleg_stateid != NULL) { + nfs4_stateid_copy(&state->stateid, deleg_stateid); + set_bit(NFS_DELEGATED_STATE, &state->flags); + } + if (open_stateid != NULL) + nfs_set_open_stateid_locked(state, open_stateid, fmode); + write_sequnlock(&state->seqlock); + spin_lock(&state->owner->so_lock); + update_open_stateflags(state, fmode); + spin_unlock(&state->owner->so_lock); +} + +static int update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, nfs4_stateid *delegation, fmode_t fmode) +{ + struct nfs_inode *nfsi = NFS_I(state->inode); + struct nfs_delegation *deleg_cur; + int ret = 0; + + fmode &= (FMODE_READ|FMODE_WRITE); + + rcu_read_lock(); + deleg_cur = rcu_dereference(nfsi->delegation); + if (deleg_cur == NULL) + goto no_delegation; + + spin_lock(&deleg_cur->lock); + if (rcu_dereference(nfsi->delegation) != deleg_cur || + test_bit(NFS_DELEGATION_RETURNING, &deleg_cur->flags) || + (deleg_cur->type & fmode) != fmode) + goto no_delegation_unlock; + + if (delegation == NULL) + delegation = &deleg_cur->stateid; + else if (!nfs4_stateid_match(&deleg_cur->stateid, delegation)) + goto no_delegation_unlock; + + nfs_mark_delegation_referenced(deleg_cur); + __update_open_stateid(state, open_stateid, &deleg_cur->stateid, fmode); + ret = 1; +no_delegation_unlock: + spin_unlock(&deleg_cur->lock); +no_delegation: + rcu_read_unlock(); + + if (!ret && open_stateid != NULL) { + __update_open_stateid(state, open_stateid, NULL, fmode); + ret = 1; + } + if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags)) + nfs4_schedule_state_manager(state->owner->so_server->nfs_client); + + return ret; +} + +static bool nfs4_update_lock_stateid(struct nfs4_lock_state *lsp, + const nfs4_stateid *stateid) +{ + struct nfs4_state *state = lsp->ls_state; + bool ret = false; + + spin_lock(&state->state_lock); + if (!nfs4_stateid_match_other(stateid, &lsp->ls_stateid)) + goto out_noupdate; + if (!nfs4_stateid_is_newer(stateid, &lsp->ls_stateid)) + goto out_noupdate; + nfs4_stateid_copy(&lsp->ls_stateid, stateid); + ret = true; +out_noupdate: + spin_unlock(&state->state_lock); + return ret; +} + +static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmode) +{ + struct nfs_delegation *delegation; + + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation == NULL || (delegation->type & fmode) == fmode) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + nfs4_inode_return_delegation(inode); +} + +static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) +{ + struct nfs4_state *state = opendata->state; + struct nfs_inode *nfsi = NFS_I(state->inode); + struct nfs_delegation *delegation; + int open_mode = opendata->o_arg.open_flags; + fmode_t fmode = opendata->o_arg.fmode; + nfs4_stateid stateid; + int ret = -EAGAIN; + + for (;;) { + spin_lock(&state->owner->so_lock); + if (can_open_cached(state, fmode, open_mode)) { + update_open_stateflags(state, fmode); + spin_unlock(&state->owner->so_lock); + goto out_return_state; + } + spin_unlock(&state->owner->so_lock); + rcu_read_lock(); + delegation = rcu_dereference(nfsi->delegation); + if (!can_open_delegated(delegation, fmode)) { + rcu_read_unlock(); + break; + } + /* Save the delegation */ + nfs4_stateid_copy(&stateid, &delegation->stateid); + rcu_read_unlock(); + nfs_release_seqid(opendata->o_arg.seqid); + if (!opendata->is_recover) { + ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode); + if (ret != 0) + goto out; + } + ret = -EAGAIN; + + /* Try to update the stateid using the delegation */ + if (update_open_stateid(state, NULL, &stateid, fmode)) + goto out_return_state; + } +out: + return ERR_PTR(ret); +out_return_state: + atomic_inc(&state->count); + return state; +} + +static void +nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state) +{ + struct nfs_client *clp = NFS_SERVER(state->inode)->nfs_client; + struct nfs_delegation *delegation; + int delegation_flags = 0; + + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(state->inode)->delegation); + if (delegation) + delegation_flags = delegation->flags; + rcu_read_unlock(); + if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) { + pr_err_ratelimited("NFS: Broken NFSv4 server %s is " + "returning a delegation for " + "OPEN(CLAIM_DELEGATE_CUR)\n", + clp->cl_hostname); + } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) + nfs_inode_set_delegation(state->inode, + data->owner->so_cred, + &data->o_res); + else + nfs_inode_reclaim_delegation(state->inode, + data->owner->so_cred, + &data->o_res); +} + +/* + * Check the inode attributes against the CLAIM_PREVIOUS returned attributes + * and update the nfs4_state. + */ +static struct nfs4_state * +_nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) +{ + struct inode *inode = data->state->inode; + struct nfs4_state *state = data->state; + int ret; + + if (!data->rpc_done) { + if (data->rpc_status) { + ret = data->rpc_status; + goto err; + } + /* cached opens have already been processed */ + goto update; + } + + ret = nfs_refresh_inode(inode, &data->f_attr); + if (ret) + goto err; + + if (data->o_res.delegation_type != 0) + nfs4_opendata_check_deleg(data, state); +update: + update_open_stateid(state, &data->o_res.stateid, NULL, + data->o_arg.fmode); + atomic_inc(&state->count); + + return state; +err: + return ERR_PTR(ret); + +} + +static struct nfs4_state * +_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) +{ + struct inode *inode; + struct nfs4_state *state = NULL; + int ret; + + if (!data->rpc_done) { + state = nfs4_try_open_cached(data); + goto out; + } + + ret = -EAGAIN; + if (!(data->f_attr.valid & NFS_ATTR_FATTR)) + goto err; + inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, &data->f_attr, data->f_label); + ret = PTR_ERR(inode); + if (IS_ERR(inode)) + goto err; + ret = -ENOMEM; + state = nfs4_get_open_state(inode, data->owner); + if (state == NULL) + goto err_put_inode; + if (data->o_res.delegation_type != 0) + nfs4_opendata_check_deleg(data, state); + update_open_stateid(state, &data->o_res.stateid, NULL, + data->o_arg.fmode); + iput(inode); +out: + nfs_release_seqid(data->o_arg.seqid); + return state; +err_put_inode: + iput(inode); +err: + return ERR_PTR(ret); +} + +static struct nfs4_state * +nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) +{ + if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) + return _nfs4_opendata_reclaim_to_nfs4_state(data); + return _nfs4_opendata_to_nfs4_state(data); +} + +static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state) +{ + struct nfs_inode *nfsi = NFS_I(state->inode); + struct nfs_open_context *ctx; + + spin_lock(&state->inode->i_lock); + list_for_each_entry(ctx, &nfsi->open_files, list) { + if (ctx->state != state) + continue; + get_nfs_open_context(ctx); + spin_unlock(&state->inode->i_lock); + return ctx; + } + spin_unlock(&state->inode->i_lock); + return ERR_PTR(-ENOENT); +} + +static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx, + struct nfs4_state *state, enum open_claim_type4 claim) +{ + struct nfs4_opendata *opendata; + + opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, + NULL, NULL, claim, GFP_NOFS); + if (opendata == NULL) + return ERR_PTR(-ENOMEM); + opendata->state = state; + atomic_inc(&state->count); + return opendata; +} + +static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res) +{ + struct nfs4_state *newstate; + int ret; + + opendata->o_arg.open_flags = 0; + opendata->o_arg.fmode = fmode; + opendata->o_arg.share_access = nfs4_map_atomic_open_share( + NFS_SB(opendata->dentry->d_sb), + fmode, 0); + memset(&opendata->o_res, 0, sizeof(opendata->o_res)); + memset(&opendata->c_res, 0, sizeof(opendata->c_res)); + nfs4_init_opendata_res(opendata); + ret = _nfs4_recover_proc_open(opendata); + if (ret != 0) + return ret; + newstate = nfs4_opendata_to_nfs4_state(opendata); + if (IS_ERR(newstate)) + return PTR_ERR(newstate); + nfs4_close_state(newstate, fmode); + *res = newstate; + return 0; +} + +static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state) +{ + struct nfs4_state *newstate; + int ret; + + /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */ + clear_bit(NFS_O_RDWR_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + /* memory barrier prior to reading state->n_* */ + clear_bit(NFS_DELEGATED_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); + smp_rmb(); + if (state->n_rdwr != 0) { + ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate); + if (ret != 0) + return ret; + if (newstate != state) + return -ESTALE; + } + if (state->n_wronly != 0) { + ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate); + if (ret != 0) + return ret; + if (newstate != state) + return -ESTALE; + } + if (state->n_rdonly != 0) { + ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate); + if (ret != 0) + return ret; + if (newstate != state) + return -ESTALE; + } + /* + * We may have performed cached opens for all three recoveries. + * Check if we need to update the current stateid. + */ + if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0 && + !nfs4_stateid_match(&state->stateid, &state->open_stateid)) { + write_seqlock(&state->seqlock); + if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + } + return 0; +} + +/* + * OPEN_RECLAIM: + * reclaim state on the server after a reboot. + */ +static int _nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state *state) +{ + struct nfs_delegation *delegation; + struct nfs4_opendata *opendata; + fmode_t delegation_type = 0; + int status; + + opendata = nfs4_open_recoverdata_alloc(ctx, state, + NFS4_OPEN_CLAIM_PREVIOUS); + if (IS_ERR(opendata)) + return PTR_ERR(opendata); + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(state->inode)->delegation); + if (delegation != NULL && test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) != 0) + delegation_type = delegation->type; + rcu_read_unlock(); + opendata->o_arg.u.delegation_type = delegation_type; + status = nfs4_open_recover(opendata, state); + nfs4_opendata_put(opendata); + return status; +} + +static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state *state) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_do_open_reclaim(ctx, state); + trace_nfs4_open_reclaim(ctx, 0, err); + if (nfs4_clear_cap_atomic_open_v1(server, err, &exception)) + continue; + if (err != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + return err; +} + +static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + struct nfs_open_context *ctx; + int ret; + + ctx = nfs4_state_find_open_context(state); + if (IS_ERR(ctx)) + return -EAGAIN; + ret = nfs4_do_open_reclaim(ctx, state); + put_nfs_open_context(ctx); + return ret; +} + +static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err) +{ + switch (err) { + default: + printk(KERN_ERR "NFS: %s: unhandled error " + "%d.\n", __func__, err); + case 0: + case -ENOENT: + case -ESTALE: + break; + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_DEADSESSION: + set_bit(NFS_DELEGATED_STATE, &state->flags); + nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); + return -EAGAIN; + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_STALE_STATEID: + set_bit(NFS_DELEGATED_STATE, &state->flags); + case -NFS4ERR_EXPIRED: + /* Don't recall a delegation if it was lost */ + nfs4_schedule_lease_recovery(server->nfs_client); + return -EAGAIN; + case -NFS4ERR_MOVED: + nfs4_schedule_migration_recovery(server); + return -EAGAIN; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(server->nfs_client); + return -EAGAIN; + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OPENMODE: + nfs_inode_find_state_and_recover(state->inode, + stateid); + nfs4_schedule_stateid_recovery(server, state); + return -EAGAIN; + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + set_bit(NFS_DELEGATED_STATE, &state->flags); + ssleep(1); + return -EAGAIN; + case -ENOMEM: + case -NFS4ERR_DENIED: + /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + return 0; + } + return err; +} + +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs4_opendata *opendata; + int err; + + opendata = nfs4_open_recoverdata_alloc(ctx, state, + NFS4_OPEN_CLAIM_DELEG_CUR_FH); + if (IS_ERR(opendata)) + return PTR_ERR(opendata); + nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); + err = nfs4_open_recover(opendata, state); + nfs4_opendata_put(opendata); + return nfs4_handle_delegation_recall_error(server, state, stateid, err); +} + +static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_opendata *data = calldata; + + nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl, + &data->c_arg.seq_args, &data->c_res.seq_res, task); +} + +static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_opendata *data = calldata; + + nfs40_sequence_done(task, &data->c_res.seq_res); + + data->rpc_status = task->tk_status; + if (data->rpc_status == 0) { + nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid); + nfs_confirm_seqid(&data->owner->so_seqid, 0); + renew_lease(data->o_res.server, data->timestamp); + data->rpc_done = 1; + } +} + +static void nfs4_open_confirm_release(void *calldata) +{ + struct nfs4_opendata *data = calldata; + struct nfs4_state *state = NULL; + + /* If this request hasn't been cancelled, do nothing */ + if (data->cancelled == 0) + goto out_free; + /* In case of error, no cleanup! */ + if (!data->rpc_done) + goto out_free; + state = nfs4_opendata_to_nfs4_state(data); + if (!IS_ERR(state)) + nfs4_close_state(state, data->o_arg.fmode); +out_free: + nfs4_opendata_put(data); +} + +static const struct rpc_call_ops nfs4_open_confirm_ops = { + .rpc_call_prepare = nfs4_open_confirm_prepare, + .rpc_call_done = nfs4_open_confirm_done, + .rpc_release = nfs4_open_confirm_release, +}; + +/* + * Note: On error, nfs4_proc_open_confirm will free the struct nfs4_opendata + */ +static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) +{ + struct nfs_server *server = NFS_SERVER(d_inode(data->dir)); + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_CONFIRM], + .rpc_argp = &data->c_arg, + .rpc_resp = &data->c_res, + .rpc_cred = data->owner->so_cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_open_confirm_ops, + .callback_data = data, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC, + }; + int status; + + nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1); + kref_get(&data->kref); + data->rpc_done = 0; + data->rpc_status = 0; + data->timestamp = jiffies; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = nfs4_wait_for_completion_rpc_task(task); + if (status != 0) { + data->cancelled = 1; + smp_wmb(); + } else + status = data->rpc_status; + rpc_put_task(task); + return status; +} + +static void nfs4_open_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_opendata *data = calldata; + struct nfs4_state_owner *sp = data->owner; + struct nfs_client *clp = sp->so_server->nfs_client; + + if (nfs_wait_on_sequence(data->o_arg.seqid, task) != 0) + goto out_wait; + /* + * Check if we still need to send an OPEN call, or if we can use + * a delegation instead. + */ + if (data->state != NULL) { + struct nfs_delegation *delegation; + + if (can_open_cached(data->state, data->o_arg.fmode, data->o_arg.open_flags)) + goto out_no_action; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); + if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR && + data->o_arg.claim != NFS4_OPEN_CLAIM_DELEG_CUR_FH && + can_open_delegated(delegation, data->o_arg.fmode)) + goto unlock_no_action; + rcu_read_unlock(); + } + /* Update client id. */ + data->o_arg.clientid = clp->cl_clientid; + switch (data->o_arg.claim) { + case NFS4_OPEN_CLAIM_PREVIOUS: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0]; + case NFS4_OPEN_CLAIM_FH: + task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; + nfs_copy_fh(&data->o_res.fh, data->o_arg.fh); + } + data->timestamp = jiffies; + if (nfs4_setup_sequence(data->o_arg.server, + &data->o_arg.seq_args, + &data->o_res.seq_res, + task) != 0) + nfs_release_seqid(data->o_arg.seqid); + + /* Set the create mode (note dependency on the session type) */ + data->o_arg.createmode = NFS4_CREATE_UNCHECKED; + if (data->o_arg.open_flags & O_EXCL) { + data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE; + if (nfs4_has_persistent_session(clp)) + data->o_arg.createmode = NFS4_CREATE_GUARDED; + else if (clp->cl_mvops->minor_version > 0) + data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1; + } + return; +unlock_no_action: + rcu_read_unlock(); +out_no_action: + task->tk_action = NULL; +out_wait: + nfs4_sequence_done(task, &data->o_res.seq_res); +} + +static void nfs4_open_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_opendata *data = calldata; + + data->rpc_status = task->tk_status; + + if (!nfs4_sequence_done(task, &data->o_res.seq_res)) + return; + + if (task->tk_status == 0) { + if (data->o_res.f_attr->valid & NFS_ATTR_FATTR_TYPE) { + switch (data->o_res.f_attr->mode & S_IFMT) { + case S_IFREG: + break; + case S_IFLNK: + data->rpc_status = -ELOOP; + break; + case S_IFDIR: + data->rpc_status = -EISDIR; + break; + default: + data->rpc_status = -ENOTDIR; + } + } + renew_lease(data->o_res.server, data->timestamp); + if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM)) + nfs_confirm_seqid(&data->owner->so_seqid, 0); + } + data->rpc_done = 1; +} + +static void nfs4_open_release(void *calldata) +{ + struct nfs4_opendata *data = calldata; + struct nfs4_state *state = NULL; + + /* If this request hasn't been cancelled, do nothing */ + if (data->cancelled == 0) + goto out_free; + /* In case of error, no cleanup! */ + if (data->rpc_status != 0 || !data->rpc_done) + goto out_free; + /* In case we need an open_confirm, no cleanup! */ + if (data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM) + goto out_free; + state = nfs4_opendata_to_nfs4_state(data); + if (!IS_ERR(state)) + nfs4_close_state(state, data->o_arg.fmode); +out_free: + nfs4_opendata_put(data); +} + +static const struct rpc_call_ops nfs4_open_ops = { + .rpc_call_prepare = nfs4_open_prepare, + .rpc_call_done = nfs4_open_done, + .rpc_release = nfs4_open_release, +}; + +static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover) +{ + struct inode *dir = d_inode(data->dir); + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_openargs *o_arg = &data->o_arg; + struct nfs_openres *o_res = &data->o_res; + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN], + .rpc_argp = o_arg, + .rpc_resp = o_res, + .rpc_cred = data->owner->so_cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_open_ops, + .callback_data = data, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC, + }; + int status; + + nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1); + kref_get(&data->kref); + data->rpc_done = 0; + data->rpc_status = 0; + data->cancelled = 0; + data->is_recover = 0; + if (isrecover) { + nfs4_set_sequence_privileged(&o_arg->seq_args); + data->is_recover = 1; + } + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = nfs4_wait_for_completion_rpc_task(task); + if (status != 0) { + data->cancelled = 1; + smp_wmb(); + } else + status = data->rpc_status; + rpc_put_task(task); + + return status; +} + +static int _nfs4_recover_proc_open(struct nfs4_opendata *data) +{ + struct inode *dir = d_inode(data->dir); + struct nfs_openres *o_res = &data->o_res; + int status; + + status = nfs4_run_open_task(data, 1); + if (status != 0 || !data->rpc_done) + return status; + + nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr); + + if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { + status = _nfs4_proc_open_confirm(data); + if (status != 0) + return status; + } + + return status; +} + +/* + * Additional permission checks in order to distinguish between an + * open for read, and an open for execute. This works around the + * fact that NFSv4 OPEN treats read and execute permissions as being + * the same. + * Note that in the non-execute case, we want to turn off permission + * checking if we just created a new file (POSIX open() semantics). + */ +static int nfs4_opendata_access(struct rpc_cred *cred, + struct nfs4_opendata *opendata, + struct nfs4_state *state, fmode_t fmode, + int openflags) +{ + struct nfs_access_entry cache; + u32 mask; + + /* access call failed or for some reason the server doesn't + * support any access modes -- defer access call until later */ + if (opendata->o_res.access_supported == 0) + return 0; + + mask = 0; + /* + * Use openflags to check for exec, because fmode won't + * always have FMODE_EXEC set when file open for exec. + */ + if (openflags & __FMODE_EXEC) { + /* ONLY check for exec rights */ + mask = MAY_EXEC; + } else if ((fmode & FMODE_READ) && !opendata->file_created) + mask = MAY_READ; + + cache.cred = cred; + cache.jiffies = jiffies; + nfs_access_set_mask(&cache, opendata->o_res.access_result); + nfs_access_add_cache(state->inode, &cache); + + if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0) + return 0; + + /* even though OPEN succeeded, access is denied. Close the file */ + nfs4_close_state(state, fmode); + return -EACCES; +} + +/* + * Note: On error, nfs4_proc_open will free the struct nfs4_opendata + */ +static int _nfs4_proc_open(struct nfs4_opendata *data) +{ + struct inode *dir = d_inode(data->dir); + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_openargs *o_arg = &data->o_arg; + struct nfs_openres *o_res = &data->o_res; + int status; + + status = nfs4_run_open_task(data, 0); + if (!data->rpc_done) + return status; + if (status != 0) { + if (status == -NFS4ERR_BADNAME && + !(o_arg->open_flags & O_CREAT)) + return -ENOENT; + return status; + } + + nfs_fattr_map_and_free_names(server, &data->f_attr); + + if (o_arg->open_flags & O_CREAT) { + update_changeattr(dir, &o_res->cinfo); + if (o_arg->open_flags & O_EXCL) + data->file_created = 1; + else if (o_res->cinfo.before != o_res->cinfo.after) + data->file_created = 1; + } + if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) + server->caps &= ~NFS_CAP_POSIX_LOCK; + if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { + status = _nfs4_proc_open_confirm(data); + if (status != 0) + return status; + } + if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) + nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label); + return 0; +} + +static int nfs4_recover_expired_lease(struct nfs_server *server) +{ + return nfs4_client_recover_expired_lease(server->nfs_client); +} + +/* + * OPEN_EXPIRED: + * reclaim state on the server after a network partition. + * Assumes caller holds the appropriate lock + */ +static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *state) +{ + struct nfs4_opendata *opendata; + int ret; + + opendata = nfs4_open_recoverdata_alloc(ctx, state, + NFS4_OPEN_CLAIM_FH); + if (IS_ERR(opendata)) + return PTR_ERR(opendata); + ret = nfs4_open_recover(opendata, state); + if (ret == -ESTALE) + d_drop(ctx->dentry); + nfs4_opendata_put(opendata); + return ret; +} + +static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state *state) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs4_open_expired(ctx, state); + trace_nfs4_open_expired(ctx, 0, err); + if (nfs4_clear_cap_atomic_open_v1(server, err, &exception)) + continue; + switch (err) { + default: + goto out; + case -NFS4ERR_GRACE: + case -NFS4ERR_DELAY: + nfs4_handle_exception(server, err, &exception); + err = 0; + } + } while (exception.retry); +out: + return err; +} + +static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + struct nfs_open_context *ctx; + int ret; + + ctx = nfs4_state_find_open_context(state); + if (IS_ERR(ctx)) + return -EAGAIN; + ret = nfs4_do_open_expired(ctx, state); + put_nfs_open_context(ctx); + return ret; +} + +static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state) +{ + nfs_remove_bad_delegation(state->inode); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); +} + +static void nfs40_clear_delegation_stateid(struct nfs4_state *state) +{ + if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL) + nfs_finish_clear_delegation_stateid(state); +} + +static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + /* NFSv4.0 doesn't allow for delegation recovery on open expire */ + nfs40_clear_delegation_stateid(state); + return nfs4_open_expired(sp, state); +} + +#if defined(CONFIG_NFS_V4_1) +static void nfs41_check_delegation_stateid(struct nfs4_state *state) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + nfs4_stateid stateid; + struct nfs_delegation *delegation; + struct rpc_cred *cred; + int status; + + /* Get the delegation credential for use by test/free_stateid */ + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(state->inode)->delegation); + if (delegation == NULL) { + rcu_read_unlock(); + return; + } + + nfs4_stateid_copy(&stateid, &delegation->stateid); + cred = get_rpccred(delegation->cred); + rcu_read_unlock(); + status = nfs41_test_stateid(server, &stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); + + if (status != NFS_OK) { + /* Free the stateid unless the server explicitly + * informs us the stateid is unrecognized. */ + if (status != -NFS4ERR_BAD_STATEID) + nfs41_free_stateid(server, &stateid, cred); + nfs_finish_clear_delegation_stateid(state); + } + + put_rpccred(cred); +} + +/** + * nfs41_check_open_stateid - possibly free an open stateid + * + * @state: NFSv4 state for an inode + * + * Returns NFS_OK if recovery for this stateid is now finished. + * Otherwise a negative NFS4ERR value is returned. + */ +static int nfs41_check_open_stateid(struct nfs4_state *state) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + nfs4_stateid *stateid = &state->open_stateid; + struct rpc_cred *cred = state->owner->so_cred; + int status; + + /* If a state reset has been done, test_stateid is unneeded */ + if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) && + (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) && + (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0)) + return -NFS4ERR_BAD_STATEID; + + status = nfs41_test_stateid(server, stateid, cred); + trace_nfs4_test_open_stateid(state, NULL, status); + if (status != NFS_OK) { + /* Free the stateid unless the server explicitly + * informs us the stateid is unrecognized. */ + if (status != -NFS4ERR_BAD_STATEID) + nfs41_free_stateid(server, stateid, cred); + + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_O_RDWR_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); + } + return status; +} + +static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + int status; + + nfs41_check_delegation_stateid(state); + status = nfs41_check_open_stateid(state); + if (status != NFS_OK) + status = nfs4_open_expired(sp, state); + return status; +} +#endif + +/* + * on an EXCLUSIVE create, the server should send back a bitmask with FATTR4-* + * fields corresponding to attributes that were used to store the verifier. + * Make sure we clobber those fields in the later setattr call + */ +static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, struct iattr *sattr) +{ + if ((opendata->o_res.attrset[1] & FATTR4_WORD1_TIME_ACCESS) && + !(sattr->ia_valid & ATTR_ATIME_SET)) + sattr->ia_valid |= ATTR_ATIME; + + if ((opendata->o_res.attrset[1] & FATTR4_WORD1_TIME_MODIFY) && + !(sattr->ia_valid & ATTR_MTIME_SET)) + sattr->ia_valid |= ATTR_MTIME; +} + +static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, + fmode_t fmode, + int flags, + struct nfs_open_context *ctx) +{ + struct nfs4_state_owner *sp = opendata->owner; + struct nfs_server *server = sp->so_server; + struct dentry *dentry; + struct nfs4_state *state; + unsigned int seq; + int ret; + + seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); + + ret = _nfs4_proc_open(opendata); + if (ret != 0) + goto out; + + state = nfs4_opendata_to_nfs4_state(opendata); + ret = PTR_ERR(state); + if (IS_ERR(state)) + goto out; + if (server->caps & NFS_CAP_POSIX_LOCK) + set_bit(NFS_STATE_POSIX_LOCKS, &state->flags); + + dentry = opendata->dentry; + if (d_really_is_negative(dentry)) { + /* FIXME: Is this d_drop() ever needed? */ + d_drop(dentry); + dentry = d_add_unique(dentry, igrab(state->inode)); + if (dentry == NULL) { + dentry = opendata->dentry; + } else if (dentry != ctx->dentry) { + dput(ctx->dentry); + ctx->dentry = dget(dentry); + } + nfs_set_verifier(dentry, + nfs_save_change_attribute(d_inode(opendata->dir))); + } + + ret = nfs4_opendata_access(sp->so_cred, opendata, state, fmode, flags); + if (ret != 0) + goto out; + + ctx->state = state; + if (d_inode(dentry) == state->inode) { + nfs_inode_attach_open_context(ctx); + if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) + nfs4_schedule_stateid_recovery(server, state); + } +out: + return ret; +} + +/* + * Returns a referenced nfs4_state + */ +static int _nfs4_do_open(struct inode *dir, + struct nfs_open_context *ctx, + int flags, + struct iattr *sattr, + struct nfs4_label *label, + int *opened) +{ + struct nfs4_state_owner *sp; + struct nfs4_state *state = NULL; + struct nfs_server *server = NFS_SERVER(dir); + struct nfs4_opendata *opendata; + struct dentry *dentry = ctx->dentry; + struct rpc_cred *cred = ctx->cred; + struct nfs4_threshold **ctx_th = &ctx->mdsthreshold; + fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC); + enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; + struct nfs4_label *olabel = NULL; + int status; + + /* Protect against reboot recovery conflicts */ + status = -ENOMEM; + sp = nfs4_get_state_owner(server, cred, GFP_KERNEL); + if (sp == NULL) { + dprintk("nfs4_do_open: nfs4_get_state_owner failed!\n"); + goto out_err; + } + status = nfs4_recover_expired_lease(server); + if (status != 0) + goto err_put_state_owner; + if (d_really_is_positive(dentry)) + nfs4_return_incompatible_delegation(d_inode(dentry), fmode); + status = -ENOMEM; + if (d_really_is_positive(dentry)) + claim = NFS4_OPEN_CLAIM_FH; + opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, + label, claim, GFP_KERNEL); + if (opendata == NULL) + goto err_put_state_owner; + + if (label) { + olabel = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(olabel)) { + status = PTR_ERR(olabel); + goto err_opendata_put; + } + } + + if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { + if (!opendata->f_attr.mdsthreshold) { + opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); + if (!opendata->f_attr.mdsthreshold) + goto err_free_label; + } + opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0]; + } + if (d_really_is_positive(dentry)) + opendata->state = nfs4_get_open_state(d_inode(dentry), sp); + + status = _nfs4_open_and_get_state(opendata, fmode, flags, ctx); + if (status != 0) + goto err_free_label; + state = ctx->state; + + if ((opendata->o_arg.open_flags & O_EXCL) && + (opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) { + nfs4_exclusive_attrset(opendata, sattr); + + nfs_fattr_init(opendata->o_res.f_attr); + status = nfs4_do_setattr(state->inode, cred, + opendata->o_res.f_attr, sattr, + state, label, olabel); + if (status == 0) { + nfs_setattr_update_inode(state->inode, sattr, + opendata->o_res.f_attr); + nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel); + } + } + if (opendata->file_created) + *opened |= FILE_CREATED; + + if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) { + *ctx_th = opendata->f_attr.mdsthreshold; + opendata->f_attr.mdsthreshold = NULL; + } + + nfs4_label_free(olabel); + + nfs4_opendata_put(opendata); + nfs4_put_state_owner(sp); + return 0; +err_free_label: + nfs4_label_free(olabel); +err_opendata_put: + nfs4_opendata_put(opendata); +err_put_state_owner: + nfs4_put_state_owner(sp); +out_err: + return status; +} + + +static struct nfs4_state *nfs4_do_open(struct inode *dir, + struct nfs_open_context *ctx, + int flags, + struct iattr *sattr, + struct nfs4_label *label, + int *opened) +{ + struct nfs_server *server = NFS_SERVER(dir); + struct nfs4_exception exception = { }; + struct nfs4_state *res; + int status; + + do { + status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened); + res = ctx->state; + trace_nfs4_open_file(ctx, flags, status); + if (status == 0) + break; + /* NOTE: BAD_SEQID means the server and client disagree about the + * book-keeping w.r.t. state-changing operations + * (OPEN/CLOSE/LOCK/LOCKU...) + * It is actually a sign of a bug on the client or on the server. + * + * If we receive a BAD_SEQID error in the particular case of + * doing an OPEN, we assume that nfs_increment_open_seqid() will + * have unhashed the old state_owner for us, and that we can + * therefore safely retry using a new one. We should still warn + * the user though... + */ + if (status == -NFS4ERR_BAD_SEQID) { + pr_warn_ratelimited("NFS: v4 server %s " + " returned a bad sequence-id error!\n", + NFS_SERVER(dir)->nfs_client->cl_hostname); + exception.retry = 1; + continue; + } + /* + * BAD_STATEID on OPEN means that the server cancelled our + * state before it received the OPEN_CONFIRM. + * Recover by retrying the request as per the discussion + * on Page 181 of RFC3530. + */ + if (status == -NFS4ERR_BAD_STATEID) { + exception.retry = 1; + continue; + } + if (status == -EAGAIN) { + /* We must have found a delegation */ + exception.retry = 1; + continue; + } + if (nfs4_clear_cap_atomic_open_v1(server, status, &exception)) + continue; + res = ERR_PTR(nfs4_handle_exception(server, + status, &exception)); + } while (exception.retry); + return res; +} + +static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, + struct nfs_fattr *fattr, struct iattr *sattr, + struct nfs4_state *state, struct nfs4_label *ilabel, + struct nfs4_label *olabel) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_setattrargs arg = { + .fh = NFS_FH(inode), + .iap = sattr, + .server = server, + .bitmask = server->attr_bitmask, + .label = ilabel, + }; + struct nfs_setattrres res = { + .fattr = fattr, + .label = olabel, + .server = server, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETATTR], + .rpc_argp = &arg, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long timestamp = jiffies; + fmode_t fmode; + bool truncate; + int status; + + arg.bitmask = nfs4_bitmask(server, ilabel); + if (ilabel) + arg.bitmask = nfs4_bitmask(server, olabel); + + nfs_fattr_init(fattr); + + /* Servers should only apply open mode checks for file size changes */ + truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false; + fmode = truncate ? FMODE_WRITE : FMODE_READ; + + if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) { + /* Use that stateid */ + } else if (truncate && state != NULL) { + struct nfs_lockowner lockowner = { + .l_owner = current->files, + .l_pid = current->tgid, + }; + if (!nfs4_valid_open_stateid(state)) + return -EBADF; + if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE, + &lockowner) == -EIO) + return -EBADF; + } else + nfs4_stateid_copy(&arg.stateid, &zero_stateid); + + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); + if (status == 0 && state != NULL) + renew_lease(server, timestamp); + return status; +} + +static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, + struct nfs_fattr *fattr, struct iattr *sattr, + struct nfs4_state *state, struct nfs4_label *ilabel, + struct nfs4_label *olabel) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs4_exception exception = { + .state = state, + .inode = inode, + }; + int err; + do { + err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel); + trace_nfs4_setattr(inode, err); + switch (err) { + case -NFS4ERR_OPENMODE: + if (!(sattr->ia_valid & ATTR_SIZE)) { + pr_warn_once("NFSv4: server %s is incorrectly " + "applying open mode checks to " + "a SETATTR that is not " + "changing file size.\n", + server->nfs_client->cl_hostname); + } + if (state && !(state->state & FMODE_WRITE)) { + err = -EBADF; + if (sattr->ia_valid & ATTR_OPEN) + err = -EACCES; + goto out; + } + } + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); +out: + return err; +} + +struct nfs4_closedata { + struct inode *inode; + struct nfs4_state *state; + struct nfs_closeargs arg; + struct nfs_closeres res; + struct nfs_fattr fattr; + unsigned long timestamp; + bool roc; + u32 roc_barrier; +}; + +static void nfs4_free_closedata(void *data) +{ + struct nfs4_closedata *calldata = data; + struct nfs4_state_owner *sp = calldata->state->owner; + struct super_block *sb = calldata->state->inode->i_sb; + + if (calldata->roc) + pnfs_roc_release(calldata->state->inode); + nfs4_put_open_state(calldata->state); + nfs_free_seqid(calldata->arg.seqid); + nfs4_put_state_owner(sp); + nfs_sb_deactive(sb); + kfree(calldata); +} + +static void nfs4_close_done(struct rpc_task *task, void *data) +{ + struct nfs4_closedata *calldata = data; + struct nfs4_state *state = calldata->state; + struct nfs_server *server = NFS_SERVER(calldata->inode); + nfs4_stateid *res_stateid = NULL; + + dprintk("%s: begin!\n", __func__); + if (!nfs4_sequence_done(task, &calldata->res.seq_res)) + return; + trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status); + /* hmm. we are done with the inode, and in the process of freeing + * the state_owner. we keep this around to process errors + */ + switch (task->tk_status) { + case 0: + res_stateid = &calldata->res.stateid; + if (calldata->arg.fmode == 0 && calldata->roc) + pnfs_roc_set_barrier(state->inode, + calldata->roc_barrier); + renew_lease(server, calldata->timestamp); + break; + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_EXPIRED: + if (!nfs4_stateid_match(&calldata->arg.stateid, + &state->open_stateid)) { + rpc_restart_call_prepare(task); + goto out_release; + } + if (calldata->arg.fmode == 0) + break; + default: + if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + goto out_release; + } + } + nfs_clear_open_stateid(state, res_stateid, calldata->arg.fmode); +out_release: + nfs_release_seqid(calldata->arg.seqid); + nfs_refresh_inode(calldata->inode, calldata->res.fattr); + dprintk("%s: done, ret = %d!\n", __func__, task->tk_status); +} + +static void nfs4_close_prepare(struct rpc_task *task, void *data) +{ + struct nfs4_closedata *calldata = data; + struct nfs4_state *state = calldata->state; + struct inode *inode = calldata->inode; + bool is_rdonly, is_wronly, is_rdwr; + int call_close = 0; + + dprintk("%s: begin!\n", __func__); + if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) + goto out_wait; + + task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE]; + spin_lock(&state->owner->so_lock); + is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); + is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); + is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); + nfs4_stateid_copy(&calldata->arg.stateid, &state->open_stateid); + /* Calculate the change in open mode */ + calldata->arg.fmode = 0; + if (state->n_rdwr == 0) { + if (state->n_rdonly == 0) + call_close |= is_rdonly; + else if (is_rdonly) + calldata->arg.fmode |= FMODE_READ; + if (state->n_wronly == 0) + call_close |= is_wronly; + else if (is_wronly) + calldata->arg.fmode |= FMODE_WRITE; + } else if (is_rdwr) + calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; + + if (calldata->arg.fmode == 0) + call_close |= is_rdwr; + + if (!nfs4_valid_open_stateid(state)) + call_close = 0; + spin_unlock(&state->owner->so_lock); + + if (!call_close) { + /* Note: exit _without_ calling nfs4_close_done */ + goto out_no_action; + } + + if (calldata->arg.fmode == 0) { + task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE]; + if (calldata->roc && + pnfs_roc_drain(inode, &calldata->roc_barrier, task)) { + nfs_release_seqid(calldata->arg.seqid); + goto out_wait; + } + } + calldata->arg.share_access = + nfs4_map_atomic_open_share(NFS_SERVER(inode), + calldata->arg.fmode, 0); + + nfs_fattr_init(calldata->res.fattr); + calldata->timestamp = jiffies; + if (nfs4_setup_sequence(NFS_SERVER(inode), + &calldata->arg.seq_args, + &calldata->res.seq_res, + task) != 0) + nfs_release_seqid(calldata->arg.seqid); + dprintk("%s: done!\n", __func__); + return; +out_no_action: + task->tk_action = NULL; +out_wait: + nfs4_sequence_done(task, &calldata->res.seq_res); +} + +static const struct rpc_call_ops nfs4_close_ops = { + .rpc_call_prepare = nfs4_close_prepare, + .rpc_call_done = nfs4_close_done, + .rpc_release = nfs4_free_closedata, +}; + +static bool nfs4_roc(struct inode *inode) +{ + if (!nfs_have_layout(inode)) + return false; + return pnfs_roc(inode); +} + +/* + * It is possible for data to be read/written from a mem-mapped file + * after the sys_close call (which hits the vfs layer as a flush). + * This means that we can't safely call nfsv4 close on a file until + * the inode is cleared. This in turn means that we are not good + * NFSv4 citizens - we do not indicate to the server to update the file's + * share state even when we are done with one of the three share + * stateid's in the inode. + * + * NOTE: Caller must be holding the sp->so_owner semaphore! + */ +int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + struct nfs4_closedata *calldata; + struct nfs4_state_owner *sp = state->owner; + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE], + .rpc_cred = state->owner->so_cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_close_ops, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC, + }; + int status = -ENOMEM; + + nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP, + &task_setup_data.rpc_client, &msg); + + calldata = kzalloc(sizeof(*calldata), gfp_mask); + if (calldata == NULL) + goto out; + nfs4_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 1); + calldata->inode = state->inode; + calldata->state = state; + calldata->arg.fh = NFS_FH(state->inode); + /* Serialization for the sequence id */ + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; + calldata->arg.seqid = alloc_seqid(&state->owner->so_seqid, gfp_mask); + if (IS_ERR(calldata->arg.seqid)) + goto out_free_calldata; + calldata->arg.fmode = 0; + calldata->arg.bitmask = server->cache_consistency_bitmask; + calldata->res.fattr = &calldata->fattr; + calldata->res.seqid = calldata->arg.seqid; + calldata->res.server = server; + calldata->roc = nfs4_roc(state->inode); + nfs_sb_active(calldata->inode->i_sb); + + msg.rpc_argp = &calldata->arg; + msg.rpc_resp = &calldata->res; + task_setup_data.callback_data = calldata; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = 0; + if (wait) + status = rpc_wait_for_completion_task(task); + rpc_put_task(task); + return status; +out_free_calldata: + kfree(calldata); +out: + nfs4_put_open_state(state); + nfs4_put_state_owner(sp); + return status; +} + +static struct inode * +nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, + int open_flags, struct iattr *attr, int *opened) +{ + struct nfs4_state *state; + struct nfs4_label l = {0, 0, 0, NULL}, *label = NULL; + + label = nfs4_label_init_security(dir, ctx->dentry, attr, &l); + + /* Protect against concurrent sillydeletes */ + state = nfs4_do_open(dir, ctx, open_flags, attr, label, opened); + + nfs4_label_release_security(label); + + if (IS_ERR(state)) + return ERR_CAST(state); + return state->inode; +} + +static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) +{ + if (ctx->state == NULL) + return; + if (is_sync) + nfs4_close_sync(ctx->state, ctx->mode); + else + nfs4_close_state(ctx->state, ctx->mode); +} + +#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL) +#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) +#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_SECURITY_LABEL - 1UL) + +static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) +{ + struct nfs4_server_caps_arg args = { + .fhandle = fhandle, + }; + struct nfs4_server_caps_res res = {}; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SERVER_CAPS], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + if (status == 0) { + /* Sanity check the server answers */ + switch (server->nfs_client->cl_minorversion) { + case 0: + res.attr_bitmask[1] &= FATTR4_WORD1_NFS40_MASK; + res.attr_bitmask[2] = 0; + break; + case 1: + res.attr_bitmask[2] &= FATTR4_WORD2_NFS41_MASK; + break; + case 2: + res.attr_bitmask[2] &= FATTR4_WORD2_NFS42_MASK; + } + memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); + server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS| + NFS_CAP_SYMLINKS|NFS_CAP_FILEID| + NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER| + NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME| + NFS_CAP_CTIME|NFS_CAP_MTIME| + NFS_CAP_SECURITY_LABEL); + if (res.attr_bitmask[0] & FATTR4_WORD0_ACL && + res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL) + server->caps |= NFS_CAP_ACLS; + if (res.has_links != 0) + server->caps |= NFS_CAP_HARDLINKS; + if (res.has_symlinks != 0) + server->caps |= NFS_CAP_SYMLINKS; + if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID) + server->caps |= NFS_CAP_FILEID; + if (res.attr_bitmask[1] & FATTR4_WORD1_MODE) + server->caps |= NFS_CAP_MODE; + if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS) + server->caps |= NFS_CAP_NLINK; + if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER) + server->caps |= NFS_CAP_OWNER; + if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP) + server->caps |= NFS_CAP_OWNER_GROUP; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS) + server->caps |= NFS_CAP_ATIME; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA) + server->caps |= NFS_CAP_CTIME; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY) + server->caps |= NFS_CAP_MTIME; +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) + server->caps |= NFS_CAP_SECURITY_LABEL; +#endif + memcpy(server->attr_bitmask_nl, res.attr_bitmask, + sizeof(server->attr_bitmask)); + server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + + memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask)); + server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE; + server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; + server->cache_consistency_bitmask[2] = 0; + server->acl_bitmask = res.acl_bitmask; + server->fh_expire_type = res.fh_expire_type; + } + + return status; +} + +int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(server, + _nfs4_server_capabilities(server, fhandle), + &exception); + } while (exception.retry); + return err; +} + +static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + u32 bitmask[3]; + struct nfs4_lookup_root_arg args = { + .bitmask = bitmask, + }; + struct nfs4_lookup_res res = { + .server = server, + .fattr = info->fattr, + .fh = fhandle, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP_ROOT], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + bitmask[0] = nfs4_fattr_bitmap[0]; + bitmask[1] = nfs4_fattr_bitmap[1]; + /* + * Process the label in the upcoming getfattr + */ + bitmask[2] = nfs4_fattr_bitmap[2] & ~FATTR4_WORD2_SECURITY_LABEL; + + nfs_fattr_init(info->fattr); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); +} + +static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_lookup_root(server, fhandle, info); + trace_nfs4_lookup_root(server, fhandle, info->fattr, err); + switch (err) { + case 0: + case -NFS4ERR_WRONGSEC: + goto out; + default: + err = nfs4_handle_exception(server, err, &exception); + } + } while (exception.retry); +out: + return err; +} + +static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info, rpc_authflavor_t flavor) +{ + struct rpc_auth_create_args auth_args = { + .pseudoflavor = flavor, + }; + struct rpc_auth *auth; + int ret; + + auth = rpcauth_create(&auth_args, server->client); + if (IS_ERR(auth)) { + ret = -EACCES; + goto out; + } + ret = nfs4_lookup_root(server, fhandle, info); +out: + return ret; +} + +/* + * Retry pseudoroot lookup with various security flavors. We do this when: + * + * NFSv4.0: the PUTROOTFH operation returns NFS4ERR_WRONGSEC + * NFSv4.1: the server does not support the SECINFO_NO_NAME operation + * + * Returns zero on success, or a negative NFS4ERR value, or a + * negative errno value. + */ +static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + /* Per 3530bis 15.33.5 */ + static const rpc_authflavor_t flav_array[] = { + RPC_AUTH_GSS_KRB5P, + RPC_AUTH_GSS_KRB5I, + RPC_AUTH_GSS_KRB5, + RPC_AUTH_UNIX, /* courtesy */ + RPC_AUTH_NULL, + }; + int status = -EPERM; + size_t i; + + if (server->auth_info.flavor_len > 0) { + /* try each flavor specified by user */ + for (i = 0; i < server->auth_info.flavor_len; i++) { + status = nfs4_lookup_root_sec(server, fhandle, info, + server->auth_info.flavors[i]); + if (status == -NFS4ERR_WRONGSEC || status == -EACCES) + continue; + break; + } + } else { + /* no flavors specified by user, try default list */ + for (i = 0; i < ARRAY_SIZE(flav_array); i++) { + status = nfs4_lookup_root_sec(server, fhandle, info, + flav_array[i]); + if (status == -NFS4ERR_WRONGSEC || status == -EACCES) + continue; + break; + } + } + + /* + * -EACCESS could mean that the user doesn't have correct permissions + * to access the mount. It could also mean that we tried to mount + * with a gss auth flavor, but rpc.gssd isn't running. Either way, + * existing mount programs don't handle -EACCES very well so it should + * be mapped to -EPERM instead. + */ + if (status == -EACCES) + status = -EPERM; + return status; +} + +static int nfs4_do_find_root_sec(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs_fsinfo *info) +{ + int mv = server->nfs_client->cl_minorversion; + return nfs_v4_minor_ops[mv]->find_root_sec(server, fhandle, info); +} + +/** + * nfs4_proc_get_rootfh - get file handle for server's pseudoroot + * @server: initialized nfs_server handle + * @fhandle: we fill in the pseudo-fs root file handle + * @info: we fill in an FSINFO struct + * @auth_probe: probe the auth flavours + * + * Returns zero on success, or a negative errno. + */ +int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info, + bool auth_probe) +{ + int status = 0; + + if (!auth_probe) + status = nfs4_lookup_root(server, fhandle, info); + + if (auth_probe || status == NFS4ERR_WRONGSEC) + status = nfs4_do_find_root_sec(server, fhandle, info); + + if (status == 0) + status = nfs4_server_capabilities(server, fhandle); + if (status == 0) + status = nfs4_do_fsinfo(server, fhandle, info); + + return nfs4_map_errors(status); +} + +static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh, + struct nfs_fsinfo *info) +{ + int error; + struct nfs_fattr *fattr = info->fattr; + struct nfs4_label *label = NULL; + + error = nfs4_server_capabilities(server, mntfh); + if (error < 0) { + dprintk("nfs4_get_root: getcaps error = %d\n", -error); + return error; + } + + label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(label)) + return PTR_ERR(label); + + error = nfs4_proc_getattr(server, mntfh, fattr, label); + if (error < 0) { + dprintk("nfs4_get_root: getattr error = %d\n", -error); + goto err_free_label; + } + + if (fattr->valid & NFS_ATTR_FATTR_FSID && + !nfs_fsid_equal(&server->fsid, &fattr->fsid)) + memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid)); + +err_free_label: + nfs4_label_free(label); + + return error; +} + +/* + * Get locations and (maybe) other attributes of a referral. + * Note that we'll actually follow the referral later when + * we detect fsid mismatch in inode revalidation + */ +static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, struct nfs_fattr *fattr, + struct nfs_fh *fhandle) +{ + int status = -ENOMEM; + struct page *page = NULL; + struct nfs4_fs_locations *locations = NULL; + + page = alloc_page(GFP_KERNEL); + if (page == NULL) + goto out; + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (locations == NULL) + goto out; + + status = nfs4_proc_fs_locations(client, dir, name, locations, page); + if (status != 0) + goto out; + + /* + * If the fsid didn't change, this is a migration event, not a + * referral. Cause us to drop into the exception handler, which + * will kick off migration recovery. + */ + if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) { + dprintk("%s: server did not return a different fsid for" + " a referral at %s\n", __func__, name->name); + status = -NFS4ERR_MOVED; + goto out; + } + /* Fixup attributes for the nfs_lookup() call to nfs_fhget() */ + nfs_fixup_referral_attributes(&locations->fattr); + + /* replace the lookup nfs_fattr with the locations nfs_fattr */ + memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr)); + memset(fhandle, 0, sizeof(struct nfs_fh)); +out: + if (page) + __free_page(page); + kfree(locations); + return status; +} + +static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs4_getattr_arg args = { + .fh = fhandle, + .bitmask = server->attr_bitmask, + }; + struct nfs4_getattr_res res = { + .fattr = fattr, + .label = label, + .server = server, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETATTR], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + args.bitmask = nfs4_bitmask(server, label); + + nfs_fattr_init(fattr); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); +} + +static int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_getattr(server, fhandle, fattr, label); + trace_nfs4_getattr(server, fhandle, fattr, err); + err = nfs4_handle_exception(server, err, + &exception); + } while (exception.retry); + return err; +} + +/* + * The file is not closed if it is opened due to the a request to change + * the size of the file. The open call will not be needed once the + * VFS layer lookup-intents are implemented. + * + * Close is called when the inode is destroyed. + * If we haven't opened the file for O_WRONLY, we + * need to in the size_change case to obtain a stateid. + * + * Got race? + * Because OPEN is always done by name in nfsv4, it is + * possible that we opened a different file by the same + * name. We can recognize this race condition, but we + * can't do anything about it besides returning an error. + * + * This will be fixed with VFS changes (lookup-intent). + */ +static int +nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, + struct iattr *sattr) +{ + struct inode *inode = d_inode(dentry); + struct rpc_cred *cred = NULL; + struct nfs4_state *state = NULL; + struct nfs4_label *label = NULL; + int status; + + if (pnfs_ld_layoutret_on_setattr(inode) && + sattr->ia_valid & ATTR_SIZE && + sattr->ia_size < i_size_read(inode)) + pnfs_commit_and_return_layout(inode); + + nfs_fattr_init(fattr); + + /* Deal with open(O_TRUNC) */ + if (sattr->ia_valid & ATTR_OPEN) + sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME); + + /* Optimization: if the end result is no change, don't RPC */ + if ((sattr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0) + return 0; + + /* Search for an existing open(O_WRITE) file */ + if (sattr->ia_valid & ATTR_FILE) { + struct nfs_open_context *ctx; + + ctx = nfs_file_open_context(sattr->ia_file); + if (ctx) { + cred = ctx->cred; + state = ctx->state; + } + } + + label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); + if (IS_ERR(label)) + return PTR_ERR(label); + + status = nfs4_do_setattr(inode, cred, fattr, sattr, state, NULL, label); + if (status == 0) { + nfs_setattr_update_inode(inode, sattr, fattr); + nfs_setsecurity(inode, fattr, label); + } + nfs4_label_free(label); + return status; +} + +static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, + const struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs_server *server = NFS_SERVER(dir); + int status; + struct nfs4_lookup_arg args = { + .bitmask = server->attr_bitmask, + .dir_fh = NFS_FH(dir), + .name = name, + }; + struct nfs4_lookup_res res = { + .server = server, + .fattr = fattr, + .label = label, + .fh = fhandle, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + args.bitmask = nfs4_bitmask(server, label); + + nfs_fattr_init(fattr); + + dprintk("NFS call lookup %s\n", name->name); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, &res.seq_res, 0); + dprintk("NFS reply lookup: %d\n", status); + return status; +} + +static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) +{ + fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | + NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_MOUNTPOINT; + fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO; + fattr->nlink = 2; +} + +static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, + struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs4_exception exception = { }; + struct rpc_clnt *client = *clnt; + int err; + do { + err = _nfs4_proc_lookup(client, dir, name, fhandle, fattr, label); + trace_nfs4_lookup(dir, name, err); + switch (err) { + case -NFS4ERR_BADNAME: + err = -ENOENT; + goto out; + case -NFS4ERR_MOVED: + err = nfs4_get_referral(client, dir, name, fattr, fhandle); + goto out; + case -NFS4ERR_WRONGSEC: + err = -EPERM; + if (client != *clnt) + goto out; + client = nfs4_negotiate_security(client, dir, name); + if (IS_ERR(client)) + return PTR_ERR(client); + + exception.retry = 1; + break; + default: + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); + } + } while (exception.retry); + +out: + if (err == 0) + *clnt = client; + else if (client != *clnt) + rpc_shutdown_client(client); + + return err; +} + +static int nfs4_proc_lookup(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + int status; + struct rpc_clnt *client = NFS_CLIENT(dir); + + status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, label); + if (client != NFS_CLIENT(dir)) { + rpc_shutdown_client(client); + nfs_fixup_secinfo_attributes(fattr); + } + return status; +} + +struct rpc_clnt * +nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) +{ + struct rpc_clnt *client = NFS_CLIENT(dir); + int status; + + status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, NULL); + if (status < 0) + return ERR_PTR(status); + return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; +} + +static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs4_accessargs args = { + .fh = NFS_FH(inode), + .bitmask = server->cache_consistency_bitmask, + }; + struct nfs4_accessres res = { + .server = server, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = entry->cred, + }; + int mode = entry->mask; + int status = 0; + + /* + * Determine which access bits we want to ask for... + */ + if (mode & MAY_READ) + args.access |= NFS4_ACCESS_READ; + if (S_ISDIR(inode->i_mode)) { + if (mode & MAY_WRITE) + args.access |= NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE; + if (mode & MAY_EXEC) + args.access |= NFS4_ACCESS_LOOKUP; + } else { + if (mode & MAY_WRITE) + args.access |= NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND; + if (mode & MAY_EXEC) + args.access |= NFS4_ACCESS_EXECUTE; + } + + res.fattr = nfs_alloc_fattr(); + if (res.fattr == NULL) + return -ENOMEM; + + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + if (!status) { + nfs_access_set_mask(entry, res.access); + nfs_refresh_inode(inode, res.fattr); + } + nfs_free_fattr(res.fattr); + return status; +} + +static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_access(inode, entry); + trace_nfs4_access(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + +/* + * TODO: For the time being, we don't try to get any attributes + * along with any of the zero-copy operations READ, READDIR, + * READLINK, WRITE. + * + * In the case of the first three, we want to put the GETATTR + * after the read-type operation -- this is because it is hard + * to predict the length of a GETATTR response in v4, and thus + * align the READ data correctly. This means that the GETATTR + * may end up partially falling into the page cache, and we should + * shift it into the 'tail' of the xdr_buf before processing. + * To do this efficiently, we need to know the total length + * of data received, which doesn't seem to be available outside + * of the RPC layer. + * + * In the case of WRITE, we also want to put the GETATTR after + * the operation -- in this case because we want to make sure + * we get the post-operation mtime and size. + * + * Both of these changes to the XDR layer would in fact be quite + * minor, but I decided to leave them for a subsequent patch. + */ +static int _nfs4_proc_readlink(struct inode *inode, struct page *page, + unsigned int pgbase, unsigned int pglen) +{ + struct nfs4_readlink args = { + .fh = NFS_FH(inode), + .pgbase = pgbase, + .pglen = pglen, + .pages = &page, + }; + struct nfs4_readlink_res res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READLINK], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + return nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0); +} + +static int nfs4_proc_readlink(struct inode *inode, struct page *page, + unsigned int pgbase, unsigned int pglen) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_readlink(inode, page, pgbase, pglen); + trace_nfs4_readlink(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + +/* + * This is just for mknod. open(O_CREAT) will always do ->open_context(). + */ +static int +nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, + int flags) +{ + struct nfs4_label l, *ilabel = NULL; + struct nfs_open_context *ctx; + struct nfs4_state *state; + int opened = 0; + int status = 0; + + ctx = alloc_nfs_open_context(dentry, FMODE_READ); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ilabel = nfs4_label_init_security(dir, dentry, sattr, &l); + + sattr->ia_mode &= ~current_umask(); + state = nfs4_do_open(dir, ctx, flags, sattr, ilabel, &opened); + if (IS_ERR(state)) { + status = PTR_ERR(state); + goto out; + } +out: + nfs4_label_release_security(ilabel); + put_nfs_open_context(ctx); + return status; +} + +static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) +{ + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_removeargs args = { + .fh = NFS_FH(dir), + .name = *name, + }; + struct nfs_removeres res = { + .server = server, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); + if (status == 0) + update_changeattr(dir, &res.cinfo); + return status; +} + +static int nfs4_proc_remove(struct inode *dir, struct qstr *name) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_remove(dir, name); + trace_nfs4_remove(dir, name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, + &exception); + } while (exception.retry); + return err; +} + +static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) +{ + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_removeargs *args = msg->rpc_argp; + struct nfs_removeres *res = msg->rpc_resp; + + res->server = server; + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; + nfs4_init_sequence(&args->seq_args, &res->seq_res, 1); + + nfs_fattr_init(res->dir_attr); +} + +static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) +{ + nfs4_setup_sequence(NFS_SERVER(data->dir), + &data->args.seq_args, + &data->res.seq_res, + task); +} + +static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) +{ + struct nfs_unlinkdata *data = task->tk_calldata; + struct nfs_removeres *res = &data->res; + + if (!nfs4_sequence_done(task, &res->seq_res)) + return 0; + if (nfs4_async_handle_error(task, res->server, NULL, + &data->timeout) == -EAGAIN) + return 0; + update_changeattr(dir, &res->cinfo); + return 1; +} + +static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir) +{ + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_renameargs *arg = msg->rpc_argp; + struct nfs_renameres *res = msg->rpc_resp; + + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME]; + res->server = server; + nfs4_init_sequence(&arg->seq_args, &res->seq_res, 1); +} + +static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data) +{ + nfs4_setup_sequence(NFS_SERVER(data->old_dir), + &data->args.seq_args, + &data->res.seq_res, + task); +} + +static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, + struct inode *new_dir) +{ + struct nfs_renamedata *data = task->tk_calldata; + struct nfs_renameres *res = &data->res; + + if (!nfs4_sequence_done(task, &res->seq_res)) + return 0; + if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN) + return 0; + + update_changeattr(old_dir, &res->old_cinfo); + update_changeattr(new_dir, &res->new_cinfo); + return 1; +} + +static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *name) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs4_link_arg arg = { + .fh = NFS_FH(inode), + .dir_fh = NFS_FH(dir), + .name = name, + .bitmask = server->attr_bitmask, + }; + struct nfs4_link_res res = { + .server = server, + .label = NULL, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LINK], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int status = -ENOMEM; + + res.fattr = nfs_alloc_fattr(); + if (res.fattr == NULL) + goto out; + + res.label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(res.label)) { + status = PTR_ERR(res.label); + goto out; + } + arg.bitmask = nfs4_bitmask(server, res.label); + + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); + if (!status) { + update_changeattr(dir, &res.cinfo); + status = nfs_post_op_update_inode(inode, res.fattr); + if (!status) + nfs_setsecurity(inode, res.fattr, res.label); + } + + + nfs4_label_free(res.label); + +out: + nfs_free_fattr(res.fattr); + return status; +} + +static int nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *name) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(NFS_SERVER(inode), + _nfs4_proc_link(inode, dir, name), + &exception); + } while (exception.retry); + return err; +} + +struct nfs4_createdata { + struct rpc_message msg; + struct nfs4_create_arg arg; + struct nfs4_create_res res; + struct nfs_fh fh; + struct nfs_fattr fattr; + struct nfs4_label *label; +}; + +static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, + struct qstr *name, struct iattr *sattr, u32 ftype) +{ + struct nfs4_createdata *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data != NULL) { + struct nfs_server *server = NFS_SERVER(dir); + + data->label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(data->label)) + goto out_free; + + data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE]; + data->msg.rpc_argp = &data->arg; + data->msg.rpc_resp = &data->res; + data->arg.dir_fh = NFS_FH(dir); + data->arg.server = server; + data->arg.name = name; + data->arg.attrs = sattr; + data->arg.ftype = ftype; + data->arg.bitmask = nfs4_bitmask(server, data->label); + data->res.server = server; + data->res.fh = &data->fh; + data->res.fattr = &data->fattr; + data->res.label = data->label; + nfs_fattr_init(data->res.fattr); + } + return data; +out_free: + kfree(data); + return NULL; +} + +static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_createdata *data) +{ + int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg, + &data->arg.seq_args, &data->res.seq_res, 1); + if (status == 0) { + update_changeattr(dir, &data->res.dir_cinfo); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label); + } + return status; +} + +static void nfs4_free_createdata(struct nfs4_createdata *data) +{ + nfs4_label_free(data->label); + kfree(data); +} + +static int _nfs4_proc_symlink(struct inode *dir, struct dentry *dentry, + struct page *page, unsigned int len, struct iattr *sattr, + struct nfs4_label *label) +{ + struct nfs4_createdata *data; + int status = -ENAMETOOLONG; + + if (len > NFS4_MAXPATHLEN) + goto out; + + status = -ENOMEM; + data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4LNK); + if (data == NULL) + goto out; + + data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SYMLINK]; + data->arg.u.symlink.pages = &page; + data->arg.u.symlink.len = len; + data->arg.label = label; + + status = nfs4_do_create(dir, dentry, data); + + nfs4_free_createdata(data); +out: + return status; +} + +static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry, + struct page *page, unsigned int len, struct iattr *sattr) +{ + struct nfs4_exception exception = { }; + struct nfs4_label l, *label = NULL; + int err; + + label = nfs4_label_init_security(dir, dentry, sattr, &l); + + do { + err = _nfs4_proc_symlink(dir, dentry, page, len, sattr, label); + trace_nfs4_symlink(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, + &exception); + } while (exception.retry); + + nfs4_label_release_security(label); + return err; +} + +static int _nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, + struct iattr *sattr, struct nfs4_label *label) +{ + struct nfs4_createdata *data; + int status = -ENOMEM; + + data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4DIR); + if (data == NULL) + goto out; + + data->arg.label = label; + status = nfs4_do_create(dir, dentry, data); + + nfs4_free_createdata(data); +out: + return status; +} + +static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, + struct iattr *sattr) +{ + struct nfs4_exception exception = { }; + struct nfs4_label l, *label = NULL; + int err; + + label = nfs4_label_init_security(dir, dentry, sattr, &l); + + sattr->ia_mode &= ~current_umask(); + do { + err = _nfs4_proc_mkdir(dir, dentry, sattr, label); + trace_nfs4_mkdir(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, + &exception); + } while (exception.retry); + nfs4_label_release_security(label); + + return err; +} + +static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, + u64 cookie, struct page **pages, unsigned int count, int plus) +{ + struct inode *dir = d_inode(dentry); + struct nfs4_readdir_arg args = { + .fh = NFS_FH(dir), + .pages = pages, + .pgbase = 0, + .count = count, + .bitmask = NFS_SERVER(d_inode(dentry))->attr_bitmask, + .plus = plus, + }; + struct nfs4_readdir_res res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READDIR], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + dprintk("%s: dentry = %pd2, cookie = %Lu\n", __func__, + dentry, + (unsigned long long)cookie); + nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args); + res.pgbase = args.pgbase; + status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); + if (status >= 0) { + memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE); + status += args.pgbase; + } + + nfs_invalidate_atime(dir); + + dprintk("%s: returns %d\n", __func__, status); + return status; +} + +static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, + u64 cookie, struct page **pages, unsigned int count, int plus) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_readdir(dentry, cred, cookie, + pages, count, plus); + trace_nfs4_readdir(d_inode(dentry), err); + err = nfs4_handle_exception(NFS_SERVER(d_inode(dentry)), err, + &exception); + } while (exception.retry); + return err; +} + +static int _nfs4_proc_mknod(struct inode *dir, struct dentry *dentry, + struct iattr *sattr, struct nfs4_label *label, dev_t rdev) +{ + struct nfs4_createdata *data; + int mode = sattr->ia_mode; + int status = -ENOMEM; + + data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4SOCK); + if (data == NULL) + goto out; + + if (S_ISFIFO(mode)) + data->arg.ftype = NF4FIFO; + else if (S_ISBLK(mode)) { + data->arg.ftype = NF4BLK; + data->arg.u.device.specdata1 = MAJOR(rdev); + data->arg.u.device.specdata2 = MINOR(rdev); + } + else if (S_ISCHR(mode)) { + data->arg.ftype = NF4CHR; + data->arg.u.device.specdata1 = MAJOR(rdev); + data->arg.u.device.specdata2 = MINOR(rdev); + } else if (!S_ISSOCK(mode)) { + status = -EINVAL; + goto out_free; + } + + data->arg.label = label; + status = nfs4_do_create(dir, dentry, data); +out_free: + nfs4_free_createdata(data); +out: + return status; +} + +static int nfs4_proc_mknod(struct inode *dir, struct dentry *dentry, + struct iattr *sattr, dev_t rdev) +{ + struct nfs4_exception exception = { }; + struct nfs4_label l, *label = NULL; + int err; + + label = nfs4_label_init_security(dir, dentry, sattr, &l); + + sattr->ia_mode &= ~current_umask(); + do { + err = _nfs4_proc_mknod(dir, dentry, sattr, label, rdev); + trace_nfs4_mknod(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, + &exception); + } while (exception.retry); + + nfs4_label_release_security(label); + + return err; +} + +static int _nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsstat *fsstat) +{ + struct nfs4_statfs_arg args = { + .fh = fhandle, + .bitmask = server->attr_bitmask, + }; + struct nfs4_statfs_res res = { + .fsstat = fsstat, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_STATFS], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + nfs_fattr_init(fsstat->fattr); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); +} + +static int nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsstat *fsstat) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(server, + _nfs4_proc_statfs(server, fhandle, fsstat), + &exception); + } while (exception.retry); + return err; +} + +static int _nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *fsinfo) +{ + struct nfs4_fsinfo_arg args = { + .fh = fhandle, + .bitmask = server->attr_bitmask, + }; + struct nfs4_fsinfo_res res = { + .fsinfo = fsinfo, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSINFO], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); +} + +static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo) +{ + struct nfs4_exception exception = { }; + unsigned long now = jiffies; + int err; + + do { + err = _nfs4_do_fsinfo(server, fhandle, fsinfo); + trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err); + if (err == 0) { + struct nfs_client *clp = server->nfs_client; + + spin_lock(&clp->cl_lock); + clp->cl_lease_time = fsinfo->lease_time * HZ; + clp->cl_last_renewal = now; + spin_unlock(&clp->cl_lock); + break; + } + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + return err; +} + +static int nfs4_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo) +{ + int error; + + nfs_fattr_init(fsinfo->fattr); + error = nfs4_do_fsinfo(server, fhandle, fsinfo); + if (error == 0) { + /* block layout checks this! */ + server->pnfs_blksize = fsinfo->blksize; + set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype); + } + + return error; +} + +static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_pathconf *pathconf) +{ + struct nfs4_pathconf_arg args = { + .fh = fhandle, + .bitmask = server->attr_bitmask, + }; + struct nfs4_pathconf_res res = { + .pathconf = pathconf, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_PATHCONF], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + /* None of the pathconf attributes are mandatory to implement */ + if ((args.bitmask[0] & nfs4_pathconf_bitmap[0]) == 0) { + memset(pathconf, 0, sizeof(*pathconf)); + return 0; + } + + nfs_fattr_init(pathconf->fattr); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); +} + +static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_pathconf *pathconf) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = nfs4_handle_exception(server, + _nfs4_proc_pathconf(server, fhandle, pathconf), + &exception); + } while (exception.retry); + return err; +} + +int nfs4_set_rw_stateid(nfs4_stateid *stateid, + const struct nfs_open_context *ctx, + const struct nfs_lock_context *l_ctx, + fmode_t fmode) +{ + const struct nfs_lockowner *lockowner = NULL; + + if (l_ctx != NULL) + lockowner = &l_ctx->lockowner; + return nfs4_select_rw_stateid(stateid, ctx->state, fmode, lockowner); +} +EXPORT_SYMBOL_GPL(nfs4_set_rw_stateid); + +static bool nfs4_stateid_is_current(nfs4_stateid *stateid, + const struct nfs_open_context *ctx, + const struct nfs_lock_context *l_ctx, + fmode_t fmode) +{ + nfs4_stateid current_stateid; + + /* If the current stateid represents a lost lock, then exit */ + if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode) == -EIO) + return true; + return nfs4_stateid_match(stateid, ¤t_stateid); +} + +static bool nfs4_error_stateid_expired(int err) +{ + switch (err) { + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_OPENMODE: + case -NFS4ERR_EXPIRED: + return true; + } + return false; +} + +void __nfs4_read_done_cb(struct nfs_pgio_header *hdr) +{ + nfs_invalidate_atime(hdr->inode); +} + +static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + struct nfs_server *server = NFS_SERVER(hdr->inode); + + trace_nfs4_read(hdr, task->tk_status); + if (nfs4_async_handle_error(task, server, + hdr->args.context->state, + NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + __nfs4_read_done_cb(hdr); + if (task->tk_status > 0) + renew_lease(server, hdr->timestamp); + return 0; +} + +static bool nfs4_read_stateid_changed(struct rpc_task *task, + struct nfs_pgio_args *args) +{ + + if (!nfs4_error_stateid_expired(task->tk_status) || + nfs4_stateid_is_current(&args->stateid, + args->context, + args->lock_context, + FMODE_READ)) + return false; + rpc_restart_call_prepare(task); + return true; +} + +static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + + dprintk("--> %s\n", __func__); + + if (!nfs4_sequence_done(task, &hdr->res.seq_res)) + return -EAGAIN; + if (nfs4_read_stateid_changed(task, &hdr->args)) + return -EAGAIN; + return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) : + nfs4_read_done_cb(task, hdr); +} + +static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr, + struct rpc_message *msg) +{ + hdr->timestamp = jiffies; + hdr->pgio_done_cb = nfs4_read_done_cb; + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; + nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0); +} + +static int nfs4_proc_pgio_rpc_prepare(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (nfs4_setup_sequence(NFS_SERVER(hdr->inode), + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return 0; + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, + hdr->rw_ops->rw_mode) == -EIO) + return -EIO; + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) + return -EIO; + return 0; +} + +static int nfs4_write_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode = hdr->inode; + + trace_nfs4_write(hdr, task->tk_status); + if (nfs4_async_handle_error(task, NFS_SERVER(inode), + hdr->args.context->state, + NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return -EAGAIN; + } + if (task->tk_status >= 0) { + renew_lease(NFS_SERVER(inode), hdr->timestamp); + nfs_writeback_update_inode(hdr); + } + return 0; +} + +static bool nfs4_write_stateid_changed(struct rpc_task *task, + struct nfs_pgio_args *args) +{ + + if (!nfs4_error_stateid_expired(task->tk_status) || + nfs4_stateid_is_current(&args->stateid, + args->context, + args->lock_context, + FMODE_WRITE)) + return false; + rpc_restart_call_prepare(task); + return true; +} + +static int nfs4_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + if (!nfs4_sequence_done(task, &hdr->res.seq_res)) + return -EAGAIN; + if (nfs4_write_stateid_changed(task, &hdr->args)) + return -EAGAIN; + return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) : + nfs4_write_done_cb(task, hdr); +} + +static +bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr) +{ + /* Don't request attributes for pNFS or O_DIRECT writes */ + if (hdr->ds_clp != NULL || hdr->dreq != NULL) + return false; + /* Otherwise, request attributes if and only if we don't hold + * a delegation + */ + return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0; +} + +static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, + struct rpc_message *msg) +{ + struct nfs_server *server = NFS_SERVER(hdr->inode); + + if (!nfs4_write_need_cache_consistency_data(hdr)) { + hdr->args.bitmask = NULL; + hdr->res.fattr = NULL; + } else + hdr->args.bitmask = server->cache_consistency_bitmask; + + if (!hdr->pgio_done_cb) + hdr->pgio_done_cb = nfs4_write_done_cb; + hdr->res.server = server; + hdr->timestamp = jiffies; + + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; + nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 1); +} + +static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) +{ + nfs4_setup_sequence(NFS_SERVER(data->inode), + &data->args.seq_args, + &data->res.seq_res, + task); +} + +static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *data) +{ + struct inode *inode = data->inode; + + trace_nfs4_commit(data, task->tk_status); + if (nfs4_async_handle_error(task, NFS_SERVER(inode), + NULL, NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return -EAGAIN; + } + return 0; +} + +static int nfs4_commit_done(struct rpc_task *task, struct nfs_commit_data *data) +{ + if (!nfs4_sequence_done(task, &data->res.seq_res)) + return -EAGAIN; + return data->commit_done_cb(task, data); +} + +static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg) +{ + struct nfs_server *server = NFS_SERVER(data->inode); + + if (data->commit_done_cb == NULL) + data->commit_done_cb = nfs4_commit_done_cb; + data->res.server = server; + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); +} + +struct nfs4_renewdata { + struct nfs_client *client; + unsigned long timestamp; +}; + +/* + * nfs4_proc_async_renew(): This is not one of the nfs_rpc_ops; it is a special + * standalone procedure for queueing an asynchronous RENEW. + */ +static void nfs4_renew_release(void *calldata) +{ + struct nfs4_renewdata *data = calldata; + struct nfs_client *clp = data->client; + + if (atomic_read(&clp->cl_count) > 1) + nfs4_schedule_state_renewal(clp); + nfs_put_client(clp); + kfree(data); +} + +static void nfs4_renew_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_renewdata *data = calldata; + struct nfs_client *clp = data->client; + unsigned long timestamp = data->timestamp; + + trace_nfs4_renew_async(clp, task->tk_status); + switch (task->tk_status) { + case 0: + break; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + break; + default: + /* Unless we're shutting down, schedule state recovery! */ + if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0) + return; + if (task->tk_status != NFS4ERR_CB_PATH_DOWN) { + nfs4_schedule_lease_recovery(clp); + return; + } + nfs4_schedule_path_down_recovery(clp); + } + do_renew_lease(clp, timestamp); +} + +static const struct rpc_call_ops nfs4_renew_ops = { + .rpc_call_done = nfs4_renew_done, + .rpc_release = nfs4_renew_release, +}; + +static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW], + .rpc_argp = clp, + .rpc_cred = cred, + }; + struct nfs4_renewdata *data; + + if (renew_flags == 0) + return 0; + if (!atomic_inc_not_zero(&clp->cl_count)) + return -EIO; + data = kmalloc(sizeof(*data), GFP_NOFS); + if (data == NULL) + return -ENOMEM; + data->client = clp; + data->timestamp = jiffies; + return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT, + &nfs4_renew_ops, data); +} + +static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW], + .rpc_argp = clp, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status < 0) + return status; + do_renew_lease(clp, now); + return 0; +} + +static inline int nfs4_server_supports_acls(struct nfs_server *server) +{ + return server->caps & NFS_CAP_ACLS; +} + +/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that + * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_SIZE) bytes on + * the stack. + */ +#define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) + +static int buf_to_pages_noslab(const void *buf, size_t buflen, + struct page **pages, unsigned int *pgbase) +{ + struct page *newpage, **spages; + int rc = 0; + size_t len; + spages = pages; + + do { + len = min_t(size_t, PAGE_SIZE, buflen); + newpage = alloc_page(GFP_KERNEL); + + if (newpage == NULL) + goto unwind; + memcpy(page_address(newpage), buf, len); + buf += len; + buflen -= len; + *pages++ = newpage; + rc++; + } while (buflen != 0); + + return rc; + +unwind: + for(; rc > 0; rc--) + __free_page(spages[rc-1]); + return -ENOMEM; +} + +struct nfs4_cached_acl { + int cached; + size_t len; + char data[0]; +}; + +static void nfs4_set_cached_acl(struct inode *inode, struct nfs4_cached_acl *acl) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + spin_lock(&inode->i_lock); + kfree(nfsi->nfs4_acl); + nfsi->nfs4_acl = acl; + spin_unlock(&inode->i_lock); +} + +static void nfs4_zap_acl_attr(struct inode *inode) +{ + nfs4_set_cached_acl(inode, NULL); +} + +static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_t buflen) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs4_cached_acl *acl; + int ret = -ENOENT; + + spin_lock(&inode->i_lock); + acl = nfsi->nfs4_acl; + if (acl == NULL) + goto out; + if (buf == NULL) /* user is just asking for length */ + goto out_len; + if (acl->cached == 0) + goto out; + ret = -ERANGE; /* see getxattr(2) man page */ + if (acl->len > buflen) + goto out; + memcpy(buf, acl->data, acl->len); +out_len: + ret = acl->len; +out: + spin_unlock(&inode->i_lock); + return ret; +} + +static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) +{ + struct nfs4_cached_acl *acl; + size_t buflen = sizeof(*acl) + acl_len; + + if (buflen <= PAGE_SIZE) { + acl = kmalloc(buflen, GFP_KERNEL); + if (acl == NULL) + goto out; + acl->cached = 1; + _copy_from_pages(acl->data, pages, pgbase, acl_len); + } else { + acl = kmalloc(sizeof(*acl), GFP_KERNEL); + if (acl == NULL) + goto out; + acl->cached = 0; + } + acl->len = acl_len; +out: + nfs4_set_cached_acl(inode, acl); +} + +/* + * The getxattr API returns the required buffer length when called with a + * NULL buf. The NFSv4 acl tool then calls getxattr again after allocating + * the required buf. On a NULL buf, we send a page of data to the server + * guessing that the ACL request can be serviced by a page. If so, we cache + * up to the page of ACL data, and the 2nd call to getxattr is serviced by + * the cache. If not so, we throw away the page, and cache the required + * length. The next getxattr call will then produce another round trip to + * the server, this time with the input buf of the required size. + */ +static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) +{ + struct page *pages[NFS4ACL_MAXPAGES] = {NULL, }; + struct nfs_getaclargs args = { + .fh = NFS_FH(inode), + .acl_pages = pages, + .acl_len = buflen, + }; + struct nfs_getaclres res = { + .acl_len = buflen, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETACL], + .rpc_argp = &args, + .rpc_resp = &res, + }; + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); + int ret = -ENOMEM, i; + + /* As long as we're doing a round trip to the server anyway, + * let's be prepared for a page of acl data. */ + if (npages == 0) + npages = 1; + if (npages > ARRAY_SIZE(pages)) + return -ERANGE; + + for (i = 0; i < npages; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_free; + } + + /* for decoding across pages */ + res.acl_scratch = alloc_page(GFP_KERNEL); + if (!res.acl_scratch) + goto out_free; + + args.acl_len = npages * PAGE_SIZE; + args.acl_pgbase = 0; + + dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", + __func__, buf, buflen, npages, args.acl_len); + ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), + &msg, &args.seq_args, &res.seq_res, 0); + if (ret) + goto out_free; + + /* Handle the case where the passed-in buffer is too short */ + if (res.acl_flags & NFS4_ACL_TRUNC) { + /* Did the user only issue a request for the acl length? */ + if (buf == NULL) + goto out_ok; + ret = -ERANGE; + goto out_free; + } + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len); + if (buf) { + if (res.acl_len > buflen) { + ret = -ERANGE; + goto out_free; + } + _copy_from_pages(buf, pages, res.acl_data_offset, res.acl_len); + } +out_ok: + ret = res.acl_len; +out_free: + for (i = 0; i < npages; i++) + if (pages[i]) + __free_page(pages[i]); + if (res.acl_scratch) + __free_page(res.acl_scratch); + return ret; +} + +static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) +{ + struct nfs4_exception exception = { }; + ssize_t ret; + do { + ret = __nfs4_get_acl_uncached(inode, buf, buflen); + trace_nfs4_get_acl(inode, ret); + if (ret >= 0) + break; + ret = nfs4_handle_exception(NFS_SERVER(inode), ret, &exception); + } while (exception.retry); + return ret; +} + +static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen) +{ + struct nfs_server *server = NFS_SERVER(inode); + int ret; + + if (!nfs4_server_supports_acls(server)) + return -EOPNOTSUPP; + ret = nfs_revalidate_inode(server, inode); + if (ret < 0) + return ret; + if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL) + nfs_zap_acl_cache(inode); + ret = nfs4_read_cached_acl(inode, buf, buflen); + if (ret != -ENOENT) + /* -ENOENT is returned if there is no ACL or if there is an ACL + * but no cached acl data, just the acl length */ + return ret; + return nfs4_get_acl_uncached(inode, buf, buflen); +} + +static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct page *pages[NFS4ACL_MAXPAGES]; + struct nfs_setaclargs arg = { + .fh = NFS_FH(inode), + .acl_pages = pages, + .acl_len = buflen, + }; + struct nfs_setaclres res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETACL], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); + int ret, i; + + if (!nfs4_server_supports_acls(server)) + return -EOPNOTSUPP; + if (npages > ARRAY_SIZE(pages)) + return -ERANGE; + i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase); + if (i < 0) + return i; + nfs4_inode_return_delegation(inode); + ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); + + /* + * Free each page after tx, so the only ref left is + * held by the network stack + */ + for (; i > 0; i--) + put_page(pages[i-1]); + + /* + * Acl update can result in inode attribute update. + * so mark the attribute cache invalid. + */ + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR; + spin_unlock(&inode->i_lock); + nfs_access_zap_cache(inode); + nfs_zap_acl_cache(inode); + return ret; +} + +static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = __nfs4_proc_set_acl(inode, buf, buflen); + trace_nfs4_set_acl(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +static int _nfs4_get_security_label(struct inode *inode, void *buf, + size_t buflen) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_fattr fattr; + struct nfs4_label label = {0, 0, buflen, buf}; + + u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL }; + struct nfs4_getattr_arg arg = { + .fh = NFS_FH(inode), + .bitmask = bitmask, + }; + struct nfs4_getattr_res res = { + .fattr = &fattr, + .label = &label, + .server = server, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETATTR], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int ret; + + nfs_fattr_init(&fattr); + + ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 0); + if (ret) + return ret; + if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL)) + return -ENOENT; + if (buflen < label.len) + return -ERANGE; + return 0; +} + +static int nfs4_get_security_label(struct inode *inode, void *buf, + size_t buflen) +{ + struct nfs4_exception exception = { }; + int err; + + if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) + return -EOPNOTSUPP; + + do { + err = _nfs4_get_security_label(inode, buf, buflen); + trace_nfs4_get_security_label(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + +static int _nfs4_do_set_security_label(struct inode *inode, + struct nfs4_label *ilabel, + struct nfs_fattr *fattr, + struct nfs4_label *olabel) +{ + + struct iattr sattr = {0}; + struct nfs_server *server = NFS_SERVER(inode); + const u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL }; + struct nfs_setattrargs arg = { + .fh = NFS_FH(inode), + .iap = &sattr, + .server = server, + .bitmask = bitmask, + .label = ilabel, + }; + struct nfs_setattrres res = { + .fattr = fattr, + .label = olabel, + .server = server, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETATTR], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int status; + + nfs4_stateid_copy(&arg.stateid, &zero_stateid); + + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); + if (status) + dprintk("%s failed: %d\n", __func__, status); + + return status; +} + +static int nfs4_do_set_security_label(struct inode *inode, + struct nfs4_label *ilabel, + struct nfs_fattr *fattr, + struct nfs4_label *olabel) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs4_do_set_security_label(inode, ilabel, + fattr, olabel); + trace_nfs4_set_security_label(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + +static int +nfs4_set_security_label(struct dentry *dentry, const void *buf, size_t buflen) +{ + struct nfs4_label ilabel, *olabel = NULL; + struct nfs_fattr fattr; + struct rpc_cred *cred; + struct inode *inode = d_inode(dentry); + int status; + + if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) + return -EOPNOTSUPP; + + nfs_fattr_init(&fattr); + + ilabel.pi = 0; + ilabel.lfs = 0; + ilabel.label = (char *)buf; + ilabel.len = buflen; + + cred = rpc_lookup_cred(); + if (IS_ERR(cred)) + return PTR_ERR(cred); + + olabel = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); + if (IS_ERR(olabel)) { + status = -PTR_ERR(olabel); + goto out; + } + + status = nfs4_do_set_security_label(inode, &ilabel, &fattr, olabel); + if (status == 0) + nfs_setsecurity(inode, &fattr, olabel); + + nfs4_label_free(olabel); +out: + put_rpccred(cred); + return status; +} +#endif /* CONFIG_NFS_V4_SECURITY_LABEL */ + + +static int +nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, + struct nfs4_state *state, long *timeout) +{ + struct nfs_client *clp = server->nfs_client; + + if (task->tk_status >= 0) + return 0; + switch(task->tk_status) { + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OPENMODE: + if (state == NULL) + break; + if (nfs4_schedule_stateid_recovery(server, state) < 0) + goto recovery_failed; + goto wait_on_recovery; + case -NFS4ERR_EXPIRED: + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(server, state) < 0) + goto recovery_failed; + } + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_STALE_CLIENTID: + nfs4_schedule_lease_recovery(clp); + goto wait_on_recovery; + case -NFS4ERR_MOVED: + if (nfs4_schedule_migration_recovery(server) < 0) + goto recovery_failed; + goto wait_on_recovery; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + goto wait_on_recovery; +#if defined(CONFIG_NFS_V4_1) + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + dprintk("%s ERROR %d, Reset session\n", __func__, + task->tk_status); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + goto wait_on_recovery; +#endif /* CONFIG_NFS_V4_1 */ + case -NFS4ERR_DELAY: + nfs_inc_server_stats(server, NFSIOS_DELAY); + rpc_delay(task, nfs4_update_delay(timeout)); + goto restart_call; + case -NFS4ERR_GRACE: + rpc_delay(task, NFS4_POLL_RETRY_MAX); + case -NFS4ERR_RETRY_UNCACHED_REP: + case -NFS4ERR_OLD_STATEID: + goto restart_call; + } + task->tk_status = nfs4_map_errors(task->tk_status); + return 0; +recovery_failed: + task->tk_status = -EIO; + return 0; +wait_on_recovery: + rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) + rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + goto recovery_failed; +restart_call: + task->tk_status = 0; + return -EAGAIN; +} + +static void nfs4_init_boot_verifier(const struct nfs_client *clp, + nfs4_verifier *bootverf) +{ + __be32 verf[2]; + + if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) { + /* An impossible timestamp guarantees this value + * will never match a generated boot time. */ + verf[0] = 0; + verf[1] = cpu_to_be32(NSEC_PER_SEC + 1); + } else { + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + verf[0] = cpu_to_be32(nn->boot_time.tv_sec); + verf[1] = cpu_to_be32(nn->boot_time.tv_nsec); + } + memcpy(bootverf->data, verf, sizeof(bootverf->data)); +} + +static unsigned int +nfs4_init_nonuniform_client_string(struct nfs_client *clp, + char *buf, size_t len) +{ + unsigned int result; + + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); + + rcu_read_lock(); + result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s", + clp->cl_ipaddr, + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR), + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_PROTO)); + rcu_read_unlock(); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); + return result; +} + +static unsigned int +nfs4_init_uniform_client_string(struct nfs_client *clp, + char *buf, size_t len) +{ + const char *nodename = clp->cl_rpcclient->cl_nodename; + unsigned int result; + + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); + + if (nfs4_client_id_uniquifier[0] != '\0') + result = scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", + clp->rpc_ops->version, + clp->cl_minorversion, + nfs4_client_id_uniquifier, + nodename); + else + result = scnprintf(buf, len, "Linux NFSv%u.%u %s", + clp->rpc_ops->version, clp->cl_minorversion, + nodename); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); + return result; +} + +/* + * nfs4_callback_up_net() starts only "tcp" and "tcp6" callback + * services. Advertise one based on the address family of the + * clientaddr. + */ +static unsigned int +nfs4_init_callback_netid(const struct nfs_client *clp, char *buf, size_t len) +{ + if (strchr(clp->cl_ipaddr, ':') != NULL) + return scnprintf(buf, len, "tcp6"); + else + return scnprintf(buf, len, "tcp"); +} + +static void nfs4_setclientid_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_setclientid *sc = calldata; + + if (task->tk_status == 0) + sc->sc_cred = get_rpccred(task->tk_rqstp->rq_cred); +} + +static const struct rpc_call_ops nfs4_setclientid_ops = { + .rpc_call_done = nfs4_setclientid_done, +}; + +/** + * nfs4_proc_setclientid - Negotiate client ID + * @clp: state data structure + * @program: RPC program for NFSv4 callback service + * @port: IP port number for NFS4 callback service + * @cred: RPC credential to use for this call + * @res: where to place the result + * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + */ +int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, + unsigned short port, struct rpc_cred *cred, + struct nfs4_setclientid_res *res) +{ + nfs4_verifier sc_verifier; + struct nfs4_setclientid setclientid = { + .sc_verifier = &sc_verifier, + .sc_prog = program, + .sc_cb_ident = clp->cl_cb_ident, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID], + .rpc_argp = &setclientid, + .rpc_resp = res, + .rpc_cred = cred, + }; + struct rpc_task *task; + struct rpc_task_setup task_setup_data = { + .rpc_client = clp->cl_rpcclient, + .rpc_message = &msg, + .callback_ops = &nfs4_setclientid_ops, + .callback_data = &setclientid, + .flags = RPC_TASK_TIMEOUT, + }; + int status; + + /* nfs_client_id4 */ + nfs4_init_boot_verifier(clp, &sc_verifier); + if (test_bit(NFS_CS_MIGRATION, &clp->cl_flags)) + setclientid.sc_name_len = + nfs4_init_uniform_client_string(clp, + setclientid.sc_name, + sizeof(setclientid.sc_name)); + else + setclientid.sc_name_len = + nfs4_init_nonuniform_client_string(clp, + setclientid.sc_name, + sizeof(setclientid.sc_name)); + /* cb_client4 */ + setclientid.sc_netid_len = + nfs4_init_callback_netid(clp, + setclientid.sc_netid, + sizeof(setclientid.sc_netid)); + setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr, + sizeof(setclientid.sc_uaddr), "%s.%u.%u", + clp->cl_ipaddr, port >> 8, port & 255); + + dprintk("NFS call setclientid auth=%s, '%.*s'\n", + clp->cl_rpcclient->cl_auth->au_ops->au_name, + setclientid.sc_name_len, setclientid.sc_name); + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) { + status = PTR_ERR(task); + goto out; + } + status = task->tk_status; + if (setclientid.sc_cred) { + clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred); + put_rpccred(setclientid.sc_cred); + } + rpc_put_task(task); +out: + trace_nfs4_setclientid(clp, status); + dprintk("NFS reply setclientid: %d\n", status); + return status; +} + +/** + * nfs4_proc_setclientid_confirm - Confirm client ID + * @clp: state data structure + * @res: result of a previous SETCLIENTID + * @cred: RPC credential to use for this call + * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + */ +int nfs4_proc_setclientid_confirm(struct nfs_client *clp, + struct nfs4_setclientid_res *arg, + struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID_CONFIRM], + .rpc_argp = arg, + .rpc_cred = cred, + }; + int status; + + dprintk("NFS call setclientid_confirm auth=%s, (client ID %llx)\n", + clp->cl_rpcclient->cl_auth->au_ops->au_name, + clp->cl_clientid); + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_setclientid_confirm(clp, status); + dprintk("NFS reply setclientid_confirm: %d\n", status); + return status; +} + +struct nfs4_delegreturndata { + struct nfs4_delegreturnargs args; + struct nfs4_delegreturnres res; + struct nfs_fh fh; + nfs4_stateid stateid; + unsigned long timestamp; + struct nfs_fattr fattr; + int rpc_status; + struct inode *inode; + bool roc; + u32 roc_barrier; +}; + +static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_delegreturndata *data = calldata; + + if (!nfs4_sequence_done(task, &data->res.seq_res)) + return; + + trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status); + switch (task->tk_status) { + case 0: + renew_lease(data->res.server, data->timestamp); + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + task->tk_status = 0; + if (data->roc) + pnfs_roc_set_barrier(data->inode, data->roc_barrier); + break; + default: + if (nfs4_async_handle_error(task, data->res.server, + NULL, NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return; + } + } + data->rpc_status = task->tk_status; +} + +static void nfs4_delegreturn_release(void *calldata) +{ + struct nfs4_delegreturndata *data = calldata; + struct inode *inode = data->inode; + + if (inode) { + if (data->roc) + pnfs_roc_release(inode); + nfs_iput_and_deactive(inode); + } + kfree(calldata); +} + +static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) +{ + struct nfs4_delegreturndata *d_data; + + d_data = (struct nfs4_delegreturndata *)data; + + if (d_data->roc && + pnfs_roc_drain(d_data->inode, &d_data->roc_barrier, task)) + return; + + nfs4_setup_sequence(d_data->res.server, + &d_data->args.seq_args, + &d_data->res.seq_res, + task); +} + +static const struct rpc_call_ops nfs4_delegreturn_ops = { + .rpc_call_prepare = nfs4_delegreturn_prepare, + .rpc_call_done = nfs4_delegreturn_done, + .rpc_release = nfs4_delegreturn_release, +}; + +static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync) +{ + struct nfs4_delegreturndata *data; + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DELEGRETURN], + .rpc_cred = cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_delegreturn_ops, + .flags = RPC_TASK_ASYNC, + }; + int status = 0; + + data = kzalloc(sizeof(*data), GFP_NOFS); + if (data == NULL) + return -ENOMEM; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + data->args.fhandle = &data->fh; + data->args.stateid = &data->stateid; + data->args.bitmask = server->cache_consistency_bitmask; + nfs_copy_fh(&data->fh, NFS_FH(inode)); + nfs4_stateid_copy(&data->stateid, stateid); + data->res.fattr = &data->fattr; + data->res.server = server; + nfs_fattr_init(data->res.fattr); + data->timestamp = jiffies; + data->rpc_status = 0; + data->inode = nfs_igrab_and_active(inode); + if (data->inode) + data->roc = nfs4_roc(inode); + + task_setup_data.callback_data = data; + msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + if (!issync) + goto out; + status = nfs4_wait_for_completion_rpc_task(task); + if (status != 0) + goto out; + status = data->rpc_status; + if (status == 0) + nfs_post_op_update_inode_force_wcc(inode, &data->fattr); + else + nfs_refresh_inode(inode, &data->fattr); +out: + rpc_put_task(task); + return status; +} + +int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_delegreturn(inode, cred, stateid, issync); + trace_nfs4_delegreturn(inode, err); + switch (err) { + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + case 0: + return 0; + } + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + return err; +} + +#define NFS4_LOCK_MINTIMEOUT (1 * HZ) +#define NFS4_LOCK_MAXTIMEOUT (30 * HZ) + +/* + * sleep, with exponential backoff, and retry the LOCK operation. + */ +static unsigned long +nfs4_set_lock_task_retry(unsigned long timeout) +{ + freezable_schedule_timeout_killable_unsafe(timeout); + timeout <<= 1; + if (timeout > NFS4_LOCK_MAXTIMEOUT) + return NFS4_LOCK_MAXTIMEOUT; + return timeout; +} + +static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock *request) +{ + struct inode *inode = state->inode; + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + struct nfs_lockt_args arg = { + .fh = NFS_FH(inode), + .fl = request, + }; + struct nfs_lockt_res res = { + .denied = request, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOCKT], + .rpc_argp = &arg, + .rpc_resp = &res, + .rpc_cred = state->owner->so_cred, + }; + struct nfs4_lock_state *lsp; + int status; + + arg.lock_owner.clientid = clp->cl_clientid; + status = nfs4_set_lock_state(state, request); + if (status != 0) + goto out; + lsp = request->fl_u.nfs4_fl.owner; + arg.lock_owner.id = lsp->ls_seqid.owner_id; + arg.lock_owner.s_dev = server->s_dev; + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); + switch (status) { + case 0: + request->fl_type = F_UNLCK; + break; + case -NFS4ERR_DENIED: + status = 0; + } + request->fl_ops->fl_release_private(request); + request->fl_ops = NULL; +out: + return status; +} + +static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock *request) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs4_proc_getlk(state, cmd, request); + trace_nfs4_get_lock(request, state, cmd, err); + err = nfs4_handle_exception(NFS_SERVER(state->inode), err, + &exception); + } while (exception.retry); + return err; +} + +static int do_vfs_lock(struct file *file, struct file_lock *fl) +{ + int res = 0; + switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { + case FL_POSIX: + res = posix_lock_file_wait(file, fl); + break; + case FL_FLOCK: + res = flock_lock_file_wait(file, fl); + break; + default: + BUG(); + } + return res; +} + +struct nfs4_unlockdata { + struct nfs_locku_args arg; + struct nfs_locku_res res; + struct nfs4_lock_state *lsp; + struct nfs_open_context *ctx; + struct file_lock fl; + const struct nfs_server *server; + unsigned long timestamp; +}; + +static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, + struct nfs_open_context *ctx, + struct nfs4_lock_state *lsp, + struct nfs_seqid *seqid) +{ + struct nfs4_unlockdata *p; + struct inode *inode = lsp->ls_state->inode; + + p = kzalloc(sizeof(*p), GFP_NOFS); + if (p == NULL) + return NULL; + p->arg.fh = NFS_FH(inode); + p->arg.fl = &p->fl; + p->arg.seqid = seqid; + p->res.seqid = seqid; + p->lsp = lsp; + atomic_inc(&lsp->ls_count); + /* Ensure we don't close file until we're done freeing locks! */ + p->ctx = get_nfs_open_context(ctx); + memcpy(&p->fl, fl, sizeof(p->fl)); + p->server = NFS_SERVER(inode); + return p; +} + +static void nfs4_locku_release_calldata(void *data) +{ + struct nfs4_unlockdata *calldata = data; + nfs_free_seqid(calldata->arg.seqid); + nfs4_put_lock_state(calldata->lsp); + put_nfs_open_context(calldata->ctx); + kfree(calldata); +} + +static void nfs4_locku_done(struct rpc_task *task, void *data) +{ + struct nfs4_unlockdata *calldata = data; + + if (!nfs4_sequence_done(task, &calldata->res.seq_res)) + return; + switch (task->tk_status) { + case 0: + renew_lease(calldata->server, calldata->timestamp); + do_vfs_lock(calldata->fl.fl_file, &calldata->fl); + if (nfs4_update_lock_stateid(calldata->lsp, + &calldata->res.stateid)) + break; + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + if (!nfs4_stateid_match(&calldata->arg.stateid, + &calldata->lsp->ls_stateid)) + rpc_restart_call_prepare(task); + break; + default: + if (nfs4_async_handle_error(task, calldata->server, + NULL, NULL) == -EAGAIN) + rpc_restart_call_prepare(task); + } + nfs_release_seqid(calldata->arg.seqid); +} + +static void nfs4_locku_prepare(struct rpc_task *task, void *data) +{ + struct nfs4_unlockdata *calldata = data; + + if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) + goto out_wait; + nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid); + if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) { + /* Note: exit _without_ running nfs4_locku_done */ + goto out_no_action; + } + calldata->timestamp = jiffies; + if (nfs4_setup_sequence(calldata->server, + &calldata->arg.seq_args, + &calldata->res.seq_res, + task) != 0) + nfs_release_seqid(calldata->arg.seqid); + return; +out_no_action: + task->tk_action = NULL; +out_wait: + nfs4_sequence_done(task, &calldata->res.seq_res); +} + +static const struct rpc_call_ops nfs4_locku_ops = { + .rpc_call_prepare = nfs4_locku_prepare, + .rpc_call_done = nfs4_locku_done, + .rpc_release = nfs4_locku_release_calldata, +}; + +static struct rpc_task *nfs4_do_unlck(struct file_lock *fl, + struct nfs_open_context *ctx, + struct nfs4_lock_state *lsp, + struct nfs_seqid *seqid) +{ + struct nfs4_unlockdata *data; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOCKU], + .rpc_cred = ctx->cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = NFS_CLIENT(lsp->ls_state->inode), + .rpc_message = &msg, + .callback_ops = &nfs4_locku_ops, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC, + }; + + nfs4_state_protect(NFS_SERVER(lsp->ls_state->inode)->nfs_client, + NFS_SP4_MACH_CRED_CLEANUP, &task_setup_data.rpc_client, &msg); + + /* Ensure this is an unlock - when canceling a lock, the + * canceled lock is passed in, and it won't be an unlock. + */ + fl->fl_type = F_UNLCK; + + data = nfs4_alloc_unlockdata(fl, ctx, lsp, seqid); + if (data == NULL) { + nfs_free_seqid(seqid); + return ERR_PTR(-ENOMEM); + } + + nfs4_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1); + msg.rpc_argp = &data->arg; + msg.rpc_resp = &data->res; + task_setup_data.callback_data = data; + return rpc_run_task(&task_setup_data); +} + +static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *request) +{ + struct inode *inode = state->inode; + struct nfs4_state_owner *sp = state->owner; + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_seqid *seqid; + struct nfs4_lock_state *lsp; + struct rpc_task *task; + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + int status = 0; + unsigned char fl_flags = request->fl_flags; + + status = nfs4_set_lock_state(state, request); + /* Unlock _before_ we do the RPC call */ + request->fl_flags |= FL_EXISTS; + /* Exclude nfs_delegation_claim_locks() */ + mutex_lock(&sp->so_delegreturn_mutex); + /* Exclude nfs4_reclaim_open_stateid() - note nesting! */ + down_read(&nfsi->rwsem); + if (do_vfs_lock(request->fl_file, request) == -ENOENT) { + up_read(&nfsi->rwsem); + mutex_unlock(&sp->so_delegreturn_mutex); + goto out; + } + up_read(&nfsi->rwsem); + mutex_unlock(&sp->so_delegreturn_mutex); + if (status != 0) + goto out; + /* Is this a delegated lock? */ + lsp = request->fl_u.nfs4_fl.owner; + if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) == 0) + goto out; + alloc_seqid = NFS_SERVER(inode)->nfs_client->cl_mvops->alloc_seqid; + seqid = alloc_seqid(&lsp->ls_seqid, GFP_KERNEL); + status = -ENOMEM; + if (IS_ERR(seqid)) + goto out; + task = nfs4_do_unlck(request, nfs_file_open_context(request->fl_file), lsp, seqid); + status = PTR_ERR(task); + if (IS_ERR(task)) + goto out; + status = nfs4_wait_for_completion_rpc_task(task); + rpc_put_task(task); +out: + request->fl_flags = fl_flags; + trace_nfs4_unlock(request, state, F_SETLK, status); + return status; +} + +struct nfs4_lockdata { + struct nfs_lock_args arg; + struct nfs_lock_res res; + struct nfs4_lock_state *lsp; + struct nfs_open_context *ctx; + struct file_lock fl; + unsigned long timestamp; + int rpc_status; + int cancelled; + struct nfs_server *server; +}; + +static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, + struct nfs_open_context *ctx, struct nfs4_lock_state *lsp, + gfp_t gfp_mask) +{ + struct nfs4_lockdata *p; + struct inode *inode = lsp->ls_state->inode; + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + + p = kzalloc(sizeof(*p), gfp_mask); + if (p == NULL) + return NULL; + + p->arg.fh = NFS_FH(inode); + p->arg.fl = &p->fl; + p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid, gfp_mask); + if (IS_ERR(p->arg.open_seqid)) + goto out_free; + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; + p->arg.lock_seqid = alloc_seqid(&lsp->ls_seqid, gfp_mask); + if (IS_ERR(p->arg.lock_seqid)) + goto out_free_seqid; + p->arg.lock_owner.clientid = server->nfs_client->cl_clientid; + p->arg.lock_owner.id = lsp->ls_seqid.owner_id; + p->arg.lock_owner.s_dev = server->s_dev; + p->res.lock_seqid = p->arg.lock_seqid; + p->lsp = lsp; + p->server = server; + atomic_inc(&lsp->ls_count); + p->ctx = get_nfs_open_context(ctx); + get_file(fl->fl_file); + memcpy(&p->fl, fl, sizeof(p->fl)); + return p; +out_free_seqid: + nfs_free_seqid(p->arg.open_seqid); +out_free: + kfree(p); + return NULL; +} + +static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_lockdata *data = calldata; + struct nfs4_state *state = data->lsp->ls_state; + + dprintk("%s: begin!\n", __func__); + if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) + goto out_wait; + /* Do we need to do an open_to_lock_owner? */ + if (!test_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags)) { + if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) { + goto out_release_lock_seqid; + } + nfs4_stateid_copy(&data->arg.open_stateid, + &state->open_stateid); + data->arg.new_lock_owner = 1; + data->res.open_seqid = data->arg.open_seqid; + } else { + data->arg.new_lock_owner = 0; + nfs4_stateid_copy(&data->arg.lock_stateid, + &data->lsp->ls_stateid); + } + if (!nfs4_valid_open_stateid(state)) { + data->rpc_status = -EBADF; + task->tk_action = NULL; + goto out_release_open_seqid; + } + data->timestamp = jiffies; + if (nfs4_setup_sequence(data->server, + &data->arg.seq_args, + &data->res.seq_res, + task) == 0) + return; +out_release_open_seqid: + nfs_release_seqid(data->arg.open_seqid); +out_release_lock_seqid: + nfs_release_seqid(data->arg.lock_seqid); +out_wait: + nfs4_sequence_done(task, &data->res.seq_res); + dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status); +} + +static void nfs4_lock_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_lockdata *data = calldata; + struct nfs4_lock_state *lsp = data->lsp; + + dprintk("%s: begin!\n", __func__); + + if (!nfs4_sequence_done(task, &data->res.seq_res)) + return; + + data->rpc_status = task->tk_status; + switch (task->tk_status) { + case 0: + renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)), + data->timestamp); + if (data->arg.new_lock) { + data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); + if (do_vfs_lock(data->fl.fl_file, &data->fl) < 0) { + rpc_restart_call_prepare(task); + break; + } + } + if (data->arg.new_lock_owner != 0) { + nfs_confirm_seqid(&lsp->ls_seqid, 0); + nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); + set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); + } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) + rpc_restart_call_prepare(task); + break; + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + if (data->arg.new_lock_owner != 0) { + if (!nfs4_stateid_match(&data->arg.open_stateid, + &lsp->ls_state->open_stateid)) + rpc_restart_call_prepare(task); + } else if (!nfs4_stateid_match(&data->arg.lock_stateid, + &lsp->ls_stateid)) + rpc_restart_call_prepare(task); + } + dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); +} + +static void nfs4_lock_release(void *calldata) +{ + struct nfs4_lockdata *data = calldata; + + dprintk("%s: begin!\n", __func__); + nfs_free_seqid(data->arg.open_seqid); + if (data->cancelled != 0) { + struct rpc_task *task; + task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, + data->arg.lock_seqid); + if (!IS_ERR(task)) + rpc_put_task_async(task); + dprintk("%s: cancelling lock!\n", __func__); + } else + nfs_free_seqid(data->arg.lock_seqid); + nfs4_put_lock_state(data->lsp); + put_nfs_open_context(data->ctx); + fput(data->fl.fl_file); + kfree(data); + dprintk("%s: done!\n", __func__); +} + +static const struct rpc_call_ops nfs4_lock_ops = { + .rpc_call_prepare = nfs4_lock_prepare, + .rpc_call_done = nfs4_lock_done, + .rpc_release = nfs4_lock_release, +}; + +static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error) +{ + switch (error) { + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED; + if (new_lock_owner != 0 || + test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) + nfs4_schedule_stateid_recovery(server, lsp->ls_state); + break; + case -NFS4ERR_STALE_STATEID: + lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED; + case -NFS4ERR_EXPIRED: + nfs4_schedule_lease_recovery(server->nfs_client); + }; +} + +static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int recovery_type) +{ + struct nfs4_lockdata *data; + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOCK], + .rpc_cred = state->owner->so_cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = NFS_CLIENT(state->inode), + .rpc_message = &msg, + .callback_ops = &nfs4_lock_ops, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC, + }; + int ret; + + dprintk("%s: begin!\n", __func__); + data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file), + fl->fl_u.nfs4_fl.owner, + recovery_type == NFS_LOCK_NEW ? GFP_KERNEL : GFP_NOFS); + if (data == NULL) + return -ENOMEM; + if (IS_SETLKW(cmd)) + data->arg.block = 1; + nfs4_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1); + msg.rpc_argp = &data->arg; + msg.rpc_resp = &data->res; + task_setup_data.callback_data = data; + if (recovery_type > NFS_LOCK_NEW) { + if (recovery_type == NFS_LOCK_RECLAIM) + data->arg.reclaim = NFS_LOCK_RECLAIM; + nfs4_set_sequence_privileged(&data->arg.seq_args); + } else + data->arg.new_lock = 1; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + ret = nfs4_wait_for_completion_rpc_task(task); + if (ret == 0) { + ret = data->rpc_status; + if (ret) + nfs4_handle_setlk_error(data->server, data->lsp, + data->arg.new_lock_owner, ret); + } else + data->cancelled = 1; + rpc_put_task(task); + dprintk("%s: done, ret = %d!\n", __func__, ret); + return ret; +} + +static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs4_exception exception = { + .inode = state->inode, + }; + int err; + + do { + /* Cache the lock if possible... */ + if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) + return 0; + err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM); + trace_nfs4_lock_reclaim(request, state, F_SETLK, err); + if (err != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + return err; +} + +static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs4_exception exception = { + .inode = state->inode, + }; + int err; + + err = nfs4_set_lock_state(state, request); + if (err != 0) + return err; + if (!recover_lost_locks) { + set_bit(NFS_LOCK_LOST, &request->fl_u.nfs4_fl.owner->ls_flags); + return 0; + } + do { + if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) + return 0; + err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED); + trace_nfs4_lock_expired(request, state, F_SETLK, err); + switch (err) { + default: + goto out; + case -NFS4ERR_GRACE: + case -NFS4ERR_DELAY: + nfs4_handle_exception(server, err, &exception); + err = 0; + } + } while (exception.retry); +out: + return err; +} + +#if defined(CONFIG_NFS_V4_1) +/** + * nfs41_check_expired_locks - possibly free a lock stateid + * + * @state: NFSv4 state for an inode + * + * Returns NFS_OK if recovery for this stateid is now finished. + * Otherwise a negative NFS4ERR value is returned. + */ +static int nfs41_check_expired_locks(struct nfs4_state *state) +{ + int status, ret = -NFS4ERR_BAD_STATEID; + struct nfs4_lock_state *lsp; + struct nfs_server *server = NFS_SERVER(state->inode); + + list_for_each_entry(lsp, &state->lock_states, ls_locks) { + if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) { + struct rpc_cred *cred = lsp->ls_state->owner->so_cred; + + status = nfs41_test_stateid(server, + &lsp->ls_stateid, + cred); + trace_nfs4_test_lock_stateid(state, lsp, status); + if (status != NFS_OK) { + /* Free the stateid unless the server + * informs us the stateid is unrecognized. */ + if (status != -NFS4ERR_BAD_STATEID) + nfs41_free_stateid(server, + &lsp->ls_stateid, + cred); + clear_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); + ret = status; + } + } + }; + + return ret; +} + +static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request) +{ + int status = NFS_OK; + + if (test_bit(LK_STATE_IN_USE, &state->flags)) + status = nfs41_check_expired_locks(state); + if (status != NFS_OK) + status = nfs4_lock_expired(state, request); + return status; +} +#endif + +static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) +{ + struct nfs_inode *nfsi = NFS_I(state->inode); + unsigned char fl_flags = request->fl_flags; + int status = -ENOLCK; + + if ((fl_flags & FL_POSIX) && + !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags)) + goto out; + /* Is this a delegated open? */ + status = nfs4_set_lock_state(state, request); + if (status != 0) + goto out; + request->fl_flags |= FL_ACCESS; + status = do_vfs_lock(request->fl_file, request); + if (status < 0) + goto out; + down_read(&nfsi->rwsem); + if (test_bit(NFS_DELEGATED_STATE, &state->flags)) { + /* Yes: cache locks! */ + /* ...but avoid races with delegation recall... */ + request->fl_flags = fl_flags & ~FL_SLEEP; + status = do_vfs_lock(request->fl_file, request); + up_read(&nfsi->rwsem); + goto out; + } + up_read(&nfsi->rwsem); + status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW); +out: + request->fl_flags = fl_flags; + return status; +} + +static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) +{ + struct nfs4_exception exception = { + .state = state, + .inode = state->inode, + }; + int err; + + do { + err = _nfs4_proc_setlk(state, cmd, request); + trace_nfs4_set_lock(request, state, cmd, err); + if (err == -NFS4ERR_DENIED) + err = -EAGAIN; + err = nfs4_handle_exception(NFS_SERVER(state->inode), + err, &exception); + } while (exception.retry); + return err; +} + +static int +nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request) +{ + struct nfs_open_context *ctx; + struct nfs4_state *state; + unsigned long timeout = NFS4_LOCK_MINTIMEOUT; + int status; + + /* verify open state */ + ctx = nfs_file_open_context(filp); + state = ctx->state; + + if (request->fl_start < 0 || request->fl_end < 0) + return -EINVAL; + + if (IS_GETLK(cmd)) { + if (state != NULL) + return nfs4_proc_getlk(state, F_GETLK, request); + return 0; + } + + if (!(IS_SETLK(cmd) || IS_SETLKW(cmd))) + return -EINVAL; + + if (request->fl_type == F_UNLCK) { + if (state != NULL) + return nfs4_proc_unlck(state, cmd, request); + return 0; + } + + if (state == NULL) + return -ENOLCK; + /* + * Don't rely on the VFS having checked the file open mode, + * since it won't do this for flock() locks. + */ + switch (request->fl_type) { + case F_RDLCK: + if (!(filp->f_mode & FMODE_READ)) + return -EBADF; + break; + case F_WRLCK: + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + } + + do { + status = nfs4_proc_setlk(state, cmd, request); + if ((status != -EAGAIN) || IS_SETLK(cmd)) + break; + timeout = nfs4_set_lock_task_retry(timeout); + status = -ERESTARTSYS; + if (signalled()) + break; + } while(status < 0); + return status; +} + +int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + int err; + + err = nfs4_set_lock_state(state, fl); + if (err != 0) + return err; + err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); + return nfs4_handle_delegation_recall_error(server, state, stateid, err); +} + +struct nfs_release_lockowner_data { + struct nfs4_lock_state *lsp; + struct nfs_server *server; + struct nfs_release_lockowner_args args; + struct nfs_release_lockowner_res res; + unsigned long timestamp; +}; + +static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_release_lockowner_data *data = calldata; + struct nfs_server *server = data->server; + nfs40_setup_sequence(server->nfs_client->cl_slot_tbl, + &data->args.seq_args, &data->res.seq_res, task); + data->args.lock_owner.clientid = server->nfs_client->cl_clientid; + data->timestamp = jiffies; +} + +static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) +{ + struct nfs_release_lockowner_data *data = calldata; + struct nfs_server *server = data->server; + + nfs40_sequence_done(task, &data->res.seq_res); + + switch (task->tk_status) { + case 0: + renew_lease(server, data->timestamp); + break; + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_EXPIRED: + nfs4_schedule_lease_recovery(server->nfs_client); + break; + case -NFS4ERR_LEASE_MOVED: + case -NFS4ERR_DELAY: + if (nfs4_async_handle_error(task, server, + NULL, NULL) == -EAGAIN) + rpc_restart_call_prepare(task); + } +} + +static void nfs4_release_lockowner_release(void *calldata) +{ + struct nfs_release_lockowner_data *data = calldata; + nfs4_free_lock_state(data->server, data->lsp); + kfree(calldata); +} + +static const struct rpc_call_ops nfs4_release_lockowner_ops = { + .rpc_call_prepare = nfs4_release_lockowner_prepare, + .rpc_call_done = nfs4_release_lockowner_done, + .rpc_release = nfs4_release_lockowner_release, +}; + +static void +nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp) +{ + struct nfs_release_lockowner_data *data; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RELEASE_LOCKOWNER], + }; + + if (server->nfs_client->cl_mvops->minor_version != 0) + return; + + data = kmalloc(sizeof(*data), GFP_NOFS); + if (!data) + return; + data->lsp = lsp; + data->server = server; + data->args.lock_owner.clientid = server->nfs_client->cl_clientid; + data->args.lock_owner.id = lsp->ls_seqid.owner_id; + data->args.lock_owner.s_dev = server->s_dev; + + msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); + rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data); +} + +#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl" + +static int nfs4_xattr_set_nfs4_acl(struct dentry *dentry, const char *key, + const void *buf, size_t buflen, + int flags, int type) +{ + if (strcmp(key, "") != 0) + return -EINVAL; + + return nfs4_proc_set_acl(d_inode(dentry), buf, buflen); +} + +static int nfs4_xattr_get_nfs4_acl(struct dentry *dentry, const char *key, + void *buf, size_t buflen, int type) +{ + if (strcmp(key, "") != 0) + return -EINVAL; + + return nfs4_proc_get_acl(d_inode(dentry), buf, buflen); +} + +static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list, + size_t list_len, const char *name, + size_t name_len, int type) +{ + size_t len = sizeof(XATTR_NAME_NFSV4_ACL); + + if (!nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)))) + return 0; + + if (list && len <= list_len) + memcpy(list, XATTR_NAME_NFSV4_ACL, len); + return len; +} + +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +static inline int nfs4_server_supports_labels(struct nfs_server *server) +{ + return server->caps & NFS_CAP_SECURITY_LABEL; +} + +static int nfs4_xattr_set_nfs4_label(struct dentry *dentry, const char *key, + const void *buf, size_t buflen, + int flags, int type) +{ + if (security_ismaclabel(key)) + return nfs4_set_security_label(dentry, buf, buflen); + + return -EOPNOTSUPP; +} + +static int nfs4_xattr_get_nfs4_label(struct dentry *dentry, const char *key, + void *buf, size_t buflen, int type) +{ + if (security_ismaclabel(key)) + return nfs4_get_security_label(d_inode(dentry), buf, buflen); + return -EOPNOTSUPP; +} + +static size_t nfs4_xattr_list_nfs4_label(struct dentry *dentry, char *list, + size_t list_len, const char *name, + size_t name_len, int type) +{ + size_t len = 0; + + if (nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) { + len = security_inode_listsecurity(d_inode(dentry), NULL, 0); + if (list && len <= list_len) + security_inode_listsecurity(d_inode(dentry), list, len); + } + return len; +} + +static const struct xattr_handler nfs4_xattr_nfs4_label_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = nfs4_xattr_list_nfs4_label, + .get = nfs4_xattr_get_nfs4_label, + .set = nfs4_xattr_set_nfs4_label, +}; +#endif + + +/* + * nfs_fhget will use either the mounted_on_fileid or the fileid + */ +static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr) +{ + if (!(((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) || + (fattr->valid & NFS_ATTR_FATTR_FILEID)) && + (fattr->valid & NFS_ATTR_FATTR_FSID) && + (fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS))) + return; + + fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | + NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_V4_REFERRAL; + fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO; + fattr->nlink = 2; +} + +static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, + struct nfs4_fs_locations *fs_locations, + struct page *page) +{ + struct nfs_server *server = NFS_SERVER(dir); + u32 bitmask[3] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .dir_fh = NFS_FH(dir), + .name = name, + .page = page, + .bitmask = bitmask, + }; + struct nfs4_fs_locations_res res = { + .fs_locations = fs_locations, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + dprintk("%s: start\n", __func__); + + /* Ask for the fileid of the absent filesystem if mounted_on_fileid + * is not supported */ + if (NFS_SERVER(dir)->attr_bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) + bitmask[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID; + else + bitmask[0] |= FATTR4_WORD0_FILEID; + + nfs_fattr_init(&fs_locations->fattr); + fs_locations->server = server; + fs_locations->nlocations = 0; + status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0); + dprintk("%s: returned status = %d\n", __func__, status); + return status; +} + +int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, + struct nfs4_fs_locations *fs_locations, + struct page *page) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_fs_locations(client, dir, name, + fs_locations, page); + trace_nfs4_get_fs_locations(dir, name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, + &exception); + } while (exception.retry); + return err; +} + +/* + * This operation also signals the server that this client is + * performing migration recovery. The server can stop returning + * NFS4ERR_LEASE_MOVED to this client. A RENEW operation is + * appended to this compound to identify the client ID which is + * performing recovery. + */ +static int _nfs40_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .clientid = server->nfs_client->cl_clientid, + .fh = NFS_FH(inode), + .page = page, + .bitmask = bitmask, + .migration = 1, /* skip LOOKUP */ + .renew = 1, /* append RENEW */ + }; + struct nfs4_fs_locations_res res = { + .fs_locations = locations, + .migration = 1, + .renew = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + nfs_fattr_init(&locations->fattr); + locations->server = server; + locations->nlocations = 0; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + if (status) + return status; + + renew_lease(server, now); + return 0; +} + +#ifdef CONFIG_NFS_V4_1 + +/* + * This operation also signals the server that this client is + * performing migration recovery. The server can stop asserting + * SEQ4_STATUS_LEASE_MOVED for this client. The client ID + * performing this operation is identified in the SEQUENCE + * operation in this compound. + * + * When the client supports GETATTR(fs_locations_info), it can + * be plumbed in here. + */ +static int _nfs41_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .fh = NFS_FH(inode), + .page = page, + .bitmask = bitmask, + .migration = 1, /* skip LOOKUP */ + }; + struct nfs4_fs_locations_res res = { + .fs_locations = locations, + .migration = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + nfs_fattr_init(&locations->fattr); + locations->server = server; + locations->nlocations = 0; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + if (status == NFS4_OK && + res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) + status = -NFS4ERR_LEASE_MOVED; + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_proc_get_locations - discover locations for a migrated FSID + * @inode: inode on FSID that is migrating + * @locations: result of query + * @page: buffer + * @cred: credential to use for this operation + * + * Returns NFS4_OK on success, a negative NFS4ERR status code if the + * operation failed, or a negative errno if a local error occurred. + * + * On success, "locations" is filled in, but if the server has + * no locations information, NFS_ATTR_FATTR_V4_LOCATIONS is not + * asserted. + * + * -NFS4ERR_LEASE_MOVED is returned if the server still has leases + * from this client that require migration recovery. + */ +int nfs4_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + const struct nfs4_mig_recovery_ops *ops = + clp->cl_mvops->mig_recovery_ops; + struct nfs4_exception exception = { }; + int status; + + dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + nfs_display_fhandle(NFS_FH(inode), __func__); + + do { + status = ops->get_locations(inode, locations, page, cred); + if (status != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, status, &exception); + } while (exception.retry); + return status; +} + +/* + * This operation also signals the server that this client is + * performing "lease moved" recovery. The server can stop + * returning NFS4ERR_LEASE_MOVED to this client. A RENEW operation + * is appended to this compound to identify the client ID which is + * performing recovery. + */ +static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + struct rpc_clnt *clnt = server->client; + struct nfs4_fsid_present_arg args = { + .fh = NFS_FH(inode), + .clientid = clp->cl_clientid, + .renew = 1, /* append RENEW */ + }; + struct nfs4_fsid_present_res res = { + .renew = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + res.fh = nfs_alloc_fhandle(); + if (res.fh == NULL) + return -ENOMEM; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + nfs_free_fhandle(res.fh); + if (status) + return status; + + do_renew_lease(clp, now); + return 0; +} + +#ifdef CONFIG_NFS_V4_1 + +/* + * This operation also signals the server that this client is + * performing "lease moved" recovery. The server can stop asserting + * SEQ4_STATUS_LEASE_MOVED for this client. The client ID performing + * this operation is identified in the SEQUENCE operation in this + * compound. + */ +static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + struct nfs4_fsid_present_arg args = { + .fh = NFS_FH(inode), + }; + struct nfs4_fsid_present_res res = { + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + res.fh = nfs_alloc_fhandle(); + if (res.fh == NULL) + return -ENOMEM; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + nfs_free_fhandle(res.fh); + if (status == NFS4_OK && + res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) + status = -NFS4ERR_LEASE_MOVED; + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_proc_fsid_present - Is this FSID present or absent on server? + * @inode: inode on FSID to check + * @cred: credential to use for this operation + * + * Server indicates whether the FSID is present, moved, or not + * recognized. This operation is necessary to clear a LEASE_MOVED + * condition for this client ID. + * + * Returns NFS4_OK if the FSID is present on this server, + * -NFS4ERR_MOVED if the FSID is no longer present, a negative + * NFS4ERR code if some error occurred on the server, or a + * negative errno if a local failure occurred. + */ +int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + const struct nfs4_mig_recovery_ops *ops = + clp->cl_mvops->mig_recovery_ops; + struct nfs4_exception exception = { }; + int status; + + dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + nfs_display_fhandle(NFS_FH(inode), __func__); + + do { + status = ops->fsid_present(inode, cred); + if (status != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, status, &exception); + } while (exception.retry); + return status; +} + +/** + * If 'use_integrity' is true and the state managment nfs_client + * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient + * and the machine credential as per RFC3530bis and RFC5661 Security + * Considerations sections. Otherwise, just use the user cred with the + * filesystem's rpc_client. + */ +static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors, bool use_integrity) +{ + int status; + struct nfs4_secinfo_arg args = { + .dir_fh = NFS_FH(dir), + .name = name, + }; + struct nfs4_secinfo_res res = { + .flavors = flavors, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SECINFO], + .rpc_argp = &args, + .rpc_resp = &res, + }; + struct rpc_clnt *clnt = NFS_SERVER(dir)->client; + struct rpc_cred *cred = NULL; + + if (use_integrity) { + clnt = NFS_SERVER(dir)->nfs_client->cl_rpcclient; + cred = nfs4_get_clid_cred(NFS_SERVER(dir)->nfs_client); + msg.rpc_cred = cred; + } + + dprintk("NFS call secinfo %s\n", name->name); + + nfs4_state_protect(NFS_SERVER(dir)->nfs_client, + NFS_SP4_MACH_CRED_SECINFO, &clnt, &msg); + + status = nfs4_call_sync(clnt, NFS_SERVER(dir), &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("NFS reply secinfo: %d\n", status); + + if (cred) + put_rpccred(cred); + + return status; +} + +int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, + struct nfs4_secinfo_flavors *flavors) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = -NFS4ERR_WRONGSEC; + + /* try to use integrity protection with machine cred */ + if (_nfs4_is_integrity_protected(NFS_SERVER(dir)->nfs_client)) + err = _nfs4_proc_secinfo(dir, name, flavors, true); + + /* + * if unable to use integrity protection, or SECINFO with + * integrity protection returns NFS4ERR_WRONGSEC (which is + * disallowed by spec, but exists in deployed servers) use + * the current filesystem's rpc_client and the user cred. + */ + if (err == -NFS4ERR_WRONGSEC) + err = _nfs4_proc_secinfo(dir, name, flavors, false); + + trace_nfs4_secinfo(dir, name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, + &exception); + } while (exception.retry); + return err; +} + +#ifdef CONFIG_NFS_V4_1 +/* + * Check the exchange flags returned by the server for invalid flags, having + * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or + * DS flags set. + */ +static int nfs4_check_cl_exchange_flags(u32 flags) +{ + if (flags & ~EXCHGID4_FLAG_MASK_R) + goto out_inval; + if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) && + (flags & EXCHGID4_FLAG_USE_NON_PNFS)) + goto out_inval; + if (!(flags & (EXCHGID4_FLAG_MASK_PNFS))) + goto out_inval; + return NFS_OK; +out_inval: + return -NFS4ERR_INVAL; +} + +static bool +nfs41_same_server_scope(struct nfs41_server_scope *a, + struct nfs41_server_scope *b) +{ + if (a->server_scope_sz == b->server_scope_sz && + memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0) + return true; + + return false; +} + +/* + * nfs4_proc_bind_conn_to_session() + * + * The 4.1 client currently uses the same TCP connection for the + * fore and backchannel. + */ +int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred) +{ + int status; + struct nfs41_bind_conn_to_session_args args = { + .client = clp, + .dir = NFS4_CDFC4_FORE_OR_BOTH, + }; + struct nfs41_bind_conn_to_session_res res; + struct rpc_message msg = { + .rpc_proc = + &nfs4_procedures[NFSPROC4_CLNT_BIND_CONN_TO_SESSION], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + + dprintk("--> %s\n", __func__); + + nfs4_copy_sessionid(&args.sessionid, &clp->cl_session->sess_id); + if (!(clp->cl_session->flags & SESSION4_BACK_CHAN)) + args.dir = NFS4_CDFC4_FORE; + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_bind_conn_to_session(clp, status); + if (status == 0) { + if (memcmp(res.sessionid.data, + clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { + dprintk("NFS: %s: Session ID mismatch\n", __func__); + status = -EIO; + goto out; + } + if ((res.dir & args.dir) != res.dir || res.dir == 0) { + dprintk("NFS: %s: Unexpected direction from server\n", + __func__); + status = -EIO; + goto out; + } + if (res.use_conn_in_rdma_mode != args.use_conn_in_rdma_mode) { + dprintk("NFS: %s: Server returned RDMA mode = true\n", + __func__); + status = -EIO; + goto out; + } + } +out: + dprintk("<-- %s status= %d\n", __func__, status); + return status; +} + +/* + * Minimum set of SP4_MACH_CRED operations from RFC 5661 in the enforce map + * and operations we'd like to see to enable certain features in the allow map + */ +static const struct nfs41_state_protection nfs4_sp4_mach_cred_request = { + .how = SP4_MACH_CRED, + .enforce.u.words = { + [1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) | + 1 << (OP_EXCHANGE_ID - 32) | + 1 << (OP_CREATE_SESSION - 32) | + 1 << (OP_DESTROY_SESSION - 32) | + 1 << (OP_DESTROY_CLIENTID - 32) + }, + .allow.u.words = { + [0] = 1 << (OP_CLOSE) | + 1 << (OP_LOCKU) | + 1 << (OP_COMMIT), + [1] = 1 << (OP_SECINFO - 32) | + 1 << (OP_SECINFO_NO_NAME - 32) | + 1 << (OP_TEST_STATEID - 32) | + 1 << (OP_FREE_STATEID - 32) | + 1 << (OP_WRITE - 32) + } +}; + +/* + * Select the state protection mode for client `clp' given the server results + * from exchange_id in `sp'. + * + * Returns 0 on success, negative errno otherwise. + */ +static int nfs4_sp4_select_mode(struct nfs_client *clp, + struct nfs41_state_protection *sp) +{ + static const u32 supported_enforce[NFS4_OP_MAP_NUM_WORDS] = { + [1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) | + 1 << (OP_EXCHANGE_ID - 32) | + 1 << (OP_CREATE_SESSION - 32) | + 1 << (OP_DESTROY_SESSION - 32) | + 1 << (OP_DESTROY_CLIENTID - 32) + }; + unsigned int i; + + if (sp->how == SP4_MACH_CRED) { + /* Print state protect result */ + dfprintk(MOUNT, "Server SP4_MACH_CRED support:\n"); + for (i = 0; i <= LAST_NFS4_OP; i++) { + if (test_bit(i, sp->enforce.u.longs)) + dfprintk(MOUNT, " enforce op %d\n", i); + if (test_bit(i, sp->allow.u.longs)) + dfprintk(MOUNT, " allow op %d\n", i); + } + + /* make sure nothing is on enforce list that isn't supported */ + for (i = 0; i < NFS4_OP_MAP_NUM_WORDS; i++) { + if (sp->enforce.u.words[i] & ~supported_enforce[i]) { + dfprintk(MOUNT, "sp4_mach_cred: disabled\n"); + return -EINVAL; + } + } + + /* + * Minimal mode - state operations are allowed to use machine + * credential. Note this already happens by default, so the + * client doesn't have to do anything more than the negotiation. + * + * NOTE: we don't care if EXCHANGE_ID is in the list - + * we're already using the machine cred for exchange_id + * and will never use a different cred. + */ + if (test_bit(OP_BIND_CONN_TO_SESSION, sp->enforce.u.longs) && + test_bit(OP_CREATE_SESSION, sp->enforce.u.longs) && + test_bit(OP_DESTROY_SESSION, sp->enforce.u.longs) && + test_bit(OP_DESTROY_CLIENTID, sp->enforce.u.longs)) { + dfprintk(MOUNT, "sp4_mach_cred:\n"); + dfprintk(MOUNT, " minimal mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_MINIMAL, &clp->cl_sp4_flags); + } else { + dfprintk(MOUNT, "sp4_mach_cred: disabled\n"); + return -EINVAL; + } + + if (test_bit(OP_CLOSE, sp->allow.u.longs) && + test_bit(OP_LOCKU, sp->allow.u.longs)) { + dfprintk(MOUNT, " cleanup mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags); + } + + if (test_bit(OP_SECINFO, sp->allow.u.longs) && + test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) { + dfprintk(MOUNT, " secinfo mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_SECINFO, &clp->cl_sp4_flags); + } + + if (test_bit(OP_TEST_STATEID, sp->allow.u.longs) && + test_bit(OP_FREE_STATEID, sp->allow.u.longs)) { + dfprintk(MOUNT, " stateid mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_STATEID, &clp->cl_sp4_flags); + } + + if (test_bit(OP_WRITE, sp->allow.u.longs)) { + dfprintk(MOUNT, " write mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_WRITE, &clp->cl_sp4_flags); + } + + if (test_bit(OP_COMMIT, sp->allow.u.longs)) { + dfprintk(MOUNT, " commit mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags); + } + } + + return 0; +} + +/* + * _nfs4_proc_exchange_id() + * + * Wrapper for EXCHANGE_ID operation. + */ +static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, + u32 sp4_how) +{ + nfs4_verifier verifier; + struct nfs41_exchange_id_args args = { + .verifier = &verifier, + .client = clp, +#ifdef CONFIG_NFS_V4_1_MIGRATION + .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | + EXCHGID4_FLAG_BIND_PRINC_STATEID | + EXCHGID4_FLAG_SUPP_MOVED_MIGR, +#else + .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | + EXCHGID4_FLAG_BIND_PRINC_STATEID, +#endif + }; + struct nfs41_exchange_id_res res = { + 0 + }; + int status; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_EXCHANGE_ID], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + + nfs4_init_boot_verifier(clp, &verifier); + args.id_len = nfs4_init_uniform_client_string(clp, args.id, + sizeof(args.id)); + dprintk("NFS call exchange_id auth=%s, '%.*s'\n", + clp->cl_rpcclient->cl_auth->au_ops->au_name, + args.id_len, args.id); + + res.server_owner = kzalloc(sizeof(struct nfs41_server_owner), + GFP_NOFS); + if (unlikely(res.server_owner == NULL)) { + status = -ENOMEM; + goto out; + } + + res.server_scope = kzalloc(sizeof(struct nfs41_server_scope), + GFP_NOFS); + if (unlikely(res.server_scope == NULL)) { + status = -ENOMEM; + goto out_server_owner; + } + + res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_NOFS); + if (unlikely(res.impl_id == NULL)) { + status = -ENOMEM; + goto out_server_scope; + } + + switch (sp4_how) { + case SP4_NONE: + args.state_protect.how = SP4_NONE; + break; + + case SP4_MACH_CRED: + args.state_protect = nfs4_sp4_mach_cred_request; + break; + + default: + /* unsupported! */ + WARN_ON_ONCE(1); + status = -EINVAL; + goto out_server_scope; + } + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_exchange_id(clp, status); + if (status == 0) + status = nfs4_check_cl_exchange_flags(res.flags); + + if (status == 0) + status = nfs4_sp4_select_mode(clp, &res.state_protect); + + if (status == 0) { + clp->cl_clientid = res.clientid; + clp->cl_exchange_flags = res.flags; + /* Client ID is not confirmed */ + if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) { + clear_bit(NFS4_SESSION_ESTABLISHED, + &clp->cl_session->session_state); + clp->cl_seqid = res.seqid; + } + + kfree(clp->cl_serverowner); + clp->cl_serverowner = res.server_owner; + res.server_owner = NULL; + + /* use the most recent implementation id */ + kfree(clp->cl_implid); + clp->cl_implid = res.impl_id; + + if (clp->cl_serverscope != NULL && + !nfs41_same_server_scope(clp->cl_serverscope, + res.server_scope)) { + dprintk("%s: server_scope mismatch detected\n", + __func__); + set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state); + kfree(clp->cl_serverscope); + clp->cl_serverscope = NULL; + } + + if (clp->cl_serverscope == NULL) { + clp->cl_serverscope = res.server_scope; + goto out; + } + } else + kfree(res.impl_id); + +out_server_owner: + kfree(res.server_owner); +out_server_scope: + kfree(res.server_scope); +out: + if (clp->cl_implid != NULL) + dprintk("NFS reply exchange_id: Server Implementation ID: " + "domain: %s, name: %s, date: %llu,%u\n", + clp->cl_implid->domain, clp->cl_implid->name, + clp->cl_implid->date.seconds, + clp->cl_implid->date.nseconds); + dprintk("NFS reply exchange_id: %d\n", status); + return status; +} + +/* + * nfs4_proc_exchange_id() + * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + * + * Since the clientid has expired, all compounds using sessions + * associated with the stale clientid will be returning + * NFS4ERR_BADSESSION in the sequence operation, and will therefore + * be in some phase of session reset. + * + * Will attempt to negotiate SP4_MACH_CRED if krb5i / krb5p auth is used. + */ +int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) +{ + rpc_authflavor_t authflavor = clp->cl_rpcclient->cl_auth->au_flavor; + int status; + + /* try SP4_MACH_CRED if krb5i/p */ + if (authflavor == RPC_AUTH_GSS_KRB5I || + authflavor == RPC_AUTH_GSS_KRB5P) { + status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED); + if (!status) + return 0; + } + + /* try SP4_NONE */ + return _nfs4_proc_exchange_id(clp, cred, SP4_NONE); +} + +static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID], + .rpc_argp = clp, + .rpc_cred = cred, + }; + int status; + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_destroy_clientid(clp, status); + if (status) + dprintk("NFS: Got error %d from the server %s on " + "DESTROY_CLIENTID.", status, clp->cl_hostname); + return status; +} + +static int nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + unsigned int loop; + int ret; + + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { + ret = _nfs4_proc_destroy_clientid(clp, cred); + switch (ret) { + case -NFS4ERR_DELAY: + case -NFS4ERR_CLIENTID_BUSY: + ssleep(1); + break; + default: + return ret; + } + } + return 0; +} + +int nfs4_destroy_clientid(struct nfs_client *clp) +{ + struct rpc_cred *cred; + int ret = 0; + + if (clp->cl_mvops->minor_version < 1) + goto out; + if (clp->cl_exchange_flags == 0) + goto out; + if (clp->cl_preserve_clid) + goto out; + cred = nfs4_get_clid_cred(clp); + ret = nfs4_proc_destroy_clientid(clp, cred); + if (cred) + put_rpccred(cred); + switch (ret) { + case 0: + case -NFS4ERR_STALE_CLIENTID: + clp->cl_exchange_flags = 0; + } +out: + return ret; +} + +struct nfs4_get_lease_time_data { + struct nfs4_get_lease_time_args *args; + struct nfs4_get_lease_time_res *res; + struct nfs_client *clp; +}; + +static void nfs4_get_lease_time_prepare(struct rpc_task *task, + void *calldata) +{ + struct nfs4_get_lease_time_data *data = + (struct nfs4_get_lease_time_data *)calldata; + + dprintk("--> %s\n", __func__); + /* just setup sequence, do not trigger session recovery + since we're invoked within one */ + nfs41_setup_sequence(data->clp->cl_session, + &data->args->la_seq_args, + &data->res->lr_seq_res, + task); + dprintk("<-- %s\n", __func__); +} + +/* + * Called from nfs4_state_manager thread for session setup, so don't recover + * from sequence operation or clientid errors. + */ +static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_get_lease_time_data *data = + (struct nfs4_get_lease_time_data *)calldata; + + dprintk("--> %s\n", __func__); + if (!nfs41_sequence_done(task, &data->res->lr_seq_res)) + return; + switch (task->tk_status) { + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status); + rpc_delay(task, NFS4_POLL_RETRY_MIN); + task->tk_status = 0; + /* fall through */ + case -NFS4ERR_RETRY_UNCACHED_REP: + rpc_restart_call_prepare(task); + return; + } + dprintk("<-- %s\n", __func__); +} + +static const struct rpc_call_ops nfs4_get_lease_time_ops = { + .rpc_call_prepare = nfs4_get_lease_time_prepare, + .rpc_call_done = nfs4_get_lease_time_done, +}; + +int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo) +{ + struct rpc_task *task; + struct nfs4_get_lease_time_args args; + struct nfs4_get_lease_time_res res = { + .lr_fsinfo = fsinfo, + }; + struct nfs4_get_lease_time_data data = { + .args = &args, + .res = &res, + .clp = clp, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GET_LEASE_TIME], + .rpc_argp = &args, + .rpc_resp = &res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = clp->cl_rpcclient, + .rpc_message = &msg, + .callback_ops = &nfs4_get_lease_time_ops, + .callback_data = &data, + .flags = RPC_TASK_TIMEOUT, + }; + int status; + + nfs4_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0); + nfs4_set_sequence_privileged(&args.la_seq_args); + dprintk("--> %s\n", __func__); + task = rpc_run_task(&task_setup); + + if (IS_ERR(task)) + status = PTR_ERR(task); + else { + status = task->tk_status; + rpc_put_task(task); + } + dprintk("<-- %s return %d\n", __func__, status); + + return status; +} + +/* + * Initialize the values to be used by the client in CREATE_SESSION + * If nfs4_init_session set the fore channel request and response sizes, + * use them. + * + * Set the back channel max_resp_sz_cached to zero to force the client to + * always set csa_cachethis to FALSE because the current implementation + * of the back channel DRC only supports caching the CB_SEQUENCE operation. + */ +static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) +{ + unsigned int max_rqst_sz, max_resp_sz; + + max_rqst_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxwrite_overhead; + max_resp_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxread_overhead; + + /* Fore channel attributes */ + args->fc_attrs.max_rqst_sz = max_rqst_sz; + args->fc_attrs.max_resp_sz = max_resp_sz; + args->fc_attrs.max_ops = NFS4_MAX_OPS; + args->fc_attrs.max_reqs = max_session_slots; + + dprintk("%s: Fore Channel : max_rqst_sz=%u max_resp_sz=%u " + "max_ops=%u max_reqs=%u\n", + __func__, + args->fc_attrs.max_rqst_sz, args->fc_attrs.max_resp_sz, + args->fc_attrs.max_ops, args->fc_attrs.max_reqs); + + /* Back channel attributes */ + args->bc_attrs.max_rqst_sz = PAGE_SIZE; + args->bc_attrs.max_resp_sz = PAGE_SIZE; + args->bc_attrs.max_resp_sz_cached = 0; + args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS; + args->bc_attrs.max_reqs = 1; + + dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u " + "max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n", + __func__, + args->bc_attrs.max_rqst_sz, args->bc_attrs.max_resp_sz, + args->bc_attrs.max_resp_sz_cached, args->bc_attrs.max_ops, + args->bc_attrs.max_reqs); +} + +static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args, + struct nfs41_create_session_res *res) +{ + struct nfs4_channel_attrs *sent = &args->fc_attrs; + struct nfs4_channel_attrs *rcvd = &res->fc_attrs; + + if (rcvd->max_resp_sz > sent->max_resp_sz) + return -EINVAL; + /* + * Our requested max_ops is the minimum we need; we're not + * prepared to break up compounds into smaller pieces than that. + * So, no point even trying to continue if the server won't + * cooperate: + */ + if (rcvd->max_ops < sent->max_ops) + return -EINVAL; + if (rcvd->max_reqs == 0) + return -EINVAL; + if (rcvd->max_reqs > NFS4_MAX_SLOT_TABLE) + rcvd->max_reqs = NFS4_MAX_SLOT_TABLE; + return 0; +} + +static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args, + struct nfs41_create_session_res *res) +{ + struct nfs4_channel_attrs *sent = &args->bc_attrs; + struct nfs4_channel_attrs *rcvd = &res->bc_attrs; + + if (!(res->flags & SESSION4_BACK_CHAN)) + goto out; + if (rcvd->max_rqst_sz > sent->max_rqst_sz) + return -EINVAL; + if (rcvd->max_resp_sz < sent->max_resp_sz) + return -EINVAL; + if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached) + return -EINVAL; + /* These would render the backchannel useless: */ + if (rcvd->max_ops != sent->max_ops) + return -EINVAL; + if (rcvd->max_reqs != sent->max_reqs) + return -EINVAL; +out: + return 0; +} + +static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args, + struct nfs41_create_session_res *res) +{ + int ret; + + ret = nfs4_verify_fore_channel_attrs(args, res); + if (ret) + return ret; + return nfs4_verify_back_channel_attrs(args, res); +} + +static void nfs4_update_session(struct nfs4_session *session, + struct nfs41_create_session_res *res) +{ + nfs4_copy_sessionid(&session->sess_id, &res->sessionid); + /* Mark client id and session as being confirmed */ + session->clp->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R; + set_bit(NFS4_SESSION_ESTABLISHED, &session->session_state); + session->flags = res->flags; + memcpy(&session->fc_attrs, &res->fc_attrs, sizeof(session->fc_attrs)); + if (res->flags & SESSION4_BACK_CHAN) + memcpy(&session->bc_attrs, &res->bc_attrs, + sizeof(session->bc_attrs)); +} + +static int _nfs4_proc_create_session(struct nfs_client *clp, + struct rpc_cred *cred) +{ + struct nfs4_session *session = clp->cl_session; + struct nfs41_create_session_args args = { + .client = clp, + .clientid = clp->cl_clientid, + .seqid = clp->cl_seqid, + .cb_program = NFS4_CALLBACK, + }; + struct nfs41_create_session_res res; + + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE_SESSION], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + nfs4_init_channel_attrs(&args); + args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN); + + status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_create_session(clp, status); + + if (!status) { + /* Verify the session's negotiated channel_attrs values */ + status = nfs4_verify_channel_attrs(&args, &res); + /* Increment the clientid slot sequence id */ + if (clp->cl_seqid == res.seqid) + clp->cl_seqid++; + if (status) + goto out; + nfs4_update_session(session, &res); + } +out: + return status; +} + +/* + * Issues a CREATE_SESSION operation to the server. + * It is the responsibility of the caller to verify the session is + * expired before calling this routine. + */ +int nfs4_proc_create_session(struct nfs_client *clp, struct rpc_cred *cred) +{ + int status; + unsigned *ptr; + struct nfs4_session *session = clp->cl_session; + + dprintk("--> %s clp=%p session=%p\n", __func__, clp, session); + + status = _nfs4_proc_create_session(clp, cred); + if (status) + goto out; + + /* Init or reset the session slot tables */ + status = nfs4_setup_session_slot_tables(session); + dprintk("slot table setup returned %d\n", status); + if (status) + goto out; + + ptr = (unsigned *)&session->sess_id.data[0]; + dprintk("%s client>seqid %d sessionid %u:%u:%u:%u\n", __func__, + clp->cl_seqid, ptr[0], ptr[1], ptr[2], ptr[3]); +out: + dprintk("<-- %s\n", __func__); + return status; +} + +/* + * Issue the over-the-wire RPC DESTROY_SESSION. + * The caller must serialize access to this routine. + */ +int nfs4_proc_destroy_session(struct nfs4_session *session, + struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION], + .rpc_argp = session, + .rpc_cred = cred, + }; + int status = 0; + + dprintk("--> nfs4_proc_destroy_session\n"); + + /* session is still being setup */ + if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state)) + return 0; + + status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_destroy_session(session->clp, status); + + if (status) + dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " + "Session has been destroyed regardless...\n", status); + + dprintk("<-- nfs4_proc_destroy_session\n"); + return status; +} + +/* + * Renew the cl_session lease. + */ +struct nfs4_sequence_data { + struct nfs_client *clp; + struct nfs4_sequence_args args; + struct nfs4_sequence_res res; +}; + +static void nfs41_sequence_release(void *data) +{ + struct nfs4_sequence_data *calldata = data; + struct nfs_client *clp = calldata->clp; + + if (atomic_read(&clp->cl_count) > 1) + nfs4_schedule_state_renewal(clp); + nfs_put_client(clp); + kfree(calldata); +} + +static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client *clp) +{ + switch(task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, NFS4_POLL_RETRY_MAX); + return -EAGAIN; + default: + nfs4_schedule_lease_recovery(clp); + } + return 0; +} + +static void nfs41_sequence_call_done(struct rpc_task *task, void *data) +{ + struct nfs4_sequence_data *calldata = data; + struct nfs_client *clp = calldata->clp; + + if (!nfs41_sequence_done(task, task->tk_msg.rpc_resp)) + return; + + trace_nfs4_sequence(clp, task->tk_status); + if (task->tk_status < 0) { + dprintk("%s ERROR %d\n", __func__, task->tk_status); + if (atomic_read(&clp->cl_count) == 1) + goto out; + + if (nfs41_sequence_handle_errors(task, clp) == -EAGAIN) { + rpc_restart_call_prepare(task); + return; + } + } + dprintk("%s rpc_cred %p\n", __func__, task->tk_msg.rpc_cred); +out: + dprintk("<-- %s\n", __func__); +} + +static void nfs41_sequence_prepare(struct rpc_task *task, void *data) +{ + struct nfs4_sequence_data *calldata = data; + struct nfs_client *clp = calldata->clp; + struct nfs4_sequence_args *args; + struct nfs4_sequence_res *res; + + args = task->tk_msg.rpc_argp; + res = task->tk_msg.rpc_resp; + + nfs41_setup_sequence(clp->cl_session, args, res, task); +} + +static const struct rpc_call_ops nfs41_sequence_ops = { + .rpc_call_done = nfs41_sequence_call_done, + .rpc_call_prepare = nfs41_sequence_prepare, + .rpc_release = nfs41_sequence_release, +}; + +static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, + struct rpc_cred *cred, + bool is_privileged) +{ + struct nfs4_sequence_data *calldata; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE], + .rpc_cred = cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clp->cl_rpcclient, + .rpc_message = &msg, + .callback_ops = &nfs41_sequence_ops, + .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT, + }; + + if (!atomic_inc_not_zero(&clp->cl_count)) + return ERR_PTR(-EIO); + calldata = kzalloc(sizeof(*calldata), GFP_NOFS); + if (calldata == NULL) { + nfs_put_client(clp); + return ERR_PTR(-ENOMEM); + } + nfs4_init_sequence(&calldata->args, &calldata->res, 0); + if (is_privileged) + nfs4_set_sequence_privileged(&calldata->args); + msg.rpc_argp = &calldata->args; + msg.rpc_resp = &calldata->res; + calldata->clp = clp; + task_setup_data.callback_data = calldata; + + return rpc_run_task(&task_setup_data); +} + +static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags) +{ + struct rpc_task *task; + int ret = 0; + + if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0) + return -EAGAIN; + task = _nfs41_proc_sequence(clp, cred, false); + if (IS_ERR(task)) + ret = PTR_ERR(task); + else + rpc_put_task_async(task); + dprintk("<-- %s status=%d\n", __func__, ret); + return ret; +} + +static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred) +{ + struct rpc_task *task; + int ret; + + task = _nfs41_proc_sequence(clp, cred, true); + if (IS_ERR(task)) { + ret = PTR_ERR(task); + goto out; + } + ret = rpc_wait_for_completion_task(task); + if (!ret) { + struct nfs4_sequence_res *res = task->tk_msg.rpc_resp; + + if (task->tk_status == 0) + nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); + ret = task->tk_status; + } + rpc_put_task(task); +out: + dprintk("<-- %s status=%d\n", __func__, ret); + return ret; +} + +struct nfs4_reclaim_complete_data { + struct nfs_client *clp; + struct nfs41_reclaim_complete_args arg; + struct nfs41_reclaim_complete_res res; +}; + +static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data) +{ + struct nfs4_reclaim_complete_data *calldata = data; + + nfs41_setup_sequence(calldata->clp->cl_session, + &calldata->arg.seq_args, + &calldata->res.seq_res, + task); +} + +static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nfs_client *clp) +{ + switch(task->tk_status) { + case 0: + case -NFS4ERR_COMPLETE_ALREADY: + case -NFS4ERR_WRONG_CRED: /* What to do here? */ + break; + case -NFS4ERR_DELAY: + rpc_delay(task, NFS4_POLL_RETRY_MAX); + /* fall through */ + case -NFS4ERR_RETRY_UNCACHED_REP: + return -EAGAIN; + default: + nfs4_schedule_lease_recovery(clp); + } + return 0; +} + +static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data) +{ + struct nfs4_reclaim_complete_data *calldata = data; + struct nfs_client *clp = calldata->clp; + struct nfs4_sequence_res *res = &calldata->res.seq_res; + + dprintk("--> %s\n", __func__); + if (!nfs41_sequence_done(task, res)) + return; + + trace_nfs4_reclaim_complete(clp, task->tk_status); + if (nfs41_reclaim_complete_handle_errors(task, clp) == -EAGAIN) { + rpc_restart_call_prepare(task); + return; + } + dprintk("<-- %s\n", __func__); +} + +static void nfs4_free_reclaim_complete_data(void *data) +{ + struct nfs4_reclaim_complete_data *calldata = data; + + kfree(calldata); +} + +static const struct rpc_call_ops nfs4_reclaim_complete_call_ops = { + .rpc_call_prepare = nfs4_reclaim_complete_prepare, + .rpc_call_done = nfs4_reclaim_complete_done, + .rpc_release = nfs4_free_reclaim_complete_data, +}; + +/* + * Issue a global reclaim complete. + */ +static int nfs41_proc_reclaim_complete(struct nfs_client *clp, + struct rpc_cred *cred) +{ + struct nfs4_reclaim_complete_data *calldata; + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RECLAIM_COMPLETE], + .rpc_cred = cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clp->cl_rpcclient, + .rpc_message = &msg, + .callback_ops = &nfs4_reclaim_complete_call_ops, + .flags = RPC_TASK_ASYNC, + }; + int status = -ENOMEM; + + dprintk("--> %s\n", __func__); + calldata = kzalloc(sizeof(*calldata), GFP_NOFS); + if (calldata == NULL) + goto out; + calldata->clp = clp; + calldata->arg.one_fs = 0; + + nfs4_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0); + nfs4_set_sequence_privileged(&calldata->arg.seq_args); + msg.rpc_argp = &calldata->arg; + msg.rpc_resp = &calldata->res; + task_setup_data.callback_data = calldata; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) { + status = PTR_ERR(task); + goto out; + } + status = nfs4_wait_for_completion_rpc_task(task); + if (status == 0) + status = task->tk_status; + rpc_put_task(task); + return 0; +out: + dprintk("<-- %s status=%d\n", __func__, status); + return status; +} + +static void +nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + struct nfs4_session *session = nfs4_get_session(server); + + dprintk("--> %s\n", __func__); + /* Note the is a race here, where a CB_LAYOUTRECALL can come in + * right now covering the LAYOUTGET we are about to send. + * However, that is not so catastrophic, and there seems + * to be no way to prevent it completely. + */ + if (nfs41_setup_sequence(session, &lgp->args.seq_args, + &lgp->res.seq_res, task)) + return; + if (pnfs_choose_layoutget_stateid(&lgp->args.stateid, + NFS_I(lgp->args.inode)->layout, + &lgp->args.range, + lgp->args.ctx->state)) { + rpc_exit(task, NFS4_OK); + } +} + +static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct inode *inode = lgp->args.inode; + struct nfs_server *server = NFS_SERVER(inode); + struct pnfs_layout_hdr *lo; + struct nfs4_state *state = NULL; + unsigned long timeo, now, giveup; + + dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status); + + if (!nfs41_sequence_done(task, &lgp->res.seq_res)) + goto out; + + switch (task->tk_status) { + case 0: + goto out; + /* + * NFS4ERR_LAYOUTTRYLATER is a conflict with another client + * (or clients) writing to the same RAID stripe + */ + case -NFS4ERR_LAYOUTTRYLATER: + /* + * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall + * existing layout before getting a new one). + */ + case -NFS4ERR_RECALLCONFLICT: + timeo = rpc_get_timeout(task->tk_client); + giveup = lgp->args.timestamp + timeo; + now = jiffies; + if (time_after(giveup, now)) { + unsigned long delay; + + /* Delay for: + * - Not less then NFS4_POLL_RETRY_MIN. + * - One last time a jiffie before we give up + * - exponential backoff (time_now minus start_attempt) + */ + delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN, + min((giveup - now - 1), + now - lgp->args.timestamp)); + + dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n", + __func__, delay); + rpc_delay(task, delay); + task->tk_status = 0; + rpc_restart_call_prepare(task); + goto out; /* Do not call nfs4_async_handle_error() */ + } + break; + case -NFS4ERR_EXPIRED: + case -NFS4ERR_BAD_STATEID: + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (!lo || list_empty(&lo->plh_segs)) { + spin_unlock(&inode->i_lock); + /* If the open stateid was bad, then recover it. */ + state = lgp->args.ctx->state; + } else { + LIST_HEAD(head); + + /* + * Mark the bad layout state as invalid, then retry + * with the current stateid. + */ + pnfs_mark_matching_lsegs_invalid(lo, &head, NULL); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&head); + + task->tk_status = 0; + rpc_restart_call_prepare(task); + } + } + if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) + rpc_restart_call_prepare(task); +out: + dprintk("<-- %s\n", __func__); +} + +static size_t max_response_pages(struct nfs_server *server) +{ + u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + return nfs_page_array_len(0, max_resp_sz); +} + +static void nfs4_free_pages(struct page **pages, size_t size) +{ + int i; + + if (!pages) + return; + + for (i = 0; i < size; i++) { + if (!pages[i]) + break; + __free_page(pages[i]); + } + kfree(pages); +} + +static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags) +{ + struct page **pages; + int i; + + pages = kcalloc(size, sizeof(struct page *), gfp_flags); + if (!pages) { + dprintk("%s: can't alloc array of %zu pages\n", __func__, size); + return NULL; + } + + for (i = 0; i < size; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) { + dprintk("%s: failed to allocate page\n", __func__); + nfs4_free_pages(pages, size); + return NULL; + } + } + + return pages; +} + +static void nfs4_layoutget_release(void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct inode *inode = lgp->args.inode; + struct nfs_server *server = NFS_SERVER(inode); + size_t max_pages = max_response_pages(server); + + dprintk("--> %s\n", __func__); + nfs4_free_pages(lgp->args.layout.pages, max_pages); + pnfs_put_layout_hdr(NFS_I(inode)->layout); + put_nfs_open_context(lgp->args.ctx); + kfree(calldata); + dprintk("<-- %s\n", __func__); +} + +static const struct rpc_call_ops nfs4_layoutget_call_ops = { + .rpc_call_prepare = nfs4_layoutget_prepare, + .rpc_call_done = nfs4_layoutget_done, + .rpc_release = nfs4_layoutget_release, +}; + +struct pnfs_layout_segment * +nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) +{ + struct inode *inode = lgp->args.inode; + struct nfs_server *server = NFS_SERVER(inode); + size_t max_pages = max_response_pages(server); + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], + .rpc_argp = &lgp->args, + .rpc_resp = &lgp->res, + .rpc_cred = lgp->cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_layoutget_call_ops, + .callback_data = lgp, + .flags = RPC_TASK_ASYNC, + }; + struct pnfs_layout_segment *lseg = NULL; + int status = 0; + + dprintk("--> %s\n", __func__); + + /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ + pnfs_get_layout_hdr(NFS_I(inode)->layout); + + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); + if (!lgp->args.layout.pages) { + nfs4_layoutget_release(lgp); + return ERR_PTR(-ENOMEM); + } + lgp->args.layout.pglen = max_pages * PAGE_SIZE; + lgp->args.timestamp = jiffies; + + lgp->res.layoutp = &lgp->args.layout; + lgp->res.seq_res.sr_slot = NULL; + nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); + status = nfs4_wait_for_completion_rpc_task(task); + if (status == 0) + status = task->tk_status; + trace_nfs4_layoutget(lgp->args.ctx, + &lgp->args.range, + &lgp->res.range, + status); + /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ + if (status == 0 && lgp->res.layoutp->len) + lseg = pnfs_layout_process(lgp); + rpc_put_task(task); + dprintk("<-- %s status=%d\n", __func__, status); + if (status) + return ERR_PTR(status); + return lseg; +} + +static void +nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutreturn *lrp = calldata; + + dprintk("--> %s\n", __func__); + nfs41_setup_sequence(lrp->clp->cl_session, + &lrp->args.seq_args, + &lrp->res.seq_res, + task); +} + +static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutreturn *lrp = calldata; + struct nfs_server *server; + + dprintk("--> %s\n", __func__); + + if (!nfs41_sequence_done(task, &lrp->res.seq_res)) + return; + + server = NFS_SERVER(lrp->args.inode); + switch (task->tk_status) { + default: + task->tk_status = 0; + case 0: + break; + case -NFS4ERR_DELAY: + if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN) + break; + rpc_restart_call_prepare(task); + return; + } + dprintk("<-- %s\n", __func__); +} + +static void nfs4_layoutreturn_release(void *calldata) +{ + struct nfs4_layoutreturn *lrp = calldata; + struct pnfs_layout_hdr *lo = lrp->args.layout; + + dprintk("--> %s\n", __func__); + spin_lock(&lo->plh_inode->i_lock); + if (lrp->res.lrs_present) + pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); + pnfs_clear_layoutreturn_waitbit(lo); + clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); + rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); + lo->plh_block_lgets--; + spin_unlock(&lo->plh_inode->i_lock); + pnfs_put_layout_hdr(lrp->args.layout); + nfs_iput_and_deactive(lrp->inode); + kfree(calldata); + dprintk("<-- %s\n", __func__); +} + +static const struct rpc_call_ops nfs4_layoutreturn_call_ops = { + .rpc_call_prepare = nfs4_layoutreturn_prepare, + .rpc_call_done = nfs4_layoutreturn_done, + .rpc_release = nfs4_layoutreturn_release, +}; + +int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) +{ + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTRETURN], + .rpc_argp = &lrp->args, + .rpc_resp = &lrp->res, + .rpc_cred = lrp->cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = NFS_SERVER(lrp->args.inode)->client, + .rpc_message = &msg, + .callback_ops = &nfs4_layoutreturn_call_ops, + .callback_data = lrp, + }; + int status = 0; + + dprintk("--> %s\n", __func__); + if (!sync) { + lrp->inode = nfs_igrab_and_active(lrp->args.inode); + if (!lrp->inode) { + nfs4_layoutreturn_release(lrp); + return -EAGAIN; + } + task_setup_data.flags |= RPC_TASK_ASYNC; + } + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1); + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + if (sync) + status = task->tk_status; + trace_nfs4_layoutreturn(lrp->args.inode, status); + dprintk("<-- %s status=%d\n", __func__, status); + rpc_put_task(task); + return status; +} + +static int +_nfs4_proc_getdeviceinfo(struct nfs_server *server, + struct pnfs_device *pdev, + struct rpc_cred *cred) +{ + struct nfs4_getdeviceinfo_args args = { + .pdev = pdev, + .notify_types = NOTIFY_DEVICEID4_CHANGE | + NOTIFY_DEVICEID4_DELETE, + }; + struct nfs4_getdeviceinfo_res res = { + .pdev = pdev, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICEINFO], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + if (res.notification & ~args.notify_types) + dprintk("%s: unsupported notification\n", __func__); + if (res.notification != args.notify_types) + pdev->nocache = 1; + + dprintk("<-- %s status=%d\n", __func__, status); + + return status; +} + +int nfs4_proc_getdeviceinfo(struct nfs_server *server, + struct pnfs_device *pdev, + struct rpc_cred *cred) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = nfs4_handle_exception(server, + _nfs4_proc_getdeviceinfo(server, pdev, cred), + &exception); + } while (exception.retry); + return err; +} +EXPORT_SYMBOL_GPL(nfs4_proc_getdeviceinfo); + +static void nfs4_layoutcommit_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutcommit_data *data = calldata; + struct nfs_server *server = NFS_SERVER(data->args.inode); + struct nfs4_session *session = nfs4_get_session(server); + + nfs41_setup_sequence(session, + &data->args.seq_args, + &data->res.seq_res, + task); +} + +static void +nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutcommit_data *data = calldata; + struct nfs_server *server = NFS_SERVER(data->args.inode); + + if (!nfs41_sequence_done(task, &data->res.seq_res)) + return; + + switch (task->tk_status) { /* Just ignore these failures */ + case -NFS4ERR_DELEG_REVOKED: /* layout was recalled */ + case -NFS4ERR_BADIOMODE: /* no IOMODE_RW layout for range */ + case -NFS4ERR_BADLAYOUT: /* no layout */ + case -NFS4ERR_GRACE: /* loca_recalim always false */ + task->tk_status = 0; + case 0: + break; + default: + if (nfs4_async_handle_error(task, server, NULL, NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return; + } + } +} + +static void nfs4_layoutcommit_release(void *calldata) +{ + struct nfs4_layoutcommit_data *data = calldata; + + pnfs_cleanup_layoutcommit(data); + nfs_post_op_update_inode_force_wcc(data->args.inode, + data->res.fattr); + put_rpccred(data->cred); + nfs_iput_and_deactive(data->inode); + kfree(data); +} + +static const struct rpc_call_ops nfs4_layoutcommit_ops = { + .rpc_call_prepare = nfs4_layoutcommit_prepare, + .rpc_call_done = nfs4_layoutcommit_done, + .rpc_release = nfs4_layoutcommit_release, +}; + +int +nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTCOMMIT], + .rpc_argp = &data->args, + .rpc_resp = &data->res, + .rpc_cred = data->cred, + }; + struct rpc_task_setup task_setup_data = { + .task = &data->task, + .rpc_client = NFS_CLIENT(data->args.inode), + .rpc_message = &msg, + .callback_ops = &nfs4_layoutcommit_ops, + .callback_data = data, + }; + struct rpc_task *task; + int status = 0; + + dprintk("NFS: %4d initiating layoutcommit call. sync %d " + "lbw: %llu inode %lu\n", + data->task.tk_pid, sync, + data->args.lastbytewritten, + data->args.inode->i_ino); + + if (!sync) { + data->inode = nfs_igrab_and_active(data->args.inode); + if (data->inode == NULL) { + nfs4_layoutcommit_release(data); + return -EAGAIN; + } + task_setup_data.flags = RPC_TASK_ASYNC; + } + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + if (sync) + status = task->tk_status; + trace_nfs4_layoutcommit(data->args.inode, status); + dprintk("%s: status %d\n", __func__, status); + rpc_put_task(task); + return status; +} + +/** + * Use the state managment nfs_client cl_rpcclient, which uses krb5i (if + * possible) as per RFC3530bis and RFC5661 Security Considerations sections + */ +static int +_nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info, + struct nfs4_secinfo_flavors *flavors, bool use_integrity) +{ + struct nfs41_secinfo_no_name_args args = { + .style = SECINFO_STYLE_CURRENT_FH, + }; + struct nfs4_secinfo_res res = { + .flavors = flavors, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SECINFO_NO_NAME], + .rpc_argp = &args, + .rpc_resp = &res, + }; + struct rpc_clnt *clnt = server->client; + struct rpc_cred *cred = NULL; + int status; + + if (use_integrity) { + clnt = server->nfs_client->cl_rpcclient; + cred = nfs4_get_clid_cred(server->nfs_client); + msg.rpc_cred = cred; + } + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("<-- %s status=%d\n", __func__, status); + + if (cred) + put_rpccred(cred); + + return status; +} + +static int +nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors) +{ + struct nfs4_exception exception = { }; + int err; + do { + /* first try using integrity protection */ + err = -NFS4ERR_WRONGSEC; + + /* try to use integrity protection with machine cred */ + if (_nfs4_is_integrity_protected(server->nfs_client)) + err = _nfs41_proc_secinfo_no_name(server, fhandle, info, + flavors, true); + + /* + * if unable to use integrity protection, or SECINFO with + * integrity protection returns NFS4ERR_WRONGSEC (which is + * disallowed by spec, but exists in deployed servers) use + * the current filesystem's rpc_client and the user cred. + */ + if (err == -NFS4ERR_WRONGSEC) + err = _nfs41_proc_secinfo_no_name(server, fhandle, info, + flavors, false); + + switch (err) { + case 0: + case -NFS4ERR_WRONGSEC: + case -ENOTSUPP: + goto out; + default: + err = nfs4_handle_exception(server, err, &exception); + } + } while (exception.retry); +out: + return err; +} + +static int +nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + int err; + struct page *page; + rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; + struct nfs4_secinfo_flavors *flavors; + struct nfs4_secinfo4 *secinfo; + int i; + + page = alloc_page(GFP_KERNEL); + if (!page) { + err = -ENOMEM; + goto out; + } + + flavors = page_address(page); + err = nfs41_proc_secinfo_no_name(server, fhandle, info, flavors); + + /* + * Fall back on "guess and check" method if + * the server doesn't support SECINFO_NO_NAME + */ + if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) { + err = nfs4_find_root_sec(server, fhandle, info); + goto out_freepage; + } + if (err) + goto out_freepage; + + for (i = 0; i < flavors->num_flavors; i++) { + secinfo = &flavors->flavors[i]; + + switch (secinfo->flavor) { + case RPC_AUTH_NULL: + case RPC_AUTH_UNIX: + case RPC_AUTH_GSS: + flavor = rpcauth_get_pseudoflavor(secinfo->flavor, + &secinfo->flavor_info); + break; + default: + flavor = RPC_AUTH_MAXFLAVOR; + break; + } + + if (!nfs_auth_info_match(&server->auth_info, flavor)) + flavor = RPC_AUTH_MAXFLAVOR; + + if (flavor != RPC_AUTH_MAXFLAVOR) { + err = nfs4_lookup_root_sec(server, fhandle, + info, flavor); + if (!err) + break; + } + } + + if (flavor == RPC_AUTH_MAXFLAVOR) + err = -EPERM; + +out_freepage: + put_page(page); + if (err == -EACCES) + return -EPERM; +out: + return err; +} + +static int _nfs41_test_stateid(struct nfs_server *server, + nfs4_stateid *stateid, + struct rpc_cred *cred) +{ + int status; + struct nfs41_test_stateid_args args = { + .stateid = stateid, + }; + struct nfs41_test_stateid_res res; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_TEST_STATEID], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + struct rpc_clnt *rpc_client = server->client; + + nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID, + &rpc_client, &msg); + + dprintk("NFS call test_stateid %p\n", stateid); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(rpc_client, server, &msg, + &args.seq_args, &res.seq_res); + if (status != NFS_OK) { + dprintk("NFS reply test_stateid: failed, %d\n", status); + return status; + } + dprintk("NFS reply test_stateid: succeeded, %d\n", -res.status); + return -res.status; +} + +/** + * nfs41_test_stateid - perform a TEST_STATEID operation + * + * @server: server / transport on which to perform the operation + * @stateid: state ID to test + * @cred: credential + * + * Returns NFS_OK if the server recognizes that "stateid" is valid. + * Otherwise a negative NFS4ERR value is returned if the operation + * failed or the state ID is not currently valid. + */ +static int nfs41_test_stateid(struct nfs_server *server, + nfs4_stateid *stateid, + struct rpc_cred *cred) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs41_test_stateid(server, stateid, cred); + if (err != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + return err; +} + +struct nfs_free_stateid_data { + struct nfs_server *server; + struct nfs41_free_stateid_args args; + struct nfs41_free_stateid_res res; +}; + +static void nfs41_free_stateid_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_free_stateid_data *data = calldata; + nfs41_setup_sequence(nfs4_get_session(data->server), + &data->args.seq_args, + &data->res.seq_res, + task); +} + +static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata) +{ + struct nfs_free_stateid_data *data = calldata; + + nfs41_sequence_done(task, &data->res.seq_res); + + switch (task->tk_status) { + case -NFS4ERR_DELAY: + if (nfs4_async_handle_error(task, data->server, NULL, NULL) == -EAGAIN) + rpc_restart_call_prepare(task); + } +} + +static void nfs41_free_stateid_release(void *calldata) +{ + kfree(calldata); +} + +static const struct rpc_call_ops nfs41_free_stateid_ops = { + .rpc_call_prepare = nfs41_free_stateid_prepare, + .rpc_call_done = nfs41_free_stateid_done, + .rpc_release = nfs41_free_stateid_release, +}; + +static struct rpc_task *_nfs41_free_stateid(struct nfs_server *server, + nfs4_stateid *stateid, + struct rpc_cred *cred, + bool privileged) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FREE_STATEID], + .rpc_cred = cred, + }; + struct rpc_task_setup task_setup = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs41_free_stateid_ops, + .flags = RPC_TASK_ASYNC, + }; + struct nfs_free_stateid_data *data; + + nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID, + &task_setup.rpc_client, &msg); + + dprintk("NFS call free_stateid %p\n", stateid); + data = kmalloc(sizeof(*data), GFP_NOFS); + if (!data) + return ERR_PTR(-ENOMEM); + data->server = server; + nfs4_stateid_copy(&data->args.stateid, stateid); + + task_setup.callback_data = data; + + msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); + if (privileged) + nfs4_set_sequence_privileged(&data->args.seq_args); + + return rpc_run_task(&task_setup); +} + +/** + * nfs41_free_stateid - perform a FREE_STATEID operation + * + * @server: server / transport on which to perform the operation + * @stateid: state ID to release + * @cred: credential + * + * Returns NFS_OK if the server freed "stateid". Otherwise a + * negative NFS4ERR value is returned. + */ +static int nfs41_free_stateid(struct nfs_server *server, + nfs4_stateid *stateid, + struct rpc_cred *cred) +{ + struct rpc_task *task; + int ret; + + task = _nfs41_free_stateid(server, stateid, cred, true); + if (IS_ERR(task)) + return PTR_ERR(task); + ret = rpc_wait_for_completion_task(task); + if (!ret) + ret = task->tk_status; + rpc_put_task(task); + return ret; +} + +static void +nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp) +{ + struct rpc_task *task; + struct rpc_cred *cred = lsp->ls_state->owner->so_cred; + + task = _nfs41_free_stateid(server, &lsp->ls_stateid, cred, false); + nfs4_free_lock_state(server, lsp); + if (IS_ERR(task)) + return; + rpc_put_task(task); +} + +static bool nfs41_match_stateid(const nfs4_stateid *s1, + const nfs4_stateid *s2) +{ + if (memcmp(s1->other, s2->other, sizeof(s1->other)) != 0) + return false; + + if (s1->seqid == s2->seqid) + return true; + if (s1->seqid == 0 || s2->seqid == 0) + return true; + + return false; +} + +#endif /* CONFIG_NFS_V4_1 */ + +static bool nfs4_match_stateid(const nfs4_stateid *s1, + const nfs4_stateid *s2) +{ + return nfs4_stateid_match(s1, s2); +} + + +static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = { + .owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT, + .state_flag_bit = NFS_STATE_RECLAIM_REBOOT, + .recover_open = nfs4_open_reclaim, + .recover_lock = nfs4_lock_reclaim, + .establish_clid = nfs4_init_clientid, + .detect_trunking = nfs40_discover_server_trunking, +}; + +#if defined(CONFIG_NFS_V4_1) +static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { + .owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT, + .state_flag_bit = NFS_STATE_RECLAIM_REBOOT, + .recover_open = nfs4_open_reclaim, + .recover_lock = nfs4_lock_reclaim, + .establish_clid = nfs41_init_clientid, + .reclaim_complete = nfs41_proc_reclaim_complete, + .detect_trunking = nfs41_discover_server_trunking, +}; +#endif /* CONFIG_NFS_V4_1 */ + +static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { + .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, + .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, + .recover_open = nfs40_open_expired, + .recover_lock = nfs4_lock_expired, + .establish_clid = nfs4_init_clientid, +}; + +#if defined(CONFIG_NFS_V4_1) +static const struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = { + .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, + .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, + .recover_open = nfs41_open_expired, + .recover_lock = nfs41_lock_expired, + .establish_clid = nfs41_init_clientid, +}; +#endif /* CONFIG_NFS_V4_1 */ + +static const struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = { + .sched_state_renewal = nfs4_proc_async_renew, + .get_state_renewal_cred_locked = nfs4_get_renew_cred_locked, + .renew_lease = nfs4_proc_renew, +}; + +#if defined(CONFIG_NFS_V4_1) +static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = { + .sched_state_renewal = nfs41_proc_async_sequence, + .get_state_renewal_cred_locked = nfs4_get_machine_cred_locked, + .renew_lease = nfs4_proc_sequence, +}; +#endif + +static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = { + .get_locations = _nfs40_proc_get_locations, + .fsid_present = _nfs40_proc_fsid_present, +}; + +#if defined(CONFIG_NFS_V4_1) +static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = { + .get_locations = _nfs41_proc_get_locations, + .fsid_present = _nfs41_proc_fsid_present, +}; +#endif /* CONFIG_NFS_V4_1 */ + +static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { + .minor_version = 0, + .init_caps = NFS_CAP_READDIRPLUS + | NFS_CAP_ATOMIC_OPEN + | NFS_CAP_CHANGE_ATTR + | NFS_CAP_POSIX_LOCK, + .init_client = nfs40_init_client, + .shutdown_client = nfs40_shutdown_client, + .match_stateid = nfs4_match_stateid, + .find_root_sec = nfs4_find_root_sec, + .free_lock_state = nfs4_release_lockowner, + .alloc_seqid = nfs_alloc_seqid, + .call_sync_ops = &nfs40_call_sync_ops, + .reboot_recovery_ops = &nfs40_reboot_recovery_ops, + .nograce_recovery_ops = &nfs40_nograce_recovery_ops, + .state_renewal_ops = &nfs40_state_renewal_ops, + .mig_recovery_ops = &nfs40_mig_recovery_ops, +}; + +#if defined(CONFIG_NFS_V4_1) +static struct nfs_seqid * +nfs_alloc_no_seqid(struct nfs_seqid_counter *arg1, gfp_t arg2) +{ + return NULL; +} + +static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { + .minor_version = 1, + .init_caps = NFS_CAP_READDIRPLUS + | NFS_CAP_ATOMIC_OPEN + | NFS_CAP_CHANGE_ATTR + | NFS_CAP_POSIX_LOCK + | NFS_CAP_STATEID_NFSV41 + | NFS_CAP_ATOMIC_OPEN_V1, + .init_client = nfs41_init_client, + .shutdown_client = nfs41_shutdown_client, + .match_stateid = nfs41_match_stateid, + .find_root_sec = nfs41_find_root_sec, + .free_lock_state = nfs41_free_lock_state, + .alloc_seqid = nfs_alloc_no_seqid, + .call_sync_ops = &nfs41_call_sync_ops, + .reboot_recovery_ops = &nfs41_reboot_recovery_ops, + .nograce_recovery_ops = &nfs41_nograce_recovery_ops, + .state_renewal_ops = &nfs41_state_renewal_ops, + .mig_recovery_ops = &nfs41_mig_recovery_ops, +}; +#endif + +#if defined(CONFIG_NFS_V4_2) +static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { + .minor_version = 2, + .init_caps = NFS_CAP_READDIRPLUS + | NFS_CAP_ATOMIC_OPEN + | NFS_CAP_CHANGE_ATTR + | NFS_CAP_POSIX_LOCK + | NFS_CAP_STATEID_NFSV41 + | NFS_CAP_ATOMIC_OPEN_V1 + | NFS_CAP_ALLOCATE + | NFS_CAP_DEALLOCATE + | NFS_CAP_SEEK, + .init_client = nfs41_init_client, + .shutdown_client = nfs41_shutdown_client, + .match_stateid = nfs41_match_stateid, + .find_root_sec = nfs41_find_root_sec, + .free_lock_state = nfs41_free_lock_state, + .call_sync_ops = &nfs41_call_sync_ops, + .alloc_seqid = nfs_alloc_no_seqid, + .reboot_recovery_ops = &nfs41_reboot_recovery_ops, + .nograce_recovery_ops = &nfs41_nograce_recovery_ops, + .state_renewal_ops = &nfs41_state_renewal_ops, +}; +#endif + +const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { + [0] = &nfs_v4_0_minor_ops, +#if defined(CONFIG_NFS_V4_1) + [1] = &nfs_v4_1_minor_ops, +#endif +#if defined(CONFIG_NFS_V4_2) + [2] = &nfs_v4_2_minor_ops, +#endif +}; + +static const struct inode_operations nfs4_dir_inode_operations = { + .create = nfs_create, + .lookup = nfs_lookup, + .atomic_open = nfs_atomic_open, + .link = nfs_link, + .unlink = nfs_unlink, + .symlink = nfs_symlink, + .mkdir = nfs_mkdir, + .rmdir = nfs_rmdir, + .mknod = nfs_mknod, + .rename = nfs_rename, + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, + .getxattr = generic_getxattr, + .setxattr = generic_setxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, +}; + +static const struct inode_operations nfs4_file_inode_operations = { + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, + .getxattr = generic_getxattr, + .setxattr = generic_setxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, +}; + +const struct nfs_rpc_ops nfs_v4_clientops = { + .version = 4, /* protocol version */ + .dentry_ops = &nfs4_dentry_operations, + .dir_inode_ops = &nfs4_dir_inode_operations, + .file_inode_ops = &nfs4_file_inode_operations, + .file_ops = &nfs4_file_operations, + .getroot = nfs4_proc_get_root, + .submount = nfs4_submount, + .try_mount = nfs4_try_mount, + .getattr = nfs4_proc_getattr, + .setattr = nfs4_proc_setattr, + .lookup = nfs4_proc_lookup, + .access = nfs4_proc_access, + .readlink = nfs4_proc_readlink, + .create = nfs4_proc_create, + .remove = nfs4_proc_remove, + .unlink_setup = nfs4_proc_unlink_setup, + .unlink_rpc_prepare = nfs4_proc_unlink_rpc_prepare, + .unlink_done = nfs4_proc_unlink_done, + .rename_setup = nfs4_proc_rename_setup, + .rename_rpc_prepare = nfs4_proc_rename_rpc_prepare, + .rename_done = nfs4_proc_rename_done, + .link = nfs4_proc_link, + .symlink = nfs4_proc_symlink, + .mkdir = nfs4_proc_mkdir, + .rmdir = nfs4_proc_remove, + .readdir = nfs4_proc_readdir, + .mknod = nfs4_proc_mknod, + .statfs = nfs4_proc_statfs, + .fsinfo = nfs4_proc_fsinfo, + .pathconf = nfs4_proc_pathconf, + .set_capabilities = nfs4_server_capabilities, + .decode_dirent = nfs4_decode_dirent, + .pgio_rpc_prepare = nfs4_proc_pgio_rpc_prepare, + .read_setup = nfs4_proc_read_setup, + .read_done = nfs4_read_done, + .write_setup = nfs4_proc_write_setup, + .write_done = nfs4_write_done, + .commit_setup = nfs4_proc_commit_setup, + .commit_rpc_prepare = nfs4_proc_commit_rpc_prepare, + .commit_done = nfs4_commit_done, + .lock = nfs4_proc_lock, + .clear_acl_cache = nfs4_zap_acl_attr, + .close_context = nfs4_close_context, + .open_context = nfs4_atomic_open, + .have_delegation = nfs4_have_delegation, + .return_delegation = nfs4_inode_return_delegation, + .alloc_client = nfs4_alloc_client, + .init_client = nfs4_init_client, + .free_client = nfs4_free_client, + .create_server = nfs4_create_server, + .clone_server = nfs_clone_server, +}; + +static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { + .prefix = XATTR_NAME_NFSV4_ACL, + .list = nfs4_xattr_list_nfs4_acl, + .get = nfs4_xattr_get_nfs4_acl, + .set = nfs4_xattr_set_nfs4_acl, +}; + +const struct xattr_handler *nfs4_xattr_handlers[] = { + &nfs4_xattr_nfs4_acl_handler, +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + &nfs4_xattr_nfs4_label_handler, +#endif + NULL +}; + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/kernel/fs/nfs/nfs4renewd.c b/kernel/fs/nfs/nfs4renewd.c new file mode 100644 index 000000000..e1ba58c3d --- /dev/null +++ b/kernel/fs/nfs/nfs4renewd.c @@ -0,0 +1,143 @@ +/* + * fs/nfs/nfs4renewd.c + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Kendrick Smith <kmsmith@umich.edu> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * Implementation of the NFSv4 "renew daemon", which wakes up periodically to + * send a RENEW, to keep state alive on the server. The daemon is implemented + * as an rpc_task, not a real kernel thread, so it always runs in rpciod's + * context. There is one renewd per nfs_server. + * + */ + +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/sunrpc/sched.h> +#include <linux/sunrpc/clnt.h> + +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" +#include "delegation.h" + +#define NFSDBG_FACILITY NFSDBG_STATE + +void +nfs4_renew_state(struct work_struct *work) +{ + const struct nfs4_state_maintenance_ops *ops; + struct nfs_client *clp = + container_of(work, struct nfs_client, cl_renewd.work); + struct rpc_cred *cred; + long lease; + unsigned long last, now; + unsigned renew_flags = 0; + + ops = clp->cl_mvops->state_renewal_ops; + dprintk("%s: start\n", __func__); + + if (test_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state)) + goto out; + + spin_lock(&clp->cl_lock); + lease = clp->cl_lease_time; + last = clp->cl_last_renewal; + now = jiffies; + /* Are we close to a lease timeout? */ + if (time_after(now, last + lease/3)) + renew_flags |= NFS4_RENEW_TIMEOUT; + if (nfs_delegations_present(clp)) + renew_flags |= NFS4_RENEW_DELEGATION_CB; + + if (renew_flags != 0) { + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) { + if (!(renew_flags & NFS4_RENEW_DELEGATION_CB)) { + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + goto out; + } + nfs_expire_all_delegations(clp); + } else { + int ret; + + /* Queue an asynchronous RENEW. */ + ret = ops->sched_state_renewal(clp, cred, renew_flags); + put_rpccred(cred); + switch (ret) { + default: + goto out_exp; + case -EAGAIN: + case -ENOMEM: + break; + } + } + } else { + dprintk("%s: failed to call renewd. Reason: lease not expired \n", + __func__); + spin_unlock(&clp->cl_lock); + } + nfs4_schedule_state_renewal(clp); +out_exp: + nfs_expire_unreferenced_delegations(clp); +out: + dprintk("%s: done\n", __func__); +} + +void +nfs4_schedule_state_renewal(struct nfs_client *clp) +{ + long timeout; + + spin_lock(&clp->cl_lock); + timeout = (2 * clp->cl_lease_time) / 3 + (long)clp->cl_last_renewal + - (long)jiffies; + if (timeout < 5 * HZ) + timeout = 5 * HZ; + dprintk("%s: requeueing work. Lease period = %ld\n", + __func__, (timeout + HZ - 1) / HZ); + mod_delayed_work(system_wq, &clp->cl_renewd, timeout); + set_bit(NFS_CS_RENEWD, &clp->cl_res_state); + spin_unlock(&clp->cl_lock); +} + +void +nfs4_kill_renewd(struct nfs_client *clp) +{ + cancel_delayed_work_sync(&clp->cl_renewd); +} + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/kernel/fs/nfs/nfs4session.c b/kernel/fs/nfs/nfs4session.c new file mode 100644 index 000000000..e23366eff --- /dev/null +++ b/kernel/fs/nfs/nfs4session.c @@ -0,0 +1,565 @@ +/* + * fs/nfs/nfs4session.c + * + * Copyright (c) 2012 Trond Myklebust <Trond.Myklebust@netapp.com> + * + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/sunrpc/sched.h> +#include <linux/sunrpc/bc_xprt.h> +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> +#include <linux/module.h> + +#include "nfs4_fs.h" +#include "internal.h" +#include "nfs4session.h" +#include "callback.h" + +#define NFSDBG_FACILITY NFSDBG_STATE + +static void nfs4_init_slot_table(struct nfs4_slot_table *tbl, const char *queue) +{ + tbl->highest_used_slotid = NFS4_NO_SLOT; + spin_lock_init(&tbl->slot_tbl_lock); + rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue); + init_completion(&tbl->complete); +} + +/* + * nfs4_shrink_slot_table - free retired slots from the slot table + */ +static void nfs4_shrink_slot_table(struct nfs4_slot_table *tbl, u32 newsize) +{ + struct nfs4_slot **p; + if (newsize >= tbl->max_slots) + return; + + p = &tbl->slots; + while (newsize--) + p = &(*p)->next; + while (*p) { + struct nfs4_slot *slot = *p; + + *p = slot->next; + kfree(slot); + tbl->max_slots--; + } +} + +/** + * nfs4_slot_tbl_drain_complete - wake waiters when drain is complete + * @tbl - controlling slot table + * + */ +void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl) +{ + if (nfs4_slot_tbl_draining(tbl)) + complete(&tbl->complete); +} + +/* + * nfs4_free_slot - free a slot and efficiently update slot table. + * + * freeing a slot is trivially done by clearing its respective bit + * in the bitmap. + * If the freed slotid equals highest_used_slotid we want to update it + * so that the server would be able to size down the slot table if needed, + * otherwise we know that the highest_used_slotid is still in use. + * When updating highest_used_slotid there may be "holes" in the bitmap + * so we need to scan down from highest_used_slotid to 0 looking for the now + * highest slotid in use. + * If none found, highest_used_slotid is set to NFS4_NO_SLOT. + * + * Must be called while holding tbl->slot_tbl_lock + */ +void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot) +{ + u32 slotid = slot->slot_nr; + + /* clear used bit in bitmap */ + __clear_bit(slotid, tbl->used_slots); + + /* update highest_used_slotid when it is freed */ + if (slotid == tbl->highest_used_slotid) { + u32 new_max = find_last_bit(tbl->used_slots, slotid); + if (new_max < slotid) + tbl->highest_used_slotid = new_max; + else { + tbl->highest_used_slotid = NFS4_NO_SLOT; + nfs4_slot_tbl_drain_complete(tbl); + } + } + dprintk("%s: slotid %u highest_used_slotid %u\n", __func__, + slotid, tbl->highest_used_slotid); +} + +static struct nfs4_slot *nfs4_new_slot(struct nfs4_slot_table *tbl, + u32 slotid, u32 seq_init, gfp_t gfp_mask) +{ + struct nfs4_slot *slot; + + slot = kzalloc(sizeof(*slot), gfp_mask); + if (slot) { + slot->table = tbl; + slot->slot_nr = slotid; + slot->seq_nr = seq_init; + } + return slot; +} + +static struct nfs4_slot *nfs4_find_or_create_slot(struct nfs4_slot_table *tbl, + u32 slotid, u32 seq_init, gfp_t gfp_mask) +{ + struct nfs4_slot **p, *slot; + + p = &tbl->slots; + for (;;) { + if (*p == NULL) { + *p = nfs4_new_slot(tbl, tbl->max_slots, + seq_init, gfp_mask); + if (*p == NULL) + break; + tbl->max_slots++; + } + slot = *p; + if (slot->slot_nr == slotid) + return slot; + p = &slot->next; + } + return ERR_PTR(-ENOMEM); +} + +/* + * nfs4_alloc_slot - efficiently look for a free slot + * + * nfs4_alloc_slot looks for an unset bit in the used_slots bitmap. + * If found, we mark the slot as used, update the highest_used_slotid, + * and respectively set up the sequence operation args. + * + * Note: must be called with under the slot_tbl_lock. + */ +struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl) +{ + struct nfs4_slot *ret = ERR_PTR(-EBUSY); + u32 slotid; + + dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n", + __func__, tbl->used_slots[0], tbl->highest_used_slotid, + tbl->max_slotid + 1); + slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1); + if (slotid > tbl->max_slotid) + goto out; + ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT); + if (IS_ERR(ret)) + goto out; + __set_bit(slotid, tbl->used_slots); + if (slotid > tbl->highest_used_slotid || + tbl->highest_used_slotid == NFS4_NO_SLOT) + tbl->highest_used_slotid = slotid; + ret->generation = tbl->generation; + +out: + dprintk("<-- %s used_slots=%04lx highest_used=%u slotid=%u\n", + __func__, tbl->used_slots[0], tbl->highest_used_slotid, + !IS_ERR(ret) ? ret->slot_nr : NFS4_NO_SLOT); + return ret; +} + +static int nfs4_grow_slot_table(struct nfs4_slot_table *tbl, + u32 max_reqs, u32 ivalue) +{ + if (max_reqs <= tbl->max_slots) + return 0; + if (!IS_ERR(nfs4_find_or_create_slot(tbl, max_reqs - 1, ivalue, GFP_NOFS))) + return 0; + return -ENOMEM; +} + +static void nfs4_reset_slot_table(struct nfs4_slot_table *tbl, + u32 server_highest_slotid, + u32 ivalue) +{ + struct nfs4_slot **p; + + nfs4_shrink_slot_table(tbl, server_highest_slotid + 1); + p = &tbl->slots; + while (*p) { + (*p)->seq_nr = ivalue; + (*p)->interrupted = 0; + p = &(*p)->next; + } + tbl->highest_used_slotid = NFS4_NO_SLOT; + tbl->target_highest_slotid = server_highest_slotid; + tbl->server_highest_slotid = server_highest_slotid; + tbl->d_target_highest_slotid = 0; + tbl->d2_target_highest_slotid = 0; + tbl->max_slotid = server_highest_slotid; +} + +/* + * (re)Initialise a slot table + */ +static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, + u32 max_reqs, u32 ivalue) +{ + int ret; + + dprintk("--> %s: max_reqs=%u, tbl->max_slots %u\n", __func__, + max_reqs, tbl->max_slots); + + if (max_reqs > NFS4_MAX_SLOT_TABLE) + max_reqs = NFS4_MAX_SLOT_TABLE; + + ret = nfs4_grow_slot_table(tbl, max_reqs, ivalue); + if (ret) + goto out; + + spin_lock(&tbl->slot_tbl_lock); + nfs4_reset_slot_table(tbl, max_reqs - 1, ivalue); + spin_unlock(&tbl->slot_tbl_lock); + + dprintk("%s: tbl=%p slots=%p max_slots=%u\n", __func__, + tbl, tbl->slots, tbl->max_slots); +out: + dprintk("<-- %s: return %d\n", __func__, ret); + return ret; +} + +/* + * nfs4_release_slot_table - release all slot table entries + */ +static void nfs4_release_slot_table(struct nfs4_slot_table *tbl) +{ + nfs4_shrink_slot_table(tbl, 0); +} + +/** + * nfs4_shutdown_slot_table - release resources attached to a slot table + * @tbl: slot table to shut down + * + */ +void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl) +{ + nfs4_release_slot_table(tbl); + rpc_destroy_wait_queue(&tbl->slot_tbl_waitq); +} + +/** + * nfs4_setup_slot_table - prepare a stand-alone slot table for use + * @tbl: slot table to set up + * @max_reqs: maximum number of requests allowed + * @queue: name to give RPC wait queue + * + * Returns zero on success, or a negative errno. + */ +int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, unsigned int max_reqs, + const char *queue) +{ + nfs4_init_slot_table(tbl, queue); + return nfs4_realloc_slot_table(tbl, max_reqs, 0); +} + +static bool nfs41_assign_slot(struct rpc_task *task, void *pslot) +{ + struct nfs4_sequence_args *args = task->tk_msg.rpc_argp; + struct nfs4_sequence_res *res = task->tk_msg.rpc_resp; + struct nfs4_slot *slot = pslot; + struct nfs4_slot_table *tbl = slot->table; + + if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged) + return false; + slot->generation = tbl->generation; + args->sa_slot = slot; + res->sr_timestamp = jiffies; + res->sr_slot = slot; + res->sr_status_flags = 0; + res->sr_status = 1; + return true; +} + +static bool __nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl, + struct nfs4_slot *slot) +{ + if (rpc_wake_up_first(&tbl->slot_tbl_waitq, nfs41_assign_slot, slot)) + return true; + return false; +} + +bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl, + struct nfs4_slot *slot) +{ + if (slot->slot_nr > tbl->max_slotid) + return false; + return __nfs41_wake_and_assign_slot(tbl, slot); +} + +static bool nfs41_try_wake_next_slot_table_entry(struct nfs4_slot_table *tbl) +{ + struct nfs4_slot *slot = nfs4_alloc_slot(tbl); + if (!IS_ERR(slot)) { + bool ret = __nfs41_wake_and_assign_slot(tbl, slot); + if (ret) + return ret; + nfs4_free_slot(tbl, slot); + } + return false; +} + +void nfs41_wake_slot_table(struct nfs4_slot_table *tbl) +{ + for (;;) { + if (!nfs41_try_wake_next_slot_table_entry(tbl)) + break; + } +} + +#if defined(CONFIG_NFS_V4_1) + +static void nfs41_set_max_slotid_locked(struct nfs4_slot_table *tbl, + u32 target_highest_slotid) +{ + u32 max_slotid; + + max_slotid = min(NFS4_MAX_SLOT_TABLE - 1, target_highest_slotid); + if (max_slotid > tbl->server_highest_slotid) + max_slotid = tbl->server_highest_slotid; + if (max_slotid > tbl->target_highest_slotid) + max_slotid = tbl->target_highest_slotid; + tbl->max_slotid = max_slotid; + nfs41_wake_slot_table(tbl); +} + +/* Update the client's idea of target_highest_slotid */ +static void nfs41_set_target_slotid_locked(struct nfs4_slot_table *tbl, + u32 target_highest_slotid) +{ + if (tbl->target_highest_slotid == target_highest_slotid) + return; + tbl->target_highest_slotid = target_highest_slotid; + tbl->generation++; +} + +void nfs41_set_target_slotid(struct nfs4_slot_table *tbl, + u32 target_highest_slotid) +{ + spin_lock(&tbl->slot_tbl_lock); + nfs41_set_target_slotid_locked(tbl, target_highest_slotid); + tbl->d_target_highest_slotid = 0; + tbl->d2_target_highest_slotid = 0; + nfs41_set_max_slotid_locked(tbl, target_highest_slotid); + spin_unlock(&tbl->slot_tbl_lock); +} + +static void nfs41_set_server_slotid_locked(struct nfs4_slot_table *tbl, + u32 highest_slotid) +{ + if (tbl->server_highest_slotid == highest_slotid) + return; + if (tbl->highest_used_slotid > highest_slotid) + return; + /* Deallocate slots */ + nfs4_shrink_slot_table(tbl, highest_slotid + 1); + tbl->server_highest_slotid = highest_slotid; +} + +static s32 nfs41_derivative_target_slotid(s32 s1, s32 s2) +{ + s1 -= s2; + if (s1 == 0) + return 0; + if (s1 < 0) + return (s1 - 1) >> 1; + return (s1 + 1) >> 1; +} + +static int nfs41_sign_s32(s32 s1) +{ + if (s1 > 0) + return 1; + if (s1 < 0) + return -1; + return 0; +} + +static bool nfs41_same_sign_or_zero_s32(s32 s1, s32 s2) +{ + if (!s1 || !s2) + return true; + return nfs41_sign_s32(s1) == nfs41_sign_s32(s2); +} + +/* Try to eliminate outliers by checking for sharp changes in the + * derivatives and second derivatives + */ +static bool nfs41_is_outlier_target_slotid(struct nfs4_slot_table *tbl, + u32 new_target) +{ + s32 d_target, d2_target; + bool ret = true; + + d_target = nfs41_derivative_target_slotid(new_target, + tbl->target_highest_slotid); + d2_target = nfs41_derivative_target_slotid(d_target, + tbl->d_target_highest_slotid); + /* Is first derivative same sign? */ + if (nfs41_same_sign_or_zero_s32(d_target, tbl->d_target_highest_slotid)) + ret = false; + /* Is second derivative same sign? */ + if (nfs41_same_sign_or_zero_s32(d2_target, tbl->d2_target_highest_slotid)) + ret = false; + tbl->d_target_highest_slotid = d_target; + tbl->d2_target_highest_slotid = d2_target; + return ret; +} + +void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, + struct nfs4_slot *slot, + struct nfs4_sequence_res *res) +{ + spin_lock(&tbl->slot_tbl_lock); + if (!nfs41_is_outlier_target_slotid(tbl, res->sr_target_highest_slotid)) + nfs41_set_target_slotid_locked(tbl, res->sr_target_highest_slotid); + if (tbl->generation == slot->generation) + nfs41_set_server_slotid_locked(tbl, res->sr_highest_slotid); + nfs41_set_max_slotid_locked(tbl, res->sr_target_highest_slotid); + spin_unlock(&tbl->slot_tbl_lock); +} + +static void nfs4_release_session_slot_tables(struct nfs4_session *session) +{ + nfs4_release_slot_table(&session->fc_slot_table); + nfs4_release_slot_table(&session->bc_slot_table); +} + +/* + * Initialize or reset the forechannel and backchannel tables + */ +int nfs4_setup_session_slot_tables(struct nfs4_session *ses) +{ + struct nfs4_slot_table *tbl; + int status; + + dprintk("--> %s\n", __func__); + /* Fore channel */ + tbl = &ses->fc_slot_table; + tbl->session = ses; + status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1); + if (status || !(ses->flags & SESSION4_BACK_CHAN)) /* -ENOMEM */ + return status; + /* Back channel */ + tbl = &ses->bc_slot_table; + tbl->session = ses; + status = nfs4_realloc_slot_table(tbl, ses->bc_attrs.max_reqs, 0); + if (status && tbl->slots == NULL) + /* Fore and back channel share a connection so get + * both slot tables or neither */ + nfs4_release_session_slot_tables(ses); + return status; +} + +struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp) +{ + struct nfs4_session *session; + + session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS); + if (!session) + return NULL; + + nfs4_init_slot_table(&session->fc_slot_table, "ForeChannel Slot table"); + nfs4_init_slot_table(&session->bc_slot_table, "BackChannel Slot table"); + session->session_state = 1<<NFS4_SESSION_INITING; + + session->clp = clp; + return session; +} + +static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) +{ + nfs4_shutdown_slot_table(&session->fc_slot_table); + nfs4_shutdown_slot_table(&session->bc_slot_table); +} + +void nfs4_destroy_session(struct nfs4_session *session) +{ + struct rpc_xprt *xprt; + struct rpc_cred *cred; + + cred = nfs4_get_clid_cred(session->clp); + nfs4_proc_destroy_session(session, cred); + if (cred) + put_rpccred(cred); + + rcu_read_lock(); + xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt); + rcu_read_unlock(); + dprintk("%s Destroy backchannel for xprt %p\n", + __func__, xprt); + xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS); + nfs4_destroy_session_slot_tables(session); + kfree(session); +} + +/* + * With sessions, the client is not marked ready until after a + * successful EXCHANGE_ID and CREATE_SESSION. + * + * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate + * other versions of NFS can be tried. + */ +static int nfs41_check_session_ready(struct nfs_client *clp) +{ + int ret; + + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) { + ret = nfs4_client_recover_expired_lease(clp); + if (ret) + return ret; + } + if (clp->cl_cons_state < NFS_CS_READY) + return -EPROTONOSUPPORT; + smp_rmb(); + return 0; +} + +int nfs4_init_session(struct nfs_client *clp) +{ + if (!nfs4_has_session(clp)) + return 0; + + clear_bit(NFS4_SESSION_INITING, &clp->cl_session->session_state); + return nfs41_check_session_ready(clp); +} + +int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time) +{ + struct nfs4_session *session = clp->cl_session; + int ret; + + spin_lock(&clp->cl_lock); + if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) { + /* + * Do not set NFS_CS_CHECK_LEASE_TIME instead set the + * DS lease to be equal to the MDS lease. + */ + clp->cl_lease_time = lease_time; + clp->cl_last_renewal = jiffies; + } + spin_unlock(&clp->cl_lock); + + ret = nfs41_check_session_ready(clp); + if (ret) + return ret; + /* Test for the DS role */ + if (!is_ds_client(clp)) + return -ENODEV; + return 0; +} +EXPORT_SYMBOL_GPL(nfs4_init_ds_session); + +#endif /* defined(CONFIG_NFS_V4_1) */ diff --git a/kernel/fs/nfs/nfs4session.h b/kernel/fs/nfs/nfs4session.h new file mode 100644 index 000000000..e3ea2c532 --- /dev/null +++ b/kernel/fs/nfs/nfs4session.h @@ -0,0 +1,160 @@ +/* + * fs/nfs/nfs4session.h + * + * Copyright (c) 2012 Trond Myklebust <Trond.Myklebust@netapp.com> + * + */ +#ifndef __LINUX_FS_NFS_NFS4SESSION_H +#define __LINUX_FS_NFS_NFS4SESSION_H + +/* maximum number of slots to use */ +#define NFS4_DEF_SLOT_TABLE_SIZE (64U) +#define NFS4_MAX_SLOT_TABLE (1024U) +#define NFS4_NO_SLOT ((u32)-1) + +#if IS_ENABLED(CONFIG_NFS_V4) + +/* Sessions slot seqid */ +struct nfs4_slot { + struct nfs4_slot_table *table; + struct nfs4_slot *next; + unsigned long generation; + u32 slot_nr; + u32 seq_nr; + unsigned int interrupted : 1; +}; + +/* Sessions */ +enum nfs4_slot_tbl_state { + NFS4_SLOT_TBL_DRAINING, +}; + +#define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long)) +struct nfs4_slot_table { + struct nfs4_session *session; /* Parent session */ + struct nfs4_slot *slots; /* seqid per slot */ + unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */ + spinlock_t slot_tbl_lock; + struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */ + u32 max_slots; /* # slots in table */ + u32 max_slotid; /* Max allowed slotid value */ + u32 highest_used_slotid; /* sent to server on each SEQ. + * op for dynamic resizing */ + u32 target_highest_slotid; /* Server max_slot target */ + u32 server_highest_slotid; /* Server highest slotid */ + s32 d_target_highest_slotid; /* Derivative */ + s32 d2_target_highest_slotid; /* 2nd derivative */ + unsigned long generation; /* Generation counter for + target_highest_slotid */ + struct completion complete; + unsigned long slot_tbl_state; +}; + +/* + * Session related parameters + */ +struct nfs4_session { + struct nfs4_sessionid sess_id; + u32 flags; + unsigned long session_state; + u32 hash_alg; + u32 ssv_len; + + /* The fore and back channel */ + struct nfs4_channel_attrs fc_attrs; + struct nfs4_slot_table fc_slot_table; + struct nfs4_channel_attrs bc_attrs; + struct nfs4_slot_table bc_slot_table; + struct nfs_client *clp; +}; + +enum nfs4_session_state { + NFS4_SESSION_INITING, + NFS4_SESSION_ESTABLISHED, +}; + +extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, + unsigned int max_reqs, const char *queue); +extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl); +extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl); +extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); +extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); +bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl, + struct nfs4_slot *slot); +void nfs41_wake_slot_table(struct nfs4_slot_table *tbl); + +static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl) +{ + return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); +} + +#if defined(CONFIG_NFS_V4_1) +extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl, + u32 target_highest_slotid); +extern void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, + struct nfs4_slot *slot, + struct nfs4_sequence_res *res); + +extern int nfs4_setup_session_slot_tables(struct nfs4_session *ses); + +extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp); +extern void nfs4_destroy_session(struct nfs4_session *session); +extern int nfs4_init_session(struct nfs_client *clp); +extern int nfs4_init_ds_session(struct nfs_client *, unsigned long); + +/* + * Determine if sessions are in use. + */ +static inline int nfs4_has_session(const struct nfs_client *clp) +{ + if (clp->cl_session) + return 1; + return 0; +} + +static inline int nfs4_has_persistent_session(const struct nfs_client *clp) +{ + if (nfs4_has_session(clp)) + return (clp->cl_session->flags & SESSION4_PERSIST); + return 0; +} + +static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst, + const struct nfs4_sessionid *src) +{ + memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN); +} + +#ifdef CONFIG_CRC32 +/* + * nfs_session_id_hash - calculate the crc32 hash for the session id + * @session - pointer to session + */ +#define nfs_session_id_hash(sess_id) \ + (~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data))) +#else +#define nfs_session_id_hash(session) (0) +#endif +#else /* defined(CONFIG_NFS_V4_1) */ + +static inline int nfs4_init_session(struct nfs_client *clp) +{ + return 0; +} + +/* + * Determine if sessions are in use. + */ +static inline int nfs4_has_session(const struct nfs_client *clp) +{ + return 0; +} + +static inline int nfs4_has_persistent_session(const struct nfs_client *clp) +{ + return 0; +} + +#endif /* defined(CONFIG_NFS_V4_1) */ +#endif /* IS_ENABLED(CONFIG_NFS_V4) */ +#endif /* __LINUX_FS_NFS_NFS4SESSION_H */ diff --git a/kernel/fs/nfs/nfs4state.c b/kernel/fs/nfs/nfs4state.c new file mode 100644 index 000000000..2782cfca2 --- /dev/null +++ b/kernel/fs/nfs/nfs4state.c @@ -0,0 +1,2455 @@ +/* + * fs/nfs/nfs4state.c + * + * Client-side XDR for NFSv4. + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Kendrick Smith <kmsmith@umich.edu> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * Implementation of the NFSv4 state model. For the time being, + * this is minimal, but will be made much more complex in a + * subsequent patch. + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/fs.h> +#include <linux/nfs_fs.h> +#include <linux/kthread.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/ratelimit.h> +#include <linux/workqueue.h> +#include <linux/bitops.h> +#include <linux/jiffies.h> + +#include <linux/sunrpc/clnt.h> + +#include "nfs4_fs.h" +#include "callback.h" +#include "delegation.h" +#include "internal.h" +#include "nfs4idmap.h" +#include "nfs4session.h" +#include "pnfs.h" +#include "netns.h" + +#define NFSDBG_FACILITY NFSDBG_STATE + +#define OPENOWNER_POOL_SIZE 8 + +const nfs4_stateid zero_stateid; +static DEFINE_MUTEX(nfs_clid_init_mutex); + +int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) +{ + struct nfs4_setclientid_res clid = { + .clientid = clp->cl_clientid, + .confirm = clp->cl_confirm, + }; + unsigned short port; + int status; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + + if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state)) + goto do_confirm; + port = nn->nfs_callback_tcpport; + if (clp->cl_addr.ss_family == AF_INET6) + port = nn->nfs_callback_tcpport6; + + status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid); + if (status != 0) + goto out; + clp->cl_clientid = clid.clientid; + clp->cl_confirm = clid.confirm; + set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); +do_confirm: + status = nfs4_proc_setclientid_confirm(clp, &clid, cred); + if (status != 0) + goto out; + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + nfs4_schedule_state_renewal(clp); +out: + return status; +} + +/** + * nfs40_discover_server_trunking - Detect server IP address trunking (mv0) + * + * @clp: nfs_client under test + * @result: OUT: found nfs_client, or clp + * @cred: credential to use for trunking test + * + * Returns zero, a negative errno, or a negative NFS4ERR status. + * If zero is returned, an nfs_client pointer is planted in + * "result". + * + * Note: The returned client may not yet be marked ready. + */ +int nfs40_discover_server_trunking(struct nfs_client *clp, + struct nfs_client **result, + struct rpc_cred *cred) +{ + struct nfs4_setclientid_res clid = { + .clientid = clp->cl_clientid, + .confirm = clp->cl_confirm, + }; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + unsigned short port; + int status; + + port = nn->nfs_callback_tcpport; + if (clp->cl_addr.ss_family == AF_INET6) + port = nn->nfs_callback_tcpport6; + + status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid); + if (status != 0) + goto out; + clp->cl_clientid = clid.clientid; + clp->cl_confirm = clid.confirm; + + status = nfs40_walk_client_list(clp, result, cred); + if (status == 0) { + /* Sustain the lease, even if it's empty. If the clientid4 + * goes stale it's of no use for trunking discovery. */ + nfs4_schedule_state_renewal(*result); + } +out: + return status; +} + +struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp) +{ + struct rpc_cred *cred = NULL; + + if (clp->cl_machine_cred != NULL) + cred = get_rpccred(clp->cl_machine_cred); + return cred; +} + +static void nfs4_root_machine_cred(struct nfs_client *clp) +{ + struct rpc_cred *cred, *new; + + new = rpc_lookup_machine_cred(NULL); + spin_lock(&clp->cl_lock); + cred = clp->cl_machine_cred; + clp->cl_machine_cred = new; + spin_unlock(&clp->cl_lock); + if (cred != NULL) + put_rpccred(cred); +} + +static struct rpc_cred * +nfs4_get_renew_cred_server_locked(struct nfs_server *server) +{ + struct rpc_cred *cred = NULL; + struct nfs4_state_owner *sp; + struct rb_node *pos; + + for (pos = rb_first(&server->state_owners); + pos != NULL; + pos = rb_next(pos)) { + sp = rb_entry(pos, struct nfs4_state_owner, so_server_node); + if (list_empty(&sp->so_states)) + continue; + cred = get_rpccred(sp->so_cred); + break; + } + return cred; +} + +/** + * nfs4_get_renew_cred_locked - Acquire credential for a renew operation + * @clp: client state handle + * + * Returns an rpc_cred with reference count bumped, or NULL. + * Caller must hold clp->cl_lock. + */ +struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp) +{ + struct rpc_cred *cred = NULL; + struct nfs_server *server; + + /* Use machine credentials if available */ + cred = nfs4_get_machine_cred_locked(clp); + if (cred != NULL) + goto out; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + cred = nfs4_get_renew_cred_server_locked(server); + if (cred != NULL) + break; + } + rcu_read_unlock(); + +out: + return cred; +} + +static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl) +{ + if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) { + spin_lock(&tbl->slot_tbl_lock); + nfs41_wake_slot_table(tbl); + spin_unlock(&tbl->slot_tbl_lock); + } +} + +static void nfs4_end_drain_session(struct nfs_client *clp) +{ + struct nfs4_session *ses = clp->cl_session; + + if (clp->cl_slot_tbl) { + nfs4_end_drain_slot_table(clp->cl_slot_tbl); + return; + } + + if (ses != NULL) { + nfs4_end_drain_slot_table(&ses->bc_slot_table); + nfs4_end_drain_slot_table(&ses->fc_slot_table); + } +} + +static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl) +{ + set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); + spin_lock(&tbl->slot_tbl_lock); + if (tbl->highest_used_slotid != NFS4_NO_SLOT) { + reinit_completion(&tbl->complete); + spin_unlock(&tbl->slot_tbl_lock); + return wait_for_completion_interruptible(&tbl->complete); + } + spin_unlock(&tbl->slot_tbl_lock); + return 0; +} + +static int nfs4_begin_drain_session(struct nfs_client *clp) +{ + struct nfs4_session *ses = clp->cl_session; + int ret = 0; + + if (clp->cl_slot_tbl) + return nfs4_drain_slot_tbl(clp->cl_slot_tbl); + + /* back channel */ + ret = nfs4_drain_slot_tbl(&ses->bc_slot_table); + if (ret) + return ret; + /* fore channel */ + return nfs4_drain_slot_tbl(&ses->fc_slot_table); +} + +#if defined(CONFIG_NFS_V4_1) + +static int nfs41_setup_state_renewal(struct nfs_client *clp) +{ + int status; + struct nfs_fsinfo fsinfo; + + if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { + nfs4_schedule_state_renewal(clp); + return 0; + } + + status = nfs4_proc_get_lease_time(clp, &fsinfo); + if (status == 0) { + /* Update lease time and schedule renewal */ + spin_lock(&clp->cl_lock); + clp->cl_lease_time = fsinfo.lease_time * HZ; + clp->cl_last_renewal = jiffies; + spin_unlock(&clp->cl_lock); + + nfs4_schedule_state_renewal(clp); + } + + return status; +} + +static void nfs41_finish_session_reset(struct nfs_client *clp) +{ + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + /* create_session negotiated new slot table */ + clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + nfs41_setup_state_renewal(clp); +} + +int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) +{ + int status; + + if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state)) + goto do_confirm; + nfs4_begin_drain_session(clp); + status = nfs4_proc_exchange_id(clp, cred); + if (status != 0) + goto out; + set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); +do_confirm: + status = nfs4_proc_create_session(clp, cred); + if (status != 0) + goto out; + nfs41_finish_session_reset(clp); + nfs_mark_client_ready(clp, NFS_CS_READY); +out: + return status; +} + +/** + * nfs41_discover_server_trunking - Detect server IP address trunking (mv1) + * + * @clp: nfs_client under test + * @result: OUT: found nfs_client, or clp + * @cred: credential to use for trunking test + * + * Returns NFS4_OK, a negative errno, or a negative NFS4ERR status. + * If NFS4_OK is returned, an nfs_client pointer is planted in + * "result". + * + * Note: The returned client may not yet be marked ready. + */ +int nfs41_discover_server_trunking(struct nfs_client *clp, + struct nfs_client **result, + struct rpc_cred *cred) +{ + int status; + + status = nfs4_proc_exchange_id(clp, cred); + if (status != NFS4_OK) + return status; + + status = nfs41_walk_client_list(clp, result, cred); + if (status < 0) + return status; + if (clp != *result) + return 0; + + /* Purge state if the client id was established in a prior instance */ + if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) + set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + else + set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + nfs4_schedule_state_manager(clp); + status = nfs_wait_client_init_complete(clp); + if (status < 0) + nfs_put_client(clp); + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_get_clid_cred - Acquire credential for a setclientid operation + * @clp: client state handle + * + * Returns an rpc_cred with reference count bumped, or NULL. + */ +struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp) +{ + struct rpc_cred *cred; + + spin_lock(&clp->cl_lock); + cred = nfs4_get_machine_cred_locked(clp); + spin_unlock(&clp->cl_lock); + return cred; +} + +static struct nfs4_state_owner * +nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred) +{ + struct rb_node **p = &server->state_owners.rb_node, + *parent = NULL; + struct nfs4_state_owner *sp; + + while (*p != NULL) { + parent = *p; + sp = rb_entry(parent, struct nfs4_state_owner, so_server_node); + + if (cred < sp->so_cred) + p = &parent->rb_left; + else if (cred > sp->so_cred) + p = &parent->rb_right; + else { + if (!list_empty(&sp->so_lru)) + list_del_init(&sp->so_lru); + atomic_inc(&sp->so_count); + return sp; + } + } + return NULL; +} + +static struct nfs4_state_owner * +nfs4_insert_state_owner_locked(struct nfs4_state_owner *new) +{ + struct nfs_server *server = new->so_server; + struct rb_node **p = &server->state_owners.rb_node, + *parent = NULL; + struct nfs4_state_owner *sp; + int err; + + while (*p != NULL) { + parent = *p; + sp = rb_entry(parent, struct nfs4_state_owner, so_server_node); + + if (new->so_cred < sp->so_cred) + p = &parent->rb_left; + else if (new->so_cred > sp->so_cred) + p = &parent->rb_right; + else { + if (!list_empty(&sp->so_lru)) + list_del_init(&sp->so_lru); + atomic_inc(&sp->so_count); + return sp; + } + } + err = ida_get_new(&server->openowner_id, &new->so_seqid.owner_id); + if (err) + return ERR_PTR(err); + rb_link_node(&new->so_server_node, parent, p); + rb_insert_color(&new->so_server_node, &server->state_owners); + return new; +} + +static void +nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp) +{ + struct nfs_server *server = sp->so_server; + + if (!RB_EMPTY_NODE(&sp->so_server_node)) + rb_erase(&sp->so_server_node, &server->state_owners); + ida_remove(&server->openowner_id, sp->so_seqid.owner_id); +} + +static void +nfs4_init_seqid_counter(struct nfs_seqid_counter *sc) +{ + sc->create_time = ktime_get(); + sc->flags = 0; + sc->counter = 0; + spin_lock_init(&sc->lock); + INIT_LIST_HEAD(&sc->list); + rpc_init_wait_queue(&sc->wait, "Seqid_waitqueue"); +} + +static void +nfs4_destroy_seqid_counter(struct nfs_seqid_counter *sc) +{ + rpc_destroy_wait_queue(&sc->wait); +} + +/* + * nfs4_alloc_state_owner(): this is called on the OPEN or CREATE path to + * create a new state_owner. + * + */ +static struct nfs4_state_owner * +nfs4_alloc_state_owner(struct nfs_server *server, + struct rpc_cred *cred, + gfp_t gfp_flags) +{ + struct nfs4_state_owner *sp; + + sp = kzalloc(sizeof(*sp), gfp_flags); + if (!sp) + return NULL; + sp->so_server = server; + sp->so_cred = get_rpccred(cred); + spin_lock_init(&sp->so_lock); + INIT_LIST_HEAD(&sp->so_states); + nfs4_init_seqid_counter(&sp->so_seqid); + atomic_set(&sp->so_count, 1); + INIT_LIST_HEAD(&sp->so_lru); + seqcount_init(&sp->so_reclaim_seqcount); + mutex_init(&sp->so_delegreturn_mutex); + return sp; +} + +static void +nfs4_drop_state_owner(struct nfs4_state_owner *sp) +{ + struct rb_node *rb_node = &sp->so_server_node; + + if (!RB_EMPTY_NODE(rb_node)) { + struct nfs_server *server = sp->so_server; + struct nfs_client *clp = server->nfs_client; + + spin_lock(&clp->cl_lock); + if (!RB_EMPTY_NODE(rb_node)) { + rb_erase(rb_node, &server->state_owners); + RB_CLEAR_NODE(rb_node); + } + spin_unlock(&clp->cl_lock); + } +} + +static void nfs4_free_state_owner(struct nfs4_state_owner *sp) +{ + nfs4_destroy_seqid_counter(&sp->so_seqid); + put_rpccred(sp->so_cred); + kfree(sp); +} + +static void nfs4_gc_state_owners(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_state_owner *sp, *tmp; + unsigned long time_min, time_max; + LIST_HEAD(doomed); + + spin_lock(&clp->cl_lock); + time_max = jiffies; + time_min = (long)time_max - (long)clp->cl_lease_time; + list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { + /* NB: LRU is sorted so that oldest is at the head */ + if (time_in_range(sp->so_expires, time_min, time_max)) + break; + list_move(&sp->so_lru, &doomed); + nfs4_remove_state_owner_locked(sp); + } + spin_unlock(&clp->cl_lock); + + list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { + list_del(&sp->so_lru); + nfs4_free_state_owner(sp); + } +} + +/** + * nfs4_get_state_owner - Look up a state owner given a credential + * @server: nfs_server to search + * @cred: RPC credential to match + * + * Returns a pointer to an instantiated nfs4_state_owner struct, or NULL. + */ +struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, + struct rpc_cred *cred, + gfp_t gfp_flags) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_state_owner *sp, *new; + + spin_lock(&clp->cl_lock); + sp = nfs4_find_state_owner_locked(server, cred); + spin_unlock(&clp->cl_lock); + if (sp != NULL) + goto out; + new = nfs4_alloc_state_owner(server, cred, gfp_flags); + if (new == NULL) + goto out; + do { + if (ida_pre_get(&server->openowner_id, gfp_flags) == 0) + break; + spin_lock(&clp->cl_lock); + sp = nfs4_insert_state_owner_locked(new); + spin_unlock(&clp->cl_lock); + } while (sp == ERR_PTR(-EAGAIN)); + if (sp != new) + nfs4_free_state_owner(new); +out: + nfs4_gc_state_owners(server); + return sp; +} + +/** + * nfs4_put_state_owner - Release a nfs4_state_owner + * @sp: state owner data to release + * + * Note that we keep released state owners on an LRU + * list. + * This caches valid state owners so that they can be + * reused, to avoid the OPEN_CONFIRM on minor version 0. + * It also pins the uniquifier of dropped state owners for + * a while, to ensure that those state owner names are + * never reused. + */ +void nfs4_put_state_owner(struct nfs4_state_owner *sp) +{ + struct nfs_server *server = sp->so_server; + struct nfs_client *clp = server->nfs_client; + + if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock)) + return; + + sp->so_expires = jiffies; + list_add_tail(&sp->so_lru, &server->state_owners_lru); + spin_unlock(&clp->cl_lock); +} + +/** + * nfs4_purge_state_owners - Release all cached state owners + * @server: nfs_server with cached state owners to release + * + * Called at umount time. Remaining state owners will be on + * the LRU with ref count of zero. + */ +void nfs4_purge_state_owners(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_state_owner *sp, *tmp; + LIST_HEAD(doomed); + + spin_lock(&clp->cl_lock); + list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { + list_move(&sp->so_lru, &doomed); + nfs4_remove_state_owner_locked(sp); + } + spin_unlock(&clp->cl_lock); + + list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { + list_del(&sp->so_lru); + nfs4_free_state_owner(sp); + } +} + +static struct nfs4_state * +nfs4_alloc_open_state(void) +{ + struct nfs4_state *state; + + state = kzalloc(sizeof(*state), GFP_NOFS); + if (!state) + return NULL; + atomic_set(&state->count, 1); + INIT_LIST_HEAD(&state->lock_states); + spin_lock_init(&state->state_lock); + seqlock_init(&state->seqlock); + return state; +} + +void +nfs4_state_set_mode_locked(struct nfs4_state *state, fmode_t fmode) +{ + if (state->state == fmode) + return; + /* NB! List reordering - see the reclaim code for why. */ + if ((fmode & FMODE_WRITE) != (state->state & FMODE_WRITE)) { + if (fmode & FMODE_WRITE) + list_move(&state->open_states, &state->owner->so_states); + else + list_move_tail(&state->open_states, &state->owner->so_states); + } + state->state = fmode; +} + +static struct nfs4_state * +__nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs4_state *state; + + list_for_each_entry(state, &nfsi->open_states, inode_states) { + if (state->owner != owner) + continue; + if (!nfs4_valid_open_stateid(state)) + continue; + if (atomic_inc_not_zero(&state->count)) + return state; + } + return NULL; +} + +static void +nfs4_free_open_state(struct nfs4_state *state) +{ + kfree(state); +} + +struct nfs4_state * +nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner) +{ + struct nfs4_state *state, *new; + struct nfs_inode *nfsi = NFS_I(inode); + + spin_lock(&inode->i_lock); + state = __nfs4_find_state_byowner(inode, owner); + spin_unlock(&inode->i_lock); + if (state) + goto out; + new = nfs4_alloc_open_state(); + spin_lock(&owner->so_lock); + spin_lock(&inode->i_lock); + state = __nfs4_find_state_byowner(inode, owner); + if (state == NULL && new != NULL) { + state = new; + state->owner = owner; + atomic_inc(&owner->so_count); + list_add(&state->inode_states, &nfsi->open_states); + ihold(inode); + state->inode = inode; + spin_unlock(&inode->i_lock); + /* Note: The reclaim code dictates that we add stateless + * and read-only stateids to the end of the list */ + list_add_tail(&state->open_states, &owner->so_states); + spin_unlock(&owner->so_lock); + } else { + spin_unlock(&inode->i_lock); + spin_unlock(&owner->so_lock); + if (new) + nfs4_free_open_state(new); + } +out: + return state; +} + +void nfs4_put_open_state(struct nfs4_state *state) +{ + struct inode *inode = state->inode; + struct nfs4_state_owner *owner = state->owner; + + if (!atomic_dec_and_lock(&state->count, &owner->so_lock)) + return; + spin_lock(&inode->i_lock); + list_del(&state->inode_states); + list_del(&state->open_states); + spin_unlock(&inode->i_lock); + spin_unlock(&owner->so_lock); + iput(inode); + nfs4_free_open_state(state); + nfs4_put_state_owner(owner); +} + +/* + * Close the current file. + */ +static void __nfs4_close(struct nfs4_state *state, + fmode_t fmode, gfp_t gfp_mask, int wait) +{ + struct nfs4_state_owner *owner = state->owner; + int call_close = 0; + fmode_t newstate; + + atomic_inc(&owner->so_count); + /* Protect against nfs4_find_state() */ + spin_lock(&owner->so_lock); + switch (fmode & (FMODE_READ | FMODE_WRITE)) { + case FMODE_READ: + state->n_rdonly--; + break; + case FMODE_WRITE: + state->n_wronly--; + break; + case FMODE_READ|FMODE_WRITE: + state->n_rdwr--; + } + newstate = FMODE_READ|FMODE_WRITE; + if (state->n_rdwr == 0) { + if (state->n_rdonly == 0) { + newstate &= ~FMODE_READ; + call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags); + call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); + } + if (state->n_wronly == 0) { + newstate &= ~FMODE_WRITE; + call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags); + call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); + } + if (newstate == 0) + clear_bit(NFS_DELEGATED_STATE, &state->flags); + } + nfs4_state_set_mode_locked(state, newstate); + spin_unlock(&owner->so_lock); + + if (!call_close) { + nfs4_put_open_state(state); + nfs4_put_state_owner(owner); + } else + nfs4_do_close(state, gfp_mask, wait); +} + +void nfs4_close_state(struct nfs4_state *state, fmode_t fmode) +{ + __nfs4_close(state, fmode, GFP_NOFS, 0); +} + +void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode) +{ + __nfs4_close(state, fmode, GFP_KERNEL, 1); +} + +/* + * Search the state->lock_states for an existing lock_owner + * that is compatible with current->files + */ +static struct nfs4_lock_state * +__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner) +{ + struct nfs4_lock_state *pos; + list_for_each_entry(pos, &state->lock_states, ls_locks) { + if (pos->ls_owner != fl_owner) + continue; + atomic_inc(&pos->ls_count); + return pos; + } + return NULL; +} + +/* + * Return a compatible lock_state. If no initialized lock_state structure + * exists, return an uninitialized one. + * + */ +static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner) +{ + struct nfs4_lock_state *lsp; + struct nfs_server *server = state->owner->so_server; + + lsp = kzalloc(sizeof(*lsp), GFP_NOFS); + if (lsp == NULL) + return NULL; + nfs4_init_seqid_counter(&lsp->ls_seqid); + atomic_set(&lsp->ls_count, 1); + lsp->ls_state = state; + lsp->ls_owner = fl_owner; + lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS); + if (lsp->ls_seqid.owner_id < 0) + goto out_free; + INIT_LIST_HEAD(&lsp->ls_locks); + return lsp; +out_free: + kfree(lsp); + return NULL; +} + +void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp) +{ + ida_simple_remove(&server->lockowner_id, lsp->ls_seqid.owner_id); + nfs4_destroy_seqid_counter(&lsp->ls_seqid); + kfree(lsp); +} + +/* + * Return a compatible lock_state. If no initialized lock_state structure + * exists, return an uninitialized one. + * + */ +static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner) +{ + struct nfs4_lock_state *lsp, *new = NULL; + + for(;;) { + spin_lock(&state->state_lock); + lsp = __nfs4_find_lock_state(state, owner); + if (lsp != NULL) + break; + if (new != NULL) { + list_add(&new->ls_locks, &state->lock_states); + set_bit(LK_STATE_IN_USE, &state->flags); + lsp = new; + new = NULL; + break; + } + spin_unlock(&state->state_lock); + new = nfs4_alloc_lock_state(state, owner); + if (new == NULL) + return NULL; + } + spin_unlock(&state->state_lock); + if (new != NULL) + nfs4_free_lock_state(state->owner->so_server, new); + return lsp; +} + +/* + * Release reference to lock_state, and free it if we see that + * it is no longer in use + */ +void nfs4_put_lock_state(struct nfs4_lock_state *lsp) +{ + struct nfs_server *server; + struct nfs4_state *state; + + if (lsp == NULL) + return; + state = lsp->ls_state; + if (!atomic_dec_and_lock(&lsp->ls_count, &state->state_lock)) + return; + list_del(&lsp->ls_locks); + if (list_empty(&state->lock_states)) + clear_bit(LK_STATE_IN_USE, &state->flags); + spin_unlock(&state->state_lock); + server = state->owner->so_server; + if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) { + struct nfs_client *clp = server->nfs_client; + + clp->cl_mvops->free_lock_state(server, lsp); + } else + nfs4_free_lock_state(server, lsp); +} + +static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src) +{ + struct nfs4_lock_state *lsp = src->fl_u.nfs4_fl.owner; + + dst->fl_u.nfs4_fl.owner = lsp; + atomic_inc(&lsp->ls_count); +} + +static void nfs4_fl_release_lock(struct file_lock *fl) +{ + nfs4_put_lock_state(fl->fl_u.nfs4_fl.owner); +} + +static const struct file_lock_operations nfs4_fl_lock_ops = { + .fl_copy_lock = nfs4_fl_copy_lock, + .fl_release_private = nfs4_fl_release_lock, +}; + +int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl) +{ + struct nfs4_lock_state *lsp; + + if (fl->fl_ops != NULL) + return 0; + lsp = nfs4_get_lock_state(state, fl->fl_owner); + if (lsp == NULL) + return -ENOMEM; + fl->fl_u.nfs4_fl.owner = lsp; + fl->fl_ops = &nfs4_fl_lock_ops; + return 0; +} + +static int nfs4_copy_lock_stateid(nfs4_stateid *dst, + struct nfs4_state *state, + const struct nfs_lockowner *lockowner) +{ + struct nfs4_lock_state *lsp; + fl_owner_t fl_owner; + int ret = -ENOENT; + + + if (lockowner == NULL) + goto out; + + if (test_bit(LK_STATE_IN_USE, &state->flags) == 0) + goto out; + + fl_owner = lockowner->l_owner; + spin_lock(&state->state_lock); + lsp = __nfs4_find_lock_state(state, fl_owner); + if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags)) + ret = -EIO; + else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) { + nfs4_stateid_copy(dst, &lsp->ls_stateid); + ret = 0; + } + spin_unlock(&state->state_lock); + nfs4_put_lock_state(lsp); +out: + return ret; +} + +static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) +{ + const nfs4_stateid *src; + int seq; + + do { + src = &zero_stateid; + seq = read_seqbegin(&state->seqlock); + if (test_bit(NFS_OPEN_STATE, &state->flags)) + src = &state->open_stateid; + nfs4_stateid_copy(dst, src); + } while (read_seqretry(&state->seqlock, seq)); +} + +/* + * Byte-range lock aware utility to initialize the stateid of read/write + * requests. + */ +int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state, + fmode_t fmode, const struct nfs_lockowner *lockowner) +{ + int ret = nfs4_copy_lock_stateid(dst, state, lockowner); + if (ret == -EIO) + /* A lost lock - don't even consider delegations */ + goto out; + /* returns true if delegation stateid found and copied */ + if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) { + ret = 0; + goto out; + } + if (ret != -ENOENT) + /* nfs4_copy_delegation_stateid() didn't over-write + * dst, so it still has the lock stateid which we now + * choose to use. + */ + goto out; + nfs4_copy_open_stateid(dst, state); + ret = 0; +out: + if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41)) + dst->seqid = 0; + return ret; +} + +struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask) +{ + struct nfs_seqid *new; + + new = kmalloc(sizeof(*new), gfp_mask); + if (new == NULL) + return ERR_PTR(-ENOMEM); + new->sequence = counter; + INIT_LIST_HEAD(&new->list); + new->task = NULL; + return new; +} + +void nfs_release_seqid(struct nfs_seqid *seqid) +{ + struct nfs_seqid_counter *sequence; + + if (seqid == NULL || list_empty(&seqid->list)) + return; + sequence = seqid->sequence; + spin_lock(&sequence->lock); + list_del_init(&seqid->list); + if (!list_empty(&sequence->list)) { + struct nfs_seqid *next; + + next = list_first_entry(&sequence->list, + struct nfs_seqid, list); + rpc_wake_up_queued_task(&sequence->wait, next->task); + } + spin_unlock(&sequence->lock); +} + +void nfs_free_seqid(struct nfs_seqid *seqid) +{ + nfs_release_seqid(seqid); + kfree(seqid); +} + +/* + * Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or + * failed with a seqid incrementing error - + * see comments nfs4.h:seqid_mutating_error() + */ +static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) +{ + switch (status) { + case 0: + break; + case -NFS4ERR_BAD_SEQID: + if (seqid->sequence->flags & NFS_SEQID_CONFIRMED) + return; + pr_warn_ratelimited("NFS: v4 server returned a bad" + " sequence-id error on an" + " unconfirmed sequence %p!\n", + seqid->sequence); + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_BADXDR: + case -NFS4ERR_RESOURCE: + case -NFS4ERR_NOFILEHANDLE: + /* Non-seqid mutating errors */ + return; + }; + /* + * Note: no locking needed as we are guaranteed to be first + * on the sequence list + */ + seqid->sequence->counter++; +} + +void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid) +{ + struct nfs4_state_owner *sp; + + if (seqid == NULL) + return; + + sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid); + if (status == -NFS4ERR_BAD_SEQID) + nfs4_drop_state_owner(sp); + if (!nfs4_has_session(sp->so_server->nfs_client)) + nfs_increment_seqid(status, seqid); +} + +/* + * Increment the seqid if the LOCK/LOCKU succeeded, or + * failed with a seqid incrementing error - + * see comments nfs4.h:seqid_mutating_error() + */ +void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid) +{ + if (seqid != NULL) + nfs_increment_seqid(status, seqid); +} + +int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task) +{ + struct nfs_seqid_counter *sequence; + int status = 0; + + if (seqid == NULL) + goto out; + sequence = seqid->sequence; + spin_lock(&sequence->lock); + seqid->task = task; + if (list_empty(&seqid->list)) + list_add_tail(&seqid->list, &sequence->list); + if (list_first_entry(&sequence->list, struct nfs_seqid, list) == seqid) + goto unlock; + rpc_sleep_on(&sequence->wait, task, NULL); + status = -EAGAIN; +unlock: + spin_unlock(&sequence->lock); +out: + return status; +} + +static int nfs4_run_state_manager(void *); + +static void nfs4_clear_state_manager_bit(struct nfs_client *clp) +{ + smp_mb__before_atomic(); + clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + smp_mb__after_atomic(); + wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING); + rpc_wake_up(&clp->cl_rpcwaitq); +} + +/* + * Schedule the nfs_client asynchronous state management routine + */ +void nfs4_schedule_state_manager(struct nfs_client *clp) +{ + struct task_struct *task; + char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); + atomic_inc(&clp->cl_count); + + /* The rcu_read_lock() is not strictly necessary, as the state + * manager is the only thread that ever changes the rpc_xprt + * after it's initialized. At this point, we're single threaded. */ + rcu_read_lock(); + snprintf(buf, sizeof(buf), "%s-manager", + rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR)); + rcu_read_unlock(); + task = kthread_run(nfs4_run_state_manager, clp, "%s", buf); + if (IS_ERR(task)) { + printk(KERN_ERR "%s: kthread_run: %ld\n", + __func__, PTR_ERR(task)); + nfs4_clear_state_manager_bit(clp); + nfs_put_client(clp); + module_put(THIS_MODULE); + } +} + +/* + * Schedule a lease recovery attempt + */ +void nfs4_schedule_lease_recovery(struct nfs_client *clp) +{ + if (!clp) + return; + if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) + set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + dprintk("%s: scheduling lease recovery for server %s\n", __func__, + clp->cl_hostname); + nfs4_schedule_state_manager(clp); +} +EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery); + +/** + * nfs4_schedule_migration_recovery - trigger migration recovery + * + * @server: FSID that is migrating + * + * Returns zero if recovery has started, otherwise a negative NFS4ERR + * value is returned. + */ +int nfs4_schedule_migration_recovery(const struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + + if (server->fh_expire_type != NFS4_FH_PERSISTENT) { + pr_err("NFS: volatile file handles not supported (server %s)\n", + clp->cl_hostname); + return -NFS4ERR_IO; + } + + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -NFS4ERR_IO; + + dprintk("%s: scheduling migration recovery for (%llx:%llx) on %s\n", + __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + + set_bit(NFS_MIG_IN_TRANSITION, + &((struct nfs_server *)server)->mig_status); + set_bit(NFS4CLNT_MOVED, &clp->cl_state); + + nfs4_schedule_state_manager(clp); + return 0; +} +EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery); + +/** + * nfs4_schedule_lease_moved_recovery - start lease-moved recovery + * + * @clp: server to check for moved leases + * + */ +void nfs4_schedule_lease_moved_recovery(struct nfs_client *clp) +{ + dprintk("%s: scheduling lease-moved recovery for client ID %llx on %s\n", + __func__, clp->cl_clientid, clp->cl_hostname); + + set_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state); + nfs4_schedule_state_manager(clp); +} +EXPORT_SYMBOL_GPL(nfs4_schedule_lease_moved_recovery); + +int nfs4_wait_clnt_recover(struct nfs_client *clp) +{ + int res; + + might_sleep(); + + atomic_inc(&clp->cl_count); + res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (res) + goto out; + if (clp->cl_cons_state < 0) + res = clp->cl_cons_state; +out: + nfs_put_client(clp); + return res; +} + +int nfs4_client_recover_expired_lease(struct nfs_client *clp) +{ + unsigned int loop; + int ret; + + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { + ret = nfs4_wait_clnt_recover(clp); + if (ret != 0) + break; + if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) && + !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state)) + break; + nfs4_schedule_state_manager(clp); + ret = -EIO; + } + return ret; +} + +/* + * nfs40_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN + * @clp: client to process + * + * Set the NFS4CLNT_LEASE_EXPIRED state in order to force a + * resend of the SETCLIENTID and hence re-establish the + * callback channel. Then return all existing delegations. + */ +static void nfs40_handle_cb_pathdown(struct nfs_client *clp) +{ + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + nfs_expire_all_delegations(clp); + dprintk("%s: handling CB_PATHDOWN recovery for server %s\n", __func__, + clp->cl_hostname); +} + +void nfs4_schedule_path_down_recovery(struct nfs_client *clp) +{ + nfs40_handle_cb_pathdown(clp); + nfs4_schedule_state_manager(clp); +} + +static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state) +{ + + set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags); + /* Don't recover state that expired before the reboot */ + if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags)) { + clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags); + return 0; + } + set_bit(NFS_OWNER_RECLAIM_REBOOT, &state->owner->so_flags); + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); + return 1; +} + +int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state) +{ + set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags); + clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags); + set_bit(NFS_OWNER_RECLAIM_NOGRACE, &state->owner->so_flags); + set_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state); + return 1; +} + +int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state) +{ + struct nfs_client *clp = server->nfs_client; + + if (!nfs4_valid_open_stateid(state)) + return -EBADF; + nfs4_state_mark_reclaim_nograce(clp, state); + dprintk("%s: scheduling stateid recovery for server %s\n", __func__, + clp->cl_hostname); + nfs4_schedule_state_manager(clp); + return 0; +} +EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery); + +void nfs_inode_find_state_and_recover(struct inode *inode, + const nfs4_stateid *stateid) +{ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_open_context *ctx; + struct nfs4_state *state; + bool found = false; + + spin_lock(&inode->i_lock); + list_for_each_entry(ctx, &nfsi->open_files, list) { + state = ctx->state; + if (state == NULL) + continue; + if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) + continue; + if (!nfs4_stateid_match(&state->stateid, stateid)) + continue; + nfs4_state_mark_reclaim_nograce(clp, state); + found = true; + } + spin_unlock(&inode->i_lock); + if (found) + nfs4_schedule_state_manager(clp); +} + +static void nfs4_state_mark_open_context_bad(struct nfs4_state *state) +{ + struct inode *inode = state->inode; + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_open_context *ctx; + + spin_lock(&inode->i_lock); + list_for_each_entry(ctx, &nfsi->open_files, list) { + if (ctx->state != state) + continue; + set_bit(NFS_CONTEXT_BAD, &ctx->flags); + } + spin_unlock(&inode->i_lock); +} + +static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error) +{ + set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags); + nfs4_state_mark_open_context_bad(state); +} + + +static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops) +{ + struct inode *inode = state->inode; + struct nfs_inode *nfsi = NFS_I(inode); + struct file_lock *fl; + int status = 0; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; + + if (flctx == NULL) + return 0; + + list = &flctx->flc_posix; + + /* Guard against delegation returns and new lock/unlock calls */ + down_write(&nfsi->rwsem); + spin_lock(&flctx->flc_lock); +restart: + list_for_each_entry(fl, list, fl_list) { + if (nfs_file_open_context(fl->fl_file)->state != state) + continue; + spin_unlock(&flctx->flc_lock); + status = ops->recover_lock(state, fl); + switch (status) { + case 0: + break; + case -ESTALE: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_EXPIRED: + case -NFS4ERR_NO_GRACE: + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + goto out; + default: + pr_err("NFS: %s: unhandled error %d\n", + __func__, status); + case -ENOMEM: + case -NFS4ERR_DENIED: + case -NFS4ERR_RECLAIM_BAD: + case -NFS4ERR_RECLAIM_CONFLICT: + /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + status = 0; + } + spin_lock(&flctx->flc_lock); + } + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } + spin_unlock(&flctx->flc_lock); +out: + up_write(&nfsi->rwsem); + return status; +} + +static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops) +{ + struct nfs4_state *state; + struct nfs4_lock_state *lock; + int status = 0; + + /* Note: we rely on the sp->so_states list being ordered + * so that we always reclaim open(O_RDWR) and/or open(O_WRITE) + * states first. + * This is needed to ensure that the server won't give us any + * read delegations that we have to return if, say, we are + * recovering after a network partition or a reboot from a + * server that doesn't support a grace period. + */ + spin_lock(&sp->so_lock); + raw_write_seqcount_begin(&sp->so_reclaim_seqcount); +restart: + list_for_each_entry(state, &sp->so_states, open_states) { + if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) + continue; + if (!nfs4_valid_open_stateid(state)) + continue; + if (state->state == 0) + continue; + atomic_inc(&state->count); + spin_unlock(&sp->so_lock); + status = ops->recover_open(sp, state); + if (status >= 0) { + status = nfs4_reclaim_locks(state, ops); + if (status >= 0) { + if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) { + spin_lock(&state->state_lock); + list_for_each_entry(lock, &state->lock_states, ls_locks) { + if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags)) + pr_warn_ratelimited("NFS: " + "%s: Lock reclaim " + "failed!\n", __func__); + } + spin_unlock(&state->state_lock); + } + nfs4_put_open_state(state); + spin_lock(&sp->so_lock); + goto restart; + } + } + switch (status) { + default: + printk(KERN_ERR "NFS: %s: unhandled error %d\n", + __func__, status); + case -ENOENT: + case -ENOMEM: + case -ESTALE: + /* Open state on this file cannot be recovered */ + nfs4_state_mark_recovery_failed(state, status); + break; + case -EAGAIN: + ssleep(1); + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_RECLAIM_BAD: + case -NFS4ERR_RECLAIM_CONFLICT: + nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state); + break; + case -NFS4ERR_EXPIRED: + case -NFS4ERR_NO_GRACE: + nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state); + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + goto out_err; + } + nfs4_put_open_state(state); + spin_lock(&sp->so_lock); + goto restart; + } + raw_write_seqcount_end(&sp->so_reclaim_seqcount); + spin_unlock(&sp->so_lock); + return 0; +out_err: + nfs4_put_open_state(state); + spin_lock(&sp->so_lock); + raw_write_seqcount_end(&sp->so_reclaim_seqcount); + spin_unlock(&sp->so_lock); + return status; +} + +static void nfs4_clear_open_state(struct nfs4_state *state) +{ + struct nfs4_lock_state *lock; + + clear_bit(NFS_DELEGATED_STATE, &state->flags); + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_O_RDWR_STATE, &state->flags); + spin_lock(&state->state_lock); + list_for_each_entry(lock, &state->lock_states, ls_locks) { + lock->ls_seqid.flags = 0; + clear_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags); + } + spin_unlock(&state->state_lock); +} + +static void nfs4_reset_seqids(struct nfs_server *server, + int (*mark_reclaim)(struct nfs_client *clp, struct nfs4_state *state)) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_state_owner *sp; + struct rb_node *pos; + struct nfs4_state *state; + + spin_lock(&clp->cl_lock); + for (pos = rb_first(&server->state_owners); + pos != NULL; + pos = rb_next(pos)) { + sp = rb_entry(pos, struct nfs4_state_owner, so_server_node); + sp->so_seqid.flags = 0; + spin_lock(&sp->so_lock); + list_for_each_entry(state, &sp->so_states, open_states) { + if (mark_reclaim(clp, state)) + nfs4_clear_open_state(state); + } + spin_unlock(&sp->so_lock); + } + spin_unlock(&clp->cl_lock); +} + +static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, + int (*mark_reclaim)(struct nfs_client *clp, struct nfs4_state *state)) +{ + struct nfs_server *server; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs4_reset_seqids(server, mark_reclaim); + rcu_read_unlock(); +} + +static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) +{ + /* Mark all delegations for reclaim */ + nfs_delegation_mark_reclaim(clp); + nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot); +} + +static void nfs4_reclaim_complete(struct nfs_client *clp, + const struct nfs4_state_recovery_ops *ops, + struct rpc_cred *cred) +{ + /* Notify the server we're done reclaiming our state */ + if (ops->reclaim_complete) + (void)ops->reclaim_complete(clp, cred); +} + +static void nfs4_clear_reclaim_server(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_state_owner *sp; + struct rb_node *pos; + struct nfs4_state *state; + + spin_lock(&clp->cl_lock); + for (pos = rb_first(&server->state_owners); + pos != NULL; + pos = rb_next(pos)) { + sp = rb_entry(pos, struct nfs4_state_owner, so_server_node); + spin_lock(&sp->so_lock); + list_for_each_entry(state, &sp->so_states, open_states) { + if (!test_and_clear_bit(NFS_STATE_RECLAIM_REBOOT, + &state->flags)) + continue; + nfs4_state_mark_reclaim_nograce(clp, state); + } + spin_unlock(&sp->so_lock); + } + spin_unlock(&clp->cl_lock); +} + +static int nfs4_state_clear_reclaim_reboot(struct nfs_client *clp) +{ + struct nfs_server *server; + + if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) + return 0; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs4_clear_reclaim_server(server); + rcu_read_unlock(); + + nfs_delegation_reap_unclaimed(clp); + return 1; +} + +static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) +{ + const struct nfs4_state_recovery_ops *ops; + struct rpc_cred *cred; + + if (!nfs4_state_clear_reclaim_reboot(clp)) + return; + ops = clp->cl_mvops->reboot_recovery_ops; + cred = nfs4_get_clid_cred(clp); + nfs4_reclaim_complete(clp, ops, cred); + put_rpccred(cred); +} + +static void nfs_delegation_clear_all(struct nfs_client *clp) +{ + nfs_delegation_mark_reclaim(clp); + nfs_delegation_reap_unclaimed(clp); +} + +static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp) +{ + nfs_delegation_clear_all(clp); + nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce); +} + +static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) +{ + switch (error) { + case 0: + break; + case -NFS4ERR_CB_PATH_DOWN: + nfs40_handle_cb_pathdown(clp); + break; + case -NFS4ERR_NO_GRACE: + nfs4_state_end_reclaim_reboot(clp); + break; + case -NFS4ERR_STALE_CLIENTID: + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + nfs4_state_clear_reclaim_reboot(clp); + nfs4_state_start_reclaim_reboot(clp); + break; + case -NFS4ERR_EXPIRED: + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + nfs4_state_start_reclaim_nograce(clp); + break; + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + /* Zero session reset errors */ + break; + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + break; + default: + dprintk("%s: failed to handle error %d for server %s\n", + __func__, error, clp->cl_hostname); + return error; + } + dprintk("%s: handled error %d for server %s\n", __func__, error, + clp->cl_hostname); + return 0; +} + +static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops) +{ + struct nfs4_state_owner *sp; + struct nfs_server *server; + struct rb_node *pos; + int status = 0; + +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + nfs4_purge_state_owners(server); + spin_lock(&clp->cl_lock); + for (pos = rb_first(&server->state_owners); + pos != NULL; + pos = rb_next(pos)) { + sp = rb_entry(pos, + struct nfs4_state_owner, so_server_node); + if (!test_and_clear_bit(ops->owner_flag_bit, + &sp->so_flags)) + continue; + atomic_inc(&sp->so_count); + spin_unlock(&clp->cl_lock); + rcu_read_unlock(); + + status = nfs4_reclaim_open_state(sp, ops); + if (status < 0) { + set_bit(ops->owner_flag_bit, &sp->so_flags); + nfs4_put_state_owner(sp); + status = nfs4_recovery_handle_error(clp, status); + return (status != 0) ? status : -EAGAIN; + } + + nfs4_put_state_owner(sp); + goto restart; + } + spin_unlock(&clp->cl_lock); + } + rcu_read_unlock(); + return 0; +} + +static int nfs4_check_lease(struct nfs_client *clp) +{ + struct rpc_cred *cred; + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + int status; + + /* Is the client already known to have an expired lease? */ + if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) + return 0; + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) { + cred = nfs4_get_clid_cred(clp); + status = -ENOKEY; + if (cred == NULL) + goto out; + } + status = ops->renew_lease(clp, cred); + put_rpccred(cred); + if (status == -ETIMEDOUT) { + set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + return 0; + } +out: + return nfs4_recovery_handle_error(clp, status); +} + +/* Set NFS4CLNT_LEASE_EXPIRED and reclaim reboot state for all v4.0 errors + * and for recoverable errors on EXCHANGE_ID for v4.1 + */ +static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) +{ + switch (status) { + case -NFS4ERR_SEQ_MISORDERED: + if (test_and_set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) + return -ESERVERFAULT; + /* Lease confirmation error: retry after purging the lease */ + ssleep(1); + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + break; + case -NFS4ERR_STALE_CLIENTID: + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + nfs4_state_start_reclaim_reboot(clp); + break; + case -NFS4ERR_CLID_INUSE: + pr_err("NFS: Server %s reports our clientid is in use\n", + clp->cl_hostname); + nfs_mark_client_ready(clp, -EPERM); + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + return -EPERM; + case -EACCES: + case -NFS4ERR_DELAY: + case -ETIMEDOUT: + case -EAGAIN: + ssleep(1); + break; + + case -NFS4ERR_MINOR_VERS_MISMATCH: + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) + nfs_mark_client_ready(clp, -EPROTONOSUPPORT); + dprintk("%s: exit with error %d for server %s\n", + __func__, -EPROTONOSUPPORT, clp->cl_hostname); + return -EPROTONOSUPPORT; + case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery + * in nfs4_exchange_id */ + default: + dprintk("%s: exit with error %d for server %s\n", __func__, + status, clp->cl_hostname); + return status; + } + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + dprintk("%s: handled error %d for server %s\n", __func__, status, + clp->cl_hostname); + return 0; +} + +static int nfs4_establish_lease(struct nfs_client *clp) +{ + struct rpc_cred *cred; + const struct nfs4_state_recovery_ops *ops = + clp->cl_mvops->reboot_recovery_ops; + int status; + + cred = nfs4_get_clid_cred(clp); + if (cred == NULL) + return -ENOENT; + status = ops->establish_clid(clp, cred); + put_rpccred(cred); + if (status != 0) + return status; + pnfs_destroy_all_layouts(clp); + return 0; +} + +/* + * Returns zero or a negative errno. NFS4ERR values are converted + * to local errno values. + */ +static int nfs4_reclaim_lease(struct nfs_client *clp) +{ + int status; + + status = nfs4_establish_lease(clp); + if (status < 0) + return nfs4_handle_reclaim_lease_error(clp, status); + if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state)) + nfs4_state_start_reclaim_nograce(clp); + if (!test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); + clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + return 0; +} + +static int nfs4_purge_lease(struct nfs_client *clp) +{ + int status; + + status = nfs4_establish_lease(clp); + if (status < 0) + return nfs4_handle_reclaim_lease_error(clp, status); + clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + nfs4_state_start_reclaim_nograce(clp); + return 0; +} + +/* + * Try remote migration of one FSID from a source server to a + * destination server. The source server provides a list of + * potential destinations. + * + * Returns zero or a negative NFS4ERR status code. + */ +static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_fs_locations *locations = NULL; + struct inode *inode; + struct page *page; + int status, result; + + dprintk("--> %s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + + result = 0; + page = alloc_page(GFP_KERNEL); + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (page == NULL || locations == NULL) { + dprintk("<-- %s: no memory\n", __func__); + goto out; + } + + inode = d_inode(server->super->s_root); + result = nfs4_proc_get_locations(inode, locations, page, cred); + if (result) { + dprintk("<-- %s: failed to retrieve fs_locations: %d\n", + __func__, result); + goto out; + } + + result = -NFS4ERR_NXIO; + if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { + dprintk("<-- %s: No fs_locations data, migration skipped\n", + __func__); + goto out; + } + + nfs4_begin_drain_session(clp); + + status = nfs4_replace_transport(server, locations); + if (status != 0) { + dprintk("<-- %s: failed to replace transport: %d\n", + __func__, status); + goto out; + } + + result = 0; + dprintk("<-- %s: migration succeeded\n", __func__); + +out: + if (page != NULL) + __free_page(page); + kfree(locations); + if (result) { + pr_err("NFS: migration recovery failed (server %s)\n", + clp->cl_hostname); + set_bit(NFS_MIG_FAILED, &server->mig_status); + } + return result; +} + +/* + * Returns zero or a negative NFS4ERR status code. + */ +static int nfs4_handle_migration(struct nfs_client *clp) +{ + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + struct nfs_server *server; + struct rpc_cred *cred; + + dprintk("%s: migration reported on \"%s\"\n", __func__, + clp->cl_hostname); + + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) + return -NFS4ERR_NOENT; + + clp->cl_mig_gen++; +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + int status; + + if (server->mig_gen == clp->cl_mig_gen) + continue; + server->mig_gen = clp->cl_mig_gen; + + if (!test_and_clear_bit(NFS_MIG_IN_TRANSITION, + &server->mig_status)) + continue; + + rcu_read_unlock(); + status = nfs4_try_migration(server, cred); + if (status < 0) { + put_rpccred(cred); + return status; + } + goto restart; + } + rcu_read_unlock(); + put_rpccred(cred); + return 0; +} + +/* + * Test each nfs_server on the clp's cl_superblocks list to see + * if it's moved to another server. Stop when the server no longer + * returns NFS4ERR_LEASE_MOVED. + */ +static int nfs4_handle_lease_moved(struct nfs_client *clp) +{ + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + struct nfs_server *server; + struct rpc_cred *cred; + + dprintk("%s: lease moved reported on \"%s\"\n", __func__, + clp->cl_hostname); + + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) + return -NFS4ERR_NOENT; + + clp->cl_mig_gen++; +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + struct inode *inode; + int status; + + if (server->mig_gen == clp->cl_mig_gen) + continue; + server->mig_gen = clp->cl_mig_gen; + + rcu_read_unlock(); + + inode = d_inode(server->super->s_root); + status = nfs4_proc_fsid_present(inode, cred); + if (status != -NFS4ERR_MOVED) + goto restart; /* wasn't this one */ + if (nfs4_try_migration(server, cred) == -NFS4ERR_LEASE_MOVED) + goto restart; /* there are more */ + goto out; + } + rcu_read_unlock(); + +out: + put_rpccred(cred); + return 0; +} + +/** + * nfs4_discover_server_trunking - Detect server IP address trunking + * + * @clp: nfs_client under test + * @result: OUT: found nfs_client, or clp + * + * Returns zero or a negative errno. If zero is returned, + * an nfs_client pointer is planted in "result". + * + * Note: since we are invoked in process context, and + * not from inside the state manager, we cannot use + * nfs4_handle_reclaim_lease_error(). + */ +int nfs4_discover_server_trunking(struct nfs_client *clp, + struct nfs_client **result) +{ + const struct nfs4_state_recovery_ops *ops = + clp->cl_mvops->reboot_recovery_ops; + struct rpc_clnt *clnt; + struct rpc_cred *cred; + int i, status; + + dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname); + + clnt = clp->cl_rpcclient; + i = 0; + + mutex_lock(&nfs_clid_init_mutex); +again: + status = -ENOENT; + cred = nfs4_get_clid_cred(clp); + if (cred == NULL) + goto out_unlock; + + status = ops->detect_trunking(clp, result, cred); + put_rpccred(cred); + switch (status) { + case 0: + break; + case -ETIMEDOUT: + if (clnt->cl_softrtry) + break; + case -NFS4ERR_DELAY: + case -EAGAIN: + ssleep(1); + case -NFS4ERR_STALE_CLIENTID: + dprintk("NFS: %s after status %d, retrying\n", + __func__, status); + goto again; + case -EACCES: + if (i++ == 0) { + nfs4_root_machine_cred(clp); + goto again; + } + if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX) + break; + case -NFS4ERR_CLID_INUSE: + case -NFS4ERR_WRONGSEC: + /* No point in retrying if we already used RPC_AUTH_UNIX */ + if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX) { + status = -EPERM; + break; + } + clnt = rpc_clone_client_set_auth(clnt, RPC_AUTH_UNIX); + if (IS_ERR(clnt)) { + status = PTR_ERR(clnt); + break; + } + /* Note: this is safe because we haven't yet marked the + * client as ready, so we are the only user of + * clp->cl_rpcclient + */ + clnt = xchg(&clp->cl_rpcclient, clnt); + rpc_shutdown_client(clnt); + clnt = clp->cl_rpcclient; + goto again; + + case -NFS4ERR_MINOR_VERS_MISMATCH: + status = -EPROTONOSUPPORT; + break; + + case -EKEYEXPIRED: + case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery + * in nfs4_exchange_id */ + status = -EKEYEXPIRED; + break; + default: + pr_warn("NFS: %s unhandled error %d. Exiting with error EIO\n", + __func__, status); + status = -EIO; + } + +out_unlock: + mutex_unlock(&nfs_clid_init_mutex); + dprintk("NFS: %s: status = %d\n", __func__, status); + return status; +} + +#ifdef CONFIG_NFS_V4_1 +void nfs4_schedule_session_recovery(struct nfs4_session *session, int err) +{ + struct nfs_client *clp = session->clp; + + switch (err) { + default: + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + break; + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + } + nfs4_schedule_lease_recovery(clp); +} +EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery); + +static void nfs41_ping_server(struct nfs_client *clp) +{ + /* Use CHECK_LEASE to ping the server with a SEQUENCE */ + set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + nfs4_schedule_state_manager(clp); +} + +void nfs41_server_notify_target_slotid_update(struct nfs_client *clp) +{ + nfs41_ping_server(clp); +} + +void nfs41_server_notify_highest_slotid_update(struct nfs_client *clp) +{ + nfs41_ping_server(clp); +} + +static void nfs4_reset_all_state(struct nfs_client *clp) +{ + if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) { + set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + nfs4_state_start_reclaim_nograce(clp); + dprintk("%s: scheduling reset of all state for server %s!\n", + __func__, clp->cl_hostname); + nfs4_schedule_state_manager(clp); + } +} + +static void nfs41_handle_server_reboot(struct nfs_client *clp) +{ + if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) { + nfs4_state_start_reclaim_reboot(clp); + dprintk("%s: server %s rebooted!\n", __func__, + clp->cl_hostname); + nfs4_schedule_state_manager(clp); + } +} + +static void nfs41_handle_state_revoked(struct nfs_client *clp) +{ + nfs4_reset_all_state(clp); + dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname); +} + +static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) +{ + /* This will need to handle layouts too */ + nfs_expire_all_delegations(clp); + dprintk("%s: Recallable state revoked on server %s!\n", __func__, + clp->cl_hostname); +} + +static void nfs41_handle_backchannel_fault(struct nfs_client *clp) +{ + nfs_expire_all_delegations(clp); + if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0) + nfs4_schedule_state_manager(clp); + dprintk("%s: server %s declared a backchannel fault\n", __func__, + clp->cl_hostname); +} + +static void nfs41_handle_cb_path_down(struct nfs_client *clp) +{ + if (test_and_set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, + &clp->cl_state) == 0) + nfs4_schedule_state_manager(clp); +} + +void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) +{ + if (!flags) + return; + + dprintk("%s: \"%s\" (client ID %llx) flags=0x%08x\n", + __func__, clp->cl_hostname, clp->cl_clientid, flags); + + if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) + nfs41_handle_server_reboot(clp); + if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | + SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | + SEQ4_STATUS_ADMIN_STATE_REVOKED)) + nfs41_handle_state_revoked(clp); + if (flags & SEQ4_STATUS_LEASE_MOVED) + nfs4_schedule_lease_moved_recovery(clp); + if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) + nfs41_handle_recallable_state_revoked(clp); + if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT) + nfs41_handle_backchannel_fault(clp); + else if (flags & (SEQ4_STATUS_CB_PATH_DOWN | + SEQ4_STATUS_CB_PATH_DOWN_SESSION)) + nfs41_handle_cb_path_down(clp); +} + +static int nfs4_reset_session(struct nfs_client *clp) +{ + struct rpc_cred *cred; + int status; + + if (!nfs4_has_session(clp)) + return 0; + nfs4_begin_drain_session(clp); + cred = nfs4_get_clid_cred(clp); + status = nfs4_proc_destroy_session(clp->cl_session, cred); + switch (status) { + case 0: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_DEADSESSION: + break; + case -NFS4ERR_BACK_CHAN_BUSY: + case -NFS4ERR_DELAY: + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + status = 0; + ssleep(1); + goto out; + default: + status = nfs4_recovery_handle_error(clp, status); + goto out; + } + + memset(clp->cl_session->sess_id.data, 0, NFS4_MAX_SESSIONID_LEN); + status = nfs4_proc_create_session(clp, cred); + if (status) { + dprintk("%s: session reset failed with status %d for server %s!\n", + __func__, status, clp->cl_hostname); + status = nfs4_handle_reclaim_lease_error(clp, status); + goto out; + } + nfs41_finish_session_reset(clp); + dprintk("%s: session reset was successful for server %s!\n", + __func__, clp->cl_hostname); +out: + if (cred) + put_rpccred(cred); + return status; +} + +static int nfs4_bind_conn_to_session(struct nfs_client *clp) +{ + struct rpc_cred *cred; + int ret; + + if (!nfs4_has_session(clp)) + return 0; + nfs4_begin_drain_session(clp); + cred = nfs4_get_clid_cred(clp); + ret = nfs4_proc_bind_conn_to_session(clp, cred); + if (cred) + put_rpccred(cred); + clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + switch (ret) { + case 0: + dprintk("%s: bind_conn_to_session was successful for server %s!\n", + __func__, clp->cl_hostname); + break; + case -NFS4ERR_DELAY: + ssleep(1); + set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + break; + default: + return nfs4_recovery_handle_error(clp, ret); + } + return 0; +} +#else /* CONFIG_NFS_V4_1 */ +static int nfs4_reset_session(struct nfs_client *clp) { return 0; } + +static int nfs4_bind_conn_to_session(struct nfs_client *clp) +{ + return 0; +} +#endif /* CONFIG_NFS_V4_1 */ + +static void nfs4_state_manager(struct nfs_client *clp) +{ + int status = 0; + const char *section = "", *section_sep = ""; + + /* Ensure exclusive access to NFSv4 state */ + do { + if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) { + section = "purge state"; + status = nfs4_purge_lease(clp); + if (status < 0) + goto out_error; + continue; + } + + if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) { + section = "lease expired"; + /* We're going to have to re-establish a clientid */ + status = nfs4_reclaim_lease(clp); + if (status < 0) + goto out_error; + continue; + } + + /* Initialize or reset the session */ + if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) { + section = "reset session"; + status = nfs4_reset_session(clp); + if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) + continue; + if (status < 0) + goto out_error; + } + + /* Send BIND_CONN_TO_SESSION */ + if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, + &clp->cl_state)) { + section = "bind conn to session"; + status = nfs4_bind_conn_to_session(clp); + if (status < 0) + goto out_error; + continue; + } + + if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) { + section = "check lease"; + status = nfs4_check_lease(clp); + if (status < 0) + goto out_error; + continue; + } + + if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { + section = "migration"; + status = nfs4_handle_migration(clp); + if (status < 0) + goto out_error; + } + + if (test_and_clear_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state)) { + section = "lease moved"; + status = nfs4_handle_lease_moved(clp); + if (status < 0) + goto out_error; + } + + /* First recover reboot state... */ + if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) { + section = "reclaim reboot"; + status = nfs4_do_reclaim(clp, + clp->cl_mvops->reboot_recovery_ops); + if (status == -EAGAIN) + continue; + if (status < 0) + goto out_error; + nfs4_state_end_reclaim_reboot(clp); + } + + /* Now recover expired state... */ + if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) { + section = "reclaim nograce"; + status = nfs4_do_reclaim(clp, + clp->cl_mvops->nograce_recovery_ops); + if (status == -EAGAIN) + continue; + if (status < 0) + goto out_error; + } + + nfs4_end_drain_session(clp); + if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) { + nfs_client_return_marked_delegations(clp); + continue; + } + + nfs4_clear_state_manager_bit(clp); + /* Did we race with an attempt to give us more work? */ + if (clp->cl_state == 0) + break; + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + break; + } while (atomic_read(&clp->cl_count) > 1); + return; +out_error: + if (strlen(section)) + section_sep = ": "; + pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s" + " with error %d\n", section_sep, section, + clp->cl_hostname, -status); + ssleep(1); + nfs4_end_drain_session(clp); + nfs4_clear_state_manager_bit(clp); +} + +static int nfs4_run_state_manager(void *ptr) +{ + struct nfs_client *clp = ptr; + + allow_signal(SIGKILL); + nfs4_state_manager(clp); + nfs_put_client(clp); + module_put_and_exit(0); + return 0; +} + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/kernel/fs/nfs/nfs4super.c b/kernel/fs/nfs/nfs4super.c new file mode 100644 index 000000000..6fb7cb6b3 --- /dev/null +++ b/kernel/fs/nfs/nfs4super.c @@ -0,0 +1,361 @@ +/* + * Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com> + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/nfs4_mount.h> +#include <linux/nfs_fs.h> +#include "delegation.h" +#include "internal.h" +#include "nfs4_fs.h" +#include "nfs4idmap.h" +#include "dns_resolve.h" +#include "pnfs.h" +#include "nfs.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc); +static void nfs4_evict_inode(struct inode *inode); +static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); + +static struct file_system_type nfs4_remote_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs4_remote_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; + +static struct file_system_type nfs4_remote_referral_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs4_remote_referral_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; + +struct file_system_type nfs4_referral_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs4_referral_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; + +static const struct super_operations nfs4_sops = { + .alloc_inode = nfs_alloc_inode, + .destroy_inode = nfs_destroy_inode, + .write_inode = nfs4_write_inode, + .drop_inode = nfs_drop_inode, + .statfs = nfs_statfs, + .evict_inode = nfs4_evict_inode, + .umount_begin = nfs_umount_begin, + .show_options = nfs_show_options, + .show_devname = nfs_show_devname, + .show_path = nfs_show_path, + .show_stats = nfs_show_stats, + .remount_fs = nfs_remount, +}; + +struct nfs_subversion nfs_v4 = { + .owner = THIS_MODULE, + .nfs_fs = &nfs4_fs_type, + .rpc_vers = &nfs_version4, + .rpc_ops = &nfs_v4_clientops, + .sops = &nfs4_sops, + .xattr = nfs4_xattr_handlers, +}; + +static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + int ret = nfs_write_inode(inode, wbc); + + if (ret == 0) + ret = pnfs_layoutcommit_inode(inode, + wbc->sync_mode == WB_SYNC_ALL); + return ret; +} + +/* + * Clean out any remaining NFSv4 state that might be left over due + * to open() calls that passed nfs_atomic_lookup, but failed to call + * nfs_open(). + */ +static void nfs4_evict_inode(struct inode *inode) +{ + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); + /* If we are holding a delegation, return it! */ + nfs_inode_return_delegation_noreclaim(inode); + /* Note that above delegreturn would trigger pnfs return-on-close */ + pnfs_return_layout(inode); + pnfs_destroy_layout(NFS_I(inode)); + /* First call standard NFS clear_inode() code */ + nfs_clear_inode(inode); +} + +/* + * Get the superblock for the NFS4 root partition + */ +static struct dentry * +nfs4_remote_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *info) +{ + struct nfs_mount_info *mount_info = info; + struct nfs_server *server; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + + mount_info->set_security = nfs_set_sb_security; + + /* Get a volume representation */ + server = nfs4_create_server(mount_info, &nfs_v4); + if (IS_ERR(server)) { + mntroot = ERR_CAST(server); + goto out; + } + + mntroot = nfs_fs_mount_common(server, flags, dev_name, mount_info, &nfs_v4); + +out: + return mntroot; +} + +static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, + int flags, void *data, const char *hostname) +{ + struct vfsmount *root_mnt; + char *root_devname; + size_t len; + + len = strlen(hostname) + 5; + root_devname = kmalloc(len, GFP_KERNEL); + if (root_devname == NULL) + return ERR_PTR(-ENOMEM); + /* Does hostname needs to be enclosed in brackets? */ + if (strchr(hostname, ':')) + snprintf(root_devname, len, "[%s]:/", hostname); + else + snprintf(root_devname, len, "%s:/", hostname); + root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data); + kfree(root_devname); + return root_mnt; +} + +struct nfs_referral_count { + struct list_head list; + const struct task_struct *task; + unsigned int referral_count; +}; + +static LIST_HEAD(nfs_referral_count_list); +static DEFINE_SPINLOCK(nfs_referral_count_list_lock); + +static struct nfs_referral_count *nfs_find_referral_count(void) +{ + struct nfs_referral_count *p; + + list_for_each_entry(p, &nfs_referral_count_list, list) { + if (p->task == current) + return p; + } + return NULL; +} + +#define NFS_MAX_NESTED_REFERRALS 2 + +static int nfs_referral_loop_protect(void) +{ + struct nfs_referral_count *p, *new; + int ret = -ENOMEM; + + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + goto out; + new->task = current; + new->referral_count = 1; + + ret = 0; + spin_lock(&nfs_referral_count_list_lock); + p = nfs_find_referral_count(); + if (p != NULL) { + if (p->referral_count >= NFS_MAX_NESTED_REFERRALS) + ret = -ELOOP; + else + p->referral_count++; + } else { + list_add(&new->list, &nfs_referral_count_list); + new = NULL; + } + spin_unlock(&nfs_referral_count_list_lock); + kfree(new); +out: + return ret; +} + +static void nfs_referral_loop_unprotect(void) +{ + struct nfs_referral_count *p; + + spin_lock(&nfs_referral_count_list_lock); + p = nfs_find_referral_count(); + p->referral_count--; + if (p->referral_count == 0) + list_del(&p->list); + else + p = NULL; + spin_unlock(&nfs_referral_count_list_lock); + kfree(p); +} + +static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, + const char *export_path) +{ + struct dentry *dentry; + int err; + + if (IS_ERR(root_mnt)) + return ERR_CAST(root_mnt); + + err = nfs_referral_loop_protect(); + if (err) { + mntput(root_mnt); + return ERR_PTR(err); + } + + dentry = mount_subtree(root_mnt, export_path); + nfs_referral_loop_unprotect(); + + return dentry; +} + +struct dentry *nfs4_try_mount(int flags, const char *dev_name, + struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + char *export_path; + struct vfsmount *root_mnt; + struct dentry *res; + struct nfs_parsed_mount_data *data = mount_info->parsed; + + dfprintk(MOUNT, "--> nfs4_try_mount()\n"); + + export_path = data->nfs_server.export_path; + data->nfs_server.export_path = "/"; + root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, + data->nfs_server.hostname); + data->nfs_server.export_path = export_path; + + res = nfs_follow_remote_path(root_mnt, export_path); + + dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", + PTR_ERR_OR_ZERO(res), + IS_ERR(res) ? " [error]" : ""); + return res; +} + +static struct dentry * +nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + struct nfs_mount_info mount_info = { + .fill_super = nfs_fill_super, + .set_security = nfs_clone_sb_security, + .cloned = raw_data, + }; + struct nfs_server *server; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + + dprintk("--> nfs4_referral_get_sb()\n"); + + mount_info.mntfh = nfs_alloc_fhandle(); + if (mount_info.cloned == NULL || mount_info.mntfh == NULL) + goto out; + + /* create a new volume representation */ + server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh); + if (IS_ERR(server)) { + mntroot = ERR_CAST(server); + goto out; + } + + mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, &nfs_v4); +out: + nfs_free_fhandle(mount_info.mntfh); + return mntroot; +} + +/* + * Create an NFS4 server record on referral traversal + */ +static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_clone_mount *data = raw_data; + char *export_path; + struct vfsmount *root_mnt; + struct dentry *res; + + dprintk("--> nfs4_referral_mount()\n"); + + export_path = data->mnt_path; + data->mnt_path = "/"; + + root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type, + flags, data, data->hostname); + data->mnt_path = export_path; + + res = nfs_follow_remote_path(root_mnt, export_path); + dprintk("<-- nfs4_referral_mount() = %d%s\n", + PTR_ERR_OR_ZERO(res), + IS_ERR(res) ? " [error]" : ""); + return res; +} + + +static int __init init_nfs_v4(void) +{ + int err; + + err = nfs_dns_resolver_init(); + if (err) + goto out; + + err = nfs_idmap_init(); + if (err) + goto out1; + + err = nfs4_register_sysctl(); + if (err) + goto out2; + + register_nfs_version(&nfs_v4); + return 0; +out2: + nfs_idmap_quit(); +out1: + nfs_dns_resolver_destroy(); +out: + return err; +} + +static void __exit exit_nfs_v4(void) +{ + /* Not called in the _init(), conditionally loaded */ + nfs4_pnfs_v3_ds_connect_unload(); + + unregister_nfs_version(&nfs_v4); + nfs4_unregister_sysctl(); + nfs_idmap_quit(); + nfs_dns_resolver_destroy(); +} + +MODULE_LICENSE("GPL"); + +module_init(init_nfs_v4); +module_exit(exit_nfs_v4); diff --git a/kernel/fs/nfs/nfs4sysctl.c b/kernel/fs/nfs/nfs4sysctl.c new file mode 100644 index 000000000..0fbd3ab1b --- /dev/null +++ b/kernel/fs/nfs/nfs4sysctl.c @@ -0,0 +1,69 @@ +/* + * linux/fs/nfs/nfs4sysctl.c + * + * Sysctl interface to NFS v4 parameters + * + * Copyright (c) 2006 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/sysctl.h> +#include <linux/nfs_fs.h> + +#include "nfs4_fs.h" +#include "nfs4idmap.h" +#include "callback.h" + +static const int nfs_set_port_min = 0; +static const int nfs_set_port_max = 65535; +static struct ctl_table_header *nfs4_callback_sysctl_table; + +static struct ctl_table nfs4_cb_sysctls[] = { + { + .procname = "nfs_callback_tcpport", + .data = &nfs_callback_set_tcpport, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (int *)&nfs_set_port_min, + .extra2 = (int *)&nfs_set_port_max, + }, + { + .procname = "idmap_cache_timeout", + .data = &nfs_idmap_cache_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static struct ctl_table nfs4_cb_sysctl_dir[] = { + { + .procname = "nfs", + .mode = 0555, + .child = nfs4_cb_sysctls, + }, + { } +}; + +static struct ctl_table nfs4_cb_sysctl_root[] = { + { + .procname = "fs", + .mode = 0555, + .child = nfs4_cb_sysctl_dir, + }, + { } +}; + +int nfs4_register_sysctl(void) +{ + nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root); + if (nfs4_callback_sysctl_table == NULL) + return -ENOMEM; + return 0; +} + +void nfs4_unregister_sysctl(void) +{ + unregister_sysctl_table(nfs4_callback_sysctl_table); + nfs4_callback_sysctl_table = NULL; +} diff --git a/kernel/fs/nfs/nfs4trace.c b/kernel/fs/nfs/nfs4trace.c new file mode 100644 index 000000000..d774335cc --- /dev/null +++ b/kernel/fs/nfs/nfs4trace.c @@ -0,0 +1,17 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" +#include "internal.h" +#include "nfs4session.h" +#include "callback.h" + +#define CREATE_TRACE_POINTS +#include "nfs4trace.h" + +#ifdef CONFIG_NFS_V4_1 +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_read); +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_write); +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_commit_ds); +#endif diff --git a/kernel/fs/nfs/nfs4trace.h b/kernel/fs/nfs/nfs4trace.h new file mode 100644 index 000000000..470af1a78 --- /dev/null +++ b/kernel/fs/nfs/nfs4trace.h @@ -0,0 +1,1148 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfs4 + +#if !defined(_TRACE_NFS4_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NFS4_H + +#include <linux/tracepoint.h> + +#define show_nfsv4_errors(error) \ + __print_symbolic(error, \ + { NFS4_OK, "OK" }, \ + /* Mapped by nfs4_stat_to_errno() */ \ + { -EPERM, "EPERM" }, \ + { -ENOENT, "ENOENT" }, \ + { -EIO, "EIO" }, \ + { -ENXIO, "ENXIO" }, \ + { -EACCES, "EACCES" }, \ + { -EEXIST, "EEXIST" }, \ + { -EXDEV, "EXDEV" }, \ + { -ENOTDIR, "ENOTDIR" }, \ + { -EISDIR, "EISDIR" }, \ + { -EFBIG, "EFBIG" }, \ + { -ENOSPC, "ENOSPC" }, \ + { -EROFS, "EROFS" }, \ + { -EMLINK, "EMLINK" }, \ + { -ENAMETOOLONG, "ENAMETOOLONG" }, \ + { -ENOTEMPTY, "ENOTEMPTY" }, \ + { -EDQUOT, "EDQUOT" }, \ + { -ESTALE, "ESTALE" }, \ + { -EBADHANDLE, "EBADHANDLE" }, \ + { -EBADCOOKIE, "EBADCOOKIE" }, \ + { -ENOTSUPP, "ENOTSUPP" }, \ + { -ETOOSMALL, "ETOOSMALL" }, \ + { -EREMOTEIO, "EREMOTEIO" }, \ + { -EBADTYPE, "EBADTYPE" }, \ + { -EAGAIN, "EAGAIN" }, \ + { -ELOOP, "ELOOP" }, \ + { -EOPNOTSUPP, "EOPNOTSUPP" }, \ + { -EDEADLK, "EDEADLK" }, \ + /* RPC errors */ \ + { -ENOMEM, "ENOMEM" }, \ + { -EKEYEXPIRED, "EKEYEXPIRED" }, \ + { -ETIMEDOUT, "ETIMEDOUT" }, \ + { -ERESTARTSYS, "ERESTARTSYS" }, \ + { -ECONNREFUSED, "ECONNREFUSED" }, \ + { -ECONNRESET, "ECONNRESET" }, \ + { -ENETUNREACH, "ENETUNREACH" }, \ + { -EHOSTUNREACH, "EHOSTUNREACH" }, \ + { -EHOSTDOWN, "EHOSTDOWN" }, \ + { -EPIPE, "EPIPE" }, \ + { -EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { -EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + /* NFSv4 native errors */ \ + { -NFS4ERR_ACCESS, "ACCESS" }, \ + { -NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { -NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { -NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { -NFS4ERR_BADCHAR, "BADCHAR" }, \ + { -NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { -NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { -NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { -NFS4ERR_BADLABEL, "BADLABEL" }, \ + { -NFS4ERR_BADNAME, "BADNAME" }, \ + { -NFS4ERR_BADOWNER, "BADOWNER" }, \ + { -NFS4ERR_BADSESSION, "BADSESSION" }, \ + { -NFS4ERR_BADSLOT, "BADSLOT" }, \ + { -NFS4ERR_BADTYPE, "BADTYPE" }, \ + { -NFS4ERR_BADXDR, "BADXDR" }, \ + { -NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { -NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { -NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { -NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { -NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { -NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { -NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { -NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { -NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { -NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { -NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ + "CONN_NOT_BOUND_TO_SESSION" }, \ + { -NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { -NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { -NFS4ERR_DELAY, "DELAY" }, \ + { -NFS4ERR_DELEG_ALREADY_WANTED, \ + "DELEG_ALREADY_WANTED" }, \ + { -NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { -NFS4ERR_DENIED, "DENIED" }, \ + { -NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { -NFS4ERR_DQUOT, "DQUOT" }, \ + { -NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { -NFS4ERR_EXIST, "EXIST" }, \ + { -NFS4ERR_EXPIRED, "EXPIRED" }, \ + { -NFS4ERR_FBIG, "FBIG" }, \ + { -NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { -NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { -NFS4ERR_GRACE, "GRACE" }, \ + { -NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { -NFS4ERR_INVAL, "INVAL" }, \ + { -NFS4ERR_IO, "IO" }, \ + { -NFS4ERR_ISDIR, "ISDIR" }, \ + { -NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { -NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { -NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { -NFS4ERR_LOCKED, "LOCKED" }, \ + { -NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { -NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { -NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { -NFS4ERR_MLINK, "MLINK" }, \ + { -NFS4ERR_MOVED, "MOVED" }, \ + { -NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { -NFS4ERR_NOENT, "NOENT" }, \ + { -NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { -NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { -NFS4ERR_NOSPC, "NOSPC" }, \ + { -NFS4ERR_NOTDIR, "NOTDIR" }, \ + { -NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { -NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { -NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { -NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { -NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { -NFS4ERR_NXIO, "NXIO" }, \ + { -NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { -NFS4ERR_OPENMODE, "OPENMODE" }, \ + { -NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { -NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { -NFS4ERR_PERM, "PERM" }, \ + { -NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { -NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { -NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { -NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { -NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { -NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { -NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { -NFS4ERR_REP_TOO_BIG_TO_CACHE, \ + "REP_TOO_BIG_TO_CACHE" }, \ + { -NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { -NFS4ERR_RESOURCE, "RESOURCE" }, \ + { -NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { -NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { -NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { -NFS4ERR_ROFS, "ROFS" }, \ + { -NFS4ERR_SAME, "SAME" }, \ + { -NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { -NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { -NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { -NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { -NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { -NFS4ERR_STALE, "STALE" }, \ + { -NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { -NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { -NFS4ERR_SYMLINK, "SYMLINK" }, \ + { -NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { -NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { -NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { -NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { -NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { -NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { -NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { -NFS4ERR_XDEV, "XDEV" }) + +#define show_open_flags(flags) \ + __print_flags(flags, "|", \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_DIRECT, "O_DIRECT" }) + +#define show_fmode_flags(mode) \ + __print_flags(mode, "|", \ + { ((__force unsigned long)FMODE_READ), "READ" }, \ + { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ + { ((__force unsigned long)FMODE_EXEC), "EXEC" }) + +#define show_nfs_fattr_flags(valid) \ + __print_flags((unsigned long)valid, "|", \ + { NFS_ATTR_FATTR_TYPE, "TYPE" }, \ + { NFS_ATTR_FATTR_MODE, "MODE" }, \ + { NFS_ATTR_FATTR_NLINK, "NLINK" }, \ + { NFS_ATTR_FATTR_OWNER, "OWNER" }, \ + { NFS_ATTR_FATTR_GROUP, "GROUP" }, \ + { NFS_ATTR_FATTR_RDEV, "RDEV" }, \ + { NFS_ATTR_FATTR_SIZE, "SIZE" }, \ + { NFS_ATTR_FATTR_FSID, "FSID" }, \ + { NFS_ATTR_FATTR_FILEID, "FILEID" }, \ + { NFS_ATTR_FATTR_ATIME, "ATIME" }, \ + { NFS_ATTR_FATTR_MTIME, "MTIME" }, \ + { NFS_ATTR_FATTR_CTIME, "CTIME" }, \ + { NFS_ATTR_FATTR_CHANGE, "CHANGE" }, \ + { NFS_ATTR_FATTR_OWNER_NAME, "OWNER_NAME" }, \ + { NFS_ATTR_FATTR_GROUP_NAME, "GROUP_NAME" }) + +DECLARE_EVENT_CLASS(nfs4_clientid_event, + TP_PROTO( + const struct nfs_client *clp, + int error + ), + + TP_ARGS(clp, error), + + TP_STRUCT__entry( + __string(dstaddr, + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR)) + __field(int, error) + ), + + TP_fast_assign( + __entry->error = error; + __assign_str(dstaddr, + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR)); + ), + + TP_printk( + "error=%d (%s) dstaddr=%s", + __entry->error, + show_nfsv4_errors(__entry->error), + __get_str(dstaddr) + ) +); +#define DEFINE_NFS4_CLIENTID_EVENT(name) \ + DEFINE_EVENT(nfs4_clientid_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp, \ + int error \ + ), \ + TP_ARGS(clp, error)) +DEFINE_NFS4_CLIENTID_EVENT(nfs4_setclientid); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_setclientid_confirm); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_renew); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_renew_async); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_CLIENTID_EVENT(nfs4_exchange_id); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_create_session); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_destroy_session); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_destroy_clientid); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete); + +TRACE_EVENT(nfs4_setup_sequence, + TP_PROTO( + const struct nfs4_session *session, + const struct nfs4_sequence_args *args + ), + TP_ARGS(session, args), + + TP_STRUCT__entry( + __field(unsigned int, session) + __field(unsigned int, slot_nr) + __field(unsigned int, seq_nr) + __field(unsigned int, highest_used_slotid) + ), + + TP_fast_assign( + const struct nfs4_slot *sa_slot = args->sa_slot; + __entry->session = nfs_session_id_hash(&session->sess_id); + __entry->slot_nr = sa_slot->slot_nr; + __entry->seq_nr = sa_slot->seq_nr; + __entry->highest_used_slotid = + sa_slot->table->highest_used_slotid; + ), + TP_printk( + "session=0x%08x slot_nr=%u seq_nr=%u " + "highest_used_slotid=%u", + __entry->session, + __entry->slot_nr, + __entry->seq_nr, + __entry->highest_used_slotid + ) +); + +#define show_nfs4_sequence_status_flags(status) \ + __print_flags((unsigned long)status, "|", \ + { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, \ + "CB_GSS_CONTEXTS_EXPIRING" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, \ + "CB_GSS_CONTEXTS_EXPIRED" }, \ + { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, \ + "EXPIRED_ALL_STATE_REVOKED" }, \ + { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, \ + "EXPIRED_SOME_STATE_REVOKED" }, \ + { SEQ4_STATUS_ADMIN_STATE_REVOKED, \ + "ADMIN_STATE_REVOKED" }, \ + { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, \ + "RECALLABLE_STATE_REVOKED" }, \ + { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ + { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, \ + "RESTART_RECLAIM_NEEDED" }, \ + { SEQ4_STATUS_CB_PATH_DOWN_SESSION, \ + "CB_PATH_DOWN_SESSION" }, \ + { SEQ4_STATUS_BACKCHANNEL_FAULT, \ + "BACKCHANNEL_FAULT" }) + +TRACE_EVENT(nfs4_sequence_done, + TP_PROTO( + const struct nfs4_session *session, + const struct nfs4_sequence_res *res + ), + TP_ARGS(session, res), + + TP_STRUCT__entry( + __field(unsigned int, session) + __field(unsigned int, slot_nr) + __field(unsigned int, seq_nr) + __field(unsigned int, highest_slotid) + __field(unsigned int, target_highest_slotid) + __field(unsigned int, status_flags) + __field(int, error) + ), + + TP_fast_assign( + const struct nfs4_slot *sr_slot = res->sr_slot; + __entry->session = nfs_session_id_hash(&session->sess_id); + __entry->slot_nr = sr_slot->slot_nr; + __entry->seq_nr = sr_slot->seq_nr; + __entry->highest_slotid = res->sr_highest_slotid; + __entry->target_highest_slotid = + res->sr_target_highest_slotid; + __entry->error = res->sr_status; + ), + TP_printk( + "error=%d (%s) session=0x%08x slot_nr=%u seq_nr=%u " + "highest_slotid=%u target_highest_slotid=%u " + "status_flags=%u (%s)", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->session, + __entry->slot_nr, + __entry->seq_nr, + __entry->highest_slotid, + __entry->target_highest_slotid, + __entry->status_flags, + show_nfs4_sequence_status_flags(__entry->status_flags) + ) +); + +struct cb_sequenceargs; +struct cb_sequenceres; + +TRACE_EVENT(nfs4_cb_sequence, + TP_PROTO( + const struct cb_sequenceargs *args, + const struct cb_sequenceres *res, + __be32 status + ), + TP_ARGS(args, res, status), + + TP_STRUCT__entry( + __field(unsigned int, session) + __field(unsigned int, slot_nr) + __field(unsigned int, seq_nr) + __field(unsigned int, highest_slotid) + __field(unsigned int, cachethis) + __field(int, error) + ), + + TP_fast_assign( + __entry->session = nfs_session_id_hash(&args->csa_sessionid); + __entry->slot_nr = args->csa_slotid; + __entry->seq_nr = args->csa_sequenceid; + __entry->highest_slotid = args->csa_highestslotid; + __entry->cachethis = args->csa_cachethis; + __entry->error = -be32_to_cpu(status); + ), + + TP_printk( + "error=%d (%s) session=0x%08x slot_nr=%u seq_nr=%u " + "highest_slotid=%u", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->session, + __entry->slot_nr, + __entry->seq_nr, + __entry->highest_slotid + ) +); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_open_event, + TP_PROTO( + const struct nfs_open_context *ctx, + int flags, + int error + ), + + TP_ARGS(ctx, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(unsigned int, fmode) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, dir) + __string(name, ctx->dentry->d_name.name) + ), + + TP_fast_assign( + const struct nfs4_state *state = ctx->state; + const struct inode *inode = NULL; + + __entry->error = error; + __entry->flags = flags; + __entry->fmode = (__force unsigned int)ctx->mode; + __entry->dev = ctx->dentry->d_sb->s_dev; + if (!IS_ERR(state)) + inode = state->inode; + if (inode != NULL) { + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + } else { + __entry->fileid = 0; + __entry->fhandle = 0; + } + __entry->dir = NFS_FILEID(d_inode(ctx->dentry->d_parent)); + __assign_str(name, ctx->dentry->d_name.name); + ), + + TP_printk( + "error=%d (%s) flags=%d (%s) fmode=%s " + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "name=%02x:%02x:%llu/%s", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->flags, + show_open_flags(__entry->flags), + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS4_OPEN_EVENT(name) \ + DEFINE_EVENT(nfs4_open_event, name, \ + TP_PROTO( \ + const struct nfs_open_context *ctx, \ + int flags, \ + int error \ + ), \ + TP_ARGS(ctx, flags, error)) +DEFINE_NFS4_OPEN_EVENT(nfs4_open_reclaim); +DEFINE_NFS4_OPEN_EVENT(nfs4_open_expired); +DEFINE_NFS4_OPEN_EVENT(nfs4_open_file); + +TRACE_EVENT(nfs4_close, + TP_PROTO( + const struct nfs4_state *state, + const struct nfs_closeargs *args, + const struct nfs_closeres *res, + int error + ), + + TP_ARGS(state, args, res, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, fmode) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fmode = (__force unsigned int)state->state; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fmode=%s fileid=%02x:%02x:%llu " + "fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->fmode ? show_fmode_flags(__entry->fmode) : + "closed", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define show_lock_cmd(type) \ + __print_symbolic((int)type, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }) +#define show_lock_type(type) \ + __print_symbolic((int)type, \ + { F_RDLCK, "RDLCK" }, \ + { F_WRLCK, "WRLCK" }, \ + { F_UNLCK, "UNLCK" }) + +DECLARE_EVENT_CLASS(nfs4_lock_event, + TP_PROTO( + const struct file_lock *request, + const struct nfs4_state *state, + int cmd, + int error + ), + + TP_ARGS(request, state, cmd, error), + + TP_STRUCT__entry( + __field(int, error) + __field(int, cmd) + __field(char, type) + __field(loff_t, start) + __field(loff_t, end) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->error = error; + __entry->cmd = cmd; + __entry->type = request->fl_type; + __entry->start = request->fl_start; + __entry->end = request->fl_end; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + ), + + TP_printk( + "error=%d (%s) cmd=%s:%s range=%lld:%lld " + "fileid=%02x:%02x:%llu fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + show_lock_cmd(__entry->cmd), + show_lock_type(__entry->type), + (long long)__entry->start, + (long long)__entry->end, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define DEFINE_NFS4_LOCK_EVENT(name) \ + DEFINE_EVENT(nfs4_lock_event, name, \ + TP_PROTO( \ + const struct file_lock *request, \ + const struct nfs4_state *state, \ + int cmd, \ + int error \ + ), \ + TP_ARGS(request, state, cmd, error)) +DEFINE_NFS4_LOCK_EVENT(nfs4_get_lock); +DEFINE_NFS4_LOCK_EVENT(nfs4_set_lock); +DEFINE_NFS4_LOCK_EVENT(nfs4_lock_reclaim); +DEFINE_NFS4_LOCK_EVENT(nfs4_lock_expired); +DEFINE_NFS4_LOCK_EVENT(nfs4_unlock); + +DECLARE_EVENT_CLASS(nfs4_set_delegation_event, + TP_PROTO( + const struct inode *inode, + fmode_t fmode + ), + + TP_ARGS(inode, fmode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, fmode) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fmode = (__force unsigned int)fmode; + ), + + TP_printk( + "fmode=%s fileid=%02x:%02x:%llu fhandle=0x%08x", + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); +#define DEFINE_NFS4_SET_DELEGATION_EVENT(name) \ + DEFINE_EVENT(nfs4_set_delegation_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + fmode_t fmode \ + ), \ + TP_ARGS(inode, fmode)) +DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_set_delegation); +DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_reclaim_delegation); + +TRACE_EVENT(nfs4_delegreturn_exit, + TP_PROTO( + const struct nfs4_delegreturnargs *args, + const struct nfs4_delegreturnres *res, + int error + ), + + TP_ARGS(args, res, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = res->server->s_dev; + __entry->fhandle = nfs_fhandle_hash(args->fhandle); + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) dev=%02x:%02x fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->fhandle + ) +); + +#ifdef CONFIG_NFS_V4_1 +DECLARE_EVENT_CLASS(nfs4_test_stateid_event, + TP_PROTO( + const struct nfs4_state *state, + const struct nfs4_lock_state *lsp, + int error + ), + + TP_ARGS(state, lsp, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->error = error; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define DEFINE_NFS4_TEST_STATEID_EVENT(name) \ + DEFINE_EVENT(nfs4_test_stateid_event, name, \ + TP_PROTO( \ + const struct nfs4_state *state, \ + const struct nfs4_lock_state *lsp, \ + int error \ + ), \ + TP_ARGS(state, lsp, error)) +DEFINE_NFS4_TEST_STATEID_EVENT(nfs4_test_delegation_stateid); +DEFINE_NFS4_TEST_STATEID_EVENT(nfs4_test_open_stateid); +DEFINE_NFS4_TEST_STATEID_EVENT(nfs4_test_lock_stateid); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_lookup_event, + TP_PROTO( + const struct inode *dir, + const struct qstr *name, + int error + ), + + TP_ARGS(dir, name, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, dir) + __string(name, name->name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __assign_str(name, name->name); + ), + + TP_printk( + "error=%d (%s) name=%02x:%02x:%llu/%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS4_LOOKUP_EVENT(name) \ + DEFINE_EVENT(nfs4_lookup_event, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct qstr *name, \ + int error \ + ), \ + TP_ARGS(dir, name, error)) + +DEFINE_NFS4_LOOKUP_EVENT(nfs4_lookup); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_symlink); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_mkdir); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_mknod); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_remove); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_get_fs_locations); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_secinfo); + +TRACE_EVENT(nfs4_rename, + TP_PROTO( + const struct inode *olddir, + const struct qstr *oldname, + const struct inode *newdir, + const struct qstr *newname, + int error + ), + + TP_ARGS(olddir, oldname, newdir, newname, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, olddir) + __string(oldname, oldname->name) + __field(u64, newdir) + __string(newname, newname->name) + ), + + TP_fast_assign( + __entry->dev = olddir->i_sb->s_dev; + __entry->olddir = NFS_FILEID(olddir); + __entry->newdir = NFS_FILEID(newdir); + __entry->error = error; + __assign_str(oldname, oldname->name); + __assign_str(newname, newname->name); + ), + + TP_printk( + "error=%d (%s) oldname=%02x:%02x:%llu/%s " + "newname=%02x:%02x:%llu/%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->olddir, + __get_str(oldname), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->newdir, + __get_str(newname) + ) +); + +DECLARE_EVENT_CLASS(nfs4_inode_event, + TP_PROTO( + const struct inode *inode, + int error + ), + + TP_ARGS(inode, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define DEFINE_NFS4_INODE_EVENT(name) \ + DEFINE_EVENT(nfs4_inode_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + int error \ + ), \ + TP_ARGS(inode, error)) + +DEFINE_NFS4_INODE_EVENT(nfs4_setattr); +DEFINE_NFS4_INODE_EVENT(nfs4_access); +DEFINE_NFS4_INODE_EVENT(nfs4_readlink); +DEFINE_NFS4_INODE_EVENT(nfs4_readdir); +DEFINE_NFS4_INODE_EVENT(nfs4_get_acl); +DEFINE_NFS4_INODE_EVENT(nfs4_set_acl); +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +DEFINE_NFS4_INODE_EVENT(nfs4_get_security_label); +DEFINE_NFS4_INODE_EVENT(nfs4_set_security_label); +#endif /* CONFIG_NFS_V4_SECURITY_LABEL */ +DEFINE_NFS4_INODE_EVENT(nfs4_recall_delegation); +DEFINE_NFS4_INODE_EVENT(nfs4_delegreturn); + +DECLARE_EVENT_CLASS(nfs4_getattr_event, + TP_PROTO( + const struct nfs_server *server, + const struct nfs_fh *fhandle, + const struct nfs_fattr *fattr, + int error + ), + + TP_ARGS(server, fhandle, fattr, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, valid) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = server->s_dev; + __entry->valid = fattr->valid; + __entry->fhandle = nfs_fhandle_hash(fhandle); + __entry->fileid = (fattr->valid & NFS_ATTR_FATTR_FILEID) ? fattr->fileid : 0; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "valid=%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_nfs_fattr_flags(__entry->valid) + ) +); + +#define DEFINE_NFS4_GETATTR_EVENT(name) \ + DEFINE_EVENT(nfs4_getattr_event, name, \ + TP_PROTO( \ + const struct nfs_server *server, \ + const struct nfs_fh *fhandle, \ + const struct nfs_fattr *fattr, \ + int error \ + ), \ + TP_ARGS(server, fhandle, fattr, error)) +DEFINE_NFS4_GETATTR_EVENT(nfs4_getattr); +DEFINE_NFS4_GETATTR_EVENT(nfs4_lookup_root); +DEFINE_NFS4_GETATTR_EVENT(nfs4_fsinfo); + +DECLARE_EVENT_CLASS(nfs4_idmap_event, + TP_PROTO( + const char *name, + int len, + u32 id, + int error + ), + + TP_ARGS(name, len, id, error), + + TP_STRUCT__entry( + __field(int, error) + __field(u32, id) + __dynamic_array(char, name, len > 0 ? len + 1 : 1) + ), + + TP_fast_assign( + if (len < 0) + len = 0; + __entry->error = error < 0 ? error : 0; + __entry->id = id; + memcpy(__get_dynamic_array(name), name, len); + ((char *)__get_dynamic_array(name))[len] = 0; + ), + + TP_printk( + "error=%d id=%u name=%s", + __entry->error, + __entry->id, + __get_str(name) + ) +); +#define DEFINE_NFS4_IDMAP_EVENT(name) \ + DEFINE_EVENT(nfs4_idmap_event, name, \ + TP_PROTO( \ + const char *name, \ + int len, \ + u32 id, \ + int error \ + ), \ + TP_ARGS(name, len, id, error)) +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_name_to_uid); +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_group_to_gid); +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_uid_to_name); +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group); + +DECLARE_EVENT_CLASS(nfs4_read_event, + TP_PROTO( + const struct nfs_pgio_header *hdr, + int error + ), + + TP_ARGS(hdr, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(size_t, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = hdr->inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->offset = hdr->args.offset; + __entry->count = hdr->args.count; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, + __entry->count + ) +); +#define DEFINE_NFS4_READ_EVENT(name) \ + DEFINE_EVENT(nfs4_read_event, name, \ + TP_PROTO( \ + const struct nfs_pgio_header *hdr, \ + int error \ + ), \ + TP_ARGS(hdr, error)) +DEFINE_NFS4_READ_EVENT(nfs4_read); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_write_event, + TP_PROTO( + const struct nfs_pgio_header *hdr, + int error + ), + + TP_ARGS(hdr, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(size_t, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = hdr->inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->offset = hdr->args.offset; + __entry->count = hdr->args.count; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, + __entry->count + ) +); + +#define DEFINE_NFS4_WRITE_EVENT(name) \ + DEFINE_EVENT(nfs4_write_event, name, \ + TP_PROTO( \ + const struct nfs_pgio_header *hdr, \ + int error \ + ), \ + TP_ARGS(hdr, error)) +DEFINE_NFS4_WRITE_EVENT(nfs4_write); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_WRITE_EVENT(nfs4_pnfs_write); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_commit_event, + TP_PROTO( + const struct nfs_commit_data *data, + int error + ), + + TP_ARGS(data, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(size_t, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = data->inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->offset = data->args.offset; + __entry->count = data->args.count; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, + __entry->count + ) +); +#define DEFINE_NFS4_COMMIT_EVENT(name) \ + DEFINE_EVENT(nfs4_commit_event, name, \ + TP_PROTO( \ + const struct nfs_commit_data *data, \ + int error \ + ), \ + TP_ARGS(data, error)) +DEFINE_NFS4_COMMIT_EVENT(nfs4_commit); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds); + +#define show_pnfs_iomode(iomode) \ + __print_symbolic(iomode, \ + { IOMODE_READ, "READ" }, \ + { IOMODE_RW, "RW" }, \ + { IOMODE_ANY, "ANY" }) + +TRACE_EVENT(nfs4_layoutget, + TP_PROTO( + const struct nfs_open_context *ctx, + const struct pnfs_layout_range *args, + const struct pnfs_layout_range *res, + int error + ), + + TP_ARGS(ctx, args, res, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u32, iomode) + __field(u64, offset) + __field(u64, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = d_inode(ctx->dentry); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->iomode = args->iomode; + __entry->offset = args->offset; + __entry->count = args->length; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "iomode=%s offset=%llu count=%llu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_pnfs_iomode(__entry->iomode), + (unsigned long long)__entry->offset, + (unsigned long long)__entry->count + ) +); + +DEFINE_NFS4_INODE_EVENT(nfs4_layoutcommit); +DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn); + +#endif /* CONFIG_NFS_V4_1 */ + +#endif /* _TRACE_NFS4_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE nfs4trace +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/kernel/fs/nfs/nfs4xdr.c b/kernel/fs/nfs/nfs4xdr.c new file mode 100644 index 000000000..0aea97841 --- /dev/null +++ b/kernel/fs/nfs/nfs4xdr.c @@ -0,0 +1,7443 @@ +/* + * fs/nfs/nfs4xdr.c + * + * Client-side XDR for NFSv4. + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Kendrick Smith <kmsmith@umich.edu> + * Andy Adamson <andros@umich.edu> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/param.h> +#include <linux/time.h> +#include <linux/mm.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/pagemap.h> +#include <linux/proc_fs.h> +#include <linux/kdev_t.h> +#include <linux/module.h> +#include <linux/utsname.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/msg_prot.h> +#include <linux/sunrpc/gss_api.h> +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <linux/nfs_fs.h> + +#include "nfs4_fs.h" +#include "internal.h" +#include "nfs4idmap.h" +#include "nfs4session.h" +#include "pnfs.h" +#include "netns.h" + +#define NFSDBG_FACILITY NFSDBG_XDR + +/* Mapping from NFS error code to "errno" error code. */ +#define errno_NFSERR_IO EIO + +static int nfs4_stat_to_errno(int); + +/* NFSv4 COMPOUND tags are only wanted for debugging purposes */ +#ifdef DEBUG +#define NFS4_MAXTAGLEN 20 +#else +#define NFS4_MAXTAGLEN 0 +#endif + +/* lock,open owner id: + * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT >> 2) + */ +#define open_owner_id_maxsz (1 + 2 + 1 + 1 + 2) +#define lock_owner_id_maxsz (1 + 1 + 4) +#define decode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +#define compound_encode_hdr_maxsz (3 + (NFS4_MAXTAGLEN >> 2)) +#define compound_decode_hdr_maxsz (3 + (NFS4_MAXTAGLEN >> 2)) +#define op_encode_hdr_maxsz (1) +#define op_decode_hdr_maxsz (2) +#define encode_stateid_maxsz (XDR_QUADLEN(NFS4_STATEID_SIZE)) +#define decode_stateid_maxsz (XDR_QUADLEN(NFS4_STATEID_SIZE)) +#define encode_verifier_maxsz (XDR_QUADLEN(NFS4_VERIFIER_SIZE)) +#define decode_verifier_maxsz (XDR_QUADLEN(NFS4_VERIFIER_SIZE)) +#define encode_putfh_maxsz (op_encode_hdr_maxsz + 1 + \ + (NFS4_FHSIZE >> 2)) +#define decode_putfh_maxsz (op_decode_hdr_maxsz) +#define encode_putrootfh_maxsz (op_encode_hdr_maxsz) +#define decode_putrootfh_maxsz (op_decode_hdr_maxsz) +#define encode_getfh_maxsz (op_encode_hdr_maxsz) +#define decode_getfh_maxsz (op_decode_hdr_maxsz + 1 + \ + ((3+NFS4_FHSIZE) >> 2)) +#define nfs4_fattr_bitmap_maxsz 4 +#define encode_getattr_maxsz (op_encode_hdr_maxsz + nfs4_fattr_bitmap_maxsz) +#define nfs4_name_maxsz (1 + ((3 + NFS4_MAXNAMLEN) >> 2)) +#define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2)) +#define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +#define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +/* PI(4 bytes) + LFS(4 bytes) + 1(for null terminator?) + MAXLABELLEN */ +#define nfs4_label_maxsz (4 + 4 + 1 + XDR_QUADLEN(NFS4_MAXLABELLEN)) +#else +#define nfs4_label_maxsz 0 +#endif +/* We support only one layout type per file system */ +#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8) +/* This is based on getfattr, which uses the most attributes: */ +#define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \ + 3 + 3 + 3 + nfs4_owner_maxsz + \ + nfs4_group_maxsz + nfs4_label_maxsz + \ + decode_mdsthreshold_maxsz)) +#define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \ + nfs4_fattr_value_maxsz) +#define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz) +#define encode_attrs_maxsz (nfs4_fattr_bitmap_maxsz + \ + 1 + 2 + 1 + \ + nfs4_owner_maxsz + \ + nfs4_group_maxsz + \ + nfs4_label_maxsz + \ + 4 + 4) +#define encode_savefh_maxsz (op_encode_hdr_maxsz) +#define decode_savefh_maxsz (op_decode_hdr_maxsz) +#define encode_restorefh_maxsz (op_encode_hdr_maxsz) +#define decode_restorefh_maxsz (op_decode_hdr_maxsz) +#define encode_fsinfo_maxsz (encode_getattr_maxsz) +/* The 5 accounts for the PNFS attributes, and assumes that at most three + * layout types will be returned. + */ +#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + \ + nfs4_fattr_bitmap_maxsz + 4 + 8 + 5) +#define encode_renew_maxsz (op_encode_hdr_maxsz + 3) +#define decode_renew_maxsz (op_decode_hdr_maxsz) +#define encode_setclientid_maxsz \ + (op_encode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \ + XDR_QUADLEN(NFS4_SETCLIENTID_NAMELEN) + \ + 1 /* sc_prog */ + \ + 1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN) + \ + 1) /* sc_cb_ident */ +#define decode_setclientid_maxsz \ + (op_decode_hdr_maxsz + \ + 2 /* clientid */ + \ + XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) +#define encode_setclientid_confirm_maxsz \ + (op_encode_hdr_maxsz + \ + 3 + (NFS4_VERIFIER_SIZE >> 2)) +#define decode_setclientid_confirm_maxsz \ + (op_decode_hdr_maxsz) +#define encode_lookup_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) +#define decode_lookup_maxsz (op_decode_hdr_maxsz) +#define encode_share_access_maxsz \ + (2) +#define encode_createmode_maxsz (1 + encode_attrs_maxsz + encode_verifier_maxsz) +#define encode_opentype_maxsz (1 + encode_createmode_maxsz) +#define encode_claim_null_maxsz (1 + nfs4_name_maxsz) +#define encode_open_maxsz (op_encode_hdr_maxsz + \ + 2 + encode_share_access_maxsz + 2 + \ + open_owner_id_maxsz + \ + encode_opentype_maxsz + \ + encode_claim_null_maxsz) +#define decode_ace_maxsz (3 + nfs4_owner_maxsz) +#define decode_delegation_maxsz (1 + decode_stateid_maxsz + 1 + \ + decode_ace_maxsz) +#define decode_change_info_maxsz (5) +#define decode_open_maxsz (op_decode_hdr_maxsz + \ + decode_stateid_maxsz + \ + decode_change_info_maxsz + 1 + \ + nfs4_fattr_bitmap_maxsz + \ + decode_delegation_maxsz) +#define encode_open_confirm_maxsz \ + (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + 1) +#define decode_open_confirm_maxsz \ + (op_decode_hdr_maxsz + \ + decode_stateid_maxsz) +#define encode_open_downgrade_maxsz \ + (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + 1 + \ + encode_share_access_maxsz) +#define decode_open_downgrade_maxsz \ + (op_decode_hdr_maxsz + \ + decode_stateid_maxsz) +#define encode_close_maxsz (op_encode_hdr_maxsz + \ + 1 + encode_stateid_maxsz) +#define decode_close_maxsz (op_decode_hdr_maxsz + \ + decode_stateid_maxsz) +#define encode_setattr_maxsz (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + \ + encode_attrs_maxsz) +#define decode_setattr_maxsz (op_decode_hdr_maxsz + \ + nfs4_fattr_bitmap_maxsz) +#define encode_read_maxsz (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + 3) +#define decode_read_maxsz (op_decode_hdr_maxsz + 2) +#define encode_readdir_maxsz (op_encode_hdr_maxsz + \ + 2 + encode_verifier_maxsz + 5 + \ + nfs4_label_maxsz) +#define decode_readdir_maxsz (op_decode_hdr_maxsz + \ + decode_verifier_maxsz) +#define encode_readlink_maxsz (op_encode_hdr_maxsz) +#define decode_readlink_maxsz (op_decode_hdr_maxsz + 1) +#define encode_write_maxsz (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + 4) +#define decode_write_maxsz (op_decode_hdr_maxsz + \ + 2 + decode_verifier_maxsz) +#define encode_commit_maxsz (op_encode_hdr_maxsz + 3) +#define decode_commit_maxsz (op_decode_hdr_maxsz + \ + decode_verifier_maxsz) +#define encode_remove_maxsz (op_encode_hdr_maxsz + \ + nfs4_name_maxsz) +#define decode_remove_maxsz (op_decode_hdr_maxsz + \ + decode_change_info_maxsz) +#define encode_rename_maxsz (op_encode_hdr_maxsz + \ + 2 * nfs4_name_maxsz) +#define decode_rename_maxsz (op_decode_hdr_maxsz + \ + decode_change_info_maxsz + \ + decode_change_info_maxsz) +#define encode_link_maxsz (op_encode_hdr_maxsz + \ + nfs4_name_maxsz) +#define decode_link_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz) +#define encode_lockowner_maxsz (7) +#define encode_lock_maxsz (op_encode_hdr_maxsz + \ + 7 + \ + 1 + encode_stateid_maxsz + 1 + \ + encode_lockowner_maxsz) +#define decode_lock_denied_maxsz \ + (8 + decode_lockowner_maxsz) +#define decode_lock_maxsz (op_decode_hdr_maxsz + \ + decode_lock_denied_maxsz) +#define encode_lockt_maxsz (op_encode_hdr_maxsz + 5 + \ + encode_lockowner_maxsz) +#define decode_lockt_maxsz (op_decode_hdr_maxsz + \ + decode_lock_denied_maxsz) +#define encode_locku_maxsz (op_encode_hdr_maxsz + 3 + \ + encode_stateid_maxsz + \ + 4) +#define decode_locku_maxsz (op_decode_hdr_maxsz + \ + decode_stateid_maxsz) +#define encode_release_lockowner_maxsz \ + (op_encode_hdr_maxsz + \ + encode_lockowner_maxsz) +#define decode_release_lockowner_maxsz \ + (op_decode_hdr_maxsz) +#define encode_access_maxsz (op_encode_hdr_maxsz + 1) +#define decode_access_maxsz (op_decode_hdr_maxsz + 2) +#define encode_symlink_maxsz (op_encode_hdr_maxsz + \ + 1 + nfs4_name_maxsz + \ + 1 + \ + nfs4_fattr_maxsz) +#define decode_symlink_maxsz (op_decode_hdr_maxsz + 8) +#define encode_create_maxsz (op_encode_hdr_maxsz + \ + 1 + 2 + nfs4_name_maxsz + \ + encode_attrs_maxsz) +#define decode_create_maxsz (op_decode_hdr_maxsz + \ + decode_change_info_maxsz + \ + nfs4_fattr_bitmap_maxsz) +#define encode_statfs_maxsz (encode_getattr_maxsz) +#define decode_statfs_maxsz (decode_getattr_maxsz) +#define encode_delegreturn_maxsz (op_encode_hdr_maxsz + 4) +#define decode_delegreturn_maxsz (op_decode_hdr_maxsz) +#define encode_getacl_maxsz (encode_getattr_maxsz) +#define decode_getacl_maxsz (op_decode_hdr_maxsz + \ + nfs4_fattr_bitmap_maxsz + 1) +#define encode_setacl_maxsz (op_encode_hdr_maxsz + \ + encode_stateid_maxsz + 3) +#define decode_setacl_maxsz (decode_setattr_maxsz) +#define encode_fs_locations_maxsz \ + (encode_getattr_maxsz) +#define decode_fs_locations_maxsz \ + (0) +#define encode_secinfo_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) +#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4)) + +#if defined(CONFIG_NFS_V4_1) +#define NFS4_MAX_MACHINE_NAME_LEN (64) +#define IMPL_NAME_LIMIT (sizeof(utsname()->sysname) + sizeof(utsname()->release) + \ + sizeof(utsname()->version) + sizeof(utsname()->machine) + 8) + +#define encode_exchange_id_maxsz (op_encode_hdr_maxsz + \ + encode_verifier_maxsz + \ + 1 /* co_ownerid.len */ + \ + XDR_QUADLEN(NFS4_EXCHANGE_ID_LEN) + \ + 1 /* flags */ + \ + 1 /* spa_how */ + \ + /* max is SP4_MACH_CRED (for now) */ + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ + 1 /* implementation id array of size 1 */ + \ + 1 /* nii_domain */ + \ + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \ + 1 /* nii_name */ + \ + XDR_QUADLEN(IMPL_NAME_LIMIT) + \ + 3 /* nii_date */) +#define decode_exchange_id_maxsz (op_decode_hdr_maxsz + \ + 2 /* eir_clientid */ + \ + 1 /* eir_sequenceid */ + \ + 1 /* eir_flags */ + \ + 1 /* spr_how */ + \ + /* max is SP4_MACH_CRED (for now) */ + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ + 2 /* eir_server_owner.so_minor_id */ + \ + /* eir_server_owner.so_major_id<> */ \ + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \ + /* eir_server_scope<> */ \ + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \ + 1 /* eir_server_impl_id array length */ + \ + 1 /* nii_domain */ + \ + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \ + 1 /* nii_name */ + \ + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \ + 3 /* nii_date */) +#define encode_channel_attrs_maxsz (6 + 1 /* ca_rdma_ird.len (0) */) +#define decode_channel_attrs_maxsz (6 + \ + 1 /* ca_rdma_ird.len */ + \ + 1 /* ca_rdma_ird */) +#define encode_create_session_maxsz (op_encode_hdr_maxsz + \ + 2 /* csa_clientid */ + \ + 1 /* csa_sequence */ + \ + 1 /* csa_flags */ + \ + encode_channel_attrs_maxsz + \ + encode_channel_attrs_maxsz + \ + 1 /* csa_cb_program */ + \ + 1 /* csa_sec_parms.len (1) */ + \ + 1 /* cb_secflavor (AUTH_SYS) */ + \ + 1 /* stamp */ + \ + 1 /* machinename.len */ + \ + XDR_QUADLEN(NFS4_MAX_MACHINE_NAME_LEN) + \ + 1 /* uid */ + \ + 1 /* gid */ + \ + 1 /* gids.len (0) */) +#define decode_create_session_maxsz (op_decode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* csr_sequence */ + \ + 1 /* csr_flags */ + \ + decode_channel_attrs_maxsz + \ + decode_channel_attrs_maxsz) +#define encode_bind_conn_to_session_maxsz (op_encode_hdr_maxsz + \ + /* bctsa_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsa_dir */ + \ + 1 /* bctsa_use_conn_in_rdma_mode */) +#define decode_bind_conn_to_session_maxsz (op_decode_hdr_maxsz + \ + /* bctsr_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsr_dir */ + \ + 1 /* bctsr_use_conn_in_rdma_mode */) +#define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4) +#define decode_destroy_session_maxsz (op_decode_hdr_maxsz) +#define encode_destroy_clientid_maxsz (op_encode_hdr_maxsz + 2) +#define decode_destroy_clientid_maxsz (op_decode_hdr_maxsz) +#define encode_sequence_maxsz (op_encode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4) +#define decode_sequence_maxsz (op_decode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) +#define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) +#define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) +#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_DEVICEID4_SIZE) + \ + 1 /* layout type */ + \ + 1 /* maxcount */ + \ + 1 /* bitmap size */ + \ + 1 /* notification bitmap length */ + \ + 1 /* notification bitmap, word 0 */) +#define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ + 1 /* layout type */ + \ + 1 /* opaque devaddr4 length */ + \ + /* devaddr4 payload is read into page */ \ + 1 /* notification bitmap length */ + \ + 1 /* notification bitmap, word 0 */) +#define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \ + encode_stateid_maxsz) +#define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \ + decode_stateid_maxsz + \ + XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE)) +#define encode_layoutcommit_maxsz (op_encode_hdr_maxsz + \ + 2 /* offset */ + \ + 2 /* length */ + \ + 1 /* reclaim */ + \ + encode_stateid_maxsz + \ + 1 /* new offset (true) */ + \ + 2 /* last byte written */ + \ + 1 /* nt_timechanged (false) */ + \ + 1 /* layoutupdate4 layout type */ + \ + 1 /* layoutupdate4 opaqueue len */) + /* the actual content of layoutupdate4 should + be allocated by drivers and spliced in + using xdr_write_pages */ +#define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3) +#define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \ + encode_stateid_maxsz + \ + 1 /* FIXME: opaque lrf_body always empty at the moment */) +#define decode_layoutreturn_maxsz (op_decode_hdr_maxsz + \ + 1 + decode_stateid_maxsz) +#define encode_secinfo_no_name_maxsz (op_encode_hdr_maxsz + 1) +#define decode_secinfo_no_name_maxsz decode_secinfo_maxsz +#define encode_test_stateid_maxsz (op_encode_hdr_maxsz + 2 + \ + XDR_QUADLEN(NFS4_STATEID_SIZE)) +#define decode_test_stateid_maxsz (op_decode_hdr_maxsz + 2 + 1) +#define encode_free_stateid_maxsz (op_encode_hdr_maxsz + 1 + \ + XDR_QUADLEN(NFS4_STATEID_SIZE)) +#define decode_free_stateid_maxsz (op_decode_hdr_maxsz) +#else /* CONFIG_NFS_V4_1 */ +#define encode_sequence_maxsz 0 +#define decode_sequence_maxsz 0 +#endif /* CONFIG_NFS_V4_1 */ + +#define NFS4_enc_compound_sz (1024) /* XXX: large enough? */ +#define NFS4_dec_compound_sz (1024) /* XXX: large enough? */ +#define NFS4_enc_read_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_read_maxsz) +#define NFS4_dec_read_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_read_maxsz) +#define NFS4_enc_readlink_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_readlink_maxsz) +#define NFS4_dec_readlink_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_readlink_maxsz) +#define NFS4_enc_readdir_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_readdir_maxsz) +#define NFS4_dec_readdir_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_readdir_maxsz) +#define NFS4_enc_write_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_write_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_write_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_write_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_commit_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_commit_maxsz) +#define NFS4_dec_commit_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_commit_maxsz) +#define NFS4_enc_open_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_open_maxsz + \ + encode_access_maxsz + \ + encode_getfh_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_open_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_open_maxsz + \ + decode_access_maxsz + \ + decode_getfh_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_open_confirm_sz \ + (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_open_confirm_maxsz) +#define NFS4_dec_open_confirm_sz \ + (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_open_confirm_maxsz) +#define NFS4_enc_open_noattr_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_open_maxsz + \ + encode_access_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_open_noattr_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_open_maxsz + \ + decode_access_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_open_downgrade_sz \ + (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_open_downgrade_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_open_downgrade_sz \ + (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_open_downgrade_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_close_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_close_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_close_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_close_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_setattr_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_setattr_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_setattr_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_setattr_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_fsinfo_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_fsinfo_maxsz) +#define NFS4_dec_fsinfo_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_fsinfo_maxsz) +#define NFS4_enc_renew_sz (compound_encode_hdr_maxsz + \ + encode_renew_maxsz) +#define NFS4_dec_renew_sz (compound_decode_hdr_maxsz + \ + decode_renew_maxsz) +#define NFS4_enc_setclientid_sz (compound_encode_hdr_maxsz + \ + encode_setclientid_maxsz) +#define NFS4_dec_setclientid_sz (compound_decode_hdr_maxsz + \ + decode_setclientid_maxsz) +#define NFS4_enc_setclientid_confirm_sz \ + (compound_encode_hdr_maxsz + \ + encode_setclientid_confirm_maxsz) +#define NFS4_dec_setclientid_confirm_sz \ + (compound_decode_hdr_maxsz + \ + decode_setclientid_confirm_maxsz) +#define NFS4_enc_lock_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_lock_maxsz) +#define NFS4_dec_lock_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_lock_maxsz) +#define NFS4_enc_lockt_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_lockt_maxsz) +#define NFS4_dec_lockt_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_lockt_maxsz) +#define NFS4_enc_locku_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_locku_maxsz) +#define NFS4_dec_locku_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_locku_maxsz) +#define NFS4_enc_release_lockowner_sz \ + (compound_encode_hdr_maxsz + \ + encode_lockowner_maxsz) +#define NFS4_dec_release_lockowner_sz \ + (compound_decode_hdr_maxsz + \ + decode_lockowner_maxsz) +#define NFS4_enc_access_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_access_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_access_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_access_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_getattr_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getattr_maxsz + \ + encode_renew_maxsz) +#define NFS4_dec_getattr_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getattr_maxsz + \ + decode_renew_maxsz) +#define NFS4_enc_lookup_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_lookup_maxsz + \ + encode_getattr_maxsz + \ + encode_getfh_maxsz) +#define NFS4_dec_lookup_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_lookup_maxsz + \ + decode_getattr_maxsz + \ + decode_getfh_maxsz) +#define NFS4_enc_lookup_root_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putrootfh_maxsz + \ + encode_getattr_maxsz + \ + encode_getfh_maxsz) +#define NFS4_dec_lookup_root_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putrootfh_maxsz + \ + decode_getattr_maxsz + \ + decode_getfh_maxsz) +#define NFS4_enc_remove_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_remove_maxsz) +#define NFS4_dec_remove_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_remove_maxsz) +#define NFS4_enc_rename_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_savefh_maxsz + \ + encode_putfh_maxsz + \ + encode_rename_maxsz) +#define NFS4_dec_rename_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_savefh_maxsz + \ + decode_putfh_maxsz + \ + decode_rename_maxsz) +#define NFS4_enc_link_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_savefh_maxsz + \ + encode_putfh_maxsz + \ + encode_link_maxsz + \ + encode_restorefh_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_link_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_savefh_maxsz + \ + decode_putfh_maxsz + \ + decode_link_maxsz + \ + decode_restorefh_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_symlink_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_symlink_maxsz + \ + encode_getattr_maxsz + \ + encode_getfh_maxsz) +#define NFS4_dec_symlink_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_symlink_maxsz + \ + decode_getattr_maxsz + \ + decode_getfh_maxsz) +#define NFS4_enc_create_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_create_maxsz + \ + encode_getfh_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_create_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_create_maxsz + \ + decode_getfh_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_pathconf_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_pathconf_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_statfs_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_statfs_maxsz) +#define NFS4_dec_statfs_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_statfs_maxsz) +#define NFS4_enc_server_caps_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_server_caps_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_delegreturn_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_delegreturn_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_delegreturn_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_delegreturn_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_getacl_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getacl_maxsz) +#define NFS4_dec_getacl_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getacl_maxsz) +#define NFS4_enc_setacl_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_setacl_maxsz) +#define NFS4_dec_setacl_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_setacl_maxsz) +#define NFS4_enc_fs_locations_sz \ + (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_lookup_maxsz + \ + encode_fs_locations_maxsz + \ + encode_renew_maxsz) +#define NFS4_dec_fs_locations_sz \ + (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_lookup_maxsz + \ + decode_fs_locations_maxsz + \ + decode_renew_maxsz) +#define NFS4_enc_secinfo_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_secinfo_maxsz) +#define NFS4_dec_secinfo_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_secinfo_maxsz) +#define NFS4_enc_fsid_present_sz \ + (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getfh_maxsz + \ + encode_renew_maxsz) +#define NFS4_dec_fsid_present_sz \ + (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getfh_maxsz + \ + decode_renew_maxsz) +#if defined(CONFIG_NFS_V4_1) +#define NFS4_enc_bind_conn_to_session_sz \ + (compound_encode_hdr_maxsz + \ + encode_bind_conn_to_session_maxsz) +#define NFS4_dec_bind_conn_to_session_sz \ + (compound_decode_hdr_maxsz + \ + decode_bind_conn_to_session_maxsz) +#define NFS4_enc_exchange_id_sz \ + (compound_encode_hdr_maxsz + \ + encode_exchange_id_maxsz) +#define NFS4_dec_exchange_id_sz \ + (compound_decode_hdr_maxsz + \ + decode_exchange_id_maxsz) +#define NFS4_enc_create_session_sz \ + (compound_encode_hdr_maxsz + \ + encode_create_session_maxsz) +#define NFS4_dec_create_session_sz \ + (compound_decode_hdr_maxsz + \ + decode_create_session_maxsz) +#define NFS4_enc_destroy_session_sz (compound_encode_hdr_maxsz + \ + encode_destroy_session_maxsz) +#define NFS4_dec_destroy_session_sz (compound_decode_hdr_maxsz + \ + decode_destroy_session_maxsz) +#define NFS4_enc_destroy_clientid_sz (compound_encode_hdr_maxsz + \ + encode_destroy_clientid_maxsz) +#define NFS4_dec_destroy_clientid_sz (compound_decode_hdr_maxsz + \ + decode_destroy_clientid_maxsz) +#define NFS4_enc_sequence_sz \ + (compound_decode_hdr_maxsz + \ + encode_sequence_maxsz) +#define NFS4_dec_sequence_sz \ + (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz) +#define NFS4_enc_get_lease_time_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putrootfh_maxsz + \ + encode_fsinfo_maxsz) +#define NFS4_dec_get_lease_time_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putrootfh_maxsz + \ + decode_fsinfo_maxsz) +#define NFS4_enc_reclaim_complete_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_reclaim_complete_maxsz) +#define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_reclaim_complete_maxsz) +#define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz +\ + encode_getdeviceinfo_maxsz) +#define NFS4_dec_getdeviceinfo_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_getdeviceinfo_maxsz) +#define NFS4_enc_layoutget_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_layoutget_maxsz) +#define NFS4_dec_layoutget_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_layoutget_maxsz) +#define NFS4_enc_layoutcommit_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz +\ + encode_putfh_maxsz + \ + encode_layoutcommit_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_layoutcommit_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_layoutcommit_maxsz + \ + decode_getattr_maxsz) +#define NFS4_enc_layoutreturn_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_layoutreturn_maxsz) +#define NFS4_dec_layoutreturn_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_layoutreturn_maxsz) +#define NFS4_enc_secinfo_no_name_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putrootfh_maxsz +\ + encode_secinfo_no_name_maxsz) +#define NFS4_dec_secinfo_no_name_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putrootfh_maxsz + \ + decode_secinfo_no_name_maxsz) +#define NFS4_enc_test_stateid_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_test_stateid_maxsz) +#define NFS4_dec_test_stateid_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_test_stateid_maxsz) +#define NFS4_enc_free_stateid_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_free_stateid_maxsz) +#define NFS4_dec_free_stateid_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_free_stateid_maxsz) + +const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH + + compound_encode_hdr_maxsz + + encode_sequence_maxsz + + encode_putfh_maxsz + + encode_getattr_maxsz) * + XDR_UNIT); + +const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH + + compound_decode_hdr_maxsz + + decode_sequence_maxsz + + decode_putfh_maxsz) * + XDR_UNIT); + +const u32 nfs41_maxgetdevinfo_overhead = ((RPC_MAX_REPHEADER_WITH_AUTH + + compound_decode_hdr_maxsz + + decode_sequence_maxsz) * + XDR_UNIT); +EXPORT_SYMBOL_GPL(nfs41_maxgetdevinfo_overhead); +#endif /* CONFIG_NFS_V4_1 */ + +static const umode_t nfs_type2fmt[] = { + [NF4BAD] = 0, + [NF4REG] = S_IFREG, + [NF4DIR] = S_IFDIR, + [NF4BLK] = S_IFBLK, + [NF4CHR] = S_IFCHR, + [NF4LNK] = S_IFLNK, + [NF4SOCK] = S_IFSOCK, + [NF4FIFO] = S_IFIFO, + [NF4ATTRDIR] = 0, + [NF4NAMEDATTR] = 0, +}; + +struct compound_hdr { + int32_t status; + uint32_t nops; + __be32 * nops_p; + uint32_t taglen; + char * tag; + uint32_t replen; /* expected reply words */ + u32 minorversion; +}; + +static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes) +{ + __be32 *p = xdr_reserve_space(xdr, nbytes); + BUG_ON(!p); + return p; +} + +static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, len); + xdr_encode_opaque_fixed(p, buf, len); +} + +static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) +{ + __be32 *p; + + p = reserve_space(xdr, 4 + len); + xdr_encode_opaque(p, str, len); +} + +static void encode_uint32(struct xdr_stream *xdr, u32 n) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(n); +} + +static void encode_uint64(struct xdr_stream *xdr, u64 n) +{ + __be32 *p; + + p = reserve_space(xdr, 8); + xdr_encode_hyper(p, n); +} + +static void encode_nfs4_seqid(struct xdr_stream *xdr, + const struct nfs_seqid *seqid) +{ + if (seqid != NULL) + encode_uint32(xdr, seqid->sequence->counter); + else + encode_uint32(xdr, 0); +} + +static void encode_compound_hdr(struct xdr_stream *xdr, + struct rpc_rqst *req, + struct compound_hdr *hdr) +{ + __be32 *p; + struct rpc_auth *auth = req->rq_cred->cr_auth; + + /* initialize running count of expected bytes in reply. + * NOTE: the replied tag SHOULD be the same is the one sent, + * but this is not required as a MUST for the server to do so. */ + hdr->replen = RPC_REPHDRSIZE + auth->au_rslack + 3 + hdr->taglen; + + WARN_ON_ONCE(hdr->taglen > NFS4_MAXTAGLEN); + encode_string(xdr, hdr->taglen, hdr->tag); + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(hdr->minorversion); + hdr->nops_p = p; + *p = cpu_to_be32(hdr->nops); +} + +static void encode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 op, + uint32_t replen, + struct compound_hdr *hdr) +{ + encode_uint32(xdr, op); + hdr->nops++; + hdr->replen += replen; +} + +static void encode_nops(struct compound_hdr *hdr) +{ + WARN_ON_ONCE(hdr->nops > NFS4_MAX_OPS); + *hdr->nops_p = htonl(hdr->nops); +} + +static void encode_nfs4_stateid(struct xdr_stream *xdr, const nfs4_stateid *stateid) +{ + encode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE); +} + +static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *verf) +{ + encode_opaque_fixed(xdr, verf->data, NFS4_VERIFIER_SIZE); +} + +static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, + const struct nfs4_label *label, + const struct nfs_server *server) +{ + char owner_name[IDMAP_NAMESZ]; + char owner_group[IDMAP_NAMESZ]; + int owner_namelen = 0; + int owner_grouplen = 0; + __be32 *p; + unsigned i; + uint32_t len = 0; + uint32_t bmval_len; + uint32_t bmval[3] = { 0 }; + + /* + * We reserve enough space to write the entire attribute buffer at once. + * In the worst-case, this would be + * 16(bitmap) + 4(attrlen) + 8(size) + 4(mode) + 4(atime) + 4(mtime) + * = 40 bytes, plus any contribution from variable-length fields + * such as owner/group. + */ + if (iap->ia_valid & ATTR_SIZE) { + bmval[0] |= FATTR4_WORD0_SIZE; + len += 8; + } + if (iap->ia_valid & ATTR_MODE) { + bmval[1] |= FATTR4_WORD1_MODE; + len += 4; + } + if (iap->ia_valid & ATTR_UID) { + owner_namelen = nfs_map_uid_to_name(server, iap->ia_uid, owner_name, IDMAP_NAMESZ); + if (owner_namelen < 0) { + dprintk("nfs: couldn't resolve uid %d to string\n", + from_kuid(&init_user_ns, iap->ia_uid)); + /* XXX */ + strcpy(owner_name, "nobody"); + owner_namelen = sizeof("nobody") - 1; + /* goto out; */ + } + bmval[1] |= FATTR4_WORD1_OWNER; + len += 4 + (XDR_QUADLEN(owner_namelen) << 2); + } + if (iap->ia_valid & ATTR_GID) { + owner_grouplen = nfs_map_gid_to_group(server, iap->ia_gid, owner_group, IDMAP_NAMESZ); + if (owner_grouplen < 0) { + dprintk("nfs: couldn't resolve gid %d to string\n", + from_kgid(&init_user_ns, iap->ia_gid)); + strcpy(owner_group, "nobody"); + owner_grouplen = sizeof("nobody") - 1; + /* goto out; */ + } + bmval[1] |= FATTR4_WORD1_OWNER_GROUP; + len += 4 + (XDR_QUADLEN(owner_grouplen) << 2); + } + if (iap->ia_valid & ATTR_ATIME_SET) { + bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET; + len += 16; + } else if (iap->ia_valid & ATTR_ATIME) { + bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET; + len += 4; + } + if (iap->ia_valid & ATTR_MTIME_SET) { + bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET; + len += 16; + } else if (iap->ia_valid & ATTR_MTIME) { + bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET; + len += 4; + } + if (label) { + len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2); + bmval[2] |= FATTR4_WORD2_SECURITY_LABEL; + } + + if (bmval[2] != 0) + bmval_len = 3; + else if (bmval[1] != 0) + bmval_len = 2; + else + bmval_len = 1; + + p = reserve_space(xdr, 4 + (bmval_len << 2) + 4 + len); + + *p++ = cpu_to_be32(bmval_len); + for (i = 0; i < bmval_len; i++) + *p++ = cpu_to_be32(bmval[i]); + *p++ = cpu_to_be32(len); + + if (bmval[0] & FATTR4_WORD0_SIZE) + p = xdr_encode_hyper(p, iap->ia_size); + if (bmval[1] & FATTR4_WORD1_MODE) + *p++ = cpu_to_be32(iap->ia_mode & S_IALLUGO); + if (bmval[1] & FATTR4_WORD1_OWNER) + p = xdr_encode_opaque(p, owner_name, owner_namelen); + if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) + p = xdr_encode_opaque(p, owner_group, owner_grouplen); + if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { + if (iap->ia_valid & ATTR_ATIME_SET) { + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + p = xdr_encode_hyper(p, (s64)iap->ia_atime.tv_sec); + *p++ = cpu_to_be32(iap->ia_atime.tv_nsec); + } else + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); + } + if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { + if (iap->ia_valid & ATTR_MTIME_SET) { + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + p = xdr_encode_hyper(p, (s64)iap->ia_mtime.tv_sec); + *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); + } else + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); + } + if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { + *p++ = cpu_to_be32(label->lfs); + *p++ = cpu_to_be32(label->pi); + *p++ = cpu_to_be32(label->len); + p = xdr_encode_opaque_fixed(p, label->label, label->len); + } + +/* out: */ +} + +static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_ACCESS, decode_access_maxsz, hdr); + encode_uint32(xdr, access); +} + +static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_CLOSE, decode_close_maxsz, hdr); + encode_nfs4_seqid(xdr, arg->seqid); + encode_nfs4_stateid(xdr, &arg->stateid); +} + +static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_COMMIT, decode_commit_maxsz, hdr); + p = reserve_space(xdr, 12); + p = xdr_encode_hyper(p, args->offset); + *p = cpu_to_be32(args->count); +} + +static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *create, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_CREATE, decode_create_maxsz, hdr); + encode_uint32(xdr, create->ftype); + + switch (create->ftype) { + case NF4LNK: + p = reserve_space(xdr, 4); + *p = cpu_to_be32(create->u.symlink.len); + xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len); + break; + + case NF4BLK: case NF4CHR: + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(create->u.device.specdata1); + *p = cpu_to_be32(create->u.device.specdata2); + break; + + default: + break; + } + + encode_string(xdr, create->name->len, create->name->name); + encode_attrs(xdr, create->attrs, create->label, create->server); +} + +static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr); + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(bitmap); +} + +static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm1, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr); + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bm0); + *p = cpu_to_be32(bm1); +} + +static void +encode_getattr_three(struct xdr_stream *xdr, + uint32_t bm0, uint32_t bm1, uint32_t bm2, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr); + if (bm2) { + p = reserve_space(xdr, 16); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bm0); + *p++ = cpu_to_be32(bm1); + *p = cpu_to_be32(bm2); + } else if (bm1) { + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bm0); + *p = cpu_to_be32(bm1); + } else { + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(bm0); + } +} + +static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) +{ + encode_getattr_three(xdr, bitmask[0] & nfs4_fattr_bitmap[0], + bitmask[1] & nfs4_fattr_bitmap[1], + bitmask[2] & nfs4_fattr_bitmap[2], + hdr); +} + +static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask, + const u32 *open_bitmap, + struct compound_hdr *hdr) +{ + encode_getattr_three(xdr, + bitmask[0] & open_bitmap[0], + bitmask[1] & open_bitmap[1], + bitmask[2] & open_bitmap[2], + hdr); +} + +static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) +{ + encode_getattr_three(xdr, + bitmask[0] & nfs4_fsinfo_bitmap[0], + bitmask[1] & nfs4_fsinfo_bitmap[1], + bitmask[2] & nfs4_fsinfo_bitmap[2], + hdr); +} + +static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) +{ + encode_getattr_two(xdr, bitmask[0] & nfs4_fs_locations_bitmap[0], + bitmask[1] & nfs4_fs_locations_bitmap[1], hdr); +} + +static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_GETFH, decode_getfh_maxsz, hdr); +} + +static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_LINK, decode_link_maxsz, hdr); + encode_string(xdr, name->len, name->name); +} + +static inline int nfs4_lock_type(struct file_lock *fl, int block) +{ + if (fl->fl_type == F_RDLCK) + return block ? NFS4_READW_LT : NFS4_READ_LT; + return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT; +} + +static inline uint64_t nfs4_lock_length(struct file_lock *fl) +{ + if (fl->fl_end == OFFSET_MAX) + return ~(uint64_t)0; + return fl->fl_end - fl->fl_start + 1; +} + +static void encode_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner) +{ + __be32 *p; + + p = reserve_space(xdr, 32); + p = xdr_encode_hyper(p, lowner->clientid); + *p++ = cpu_to_be32(20); + p = xdr_encode_opaque_fixed(p, "lock id:", 8); + *p++ = cpu_to_be32(lowner->s_dev); + xdr_encode_hyper(p, lowner->id); +} + +/* + * opcode,type,reclaim,offset,length,new_lock_owner = 32 + * open_seqid,open_stateid,lock_seqid,lock_owner.clientid, lock_owner.id = 40 + */ +static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_LOCK, decode_lock_maxsz, hdr); + p = reserve_space(xdr, 28); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block)); + *p++ = cpu_to_be32(args->reclaim); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); + *p = cpu_to_be32(args->new_lock_owner); + if (args->new_lock_owner){ + encode_nfs4_seqid(xdr, args->open_seqid); + encode_nfs4_stateid(xdr, &args->open_stateid); + encode_nfs4_seqid(xdr, args->lock_seqid); + encode_lockowner(xdr, &args->lock_owner); + } + else { + encode_nfs4_stateid(xdr, &args->lock_stateid); + encode_nfs4_seqid(xdr, args->lock_seqid); + } +} + +static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *args, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_LOCKT, decode_lockt_maxsz, hdr); + p = reserve_space(xdr, 20); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); + encode_lockowner(xdr, &args->lock_owner); +} + +static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *args, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_LOCKU, decode_locku_maxsz, hdr); + encode_uint32(xdr, nfs4_lock_type(args->fl, 0)); + encode_nfs4_seqid(xdr, args->seqid); + encode_nfs4_stateid(xdr, &args->stateid); + p = reserve_space(xdr, 16); + p = xdr_encode_hyper(p, args->fl->fl_start); + xdr_encode_hyper(p, nfs4_lock_length(args->fl)); +} + +static void encode_release_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_RELEASE_LOCKOWNER, decode_release_lockowner_maxsz, hdr); + encode_lockowner(xdr, lowner); +} + +static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_LOOKUP, decode_lookup_maxsz, hdr); + encode_string(xdr, name->len, name->name); +} + +static void encode_share_access(struct xdr_stream *xdr, u32 share_access) +{ + __be32 *p; + + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(share_access); + *p = cpu_to_be32(0); /* for linux, share_deny = 0 always */ +} + +static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_openargs *arg) +{ + __be32 *p; + /* + * opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4, + * owner 4 = 32 + */ + encode_nfs4_seqid(xdr, arg->seqid); + encode_share_access(xdr, arg->share_access); + p = reserve_space(xdr, 36); + p = xdr_encode_hyper(p, arg->clientid); + *p++ = cpu_to_be32(24); + p = xdr_encode_opaque_fixed(p, "open id:", 8); + *p++ = cpu_to_be32(arg->server->s_dev); + *p++ = cpu_to_be32(arg->id.uniquifier); + xdr_encode_hyper(p, arg->id.create_time); +} + +static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) +{ + struct iattr dummy; + __be32 *p; + + p = reserve_space(xdr, 4); + switch(arg->createmode) { + case NFS4_CREATE_UNCHECKED: + *p = cpu_to_be32(NFS4_CREATE_UNCHECKED); + encode_attrs(xdr, arg->u.attrs, arg->label, arg->server); + break; + case NFS4_CREATE_GUARDED: + *p = cpu_to_be32(NFS4_CREATE_GUARDED); + encode_attrs(xdr, arg->u.attrs, arg->label, arg->server); + break; + case NFS4_CREATE_EXCLUSIVE: + *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); + encode_nfs4_verifier(xdr, &arg->u.verifier); + break; + case NFS4_CREATE_EXCLUSIVE4_1: + *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1); + encode_nfs4_verifier(xdr, &arg->u.verifier); + dummy.ia_valid = 0; + encode_attrs(xdr, &dummy, arg->label, arg->server); + } +} + +static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *arg) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + switch (arg->open_flags & O_CREAT) { + case 0: + *p = cpu_to_be32(NFS4_OPEN_NOCREATE); + break; + default: + *p = cpu_to_be32(NFS4_OPEN_CREATE); + encode_createmode(xdr, arg); + } +} + +static inline void encode_delegation_type(struct xdr_stream *xdr, fmode_t delegation_type) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + switch (delegation_type) { + case 0: + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE); + break; + case FMODE_READ: + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_READ); + break; + case FMODE_WRITE|FMODE_READ: + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_WRITE); + break; + default: + BUG(); + } +} + +static inline void encode_claim_null(struct xdr_stream *xdr, const struct qstr *name) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_NULL); + encode_string(xdr, name->len, name->name); +} + +static inline void encode_claim_previous(struct xdr_stream *xdr, fmode_t type) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS); + encode_delegation_type(xdr, type); +} + +static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struct qstr *name, const nfs4_stateid *stateid) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR); + encode_nfs4_stateid(xdr, stateid); + encode_string(xdr, name->len, name->name); +} + +static inline void encode_claim_fh(struct xdr_stream *xdr) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_FH); +} + +static inline void encode_claim_delegate_cur_fh(struct xdr_stream *xdr, const nfs4_stateid *stateid) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_DELEG_CUR_FH); + encode_nfs4_stateid(xdr, stateid); +} + +static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_OPEN, decode_open_maxsz, hdr); + encode_openhdr(xdr, arg); + encode_opentype(xdr, arg); + switch (arg->claim) { + case NFS4_OPEN_CLAIM_NULL: + encode_claim_null(xdr, arg->name); + break; + case NFS4_OPEN_CLAIM_PREVIOUS: + encode_claim_previous(xdr, arg->u.delegation_type); + break; + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + encode_claim_delegate_cur(xdr, arg->name, &arg->u.delegation); + break; + case NFS4_OPEN_CLAIM_FH: + encode_claim_fh(xdr); + break; + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + encode_claim_delegate_cur_fh(xdr, &arg->u.delegation); + break; + default: + BUG(); + } +} + +static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_confirmargs *arg, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_OPEN_CONFIRM, decode_open_confirm_maxsz, hdr); + encode_nfs4_stateid(xdr, arg->stateid); + encode_nfs4_seqid(xdr, arg->seqid); +} + +static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr); + encode_nfs4_stateid(xdr, &arg->stateid); + encode_nfs4_seqid(xdr, arg->seqid); + encode_share_access(xdr, arg->share_access); +} + +static void +encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_PUTFH, decode_putfh_maxsz, hdr); + encode_string(xdr, fh->size, fh->data); +} + +static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr); +} + +static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_READ, decode_read_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->stateid); + + p = reserve_space(xdr, 12); + p = xdr_encode_hyper(p, args->offset); + *p = cpu_to_be32(args->count); +} + +static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr) +{ + uint32_t attrs[3] = { + FATTR4_WORD0_RDATTR_ERROR, + FATTR4_WORD1_MOUNTED_ON_FILEID, + }; + uint32_t dircount = readdir->count >> 1; + __be32 *p, verf[2]; + uint32_t attrlen = 0; + unsigned int i; + + if (readdir->plus) { + attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE| + FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE|FATTR4_WORD0_FILEID; + attrs[1] |= FATTR4_WORD1_MODE|FATTR4_WORD1_NUMLINKS|FATTR4_WORD1_OWNER| + FATTR4_WORD1_OWNER_GROUP|FATTR4_WORD1_RAWDEV| + FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS| + FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; + attrs[2] |= FATTR4_WORD2_SECURITY_LABEL; + dircount >>= 1; + } + /* Use mounted_on_fileid only if the server supports it */ + if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) + attrs[0] |= FATTR4_WORD0_FILEID; + for (i = 0; i < ARRAY_SIZE(attrs); i++) { + attrs[i] &= readdir->bitmask[i]; + if (attrs[i] != 0) + attrlen = i+1; + } + + encode_op_hdr(xdr, OP_READDIR, decode_readdir_maxsz, hdr); + encode_uint64(xdr, readdir->cookie); + encode_nfs4_verifier(xdr, &readdir->verifier); + p = reserve_space(xdr, 12 + (attrlen << 2)); + *p++ = cpu_to_be32(dircount); + *p++ = cpu_to_be32(readdir->count); + *p++ = cpu_to_be32(attrlen); + for (i = 0; i < attrlen; i++) + *p++ = cpu_to_be32(attrs[i]); + memcpy(verf, readdir->verifier.data, sizeof(verf)); + + dprintk("%s: cookie = %llu, verifier = %08x:%08x, bitmap = %08x:%08x:%08x\n", + __func__, + (unsigned long long)readdir->cookie, + verf[0], verf[1], + attrs[0] & readdir->bitmask[0], + attrs[1] & readdir->bitmask[1], + attrs[2] & readdir->bitmask[2]); +} + +static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink *readlink, struct rpc_rqst *req, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_READLINK, decode_readlink_maxsz, hdr); +} + +static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_REMOVE, decode_remove_maxsz, hdr); + encode_string(xdr, name->len, name->name); +} + +static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, const struct qstr *newname, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_RENAME, decode_rename_maxsz, hdr); + encode_string(xdr, oldname->len, oldname->name); + encode_string(xdr, newname->len, newname->name); +} + +static void encode_renew(struct xdr_stream *xdr, clientid4 clid, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_RENEW, decode_renew_maxsz, hdr); + encode_uint64(xdr, clid); +} + +static void +encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr); +} + +static void +encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr); + encode_nfs4_stateid(xdr, &zero_stateid); + p = reserve_space(xdr, 2*4); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(FATTR4_WORD0_ACL); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(arg->acl_len); + xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); +} + +static void +encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_SAVEFH, decode_savefh_maxsz, hdr); +} + +static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs *arg, const struct nfs_server *server, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_SETATTR, decode_setattr_maxsz, hdr); + encode_nfs4_stateid(xdr, &arg->stateid); + encode_attrs(xdr, arg->iap, arg->label, server); +} + +static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclientid *setclientid, struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_SETCLIENTID, decode_setclientid_maxsz, hdr); + encode_nfs4_verifier(xdr, setclientid->sc_verifier); + + encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(setclientid->sc_prog); + encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid); + encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(setclientid->sc_cb_ident); +} + +static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4_setclientid_res *arg, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM, + decode_setclientid_confirm_maxsz, hdr); + encode_uint64(xdr, arg->clientid); + encode_nfs4_verifier(xdr, &arg->confirm); +} + +static void encode_write(struct xdr_stream *xdr, const struct nfs_pgio_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_WRITE, decode_write_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->stateid); + + p = reserve_space(xdr, 16); + p = xdr_encode_hyper(p, args->offset); + *p++ = cpu_to_be32(args->stable); + *p = cpu_to_be32(args->count); + + xdr_write_pages(xdr, args->pages, args->pgbase, args->count); +} + +static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *stateid, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DELEGRETURN, decode_delegreturn_maxsz, hdr); + encode_nfs4_stateid(xdr, stateid); +} + +static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_SECINFO, decode_secinfo_maxsz, hdr); + encode_string(xdr, name->len, name->name); +} + +#if defined(CONFIG_NFS_V4_1) +/* NFSv4.1 operations */ +static void encode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs41_bind_conn_to_session_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION, + decode_bind_conn_to_session_maxsz, hdr); + encode_opaque_fixed(xdr, args->sessionid.data, NFS4_MAX_SESSIONID_LEN); + p = xdr_reserve_space(xdr, 8); + *p++ = cpu_to_be32(args->dir); + *p = (args->use_conn_in_rdma_mode) ? cpu_to_be32(1) : cpu_to_be32(0); +} + +static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +{ + unsigned int i; + encode_uint32(xdr, NFS4_OP_MAP_NUM_WORDS); + for (i = 0; i < NFS4_OP_MAP_NUM_WORDS; i++) + encode_uint32(xdr, op_map->u.words[i]); +} + +static void encode_exchange_id(struct xdr_stream *xdr, + struct nfs41_exchange_id_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + char impl_name[IMPL_NAME_LIMIT]; + int len = 0; + + encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr); + encode_nfs4_verifier(xdr, args->verifier); + + encode_string(xdr, args->id_len, args->id); + + encode_uint32(xdr, args->flags); + encode_uint32(xdr, args->state_protect.how); + + switch (args->state_protect.how) { + case SP4_NONE: + break; + case SP4_MACH_CRED: + encode_op_map(xdr, &args->state_protect.enforce); + encode_op_map(xdr, &args->state_protect.allow); + break; + default: + WARN_ON_ONCE(1); + break; + } + + if (send_implementation_id && + sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) > 1 && + sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) + <= sizeof(impl_name) + 1) + len = snprintf(impl_name, sizeof(impl_name), "%s %s %s %s", + utsname()->sysname, utsname()->release, + utsname()->version, utsname()->machine); + + if (len > 0) { + encode_uint32(xdr, 1); /* implementation id array length=1 */ + + encode_string(xdr, + sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) - 1, + CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN); + encode_string(xdr, len, impl_name); + /* just send zeros for nii_date - the date is in nii_name */ + p = reserve_space(xdr, 12); + p = xdr_encode_hyper(p, 0); + *p = cpu_to_be32(0); + } else + encode_uint32(xdr, 0); /* implementation id array length=0 */ +} + +static void encode_create_session(struct xdr_stream *xdr, + struct nfs41_create_session_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + struct nfs_client *clp = args->client; + struct rpc_clnt *clnt = clp->cl_rpcclient; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + u32 max_resp_sz_cached; + + /* + * Assumes OPEN is the biggest non-idempotent compound. + * 2 is the verifier. + */ + max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + + RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT; + + encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr); + p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12); + p = xdr_encode_hyper(p, args->clientid); + *p++ = cpu_to_be32(args->seqid); /*Sequence id */ + *p++ = cpu_to_be32(args->flags); /*flags */ + + /* Fore Channel */ + *p++ = cpu_to_be32(0); /* header padding size */ + *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */ + *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz); /* max resp size */ + *p++ = cpu_to_be32(max_resp_sz_cached); /* Max resp sz cached */ + *p++ = cpu_to_be32(args->fc_attrs.max_ops); /* max operations */ + *p++ = cpu_to_be32(args->fc_attrs.max_reqs); /* max requests */ + *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ + + /* Back Channel */ + *p++ = cpu_to_be32(0); /* header padding size */ + *p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz); /* max req size */ + *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz); /* max resp size */ + *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ + *p++ = cpu_to_be32(args->bc_attrs.max_ops); /* max operations */ + *p++ = cpu_to_be32(args->bc_attrs.max_reqs); /* max requests */ + *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ + + *p++ = cpu_to_be32(args->cb_program); /* cb_program */ + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ + + /* authsys_parms rfc1831 */ + *p++ = cpu_to_be32(nn->boot_time.tv_nsec); /* stamp */ + p = xdr_encode_array(p, clnt->cl_nodename, clnt->cl_nodelen); + *p++ = cpu_to_be32(0); /* UID */ + *p++ = cpu_to_be32(0); /* GID */ + *p = cpu_to_be32(0); /* No more gids */ +} + +static void encode_destroy_session(struct xdr_stream *xdr, + struct nfs4_session *session, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr); + encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); +} + +static void encode_destroy_clientid(struct xdr_stream *xdr, + uint64_t clientid, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DESTROY_CLIENTID, decode_destroy_clientid_maxsz, hdr); + encode_uint64(xdr, clientid); +} + +static void encode_reclaim_complete(struct xdr_stream *xdr, + struct nfs41_reclaim_complete_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr); + encode_uint32(xdr, args->one_fs); +} +#endif /* CONFIG_NFS_V4_1 */ + +static void encode_sequence(struct xdr_stream *xdr, + const struct nfs4_sequence_args *args, + struct compound_hdr *hdr) +{ +#if defined(CONFIG_NFS_V4_1) + struct nfs4_session *session; + struct nfs4_slot_table *tp; + struct nfs4_slot *slot = args->sa_slot; + __be32 *p; + + tp = slot->table; + session = tp->session; + if (!session) + return; + + encode_op_hdr(xdr, OP_SEQUENCE, decode_sequence_maxsz, hdr); + + /* + * Sessionid + seqid + slotid + max slotid + cache_this + */ + dprintk("%s: sessionid=%u:%u:%u:%u seqid=%d slotid=%d " + "max_slotid=%d cache_this=%d\n", + __func__, + ((u32 *)session->sess_id.data)[0], + ((u32 *)session->sess_id.data)[1], + ((u32 *)session->sess_id.data)[2], + ((u32 *)session->sess_id.data)[3], + slot->seq_nr, slot->slot_nr, + tp->highest_used_slotid, args->sa_cache_this); + p = reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 16); + p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(slot->seq_nr); + *p++ = cpu_to_be32(slot->slot_nr); + *p++ = cpu_to_be32(tp->highest_used_slotid); + *p = cpu_to_be32(args->sa_cache_this); +#endif /* CONFIG_NFS_V4_1 */ +} + +#ifdef CONFIG_NFS_V4_1 +static void +encode_getdeviceinfo(struct xdr_stream *xdr, + const struct nfs4_getdeviceinfo_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_GETDEVICEINFO, decode_getdeviceinfo_maxsz, hdr); + p = reserve_space(xdr, NFS4_DEVICEID4_SIZE + 4 + 4); + p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data, + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(args->pdev->layout_type); + *p++ = cpu_to_be32(args->pdev->maxcount); /* gdia_maxcount */ + + p = reserve_space(xdr, 4 + 4); + *p++ = cpu_to_be32(1); /* bitmap length */ + *p++ = cpu_to_be32(args->notify_types); +} + +static void +encode_layoutget(struct xdr_stream *xdr, + const struct nfs4_layoutget_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_LAYOUTGET, decode_layoutget_maxsz, hdr); + p = reserve_space(xdr, 36); + *p++ = cpu_to_be32(0); /* Signal layout available */ + *p++ = cpu_to_be32(args->type); + *p++ = cpu_to_be32(args->range.iomode); + p = xdr_encode_hyper(p, args->range.offset); + p = xdr_encode_hyper(p, args->range.length); + p = xdr_encode_hyper(p, args->minlength); + encode_nfs4_stateid(xdr, &args->stateid); + encode_uint32(xdr, args->maxcount); + + dprintk("%s: 1st type:0x%x iomode:%d off:%lu len:%lu mc:%d\n", + __func__, + args->type, + args->range.iomode, + (unsigned long)args->range.offset, + (unsigned long)args->range.length, + args->maxcount); +} + +static int +encode_layoutcommit(struct xdr_stream *xdr, + struct inode *inode, + struct nfs4_layoutcommit_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + dprintk("%s: lbw: %llu type: %d\n", __func__, args->lastbytewritten, + NFS_SERVER(args->inode)->pnfs_curr_ld->id); + + encode_op_hdr(xdr, OP_LAYOUTCOMMIT, decode_layoutcommit_maxsz, hdr); + p = reserve_space(xdr, 20); + /* Only whole file layouts */ + p = xdr_encode_hyper(p, 0); /* offset */ + p = xdr_encode_hyper(p, args->lastbytewritten + 1); /* length */ + *p = cpu_to_be32(0); /* reclaim */ + encode_nfs4_stateid(xdr, &args->stateid); + p = reserve_space(xdr, 20); + *p++ = cpu_to_be32(1); /* newoffset = TRUE */ + p = xdr_encode_hyper(p, args->lastbytewritten); + *p++ = cpu_to_be32(0); /* Never send time_modify_changed */ + *p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */ + + if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) { + NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit( + NFS_I(inode)->layout, xdr, args); + } else { + encode_uint32(xdr, args->layoutupdate_len); + if (args->layoutupdate_pages) { + xdr_write_pages(xdr, args->layoutupdate_pages, 0, + args->layoutupdate_len); + } + } + + return 0; +} + +static void +encode_layoutreturn(struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_LAYOUTRETURN, decode_layoutreturn_maxsz, hdr); + p = reserve_space(xdr, 16); + *p++ = cpu_to_be32(0); /* reclaim. always 0 for now */ + *p++ = cpu_to_be32(args->layout_type); + *p++ = cpu_to_be32(args->range.iomode); + *p = cpu_to_be32(RETURN_FILE); + p = reserve_space(xdr, 16); + p = xdr_encode_hyper(p, args->range.offset); + p = xdr_encode_hyper(p, args->range.length); + spin_lock(&args->inode->i_lock); + encode_nfs4_stateid(xdr, &args->stateid); + spin_unlock(&args->inode->i_lock); + if (NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn) { + NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn( + NFS_I(args->inode)->layout, xdr, args); + } else + encode_uint32(xdr, 0); +} + +static int +encode_secinfo_no_name(struct xdr_stream *xdr, + const struct nfs41_secinfo_no_name_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_SECINFO_NO_NAME, decode_secinfo_no_name_maxsz, hdr); + encode_uint32(xdr, args->style); + return 0; +} + +static void encode_test_stateid(struct xdr_stream *xdr, + struct nfs41_test_stateid_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr); + encode_uint32(xdr, 1); + encode_nfs4_stateid(xdr, args->stateid); +} + +static void encode_free_stateid(struct xdr_stream *xdr, + struct nfs41_free_stateid_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->stateid); +} +#endif /* CONFIG_NFS_V4_1 */ + +/* + * END OF "GENERIC" ENCODE ROUTINES. + */ + +static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args) +{ +#if defined(CONFIG_NFS_V4_1) + struct nfs4_session *session = args->sa_slot->table->session; + if (session) + return session->clp->cl_mvops->minor_version; +#endif /* CONFIG_NFS_V4_1 */ + return 0; +} + +/* + * Encode an ACCESS request + */ +static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_accessargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_access(xdr, args->access, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode LOOKUP request + */ +static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_lookup_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->dir_fh, &hdr); + encode_lookup(xdr, args->name, &hdr); + encode_getfh(xdr, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode LOOKUP_ROOT request + */ +static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs4_lookup_root_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putrootfh(xdr, &hdr); + encode_getfh(xdr, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode REMOVE request + */ +static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs_removeargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_remove(xdr, &args->name, &hdr); + encode_nops(&hdr); +} + +/* + * Encode RENAME request + */ +static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs_renameargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->old_dir, &hdr); + encode_savefh(xdr, &hdr); + encode_putfh(xdr, args->new_dir, &hdr); + encode_rename(xdr, args->old_name, args->new_name, &hdr); + encode_nops(&hdr); +} + +/* + * Encode LINK request + */ +static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_link_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_savefh(xdr, &hdr); + encode_putfh(xdr, args->dir_fh, &hdr); + encode_link(xdr, args->name, &hdr); + encode_restorefh(xdr, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode CREATE request + */ +static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_create_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->dir_fh, &hdr); + encode_create(xdr, args, &hdr); + encode_getfh(xdr, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode SYMLINK request + */ +static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_create_arg *args) +{ + nfs4_xdr_enc_create(req, xdr, args); +} + +/* + * Encode GETATTR request + */ +static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_getattr_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode a CLOSE request + */ +static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_closeargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_close(xdr, args, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode an OPEN request + */ +static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_openargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_open(xdr, args, &hdr); + encode_getfh(xdr, &hdr); + if (args->access) + encode_access(xdr, args->access, &hdr); + encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr); + encode_nops(&hdr); +} + +/* + * Encode an OPEN_CONFIRM request + */ +static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_open_confirmargs *args) +{ + struct compound_hdr hdr = { + .nops = 0, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_open_confirm(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode an OPEN request with no attributes. + */ +static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_openargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_open(xdr, args, &hdr); + if (args->access) + encode_access(xdr, args->access, &hdr); + encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr); + encode_nops(&hdr); +} + +/* + * Encode an OPEN_DOWNGRADE request + */ +static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_closeargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_open_downgrade(xdr, args, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode a LOCK request + */ +static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_lock_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_lock(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode a LOCKT request + */ +static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_lockt_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_lockt(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode a LOCKU request + */ +static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_locku_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_locku(xdr, args, &hdr); + encode_nops(&hdr); +} + +static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_release_lockowner_args *args) +{ + struct compound_hdr hdr = { + .minorversion = 0, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_release_lockowner(xdr, &args->lock_owner, &hdr); + encode_nops(&hdr); +} + +/* + * Encode a READLINK request + */ +static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_readlink *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_readlink(xdr, args, req, &hdr); + + xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages, + args->pgbase, args->pglen); + encode_nops(&hdr); +} + +/* + * Encode a READDIR request + */ +static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_readdir_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_readdir(xdr, args, req, &hdr); + + xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages, + args->pgbase, args->count); + dprintk("%s: inlined page args = (%u, %p, %u, %u)\n", + __func__, hdr.replen << 2, args->pages, + args->pgbase, args->count); + encode_nops(&hdr); +} + +/* + * Encode a READ request + */ +static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_pgio_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_read(xdr, args, &hdr); + + xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, + args->pages, args->pgbase, args->count); + req->rq_rcv_buf.flags |= XDRBUF_READ; + encode_nops(&hdr); +} + +/* + * Encode an SETATTR request + */ +static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_setattrargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_setattr(xdr, args, args->server, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode a GETACL request + */ +static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_getaclargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + uint32_t replen; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + replen = hdr.replen + op_decode_hdr_maxsz + 1; + encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr); + + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, + args->acl_pages, args->acl_pgbase, args->acl_len); + + encode_nops(&hdr); +} + +/* + * Encode a WRITE request + */ +static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_pgio_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_write(xdr, args, &hdr); + req->rq_snd_buf.flags |= XDRBUF_WRITE; + if (args->bitmask) + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * a COMMIT request + */ +static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_commitargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_commit(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * FSINFO request + */ +static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs4_fsinfo_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_fsinfo(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * a PATHCONF request + */ +static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_pathconf_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getattr_one(xdr, args->bitmask[0] & nfs4_pathconf_bitmap[0], + &hdr); + encode_nops(&hdr); +} + +/* + * a STATFS request + */ +static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct nfs4_statfs_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getattr_two(xdr, args->bitmask[0] & nfs4_statfs_bitmap[0], + args->bitmask[1] & nfs4_statfs_bitmap[1], &hdr); + encode_nops(&hdr); +} + +/* + * GETATTR_BITMAP request + */ +static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_server_caps_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fhandle, &hdr); + encode_getattr_one(xdr, FATTR4_WORD0_SUPPORTED_ATTRS| + FATTR4_WORD0_FH_EXPIRE_TYPE| + FATTR4_WORD0_LINK_SUPPORT| + FATTR4_WORD0_SYMLINK_SUPPORT| + FATTR4_WORD0_ACLSUPPORT, &hdr); + encode_nops(&hdr); +} + +/* + * a RENEW request + */ +static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .nops = 0, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_renew(xdr, clp->cl_clientid, &hdr); + encode_nops(&hdr); +} + +/* + * a SETCLIENTID request + */ +static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_setclientid *sc) +{ + struct compound_hdr hdr = { + .nops = 0, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_setclientid(xdr, sc, &hdr); + encode_nops(&hdr); +} + +/* + * a SETCLIENTID_CONFIRM request + */ +static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_setclientid_res *arg) +{ + struct compound_hdr hdr = { + .nops = 0, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_setclientid_confirm(xdr, arg, &hdr); + encode_nops(&hdr); +} + +/* + * DELEGRETURN request + */ +static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfs4_delegreturnargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fhandle, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_delegreturn(xdr, args->stateid, &hdr); + encode_nops(&hdr); +} + +/* + * Encode FS_LOCATIONS request + */ +static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_fs_locations_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + uint32_t replen; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + if (args->migration) { + encode_putfh(xdr, args->fh, &hdr); + replen = hdr.replen; + encode_fs_locations(xdr, args->bitmask, &hdr); + if (args->renew) + encode_renew(xdr, args->clientid, &hdr); + } else { + encode_putfh(xdr, args->dir_fh, &hdr); + encode_lookup(xdr, args->name, &hdr); + replen = hdr.replen; + encode_fs_locations(xdr, args->bitmask, &hdr); + } + + /* Set up reply kvec to capture returned fs_locations array. */ + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page, + 0, PAGE_SIZE); + encode_nops(&hdr); +} + +/* + * Encode SECINFO request + */ +static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_secinfo_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->dir_fh, &hdr); + encode_secinfo(xdr, args->name, &hdr); + encode_nops(&hdr); +} + +/* + * Encode FSID_PRESENT request + */ +static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_fsid_present_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getfh(xdr, &hdr); + if (args->renew) + encode_renew(xdr, args->clientid, &hdr); + encode_nops(&hdr); +} + +#if defined(CONFIG_NFS_V4_1) +/* + * BIND_CONN_TO_SESSION request + */ +static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_bind_conn_to_session_args *args) +{ + struct compound_hdr hdr = { + .minorversion = args->client->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_bind_conn_to_session(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * EXCHANGE_ID request + */ +static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_exchange_id_args *args) +{ + struct compound_hdr hdr = { + .minorversion = args->client->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_exchange_id(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * a CREATE_SESSION request + */ +static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_create_session_args *args) +{ + struct compound_hdr hdr = { + .minorversion = args->client->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_create_session(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * a DESTROY_SESSION request + */ +static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_session *session) +{ + struct compound_hdr hdr = { + .minorversion = session->clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_destroy_session(xdr, session, &hdr); + encode_nops(&hdr); +} + +/* + * a DESTROY_CLIENTID request + */ +static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_destroy_clientid(xdr, clp->cl_clientid, &hdr); + encode_nops(&hdr); +} + +/* + * a SEQUENCE request + */ +static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs4_sequence_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * a GET_LEASE_TIME request + */ +static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_get_lease_time_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->la_seq_args), + }; + const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->la_seq_args, &hdr); + encode_putrootfh(xdr, &hdr); + encode_fsinfo(xdr, lease_bitmap, &hdr); + encode_nops(&hdr); +} + +/* + * a RECLAIM_COMPLETE request + */ +static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_reclaim_complete_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args) + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_reclaim_complete(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode GETDEVICEINFO request + */ +static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_getdeviceinfo_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_getdeviceinfo(xdr, args, &hdr); + + /* set up reply kvec. Subtract notification bitmap max size (2) + * so that notification bitmap is put in xdr_buf tail */ + xdr_inline_pages(&req->rq_rcv_buf, (hdr.replen - 2) << 2, + args->pdev->pages, args->pdev->pgbase, + args->pdev->pglen); + + encode_nops(&hdr); +} + +/* + * Encode LAYOUTGET request + */ +static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_layoutget_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, NFS_FH(args->inode), &hdr); + encode_layoutget(xdr, args, &hdr); + + xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, + args->layout.pages, 0, args->layout.pglen); + + encode_nops(&hdr); +} + +/* + * Encode LAYOUTCOMMIT request + */ +static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_layoutcommit_args *args) +{ + struct nfs4_layoutcommit_data *data = + container_of(args, struct nfs4_layoutcommit_data, args); + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, NFS_FH(args->inode), &hdr); + encode_layoutcommit(xdr, data->args.inode, args, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* + * Encode LAYOUTRETURN request + */ +static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_layoutreturn_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, NFS_FH(args->inode), &hdr); + encode_layoutreturn(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode SECINFO_NO_NAME request + */ +static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_secinfo_no_name_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putrootfh(xdr, &hdr); + encode_secinfo_no_name(xdr, args, &hdr); + encode_nops(&hdr); + return 0; +} + +/* + * Encode TEST_STATEID request + */ +static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_test_stateid_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_test_stateid(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode FREE_STATEID request + */ +static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs41_free_stateid_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_free_stateid(xdr, args, &hdr); + encode_nops(&hdr); +} +#endif /* CONFIG_NFS_V4_1 */ + +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("nfs: %s: prematurely hit end of receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); +} + +static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, *len); + if (unlikely(!p)) + goto out_overflow; + *string = (char *)p; + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + hdr->status = be32_to_cpup(p++); + hdr->taglen = be32_to_cpup(p); + + p = xdr_inline_decode(xdr, hdr->taglen + 4); + if (unlikely(!p)) + goto out_overflow; + hdr->tag = (char *)p; + p += XDR_QUADLEN(hdr->taglen); + hdr->nops = be32_to_cpup(p); + if (unlikely(hdr->nops < 1)) + return nfs4_stat_to_errno(hdr->status); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected, + int *nfs_retval) +{ + __be32 *p; + uint32_t opnum; + int32_t nfserr; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + opnum = be32_to_cpup(p++); + if (unlikely(opnum != expected)) + goto out_bad_operation; + nfserr = be32_to_cpup(p); + if (nfserr == NFS_OK) + *nfs_retval = 0; + else + *nfs_retval = nfs4_stat_to_errno(nfserr); + return true; +out_bad_operation: + dprintk("nfs: Server returned operation" + " %d but we issued a request for %d\n", + opnum, expected); + *nfs_retval = -EREMOTEIO; + return false; +out_overflow: + print_overflow_msg(__func__, xdr); + *nfs_retval = -EIO; + return false; +} + +static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) +{ + int retval; + + __decode_op_hdr(xdr, expected, &retval); + return retval; +} + +/* Dummy routine */ +static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp) +{ + __be32 *p; + unsigned int strlen; + char *str; + + p = xdr_inline_decode(xdr, 12); + if (likely(p)) + return decode_opaque_inline(xdr, &strlen, &str); + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) +{ + uint32_t bmlen; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bmlen = be32_to_cpup(p); + + bitmap[0] = bitmap[1] = bitmap[2] = 0; + p = xdr_inline_decode(xdr, (bmlen << 2)); + if (unlikely(!p)) + goto out_overflow; + if (bmlen > 0) { + bitmap[0] = be32_to_cpup(p++); + if (bmlen > 1) { + bitmap[1] = be32_to_cpup(p++); + if (bmlen > 2) + bitmap[2] = be32_to_cpup(p); + } + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, unsigned int *savep) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *attrlen = be32_to_cpup(p); + *savep = xdr_stream_pos(xdr); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask) +{ + if (likely(bitmap[0] & FATTR4_WORD0_SUPPORTED_ATTRS)) { + int ret; + ret = decode_attr_bitmap(xdr, bitmask); + if (unlikely(ret < 0)) + return ret; + bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS; + } else + bitmask[0] = bitmask[1] = bitmask[2] = 0; + dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__, + bitmask[0], bitmask[1], bitmask[2]); + return 0; +} + +static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *type) +{ + __be32 *p; + int ret = 0; + + *type = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_TYPE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_TYPE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *type = be32_to_cpup(p); + if (*type < NF4REG || *type > NF4NAMEDATTR) { + dprintk("%s: bad type %d\n", __func__, *type); + return -EIO; + } + bitmap[0] &= ~FATTR4_WORD0_TYPE; + ret = NFS_ATTR_FATTR_TYPE; + } + dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_fh_expire_type(struct xdr_stream *xdr, + uint32_t *bitmap, uint32_t *type) +{ + __be32 *p; + + *type = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_FH_EXPIRE_TYPE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FH_EXPIRE_TYPE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *type = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_FH_EXPIRE_TYPE; + } + dprintk("%s: expire type=0x%x\n", __func__, *type); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change) +{ + __be32 *p; + int ret = 0; + + *change = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CHANGE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CHANGE)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, change); + bitmap[0] &= ~FATTR4_WORD0_CHANGE; + ret = NFS_ATTR_FATTR_CHANGE; + } + dprintk("%s: change attribute=%Lu\n", __func__, + (unsigned long long)*change); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size) +{ + __be32 *p; + int ret = 0; + + *size = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_SIZE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_SIZE)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, size); + bitmap[0] &= ~FATTR4_WORD0_SIZE; + ret = NFS_ATTR_FATTR_SIZE; + } + dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_LINK_SUPPORT - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_LINK_SUPPORT)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT; + } + dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_SYMLINK_SUPPORT - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_SYMLINK_SUPPORT)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT; + } + dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid) +{ + __be32 *p; + int ret = 0; + + fsid->major = 0; + fsid->minor = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_FSID - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FSID)) { + p = xdr_inline_decode(xdr, 16); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &fsid->major); + xdr_decode_hyper(p, &fsid->minor); + bitmap[0] &= ~FATTR4_WORD0_FSID; + ret = NFS_ATTR_FATTR_FSID; + } + dprintk("%s: fsid=(0x%Lx/0x%Lx)\n", __func__, + (unsigned long long)fsid->major, + (unsigned long long)fsid->minor); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 60; + if (unlikely(bitmap[0] & (FATTR4_WORD0_LEASE_TIME - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_LEASE_TIME)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME; + } + dprintk("%s: file size=%u\n", __func__, (unsigned int)*res); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap, int32_t *res) +{ + __be32 *p; + + if (unlikely(bitmap[0] & (FATTR4_WORD0_RDATTR_ERROR - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_RDATTR_ERROR)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR; + *res = -be32_to_cpup(p); + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fh *fh) +{ + __be32 *p; + int len; + + if (fh != NULL) + memset(fh, 0, sizeof(*fh)); + + if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEHANDLE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FILEHANDLE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len > NFS4_FHSIZE) + return -EIO; + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (fh != NULL) { + memcpy(fh->data, p, len); + fh->size = len; + } + bitmap[0] &= ~FATTR4_WORD0_FILEHANDLE; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT; + } + dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) +{ + __be32 *p; + int ret = 0; + + *fileid = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEID - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FILEID)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, fileid); + bitmap[0] &= ~FATTR4_WORD0_FILEID; + ret = NFS_ATTR_FATTR_FILEID; + } + dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) +{ + __be32 *p; + int ret = 0; + + *fileid = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, fileid); + bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; + ret = NFS_ATTR_FATTR_MOUNTED_ON_FILEID; + } + dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_AVAIL - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FILES_AVAIL)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL; + } + dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_FREE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FILES_FREE)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[0] &= ~FATTR4_WORD0_FILES_FREE; + } + dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_TOTAL - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FILES_TOTAL)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL; + } + dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) +{ + u32 n; + __be32 *p; + int status = 0; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + n = be32_to_cpup(p); + if (n == 0) + goto root_path; + dprintk("pathname4: "); + if (n > NFS4_PATHNAME_MAXCOMPONENTS) { + dprintk("cannot parse %d components in path\n", n); + goto out_eio; + } + for (path->ncomponents = 0; path->ncomponents < n; path->ncomponents++) { + struct nfs4_string *component = &path->components[path->ncomponents]; + status = decode_opaque_inline(xdr, &component->len, &component->data); + if (unlikely(status != 0)) + goto out_eio; + ifdebug (XDR) + pr_cont("%s%.*s ", + (path->ncomponents != n ? "/ " : ""), + component->len, component->data); + } +out: + return status; +root_path: +/* a root pathname is sent as a zero component4 */ + path->ncomponents = 1; + path->components[0].len=0; + path->components[0].data=NULL; + dprintk("pathname4: /\n"); + goto out; +out_eio: + dprintk(" status %d", status); + status = -EIO; + goto out; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fs_locations *res) +{ + int n; + __be32 *p; + int status = -EIO; + + if (unlikely(bitmap[0] & (FATTR4_WORD0_FS_LOCATIONS -1U))) + goto out; + status = 0; + if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS))) + goto out; + status = -EIO; + /* Ignore borken servers that return unrequested attrs */ + if (unlikely(res == NULL)) + goto out; + dprintk("%s: fsroot:\n", __func__); + status = decode_pathname(xdr, &res->fs_path); + if (unlikely(status != 0)) + goto out; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + n = be32_to_cpup(p); + if (n <= 0) + goto out_eio; + for (res->nlocations = 0; res->nlocations < n; res->nlocations++) { + u32 m; + struct nfs4_fs_location *loc; + + if (res->nlocations == NFS4_FS_LOCATIONS_MAXENTRIES) + break; + loc = &res->locations[res->nlocations]; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + m = be32_to_cpup(p); + + dprintk("%s: servers:\n", __func__); + for (loc->nservers = 0; loc->nservers < m; loc->nservers++) { + struct nfs4_string *server; + + if (loc->nservers == NFS4_FS_LOCATION_MAXSERVERS) { + unsigned int i; + dprintk("%s: using first %u of %u servers " + "returned for location %u\n", + __func__, + NFS4_FS_LOCATION_MAXSERVERS, + m, res->nlocations); + for (i = loc->nservers; i < m; i++) { + unsigned int len; + char *data; + status = decode_opaque_inline(xdr, &len, &data); + if (unlikely(status != 0)) + goto out_eio; + } + break; + } + server = &loc->servers[loc->nservers]; + status = decode_opaque_inline(xdr, &server->len, &server->data); + if (unlikely(status != 0)) + goto out_eio; + dprintk("%s ", server->data); + } + status = decode_pathname(xdr, &loc->rootpath); + if (unlikely(status != 0)) + goto out_eio; + } + if (res->nlocations != 0) + status = NFS_ATTR_FATTR_V4_LOCATIONS; +out: + dprintk("%s: fs_locations done, error = %d\n", __func__, status); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); +out_eio: + status = -EIO; + goto out; +} + +static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXFILESIZE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_MAXFILESIZE)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE; + } + dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxlink) +{ + __be32 *p; + int status = 0; + + *maxlink = 1; + if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXLINK - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_MAXLINK)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *maxlink = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_MAXLINK; + } + dprintk("%s: maxlink=%u\n", __func__, *maxlink); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxname) +{ + __be32 *p; + int status = 0; + + *maxname = 1024; + if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXNAME - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_MAXNAME)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *maxname = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_MAXNAME; + } + dprintk("%s: maxname=%u\n", __func__, *maxname); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + int status = 0; + + *res = 1024; + if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXREAD - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_MAXREAD)) { + uint64_t maxread; + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, &maxread); + if (maxread > 0x7FFFFFFF) + maxread = 0x7FFFFFFF; + *res = (uint32_t)maxread; + bitmap[0] &= ~FATTR4_WORD0_MAXREAD; + } + dprintk("%s: maxread=%lu\n", __func__, (unsigned long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + int status = 0; + + *res = 1024; + if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXWRITE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_MAXWRITE)) { + uint64_t maxwrite; + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, &maxwrite); + if (maxwrite > 0x7FFFFFFF) + maxwrite = 0x7FFFFFFF; + *res = (uint32_t)maxwrite; + bitmap[0] &= ~FATTR4_WORD0_MAXWRITE; + } + dprintk("%s: maxwrite=%lu\n", __func__, (unsigned long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode) +{ + uint32_t tmp; + __be32 *p; + int ret = 0; + + *mode = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_MODE - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_MODE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + tmp = be32_to_cpup(p); + *mode = tmp & ~S_IFMT; + bitmap[1] &= ~FATTR4_WORD1_MODE; + ret = NFS_ATTR_FATTR_MODE; + } + dprintk("%s: file mode=0%o\n", __func__, (unsigned int)*mode); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink) +{ + __be32 *p; + int ret = 0; + + *nlink = 1; + if (unlikely(bitmap[1] & (FATTR4_WORD1_NUMLINKS - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_NUMLINKS)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *nlink = be32_to_cpup(p); + bitmap[1] &= ~FATTR4_WORD1_NUMLINKS; + ret = NFS_ATTR_FATTR_NLINK; + } + dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, + const struct nfs_server *server, kuid_t *uid, + struct nfs4_string *owner_name) +{ + uint32_t len; + __be32 *p; + int ret = 0; + + *uid = make_kuid(&init_user_ns, -2); + if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (owner_name != NULL) { + owner_name->data = kmemdup(p, len, GFP_NOWAIT); + if (owner_name->data != NULL) { + owner_name->len = len; + ret = NFS_ATTR_FATTR_OWNER_NAME; + } + } else if (len < XDR_MAX_NETOBJ) { + if (nfs_map_name_to_uid(server, (char *)p, len, uid) == 0) + ret = NFS_ATTR_FATTR_OWNER; + else + dprintk("%s: nfs_map_name_to_uid failed!\n", + __func__); + } else + dprintk("%s: name too long (%u)!\n", + __func__, len); + bitmap[1] &= ~FATTR4_WORD1_OWNER; + } + dprintk("%s: uid=%d\n", __func__, (int)from_kuid(&init_user_ns, *uid)); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, + const struct nfs_server *server, kgid_t *gid, + struct nfs4_string *group_name) +{ + uint32_t len; + __be32 *p; + int ret = 0; + + *gid = make_kgid(&init_user_ns, -2); + if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (group_name != NULL) { + group_name->data = kmemdup(p, len, GFP_NOWAIT); + if (group_name->data != NULL) { + group_name->len = len; + ret = NFS_ATTR_FATTR_GROUP_NAME; + } + } else if (len < XDR_MAX_NETOBJ) { + if (nfs_map_group_to_gid(server, (char *)p, len, gid) == 0) + ret = NFS_ATTR_FATTR_GROUP; + else + dprintk("%s: nfs_map_group_to_gid failed!\n", + __func__); + } else + dprintk("%s: name too long (%u)!\n", + __func__, len); + bitmap[1] &= ~FATTR4_WORD1_OWNER_GROUP; + } + dprintk("%s: gid=%d\n", __func__, (int)from_kgid(&init_user_ns, *gid)); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev) +{ + uint32_t major = 0, minor = 0; + __be32 *p; + int ret = 0; + + *rdev = MKDEV(0,0); + if (unlikely(bitmap[1] & (FATTR4_WORD1_RAWDEV - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_RAWDEV)) { + dev_t tmp; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + major = be32_to_cpup(p++); + minor = be32_to_cpup(p); + tmp = MKDEV(major, minor); + if (MAJOR(tmp) == major && MINOR(tmp) == minor) + *rdev = tmp; + bitmap[1] &= ~ FATTR4_WORD1_RAWDEV; + ret = NFS_ATTR_FATTR_RDEV; + } + dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_AVAIL - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_SPACE_AVAIL)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL; + } + dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_FREE - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_SPACE_FREE)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE; + } + dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) +{ + __be32 *p; + int status = 0; + + *res = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_TOTAL - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_SPACE_TOTAL)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL; + } + dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used) +{ + __be32 *p; + int ret = 0; + + *used = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_USED - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_SPACE_USED)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, used); + bitmap[1] &= ~FATTR4_WORD1_SPACE_USED; + ret = NFS_ATTR_FATTR_SPACE_USED; + } + dprintk("%s: space used=%Lu\n", __func__, + (unsigned long long)*used); + return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) +{ + __be32 *p; + uint64_t sec; + uint32_t nsec; + + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &sec); + nsec = be32_to_cpup(p); + time->tv_sec = (time_t)sec; + time->tv_nsec = (long)nsec; + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +{ + int status = 0; + + time->tv_sec = 0; + time->tv_nsec = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_ACCESS - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_TIME_ACCESS)) { + status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_ATIME; + bitmap[1] &= ~FATTR4_WORD1_TIME_ACCESS; + } + dprintk("%s: atime=%ld\n", __func__, (long)time->tv_sec); + return status; +} + +static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +{ + int status = 0; + + time->tv_sec = 0; + time->tv_nsec = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_METADATA - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_TIME_METADATA)) { + status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_CTIME; + bitmap[1] &= ~FATTR4_WORD1_TIME_METADATA; + } + dprintk("%s: ctime=%ld\n", __func__, (long)time->tv_sec); + return status; +} + +static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap, + struct timespec *time) +{ + int status = 0; + + time->tv_sec = 0; + time->tv_nsec = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_DELTA - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_TIME_DELTA)) { + status = decode_attr_time(xdr, time); + bitmap[1] &= ~FATTR4_WORD1_TIME_DELTA; + } + dprintk("%s: time_delta=%ld %ld\n", __func__, (long)time->tv_sec, + (long)time->tv_nsec); + return status; +} + +static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs4_label *label) +{ + uint32_t pi = 0; + uint32_t lfs = 0; + __u32 len; + __be32 *p; + int status = 0; + + if (unlikely(bitmap[2] & (FATTR4_WORD2_SECURITY_LABEL - 1U))) + return -EIO; + if (likely(bitmap[2] & FATTR4_WORD2_SECURITY_LABEL)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + lfs = be32_to_cpup(p++); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + pi = be32_to_cpup(p++); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p++); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (len < NFS4_MAXLABELLEN) { + if (label) { + memcpy(label->label, p, len); + label->len = len; + label->pi = pi; + label->lfs = lfs; + status = NFS_ATTR_FATTR_V4_SECURITY_LABEL; + } + bitmap[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + } else + printk(KERN_WARNING "%s: label too long (%u)!\n", + __func__, len); + } + if (label && label->label) + dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__, + (char *)label->label, label->len, label->pi, label->lfs); + return status; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +{ + int status = 0; + + time->tv_sec = 0; + time->tv_nsec = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_MODIFY - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_TIME_MODIFY)) { + status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_MTIME; + bitmap[1] &= ~FATTR4_WORD1_TIME_MODIFY; + } + dprintk("%s: mtime=%ld\n", __func__, (long)time->tv_sec); + return status; +} + +static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen) +{ + unsigned int attrwords = XDR_QUADLEN(attrlen); + unsigned int nwords = (xdr_stream_pos(xdr) - savep) >> 2; + + if (unlikely(attrwords != nwords)) { + dprintk("%s: server returned incorrect attribute length: " + "%u %c %u\n", + __func__, + attrwords << 2, + (attrwords < nwords) ? '<' : '>', + nwords << 2); + return -EIO; + } + return 0; +} + +static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 20); + if (unlikely(!p)) + goto out_overflow; + cinfo->atomic = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &cinfo->before); + xdr_decode_hyper(p, &cinfo->after); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access) +{ + __be32 *p; + uint32_t supp, acc; + int status; + + status = decode_op_hdr(xdr, OP_ACCESS); + if (status) + return status; + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + supp = be32_to_cpup(p++); + acc = be32_to_cpup(p); + *supported = supp; + *access = acc; + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, len); + if (likely(p)) { + memcpy(buf, p, len); + return 0; + } + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE); +} + +static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res) +{ + int status; + + status = decode_op_hdr(xdr, OP_CLOSE); + if (status != -EIO) + nfs_increment_open_seqid(status, res->seqid); + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; +} + +static int decode_verifier(struct xdr_stream *xdr, void *verifier) +{ + return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE); +} + +static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifier *verifier) +{ + return decode_opaque_fixed(xdr, verifier->data, NFS4_VERIFIER_SIZE); +} + +static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res) +{ + int status; + + status = decode_op_hdr(xdr, OP_COMMIT); + if (!status) + status = decode_write_verifier(xdr, &res->verf->verifier); + return status; +} + +static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) +{ + __be32 *p; + uint32_t bmlen; + int status; + + status = decode_op_hdr(xdr, OP_CREATE); + if (status) + return status; + if ((status = decode_change_info(xdr, cinfo))) + return status; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bmlen = be32_to_cpup(p); + p = xdr_inline_decode(xdr, bmlen << 2); + if (likely(p)) + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res) +{ + unsigned int savep; + uint32_t attrlen, bitmap[3] = {0}; + int status; + + if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) + goto xdr_error; + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) + goto xdr_error; + if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) + goto xdr_error; + if ((status = decode_attr_supported(xdr, bitmap, res->attr_bitmask)) != 0) + goto xdr_error; + if ((status = decode_attr_fh_expire_type(xdr, bitmap, + &res->fh_expire_type)) != 0) + goto xdr_error; + if ((status = decode_attr_link_support(xdr, bitmap, &res->has_links)) != 0) + goto xdr_error; + if ((status = decode_attr_symlink_support(xdr, bitmap, &res->has_symlinks)) != 0) + goto xdr_error; + if ((status = decode_attr_aclsupport(xdr, bitmap, &res->acl_bitmask)) != 0) + goto xdr_error; + status = verify_attr_len(xdr, savep, attrlen); +xdr_error: + dprintk("%s: xdr returned %d!\n", __func__, -status); + return status; +} + +static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat) +{ + unsigned int savep; + uint32_t attrlen, bitmap[3] = {0}; + int status; + + if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) + goto xdr_error; + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) + goto xdr_error; + if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) + goto xdr_error; + + if ((status = decode_attr_files_avail(xdr, bitmap, &fsstat->afiles)) != 0) + goto xdr_error; + if ((status = decode_attr_files_free(xdr, bitmap, &fsstat->ffiles)) != 0) + goto xdr_error; + if ((status = decode_attr_files_total(xdr, bitmap, &fsstat->tfiles)) != 0) + goto xdr_error; + if ((status = decode_attr_space_avail(xdr, bitmap, &fsstat->abytes)) != 0) + goto xdr_error; + if ((status = decode_attr_space_free(xdr, bitmap, &fsstat->fbytes)) != 0) + goto xdr_error; + if ((status = decode_attr_space_total(xdr, bitmap, &fsstat->tbytes)) != 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); +xdr_error: + dprintk("%s: xdr returned %d!\n", __func__, -status); + return status; +} + +static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf) +{ + unsigned int savep; + uint32_t attrlen, bitmap[3] = {0}; + int status; + + if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) + goto xdr_error; + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) + goto xdr_error; + if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) + goto xdr_error; + + if ((status = decode_attr_maxlink(xdr, bitmap, &pathconf->max_link)) != 0) + goto xdr_error; + if ((status = decode_attr_maxname(xdr, bitmap, &pathconf->max_namelen)) != 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); +xdr_error: + dprintk("%s: xdr returned %d!\n", __func__, -status); + return status; +} + +static int decode_threshold_hint(struct xdr_stream *xdr, + uint32_t *bitmap, + uint64_t *res, + uint32_t hint_bit) +{ + __be32 *p; + + *res = 0; + if (likely(bitmap[0] & hint_bit)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_first_threshold_item4(struct xdr_stream *xdr, + struct nfs4_threshold *res) +{ + __be32 *p; + unsigned int savep; + uint32_t bitmap[3] = {0,}, attrlen; + int status; + + /* layout type */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + res->l_type = be32_to_cpup(p); + + /* thi_hintset bitmap */ + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; + + /* thi_hintlist length */ + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) + goto xdr_error; + /* thi_hintlist */ + status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz, + THRESHOLD_RD_IO); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz, + THRESHOLD_WR_IO); + if (status < 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); + res->bm = bitmap[0]; + + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n", + __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz, + res->wr_io_sz); +xdr_error: + dprintk("%s ret=%d!\n", __func__, status); + return status; +} + +/* + * Thresholds on pNFS direct I/O vrs MDS I/O + */ +static int decode_attr_mdsthreshold(struct xdr_stream *xdr, + uint32_t *bitmap, + struct nfs4_threshold *res) +{ + __be32 *p; + int status = 0; + uint32_t num; + + if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U))) + return -EIO; + if (bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD) { + /* Did the server return an unrequested attribute? */ + if (unlikely(res == NULL)) + return -EREMOTEIO; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + if (num == 0) + return 0; + if (num > 1) + printk(KERN_INFO "%s: Warning: Multiple pNFS layout " + "drivers per filesystem not supported\n", + __func__); + + status = decode_first_threshold_item4(xdr, res); + bitmap[2] &= ~FATTR4_WORD2_MDSTHRESHOLD; + } + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs_fattr *fattr, struct nfs_fh *fh, + struct nfs4_fs_locations *fs_loc, struct nfs4_label *label, + const struct nfs_server *server) +{ + int status; + umode_t fmode = 0; + uint32_t type; + int32_t err; + + status = decode_attr_type(xdr, bitmap, &type); + if (status < 0) + goto xdr_error; + fattr->mode = 0; + if (status != 0) { + fattr->mode |= nfs_type2fmt[type]; + fattr->valid |= status; + } + + status = decode_attr_change(xdr, bitmap, &fattr->change_attr); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_size(xdr, bitmap, &fattr->size); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_fsid(xdr, bitmap, &fattr->fsid); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + err = 0; + status = decode_attr_error(xdr, bitmap, &err); + if (status < 0) + goto xdr_error; + + status = decode_attr_filehandle(xdr, bitmap, fh); + if (status < 0) + goto xdr_error; + + status = decode_attr_fileid(xdr, bitmap, &fattr->fileid); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_fs_locations(xdr, bitmap, fs_loc); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_mode(xdr, bitmap, &fmode); + if (status < 0) + goto xdr_error; + if (status != 0) { + fattr->mode |= fmode; + fattr->valid |= status; + } + + status = decode_attr_nlink(xdr, bitmap, &fattr->nlink); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_owner(xdr, bitmap, server, &fattr->uid, fattr->owner_name); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_group(xdr, bitmap, server, &fattr->gid, fattr->group_name); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_rdev(xdr, bitmap, &fattr->rdev); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_space_used(xdr, bitmap, &fattr->du.nfs3.used); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_time_access(xdr, bitmap, &fattr->atime); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_time_modify(xdr, bitmap, &fattr->mtime); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_mounted_on_fileid(xdr, bitmap, &fattr->mounted_on_fileid); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + + status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold); + if (status < 0) + goto xdr_error; + + if (label) { + status = decode_attr_security_label(xdr, bitmap, label); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + } + +xdr_error: + dprintk("%s: xdr returned %d\n", __func__, -status); + return status; +} + +static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc, + struct nfs4_label *label, const struct nfs_server *server) +{ + unsigned int savep; + uint32_t attrlen, + bitmap[3] = {0}; + int status; + + status = decode_op_hdr(xdr, OP_GETATTR); + if (status < 0) + goto xdr_error; + + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; + + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) + goto xdr_error; + + status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc, + label, server); + if (status < 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); +xdr_error: + dprintk("%s: xdr returned %d\n", __func__, -status); + return status; +} + +static int decode_getfattr_label(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct nfs4_label *label, const struct nfs_server *server) +{ + return decode_getfattr_generic(xdr, fattr, NULL, NULL, label, server); +} + +static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, + const struct nfs_server *server) +{ + return decode_getfattr_generic(xdr, fattr, NULL, NULL, NULL, server); +} + +/* + * Decode potentially multiple layout types. Currently we only support + * one layout driver per file system. + */ +static int decode_first_pnfs_layout_type(struct xdr_stream *xdr, + uint32_t *layouttype) +{ + __be32 *p; + int num; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + + /* pNFS is not supported by the underlying file system */ + if (num == 0) { + *layouttype = 0; + return 0; + } + if (num > 1) + printk(KERN_INFO "NFS: %s: Warning: Multiple pNFS layout " + "drivers per filesystem not supported\n", __func__); + + /* Decode and set first layout type, move xdr->p past unused types */ + p = xdr_inline_decode(xdr, num * 4); + if (unlikely(!p)) + goto out_overflow; + *layouttype = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * The type of file system exported. + * Note we must ensure that layouttype is set in any non-error case. + */ +static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *layouttype) +{ + int status = 0; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[1]); + if (unlikely(bitmap[1] & (FATTR4_WORD1_FS_LAYOUT_TYPES - 1U))) + return -EIO; + if (bitmap[1] & FATTR4_WORD1_FS_LAYOUT_TYPES) { + status = decode_first_pnfs_layout_type(xdr, layouttype); + bitmap[1] &= ~FATTR4_WORD1_FS_LAYOUT_TYPES; + } else + *layouttype = 0; + return status; +} + +/* + * The prefered block size for layout directed io + */ +static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *res) +{ + __be32 *p; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[2]); + *res = 0; + if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + *res = be32_to_cpup(p); + bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE; + } + return 0; +} + +static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) +{ + unsigned int savep; + uint32_t attrlen, bitmap[3]; + int status; + + if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) + goto xdr_error; + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) + goto xdr_error; + if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) + goto xdr_error; + + fsinfo->rtmult = fsinfo->wtmult = 512; /* ??? */ + + if ((status = decode_attr_lease_time(xdr, bitmap, &fsinfo->lease_time)) != 0) + goto xdr_error; + if ((status = decode_attr_maxfilesize(xdr, bitmap, &fsinfo->maxfilesize)) != 0) + goto xdr_error; + if ((status = decode_attr_maxread(xdr, bitmap, &fsinfo->rtmax)) != 0) + goto xdr_error; + fsinfo->rtpref = fsinfo->dtpref = fsinfo->rtmax; + if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0) + goto xdr_error; + fsinfo->wtpref = fsinfo->wtmax; + status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta); + if (status != 0) + goto xdr_error; + status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); + if (status != 0) + goto xdr_error; + status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize); + if (status) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); +xdr_error: + dprintk("%s: xdr returned %d!\n", __func__, -status); + return status; +} + +static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + uint32_t len; + int status; + + /* Zero handle first to allow comparisons */ + memset(fh, 0, sizeof(*fh)); + + status = decode_op_hdr(xdr, OP_GETFH); + if (status) + return status; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len > NFS4_FHSIZE) + return -EIO; + fh->size = len; + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + memcpy(fh->data, p, len); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_link(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) +{ + int status; + + status = decode_op_hdr(xdr, OP_LINK); + if (status) + return status; + return decode_change_info(xdr, cinfo); +} + +/* + * We create the owner, so we know a proper owner.id length is 4. + */ +static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) +{ + uint64_t offset, length, clientid; + __be32 *p; + uint32_t namelen, type; + + p = xdr_inline_decode(xdr, 32); /* read 32 bytes */ + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &offset); /* read 2 8-byte long words */ + p = xdr_decode_hyper(p, &length); + type = be32_to_cpup(p++); /* 4 byte read */ + if (fl != NULL) { /* manipulate file lock */ + fl->fl_start = (loff_t)offset; + fl->fl_end = fl->fl_start + (loff_t)length - 1; + if (length == ~(uint64_t)0) + fl->fl_end = OFFSET_MAX; + fl->fl_type = F_WRLCK; + if (type & 1) + fl->fl_type = F_RDLCK; + fl->fl_pid = 0; + } + p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */ + namelen = be32_to_cpup(p); /* read 4 bytes */ /* have read all 32 bytes now */ + p = xdr_inline_decode(xdr, namelen); /* variable size field */ + if (likely(p)) + return -NFS4ERR_DENIED; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res) +{ + int status; + + status = decode_op_hdr(xdr, OP_LOCK); + if (status == -EIO) + goto out; + if (status == 0) { + status = decode_stateid(xdr, &res->stateid); + if (unlikely(status)) + goto out; + } else if (status == -NFS4ERR_DENIED) + status = decode_lock_denied(xdr, NULL); + if (res->open_seqid != NULL) + nfs_increment_open_seqid(status, res->open_seqid); + nfs_increment_lock_seqid(status, res->lock_seqid); +out: + return status; +} + +static int decode_lockt(struct xdr_stream *xdr, struct nfs_lockt_res *res) +{ + int status; + status = decode_op_hdr(xdr, OP_LOCKT); + if (status == -NFS4ERR_DENIED) + return decode_lock_denied(xdr, res->denied); + return status; +} + +static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res) +{ + int status; + + status = decode_op_hdr(xdr, OP_LOCKU); + if (status != -EIO) + nfs_increment_lock_seqid(status, res->seqid); + if (status == 0) + status = decode_stateid(xdr, &res->stateid); + return status; +} + +static int decode_release_lockowner(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_RELEASE_LOCKOWNER); +} + +static int decode_lookup(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_LOOKUP); +} + +/* This is too sick! */ +static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) +{ + __be32 *p; + uint32_t limit_type, nblocks, blocksize; + + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + limit_type = be32_to_cpup(p++); + switch (limit_type) { + case 1: + xdr_decode_hyper(p, maxsize); + break; + case 2: + nblocks = be32_to_cpup(p++); + blocksize = be32_to_cpup(p); + *maxsize = (uint64_t)nblocks * (uint64_t)blocksize; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_rw_delegation(struct xdr_stream *xdr, + uint32_t delegation_type, + struct nfs_openres *res) +{ + __be32 *p; + int status; + + status = decode_stateid(xdr, &res->delegation); + if (unlikely(status)) + return status; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + res->do_recall = be32_to_cpup(p); + + switch (delegation_type) { + case NFS4_OPEN_DELEGATE_READ: + res->delegation_type = FMODE_READ; + break; + case NFS4_OPEN_DELEGATE_WRITE: + res->delegation_type = FMODE_WRITE|FMODE_READ; + if (decode_space_limit(xdr, &res->maxsize) < 0) + return -EIO; + } + return decode_ace(xdr, NULL, res->server->nfs_client); +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_no_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t why_no_delegation; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + why_no_delegation = be32_to_cpup(p); + switch (why_no_delegation) { + case WND4_CONTENTION: + case WND4_RESOURCE: + xdr_inline_decode(xdr, 4); + /* Ignore for now */ + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t delegation_type; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + delegation_type = be32_to_cpup(p); + res->delegation_type = 0; + switch (delegation_type) { + case NFS4_OPEN_DELEGATE_NONE: + return 0; + case NFS4_OPEN_DELEGATE_READ: + case NFS4_OPEN_DELEGATE_WRITE: + return decode_rw_delegation(xdr, delegation_type, res); + case NFS4_OPEN_DELEGATE_NONE_EXT: + return decode_no_delegation(xdr, res); + } + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t savewords, bmlen, i; + int status; + + if (!__decode_op_hdr(xdr, OP_OPEN, &status)) + return status; + nfs_increment_open_seqid(status, res->seqid); + if (status) + return status; + status = decode_stateid(xdr, &res->stateid); + if (unlikely(status)) + return status; + + decode_change_info(xdr, &res->cinfo); + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + res->rflags = be32_to_cpup(p++); + bmlen = be32_to_cpup(p); + if (bmlen > 10) + goto xdr_error; + + p = xdr_inline_decode(xdr, bmlen << 2); + if (unlikely(!p)) + goto out_overflow; + savewords = min_t(uint32_t, bmlen, NFS4_BITMAP_SIZE); + for (i = 0; i < savewords; ++i) + res->attrset[i] = be32_to_cpup(p++); + for (; i < NFS4_BITMAP_SIZE; i++) + res->attrset[i] = 0; + + return decode_delegation(xdr, res); +xdr_error: + dprintk("%s: Bitmap too large! Length = %u\n", __func__, bmlen); + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmres *res) +{ + int status; + + status = decode_op_hdr(xdr, OP_OPEN_CONFIRM); + if (status != -EIO) + nfs_increment_open_seqid(status, res->seqid); + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; +} + +static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *res) +{ + int status; + + status = decode_op_hdr(xdr, OP_OPEN_DOWNGRADE); + if (status != -EIO) + nfs_increment_open_seqid(status, res->seqid); + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; +} + +static int decode_putfh(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_PUTFH); +} + +static int decode_putrootfh(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_PUTROOTFH); +} + +static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, + struct nfs_pgio_res *res) +{ + __be32 *p; + uint32_t count, eof, recvd; + int status; + + status = decode_op_hdr(xdr, OP_READ); + if (status) + return status; + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + eof = be32_to_cpup(p++); + count = be32_to_cpup(p); + recvd = xdr_read_pages(xdr, count); + if (count > recvd) { + dprintk("NFS: server cheating in read reply: " + "count %u > recvd %u\n", count, recvd); + count = recvd; + eof = 0; + } + res->eof = eof; + res->count = count; + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir) +{ + int status; + __be32 verf[2]; + + status = decode_op_hdr(xdr, OP_READDIR); + if (!status) + status = decode_verifier(xdr, readdir->verifier.data); + if (unlikely(status)) + return status; + memcpy(verf, readdir->verifier.data, sizeof(verf)); + dprintk("%s: verifier = %08x:%08x\n", + __func__, verf[0], verf[1]); + return xdr_read_pages(xdr, xdr->buf->page_len); +} + +static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) +{ + struct xdr_buf *rcvbuf = &req->rq_rcv_buf; + u32 len, recvd; + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_READLINK); + if (status) + return status; + + /* Convert length of symlink */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len >= rcvbuf->page_len || len <= 0) { + dprintk("nfs: server returned giant symlink!\n"); + return -ENAMETOOLONG; + } + recvd = xdr_read_pages(xdr, len); + if (recvd < len) { + dprintk("NFS: server cheating in readlink reply: " + "count %u > recvd %u\n", len, recvd); + return -EIO; + } + /* + * The XDR encode routine has set things up so that + * the link text will be copied directly into the + * buffer. We just have to do overflow-checking, + * and and null-terminate the text (the VFS expects + * null-termination). + */ + xdr_terminate_string(rcvbuf, len); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_remove(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) +{ + int status; + + status = decode_op_hdr(xdr, OP_REMOVE); + if (status) + goto out; + status = decode_change_info(xdr, cinfo); +out: + return status; +} + +static int decode_rename(struct xdr_stream *xdr, struct nfs4_change_info *old_cinfo, + struct nfs4_change_info *new_cinfo) +{ + int status; + + status = decode_op_hdr(xdr, OP_RENAME); + if (status) + goto out; + if ((status = decode_change_info(xdr, old_cinfo))) + goto out; + status = decode_change_info(xdr, new_cinfo); +out: + return status; +} + +static int decode_renew(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_RENEW); +} + +static int +decode_restorefh(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_RESTOREFH); +} + +static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, + struct nfs_getaclres *res) +{ + unsigned int savep; + uint32_t attrlen, + bitmap[3] = {0}; + int status; + unsigned int pg_offset; + + res->acl_len = 0; + if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) + goto out; + + xdr_enter_page(xdr, xdr->buf->page_len); + + /* Calculate the offset of the page data */ + pg_offset = xdr->buf->head[0].iov_len; + + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) + goto out; + if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) + goto out; + + if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_ACL)) { + + /* The bitmap (xdr len + bitmaps) and the attr xdr len words + * are stored with the acl data to handle the problem of + * variable length bitmaps.*/ + res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset; + res->acl_len = attrlen; + + /* Check for receive buffer overflow */ + if (res->acl_len > (xdr->nwords << 2) || + res->acl_len + res->acl_data_offset > xdr->buf->page_len) { + res->acl_flags |= NFS4_ACL_TRUNC; + dprintk("NFS: acl reply: attrlen %u > page_len %u\n", + attrlen, xdr->nwords << 2); + } + } else + status = -EOPNOTSUPP; + +out: + return status; +} + +static int +decode_savefh(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_SAVEFH); +} + +static int decode_setattr(struct xdr_stream *xdr) +{ + __be32 *p; + uint32_t bmlen; + int status; + + status = decode_op_hdr(xdr, OP_SETATTR); + if (status) + return status; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bmlen = be32_to_cpup(p); + p = xdr_inline_decode(xdr, bmlen << 2); + if (likely(p)) + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_setclientid(struct xdr_stream *xdr, struct nfs4_setclientid_res *res) +{ + __be32 *p; + uint32_t opnum; + int32_t nfserr; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + opnum = be32_to_cpup(p++); + if (opnum != OP_SETCLIENTID) { + dprintk("nfs: decode_setclientid: Server returned operation" + " %d\n", opnum); + return -EIO; + } + nfserr = be32_to_cpup(p); + if (nfserr == NFS_OK) { + p = xdr_inline_decode(xdr, 8 + NFS4_VERIFIER_SIZE); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &res->clientid); + memcpy(res->confirm.data, p, NFS4_VERIFIER_SIZE); + } else if (nfserr == NFSERR_CLID_INUSE) { + uint32_t len; + + /* skip netid string */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + + /* skip uaddr string */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + return -NFSERR_CLID_INUSE; + } else + return nfs4_stat_to_errno(nfserr); + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_setclientid_confirm(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM); +} + +static int decode_write(struct xdr_stream *xdr, struct nfs_pgio_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_WRITE); + if (status) + return status; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + res->count = be32_to_cpup(p++); + res->verf->committed = be32_to_cpup(p++); + return decode_write_verifier(xdr, &res->verf->verifier); +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_delegreturn(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_DELEGRETURN); +} + +static int decode_secinfo_gss(struct xdr_stream *xdr, + struct nfs4_secinfo4 *flavor) +{ + u32 oid_len; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + oid_len = be32_to_cpup(p); + if (oid_len > GSS_OID_MAX_LEN) + goto out_err; + + p = xdr_inline_decode(xdr, oid_len); + if (unlikely(!p)) + goto out_overflow; + memcpy(flavor->flavor_info.oid.data, p, oid_len); + flavor->flavor_info.oid.len = oid_len; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + flavor->flavor_info.qop = be32_to_cpup(p++); + flavor->flavor_info.service = be32_to_cpup(p); + + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +out_err: + return -EINVAL; +} + +static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + struct nfs4_secinfo4 *sec_flavor; + unsigned int i, num_flavors; + int status; + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + + res->flavors->num_flavors = 0; + num_flavors = be32_to_cpup(p); + + for (i = 0; i < num_flavors; i++) { + sec_flavor = &res->flavors->flavors[i]; + if ((char *)&sec_flavor[1] - (char *)res->flavors > PAGE_SIZE) + break; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + sec_flavor->flavor = be32_to_cpup(p); + + if (sec_flavor->flavor == RPC_AUTH_GSS) { + status = decode_secinfo_gss(xdr, sec_flavor); + if (status) + goto out; + } + res->flavors->num_flavors++; + } + + status = 0; +out: + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + int status = decode_op_hdr(xdr, OP_SECINFO); + if (status) + return status; + return decode_secinfo_common(xdr, res); +} + +#if defined(CONFIG_NFS_V4_1) +static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + int status = decode_op_hdr(xdr, OP_SECINFO_NO_NAME); + if (status) + return status; + return decode_secinfo_common(xdr, res); +} + +static int decode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +{ + __be32 *p; + uint32_t bitmap_words; + unsigned int i; + + p = xdr_inline_decode(xdr, 4); + bitmap_words = be32_to_cpup(p++); + if (bitmap_words > NFS4_OP_MAP_NUM_WORDS) + return -EIO; + p = xdr_inline_decode(xdr, 4 * bitmap_words); + for (i = 0; i < bitmap_words; i++) + op_map->u.words[i] = be32_to_cpup(p++); + + return 0; +} + +static int decode_exchange_id(struct xdr_stream *xdr, + struct nfs41_exchange_id_res *res) +{ + __be32 *p; + uint32_t dummy; + char *dummy_str; + int status; + uint32_t impl_id_count; + + status = decode_op_hdr(xdr, OP_EXCHANGE_ID); + if (status) + return status; + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, &res->clientid); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + res->seqid = be32_to_cpup(p++); + res->flags = be32_to_cpup(p++); + + res->state_protect.how = be32_to_cpup(p); + switch (res->state_protect.how) { + case SP4_NONE: + break; + case SP4_MACH_CRED: + status = decode_op_map(xdr, &res->state_protect.enforce); + if (status) + return status; + status = decode_op_map(xdr, &res->state_protect.allow); + if (status) + return status; + break; + default: + WARN_ON_ONCE(1); + return -EIO; + } + + /* server_owner4.so_minor_id */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &res->server_owner->minor_id); + + /* server_owner4.so_major_id */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->server_owner->major_id, dummy_str, dummy); + res->server_owner->major_id_sz = dummy; + + /* server_scope4 */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->server_scope->server_scope, dummy_str, dummy); + res->server_scope->server_scope_sz = dummy; + + /* Implementation Id */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + impl_id_count = be32_to_cpup(p++); + + if (impl_id_count) { + /* nii_domain */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->impl_id->domain, dummy_str, dummy); + + /* nii_name */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->impl_id->name, dummy_str, dummy); + + /* nii_date */ + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &res->impl_id->date.seconds); + res->impl_id->date.nseconds = be32_to_cpup(p); + + /* if there's more than one entry, ignore the rest */ + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_chan_attrs(struct xdr_stream *xdr, + struct nfs4_channel_attrs *attrs) +{ + __be32 *p; + u32 nr_attrs, val; + + p = xdr_inline_decode(xdr, 28); + if (unlikely(!p)) + goto out_overflow; + val = be32_to_cpup(p++); /* headerpadsz */ + if (val) + return -EINVAL; /* no support for header padding yet */ + attrs->max_rqst_sz = be32_to_cpup(p++); + attrs->max_resp_sz = be32_to_cpup(p++); + attrs->max_resp_sz_cached = be32_to_cpup(p++); + attrs->max_ops = be32_to_cpup(p++); + attrs->max_reqs = be32_to_cpup(p++); + nr_attrs = be32_to_cpup(p); + if (unlikely(nr_attrs > 1)) { + printk(KERN_WARNING "NFS: %s: Invalid rdma channel attrs " + "count %u\n", __func__, nr_attrs); + return -EINVAL; + } + if (nr_attrs == 1) { + p = xdr_inline_decode(xdr, 4); /* skip rdma_attrs */ + if (unlikely(!p)) + goto out_overflow; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) +{ + return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN); +} + +static int decode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs41_bind_conn_to_session_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION); + if (!status) + status = decode_sessionid(xdr, &res->sessionid); + if (unlikely(status)) + return status; + + /* dir flags, rdma mode bool */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + + res->dir = be32_to_cpup(p++); + if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH) + return -EIO; + if (be32_to_cpup(p) == 0) + res->use_conn_in_rdma_mode = false; + else + res->use_conn_in_rdma_mode = true; + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_create_session(struct xdr_stream *xdr, + struct nfs41_create_session_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_CREATE_SESSION); + if (!status) + status = decode_sessionid(xdr, &res->sessionid); + if (unlikely(status)) + return status; + + /* seqid, flags */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + res->seqid = be32_to_cpup(p++); + res->flags = be32_to_cpup(p); + + /* Channel attributes */ + status = decode_chan_attrs(xdr, &res->fc_attrs); + if (!status) + status = decode_chan_attrs(xdr, &res->bc_attrs); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_destroy_session(struct xdr_stream *xdr, void *dummy) +{ + return decode_op_hdr(xdr, OP_DESTROY_SESSION); +} + +static int decode_destroy_clientid(struct xdr_stream *xdr, void *dummy) +{ + return decode_op_hdr(xdr, OP_DESTROY_CLIENTID); +} + +static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy) +{ + return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE); +} +#endif /* CONFIG_NFS_V4_1 */ + +static int decode_sequence(struct xdr_stream *xdr, + struct nfs4_sequence_res *res, + struct rpc_rqst *rqstp) +{ +#if defined(CONFIG_NFS_V4_1) + struct nfs4_session *session; + struct nfs4_sessionid id; + u32 dummy; + int status; + __be32 *p; + + if (res->sr_slot == NULL) + return 0; + if (!res->sr_slot->table->session) + return 0; + + status = decode_op_hdr(xdr, OP_SEQUENCE); + if (!status) + status = decode_sessionid(xdr, &id); + if (unlikely(status)) + goto out_err; + + /* + * If the server returns different values for sessionID, slotID or + * sequence number, the server is looney tunes. + */ + status = -EREMOTEIO; + session = res->sr_slot->table->session; + + if (memcmp(id.data, session->sess_id.data, + NFS4_MAX_SESSIONID_LEN)) { + dprintk("%s Invalid session id\n", __func__); + goto out_err; + } + + p = xdr_inline_decode(xdr, 20); + if (unlikely(!p)) + goto out_overflow; + + /* seqid */ + dummy = be32_to_cpup(p++); + if (dummy != res->sr_slot->seq_nr) { + dprintk("%s Invalid sequence number\n", __func__); + goto out_err; + } + /* slot id */ + dummy = be32_to_cpup(p++); + if (dummy != res->sr_slot->slot_nr) { + dprintk("%s Invalid slot id\n", __func__); + goto out_err; + } + /* highest slot id */ + res->sr_highest_slotid = be32_to_cpup(p++); + /* target highest slot id */ + res->sr_target_highest_slotid = be32_to_cpup(p++); + /* result flags */ + res->sr_status_flags = be32_to_cpup(p); + status = 0; +out_err: + res->sr_status = status; + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + status = -EIO; + goto out_err; +#else /* CONFIG_NFS_V4_1 */ + return 0; +#endif /* CONFIG_NFS_V4_1 */ +} + +#if defined(CONFIG_NFS_V4_1) +static int decode_getdeviceinfo(struct xdr_stream *xdr, + struct nfs4_getdeviceinfo_res *res) +{ + struct pnfs_device *pdev = res->pdev; + __be32 *p; + uint32_t len, type; + int status; + + status = decode_op_hdr(xdr, OP_GETDEVICEINFO); + if (status) { + if (status == -ETOOSMALL) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + pdev->mincount = be32_to_cpup(p); + dprintk("%s: Min count too small. mincnt = %u\n", + __func__, pdev->mincount); + } + return status; + } + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + type = be32_to_cpup(p++); + if (type != pdev->layout_type) { + dprintk("%s: layout mismatch req: %u pdev: %u\n", + __func__, pdev->layout_type, type); + return -EINVAL; + } + /* + * Get the length of the opaque device_addr4. xdr_read_pages places + * the opaque device_addr4 in the xdr_buf->pages (pnfs_device->pages) + * and places the remaining xdr data in xdr_buf->tail + */ + pdev->mincount = be32_to_cpup(p); + if (xdr_read_pages(xdr, pdev->mincount) != pdev->mincount) + goto out_overflow; + + /* Parse notification bitmap, verifying that it is zero. */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len) { + uint32_t i; + + p = xdr_inline_decode(xdr, 4 * len); + if (unlikely(!p)) + goto out_overflow; + + res->notification = be32_to_cpup(p++); + for (i = 1; i < len; i++) { + if (be32_to_cpup(p++)) { + dprintk("%s: unsupported notification\n", + __func__); + return -EIO; + } + } + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, + struct nfs4_layoutget_res *res) +{ + __be32 *p; + int status; + u32 layout_count; + u32 recvd; + + status = decode_op_hdr(xdr, OP_LAYOUTGET); + if (status) + return status; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + res->return_on_close = be32_to_cpup(p); + decode_stateid(xdr, &res->stateid); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + layout_count = be32_to_cpup(p); + if (!layout_count) { + dprintk("%s: server responded with empty layout array\n", + __func__); + return -EINVAL; + } + + p = xdr_inline_decode(xdr, 28); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &res->range.offset); + p = xdr_decode_hyper(p, &res->range.length); + res->range.iomode = be32_to_cpup(p++); + res->type = be32_to_cpup(p++); + res->layoutp->len = be32_to_cpup(p); + + dprintk("%s roff:%lu rlen:%lu riomode:%d, lo_type:0x%x, lo.len:%d\n", + __func__, + (unsigned long)res->range.offset, + (unsigned long)res->range.length, + res->range.iomode, + res->type, + res->layoutp->len); + + recvd = xdr_read_pages(xdr, res->layoutp->len); + if (res->layoutp->len > recvd) { + dprintk("NFS: server cheating in layoutget reply: " + "layout len %u > recvd %u\n", + res->layoutp->len, recvd); + return -EINVAL; + } + + if (layout_count > 1) { + /* We only handle a length one array at the moment. Any + * further entries are just ignored. Note that this means + * the client may see a response that is less than the + * minimum it requested. + */ + dprintk("%s: server responded with %d layouts, dropping tail\n", + __func__, layout_count); + } + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_layoutreturn(struct xdr_stream *xdr, + struct nfs4_layoutreturn_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_LAYOUTRETURN); + if (status) + return status; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + res->lrs_present = be32_to_cpup(p); + if (res->lrs_present) + status = decode_stateid(xdr, &res->stateid); + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_layoutcommit(struct xdr_stream *xdr, + struct rpc_rqst *req, + struct nfs4_layoutcommit_res *res) +{ + __be32 *p; + __u32 sizechanged; + int status; + + status = decode_op_hdr(xdr, OP_LAYOUTCOMMIT); + res->status = status; + if (status) + return status; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + sizechanged = be32_to_cpup(p); + + if (sizechanged) { + /* throw away new size */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_test_stateid(struct xdr_stream *xdr, + struct nfs41_test_stateid_res *res) +{ + __be32 *p; + int status; + int num_res; + + status = decode_op_hdr(xdr, OP_TEST_STATEID); + if (status) + return status; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num_res = be32_to_cpup(p++); + if (num_res != 1) + goto out; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + res->status = be32_to_cpup(p++); + + return status; +out_overflow: + print_overflow_msg(__func__, xdr); +out: + return -EIO; +} + +static int decode_free_stateid(struct xdr_stream *xdr, + struct nfs41_free_stateid_res *res) +{ + res->status = decode_op_hdr(xdr, OP_FREE_STATEID); + return res->status; +} +#endif /* CONFIG_NFS_V4_1 */ + +/* + * END OF "GENERIC" DECODE ROUTINES. + */ + +/* + * Decode OPEN_DOWNGRADE response + */ +static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs_closeres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_open_downgrade(xdr, res); + if (status != 0) + goto out; + decode_getfattr(xdr, res->fattr, res->server); +out: + return status; +} + +/* + * Decode ACCESS response + */ +static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_accessres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status != 0) + goto out; + status = decode_access(xdr, &res->supported, &res->access); + if (status != 0) + goto out; + decode_getfattr(xdr, res->fattr, res->server); +out: + return status; +} + +/* + * Decode LOOKUP response + */ +static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_lookup_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_lookup(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + +/* + * Decode LOOKUP_ROOT response + */ +static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_lookup_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putrootfh(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status == 0) + status = decode_getfattr_label(xdr, res->fattr, + res->label, res->server); +out: + return status; +} + +/* + * Decode REMOVE response + */ +static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_removeres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_remove(xdr, &res->cinfo); +out: + return status; +} + +/* + * Decode RENAME response + */ +static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_renameres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_savefh(xdr); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo); +out: + return status; +} + +/* + * Decode LINK response + */ +static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_link_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_savefh(xdr); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_link(xdr, &res->cinfo); + if (status) + goto out; + /* + * Note order: OP_LINK leaves the directory as the current + * filehandle. + */ + status = decode_restorefh(xdr); + if (status) + goto out; + decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + +/* + * Decode CREATE response + */ +static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_create_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_create(xdr, &res->dir_cinfo); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + +/* + * Decode SYMLINK response + */ +static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_create_res *res) +{ + return nfs4_xdr_dec_create(rqstp, xdr, res); +} + +/* + * Decode GETATTR response + */ +static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_getattr_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + +/* + * Encode an SETACL request + */ +static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs_setaclargs *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_setacl(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Decode SETACL response + */ +static int +nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_setaclres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_setattr(xdr); +out: + return status; +} + +/* + * Decode GETACL response + */ +static int +nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_getaclres *res) +{ + struct compound_hdr hdr; + int status; + + if (res->acl_scratch != NULL) { + void *p = page_address(res->acl_scratch); + xdr_set_scratch_buffer(xdr, p, PAGE_SIZE); + } + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_getacl(xdr, rqstp, res); + +out: + return status; +} + +/* + * Decode CLOSE response + */ +static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_closeres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_close(xdr, res); + if (status != 0) + goto out; + /* + * Note: Server may do delete on close for this file + * in which case the getattr call will fail with + * an ESTALE error. Shouldn't be a problem, + * though, since fattr->valid will remain unset. + */ + decode_getfattr(xdr, res->fattr, res->server); +out: + return status; +} + +/* + * Decode OPEN response + */ +static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_openres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_open(xdr, res); + if (status) + goto out; + status = decode_getfh(xdr, &res->fh); + if (status) + goto out; + if (res->access_request) + decode_access(xdr, &res->access_supported, &res->access_result); + decode_getfattr_label(xdr, res->f_attr, res->f_label, res->server); +out: + return status; +} + +/* + * Decode OPEN_CONFIRM response + */ +static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs_open_confirmres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_open_confirm(xdr, res); +out: + return status; +} + +/* + * Decode OPEN response + */ +static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs_openres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_open(xdr, res); + if (status) + goto out; + if (res->access_request) + decode_access(xdr, &res->access_supported, &res->access_result); + decode_getfattr(xdr, res->f_attr, res->server); +out: + return status; +} + +/* + * Decode SETATTR response + */ +static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs_setattrres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_setattr(xdr); + if (status) + goto out; + decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + +/* + * Decode LOCK response + */ +static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_lock_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_lock(xdr, res); +out: + return status; +} + +/* + * Decode LOCKT response + */ +static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_lockt_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_lockt(xdr, res); +out: + return status; +} + +/* + * Decode LOCKU response + */ +static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_locku_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_locku(xdr, res); +out: + return status; +} + +static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, void *dummy) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_release_lockowner(xdr); + return status; +} + +/* + * Decode READLINK response + */ +static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_readlink_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_readlink(xdr, rqstp); +out: + return status; +} + +/* + * Decode READDIR response + */ +static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs4_readdir_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_readdir(xdr, rqstp, res); +out: + return status; +} + +/* + * Decode Read response + */ +static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_pgio_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_read(xdr, rqstp, res); + if (!status) + status = res->count; +out: + return status; +} + +/* + * Decode WRITE response + */ +static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_pgio_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_write(xdr, res); + if (status) + goto out; + if (res->fattr) + decode_getfattr(xdr, res->fattr, res->server); + if (!status) + status = res->count; +out: + return status; +} + +/* + * Decode COMMIT response + */ +static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + struct nfs_commitres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_commit(xdr, res); +out: + return status; +} + +/* + * Decode FSINFO response + */ +static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs4_fsinfo_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_sequence(xdr, &res->seq_res, req); + if (!status) + status = decode_putfh(xdr); + if (!status) + status = decode_fsinfo(xdr, res->fsinfo); + return status; +} + +/* + * Decode PATHCONF response + */ +static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs4_pathconf_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_sequence(xdr, &res->seq_res, req); + if (!status) + status = decode_putfh(xdr); + if (!status) + status = decode_pathconf(xdr, res->pathconf); + return status; +} + +/* + * Decode STATFS response + */ +static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, + struct nfs4_statfs_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_sequence(xdr, &res->seq_res, req); + if (!status) + status = decode_putfh(xdr); + if (!status) + status = decode_statfs(xdr, res->fsstat); + return status; +} + +/* + * Decode GETATTR_BITMAP response + */ +static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_server_caps_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, req); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_server_caps(xdr, res); +out: + return status; +} + +/* + * Decode RENEW response + */ +static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *__unused) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_renew(xdr); + return status; +} + +/* + * Decode SETCLIENTID response + */ +static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_setclientid_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_setclientid(xdr, res); + return status; +} + +/* + * Decode SETCLIENTID_CONFIRM response + */ +static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, + struct xdr_stream *xdr) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_setclientid_confirm(xdr); + return status; +} + +/* + * Decode DELEGRETURN response + */ +static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_delegreturnres *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status != 0) + goto out; + status = decode_getfattr(xdr, res->fattr, res->server); + if (status != 0) + goto out; + status = decode_delegreturn(xdr); +out: + return status; +} + +/* + * Decode FS_LOCATIONS response + */ +static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_fs_locations_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, req); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + if (res->migration) { + xdr_enter_page(xdr, PAGE_SIZE); + status = decode_getfattr_generic(xdr, + &res->fs_locations->fattr, + NULL, res->fs_locations, + NULL, res->fs_locations->server); + if (status) + goto out; + if (res->renew) + status = decode_renew(xdr); + } else { + status = decode_lookup(xdr); + if (status) + goto out; + xdr_enter_page(xdr, PAGE_SIZE); + status = decode_getfattr_generic(xdr, + &res->fs_locations->fattr, + NULL, res->fs_locations, + NULL, res->fs_locations->server); + } +out: + return status; +} + +/* + * Decode SECINFO response + */ +static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_secinfo_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_secinfo(xdr, res); +out: + return status; +} + +/* + * Decode FSID_PRESENT response + */ +static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_fsid_present_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + if (res->renew) + status = decode_renew(xdr); +out: + return status; +} + +#if defined(CONFIG_NFS_V4_1) +/* + * Decode BIND_CONN_TO_SESSION response + */ +static int nfs4_xdr_dec_bind_conn_to_session(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_bind_conn_to_session(xdr, res); + return status; +} + +/* + * Decode EXCHANGE_ID response + */ +static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_exchange_id(xdr, res); + return status; +} + +/* + * Decode CREATE_SESSION response + */ +static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs41_create_session_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_create_session(xdr, res); + return status; +} + +/* + * Decode DESTROY_SESSION response + */ +static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_destroy_session(xdr, res); + return status; +} + +/* + * Decode DESTROY_CLIENTID response + */ +static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_destroy_clientid(xdr, res); + return status; +} + +/* + * Decode SEQUENCE response + */ +static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_sequence_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_sequence(xdr, res, rqstp); + return status; +} + +/* + * Decode GET_LEASE_TIME response + */ +static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_get_lease_time_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_sequence(xdr, &res->lr_seq_res, rqstp); + if (!status) + status = decode_putrootfh(xdr); + if (!status) + status = decode_fsinfo(xdr, res->lr_fsinfo); + return status; +} + +/* + * Decode RECLAIM_COMPLETE response + */ +static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs41_reclaim_complete_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (!status) + status = decode_reclaim_complete(xdr, NULL); + return status; +} + +/* + * Decode GETDEVINFO response + */ +static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_getdeviceinfo_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status != 0) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status != 0) + goto out; + status = decode_getdeviceinfo(xdr, res); +out: + return status; +} + +/* + * Decode LAYOUTGET response + */ +static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_layoutget_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_layoutget(xdr, rqstp, res); +out: + return status; +} + +/* + * Decode LAYOUTRETURN response + */ +static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_layoutreturn_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_layoutreturn(xdr, res); +out: + return status; +} + +/* + * Decode LAYOUTCOMMIT response + */ +static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_layoutcommit_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_layoutcommit(xdr, rqstp, res); + if (status) + goto out; + decode_getfattr(xdr, res->fattr, res->server); +out: + return status; +} + +/* + * Decode SECINFO_NO_NAME response + */ +static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_secinfo_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putrootfh(xdr); + if (status) + goto out; + status = decode_secinfo_no_name(xdr, res); +out: + return status; +} + +/* + * Decode TEST_STATEID response + */ +static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs41_test_stateid_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_test_stateid(xdr, res); +out: + return status; +} + +/* + * Decode FREE_STATEID response + */ +static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs41_free_stateid_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_free_stateid(xdr, res); +out: + return status; +} +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_decode_dirent - Decode a single NFSv4 directory entry stored in + * the local page cache. + * @xdr: XDR stream where entry resides + * @entry: buffer to fill in with entry data + * @plus: boolean indicating whether this should be a readdirplus entry + * + * Returns zero if successful, otherwise a negative errno value is + * returned. + * + * This function is not invoked during READDIR reply decoding, but + * rather whenever an application invokes the getdents(2) system call + * on a directory already in our cache. + */ +int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, + int plus) +{ + unsigned int savep; + uint32_t bitmap[3] = {0}; + uint32_t len; + __be32 *p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (*p == xdr_zero) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (*p == xdr_zero) + return -EAGAIN; + entry->eof = 1; + return -EBADCOOKIE; + } + + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + entry->prev_cookie = entry->cookie; + p = xdr_decode_hyper(p, &entry->cookie); + entry->len = be32_to_cpup(p); + + p = xdr_inline_decode(xdr, entry->len); + if (unlikely(!p)) + goto out_overflow; + entry->name = (const char *) p; + + /* + * In case the server doesn't return an inode number, + * we fake one here. (We don't use inode number 0, + * since glibc seems to choke on it...) + */ + entry->ino = 1; + entry->fattr->valid = 0; + + if (decode_attr_bitmap(xdr, bitmap) < 0) + goto out_overflow; + + if (decode_attr_length(xdr, &len, &savep) < 0) + goto out_overflow; + + if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh, + NULL, entry->label, entry->server) < 0) + goto out_overflow; + if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) + entry->ino = entry->fattr->mounted_on_fileid; + else if (entry->fattr->valid & NFS_ATTR_FATTR_FILEID) + entry->ino = entry->fattr->fileid; + + entry->d_type = DT_UNKNOWN; + if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE) + entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); + + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EAGAIN; +} + +/* + * We need to translate between nfs status return values and + * the local errno values which may not be the same. + */ +static struct { + int stat; + int errno; +} nfs_errtbl[] = { + { NFS4_OK, 0 }, + { NFS4ERR_PERM, -EPERM }, + { NFS4ERR_NOENT, -ENOENT }, + { NFS4ERR_IO, -errno_NFSERR_IO}, + { NFS4ERR_NXIO, -ENXIO }, + { NFS4ERR_ACCESS, -EACCES }, + { NFS4ERR_EXIST, -EEXIST }, + { NFS4ERR_XDEV, -EXDEV }, + { NFS4ERR_NOTDIR, -ENOTDIR }, + { NFS4ERR_ISDIR, -EISDIR }, + { NFS4ERR_INVAL, -EINVAL }, + { NFS4ERR_FBIG, -EFBIG }, + { NFS4ERR_NOSPC, -ENOSPC }, + { NFS4ERR_ROFS, -EROFS }, + { NFS4ERR_MLINK, -EMLINK }, + { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFS4ERR_NOTEMPTY, -ENOTEMPTY }, + { NFS4ERR_DQUOT, -EDQUOT }, + { NFS4ERR_STALE, -ESTALE }, + { NFS4ERR_BADHANDLE, -EBADHANDLE }, + { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, + { NFS4ERR_NOTSUPP, -ENOTSUPP }, + { NFS4ERR_TOOSMALL, -ETOOSMALL }, + { NFS4ERR_SERVERFAULT, -EREMOTEIO }, + { NFS4ERR_BADTYPE, -EBADTYPE }, + { NFS4ERR_LOCKED, -EAGAIN }, + { NFS4ERR_SYMLINK, -ELOOP }, + { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, + { NFS4ERR_DEADLOCK, -EDEADLK }, + { -1, -EIO } +}; + +/* + * Convert an NFS error code to a local one. + * This one is used jointly by NFSv2 and NFSv3. + */ +static int +nfs4_stat_to_errno(int stat) +{ + int i; + for (i = 0; nfs_errtbl[i].stat != -1; i++) { + if (nfs_errtbl[i].stat == stat) + return nfs_errtbl[i].errno; + } + if (stat <= 10000 || stat > 10100) { + /* The server is looney tunes. */ + return -EREMOTEIO; + } + /* If we cannot translate the error, the recovery routines should + * handle it. + * Note: remaining NFSv4 error codes have values > 10000, so should + * not conflict with native Linux error codes. + */ + return -stat; +} + +#ifdef CONFIG_NFS_V4_2 +#include "nfs42xdr.c" +#endif /* CONFIG_NFS_V4_2 */ + +#define PROC(proc, argtype, restype) \ +[NFSPROC4_CLNT_##proc] = { \ + .p_proc = NFSPROC4_COMPOUND, \ + .p_encode = (kxdreproc_t)nfs4_xdr_##argtype, \ + .p_decode = (kxdrdproc_t)nfs4_xdr_##restype, \ + .p_arglen = NFS4_##argtype##_sz, \ + .p_replen = NFS4_##restype##_sz, \ + .p_statidx = NFSPROC4_CLNT_##proc, \ + .p_name = #proc, \ +} + +#define STUB(proc) \ +[NFSPROC4_CLNT_##proc] = { \ + .p_name = #proc, \ +} + +struct rpc_procinfo nfs4_procedures[] = { + PROC(READ, enc_read, dec_read), + PROC(WRITE, enc_write, dec_write), + PROC(COMMIT, enc_commit, dec_commit), + PROC(OPEN, enc_open, dec_open), + PROC(OPEN_CONFIRM, enc_open_confirm, dec_open_confirm), + PROC(OPEN_NOATTR, enc_open_noattr, dec_open_noattr), + PROC(OPEN_DOWNGRADE, enc_open_downgrade, dec_open_downgrade), + PROC(CLOSE, enc_close, dec_close), + PROC(SETATTR, enc_setattr, dec_setattr), + PROC(FSINFO, enc_fsinfo, dec_fsinfo), + PROC(RENEW, enc_renew, dec_renew), + PROC(SETCLIENTID, enc_setclientid, dec_setclientid), + PROC(SETCLIENTID_CONFIRM, enc_setclientid_confirm, dec_setclientid_confirm), + PROC(LOCK, enc_lock, dec_lock), + PROC(LOCKT, enc_lockt, dec_lockt), + PROC(LOCKU, enc_locku, dec_locku), + PROC(ACCESS, enc_access, dec_access), + PROC(GETATTR, enc_getattr, dec_getattr), + PROC(LOOKUP, enc_lookup, dec_lookup), + PROC(LOOKUP_ROOT, enc_lookup_root, dec_lookup_root), + PROC(REMOVE, enc_remove, dec_remove), + PROC(RENAME, enc_rename, dec_rename), + PROC(LINK, enc_link, dec_link), + PROC(SYMLINK, enc_symlink, dec_symlink), + PROC(CREATE, enc_create, dec_create), + PROC(PATHCONF, enc_pathconf, dec_pathconf), + PROC(STATFS, enc_statfs, dec_statfs), + PROC(READLINK, enc_readlink, dec_readlink), + PROC(READDIR, enc_readdir, dec_readdir), + PROC(SERVER_CAPS, enc_server_caps, dec_server_caps), + PROC(DELEGRETURN, enc_delegreturn, dec_delegreturn), + PROC(GETACL, enc_getacl, dec_getacl), + PROC(SETACL, enc_setacl, dec_setacl), + PROC(FS_LOCATIONS, enc_fs_locations, dec_fs_locations), + PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), + PROC(SECINFO, enc_secinfo, dec_secinfo), + PROC(FSID_PRESENT, enc_fsid_present, dec_fsid_present), +#if defined(CONFIG_NFS_V4_1) + PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), + PROC(CREATE_SESSION, enc_create_session, dec_create_session), + PROC(DESTROY_SESSION, enc_destroy_session, dec_destroy_session), + PROC(SEQUENCE, enc_sequence, dec_sequence), + PROC(GET_LEASE_TIME, enc_get_lease_time, dec_get_lease_time), + PROC(RECLAIM_COMPLETE, enc_reclaim_complete, dec_reclaim_complete), + PROC(GETDEVICEINFO, enc_getdeviceinfo, dec_getdeviceinfo), + PROC(LAYOUTGET, enc_layoutget, dec_layoutget), + PROC(LAYOUTCOMMIT, enc_layoutcommit, dec_layoutcommit), + PROC(LAYOUTRETURN, enc_layoutreturn, dec_layoutreturn), + PROC(SECINFO_NO_NAME, enc_secinfo_no_name, dec_secinfo_no_name), + PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), + PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), + STUB(GETDEVICELIST), + PROC(BIND_CONN_TO_SESSION, + enc_bind_conn_to_session, dec_bind_conn_to_session), + PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid), +#endif /* CONFIG_NFS_V4_1 */ +#ifdef CONFIG_NFS_V4_2 + PROC(SEEK, enc_seek, dec_seek), + PROC(ALLOCATE, enc_allocate, dec_allocate), + PROC(DEALLOCATE, enc_deallocate, dec_deallocate), +#endif /* CONFIG_NFS_V4_2 */ +}; + +const struct rpc_version nfs_version4 = { + .number = 4, + .nrprocs = ARRAY_SIZE(nfs4_procedures), + .procs = nfs4_procedures +}; + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/kernel/fs/nfs/nfsroot.c b/kernel/fs/nfs/nfsroot.c new file mode 100644 index 000000000..9bc9f04fb --- /dev/null +++ b/kernel/fs/nfs/nfsroot.c @@ -0,0 +1,309 @@ +/* + * Copyright (C) 1995, 1996 Gero Kuhlmann <gero@gkminix.han.de> + * + * Allow an NFS filesystem to be mounted as root. The way this works is: + * (1) Use the IP autoconfig mechanism to set local IP addresses and routes. + * (2) Construct the device string and the options string using DHCP + * option 17 and/or kernel command line options. + * (3) When mount_root() sets up the root file system, pass these strings + * to the NFS client's regular mount interface via sys_mount(). + * + * + * Changes: + * + * Alan Cox : Removed get_address name clash with FPU. + * Alan Cox : Reformatted a bit. + * Gero Kuhlmann : Code cleanup + * Michael Rausch : Fixed recognition of an incoming RARP answer. + * Martin Mares : (2.0) Auto-configuration via BOOTP supported. + * Martin Mares : Manual selection of interface & BOOTP/RARP. + * Martin Mares : Using network routes instead of host routes, + * allowing the default configuration to be used + * for normal operation of the host. + * Martin Mares : Randomized timer with exponential backoff + * installed to minimize network congestion. + * Martin Mares : Code cleanup. + * Martin Mares : (2.1) BOOTP and RARP made configuration options. + * Martin Mares : Server hostname generation fixed. + * Gerd Knorr : Fixed wired inode handling + * Martin Mares : (2.2) "0.0.0.0" addresses from command line ignored. + * Martin Mares : RARP replies not tested for server address. + * Gero Kuhlmann : (2.3) Some bug fixes and code cleanup again (please + * send me your new patches _before_ bothering + * Linus so that I don' always have to cleanup + * _afterwards_ - thanks) + * Gero Kuhlmann : Last changes of Martin Mares undone. + * Gero Kuhlmann : RARP replies are tested for specified server + * again. However, it's now possible to have + * different RARP and NFS servers. + * Gero Kuhlmann : "0.0.0.0" addresses from command line are + * now mapped to INADDR_NONE. + * Gero Kuhlmann : Fixed a bug which prevented BOOTP path name + * from being used (thanks to Leo Spiekman) + * Andy Walker : Allow to specify the NFS server in nfs_root + * without giving a path name + * Swen Thümmler : Allow to specify the NFS options in nfs_root + * without giving a path name. Fix BOOTP request + * for domainname (domainname is NIS domain, not + * DNS domain!). Skip dummy devices for BOOTP. + * Jacek Zapala : Fixed a bug which prevented server-ip address + * from nfsroot parameter from being used. + * Olaf Kirch : Adapted to new NFS code. + * Jakub Jelinek : Free used code segment. + * Marko Kohtala : Fixed some bugs. + * Martin Mares : Debug message cleanup + * Martin Mares : Changed to use the new generic IP layer autoconfig + * code. BOOTP and RARP moved there. + * Martin Mares : Default path now contains host name instead of + * host IP address (but host name defaults to IP + * address anyway). + * Martin Mares : Use root_server_addr appropriately during setup. + * Martin Mares : Rewrote parameter parsing, now hopefully giving + * correct overriding. + * Trond Myklebust : Add in preliminary support for NFSv3 and TCP. + * Fix bug in root_nfs_addr(). nfs_data.namlen + * is NOT for the length of the hostname. + * Hua Qin : Support for mounting root file system via + * NFS over TCP. + * Fabian Frederick: Option parser rebuilt (using parser lib) + * Chuck Lever : Use super.c's text-based mount option parsing + * Chuck Lever : Add "nfsrootdebug". + */ + +#include <linux/types.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/nfs.h> +#include <linux/nfs_fs.h> +#include <linux/utsname.h> +#include <linux/root_dev.h> +#include <net/ipconfig.h> + +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_ROOT + +/* Default path we try to mount. "%s" gets replaced by our IP address */ +#define NFS_ROOT "/tftpboot/%s" + +/* Default NFSROOT mount options. */ +#define NFS_DEF_OPTIONS "vers=2,udp,rsize=4096,wsize=4096" + +/* Parameters passed from the kernel command line */ +static char nfs_root_parms[256] __initdata = ""; + +/* Text-based mount options passed to super.c */ +static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS; + +/* Address of NFS server */ +static __be32 servaddr __initdata = htonl(INADDR_NONE); + +/* Name of directory to mount */ +static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = ""; + +/* server:export path string passed to super.c */ +static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = ""; + +#ifdef NFS_DEBUG +/* + * When the "nfsrootdebug" kernel command line option is specified, + * enable debugging messages for NFSROOT. + */ +static int __init nfs_root_debug(char *__unused) +{ + nfs_debug |= NFSDBG_ROOT | NFSDBG_MOUNT; + return 1; +} + +__setup("nfsrootdebug", nfs_root_debug); +#endif + +/* + * Parse NFS server and directory information passed on the kernel + * command line. + * + * nfsroot=[<server-ip>:]<root-dir>[,<nfs-options>] + * + * If there is a "%s" token in the <root-dir> string, it is replaced + * by the ASCII-representation of the client's IP address. + */ +static int __init nfs_root_setup(char *line) +{ + ROOT_DEV = Root_NFS; + + if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) { + strlcpy(nfs_root_parms, line, sizeof(nfs_root_parms)); + } else { + size_t n = strlen(line) + sizeof(NFS_ROOT) - 1; + if (n >= sizeof(nfs_root_parms)) + line[sizeof(nfs_root_parms) - sizeof(NFS_ROOT) - 2] = '\0'; + sprintf(nfs_root_parms, NFS_ROOT, line); + } + + /* + * Extract the IP address of the NFS server containing our + * root file system, if one was specified. + * + * Note: root_nfs_parse_addr() removes the server-ip from + * nfs_root_parms, if it exists. + */ + root_server_addr = root_nfs_parse_addr(nfs_root_parms); + + return 1; +} + +__setup("nfsroot=", nfs_root_setup); + +static int __init root_nfs_copy(char *dest, const char *src, + const size_t destlen) +{ + if (strlcpy(dest, src, destlen) > destlen) + return -1; + return 0; +} + +static int __init root_nfs_cat(char *dest, const char *src, + const size_t destlen) +{ + size_t len = strlen(dest); + + if (len && dest[len - 1] != ',') + if (strlcat(dest, ",", destlen) > destlen) + return -1; + + if (strlcat(dest, src, destlen) > destlen) + return -1; + return 0; +} + +/* + * Parse out root export path and mount options from + * passed-in string @incoming. + * + * Copy the export path into @exppath. + */ +static int __init root_nfs_parse_options(char *incoming, char *exppath, + const size_t exppathlen) +{ + char *p; + + /* + * Set the NFS remote path + */ + p = strsep(&incoming, ","); + if (*p != '\0' && strcmp(p, "default") != 0) + if (root_nfs_copy(exppath, p, exppathlen)) + return -1; + + /* + * @incoming now points to the rest of the string; if it + * contains something, append it to our root options buffer + */ + if (incoming != NULL && *incoming != '\0') + if (root_nfs_cat(nfs_root_options, incoming, + sizeof(nfs_root_options))) + return -1; + return 0; +} + +/* + * Decode the export directory path name and NFS options from + * the kernel command line. This has to be done late in order to + * use a dynamically acquired client IP address for the remote + * root directory path. + * + * Returns zero if successful; otherwise -1 is returned. + */ +static int __init root_nfs_data(char *cmdline) +{ + char mand_options[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1]; + int len, retval = -1; + char *tmp = NULL; + const size_t tmplen = sizeof(nfs_export_path); + + tmp = kzalloc(tmplen, GFP_KERNEL); + if (tmp == NULL) + goto out_nomem; + strcpy(tmp, NFS_ROOT); + + if (root_server_path[0] != '\0') { + dprintk("Root-NFS: DHCPv4 option 17: %s\n", + root_server_path); + if (root_nfs_parse_options(root_server_path, tmp, tmplen)) + goto out_optionstoolong; + } + + if (cmdline[0] != '\0') { + dprintk("Root-NFS: nfsroot=%s\n", cmdline); + if (root_nfs_parse_options(cmdline, tmp, tmplen)) + goto out_optionstoolong; + } + + /* + * Append mandatory options for nfsroot so they override + * what has come before + */ + snprintf(mand_options, sizeof(mand_options), "nolock,addr=%pI4", + &servaddr); + if (root_nfs_cat(nfs_root_options, mand_options, + sizeof(nfs_root_options))) + goto out_optionstoolong; + + /* + * Set up nfs_root_device. For NFS mounts, this looks like + * + * server:/path + * + * At this point, utsname()->nodename contains our local + * IP address or hostname, set by ipconfig. If "%s" exists + * in tmp, substitute the nodename, then shovel the whole + * mess into nfs_root_device. + */ + len = snprintf(nfs_export_path, sizeof(nfs_export_path), + tmp, utsname()->nodename); + if (len >= (int)sizeof(nfs_export_path)) + goto out_devnametoolong; + len = snprintf(nfs_root_device, sizeof(nfs_root_device), + "%pI4:%s", &servaddr, nfs_export_path); + if (len >= (int)sizeof(nfs_root_device)) + goto out_devnametoolong; + + retval = 0; + +out: + kfree(tmp); + return retval; +out_nomem: + printk(KERN_ERR "Root-NFS: could not allocate memory\n"); + goto out; +out_optionstoolong: + printk(KERN_ERR "Root-NFS: mount options string too long\n"); + goto out; +out_devnametoolong: + printk(KERN_ERR "Root-NFS: root device name too long.\n"); + goto out; +} + +/** + * nfs_root_data - Return prepared 'data' for NFSROOT mount + * @root_device: OUT: address of string containing NFSROOT device + * @root_data: OUT: address of string containing NFSROOT mount options + * + * Returns zero and sets @root_device and @root_data if successful, + * otherwise -1 is returned. + */ +int __init nfs_root_data(char **root_device, char **root_data) +{ + servaddr = root_server_addr; + if (servaddr == htonl(INADDR_NONE)) { + printk(KERN_ERR "Root-NFS: no NFS server address\n"); + return -1; + } + + if (root_nfs_data(nfs_root_parms) < 0) + return -1; + + *root_device = nfs_root_device; + *root_data = nfs_root_options; + return 0; +} diff --git a/kernel/fs/nfs/nfstrace.c b/kernel/fs/nfs/nfstrace.c new file mode 100644 index 000000000..c74f7af23 --- /dev/null +++ b/kernel/fs/nfs/nfstrace.c @@ -0,0 +1,12 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/nfs_fs.h> +#include <linux/namei.h> +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include "nfstrace.h" + +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_enter); +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_exit); diff --git a/kernel/fs/nfs/nfstrace.h b/kernel/fs/nfs/nfstrace.h new file mode 100644 index 000000000..59f838cdc --- /dev/null +++ b/kernel/fs/nfs/nfstrace.h @@ -0,0 +1,730 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfs + +#if !defined(_TRACE_NFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NFS_H + +#include <linux/tracepoint.h> + +#define nfs_show_file_type(ftype) \ + __print_symbolic(ftype, \ + { DT_UNKNOWN, "UNKNOWN" }, \ + { DT_FIFO, "FIFO" }, \ + { DT_CHR, "CHR" }, \ + { DT_DIR, "DIR" }, \ + { DT_BLK, "BLK" }, \ + { DT_REG, "REG" }, \ + { DT_LNK, "LNK" }, \ + { DT_SOCK, "SOCK" }, \ + { DT_WHT, "WHT" }) + +#define nfs_show_cache_validity(v) \ + __print_flags(v, "|", \ + { NFS_INO_INVALID_ATTR, "INVALID_ATTR" }, \ + { NFS_INO_INVALID_DATA, "INVALID_DATA" }, \ + { NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \ + { NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \ + { NFS_INO_INVALID_ACL, "INVALID_ACL" }, \ + { NFS_INO_REVAL_PAGECACHE, "REVAL_PAGECACHE" }, \ + { NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \ + { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }) + +#define nfs_show_nfsi_flags(v) \ + __print_flags(v, "|", \ + { 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \ + { 1 << NFS_INO_STALE, "STALE" }, \ + { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \ + { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \ + { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \ + { 1 << NFS_INO_COMMIT, "COMMIT" }, \ + { 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \ + { 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" }) + +DECLARE_EVENT_CLASS(nfs_inode_event, + TP_PROTO( + const struct inode *inode + ), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode->i_version; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu ", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (unsigned long long)__entry->version + ) +); + +DECLARE_EVENT_CLASS(nfs_inode_event_done, + TP_PROTO( + const struct inode *inode, + int error + ), + + TP_ARGS(inode, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(unsigned char, type) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, size) + __field(unsigned long, nfsi_flags) + __field(unsigned long, cache_validity) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->error = error; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->type = nfs_umode_to_dtype(inode->i_mode); + __entry->version = inode->i_version; + __entry->size = i_size_read(inode); + __entry->nfsi_flags = nfsi->flags; + __entry->cache_validity = nfsi->cache_validity; + ), + + TP_printk( + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "type=%u (%s) version=%llu size=%lld " + "cache_validity=%lu (%s) nfs_flags=%ld (%s)", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->type, + nfs_show_file_type(__entry->type), + (unsigned long long)__entry->version, + (long long)__entry->size, + __entry->cache_validity, + nfs_show_cache_validity(__entry->cache_validity), + __entry->nfsi_flags, + nfs_show_nfsi_flags(__entry->nfsi_flags) + ) +); + +#define DEFINE_NFS_INODE_EVENT(name) \ + DEFINE_EVENT(nfs_inode_event, name, \ + TP_PROTO( \ + const struct inode *inode \ + ), \ + TP_ARGS(inode)) +#define DEFINE_NFS_INODE_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_inode_event_done, name, \ + TP_PROTO( \ + const struct inode *inode, \ + int error \ + ), \ + TP_ARGS(inode, error)) +DEFINE_NFS_INODE_EVENT(nfs_refresh_inode_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_refresh_inode_exit); +DEFINE_NFS_INODE_EVENT(nfs_revalidate_inode_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_revalidate_inode_exit); +DEFINE_NFS_INODE_EVENT(nfs_invalidate_mapping_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_invalidate_mapping_exit); +DEFINE_NFS_INODE_EVENT(nfs_getattr_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_getattr_exit); +DEFINE_NFS_INODE_EVENT(nfs_setattr_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_setattr_exit); +DEFINE_NFS_INODE_EVENT(nfs_writeback_page_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_page_exit); +DEFINE_NFS_INODE_EVENT(nfs_writeback_inode_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); +DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); +DEFINE_NFS_INODE_EVENT(nfs_access_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_access_exit); + +#define show_lookup_flags(flags) \ + __print_flags((unsigned long)flags, "|", \ + { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ + { LOOKUP_DIRECTORY, "DIRECTORY" }, \ + { LOOKUP_OPEN, "OPEN" }, \ + { LOOKUP_CREATE, "CREATE" }, \ + { LOOKUP_EXCL, "EXCL" }) + +DECLARE_EVENT_CLASS(nfs_lookup_event, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags + ), + + TP_ARGS(dir, dentry, flags), + + TP_STRUCT__entry( + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->flags, + show_lookup_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_LOOKUP_EVENT(name) \ + DEFINE_EVENT(nfs_lookup_event, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry, \ + unsigned int flags \ + ), \ + TP_ARGS(dir, dentry, flags)) + +DECLARE_EVENT_CLASS(nfs_lookup_event_done, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags, + int error + ), + + TP_ARGS(dir, dentry, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->error, + __entry->flags, + show_lookup_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_LOOKUP_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_lookup_event_done, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry, \ + unsigned int flags, \ + int error \ + ), \ + TP_ARGS(dir, dentry, flags, error)) + +DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter); +DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); +DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); +DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); + +#define show_open_flags(flags) \ + __print_flags((unsigned long)flags, "|", \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_APPEND, "O_APPEND" }, \ + { O_DSYNC, "O_DSYNC" }, \ + { O_DIRECT, "O_DIRECT" }, \ + { O_DIRECTORY, "O_DIRECTORY" }) + +#define show_fmode_flags(mode) \ + __print_flags(mode, "|", \ + { ((__force unsigned long)FMODE_READ), "READ" }, \ + { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ + { ((__force unsigned long)FMODE_EXEC), "EXEC" }) + +TRACE_EVENT(nfs_atomic_open_enter, + TP_PROTO( + const struct inode *dir, + const struct nfs_open_context *ctx, + unsigned int flags + ), + + TP_ARGS(dir, ctx, flags), + + TP_STRUCT__entry( + __field(unsigned int, flags) + __field(unsigned int, fmode) + __field(dev_t, dev) + __field(u64, dir) + __string(name, ctx->dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __entry->fmode = (__force unsigned int)ctx->mode; + __assign_str(name, ctx->dentry->d_name.name); + ), + + TP_printk( + "flags=%u (%s) fmode=%s name=%02x:%02x:%llu/%s", + __entry->flags, + show_open_flags(__entry->flags), + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_atomic_open_exit, + TP_PROTO( + const struct inode *dir, + const struct nfs_open_context *ctx, + unsigned int flags, + int error + ), + + TP_ARGS(dir, ctx, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(unsigned int, fmode) + __field(dev_t, dev) + __field(u64, dir) + __string(name, ctx->dentry->d_name.name) + ), + + TP_fast_assign( + __entry->error = error; + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __entry->fmode = (__force unsigned int)ctx->mode; + __assign_str(name, ctx->dentry->d_name.name); + ), + + TP_printk( + "error=%d flags=%u (%s) fmode=%s " + "name=%02x:%02x:%llu/%s", + __entry->error, + __entry->flags, + show_open_flags(__entry->flags), + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_create_enter, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags + ), + + TP_ARGS(dir, dentry, flags), + + TP_STRUCT__entry( + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->flags, + show_open_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_create_exit, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags, + int error + ), + + TP_ARGS(dir, dentry, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->error = error; + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->error, + __entry->flags, + show_open_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +DECLARE_EVENT_CLASS(nfs_directory_event, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry + ), + + TP_ARGS(dir, dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "name=%02x:%02x:%llu/%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_DIRECTORY_EVENT(name) \ + DEFINE_EVENT(nfs_directory_event, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry \ + ), \ + TP_ARGS(dir, dentry)) + +DECLARE_EVENT_CLASS(nfs_directory_event_done, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + int error + ), + + TP_ARGS(dir, dentry, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_DIRECTORY_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_directory_event_done, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry, \ + int error \ + ), \ + TP_ARGS(dir, dentry, error)) + +DEFINE_NFS_DIRECTORY_EVENT(nfs_mknod_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mknod_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_mkdir_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mkdir_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_rmdir_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_rmdir_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_remove_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_remove_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_unlink_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_unlink_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_symlink_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_symlink_exit); + +TRACE_EVENT(nfs_link_enter, + TP_PROTO( + const struct inode *inode, + const struct inode *dir, + const struct dentry *dentry + ), + + TP_ARGS(inode, dir, dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->dir = NFS_FILEID(dir); + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->fileid, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_link_exit, + TP_PROTO( + const struct inode *inode, + const struct inode *dir, + const struct dentry *dentry, + int error + ), + + TP_ARGS(inode, dir, dentry, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u64, fileid) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->fileid, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +DECLARE_EVENT_CLASS(nfs_rename_event, + TP_PROTO( + const struct inode *old_dir, + const struct dentry *old_dentry, + const struct inode *new_dir, + const struct dentry *new_dentry + ), + + TP_ARGS(old_dir, old_dentry, new_dir, new_dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, old_dir) + __field(u64, new_dir) + __string(old_name, old_dentry->d_name.name) + __string(new_name, new_dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = old_dir->i_sb->s_dev; + __entry->old_dir = NFS_FILEID(old_dir); + __entry->new_dir = NFS_FILEID(new_dir); + __assign_str(old_name, old_dentry->d_name.name); + __assign_str(new_name, new_dentry->d_name.name); + ), + + TP_printk( + "old_name=%02x:%02x:%llu/%s new_name=%02x:%02x:%llu/%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->old_dir, + __get_str(old_name), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->new_dir, + __get_str(new_name) + ) +); +#define DEFINE_NFS_RENAME_EVENT(name) \ + DEFINE_EVENT(nfs_rename_event, name, \ + TP_PROTO( \ + const struct inode *old_dir, \ + const struct dentry *old_dentry, \ + const struct inode *new_dir, \ + const struct dentry *new_dentry \ + ), \ + TP_ARGS(old_dir, old_dentry, new_dir, new_dentry)) + +DECLARE_EVENT_CLASS(nfs_rename_event_done, + TP_PROTO( + const struct inode *old_dir, + const struct dentry *old_dentry, + const struct inode *new_dir, + const struct dentry *new_dentry, + int error + ), + + TP_ARGS(old_dir, old_dentry, new_dir, new_dentry, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, old_dir) + __string(old_name, old_dentry->d_name.name) + __field(u64, new_dir) + __string(new_name, new_dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = old_dir->i_sb->s_dev; + __entry->old_dir = NFS_FILEID(old_dir); + __entry->new_dir = NFS_FILEID(new_dir); + __entry->error = error; + __assign_str(old_name, old_dentry->d_name.name); + __assign_str(new_name, new_dentry->d_name.name); + ), + + TP_printk( + "error=%d old_name=%02x:%02x:%llu/%s " + "new_name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->old_dir, + __get_str(old_name), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->new_dir, + __get_str(new_name) + ) +); +#define DEFINE_NFS_RENAME_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_rename_event_done, name, \ + TP_PROTO( \ + const struct inode *old_dir, \ + const struct dentry *old_dentry, \ + const struct inode *new_dir, \ + const struct dentry *new_dentry, \ + int error \ + ), \ + TP_ARGS(old_dir, old_dentry, new_dir, \ + new_dentry, error)) + +DEFINE_NFS_RENAME_EVENT(nfs_rename_enter); +DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit); + +DEFINE_NFS_RENAME_EVENT_DONE(nfs_sillyrename_rename); + +TRACE_EVENT(nfs_sillyrename_unlink, + TP_PROTO( + const struct nfs_unlinkdata *data, + int error + ), + + TP_ARGS(data, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, dir) + __dynamic_array(char, name, data->args.name.len + 1) + ), + + TP_fast_assign( + struct inode *dir = data->dir; + size_t len = data->args.name.len; + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + memcpy(__get_dynamic_array(name), + data->args.name.name, len); + ((char *)__get_dynamic_array(name))[len] = 0; + ), + + TP_printk( + "error=%d name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); +#endif /* _TRACE_NFS_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE nfstrace +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/kernel/fs/nfs/objlayout/Kbuild b/kernel/fs/nfs/objlayout/Kbuild new file mode 100644 index 000000000..ed30ea072 --- /dev/null +++ b/kernel/fs/nfs/objlayout/Kbuild @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Objects Layout Driver kernel module +# +objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o +obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o diff --git a/kernel/fs/nfs/objlayout/objio_osd.c b/kernel/fs/nfs/objlayout/objio_osd.c new file mode 100644 index 000000000..5aaed3635 --- /dev/null +++ b/kernel/fs/nfs/objlayout/objio_osd.c @@ -0,0 +1,678 @@ +/* + * pNFS Objects layout implementation over open-osd initiator library + * + * Copyright (C) 2009 Panasas Inc. [year of first publication] + * All rights reserved. + * + * Benny Halevy <bhalevy@panasas.com> + * Boaz Harrosh <ooo@electrozaur.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * See the file COPYING included with this distribution for more details. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Panasas company nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/module.h> +#include <scsi/osd_ore.h> + +#include "objlayout.h" +#include "../internal.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +struct objio_dev_ent { + struct nfs4_deviceid_node id_node; + struct ore_dev od; +}; + +static void +objio_free_deviceid_node(struct nfs4_deviceid_node *d) +{ + struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node); + + dprintk("%s: free od=%p\n", __func__, de->od.od); + osduld_put_device(de->od.od); + kfree_rcu(d, rcu); +} + +struct objio_segment { + struct pnfs_layout_segment lseg; + + struct ore_layout layout; + struct ore_components oc; +}; + +static inline struct objio_segment * +OBJIO_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, struct objio_segment, lseg); +} + +struct objio_state { + /* Generic layer */ + struct objlayout_io_res oir; + + bool sync; + /*FIXME: Support for extra_bytes at ore_get_rw_state() */ + struct ore_io_state *ios; +}; + +/* Send and wait for a get_device_info of devices in the layout, + then look them up with the osd_initiator library */ +struct nfs4_deviceid_node * +objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags) +{ + struct pnfs_osd_deviceaddr *deviceaddr; + struct objio_dev_ent *ode = NULL; + struct osd_dev *od; + struct osd_dev_info odi; + bool retry_flag = true; + __be32 *p; + int err; + + deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags); + if (!deviceaddr) + return NULL; + + p = page_address(pdev->pages[0]); + pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p); + + odi.systemid_len = deviceaddr->oda_systemid.len; + if (odi.systemid_len > sizeof(odi.systemid)) { + dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n", + __func__, sizeof(odi.systemid)); + err = -EINVAL; + goto out; + } else if (odi.systemid_len) + memcpy(odi.systemid, deviceaddr->oda_systemid.data, + odi.systemid_len); + odi.osdname_len = deviceaddr->oda_osdname.len; + odi.osdname = (u8 *)deviceaddr->oda_osdname.data; + + if (!odi.osdname_len && !odi.systemid_len) { + dprintk("%s: !odi.osdname_len && !odi.systemid_len\n", + __func__); + err = -ENODEV; + goto out; + } + +retry_lookup: + od = osduld_info_lookup(&odi); + if (unlikely(IS_ERR(od))) { + err = PTR_ERR(od); + dprintk("%s: osduld_info_lookup => %d\n", __func__, err); + if (err == -ENODEV && retry_flag) { + err = objlayout_autologin(deviceaddr); + if (likely(!err)) { + retry_flag = false; + goto retry_lookup; + } + } + goto out; + } + + dprintk("Adding new dev_id(%llx:%llx)\n", + _DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id)); + + ode = kzalloc(sizeof(*ode), gfp_flags); + if (!ode) { + dprintk("%s: -ENOMEM od=%p\n", __func__, od); + goto out; + } + + nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id); + kfree(deviceaddr); + + ode->od.od = od; + return &ode->id_node; + +out: + kfree(deviceaddr); + return NULL; +} + +static void copy_single_comp(struct ore_components *oc, unsigned c, + struct pnfs_osd_object_cred *src_comp) +{ + struct ore_comp *ocomp = &oc->comps[c]; + + WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */ + WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred)); + + ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id; + ocomp->obj.id = src_comp->oc_object_id.oid_object_id; + + memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred)); +} + +static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags, + struct objio_segment **pseg) +{ +/* This is the in memory structure of the objio_segment + * + * struct __alloc_objio_segment { + * struct objio_segment olseg; + * struct ore_dev *ods[numdevs]; + * struct ore_comp comps[numdevs]; + * } *aolseg; + * NOTE: The code as above compiles and runs perfectly. It is elegant, + * type safe and compact. At some Past time Linus has decided he does not + * like variable length arrays, For the sake of this principal we uglify + * the code as below. + */ + struct objio_segment *lseg; + size_t lseg_size = sizeof(*lseg) + + numdevs * sizeof(lseg->oc.ods[0]) + + numdevs * sizeof(*lseg->oc.comps); + + lseg = kzalloc(lseg_size, gfp_flags); + if (unlikely(!lseg)) { + dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__, + numdevs, lseg_size); + return -ENOMEM; + } + + lseg->oc.numdevs = numdevs; + lseg->oc.single_comp = EC_MULTPLE_COMPS; + lseg->oc.ods = (void *)(lseg + 1); + lseg->oc.comps = (void *)(lseg->oc.ods + numdevs); + + *pseg = lseg; + return 0; +} + +int objio_alloc_lseg(struct pnfs_layout_segment **outp, + struct pnfs_layout_hdr *pnfslay, + struct pnfs_layout_range *range, + struct xdr_stream *xdr, + gfp_t gfp_flags) +{ + struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode); + struct objio_segment *objio_seg; + struct pnfs_osd_xdr_decode_layout_iter iter; + struct pnfs_osd_layout layout; + struct pnfs_osd_object_cred src_comp; + unsigned cur_comp; + int err; + + err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr); + if (unlikely(err)) + return err; + + err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg); + if (unlikely(err)) + return err; + + objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit; + objio_seg->layout.group_width = layout.olo_map.odm_group_width; + objio_seg->layout.group_depth = layout.olo_map.odm_group_depth; + objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1; + objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm; + + err = ore_verify_layout(layout.olo_map.odm_num_comps, + &objio_seg->layout); + if (unlikely(err)) + goto err; + + objio_seg->oc.first_dev = layout.olo_comps_index; + cur_comp = 0; + while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) { + struct nfs4_deviceid_node *d; + struct objio_dev_ent *ode; + + copy_single_comp(&objio_seg->oc, cur_comp, &src_comp); + + d = nfs4_find_get_deviceid(server, + &src_comp.oc_object_id.oid_device_id, + pnfslay->plh_lc_cred, gfp_flags); + if (!d) { + err = -ENXIO; + goto err; + } + + ode = container_of(d, struct objio_dev_ent, id_node); + objio_seg->oc.ods[cur_comp++] = &ode->od; + } + /* pnfs_osd_xdr_decode_layout_comp returns false on error */ + if (unlikely(err)) + goto err; + + *outp = &objio_seg->lseg; + return 0; + +err: + kfree(objio_seg); + dprintk("%s: Error: return %d\n", __func__, err); + *outp = NULL; + return err; +} + +void objio_free_lseg(struct pnfs_layout_segment *lseg) +{ + int i; + struct objio_segment *objio_seg = OBJIO_LSEG(lseg); + + for (i = 0; i < objio_seg->oc.numdevs; i++) { + struct ore_dev *od = objio_seg->oc.ods[i]; + struct objio_dev_ent *ode; + + if (!od) + break; + ode = container_of(od, typeof(*ode), od); + nfs4_put_deviceid_node(&ode->id_node); + } + kfree(objio_seg); +} + +static int +objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading, + struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase, + loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags, + struct objio_state **outp) +{ + struct objio_segment *objio_seg = OBJIO_LSEG(lseg); + struct ore_io_state *ios; + int ret; + struct __alloc_objio_state { + struct objio_state objios; + struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs]; + } *aos; + + aos = kzalloc(sizeof(*aos), gfp_flags); + if (unlikely(!aos)) + return -ENOMEM; + + objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs, + aos->ioerrs, rpcdata, pnfs_layout_type); + + ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading, + offset, count, &ios); + if (unlikely(ret)) { + kfree(aos); + return ret; + } + + ios->pages = pages; + ios->pgbase = pgbase; + ios->private = aos; + BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT); + + aos->objios.sync = 0; + aos->objios.ios = ios; + *outp = &aos->objios; + return 0; +} + +void objio_free_result(struct objlayout_io_res *oir) +{ + struct objio_state *objios = container_of(oir, struct objio_state, oir); + + ore_put_io_state(objios->ios); + kfree(objios); +} + +static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep) +{ + switch (oep) { + case OSD_ERR_PRI_NO_ERROR: + return (enum pnfs_osd_errno)0; + + case OSD_ERR_PRI_CLEAR_PAGES: + BUG_ON(1); + return 0; + + case OSD_ERR_PRI_RESOURCE: + return PNFS_OSD_ERR_RESOURCE; + case OSD_ERR_PRI_BAD_CRED: + return PNFS_OSD_ERR_BAD_CRED; + case OSD_ERR_PRI_NO_ACCESS: + return PNFS_OSD_ERR_NO_ACCESS; + case OSD_ERR_PRI_UNREACHABLE: + return PNFS_OSD_ERR_UNREACHABLE; + case OSD_ERR_PRI_NOT_FOUND: + return PNFS_OSD_ERR_NOT_FOUND; + case OSD_ERR_PRI_NO_SPACE: + return PNFS_OSD_ERR_NO_SPACE; + default: + WARN_ON(1); + /* fallthrough */ + case OSD_ERR_PRI_EIO: + return PNFS_OSD_ERR_EIO; + } +} + +static void __on_dev_error(struct ore_io_state *ios, + struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep, + u64 dev_offset, u64 dev_len) +{ + struct objio_state *objios = ios->private; + struct pnfs_osd_objid pooid; + struct objio_dev_ent *ode = container_of(od, typeof(*ode), od); + /* FIXME: what to do with more-then-one-group layouts. We need to + * translate from ore_io_state index to oc->comps index + */ + unsigned comp = dev_index; + + pooid.oid_device_id = ode->id_node.deviceid; + pooid.oid_partition_id = ios->oc->comps[comp].obj.partition; + pooid.oid_object_id = ios->oc->comps[comp].obj.id; + + objlayout_io_set_result(&objios->oir, comp, + &pooid, osd_pri_2_pnfs_err(oep), + dev_offset, dev_len, !ios->reading); +} + +/* + * read + */ +static void _read_done(struct ore_io_state *ios, void *private) +{ + struct objio_state *objios = private; + ssize_t status; + int ret = ore_check_io(ios, &__on_dev_error); + + /* FIXME: _io_free(ios) can we dealocate the libosd resources; */ + + if (likely(!ret)) + status = ios->length; + else + status = ret; + + objlayout_read_done(&objios->oir, status, objios->sync); +} + +int objio_read_pagelist(struct nfs_pgio_header *hdr) +{ + struct objio_state *objios; + int ret; + + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true, + hdr->lseg, hdr->args.pages, hdr->args.pgbase, + hdr->args.offset, hdr->args.count, hdr, + GFP_KERNEL, &objios); + if (unlikely(ret)) + return ret; + + objios->ios->done = _read_done; + dprintk("%s: offset=0x%llx length=0x%x\n", __func__, + hdr->args.offset, hdr->args.count); + ret = ore_read(objios->ios); + if (unlikely(ret)) + objio_free_result(&objios->oir); + return ret; +} + +/* + * write + */ +static void _write_done(struct ore_io_state *ios, void *private) +{ + struct objio_state *objios = private; + ssize_t status; + int ret = ore_check_io(ios, &__on_dev_error); + + /* FIXME: _io_free(ios) can we dealocate the libosd resources; */ + + if (likely(!ret)) { + /* FIXME: should be based on the OSD's persistence model + * See OSD2r05 Section 4.13 Data persistence model */ + objios->oir.committed = NFS_FILE_SYNC; + status = ios->length; + } else { + status = ret; + } + + objlayout_write_done(&objios->oir, status, objios->sync); +} + +static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) +{ + struct objio_state *objios = priv; + struct nfs_pgio_header *hdr = objios->oir.rpcdata; + struct address_space *mapping = hdr->inode->i_mapping; + pgoff_t index = offset / PAGE_SIZE; + struct page *page; + loff_t i_size = i_size_read(hdr->inode); + + if (offset >= i_size) { + *uptodate = true; + dprintk("%s: g_zero_page index=0x%lx\n", __func__, index); + return ZERO_PAGE(0); + } + + page = find_get_page(mapping, index); + if (!page) { + page = find_or_create_page(mapping, index, GFP_NOFS); + if (unlikely(!page)) { + dprintk("%s: grab_cache_page Failed index=0x%lx\n", + __func__, index); + return NULL; + } + unlock_page(page); + } + if (PageDirty(page) || PageWriteback(page)) + *uptodate = true; + else + *uptodate = PageUptodate(page); + dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate); + return page; +} + +static void __r4w_put_page(void *priv, struct page *page) +{ + dprintk("%s: index=0x%lx\n", __func__, + (page == ZERO_PAGE(0)) ? -1UL : page->index); + if (ZERO_PAGE(0) != page) + page_cache_release(page); + return; +} + +static const struct _ore_r4w_op _r4w_op = { + .get_page = &__r4w_get_page, + .put_page = &__r4w_put_page, +}; + +int objio_write_pagelist(struct nfs_pgio_header *hdr, int how) +{ + struct objio_state *objios; + int ret; + + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false, + hdr->lseg, hdr->args.pages, hdr->args.pgbase, + hdr->args.offset, hdr->args.count, hdr, GFP_NOFS, + &objios); + if (unlikely(ret)) + return ret; + + objios->sync = 0 != (how & FLUSH_SYNC); + objios->ios->r4w = &_r4w_op; + + if (!objios->sync) + objios->ios->done = _write_done; + + dprintk("%s: offset=0x%llx length=0x%x\n", __func__, + hdr->args.offset, hdr->args.count); + ret = ore_write(objios->ios); + if (unlikely(ret)) { + objio_free_result(&objios->oir); + return ret; + } + + if (objios->sync) + _write_done(objios->ios, objios); + + return 0; +} + +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio, + struct nfs_page *prev, struct nfs_page *req) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio); + unsigned int size; + + size = pnfs_generic_pg_test(pgio, prev, req); + + if (!size || mirror->pg_count + req->wb_bytes > + (unsigned long)pgio->pg_layout_private) + return 0; + + return min(size, req->wb_bytes); +} + +static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + pnfs_generic_pg_init_read(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; +} + +static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout, + unsigned long *stripe_end) +{ + u32 stripe_off; + unsigned stripe_size; + + if (layout->raid_algorithm == PNFS_OSD_RAID_0) + return true; + + stripe_size = layout->stripe_unit * + (layout->group_width - layout->parity); + + div_u64_rem(offset, stripe_size, &stripe_off); + if (!stripe_off) + return true; + + *stripe_end = stripe_size - stripe_off; + return false; +} + +static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + unsigned long stripe_end = 0; + u64 wb_size; + + if (pgio->pg_dreq == NULL) + wb_size = i_size_read(pgio->pg_inode) - req_offset(req); + else + wb_size = nfs_dreq_bytes_left(pgio->pg_dreq); + + pnfs_generic_pg_init_write(pgio, req, wb_size); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + if (req->wb_offset || + !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE, + &OBJIO_LSEG(pgio->pg_lseg)->layout, + &stripe_end)) { + pgio->pg_layout_private = (void *)stripe_end; + } else { + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + } +} + +static const struct nfs_pageio_ops objio_pg_read_ops = { + .pg_init = objio_init_read, + .pg_test = objio_pg_test, + .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static const struct nfs_pageio_ops objio_pg_write_ops = { + .pg_init = objio_init_write, + .pg_test = objio_pg_test, + .pg_doio = pnfs_generic_pg_writepages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static struct pnfs_layoutdriver_type objlayout_type = { + .id = LAYOUT_OSD2_OBJECTS, + .name = "LAYOUT_OSD2_OBJECTS", + .flags = PNFS_LAYOUTRET_ON_SETATTR | + PNFS_LAYOUTRET_ON_ERROR, + + .max_deviceinfo_size = PAGE_SIZE, + .owner = THIS_MODULE, + .alloc_layout_hdr = objlayout_alloc_layout_hdr, + .free_layout_hdr = objlayout_free_layout_hdr, + + .alloc_lseg = objlayout_alloc_lseg, + .free_lseg = objlayout_free_lseg, + + .read_pagelist = objlayout_read_pagelist, + .write_pagelist = objlayout_write_pagelist, + .pg_read_ops = &objio_pg_read_ops, + .pg_write_ops = &objio_pg_write_ops, + + .sync = pnfs_generic_sync, + + .free_deviceid_node = objio_free_deviceid_node, + + .encode_layoutcommit = objlayout_encode_layoutcommit, + .encode_layoutreturn = objlayout_encode_layoutreturn, +}; + +MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects"); +MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>"); +MODULE_LICENSE("GPL"); + +static int __init +objlayout_init(void) +{ + int ret = pnfs_register_layoutdriver(&objlayout_type); + + if (ret) + printk(KERN_INFO + "NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n", + __func__, ret); + else + printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n", + __func__); + return ret; +} + +static void __exit +objlayout_exit(void) +{ + pnfs_unregister_layoutdriver(&objlayout_type); + printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n", + __func__); +} + +MODULE_ALIAS("nfs-layouttype4-2"); + +module_init(objlayout_init); +module_exit(objlayout_exit); diff --git a/kernel/fs/nfs/objlayout/objlayout.c b/kernel/fs/nfs/objlayout/objlayout.c new file mode 100644 index 000000000..919efd4a1 --- /dev/null +++ b/kernel/fs/nfs/objlayout/objlayout.c @@ -0,0 +1,706 @@ +/* + * pNFS Objects layout driver high level definitions + * + * Copyright (C) 2007 Panasas Inc. [year of first publication] + * All rights reserved. + * + * Benny Halevy <bhalevy@panasas.com> + * Boaz Harrosh <ooo@electrozaur.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * See the file COPYING included with this distribution for more details. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Panasas company nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/kmod.h> +#include <linux/moduleparam.h> +#include <linux/ratelimit.h> +#include <scsi/osd_initiator.h> +#include "objlayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD +/* + * Create a objlayout layout structure for the given inode and return it. + */ +struct pnfs_layout_hdr * +objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) +{ + struct objlayout *objlay; + + objlay = kzalloc(sizeof(struct objlayout), gfp_flags); + if (!objlay) + return NULL; + spin_lock_init(&objlay->lock); + INIT_LIST_HEAD(&objlay->err_list); + dprintk("%s: Return %p\n", __func__, objlay); + return &objlay->pnfs_layout; +} + +/* + * Free an objlayout layout structure + */ +void +objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct objlayout *objlay = OBJLAYOUT(lo); + + dprintk("%s: objlay %p\n", __func__, objlay); + + WARN_ON(!list_empty(&objlay->err_list)); + kfree(objlay); +} + +/* + * Unmarshall layout and store it in pnfslay. + */ +struct pnfs_layout_segment * +objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay, + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) +{ + int status = -ENOMEM; + struct xdr_stream stream; + struct xdr_buf buf = { + .pages = lgr->layoutp->pages, + .page_len = lgr->layoutp->len, + .buflen = lgr->layoutp->len, + .len = lgr->layoutp->len, + }; + struct page *scratch; + struct pnfs_layout_segment *lseg; + + dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay); + + scratch = alloc_page(gfp_flags); + if (!scratch) + goto err_nofree; + + xdr_init_decode(&stream, &buf, NULL); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags); + if (unlikely(status)) { + dprintk("%s: objio_alloc_lseg Return err %d\n", __func__, + status); + goto err; + } + + __free_page(scratch); + + dprintk("%s: Return %p\n", __func__, lseg); + return lseg; + +err: + __free_page(scratch); +err_nofree: + dprintk("%s: Err Return=>%d\n", __func__, status); + return ERR_PTR(status); +} + +/* + * Free a layout segement + */ +void +objlayout_free_lseg(struct pnfs_layout_segment *lseg) +{ + dprintk("%s: freeing layout segment %p\n", __func__, lseg); + + if (unlikely(!lseg)) + return; + + objio_free_lseg(lseg); +} + +/* + * I/O Operations + */ +static inline u64 +end_offset(u64 start, u64 len) +{ + u64 end; + + end = start + len; + return end >= start ? end : NFS4_MAX_UINT64; +} + +static void _fix_verify_io_params(struct pnfs_layout_segment *lseg, + struct page ***p_pages, unsigned *p_pgbase, + u64 offset, unsigned long count) +{ + u64 lseg_end_offset; + + BUG_ON(offset < lseg->pls_range.offset); + lseg_end_offset = end_offset(lseg->pls_range.offset, + lseg->pls_range.length); + BUG_ON(offset >= lseg_end_offset); + WARN_ON(offset + count > lseg_end_offset); + + if (*p_pgbase > PAGE_SIZE) { + dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase); + *p_pages += *p_pgbase >> PAGE_SHIFT; + *p_pgbase &= ~PAGE_MASK; + } +} + +/* + * I/O done common code + */ +static void +objlayout_iodone(struct objlayout_io_res *oir) +{ + if (likely(oir->status >= 0)) { + objio_free_result(oir); + } else { + struct objlayout *objlay = oir->objlay; + + spin_lock(&objlay->lock); + objlay->delta_space_valid = OBJ_DSU_INVALID; + list_add(&objlay->err_list, &oir->err_list); + spin_unlock(&objlay->lock); + } +} + +/* + * objlayout_io_set_result - Set an osd_error code on a specific osd comp. + * + * The @index component IO failed (error returned from target). Register + * the error for later reporting at layout-return. + */ +void +objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index, + struct pnfs_osd_objid *pooid, int osd_error, + u64 offset, u64 length, bool is_write) +{ + struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index]; + + BUG_ON(index >= oir->num_comps); + if (osd_error) { + ioerr->oer_component = *pooid; + ioerr->oer_comp_offset = offset; + ioerr->oer_comp_length = length; + ioerr->oer_iswrite = is_write; + ioerr->oer_errno = osd_error; + + dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) " + "par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n", + __func__, index, ioerr->oer_errno, + ioerr->oer_iswrite, + _DEVID_LO(&ioerr->oer_component.oid_device_id), + _DEVID_HI(&ioerr->oer_component.oid_device_id), + ioerr->oer_component.oid_partition_id, + ioerr->oer_component.oid_object_id, + ioerr->oer_comp_offset, + ioerr->oer_comp_length); + } else { + /* User need not call if no error is reported */ + ioerr->oer_errno = 0; + } +} + +/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete(). + * This is because the osd completion is called with ints-off from + * the block layer + */ +static void _rpc_read_complete(struct work_struct *work) +{ + struct rpc_task *task; + struct nfs_pgio_header *hdr; + + dprintk("%s enter\n", __func__); + task = container_of(work, struct rpc_task, u.tk_work); + hdr = container_of(task, struct nfs_pgio_header, task); + + pnfs_ld_read_done(hdr); +} + +void +objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) +{ + struct nfs_pgio_header *hdr = oir->rpcdata; + + oir->status = hdr->task.tk_status = status; + if (status >= 0) + hdr->res.count = status; + else + hdr->pnfs_error = status; + objlayout_iodone(oir); + /* must not use oir after this point */ + + dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__, + status, hdr->res.eof, sync); + + if (sync) + pnfs_ld_read_done(hdr); + else { + INIT_WORK(&hdr->task.u.tk_work, _rpc_read_complete); + schedule_work(&hdr->task.u.tk_work); + } +} + +/* + * Perform sync or async reads. + */ +enum pnfs_try_status +objlayout_read_pagelist(struct nfs_pgio_header *hdr) +{ + struct inode *inode = hdr->inode; + loff_t offset = hdr->args.offset; + size_t count = hdr->args.count; + int err; + loff_t eof; + + eof = i_size_read(inode); + if (unlikely(offset + count > eof)) { + if (offset >= eof) { + err = 0; + hdr->res.count = 0; + hdr->res.eof = 1; + /*FIXME: do we need to call pnfs_ld_read_done() */ + goto out; + } + count = eof - offset; + } + + hdr->res.eof = (offset + count) >= eof; + _fix_verify_io_params(hdr->lseg, &hdr->args.pages, + &hdr->args.pgbase, + hdr->args.offset, hdr->args.count); + + dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n", + __func__, inode->i_ino, offset, count, hdr->res.eof); + + err = objio_read_pagelist(hdr); + out: + if (unlikely(err)) { + hdr->pnfs_error = err; + dprintk("%s: Returned Error %d\n", __func__, err); + return PNFS_NOT_ATTEMPTED; + } + return PNFS_ATTEMPTED; +} + +/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete(). + * This is because the osd completion is called with ints-off from + * the block layer + */ +static void _rpc_write_complete(struct work_struct *work) +{ + struct rpc_task *task; + struct nfs_pgio_header *hdr; + + dprintk("%s enter\n", __func__); + task = container_of(work, struct rpc_task, u.tk_work); + hdr = container_of(task, struct nfs_pgio_header, task); + + pnfs_ld_write_done(hdr); +} + +void +objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) +{ + struct nfs_pgio_header *hdr = oir->rpcdata; + + oir->status = hdr->task.tk_status = status; + if (status >= 0) { + hdr->res.count = status; + hdr->verf.committed = oir->committed; + } else { + hdr->pnfs_error = status; + } + objlayout_iodone(oir); + /* must not use oir after this point */ + + dprintk("%s: Return status %zd committed %d sync=%d\n", __func__, + status, hdr->verf.committed, sync); + + if (sync) + pnfs_ld_write_done(hdr); + else { + INIT_WORK(&hdr->task.u.tk_work, _rpc_write_complete); + schedule_work(&hdr->task.u.tk_work); + } +} + +/* + * Perform sync or async writes. + */ +enum pnfs_try_status +objlayout_write_pagelist(struct nfs_pgio_header *hdr, int how) +{ + int err; + + _fix_verify_io_params(hdr->lseg, &hdr->args.pages, + &hdr->args.pgbase, + hdr->args.offset, hdr->args.count); + + err = objio_write_pagelist(hdr, how); + if (unlikely(err)) { + hdr->pnfs_error = err; + dprintk("%s: Returned Error %d\n", __func__, err); + return PNFS_NOT_ATTEMPTED; + } + return PNFS_ATTEMPTED; +} + +void +objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay, + struct xdr_stream *xdr, + const struct nfs4_layoutcommit_args *args) +{ + struct objlayout *objlay = OBJLAYOUT(pnfslay); + struct pnfs_osd_layoutupdate lou; + __be32 *start; + + dprintk("%s: Begin\n", __func__); + + spin_lock(&objlay->lock); + lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID); + lou.dsu_delta = objlay->delta_space_used; + objlay->delta_space_used = 0; + objlay->delta_space_valid = OBJ_DSU_INIT; + lou.olu_ioerr_flag = !list_empty(&objlay->err_list); + spin_unlock(&objlay->lock); + + start = xdr_reserve_space(xdr, 4); + + BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou)); + + *start = cpu_to_be32((xdr->p - start - 1) * 4); + + dprintk("%s: Return delta_space_used %lld err %d\n", __func__, + lou.dsu_delta, lou.olu_ioerr_flag); +} + +static int +err_prio(u32 oer_errno) +{ + switch (oer_errno) { + case 0: + return 0; + + case PNFS_OSD_ERR_RESOURCE: + return OSD_ERR_PRI_RESOURCE; + case PNFS_OSD_ERR_BAD_CRED: + return OSD_ERR_PRI_BAD_CRED; + case PNFS_OSD_ERR_NO_ACCESS: + return OSD_ERR_PRI_NO_ACCESS; + case PNFS_OSD_ERR_UNREACHABLE: + return OSD_ERR_PRI_UNREACHABLE; + case PNFS_OSD_ERR_NOT_FOUND: + return OSD_ERR_PRI_NOT_FOUND; + case PNFS_OSD_ERR_NO_SPACE: + return OSD_ERR_PRI_NO_SPACE; + default: + WARN_ON(1); + /* fallthrough */ + case PNFS_OSD_ERR_EIO: + return OSD_ERR_PRI_EIO; + } +} + +static void +merge_ioerr(struct pnfs_osd_ioerr *dest_err, + const struct pnfs_osd_ioerr *src_err) +{ + u64 dest_end, src_end; + + if (!dest_err->oer_errno) { + *dest_err = *src_err; + /* accumulated device must be blank */ + memset(&dest_err->oer_component.oid_device_id, 0, + sizeof(dest_err->oer_component.oid_device_id)); + + return; + } + + if (dest_err->oer_component.oid_partition_id != + src_err->oer_component.oid_partition_id) + dest_err->oer_component.oid_partition_id = 0; + + if (dest_err->oer_component.oid_object_id != + src_err->oer_component.oid_object_id) + dest_err->oer_component.oid_object_id = 0; + + if (dest_err->oer_comp_offset > src_err->oer_comp_offset) + dest_err->oer_comp_offset = src_err->oer_comp_offset; + + dest_end = end_offset(dest_err->oer_comp_offset, + dest_err->oer_comp_length); + src_end = end_offset(src_err->oer_comp_offset, + src_err->oer_comp_length); + if (dest_end < src_end) + dest_end = src_end; + + dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset; + + if ((src_err->oer_iswrite == dest_err->oer_iswrite) && + (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) { + dest_err->oer_errno = src_err->oer_errno; + } else if (src_err->oer_iswrite) { + dest_err->oer_iswrite = true; + dest_err->oer_errno = src_err->oer_errno; + } +} + +static void +encode_accumulated_error(struct objlayout *objlay, __be32 *p) +{ + struct objlayout_io_res *oir, *tmp; + struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0}; + + list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) { + unsigned i; + + for (i = 0; i < oir->num_comps; i++) { + struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i]; + + if (!ioerr->oer_errno) + continue; + + printk(KERN_ERR "NFS: %s: err[%d]: errno=%d " + "is_write=%d dev(%llx:%llx) par=0x%llx " + "obj=0x%llx offset=0x%llx length=0x%llx\n", + __func__, i, ioerr->oer_errno, + ioerr->oer_iswrite, + _DEVID_LO(&ioerr->oer_component.oid_device_id), + _DEVID_HI(&ioerr->oer_component.oid_device_id), + ioerr->oer_component.oid_partition_id, + ioerr->oer_component.oid_object_id, + ioerr->oer_comp_offset, + ioerr->oer_comp_length); + + merge_ioerr(&accumulated_err, ioerr); + } + list_del(&oir->err_list); + objio_free_result(oir); + } + + pnfs_osd_xdr_encode_ioerr(p, &accumulated_err); +} + +void +objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct objlayout *objlay = OBJLAYOUT(pnfslay); + struct objlayout_io_res *oir, *tmp; + __be32 *start; + + dprintk("%s: Begin\n", __func__); + start = xdr_reserve_space(xdr, 4); + BUG_ON(!start); + + spin_lock(&objlay->lock); + + list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) { + __be32 *last_xdr = NULL, *p; + unsigned i; + int res = 0; + + for (i = 0; i < oir->num_comps; i++) { + struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i]; + + if (!ioerr->oer_errno) + continue; + + dprintk("%s: err[%d]: errno=%d is_write=%d " + "dev(%llx:%llx) par=0x%llx obj=0x%llx " + "offset=0x%llx length=0x%llx\n", + __func__, i, ioerr->oer_errno, + ioerr->oer_iswrite, + _DEVID_LO(&ioerr->oer_component.oid_device_id), + _DEVID_HI(&ioerr->oer_component.oid_device_id), + ioerr->oer_component.oid_partition_id, + ioerr->oer_component.oid_object_id, + ioerr->oer_comp_offset, + ioerr->oer_comp_length); + + p = pnfs_osd_xdr_ioerr_reserve_space(xdr); + if (unlikely(!p)) { + res = -E2BIG; + break; /* accumulated_error */ + } + + last_xdr = p; + pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]); + } + + /* TODO: use xdr_write_pages */ + if (unlikely(res)) { + /* no space for even one error descriptor */ + BUG_ON(!last_xdr); + + /* we've encountered a situation with lots and lots of + * errors and no space to encode them all. Use the last + * available slot to report the union of all the + * remaining errors. + */ + encode_accumulated_error(objlay, last_xdr); + goto loop_done; + } + list_del(&oir->err_list); + objio_free_result(oir); + } +loop_done: + spin_unlock(&objlay->lock); + + *start = cpu_to_be32((xdr->p - start - 1) * 4); + dprintk("%s: Return\n", __func__); +} + +enum { + OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64, + OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1, + OSD_LOGIN_UPCALL_PATHLEN = 256 +}; + +static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login"; + +module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog), + 0600); +MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program"); + +struct __auto_login { + char uri[OBJLAYOUT_MAX_URI_LEN]; + char osdname[OBJLAYOUT_MAX_OSDNAME_LEN]; + char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN]; +}; + +static int __objlayout_upcall(struct __auto_login *login) +{ + static char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + char *argv[8]; + int ret; + + if (unlikely(!osd_login_prog[0])) { + dprintk("%s: osd_login_prog is disabled\n", __func__); + return -EACCES; + } + + dprintk("%s uri: %s\n", __func__, login->uri); + dprintk("%s osdname %s\n", __func__, login->osdname); + dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex); + + argv[0] = (char *)osd_login_prog; + argv[1] = "-u"; + argv[2] = login->uri; + argv[3] = "-o"; + argv[4] = login->osdname; + argv[5] = "-s"; + argv[6] = login->systemid_hex; + argv[7] = NULL; + + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + /* + * Disable the upcall mechanism if we're getting an ENOENT or + * EACCES error. The admin can re-enable it on the fly by using + * sysfs to set the objlayoutdriver.osd_login_prog module parameter once + * the problem has been fixed. + */ + if (ret == -ENOENT || ret == -EACCES) { + printk(KERN_ERR "PNFS-OBJ: %s was not found please set " + "objlayoutdriver.osd_login_prog kernel parameter!\n", + osd_login_prog); + osd_login_prog[0] = '\0'; + } + dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret); + + return ret; +} + +/* Assume dest is all zeros */ +static void __copy_nfsS_and_zero_terminate(struct nfs4_string s, + char *dest, int max_len, + const char *var_name) +{ + if (!s.len) + return; + + if (s.len >= max_len) { + pr_warn_ratelimited( + "objlayout_autologin: %s: s.len(%d) >= max_len(%d)", + var_name, s.len, max_len); + s.len = max_len - 1; /* space for null terminator */ + } + + memcpy(dest, s.data, s.len); +} + +/* Assume sysid is all zeros */ +static void _sysid_2_hex(struct nfs4_string s, + char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN]) +{ + int i; + char *cur; + + if (!s.len) + return; + + if (s.len != OSD_SYSTEMID_LEN) { + pr_warn_ratelimited( + "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN", + s.len); + if (s.len > OSD_SYSTEMID_LEN) + s.len = OSD_SYSTEMID_LEN; + } + + cur = sysid; + for (i = 0; i < s.len; i++) + cur = hex_byte_pack(cur, s.data[i]); +} + +int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr) +{ + int rc; + struct __auto_login login; + + if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len) + return -ENODEV; + + memset(&login, 0, sizeof(login)); + __copy_nfsS_and_zero_terminate( + deviceaddr->oda_targetaddr.ota_netaddr.r_addr, + login.uri, sizeof(login.uri), "URI"); + + __copy_nfsS_and_zero_terminate( + deviceaddr->oda_osdname, + login.osdname, sizeof(login.osdname), "OSDNAME"); + + _sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex); + + rc = __objlayout_upcall(&login); + if (rc > 0) /* script returns positive values */ + rc = -ENODEV; + + return rc; +} diff --git a/kernel/fs/nfs/objlayout/objlayout.h b/kernel/fs/nfs/objlayout/objlayout.h new file mode 100644 index 000000000..2641dbad3 --- /dev/null +++ b/kernel/fs/nfs/objlayout/objlayout.h @@ -0,0 +1,184 @@ +/* + * Data types and function declerations for interfacing with the + * pNFS standard object layout driver. + * + * Copyright (C) 2007 Panasas Inc. [year of first publication] + * All rights reserved. + * + * Benny Halevy <bhalevy@panasas.com> + * Boaz Harrosh <ooo@electrozaur.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * See the file COPYING included with this distribution for more details. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Panasas company nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _OBJLAYOUT_H +#define _OBJLAYOUT_H + +#include <linux/nfs_fs.h> +#include <linux/pnfs_osd_xdr.h> +#include "../pnfs.h" + +/* + * per-inode layout + */ +struct objlayout { + struct pnfs_layout_hdr pnfs_layout; + + /* for layout_commit */ + enum osd_delta_space_valid_enum { + OBJ_DSU_INIT = 0, + OBJ_DSU_VALID, + OBJ_DSU_INVALID, + } delta_space_valid; + s64 delta_space_used; /* consumed by write ops */ + + /* for layout_return */ + spinlock_t lock; + struct list_head err_list; +}; + +static inline struct objlayout * +OBJLAYOUT(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct objlayout, pnfs_layout); +} + +/* + * per-I/O operation state + * embedded in objects provider io_state data structure + */ +struct objlayout_io_res { + struct objlayout *objlay; + + void *rpcdata; + int status; /* res */ + int committed; /* res */ + + /* Error reporting (layout_return) */ + struct list_head err_list; + unsigned num_comps; + /* Pointer to array of error descriptors of size num_comps. + * It should contain as many entries as devices in the osd_layout + * that participate in the I/O. It is up to the io_engine to allocate + * needed space and set num_comps. + */ + struct pnfs_osd_ioerr *ioerrs; +}; + +static inline +void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps, + struct pnfs_osd_ioerr *ioerrs, void *rpcdata, + struct pnfs_layout_hdr *pnfs_layout_type) +{ + oir->objlay = OBJLAYOUT(pnfs_layout_type); + oir->rpcdata = rpcdata; + INIT_LIST_HEAD(&oir->err_list); + oir->num_comps = num_comps; + oir->ioerrs = ioerrs; +} + +/* + * Raid engine I/O API + */ +extern int objio_alloc_lseg(struct pnfs_layout_segment **outp, + struct pnfs_layout_hdr *pnfslay, + struct pnfs_layout_range *range, + struct xdr_stream *xdr, + gfp_t gfp_flags); +extern void objio_free_lseg(struct pnfs_layout_segment *lseg); + +/* objio_free_result will free these @oir structs received from + * objlayout_{read,write}_done + */ +extern void objio_free_result(struct objlayout_io_res *oir); + +extern int objio_read_pagelist(struct nfs_pgio_header *rdata); +extern int objio_write_pagelist(struct nfs_pgio_header *wdata, int how); + +/* + * callback API + */ +extern void objlayout_io_set_result(struct objlayout_io_res *oir, + unsigned index, struct pnfs_osd_objid *pooid, + int osd_error, u64 offset, u64 length, bool is_write); + +static inline void +objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used) +{ + /* If one of the I/Os errored out and the delta_space_used was + * invalid we render the complete report as invalid. Protocol mandate + * the DSU be accurate or not reported. + */ + spin_lock(&objlay->lock); + if (objlay->delta_space_valid != OBJ_DSU_INVALID) { + objlay->delta_space_valid = OBJ_DSU_VALID; + objlay->delta_space_used += space_used; + } + spin_unlock(&objlay->lock); +} + +extern void objlayout_read_done(struct objlayout_io_res *oir, + ssize_t status, bool sync); +extern void objlayout_write_done(struct objlayout_io_res *oir, + ssize_t status, bool sync); + +/* + * exported generic objects function vectors + */ + +extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags); +extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *); + +extern struct pnfs_layout_segment *objlayout_alloc_lseg( + struct pnfs_layout_hdr *, + struct nfs4_layoutget_res *, + gfp_t gfp_flags); +extern void objlayout_free_lseg(struct pnfs_layout_segment *); + +extern enum pnfs_try_status objlayout_read_pagelist( + struct nfs_pgio_header *); + +extern enum pnfs_try_status objlayout_write_pagelist( + struct nfs_pgio_header *, + int how); + +extern void objlayout_encode_layoutcommit( + struct pnfs_layout_hdr *, + struct xdr_stream *, + const struct nfs4_layoutcommit_args *); + +extern void objlayout_encode_layoutreturn( + struct pnfs_layout_hdr *, + struct xdr_stream *, + const struct nfs4_layoutreturn_args *); + +extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr); + +#endif /* _OBJLAYOUT_H */ diff --git a/kernel/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/kernel/fs/nfs/objlayout/pnfs_osd_xdr_cli.c new file mode 100644 index 000000000..f093c7ec9 --- /dev/null +++ b/kernel/fs/nfs/objlayout/pnfs_osd_xdr_cli.c @@ -0,0 +1,415 @@ +/* + * Object-Based pNFS Layout XDR layer + * + * Copyright (C) 2007 Panasas Inc. [year of first publication] + * All rights reserved. + * + * Benny Halevy <bhalevy@panasas.com> + * Boaz Harrosh <ooo@electrozaur.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * See the file COPYING included with this distribution for more details. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Panasas company nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/pnfs_osd_xdr.h> + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +/* + * The following implementation is based on RFC5664 + */ + +/* + * struct pnfs_osd_objid { + * struct nfs4_deviceid oid_device_id; + * u64 oid_partition_id; + * u64 oid_object_id; + * }; // xdr size 32 bytes + */ +static __be32 * +_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid) +{ + p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data, + sizeof(objid->oid_device_id.data)); + + p = xdr_decode_hyper(p, &objid->oid_partition_id); + p = xdr_decode_hyper(p, &objid->oid_object_id); + return p; +} +/* + * struct pnfs_osd_opaque_cred { + * u32 cred_len; + * void *cred; + * }; // xdr size [variable] + * The return pointers are from the xdr buffer + */ +static int +_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred, + struct xdr_stream *xdr) +{ + __be32 *p = xdr_inline_decode(xdr, 1); + + if (!p) + return -EINVAL; + + opaque_cred->cred_len = be32_to_cpu(*p++); + + p = xdr_inline_decode(xdr, opaque_cred->cred_len); + if (!p) + return -EINVAL; + + opaque_cred->cred = p; + return 0; +} + +/* + * struct pnfs_osd_object_cred { + * struct pnfs_osd_objid oc_object_id; + * u32 oc_osd_version; + * u32 oc_cap_key_sec; + * struct pnfs_osd_opaque_cred oc_cap_key + * struct pnfs_osd_opaque_cred oc_cap; + * }; // xdr size 32 + 4 + 4 + [variable] + [variable] + */ +static int +_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp, + struct xdr_stream *xdr) +{ + __be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4); + int ret; + + if (!p) + return -EIO; + + p = _osd_xdr_decode_objid(p, &comp->oc_object_id); + comp->oc_osd_version = be32_to_cpup(p++); + comp->oc_cap_key_sec = be32_to_cpup(p); + + ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr); + if (unlikely(ret)) + return ret; + + ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr); + return ret; +} + +/* + * struct pnfs_osd_data_map { + * u32 odm_num_comps; + * u64 odm_stripe_unit; + * u32 odm_group_width; + * u32 odm_group_depth; + * u32 odm_mirror_cnt; + * u32 odm_raid_algorithm; + * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4 + */ +static inline int +_osd_data_map_xdr_sz(void) +{ + return 4 + 8 + 4 + 4 + 4 + 4; +} + +static __be32 * +_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map) +{ + data_map->odm_num_comps = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &data_map->odm_stripe_unit); + data_map->odm_group_width = be32_to_cpup(p++); + data_map->odm_group_depth = be32_to_cpup(p++); + data_map->odm_mirror_cnt = be32_to_cpup(p++); + data_map->odm_raid_algorithm = be32_to_cpup(p++); + dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u " + "odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n", + __func__, + data_map->odm_num_comps, + (unsigned long long)data_map->odm_stripe_unit, + data_map->odm_group_width, + data_map->odm_group_depth, + data_map->odm_mirror_cnt, + data_map->odm_raid_algorithm); + return p; +} + +int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout, + struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr) +{ + __be32 *p; + + memset(iter, 0, sizeof(*iter)); + + p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4); + if (unlikely(!p)) + return -EINVAL; + + p = _osd_xdr_decode_data_map(p, &layout->olo_map); + layout->olo_comps_index = be32_to_cpup(p++); + layout->olo_num_comps = be32_to_cpup(p++); + dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__, + layout->olo_comps_index, layout->olo_num_comps); + + iter->total_comps = layout->olo_num_comps; + return 0; +} + +bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp, + struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr, + int *err) +{ + BUG_ON(iter->decoded_comps > iter->total_comps); + if (iter->decoded_comps == iter->total_comps) + return false; + + *err = _osd_xdr_decode_object_cred(comp, xdr); + if (unlikely(*err)) { + dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d " + "total_comps=%d\n", __func__, *err, + iter->decoded_comps, iter->total_comps); + return false; /* stop the loop */ + } + dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx " + "key_len=%u cap_len=%u\n", + __func__, + _DEVID_LO(&comp->oc_object_id.oid_device_id), + _DEVID_HI(&comp->oc_object_id.oid_device_id), + comp->oc_object_id.oid_partition_id, + comp->oc_object_id.oid_object_id, + comp->oc_cap_key.cred_len, comp->oc_cap.cred_len); + + iter->decoded_comps++; + return true; +} + +/* + * Get Device Information Decoding + * + * Note: since Device Information is currently done synchronously, all + * variable strings fields are left inside the rpc buffer and are only + * pointed to by the pnfs_osd_deviceaddr members. So the read buffer + * should not be freed while the returned information is in use. + */ +/* + *struct nfs4_string { + * unsigned int len; + * char *data; + *}; // size [variable] + * NOTE: Returned string points to inside the XDR buffer + */ +static __be32 * +__read_u8_opaque(__be32 *p, struct nfs4_string *str) +{ + str->len = be32_to_cpup(p++); + str->data = (char *)p; + + p += XDR_QUADLEN(str->len); + return p; +} + +/* + * struct pnfs_osd_targetid { + * u32 oti_type; + * struct nfs4_string oti_scsi_device_id; + * };// size 4 + [variable] + */ +static __be32 * +__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid) +{ + u32 oti_type; + + oti_type = be32_to_cpup(p++); + targetid->oti_type = oti_type; + + switch (oti_type) { + case OBJ_TARGET_SCSI_NAME: + case OBJ_TARGET_SCSI_DEVICE_ID: + p = __read_u8_opaque(p, &targetid->oti_scsi_device_id); + } + + return p; +} + +/* + * struct pnfs_osd_net_addr { + * struct nfs4_string r_netid; + * struct nfs4_string r_addr; + * }; + */ +static __be32 * +__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr) +{ + p = __read_u8_opaque(p, &netaddr->r_netid); + p = __read_u8_opaque(p, &netaddr->r_addr); + + return p; +} + +/* + * struct pnfs_osd_targetaddr { + * u32 ota_available; + * struct pnfs_osd_net_addr ota_netaddr; + * }; + */ +static __be32 * +__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr) +{ + u32 ota_available; + + ota_available = be32_to_cpup(p++); + targetaddr->ota_available = ota_available; + + if (ota_available) + p = __read_net_addr(p, &targetaddr->ota_netaddr); + + + return p; +} + +/* + * struct pnfs_osd_deviceaddr { + * struct pnfs_osd_targetid oda_targetid; + * struct pnfs_osd_targetaddr oda_targetaddr; + * u8 oda_lun[8]; + * struct nfs4_string oda_systemid; + * struct pnfs_osd_object_cred oda_root_obj_cred; + * struct nfs4_string oda_osdname; + * }; + */ + +/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does + * not have an xdr_stream + */ +static __be32 * +__read_opaque_cred(__be32 *p, + struct pnfs_osd_opaque_cred *opaque_cred) +{ + opaque_cred->cred_len = be32_to_cpu(*p++); + opaque_cred->cred = p; + return p + XDR_QUADLEN(opaque_cred->cred_len); +} + +static __be32 * +__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp) +{ + p = _osd_xdr_decode_objid(p, &comp->oc_object_id); + comp->oc_osd_version = be32_to_cpup(p++); + comp->oc_cap_key_sec = be32_to_cpup(p++); + + p = __read_opaque_cred(p, &comp->oc_cap_key); + p = __read_opaque_cred(p, &comp->oc_cap); + return p; +} + +void pnfs_osd_xdr_decode_deviceaddr( + struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p) +{ + p = __read_targetid(p, &deviceaddr->oda_targetid); + + p = __read_targetaddr(p, &deviceaddr->oda_targetaddr); + + p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun, + sizeof(deviceaddr->oda_lun)); + + p = __read_u8_opaque(p, &deviceaddr->oda_systemid); + + p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred); + + p = __read_u8_opaque(p, &deviceaddr->oda_osdname); + + /* libosd likes this terminated in dbg. It's last, so no problems */ + deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0; +} + +/* + * struct pnfs_osd_layoutupdate { + * u32 dsu_valid; + * s64 dsu_delta; + * u32 olu_ioerr_flag; + * }; xdr size 4 + 8 + 4 + */ +int +pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr, + struct pnfs_osd_layoutupdate *lou) +{ + __be32 *p = xdr_reserve_space(xdr, 4 + 8 + 4); + + if (!p) + return -E2BIG; + + *p++ = cpu_to_be32(lou->dsu_valid); + if (lou->dsu_valid) + p = xdr_encode_hyper(p, lou->dsu_delta); + *p++ = cpu_to_be32(lou->olu_ioerr_flag); + return 0; +} + +/* + * struct pnfs_osd_objid { + * struct nfs4_deviceid oid_device_id; + * u64 oid_partition_id; + * u64 oid_object_id; + * }; // xdr size 32 bytes + */ +static inline __be32 * +pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id) +{ + p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data, + sizeof(object_id->oid_device_id.data)); + p = xdr_encode_hyper(p, object_id->oid_partition_id); + p = xdr_encode_hyper(p, object_id->oid_object_id); + + return p; +} + +/* + * struct pnfs_osd_ioerr { + * struct pnfs_osd_objid oer_component; + * u64 oer_comp_offset; + * u64 oer_comp_length; + * u32 oer_iswrite; + * u32 oer_errno; + * }; // xdr size 32 + 24 bytes + */ +void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr) +{ + p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component); + p = xdr_encode_hyper(p, ioerr->oer_comp_offset); + p = xdr_encode_hyper(p, ioerr->oer_comp_length); + *p++ = cpu_to_be32(ioerr->oer_iswrite); + *p = cpu_to_be32(ioerr->oer_errno); +} + +__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 32 + 24); + if (unlikely(!p)) + dprintk("%s: out of xdr space\n", __func__); + + return p; +} diff --git a/kernel/fs/nfs/pagelist.c b/kernel/fs/nfs/pagelist.c new file mode 100644 index 000000000..282b39369 --- /dev/null +++ b/kernel/fs/nfs/pagelist.c @@ -0,0 +1,1309 @@ +/* + * linux/fs/nfs/pagelist.c + * + * A set of helper functions for managing NFS read and write requests. + * The main purpose of these routines is to provide support for the + * coalescing of several requests into a single RPC call. + * + * Copyright 2000, 2001 (c) Trond Myklebust <trond.myklebust@fys.uio.no> + * + */ + +#include <linux/slab.h> +#include <linux/file.h> +#include <linux/sched.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs3.h> +#include <linux/nfs4.h> +#include <linux/nfs_page.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/export.h> + +#include "internal.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_PAGECACHE + +static struct kmem_cache *nfs_page_cachep; +static const struct rpc_call_ops nfs_pgio_common_ops; + +static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) +{ + p->npages = pagecount; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; + else { + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + if (!p->pagevec) + p->npages = 0; + } + return p->pagevec != NULL; +} + +struct nfs_pgio_mirror * +nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc) +{ + return nfs_pgio_has_mirroring(desc) ? + &desc->pg_mirrors[desc->pg_mirror_idx] : + &desc->pg_mirrors[0]; +} +EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror); + +void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + + hdr->req = nfs_list_entry(mirror->pg_list.next); + hdr->inode = desc->pg_inode; + hdr->cred = hdr->req->wb_context->cred; + hdr->io_start = req_offset(hdr->req); + hdr->good_bytes = mirror->pg_count; + hdr->dreq = desc->pg_dreq; + hdr->layout_private = desc->pg_layout_private; + hdr->release = release; + hdr->completion_ops = desc->pg_completion_ops; + if (hdr->completion_ops->init_hdr) + hdr->completion_ops->init_hdr(hdr); + + hdr->pgio_mirror_idx = desc->pg_mirror_idx; +} +EXPORT_SYMBOL_GPL(nfs_pgheader_init); + +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) +{ + spin_lock(&hdr->lock); + if (pos < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_ERROR, &hdr->flags); + clear_bit(NFS_IOHDR_EOF, &hdr->flags); + hdr->good_bytes = pos - hdr->io_start; + hdr->error = error; + } + spin_unlock(&hdr->lock); +} + +static inline struct nfs_page * +nfs_page_alloc(void) +{ + struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO); + if (p) + INIT_LIST_HEAD(&p->wb_list); + return p; +} + +static inline void +nfs_page_free(struct nfs_page *p) +{ + kmem_cache_free(nfs_page_cachep, p); +} + +static void +nfs_iocounter_inc(struct nfs_io_counter *c) +{ + atomic_inc(&c->io_count); +} + +static void +nfs_iocounter_dec(struct nfs_io_counter *c) +{ + if (atomic_dec_and_test(&c->io_count)) { + clear_bit(NFS_IO_INPROGRESS, &c->flags); + smp_mb__after_atomic(); + wake_up_bit(&c->flags, NFS_IO_INPROGRESS); + } +} + +static int +__nfs_iocounter_wait(struct nfs_io_counter *c) +{ + wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS); + DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS); + int ret = 0; + + do { + prepare_to_wait(wq, &q.wait, TASK_KILLABLE); + set_bit(NFS_IO_INPROGRESS, &c->flags); + if (atomic_read(&c->io_count) == 0) + break; + ret = nfs_wait_bit_killable(&q.key); + } while (atomic_read(&c->io_count) != 0 && !ret); + finish_wait(wq, &q.wait); + return ret; +} + +/** + * nfs_iocounter_wait - wait for i/o to complete + * @c: nfs_io_counter to use + * + * returns -ERESTARTSYS if interrupted by a fatal signal. + * Otherwise returns 0 once the io_count hits 0. + */ +int +nfs_iocounter_wait(struct nfs_io_counter *c) +{ + if (atomic_read(&c->io_count) == 0) + return 0; + return __nfs_iocounter_wait(c); +} + +/* + * nfs_page_group_lock - lock the head of the page group + * @req - request in group that is to be locked + * @nonblock - if true don't block waiting for lock + * + * this lock must be held if modifying the page group list + * + * return 0 on success, < 0 on error: -EDELAY if nonblocking or the + * result from wait_on_bit_lock + * + * NOTE: calling with nonblock=false should always have set the + * lock bit (see fs/buffer.c and other uses of wait_on_bit_lock + * with TASK_UNINTERRUPTIBLE), so there is no need to check the result. + */ +int +nfs_page_group_lock(struct nfs_page *req, bool nonblock) +{ + struct nfs_page *head = req->wb_head; + + WARN_ON_ONCE(head != head->wb_head); + + if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags)) + return 0; + + if (!nonblock) + return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, + TASK_UNINTERRUPTIBLE); + + return -EAGAIN; +} + +/* + * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it + * @req - a request in the group + * + * This is a blocking call to wait for the group lock to be cleared. + */ +void +nfs_page_group_lock_wait(struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + WARN_ON_ONCE(head != head->wb_head); + + wait_on_bit(&head->wb_flags, PG_HEADLOCK, + TASK_UNINTERRUPTIBLE); +} + +/* + * nfs_page_group_unlock - unlock the head of the page group + * @req - request in group that is to be unlocked + */ +void +nfs_page_group_unlock(struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + WARN_ON_ONCE(head != head->wb_head); + + smp_mb__before_atomic(); + clear_bit(PG_HEADLOCK, &head->wb_flags); + smp_mb__after_atomic(); + wake_up_bit(&head->wb_flags, PG_HEADLOCK); +} + +/* + * nfs_page_group_sync_on_bit_locked + * + * must be called with page group lock held + */ +static bool +nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) +{ + struct nfs_page *head = req->wb_head; + struct nfs_page *tmp; + + WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_flags)); + WARN_ON_ONCE(test_and_set_bit(bit, &req->wb_flags)); + + tmp = req->wb_this_page; + while (tmp != req) { + if (!test_bit(bit, &tmp->wb_flags)) + return false; + tmp = tmp->wb_this_page; + } + + /* true! reset all bits */ + tmp = req; + do { + clear_bit(bit, &tmp->wb_flags); + tmp = tmp->wb_this_page; + } while (tmp != req); + + return true; +} + +/* + * nfs_page_group_sync_on_bit - set bit on current request, but only + * return true if the bit is set for all requests in page group + * @req - request in page group + * @bit - PG_* bit that is used to sync page group + */ +bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit) +{ + bool ret; + + nfs_page_group_lock(req, false); + ret = nfs_page_group_sync_on_bit_locked(req, bit); + nfs_page_group_unlock(req); + + return ret; +} + +/* + * nfs_page_group_init - Initialize the page group linkage for @req + * @req - a new nfs request + * @prev - the previous request in page group, or NULL if @req is the first + * or only request in the group (the head). + */ +static inline void +nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) +{ + struct inode *inode; + WARN_ON_ONCE(prev == req); + + if (!prev) { + /* a head request */ + req->wb_head = req; + req->wb_this_page = req; + } else { + /* a subrequest */ + WARN_ON_ONCE(prev->wb_this_page != prev->wb_head); + WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags)); + req->wb_head = prev->wb_head; + req->wb_this_page = prev->wb_this_page; + prev->wb_this_page = req; + + /* All subrequests take a ref on the head request until + * nfs_page_group_destroy is called */ + kref_get(&req->wb_head->wb_kref); + + /* grab extra ref and bump the request count if head request + * has extra ref from the write/commit path to handle handoff + * between write and commit lists. */ + if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) { + inode = page_file_mapping(req->wb_page)->host; + set_bit(PG_INODE_REF, &req->wb_flags); + kref_get(&req->wb_kref); + spin_lock(&inode->i_lock); + NFS_I(inode)->nrequests++; + spin_unlock(&inode->i_lock); + } + } +} + +/* + * nfs_page_group_destroy - sync the destruction of page groups + * @req - request that no longer needs the page group + * + * releases the page group reference from each member once all + * members have called this function. + */ +static void +nfs_page_group_destroy(struct kref *kref) +{ + struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); + struct nfs_page *tmp, *next; + + /* subrequests must release the ref on the head request */ + if (req->wb_head != req) + nfs_release_request(req->wb_head); + + if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN)) + return; + + tmp = req; + do { + next = tmp->wb_this_page; + /* unlink and free */ + tmp->wb_this_page = tmp; + tmp->wb_head = tmp; + nfs_free_request(tmp); + tmp = next; + } while (tmp != req); +} + +/** + * nfs_create_request - Create an NFS read/write request. + * @ctx: open context to use + * @page: page to write + * @last: last nfs request created for this page group or NULL if head + * @offset: starting offset within the page for the write + * @count: number of bytes to read/write + * + * The page must be locked by the caller. This makes sure we never + * create two different requests for the same page. + * User should ensure it is safe to sleep in this function. + */ +struct nfs_page * +nfs_create_request(struct nfs_open_context *ctx, struct page *page, + struct nfs_page *last, unsigned int offset, + unsigned int count) +{ + struct nfs_page *req; + struct nfs_lock_context *l_ctx; + + if (test_bit(NFS_CONTEXT_BAD, &ctx->flags)) + return ERR_PTR(-EBADF); + /* try to allocate the request struct */ + req = nfs_page_alloc(); + if (req == NULL) + return ERR_PTR(-ENOMEM); + + /* get lock context early so we can deal with alloc failures */ + l_ctx = nfs_get_lock_context(ctx); + if (IS_ERR(l_ctx)) { + nfs_page_free(req); + return ERR_CAST(l_ctx); + } + req->wb_lock_context = l_ctx; + nfs_iocounter_inc(&l_ctx->io_count); + + /* Initialize the request struct. Initially, we assume a + * long write-back delay. This will be adjusted in + * update_nfs_request below if the region is not locked. */ + req->wb_page = page; + req->wb_index = page_file_index(page); + page_cache_get(page); + req->wb_offset = offset; + req->wb_pgbase = offset; + req->wb_bytes = count; + req->wb_context = get_nfs_open_context(ctx); + kref_init(&req->wb_kref); + nfs_page_group_init(req, last); + return req; +} + +/** + * nfs_unlock_request - Unlock request and wake up sleepers. + * @req: + */ +void nfs_unlock_request(struct nfs_page *req) +{ + if (!NFS_WBACK_BUSY(req)) { + printk(KERN_ERR "NFS: Invalid unlock attempted\n"); + BUG(); + } + smp_mb__before_atomic(); + clear_bit(PG_BUSY, &req->wb_flags); + smp_mb__after_atomic(); + wake_up_bit(&req->wb_flags, PG_BUSY); +} + +/** + * nfs_unlock_and_release_request - Unlock request and release the nfs_page + * @req: + */ +void nfs_unlock_and_release_request(struct nfs_page *req) +{ + nfs_unlock_request(req); + nfs_release_request(req); +} + +/* + * nfs_clear_request - Free up all resources allocated to the request + * @req: + * + * Release page and open context resources associated with a read/write + * request after it has completed. + */ +static void nfs_clear_request(struct nfs_page *req) +{ + struct page *page = req->wb_page; + struct nfs_open_context *ctx = req->wb_context; + struct nfs_lock_context *l_ctx = req->wb_lock_context; + + if (page != NULL) { + page_cache_release(page); + req->wb_page = NULL; + } + if (l_ctx != NULL) { + nfs_iocounter_dec(&l_ctx->io_count); + nfs_put_lock_context(l_ctx); + req->wb_lock_context = NULL; + } + if (ctx != NULL) { + put_nfs_open_context(ctx); + req->wb_context = NULL; + } +} + +/** + * nfs_release_request - Release the count on an NFS read/write request + * @req: request to release + * + * Note: Should never be called with the spinlock held! + */ +void nfs_free_request(struct nfs_page *req) +{ + WARN_ON_ONCE(req->wb_this_page != req); + + /* extra debug: make sure no sync bits are still set */ + WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_UNLOCKPAGE, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_UPTODATE, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_WB_END, &req->wb_flags)); + WARN_ON_ONCE(test_bit(PG_REMOVE, &req->wb_flags)); + + /* Release struct file and open context */ + nfs_clear_request(req); + nfs_page_free(req); +} + +void nfs_release_request(struct nfs_page *req) +{ + kref_put(&req->wb_kref, nfs_page_group_destroy); +} + +/** + * nfs_wait_on_request - Wait for a request to complete. + * @req: request to wait upon. + * + * Interruptible by fatal signals only. + * The user is responsible for holding a count on the request. + */ +int +nfs_wait_on_request(struct nfs_page *req) +{ + return wait_on_bit_io(&req->wb_flags, PG_BUSY, + TASK_UNINTERRUPTIBLE); +} + +/* + * nfs_generic_pg_test - determine if requests can be coalesced + * @desc: pointer to descriptor + * @prev: previous request in desc, or NULL + * @req: this request + * + * Returns zero if @req can be coalesced into @desc, otherwise it returns + * the size of the request. + */ +size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, + struct nfs_page *prev, struct nfs_page *req) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + + if (mirror->pg_count > mirror->pg_bsize) { + /* should never happen */ + WARN_ON_ONCE(1); + return 0; + } + + /* + * Limit the request size so that we can still allocate a page array + * for it without upsetting the slab allocator. + */ + if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) * + sizeof(struct page) > PAGE_SIZE) + return 0; + + return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes); +} +EXPORT_SYMBOL_GPL(nfs_generic_pg_test); + +struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops) +{ + struct nfs_pgio_header *hdr = ops->rw_alloc_header(); + + if (hdr) { + INIT_LIST_HEAD(&hdr->pages); + spin_lock_init(&hdr->lock); + hdr->rw_ops = ops; + } + return hdr; +} +EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc); + +/* + * nfs_pgio_header_free - Free a read or write header + * @hdr: The header to free + */ +void nfs_pgio_header_free(struct nfs_pgio_header *hdr) +{ + hdr->rw_ops->rw_free_header(hdr); +} +EXPORT_SYMBOL_GPL(nfs_pgio_header_free); + +/** + * nfs_pgio_data_destroy - make @hdr suitable for reuse + * + * Frees memory and releases refs from nfs_generic_pgio, so that it may + * be called again. + * + * @hdr: A header that has had nfs_generic_pgio called + */ +void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr) +{ + if (hdr->args.context) + put_nfs_open_context(hdr->args.context); + if (hdr->page_array.pagevec != hdr->page_array.page_array) + kfree(hdr->page_array.pagevec); +} +EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy); + +/** + * nfs_pgio_rpcsetup - Set up arguments for a pageio call + * @hdr: The pageio hdr + * @count: Number of bytes to read + * @offset: Initial offset + * @how: How to commit data (writes only) + * @cinfo: Commit information for the call (writes only) + */ +static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr, + unsigned int count, unsigned int offset, + int how, struct nfs_commit_info *cinfo) +{ + struct nfs_page *req = hdr->req; + + /* Set up the RPC argument and reply structs + * NB: take care not to mess about with hdr->commit et al. */ + + hdr->args.fh = NFS_FH(hdr->inode); + hdr->args.offset = req_offset(req) + offset; + /* pnfs_set_layoutcommit needs this */ + hdr->mds_offset = hdr->args.offset; + hdr->args.pgbase = req->wb_pgbase + offset; + hdr->args.pages = hdr->page_array.pagevec; + hdr->args.count = count; + hdr->args.context = get_nfs_open_context(req->wb_context); + hdr->args.lock_context = req->wb_lock_context; + hdr->args.stable = NFS_UNSTABLE; + switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) { + case 0: + break; + case FLUSH_COND_STABLE: + if (nfs_reqs_to_commit(cinfo)) + break; + default: + hdr->args.stable = NFS_FILE_SYNC; + } + + hdr->res.fattr = &hdr->fattr; + hdr->res.count = count; + hdr->res.eof = 0; + hdr->res.verf = &hdr->verf; + nfs_fattr_init(&hdr->fattr); +} + +/** + * nfs_pgio_prepare - Prepare pageio hdr to go over the wire + * @task: The current task + * @calldata: pageio header to prepare + */ +static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_pgio_header *hdr = calldata; + int err; + err = NFS_PROTO(hdr->inode)->pgio_rpc_prepare(task, hdr); + if (err) + rpc_exit(task, err); +} + +int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, + struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, + const struct rpc_call_ops *call_ops, int how, int flags) +{ + struct rpc_task *task; + struct rpc_message msg = { + .rpc_argp = &hdr->args, + .rpc_resp = &hdr->res, + .rpc_cred = cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .task = &hdr->task, + .rpc_message = &msg, + .callback_ops = call_ops, + .callback_data = hdr, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC | flags, + }; + int ret = 0; + + hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how); + + dprintk("NFS: %5u initiated pgio call " + "(req %s/%llu, %u bytes @ offset %llu)\n", + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) { + ret = PTR_ERR(task); + goto out; + } + if (how & FLUSH_SYNC) { + ret = rpc_wait_for_completion_task(task); + if (ret == 0) + ret = task->tk_status; + } + rpc_put_task(task); +out: + return ret; +} +EXPORT_SYMBOL_GPL(nfs_initiate_pgio); + +/** + * nfs_pgio_error - Clean up from a pageio error + * @desc: IO descriptor + * @hdr: pageio header + */ +static int nfs_pgio_error(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + struct nfs_pgio_mirror *mirror; + u32 midx; + + set_bit(NFS_IOHDR_REDO, &hdr->flags); + nfs_pgio_data_destroy(hdr); + hdr->completion_ops->completion(hdr); + /* TODO: Make sure it's right to clean up all mirrors here + * and not just hdr->pgio_mirror_idx */ + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + } + return -ENOMEM; +} + +/** + * nfs_pgio_release - Release pageio data + * @calldata: The pageio header to release + */ +static void nfs_pgio_release(void *calldata) +{ + struct nfs_pgio_header *hdr = calldata; + if (hdr->rw_ops->rw_release) + hdr->rw_ops->rw_release(hdr); + nfs_pgio_data_destroy(hdr); + hdr->completion_ops->completion(hdr); +} + +static void nfs_pageio_mirror_init(struct nfs_pgio_mirror *mirror, + unsigned int bsize) +{ + INIT_LIST_HEAD(&mirror->pg_list); + mirror->pg_bytes_written = 0; + mirror->pg_count = 0; + mirror->pg_bsize = bsize; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; +} + +/** + * nfs_pageio_init - initialise a page io descriptor + * @desc: pointer to descriptor + * @inode: pointer to inode + * @doio: pointer to io function + * @bsize: io block size + * @io_flags: extra parameters for the io function + */ +void nfs_pageio_init(struct nfs_pageio_descriptor *desc, + struct inode *inode, + const struct nfs_pageio_ops *pg_ops, + const struct nfs_pgio_completion_ops *compl_ops, + const struct nfs_rw_ops *rw_ops, + size_t bsize, + int io_flags) +{ + struct nfs_pgio_mirror *new; + int i; + + desc->pg_moreio = 0; + desc->pg_inode = inode; + desc->pg_ops = pg_ops; + desc->pg_completion_ops = compl_ops; + desc->pg_rw_ops = rw_ops; + desc->pg_ioflags = io_flags; + desc->pg_error = 0; + desc->pg_lseg = NULL; + desc->pg_dreq = NULL; + desc->pg_layout_private = NULL; + desc->pg_bsize = bsize; + + desc->pg_mirror_count = 1; + desc->pg_mirror_idx = 0; + + if (pg_ops->pg_get_mirror_count) { + /* until we have a request, we don't have an lseg and no + * idea how many mirrors there will be */ + new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX, + sizeof(struct nfs_pgio_mirror), GFP_KERNEL); + desc->pg_mirrors_dynamic = new; + desc->pg_mirrors = new; + + for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++) + nfs_pageio_mirror_init(&desc->pg_mirrors[i], bsize); + } else { + desc->pg_mirrors_dynamic = NULL; + desc->pg_mirrors = desc->pg_mirrors_static; + nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize); + } +} +EXPORT_SYMBOL_GPL(nfs_pageio_init); + +/** + * nfs_pgio_result - Basic pageio error handling + * @task: The task that ran + * @calldata: Pageio header to check + */ +static void nfs_pgio_result(struct rpc_task *task, void *calldata) +{ + struct nfs_pgio_header *hdr = calldata; + struct inode *inode = hdr->inode; + + dprintk("NFS: %s: %5u, (status %d)\n", __func__, + task->tk_pid, task->tk_status); + + if (hdr->rw_ops->rw_done(task, hdr, inode) != 0) + return; + if (task->tk_status < 0) + nfs_set_pgio_error(hdr, task->tk_status, hdr->args.offset); + else + hdr->rw_ops->rw_result(task, hdr); +} + +/* + * Create an RPC task for the given read or write request and kick it. + * The page must have been locked by the caller. + * + * It may happen that the page we're passed is not marked dirty. + * This is the case if nfs_updatepage detects a conflicting request + * that has been written but not committed. + */ +int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + struct nfs_page *req; + struct page **pages, + *last_page; + struct list_head *head = &mirror->pg_list; + struct nfs_commit_info cinfo; + unsigned int pagecount, pageused; + + pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); + if (!nfs_pgarray_set(&hdr->page_array, pagecount)) + return nfs_pgio_error(desc, hdr); + + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); + pages = hdr->page_array.pagevec; + last_page = NULL; + pageused = 0; + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); + + if (!last_page || last_page != req->wb_page) { + pageused++; + if (pageused > pagecount) + break; + *pages++ = last_page = req->wb_page; + } + } + if (WARN_ON_ONCE(pageused != pagecount)) + return nfs_pgio_error(desc, hdr); + + if ((desc->pg_ioflags & FLUSH_COND_STABLE) && + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) + desc->pg_ioflags &= ~FLUSH_COND_STABLE; + + /* Set up the argument struct */ + nfs_pgio_rpcsetup(hdr, mirror->pg_count, 0, desc->pg_ioflags, &cinfo); + desc->pg_rpc_callops = &nfs_pgio_common_ops; + return 0; +} +EXPORT_SYMBOL_GPL(nfs_generic_pgio); + +static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) +{ + struct nfs_pgio_mirror *mirror; + struct nfs_pgio_header *hdr; + int ret; + + mirror = nfs_pgio_current_mirror(desc); + + hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); + if (!hdr) { + /* TODO: make sure this is right with mirroring - or + * should it back out all mirrors? */ + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + return -ENOMEM; + } + nfs_pgheader_init(desc, hdr, nfs_pgio_header_free); + ret = nfs_generic_pgio(desc, hdr); + if (ret == 0) + ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode), + hdr, + hdr->cred, + NFS_PROTO(hdr->inode), + desc->pg_rpc_callops, + desc->pg_ioflags, 0); + return ret; +} + +/* + * nfs_pageio_setup_mirroring - determine if mirroring is to be used + * by calling the pg_get_mirror_count op + */ +static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + int mirror_count = 1; + + if (!pgio->pg_ops->pg_get_mirror_count) + return 0; + + mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + + if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) + return -EINVAL; + + if (WARN_ON_ONCE(!pgio->pg_mirrors_dynamic)) + return -EINVAL; + + pgio->pg_mirror_count = mirror_count; + + return 0; +} + +/* + * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1) + */ +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio) +{ + pgio->pg_mirror_count = 1; + pgio->pg_mirror_idx = 0; +} + +static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio) +{ + pgio->pg_mirror_count = 1; + pgio->pg_mirror_idx = 0; + pgio->pg_mirrors = pgio->pg_mirrors_static; + kfree(pgio->pg_mirrors_dynamic); + pgio->pg_mirrors_dynamic = NULL; +} + +static bool nfs_match_open_context(const struct nfs_open_context *ctx1, + const struct nfs_open_context *ctx2) +{ + return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; +} + +static bool nfs_match_lock_context(const struct nfs_lock_context *l1, + const struct nfs_lock_context *l2) +{ + return l1->lockowner.l_owner == l2->lockowner.l_owner + && l1->lockowner.l_pid == l2->lockowner.l_pid; +} + +/** + * nfs_can_coalesce_requests - test two requests for compatibility + * @prev: pointer to nfs_page + * @req: pointer to nfs_page + * + * The nfs_page structures 'prev' and 'req' are compared to ensure that the + * page data area they describe is contiguous, and that their RPC + * credentials, NFSv4 open state, and lockowners are the same. + * + * Return 'true' if this is the case, else return 'false'. + */ +static bool nfs_can_coalesce_requests(struct nfs_page *prev, + struct nfs_page *req, + struct nfs_pageio_descriptor *pgio) +{ + size_t size; + struct file_lock_context *flctx; + + if (prev) { + if (!nfs_match_open_context(req->wb_context, prev->wb_context)) + return false; + flctx = d_inode(req->wb_context->dentry)->i_flctx; + if (flctx != NULL && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock)) && + !nfs_match_lock_context(req->wb_lock_context, + prev->wb_lock_context)) + return false; + if (req_offset(req) != req_offset(prev) + prev->wb_bytes) + return false; + if (req->wb_page == prev->wb_page) { + if (req->wb_pgbase != prev->wb_pgbase + prev->wb_bytes) + return false; + } else { + if (req->wb_pgbase != 0 || + prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE) + return false; + } + } + size = pgio->pg_ops->pg_test(pgio, prev, req); + WARN_ON_ONCE(size > req->wb_bytes); + if (size && size < req->wb_bytes) + req->wb_bytes = size; + return size > 0; +} + +/** + * nfs_pageio_do_add_request - Attempt to coalesce a request into a page list. + * @desc: destination io descriptor + * @req: request + * + * Returns true if the request 'req' was successfully coalesced into the + * existing list of pages 'desc'. + */ +static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + struct nfs_page *prev = NULL; + + if (mirror->pg_count != 0) { + prev = nfs_list_entry(mirror->pg_list.prev); + } else { + if (desc->pg_ops->pg_init) + desc->pg_ops->pg_init(desc, req); + mirror->pg_base = req->wb_pgbase; + } + if (!nfs_can_coalesce_requests(prev, req, desc)) + return 0; + nfs_list_remove_request(req); + nfs_list_add_request(req, &mirror->pg_list); + mirror->pg_count += req->wb_bytes; + return 1; +} + +/* + * Helper for nfs_pageio_add_request and nfs_pageio_complete + */ +static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + + if (!list_empty(&mirror->pg_list)) { + int error = desc->pg_ops->pg_doio(desc); + if (error < 0) + desc->pg_error = error; + else + mirror->pg_bytes_written += mirror->pg_count; + } + if (list_empty(&mirror->pg_list)) { + mirror->pg_count = 0; + mirror->pg_base = 0; + } +} + +/** + * nfs_pageio_add_request - Attempt to coalesce a request into a page list. + * @desc: destination io descriptor + * @req: request + * + * This may split a request into subrequests which are all part of the + * same page group. + * + * Returns true if the request 'req' was successfully coalesced into the + * existing list of pages 'desc'. + */ +static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + struct nfs_page *subreq; + unsigned int bytes_left = 0; + unsigned int offset, pgbase; + + nfs_page_group_lock(req, false); + + subreq = req; + bytes_left = subreq->wb_bytes; + offset = subreq->wb_offset; + pgbase = subreq->wb_pgbase; + + do { + if (!nfs_pageio_do_add_request(desc, subreq)) { + /* make sure pg_test call(s) did nothing */ + WARN_ON_ONCE(subreq->wb_bytes != bytes_left); + WARN_ON_ONCE(subreq->wb_offset != offset); + WARN_ON_ONCE(subreq->wb_pgbase != pgbase); + + nfs_page_group_unlock(req); + desc->pg_moreio = 1; + nfs_pageio_doio(desc); + if (desc->pg_error < 0) + return 0; + if (mirror->pg_recoalesce) + return 0; + /* retry add_request for this subreq */ + nfs_page_group_lock(req, false); + continue; + } + + /* check for buggy pg_test call(s) */ + WARN_ON_ONCE(subreq->wb_bytes + subreq->wb_pgbase > PAGE_SIZE); + WARN_ON_ONCE(subreq->wb_bytes > bytes_left); + WARN_ON_ONCE(subreq->wb_bytes == 0); + + bytes_left -= subreq->wb_bytes; + offset += subreq->wb_bytes; + pgbase += subreq->wb_bytes; + + if (bytes_left) { + subreq = nfs_create_request(req->wb_context, + req->wb_page, + subreq, pgbase, bytes_left); + if (IS_ERR(subreq)) + goto err_ptr; + nfs_lock_request(subreq); + subreq->wb_offset = offset; + subreq->wb_index = req->wb_index; + } + } while (bytes_left > 0); + + nfs_page_group_unlock(req); + return 1; +err_ptr: + desc->pg_error = PTR_ERR(subreq); + nfs_page_group_unlock(req); + return 0; +} + +static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + LIST_HEAD(head); + + do { + list_splice_init(&mirror->pg_list, &head); + mirror->pg_bytes_written -= mirror->pg_count; + mirror->pg_count = 0; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; + + desc->pg_moreio = 0; + + while (!list_empty(&head)) { + struct nfs_page *req; + + req = list_first_entry(&head, struct nfs_page, wb_list); + nfs_list_remove_request(req); + if (__nfs_pageio_add_request(desc, req)) + continue; + if (desc->pg_error < 0) + return 0; + break; + } + } while (mirror->pg_recoalesce); + return 1; +} + +static int nfs_pageio_add_request_mirror(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + int ret; + + do { + ret = __nfs_pageio_add_request(desc, req); + if (ret) + break; + if (desc->pg_error < 0) + break; + ret = nfs_do_recoalesce(desc); + } while (ret); + + return ret; +} + +int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + u32 midx; + unsigned int pgbase, offset, bytes; + struct nfs_page *dupreq, *lastreq; + + pgbase = req->wb_pgbase; + offset = req->wb_offset; + bytes = req->wb_bytes; + + nfs_pageio_setup_mirroring(desc, req); + + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + if (midx) { + nfs_page_group_lock(req, false); + + /* find the last request */ + for (lastreq = req->wb_head; + lastreq->wb_this_page != req->wb_head; + lastreq = lastreq->wb_this_page) + ; + + dupreq = nfs_create_request(req->wb_context, + req->wb_page, lastreq, pgbase, bytes); + + if (IS_ERR(dupreq)) { + nfs_page_group_unlock(req); + return 0; + } + + nfs_lock_request(dupreq); + nfs_page_group_unlock(req); + dupreq->wb_offset = offset; + dupreq->wb_index = req->wb_index; + } else + dupreq = req; + + if (nfs_pgio_has_mirroring(desc)) + desc->pg_mirror_idx = midx; + if (!nfs_pageio_add_request_mirror(desc, dupreq)) + return 0; + } + + return 1; +} + +/* + * nfs_pageio_complete_mirror - Complete I/O on the current mirror of an + * nfs_pageio_descriptor + * @desc: pointer to io descriptor + */ +static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, + u32 mirror_idx) +{ + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; + u32 restore_idx = desc->pg_mirror_idx; + + if (nfs_pgio_has_mirroring(desc)) + desc->pg_mirror_idx = mirror_idx; + for (;;) { + nfs_pageio_doio(desc); + if (!mirror->pg_recoalesce) + break; + if (!nfs_do_recoalesce(desc)) + break; + } + desc->pg_mirror_idx = restore_idx; +} + +/* + * nfs_pageio_resend - Transfer requests to new descriptor and resend + * @hdr - the pgio header to move request from + * @desc - the pageio descriptor to add requests to + * + * Try to move each request (nfs_page) from @hdr to @desc then attempt + * to send them. + * + * Returns 0 on success and < 0 on error. + */ +int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + LIST_HEAD(failed); + + desc->pg_dreq = hdr->dreq; + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + nfs_list_remove_request(req); + if (!nfs_pageio_add_request(desc, req)) + nfs_list_add_request(req, &failed); + } + nfs_pageio_complete(desc); + if (!list_empty(&failed)) { + list_move(&failed, &hdr->pages); + return -EIO; + } + return 0; +} +EXPORT_SYMBOL_GPL(nfs_pageio_resend); + +/** + * nfs_pageio_complete - Complete I/O then cleanup an nfs_pageio_descriptor + * @desc: pointer to io descriptor + */ +void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) +{ + u32 midx; + + for (midx = 0; midx < desc->pg_mirror_count; midx++) + nfs_pageio_complete_mirror(desc, midx); + + if (desc->pg_ops->pg_cleanup) + desc->pg_ops->pg_cleanup(desc); + nfs_pageio_cleanup_mirroring(desc); +} + +/** + * nfs_pageio_cond_complete - Conditional I/O completion + * @desc: pointer to io descriptor + * @index: page index + * + * It is important to ensure that processes don't try to take locks + * on non-contiguous ranges of pages as that might deadlock. This + * function should be called before attempting to wait on a locked + * nfs_page. It will complete the I/O if the page index 'index' + * is not contiguous with the existing list of pages in 'desc'. + */ +void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) +{ + struct nfs_pgio_mirror *mirror; + struct nfs_page *prev; + u32 midx; + + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + if (!list_empty(&mirror->pg_list)) { + prev = nfs_list_entry(mirror->pg_list.prev); + if (index != prev->wb_index + 1) + nfs_pageio_complete_mirror(desc, midx); + } + } +} + +int __init nfs_init_nfspagecache(void) +{ + nfs_page_cachep = kmem_cache_create("nfs_page", + sizeof(struct nfs_page), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (nfs_page_cachep == NULL) + return -ENOMEM; + + return 0; +} + +void nfs_destroy_nfspagecache(void) +{ + kmem_cache_destroy(nfs_page_cachep); +} + +static const struct rpc_call_ops nfs_pgio_common_ops = { + .rpc_call_prepare = nfs_pgio_prepare, + .rpc_call_done = nfs_pgio_result, + .rpc_release = nfs_pgio_release, +}; + +const struct nfs_pageio_ops nfs_pgio_rw_ops = { + .pg_test = nfs_generic_pg_test, + .pg_doio = nfs_generic_pg_pgios, +}; diff --git a/kernel/fs/nfs/pnfs.c b/kernel/fs/nfs/pnfs.c new file mode 100644 index 000000000..230606243 --- /dev/null +++ b/kernel/fs/nfs/pnfs.c @@ -0,0 +1,2249 @@ +/* + * pNFS functions to call and manage layout drivers. + * + * Copyright (c) 2002 [year of first publication] + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/module.h> +#include "internal.h" +#include "pnfs.h" +#include "iostat.h" +#include "nfs4trace.h" +#include "delegation.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS +#define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ) + +/* Locking: + * + * pnfs_spinlock: + * protects pnfs_modules_tbl. + */ +static DEFINE_SPINLOCK(pnfs_spinlock); + +/* + * pnfs_modules_tbl holds all pnfs modules + */ +static LIST_HEAD(pnfs_modules_tbl); + +static int +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, + enum pnfs_iomode iomode, bool sync); + +/* Return the registered pnfs layout driver module matching given id */ +static struct pnfs_layoutdriver_type * +find_pnfs_driver_locked(u32 id) +{ + struct pnfs_layoutdriver_type *local; + + list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid) + if (local->id == id) + goto out; + local = NULL; +out: + dprintk("%s: Searching for id %u, found %p\n", __func__, id, local); + return local; +} + +static struct pnfs_layoutdriver_type * +find_pnfs_driver(u32 id) +{ + struct pnfs_layoutdriver_type *local; + + spin_lock(&pnfs_spinlock); + local = find_pnfs_driver_locked(id); + if (local != NULL && !try_module_get(local->owner)) { + dprintk("%s: Could not grab reference on module\n", __func__); + local = NULL; + } + spin_unlock(&pnfs_spinlock); + return local; +} + +void +unset_pnfs_layoutdriver(struct nfs_server *nfss) +{ + if (nfss->pnfs_curr_ld) { + if (nfss->pnfs_curr_ld->clear_layoutdriver) + nfss->pnfs_curr_ld->clear_layoutdriver(nfss); + /* Decrement the MDS count. Purge the deviceid cache if zero */ + if (atomic_dec_and_test(&nfss->nfs_client->cl_mds_count)) + nfs4_deviceid_purge_client(nfss->nfs_client); + module_put(nfss->pnfs_curr_ld->owner); + } + nfss->pnfs_curr_ld = NULL; +} + +/* + * Try to set the server's pnfs module to the pnfs layout type specified by id. + * Currently only one pNFS layout driver per filesystem is supported. + * + * @id layout type. Zero (illegal layout type) indicates pNFS not in use. + */ +void +set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, + u32 id) +{ + struct pnfs_layoutdriver_type *ld_type = NULL; + + if (id == 0) + goto out_no_driver; + if (!(server->nfs_client->cl_exchange_flags & + (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) { + printk(KERN_ERR "NFS: %s: id %u cl_exchange_flags 0x%x\n", + __func__, id, server->nfs_client->cl_exchange_flags); + goto out_no_driver; + } + ld_type = find_pnfs_driver(id); + if (!ld_type) { + request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id); + ld_type = find_pnfs_driver(id); + if (!ld_type) { + dprintk("%s: No pNFS module found for %u.\n", + __func__, id); + goto out_no_driver; + } + } + server->pnfs_curr_ld = ld_type; + if (ld_type->set_layoutdriver + && ld_type->set_layoutdriver(server, mntfh)) { + printk(KERN_ERR "NFS: %s: Error initializing pNFS layout " + "driver %u.\n", __func__, id); + module_put(ld_type->owner); + goto out_no_driver; + } + /* Bump the MDS count */ + atomic_inc(&server->nfs_client->cl_mds_count); + + dprintk("%s: pNFS module for %u set\n", __func__, id); + return; + +out_no_driver: + dprintk("%s: Using NFSv4 I/O\n", __func__); + server->pnfs_curr_ld = NULL; +} + +int +pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type) +{ + int status = -EINVAL; + struct pnfs_layoutdriver_type *tmp; + + if (ld_type->id == 0) { + printk(KERN_ERR "NFS: %s id 0 is reserved\n", __func__); + return status; + } + if (!ld_type->alloc_lseg || !ld_type->free_lseg) { + printk(KERN_ERR "NFS: %s Layout driver must provide " + "alloc_lseg and free_lseg.\n", __func__); + return status; + } + + spin_lock(&pnfs_spinlock); + tmp = find_pnfs_driver_locked(ld_type->id); + if (!tmp) { + list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl); + status = 0; + dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id, + ld_type->name); + } else { + printk(KERN_ERR "NFS: %s Module with id %d already loaded!\n", + __func__, ld_type->id); + } + spin_unlock(&pnfs_spinlock); + + return status; +} +EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver); + +void +pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type) +{ + dprintk("%s Deregistering id:%u\n", __func__, ld_type->id); + spin_lock(&pnfs_spinlock); + list_del(&ld_type->pnfs_tblid); + spin_unlock(&pnfs_spinlock); +} +EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver); + +/* + * pNFS client layout cache + */ + +/* Need to hold i_lock if caller does not already hold reference */ +void +pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo) +{ + atomic_inc(&lo->plh_refcount); +} + +static struct pnfs_layout_hdr * +pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; + return ld->alloc_layout_hdr(ino, gfp_flags); +} + +static void +pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct nfs_server *server = NFS_SERVER(lo->plh_inode); + struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; + + if (!list_empty(&lo->plh_layouts)) { + struct nfs_client *clp = server->nfs_client; + + spin_lock(&clp->cl_lock); + list_del_init(&lo->plh_layouts); + spin_unlock(&clp->cl_lock); + } + put_rpccred(lo->plh_lc_cred); + return ld->free_layout_hdr(lo); +} + +static void +pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct nfs_inode *nfsi = NFS_I(lo->plh_inode); + dprintk("%s: freeing layout cache %p\n", __func__, lo); + nfsi->layout = NULL; + /* Reset MDS Threshold I/O counters */ + nfsi->write_io = 0; + nfsi->read_io = 0; +} + +void +pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct inode *inode = lo->plh_inode; + + if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { + if (!list_empty(&lo->plh_segs)) + WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); + pnfs_detach_layout_hdr(lo); + spin_unlock(&inode->i_lock); + pnfs_free_layout_hdr(lo); + } +} + +static int +pnfs_iomode_to_fail_bit(u32 iomode) +{ + return iomode == IOMODE_RW ? + NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED; +} + +static void +pnfs_layout_set_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit) +{ + lo->plh_retry_timestamp = jiffies; + if (!test_and_set_bit(fail_bit, &lo->plh_flags)) + atomic_inc(&lo->plh_refcount); +} + +static void +pnfs_layout_clear_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit) +{ + if (test_and_clear_bit(fail_bit, &lo->plh_flags)) + atomic_dec(&lo->plh_refcount); +} + +static void +pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode) +{ + struct inode *inode = lo->plh_inode; + struct pnfs_layout_range range = { + .iomode = iomode, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + LIST_HEAD(head); + + spin_lock(&inode->i_lock); + pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode)); + pnfs_mark_matching_lsegs_invalid(lo, &head, &range); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&head); + dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__, + iomode == IOMODE_RW ? "RW" : "READ"); +} + +static bool +pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode) +{ + unsigned long start, end; + int fail_bit = pnfs_iomode_to_fail_bit(iomode); + + if (test_bit(fail_bit, &lo->plh_flags) == 0) + return false; + end = jiffies; + start = end - PNFS_LAYOUTGET_RETRY_TIMEOUT; + if (!time_in_range(lo->plh_retry_timestamp, start, end)) { + /* It is time to retry the failed layoutgets */ + pnfs_layout_clear_fail_bit(lo, fail_bit); + return false; + } + return true; +} + +static void +init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg) +{ + INIT_LIST_HEAD(&lseg->pls_list); + INIT_LIST_HEAD(&lseg->pls_lc_list); + atomic_set(&lseg->pls_refcount, 1); + smp_mb(); + set_bit(NFS_LSEG_VALID, &lseg->pls_flags); + lseg->pls_layout = lo; +} + +static void pnfs_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct inode *ino = lseg->pls_layout->plh_inode; + + NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); +} + +static void +pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg) +{ + struct inode *inode = lo->plh_inode; + + WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); + list_del_init(&lseg->pls_list); + /* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */ + atomic_dec(&lo->plh_refcount); + if (list_empty(&lo->plh_segs)) + clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); + rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); +} + +/* Return true if layoutreturn is needed */ +static bool +pnfs_layout_need_return(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_segment *s; + + if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + return false; + + list_for_each_entry(s, &lo->plh_segs, pls_list) + if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) + return false; + + return true; +} + +static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, + struct pnfs_layout_hdr *lo, struct inode *inode) +{ + lo = lseg->pls_layout; + inode = lo->plh_inode; + + spin_lock(&inode->i_lock); + if (pnfs_layout_need_return(lo, lseg)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode; + + stateid = lo->plh_stateid; + iomode = lo->plh_return_iomode; + /* decreased in pnfs_send_layoutreturn() */ + lo->plh_block_lgets++; + lo->plh_return_iomode = 0; + spin_unlock(&inode->i_lock); + pnfs_get_layout_hdr(lo); + + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, stateid, iomode, false); + } else + spin_unlock(&inode->i_lock); +} + +void +pnfs_put_lseg(struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_hdr *lo; + struct inode *inode; + + if (!lseg) + return; + + dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg, + atomic_read(&lseg->pls_refcount), + test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); + + /* Handle the case where refcount != 1 */ + if (atomic_add_unless(&lseg->pls_refcount, -1, 1)) + return; + + lo = lseg->pls_layout; + inode = lo->plh_inode; + /* Do we need a layoutreturn? */ + if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); + + if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { + pnfs_get_layout_hdr(lo); + pnfs_layout_remove_lseg(lo, lseg); + spin_unlock(&inode->i_lock); + pnfs_free_lseg(lseg); + pnfs_put_layout_hdr(lo); + } +} +EXPORT_SYMBOL_GPL(pnfs_put_lseg); + +static void pnfs_free_lseg_async_work(struct work_struct *work) +{ + struct pnfs_layout_segment *lseg; + struct pnfs_layout_hdr *lo; + + lseg = container_of(work, struct pnfs_layout_segment, pls_work); + lo = lseg->pls_layout; + + pnfs_free_lseg(lseg); + pnfs_put_layout_hdr(lo); +} + +static void pnfs_free_lseg_async(struct pnfs_layout_segment *lseg) +{ + INIT_WORK(&lseg->pls_work, pnfs_free_lseg_async_work); + schedule_work(&lseg->pls_work); +} + +void +pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg) +{ + if (!lseg) + return; + + assert_spin_locked(&lseg->pls_layout->plh_inode->i_lock); + + dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg, + atomic_read(&lseg->pls_refcount), + test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); + if (atomic_dec_and_test(&lseg->pls_refcount)) { + struct pnfs_layout_hdr *lo = lseg->pls_layout; + pnfs_get_layout_hdr(lo); + pnfs_layout_remove_lseg(lo, lseg); + pnfs_free_lseg_async(lseg); + } +} +EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked); + +static u64 +end_offset(u64 start, u64 len) +{ + u64 end; + + end = start + len; + return end >= start ? end : NFS4_MAX_UINT64; +} + +/* + * is l2 fully contained in l1? + * start1 end1 + * [----------------------------------) + * start2 end2 + * [----------------) + */ +static bool +pnfs_lseg_range_contained(const struct pnfs_layout_range *l1, + const struct pnfs_layout_range *l2) +{ + u64 start1 = l1->offset; + u64 end1 = end_offset(start1, l1->length); + u64 start2 = l2->offset; + u64 end2 = end_offset(start2, l2->length); + + return (start1 <= start2) && (end1 >= end2); +} + +/* + * is l1 and l2 intersecting? + * start1 end1 + * [----------------------------------) + * start2 end2 + * [----------------) + */ +static bool +pnfs_lseg_range_intersecting(const struct pnfs_layout_range *l1, + const struct pnfs_layout_range *l2) +{ + u64 start1 = l1->offset; + u64 end1 = end_offset(start1, l1->length); + u64 start2 = l2->offset; + u64 end2 = end_offset(start2, l2->length); + + return (end1 == NFS4_MAX_UINT64 || end1 > start2) && + (end2 == NFS4_MAX_UINT64 || end2 > start1); +} + +static bool +should_free_lseg(const struct pnfs_layout_range *lseg_range, + const struct pnfs_layout_range *recall_range) +{ + return (recall_range->iomode == IOMODE_ANY || + lseg_range->iomode == recall_range->iomode) && + pnfs_lseg_range_intersecting(lseg_range, recall_range); +} + +static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg, + struct list_head *tmp_list) +{ + if (!atomic_dec_and_test(&lseg->pls_refcount)) + return false; + pnfs_layout_remove_lseg(lseg->pls_layout, lseg); + list_add(&lseg->pls_list, tmp_list); + return true; +} + +/* Returns 1 if lseg is removed from list, 0 otherwise */ +static int mark_lseg_invalid(struct pnfs_layout_segment *lseg, + struct list_head *tmp_list) +{ + int rv = 0; + + if (test_and_clear_bit(NFS_LSEG_VALID, &lseg->pls_flags)) { + /* Remove the reference keeping the lseg in the + * list. It will now be removed when all + * outstanding io is finished. + */ + dprintk("%s: lseg %p ref %d\n", __func__, lseg, + atomic_read(&lseg->pls_refcount)); + if (pnfs_lseg_dec_and_remove_zero(lseg, tmp_list)) + rv = 1; + } + return rv; +} + +/* Returns count of number of matching invalid lsegs remaining in list + * after call. + */ +int +pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, + struct list_head *tmp_list, + struct pnfs_layout_range *recall_range) +{ + struct pnfs_layout_segment *lseg, *next; + int invalid = 0, removed = 0; + + dprintk("%s:Begin lo %p\n", __func__, lo); + + if (list_empty(&lo->plh_segs)) + return 0; + list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) + if (!recall_range || + should_free_lseg(&lseg->pls_range, recall_range)) { + dprintk("%s: freeing lseg %p iomode %d " + "offset %llu length %llu\n", __func__, + lseg, lseg->pls_range.iomode, lseg->pls_range.offset, + lseg->pls_range.length); + invalid++; + removed += mark_lseg_invalid(lseg, tmp_list); + } + dprintk("%s:Return %i\n", __func__, invalid - removed); + return invalid - removed; +} + +/* note free_me must contain lsegs from a single layout_hdr */ +void +pnfs_free_lseg_list(struct list_head *free_me) +{ + struct pnfs_layout_segment *lseg, *tmp; + + if (list_empty(free_me)) + return; + + list_for_each_entry_safe(lseg, tmp, free_me, pls_list) { + list_del(&lseg->pls_list); + pnfs_free_lseg(lseg); + } +} + +void +pnfs_destroy_layout(struct nfs_inode *nfsi) +{ + struct pnfs_layout_hdr *lo; + LIST_HEAD(tmp_list); + + spin_lock(&nfsi->vfs_inode.i_lock); + lo = nfsi->layout; + if (lo) { + lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ + pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); + pnfs_get_layout_hdr(lo); + pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); + pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); + pnfs_clear_retry_layoutget(lo); + spin_unlock(&nfsi->vfs_inode.i_lock); + pnfs_free_lseg_list(&tmp_list); + pnfs_put_layout_hdr(lo); + } else + spin_unlock(&nfsi->vfs_inode.i_lock); +} +EXPORT_SYMBOL_GPL(pnfs_destroy_layout); + +static bool +pnfs_layout_add_bulk_destroy_list(struct inode *inode, + struct list_head *layout_list) +{ + struct pnfs_layout_hdr *lo; + bool ret = false; + + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (lo != NULL && list_empty(&lo->plh_bulk_destroy)) { + pnfs_get_layout_hdr(lo); + list_add(&lo->plh_bulk_destroy, layout_list); + ret = true; + } + spin_unlock(&inode->i_lock); + return ret; +} + +/* Caller must hold rcu_read_lock and clp->cl_lock */ +static int +pnfs_layout_bulk_destroy_byserver_locked(struct nfs_client *clp, + struct nfs_server *server, + struct list_head *layout_list) +{ + struct pnfs_layout_hdr *lo, *next; + struct inode *inode; + + list_for_each_entry_safe(lo, next, &server->layouts, plh_layouts) { + inode = igrab(lo->plh_inode); + if (inode == NULL) + continue; + list_del_init(&lo->plh_layouts); + if (pnfs_layout_add_bulk_destroy_list(inode, layout_list)) + continue; + rcu_read_unlock(); + spin_unlock(&clp->cl_lock); + iput(inode); + spin_lock(&clp->cl_lock); + rcu_read_lock(); + return -EAGAIN; + } + return 0; +} + +static int +pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, + bool is_bulk_recall) +{ + struct pnfs_layout_hdr *lo; + struct inode *inode; + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + LIST_HEAD(lseg_list); + int ret = 0; + + while (!list_empty(layout_list)) { + lo = list_entry(layout_list->next, struct pnfs_layout_hdr, + plh_bulk_destroy); + dprintk("%s freeing layout for inode %lu\n", __func__, + lo->plh_inode->i_ino); + inode = lo->plh_inode; + + pnfs_layoutcommit_inode(inode, false); + + spin_lock(&inode->i_lock); + list_del_init(&lo->plh_bulk_destroy); + lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ + if (is_bulk_recall) + set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); + if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range)) + ret = -EAGAIN; + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&lseg_list); + pnfs_put_layout_hdr(lo); + iput(inode); + } + return ret; +} + +int +pnfs_destroy_layouts_byfsid(struct nfs_client *clp, + struct nfs_fsid *fsid, + bool is_recall) +{ + struct nfs_server *server; + LIST_HEAD(layout_list); + + spin_lock(&clp->cl_lock); + rcu_read_lock(); +restart: + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + if (memcmp(&server->fsid, fsid, sizeof(*fsid)) != 0) + continue; + if (pnfs_layout_bulk_destroy_byserver_locked(clp, + server, + &layout_list) != 0) + goto restart; + } + rcu_read_unlock(); + spin_unlock(&clp->cl_lock); + + if (list_empty(&layout_list)) + return 0; + return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall); +} + +int +pnfs_destroy_layouts_byclid(struct nfs_client *clp, + bool is_recall) +{ + struct nfs_server *server; + LIST_HEAD(layout_list); + + spin_lock(&clp->cl_lock); + rcu_read_lock(); +restart: + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + if (pnfs_layout_bulk_destroy_byserver_locked(clp, + server, + &layout_list) != 0) + goto restart; + } + rcu_read_unlock(); + spin_unlock(&clp->cl_lock); + + if (list_empty(&layout_list)) + return 0; + return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall); +} + +/* + * Called by the state manger to remove all layouts established under an + * expired lease. + */ +void +pnfs_destroy_all_layouts(struct nfs_client *clp) +{ + nfs4_deviceid_mark_client_invalid(clp); + nfs4_deviceid_purge_client(clp); + + pnfs_destroy_layouts_byclid(clp, false); +} + +/* + * Compare 2 layout stateid sequence ids, to see which is newer, + * taking into account wraparound issues. + */ +static bool pnfs_seqid_is_newer(u32 s1, u32 s2) +{ + return (s32)(s1 - s2) > 0; +} + +/* update lo->plh_stateid with new if is more recent */ +void +pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new, + bool update_barrier) +{ + u32 oldseq, newseq, new_barrier; + int empty = list_empty(&lo->plh_segs); + + oldseq = be32_to_cpu(lo->plh_stateid.seqid); + newseq = be32_to_cpu(new->seqid); + if (empty || pnfs_seqid_is_newer(newseq, oldseq)) { + nfs4_stateid_copy(&lo->plh_stateid, new); + if (update_barrier) { + new_barrier = be32_to_cpu(new->seqid); + } else { + /* Because of wraparound, we want to keep the barrier + * "close" to the current seqids. + */ + new_barrier = newseq - atomic_read(&lo->plh_outstanding); + } + if (empty || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier)) + lo->plh_barrier = new_barrier; + } +} + +static bool +pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo, + const nfs4_stateid *stateid) +{ + u32 seqid = be32_to_cpu(stateid->seqid); + + return !pnfs_seqid_is_newer(seqid, lo->plh_barrier); +} + +static bool +pnfs_layout_returning(const struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range) +{ + return test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) && + (lo->plh_return_iomode == IOMODE_ANY || + lo->plh_return_iomode == range->iomode); +} + +/* lget is set to 1 if called from inside send_layoutget call chain */ +static bool +pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range, int lget) +{ + return lo->plh_block_lgets || + test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || + (list_empty(&lo->plh_segs) && + (atomic_read(&lo->plh_outstanding) > lget)) || + pnfs_layout_returning(lo, range); +} + +int +pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range, + struct nfs4_state *open_state) +{ + int status = 0; + + dprintk("--> %s\n", __func__); + spin_lock(&lo->plh_inode->i_lock); + if (pnfs_layoutgets_blocked(lo, range, 1)) { + status = -EAGAIN; + } else if (!nfs4_valid_open_stateid(open_state)) { + status = -EBADF; + } else if (list_empty(&lo->plh_segs) || + test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) { + int seq; + + do { + seq = read_seqbegin(&open_state->seqlock); + nfs4_stateid_copy(dst, &open_state->stateid); + } while (read_seqretry(&open_state->seqlock, seq)); + } else + nfs4_stateid_copy(dst, &lo->plh_stateid); + spin_unlock(&lo->plh_inode->i_lock); + dprintk("<-- %s\n", __func__); + return status; +} + +/* +* Get layout from server. +* for now, assume that whole file layouts are requested. +* arg->offset: 0 +* arg->length: all ones +*/ +static struct pnfs_layout_segment * +send_layoutget(struct pnfs_layout_hdr *lo, + struct nfs_open_context *ctx, + struct pnfs_layout_range *range, + gfp_t gfp_flags) +{ + struct inode *ino = lo->plh_inode; + struct nfs_server *server = NFS_SERVER(ino); + struct nfs4_layoutget *lgp; + struct pnfs_layout_segment *lseg; + + dprintk("--> %s\n", __func__); + + lgp = kzalloc(sizeof(*lgp), gfp_flags); + if (lgp == NULL) + return NULL; + + lgp->args.minlength = PAGE_CACHE_SIZE; + if (lgp->args.minlength > range->length) + lgp->args.minlength = range->length; + lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; + lgp->args.range = *range; + lgp->args.type = server->pnfs_curr_ld->id; + lgp->args.inode = ino; + lgp->args.ctx = get_nfs_open_context(ctx); + lgp->gfp_flags = gfp_flags; + lgp->cred = lo->plh_lc_cred; + + /* Synchronously retrieve layout information from server and + * store in lseg. + */ + lseg = nfs4_proc_layoutget(lgp, gfp_flags); + if (IS_ERR(lseg)) { + switch (PTR_ERR(lseg)) { + case -ENOMEM: + case -ERESTARTSYS: + break; + default: + /* remember that LAYOUTGET failed and suspend trying */ + pnfs_layout_io_set_failed(lo, range->iomode); + } + return NULL; + } else + pnfs_layout_clear_fail_bit(lo, + pnfs_iomode_to_fail_bit(range->iomode)); + + return lseg; +} + +static void pnfs_clear_layoutcommit(struct inode *inode, + struct list_head *head) +{ + struct nfs_inode *nfsi = NFS_I(inode); + struct pnfs_layout_segment *lseg, *tmp; + + if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) + return; + list_for_each_entry_safe(lseg, tmp, &nfsi->layout->plh_segs, pls_list) { + if (!test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) + continue; + pnfs_lseg_dec_and_remove_zero(lseg, head); + } +} + +void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) +{ + clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); + smp_mb__after_atomic(); + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); +} + +static int +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, + enum pnfs_iomode iomode, bool sync) +{ + struct inode *ino = lo->plh_inode; + struct nfs4_layoutreturn *lrp; + int status = 0; + + lrp = kzalloc(sizeof(*lrp), GFP_NOFS); + if (unlikely(lrp == NULL)) { + status = -ENOMEM; + spin_lock(&ino->i_lock); + lo->plh_block_lgets--; + pnfs_clear_layoutreturn_waitbit(lo); + rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq); + spin_unlock(&ino->i_lock); + pnfs_put_layout_hdr(lo); + goto out; + } + + lrp->args.stateid = stateid; + lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; + lrp->args.inode = ino; + lrp->args.range.iomode = iomode; + lrp->args.range.offset = 0; + lrp->args.range.length = NFS4_MAX_UINT64; + lrp->args.layout = lo; + lrp->clp = NFS_SERVER(ino)->nfs_client; + lrp->cred = lo->plh_lc_cred; + + status = nfs4_proc_layoutreturn(lrp, sync); +out: + dprintk("<-- %s status: %d\n", __func__, status); + return status; +} + +/* + * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr + * when the layout segment list is empty. + * + * Note that a pnfs_layout_hdr can exist with an empty layout segment + * list when LAYOUTGET has failed, or when LAYOUTGET succeeded, but the + * deviceid is marked invalid. + */ +int +_pnfs_return_layout(struct inode *ino) +{ + struct pnfs_layout_hdr *lo = NULL; + struct nfs_inode *nfsi = NFS_I(ino); + LIST_HEAD(tmp_list); + nfs4_stateid stateid; + int status = 0, empty; + + dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino); + + spin_lock(&ino->i_lock); + lo = nfsi->layout; + if (!lo) { + spin_unlock(&ino->i_lock); + dprintk("NFS: %s no layout to return\n", __func__); + goto out; + } + stateid = nfsi->layout->plh_stateid; + /* Reference matched in nfs4_layoutreturn_release */ + pnfs_get_layout_hdr(lo); + empty = list_empty(&lo->plh_segs); + pnfs_clear_layoutcommit(ino, &tmp_list); + pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); + + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range); + } + + /* Don't send a LAYOUTRETURN if list was initially empty */ + if (empty) { + spin_unlock(&ino->i_lock); + pnfs_put_layout_hdr(lo); + dprintk("NFS: %s no layout segments to return\n", __func__); + goto out; + } + + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + lo->plh_block_lgets++; + spin_unlock(&ino->i_lock); + pnfs_free_lseg_list(&tmp_list); + + status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); +out: + dprintk("<-- %s status: %d\n", __func__, status); + return status; +} +EXPORT_SYMBOL_GPL(_pnfs_return_layout); + +int +pnfs_commit_and_return_layout(struct inode *inode) +{ + struct pnfs_layout_hdr *lo; + int ret; + + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (lo == NULL) { + spin_unlock(&inode->i_lock); + return 0; + } + pnfs_get_layout_hdr(lo); + /* Block new layoutgets and read/write to ds */ + lo->plh_block_lgets++; + spin_unlock(&inode->i_lock); + filemap_fdatawait(inode->i_mapping); + ret = pnfs_layoutcommit_inode(inode, true); + if (ret == 0) + ret = _pnfs_return_layout(inode); + spin_lock(&inode->i_lock); + lo->plh_block_lgets--; + spin_unlock(&inode->i_lock); + pnfs_put_layout_hdr(lo); + return ret; +} + +bool pnfs_roc(struct inode *ino) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct nfs_open_context *ctx; + struct nfs4_state *state; + struct pnfs_layout_hdr *lo; + struct pnfs_layout_segment *lseg, *tmp; + nfs4_stateid stateid; + LIST_HEAD(tmp_list); + bool found = false, layoutreturn = false; + + spin_lock(&ino->i_lock); + lo = nfsi->layout; + if (!lo || !test_and_clear_bit(NFS_LAYOUT_ROC, &lo->plh_flags) || + test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) + goto out_noroc; + + /* Don't return layout if we hold a delegation */ + if (nfs4_check_delegation(ino, FMODE_READ)) + goto out_noroc; + + list_for_each_entry(ctx, &nfsi->open_files, list) { + state = ctx->state; + /* Don't return layout if there is open file state */ + if (state != NULL && state->state != 0) + goto out_noroc; + } + + pnfs_clear_retry_layoutget(lo); + list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list) + if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { + mark_lseg_invalid(lseg, &tmp_list); + found = true; + } + if (!found) + goto out_noroc; + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */ + spin_unlock(&ino->i_lock); + pnfs_free_lseg_list(&tmp_list); + pnfs_layoutcommit_inode(ino, true); + return true; + +out_noroc: + if (lo) { + stateid = lo->plh_stateid; + layoutreturn = + test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags); + if (layoutreturn) { + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); + } + } + spin_unlock(&ino->i_lock); + if (layoutreturn) { + pnfs_layoutcommit_inode(ino, true); + pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + } + return false; +} + +void pnfs_roc_release(struct inode *ino) +{ + struct pnfs_layout_hdr *lo; + + spin_lock(&ino->i_lock); + lo = NFS_I(ino)->layout; + lo->plh_block_lgets--; + if (atomic_dec_and_test(&lo->plh_refcount)) { + pnfs_detach_layout_hdr(lo); + spin_unlock(&ino->i_lock); + pnfs_free_layout_hdr(lo); + } else + spin_unlock(&ino->i_lock); +} + +void pnfs_roc_set_barrier(struct inode *ino, u32 barrier) +{ + struct pnfs_layout_hdr *lo; + + spin_lock(&ino->i_lock); + lo = NFS_I(ino)->layout; + if (pnfs_seqid_is_newer(barrier, lo->plh_barrier)) + lo->plh_barrier = barrier; + spin_unlock(&ino->i_lock); +} + +bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *lo; + struct pnfs_layout_segment *lseg; + nfs4_stateid stateid; + u32 current_seqid; + bool found = false, layoutreturn = false; + + spin_lock(&ino->i_lock); + list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) + if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + found = true; + goto out; + } + lo = nfsi->layout; + current_seqid = be32_to_cpu(lo->plh_stateid.seqid); + + /* Since close does not return a layout stateid for use as + * a barrier, we choose the worst-case barrier. + */ + *barrier = current_seqid + atomic_read(&lo->plh_outstanding); +out: + if (!found) { + stateid = lo->plh_stateid; + layoutreturn = + test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags); + if (layoutreturn) { + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); + } + } + spin_unlock(&ino->i_lock); + if (layoutreturn) { + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false); + } + return found; +} + +/* + * Compare two layout segments for sorting into layout cache. + * We want to preferentially return RW over RO layouts, so ensure those + * are seen first. + */ +static s64 +pnfs_lseg_range_cmp(const struct pnfs_layout_range *l1, + const struct pnfs_layout_range *l2) +{ + s64 d; + + /* high offset > low offset */ + d = l1->offset - l2->offset; + if (d) + return d; + + /* short length > long length */ + d = l2->length - l1->length; + if (d) + return d; + + /* read > read/write */ + return (int)(l1->iomode == IOMODE_READ) - (int)(l2->iomode == IOMODE_READ); +} + +static void +pnfs_layout_insert_lseg(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_segment *lp; + + dprintk("%s:Begin\n", __func__); + + list_for_each_entry(lp, &lo->plh_segs, pls_list) { + if (pnfs_lseg_range_cmp(&lseg->pls_range, &lp->pls_range) > 0) + continue; + list_add_tail(&lseg->pls_list, &lp->pls_list); + dprintk("%s: inserted lseg %p " + "iomode %d offset %llu length %llu before " + "lp %p iomode %d offset %llu length %llu\n", + __func__, lseg, lseg->pls_range.iomode, + lseg->pls_range.offset, lseg->pls_range.length, + lp, lp->pls_range.iomode, lp->pls_range.offset, + lp->pls_range.length); + goto out; + } + list_add_tail(&lseg->pls_list, &lo->plh_segs); + dprintk("%s: inserted lseg %p " + "iomode %d offset %llu length %llu at tail\n", + __func__, lseg, lseg->pls_range.iomode, + lseg->pls_range.offset, lseg->pls_range.length); +out: + pnfs_get_layout_hdr(lo); + + dprintk("%s:Return\n", __func__); +} + +static struct pnfs_layout_hdr * +alloc_init_layout_hdr(struct inode *ino, + struct nfs_open_context *ctx, + gfp_t gfp_flags) +{ + struct pnfs_layout_hdr *lo; + + lo = pnfs_alloc_layout_hdr(ino, gfp_flags); + if (!lo) + return NULL; + atomic_set(&lo->plh_refcount, 1); + INIT_LIST_HEAD(&lo->plh_layouts); + INIT_LIST_HEAD(&lo->plh_segs); + INIT_LIST_HEAD(&lo->plh_bulk_destroy); + lo->plh_inode = ino; + lo->plh_lc_cred = get_rpccred(ctx->cred); + return lo; +} + +static struct pnfs_layout_hdr * +pnfs_find_alloc_layout(struct inode *ino, + struct nfs_open_context *ctx, + gfp_t gfp_flags) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *new = NULL; + + dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout); + + if (nfsi->layout != NULL) + goto out_existing; + spin_unlock(&ino->i_lock); + new = alloc_init_layout_hdr(ino, ctx, gfp_flags); + spin_lock(&ino->i_lock); + + if (likely(nfsi->layout == NULL)) { /* Won the race? */ + nfsi->layout = new; + return new; + } else if (new != NULL) + pnfs_free_layout_hdr(new); +out_existing: + pnfs_get_layout_hdr(nfsi->layout); + return nfsi->layout; +} + +/* + * iomode matching rules: + * iomode lseg match + * ----- ----- ----- + * ANY READ true + * ANY RW true + * RW READ false + * RW RW true + * READ READ true + * READ RW true + */ +static bool +pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range, + const struct pnfs_layout_range *range) +{ + struct pnfs_layout_range range1; + + if ((range->iomode == IOMODE_RW && + ls_range->iomode != IOMODE_RW) || + !pnfs_lseg_range_intersecting(ls_range, range)) + return 0; + + /* range1 covers only the first byte in the range */ + range1 = *range; + range1.length = 1; + return pnfs_lseg_range_contained(ls_range, &range1); +} + +/* + * lookup range in layout + */ +static struct pnfs_layout_segment * +pnfs_find_lseg(struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range) +{ + struct pnfs_layout_segment *lseg, *ret = NULL; + + dprintk("%s:Begin\n", __func__); + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) && + !test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) && + pnfs_lseg_range_match(&lseg->pls_range, range)) { + ret = pnfs_get_lseg(lseg); + break; + } + if (lseg->pls_range.offset > range->offset) + break; + } + + dprintk("%s:Return lseg %p ref %d\n", + __func__, ret, ret ? atomic_read(&ret->pls_refcount) : 0); + return ret; +} + +/* + * Use mdsthreshold hints set at each OPEN to determine if I/O should go + * to the MDS or over pNFS + * + * The nfs_inode read_io and write_io fields are cumulative counters reset + * when there are no layout segments. Note that in pnfs_update_layout iomode + * is set to IOMODE_READ for a READ request, and set to IOMODE_RW for a + * WRITE request. + * + * A return of true means use MDS I/O. + * + * From rfc 5661: + * If a file's size is smaller than the file size threshold, data accesses + * SHOULD be sent to the metadata server. If an I/O request has a length that + * is below the I/O size threshold, the I/O SHOULD be sent to the metadata + * server. If both file size and I/O size are provided, the client SHOULD + * reach or exceed both thresholds before sending its read or write + * requests to the data server. + */ +static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, + struct inode *ino, int iomode) +{ + struct nfs4_threshold *t = ctx->mdsthreshold; + struct nfs_inode *nfsi = NFS_I(ino); + loff_t fsize = i_size_read(ino); + bool size = false, size_set = false, io = false, io_set = false, ret = false; + + if (t == NULL) + return ret; + + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n", + __func__, t->bm, t->rd_sz, t->wr_sz, t->rd_io_sz, t->wr_io_sz); + + switch (iomode) { + case IOMODE_READ: + if (t->bm & THRESHOLD_RD) { + dprintk("%s fsize %llu\n", __func__, fsize); + size_set = true; + if (fsize < t->rd_sz) + size = true; + } + if (t->bm & THRESHOLD_RD_IO) { + dprintk("%s nfsi->read_io %llu\n", __func__, + nfsi->read_io); + io_set = true; + if (nfsi->read_io < t->rd_io_sz) + io = true; + } + break; + case IOMODE_RW: + if (t->bm & THRESHOLD_WR) { + dprintk("%s fsize %llu\n", __func__, fsize); + size_set = true; + if (fsize < t->wr_sz) + size = true; + } + if (t->bm & THRESHOLD_WR_IO) { + dprintk("%s nfsi->write_io %llu\n", __func__, + nfsi->write_io); + io_set = true; + if (nfsi->write_io < t->wr_io_sz) + io = true; + } + break; + } + if (size_set && io_set) { + if (size && io) + ret = true; + } else if (size || io) + ret = true; + + dprintk("<-- %s size %d io %d ret %d\n", __func__, size, io, ret); + return ret; +} + +/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */ +static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key) +{ + if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags)) + return 1; + return nfs_wait_bit_killable(key); +} + +static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + /* + * send layoutcommit as it can hold up layoutreturn due to lseg + * reference + */ + pnfs_layoutcommit_inode(lo->plh_inode, false); + return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, + pnfs_layoutget_retry_bit_wait, + TASK_UNINTERRUPTIBLE); +} + +static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo) +{ + unsigned long *bitlock = &lo->plh_flags; + + clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET); +} + +/* + * Layout segment is retreived from the server if not cached. + * The appropriate layout segment is referenced and returned to the caller. + */ +struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, + struct nfs_open_context *ctx, + loff_t pos, + u64 count, + enum pnfs_iomode iomode, + gfp_t gfp_flags) +{ + struct pnfs_layout_range arg = { + .iomode = iomode, + .offset = pos, + .length = count, + }; + unsigned pg_offset; + struct nfs_server *server = NFS_SERVER(ino); + struct nfs_client *clp = server->nfs_client; + struct pnfs_layout_hdr *lo; + struct pnfs_layout_segment *lseg = NULL; + bool first; + + if (!pnfs_enabled_sb(NFS_SERVER(ino))) + goto out; + + if (pnfs_within_mdsthreshold(ctx, ino, iomode)) + goto out; + +lookup_again: + first = false; + spin_lock(&ino->i_lock); + lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); + if (lo == NULL) { + spin_unlock(&ino->i_lock); + goto out; + } + + /* Do we even need to bother with this? */ + if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + dprintk("%s matches recall, use MDS\n", __func__); + goto out_unlock; + } + + /* if LAYOUTGET already failed once we don't try again */ + if (pnfs_layout_io_test_failed(lo, iomode) && + !pnfs_should_retry_layoutget(lo)) + goto out_unlock; + + first = list_empty(&lo->plh_segs); + if (first) { + /* The first layoutget for the file. Need to serialize per + * RFC 5661 Errata 3208. + */ + if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET, + &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto lookup_again; + } + } else { + /* Check to see if the layout for the given range + * already exists + */ + lseg = pnfs_find_lseg(lo, &arg); + if (lseg) + goto out_unlock; + } + + /* + * Because we free lsegs before sending LAYOUTRETURN, we need to wait + * for LAYOUTRETURN even if first is true. + */ + if (!lseg && pnfs_should_retry_layoutget(lo) && + test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + dprintk("%s wait for layoutreturn\n", __func__); + if (pnfs_prepare_to_retry_layoutget(lo)) { + if (first) + pnfs_clear_first_layoutget(lo); + pnfs_put_layout_hdr(lo); + dprintk("%s retrying\n", __func__); + goto lookup_again; + } + goto out_put_layout_hdr; + } + + if (pnfs_layoutgets_blocked(lo, &arg, 0)) + goto out_unlock; + atomic_inc(&lo->plh_outstanding); + spin_unlock(&ino->i_lock); + + if (list_empty(&lo->plh_layouts)) { + /* The lo must be on the clp list if there is any + * chance of a CB_LAYOUTRECALL(FILE) coming in. + */ + spin_lock(&clp->cl_lock); + if (list_empty(&lo->plh_layouts)) + list_add_tail(&lo->plh_layouts, &server->layouts); + spin_unlock(&clp->cl_lock); + } + + pg_offset = arg.offset & ~PAGE_CACHE_MASK; + if (pg_offset) { + arg.offset -= pg_offset; + arg.length += pg_offset; + } + if (arg.length != NFS4_MAX_UINT64) + arg.length = PAGE_CACHE_ALIGN(arg.length); + + lseg = send_layoutget(lo, ctx, &arg, gfp_flags); + pnfs_clear_retry_layoutget(lo); + atomic_dec(&lo->plh_outstanding); +out_put_layout_hdr: + if (first) + pnfs_clear_first_layoutget(lo); + pnfs_put_layout_hdr(lo); +out: + dprintk("%s: inode %s/%llu pNFS layout segment %s for " + "(%s, offset: %llu, length: %llu)\n", + __func__, ino->i_sb->s_id, + (unsigned long long)NFS_FILEID(ino), + lseg == NULL ? "not found" : "found", + iomode==IOMODE_RW ? "read/write" : "read-only", + (unsigned long long)pos, + (unsigned long long)count); + return lseg; +out_unlock: + spin_unlock(&ino->i_lock); + goto out_put_layout_hdr; +} +EXPORT_SYMBOL_GPL(pnfs_update_layout); + +struct pnfs_layout_segment * +pnfs_layout_process(struct nfs4_layoutget *lgp) +{ + struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout; + struct nfs4_layoutget_res *res = &lgp->res; + struct pnfs_layout_segment *lseg; + struct inode *ino = lo->plh_inode; + LIST_HEAD(free_me); + int status = 0; + + /* Inject layout blob into I/O device driver */ + lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags); + if (!lseg || IS_ERR(lseg)) { + if (!lseg) + status = -ENOMEM; + else + status = PTR_ERR(lseg); + dprintk("%s: Could not allocate layout: error %d\n", + __func__, status); + goto out; + } + + init_lseg(lo, lseg); + lseg->pls_range = res->range; + + spin_lock(&ino->i_lock); + if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + dprintk("%s forget reply due to recall\n", __func__); + goto out_forget_reply; + } + + if (pnfs_layoutgets_blocked(lo, &lgp->args.range, 1)) { + dprintk("%s forget reply due to state\n", __func__); + goto out_forget_reply; + } + + if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { + /* existing state ID, make sure the sequence number matches. */ + if (pnfs_layout_stateid_blocked(lo, &res->stateid)) { + dprintk("%s forget reply due to sequence\n", __func__); + goto out_forget_reply; + } + pnfs_set_layout_stateid(lo, &res->stateid, false); + } else { + /* + * We got an entirely new state ID. Mark all segments for the + * inode invalid, and don't bother validating the stateid + * sequence number. + */ + pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL); + + nfs4_stateid_copy(&lo->plh_stateid, &res->stateid); + lo->plh_barrier = be32_to_cpu(res->stateid.seqid); + } + + clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + + pnfs_get_lseg(lseg); + pnfs_layout_insert_lseg(lo, lseg); + + if (res->return_on_close) { + set_bit(NFS_LSEG_ROC, &lseg->pls_flags); + set_bit(NFS_LAYOUT_ROC, &lo->plh_flags); + } + + spin_unlock(&ino->i_lock); + pnfs_free_lseg_list(&free_me); + return lseg; +out: + return ERR_PTR(status); + +out_forget_reply: + spin_unlock(&ino->i_lock); + lseg->pls_layout = lo; + NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + goto out; +} + +static void +pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, + struct list_head *tmp_list, + struct pnfs_layout_range *return_range) +{ + struct pnfs_layout_segment *lseg, *next; + + dprintk("%s:Begin lo %p\n", __func__, lo); + + if (list_empty(&lo->plh_segs)) + return; + + list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) + if (should_free_lseg(&lseg->pls_range, return_range)) { + dprintk("%s: marking lseg %p iomode %d " + "offset %llu length %llu\n", __func__, + lseg, lseg->pls_range.iomode, + lseg->pls_range.offset, + lseg->pls_range.length); + set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); + mark_lseg_invalid(lseg, tmp_list); + } +} + +void pnfs_error_mark_layout_for_return(struct inode *inode, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_hdr *lo = NFS_I(inode)->layout; + int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode); + struct pnfs_layout_range range = { + .iomode = lseg->pls_range.iomode, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + LIST_HEAD(free_me); + + spin_lock(&inode->i_lock); + /* set failure bit so that pnfs path will be retried later */ + pnfs_layout_set_fail_bit(lo, iomode); + set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); + if (lo->plh_return_iomode == 0) + lo->plh_return_iomode = range.iomode; + else if (lo->plh_return_iomode != range.iomode) + lo->plh_return_iomode = IOMODE_ANY; + /* + * mark all matching lsegs so that we are sure to have no live + * segments at hand when sending layoutreturn. See pnfs_put_lseg() + * for how it works. + */ + pnfs_mark_matching_lsegs_return(lo, &free_me, &range); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&free_me); +} +EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return); + +void +pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + u64 rd_size = req->wb_bytes; + + if (pgio->pg_lseg == NULL) { + if (pgio->pg_dreq == NULL) + rd_size = i_size_read(pgio->pg_inode) - req_offset(req); + else + rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); + + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + req_offset(req), + rd_size, + IOMODE_READ, + GFP_KERNEL); + } + /* If no lseg, fall back to read through mds */ + if (pgio->pg_lseg == NULL) + nfs_pageio_reset_read_mds(pgio); + +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_read); + +void +pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req, u64 wb_size) +{ + if (pgio->pg_lseg == NULL) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + req_offset(req), + wb_size, + IOMODE_RW, + GFP_NOFS); + /* If no lseg, fall back to write through mds */ + if (pgio->pg_lseg == NULL) + nfs_pageio_reset_write_mds(pgio); +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); + +void +pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *desc) +{ + if (desc->pg_lseg) { + pnfs_put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + } +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup); + +/* + * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number + * of bytes (maximum @req->wb_bytes) that can be coalesced. + */ +size_t +pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, + struct nfs_page *prev, struct nfs_page *req) +{ + unsigned int size; + u64 seg_end, req_start, seg_left; + + size = nfs_generic_pg_test(pgio, prev, req); + if (!size) + return 0; + + /* + * 'size' contains the number of bytes left in the current page (up + * to the original size asked for in @req->wb_bytes). + * + * Calculate how many bytes are left in the layout segment + * and if there are less bytes than 'size', return that instead. + * + * Please also note that 'end_offset' is actually the offset of the + * first byte that lies outside the pnfs_layout_range. FIXME? + * + */ + if (pgio->pg_lseg) { + seg_end = end_offset(pgio->pg_lseg->pls_range.offset, + pgio->pg_lseg->pls_range.length); + req_start = req_offset(req); + WARN_ON_ONCE(req_start >= seg_end); + /* start of request is past the last byte of this segment */ + if (req_start >= seg_end) { + /* reference the new lseg */ + if (pgio->pg_ops->pg_cleanup) + pgio->pg_ops->pg_cleanup(pgio); + if (pgio->pg_ops->pg_init) + pgio->pg_ops->pg_init(pgio, req); + return 0; + } + + /* adjust 'size' iff there are fewer bytes left in the + * segment than what nfs_generic_pg_test returned */ + seg_left = seg_end - req_start; + if (seg_left < size) + size = (unsigned int)seg_left; + } + + return size; +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); + +int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) +{ + struct nfs_pageio_descriptor pgio; + + /* Resend all requests through the MDS */ + nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, + hdr->completion_ops); + return nfs_pageio_resend(&pgio, hdr); +} +EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); + +static void pnfs_ld_handle_write_error(struct nfs_pgio_header *hdr) +{ + + dprintk("pnfs write error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & + PNFS_LAYOUTRET_ON_ERROR) { + pnfs_return_layout(hdr->inode); + } + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + hdr->task.tk_status = pnfs_write_done_resend_to_mds(hdr); +} + +/* + * Called by non rpc-based layout drivers + */ +void pnfs_ld_write_done(struct nfs_pgio_header *hdr) +{ + trace_nfs4_pnfs_write(hdr, hdr->pnfs_error); + if (!hdr->pnfs_error) { + pnfs_set_layoutcommit(hdr->inode, hdr->lseg, + hdr->mds_offset + hdr->res.count); + hdr->mds_ops->rpc_call_done(&hdr->task, hdr); + } else + pnfs_ld_handle_write_error(hdr); + hdr->mds_ops->rpc_release(hdr); +} +EXPORT_SYMBOL_GPL(pnfs_ld_write_done); + +static void +pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &mirror->pg_list); + nfs_pageio_reset_write_mds(desc); + mirror->pg_recoalesce = 1; + } + nfs_pgio_data_destroy(hdr); +} + +static enum pnfs_try_status +pnfs_try_to_write_data(struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops, + struct pnfs_layout_segment *lseg, + int how) +{ + struct inode *inode = hdr->inode; + enum pnfs_try_status trypnfs; + struct nfs_server *nfss = NFS_SERVER(inode); + + hdr->mds_ops = call_ops; + + dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__, + inode->i_ino, hdr->args.count, hdr->args.offset, how); + trypnfs = nfss->pnfs_curr_ld->write_pagelist(hdr, how); + if (trypnfs != PNFS_NOT_ATTEMPTED) + nfs_inc_stats(inode, NFSIOS_PNFS_WRITE); + dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); + return trypnfs; +} + +static void +pnfs_do_write(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, int how) +{ + const struct rpc_call_ops *call_ops = desc->pg_rpc_callops; + struct pnfs_layout_segment *lseg = desc->pg_lseg; + enum pnfs_try_status trypnfs; + + trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how); + if (trypnfs == PNFS_NOT_ATTEMPTED) + pnfs_write_through_mds(desc, hdr); +} + +static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) +{ + pnfs_put_lseg(hdr->lseg); + nfs_pgio_header_free(hdr); +} + +int +pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + struct nfs_pgio_header *hdr; + int ret; + + hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); + if (!hdr) { + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + return -ENOMEM; + } + nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); + + hdr->lseg = pnfs_get_lseg(desc->pg_lseg); + ret = nfs_generic_pgio(desc, hdr); + if (!ret) + pnfs_do_write(desc, hdr, desc->pg_ioflags); + + return ret; +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); + +int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *hdr) +{ + struct nfs_pageio_descriptor pgio; + + /* Resend all requests through the MDS */ + nfs_pageio_init_read(&pgio, hdr->inode, true, hdr->completion_ops); + return nfs_pageio_resend(&pgio, hdr); +} +EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds); + +static void pnfs_ld_handle_read_error(struct nfs_pgio_header *hdr) +{ + dprintk("pnfs read error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & + PNFS_LAYOUTRET_ON_ERROR) { + pnfs_return_layout(hdr->inode); + } + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + hdr->task.tk_status = pnfs_read_done_resend_to_mds(hdr); +} + +/* + * Called by non rpc-based layout drivers + */ +void pnfs_ld_read_done(struct nfs_pgio_header *hdr) +{ + trace_nfs4_pnfs_read(hdr, hdr->pnfs_error); + if (likely(!hdr->pnfs_error)) { + __nfs4_read_done_cb(hdr); + hdr->mds_ops->rpc_call_done(&hdr->task, hdr); + } else + pnfs_ld_handle_read_error(hdr); + hdr->mds_ops->rpc_release(hdr); +} +EXPORT_SYMBOL_GPL(pnfs_ld_read_done); + +static void +pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &mirror->pg_list); + nfs_pageio_reset_read_mds(desc); + mirror->pg_recoalesce = 1; + } + nfs_pgio_data_destroy(hdr); +} + +/* + * Call the appropriate parallel I/O subsystem read function. + */ +static enum pnfs_try_status +pnfs_try_to_read_data(struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops, + struct pnfs_layout_segment *lseg) +{ + struct inode *inode = hdr->inode; + struct nfs_server *nfss = NFS_SERVER(inode); + enum pnfs_try_status trypnfs; + + hdr->mds_ops = call_ops; + + dprintk("%s: Reading ino:%lu %u@%llu\n", + __func__, inode->i_ino, hdr->args.count, hdr->args.offset); + + trypnfs = nfss->pnfs_curr_ld->read_pagelist(hdr); + if (trypnfs != PNFS_NOT_ATTEMPTED) + nfs_inc_stats(inode, NFSIOS_PNFS_READ); + dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); + return trypnfs; +} + +/* Resend all requests through pnfs. */ +int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr) +{ + struct nfs_pageio_descriptor pgio; + + nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops); + return nfs_pageio_resend(&pgio, hdr); +} +EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs); + +static void +pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) +{ + const struct rpc_call_ops *call_ops = desc->pg_rpc_callops; + struct pnfs_layout_segment *lseg = desc->pg_lseg; + enum pnfs_try_status trypnfs; + int err = 0; + + trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg); + if (trypnfs == PNFS_TRY_AGAIN) + err = pnfs_read_resend_pnfs(hdr); + if (trypnfs == PNFS_NOT_ATTEMPTED || err) + pnfs_read_through_mds(desc, hdr); +} + +static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) +{ + pnfs_put_lseg(hdr->lseg); + nfs_pgio_header_free(hdr); +} + +int +pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) +{ + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); + + struct nfs_pgio_header *hdr; + int ret; + + hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); + if (!hdr) { + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + return -ENOMEM; + } + nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); + hdr->lseg = pnfs_get_lseg(desc->pg_lseg); + ret = nfs_generic_pgio(desc, hdr); + if (!ret) + pnfs_do_read(desc, hdr); + return ret; +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); + +static void pnfs_clear_layoutcommitting(struct inode *inode) +{ + unsigned long *bitlock = &NFS_I(inode)->flags; + + clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING); +} + +/* + * There can be multiple RW segments. + */ +static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) { + if (lseg->pls_range.iomode == IOMODE_RW && + test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) + list_add(&lseg->pls_lc_list, listp); + } +} + +static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp) +{ + struct pnfs_layout_segment *lseg, *tmp; + + /* Matched by references in pnfs_set_layoutcommit */ + list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) { + list_del_init(&lseg->pls_lc_list); + pnfs_put_lseg(lseg); + } + + pnfs_clear_layoutcommitting(inode); +} + +void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg) +{ + pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode); +} +EXPORT_SYMBOL_GPL(pnfs_set_lo_fail); + +void +pnfs_set_layoutcommit(struct inode *inode, struct pnfs_layout_segment *lseg, + loff_t end_pos) +{ + struct nfs_inode *nfsi = NFS_I(inode); + bool mark_as_dirty = false; + + spin_lock(&inode->i_lock); + if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { + nfsi->layout->plh_lwb = end_pos; + mark_as_dirty = true; + dprintk("%s: Set layoutcommit for inode %lu ", + __func__, inode->i_ino); + } else if (end_pos > nfsi->layout->plh_lwb) + nfsi->layout->plh_lwb = end_pos; + if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) { + /* references matched in nfs4_layoutcommit_release */ + pnfs_get_lseg(lseg); + } + spin_unlock(&inode->i_lock); + dprintk("%s: lseg %p end_pos %llu\n", + __func__, lseg, nfsi->layout->plh_lwb); + + /* if pnfs_layoutcommit_inode() runs between inode locks, the next one + * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */ + if (mark_as_dirty) + mark_inode_dirty_sync(inode); +} +EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); + +void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data) +{ + struct nfs_server *nfss = NFS_SERVER(data->args.inode); + + if (nfss->pnfs_curr_ld->cleanup_layoutcommit) + nfss->pnfs_curr_ld->cleanup_layoutcommit(data); + pnfs_list_write_lseg_done(data->args.inode, &data->lseg_list); +} + +/* + * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and + * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough + * data to disk to allow the server to recover the data if it crashes. + * LAYOUTCOMMIT is only needed when the NFL4_UFLG_COMMIT_THRU_MDS flag + * is off, and a COMMIT is sent to a data server, or + * if WRITEs to a data server return NFS_DATA_SYNC. + */ +int +pnfs_layoutcommit_inode(struct inode *inode, bool sync) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + struct nfs4_layoutcommit_data *data; + struct nfs_inode *nfsi = NFS_I(inode); + loff_t end_pos; + int status; + + if (!pnfs_layoutcommit_outstanding(inode)) + return 0; + + dprintk("--> %s inode %lu\n", __func__, inode->i_ino); + + status = -EAGAIN; + if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) { + if (!sync) + goto out; + status = wait_on_bit_lock_action(&nfsi->flags, + NFS_INO_LAYOUTCOMMITTING, + nfs_wait_bit_killable, + TASK_KILLABLE); + if (status) + goto out; + } + + status = -ENOMEM; + /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */ + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) + goto clear_layoutcommitting; + + status = 0; + spin_lock(&inode->i_lock); + if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) + goto out_unlock; + + INIT_LIST_HEAD(&data->lseg_list); + pnfs_list_write_lseg(inode, &data->lseg_list); + + end_pos = nfsi->layout->plh_lwb; + + nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid); + spin_unlock(&inode->i_lock); + + data->args.inode = inode; + data->cred = get_rpccred(nfsi->layout->plh_lc_cred); + nfs_fattr_init(&data->fattr); + data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask; + data->res.fattr = &data->fattr; + data->args.lastbytewritten = end_pos - 1; + data->res.server = NFS_SERVER(inode); + + if (ld->prepare_layoutcommit) { + status = ld->prepare_layoutcommit(&data->args); + if (status) { + spin_lock(&inode->i_lock); + set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags); + if (end_pos > nfsi->layout->plh_lwb) + nfsi->layout->plh_lwb = end_pos; + spin_unlock(&inode->i_lock); + put_rpccred(data->cred); + goto clear_layoutcommitting; + } + } + + + status = nfs4_proc_layoutcommit(data, sync); +out: + if (status) + mark_inode_dirty_sync(inode); + dprintk("<-- %s status %d\n", __func__, status); + return status; +out_unlock: + spin_unlock(&inode->i_lock); + kfree(data); +clear_layoutcommitting: + pnfs_clear_layoutcommitting(inode); + goto out; +} +EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode); + +int +pnfs_generic_sync(struct inode *inode, bool datasync) +{ + return pnfs_layoutcommit_inode(inode, true); +} +EXPORT_SYMBOL_GPL(pnfs_generic_sync); + +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + struct nfs4_threshold *thp; + + thp = kzalloc(sizeof(*thp), GFP_NOFS); + if (!thp) { + dprintk("%s mdsthreshold allocation failed\n", __func__); + return NULL; + } + return thp; +} diff --git a/kernel/fs/nfs/pnfs.h b/kernel/fs/nfs/pnfs.h new file mode 100644 index 000000000..1e6308f82 --- /dev/null +++ b/kernel/fs/nfs/pnfs.h @@ -0,0 +1,692 @@ +/* + * pNFS client data structures. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#ifndef FS_NFS_PNFS_H +#define FS_NFS_PNFS_H + +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/workqueue.h> + +enum { + NFS_LSEG_VALID = 0, /* cleared when lseg is recalled/returned */ + NFS_LSEG_ROC, /* roc bit received from server */ + NFS_LSEG_LAYOUTCOMMIT, /* layoutcommit bit set for layoutcommit */ + NFS_LSEG_LAYOUTRETURN, /* layoutreturn bit set for layoutreturn */ +}; + +/* Individual ip address */ +struct nfs4_pnfs_ds_addr { + struct sockaddr_storage da_addr; + size_t da_addrlen; + struct list_head da_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + char *da_remotestr; /* human readable addr+port */ +}; + +struct nfs4_pnfs_ds { + struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + char *ds_remotestr; /* comma sep list of addrs */ + struct list_head ds_addrs; + struct nfs_client *ds_clp; + atomic_t ds_count; + unsigned long ds_state; +#define NFS4DS_CONNECTING 0 /* ds is establishing connection */ +}; + +struct pnfs_layout_segment { + struct list_head pls_list; + struct list_head pls_lc_list; + struct pnfs_layout_range pls_range; + atomic_t pls_refcount; + unsigned long pls_flags; + struct pnfs_layout_hdr *pls_layout; + struct work_struct pls_work; +}; + +enum pnfs_try_status { + PNFS_ATTEMPTED = 0, + PNFS_NOT_ATTEMPTED = 1, + PNFS_TRY_AGAIN = 2, +}; + +#ifdef CONFIG_NFS_V4_1 + +#define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" + +/* + * Default data server connection timeout and retrans vaules. + * Set by module parameters dataserver_timeo and dataserver_retrans. + */ +#define NFS4_DEF_DS_TIMEO 600 /* in tenths of a second */ +#define NFS4_DEF_DS_RETRANS 5 + +/* error codes for internal use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + +enum { + NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ + NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ + NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ + NFS_LAYOUT_ROC, /* some lseg had roc bit set */ + NFS_LAYOUT_RETURN, /* Return this layout ASAP */ + NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ + NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ + NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ + NFS_LAYOUT_RETRY_LAYOUTGET, /* Retry layoutget */ +}; + +enum layoutdriver_policy_flags { + /* Should the pNFS client commit and return the layout upon truncate to + * a smaller size */ + PNFS_LAYOUTRET_ON_SETATTR = 1 << 0, + PNFS_LAYOUTRET_ON_ERROR = 1 << 1, + PNFS_READ_WHOLE_PAGE = 1 << 2, +}; + +struct nfs4_deviceid_node; + +/* Per-layout driver specific registration structure */ +struct pnfs_layoutdriver_type { + struct list_head pnfs_tblid; + const u32 id; + const char *name; + struct module *owner; + unsigned flags; + unsigned max_deviceinfo_size; + + int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *); + int (*clear_layoutdriver) (struct nfs_server *); + + struct pnfs_layout_hdr * (*alloc_layout_hdr) (struct inode *inode, gfp_t gfp_flags); + void (*free_layout_hdr) (struct pnfs_layout_hdr *); + + struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); + void (*free_lseg) (struct pnfs_layout_segment *lseg); + + void (*return_range) (struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range); + + /* test for nfs page cache coalescing */ + const struct nfs_pageio_ops *pg_read_ops; + const struct nfs_pageio_ops *pg_write_ops; + + struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode); + void (*mark_request_commit) (struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); + void (*clear_request_commit) (struct nfs_page *req, + struct nfs_commit_info *cinfo); + int (*scan_commit_lists) (struct nfs_commit_info *cinfo, + int max); + void (*recover_commit_reqs) (struct list_head *list, + struct nfs_commit_info *cinfo); + struct nfs_page * (*search_commit_reqs)(struct nfs_commit_info *cinfo, + struct page *page); + int (*commit_pagelist)(struct inode *inode, + struct list_head *mds_pages, + int how, + struct nfs_commit_info *cinfo); + + int (*sync)(struct inode *inode, bool datasync); + + /* + * Return PNFS_ATTEMPTED to indicate the layout code has attempted + * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS + */ + enum pnfs_try_status (*read_pagelist)(struct nfs_pgio_header *); + enum pnfs_try_status (*write_pagelist)(struct nfs_pgio_header *, int); + + void (*free_deviceid_node) (struct nfs4_deviceid_node *); + struct nfs4_deviceid_node * (*alloc_deviceid_node) + (struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags); + + void (*encode_layoutreturn) (struct pnfs_layout_hdr *layoutid, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args); + + void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data); + int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args); + void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo, + struct xdr_stream *xdr, + const struct nfs4_layoutcommit_args *args); +}; + +struct pnfs_layout_hdr { + atomic_t plh_refcount; + struct list_head plh_layouts; /* other client layouts */ + struct list_head plh_bulk_destroy; + struct list_head plh_segs; /* layout segments list */ + nfs4_stateid plh_stateid; + atomic_t plh_outstanding; /* number of RPCs out */ + unsigned long plh_block_lgets; /* block LAYOUTGET if >0 */ + u32 plh_barrier; /* ignore lower seqids */ + unsigned long plh_retry_timestamp; + unsigned long plh_flags; + enum pnfs_iomode plh_return_iomode; + loff_t plh_lwb; /* last write byte for layoutcommit */ + struct rpc_cred *plh_lc_cred; /* layoutcommit cred */ + struct inode *plh_inode; +}; + +struct pnfs_device { + struct nfs4_deviceid dev_id; + unsigned int layout_type; + unsigned int mincount; + unsigned int maxcount; /* gdia_maxcount */ + struct page **pages; + unsigned int pgbase; + unsigned int pglen; /* reply buffer length */ + unsigned char nocache : 1;/* May not be cached */ +}; + +#define NFS4_PNFS_GETDEVLIST_MAXNUM 16 + +struct pnfs_devicelist { + unsigned int eof; + unsigned int num_devs; + struct nfs4_deviceid dev_id[NFS4_PNFS_GETDEVLIST_MAXNUM]; +}; + +extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); +extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); + +/* nfs4proc.c */ +extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, + struct pnfs_device *dev, + struct rpc_cred *cred); +extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); +extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync); + +/* pnfs.c */ +void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo); +void pnfs_put_lseg(struct pnfs_layout_segment *lseg); +void pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg); + +void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32); +void unset_pnfs_layoutdriver(struct nfs_server *); +void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *); +int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); +void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req, u64 wb_size); +void pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *); +int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); +size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, + struct nfs_page *prev, struct nfs_page *req); +void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg); +struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp); +void pnfs_free_lseg_list(struct list_head *tmp_list); +void pnfs_destroy_layout(struct nfs_inode *); +void pnfs_destroy_all_layouts(struct nfs_client *); +int pnfs_destroy_layouts_byfsid(struct nfs_client *clp, + struct nfs_fsid *fsid, + bool is_recall); +int pnfs_destroy_layouts_byclid(struct nfs_client *clp, + bool is_recall); +void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo); +void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, + const nfs4_stateid *new, + bool update_barrier); +int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, + struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range, + struct nfs4_state *open_state); +int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, + struct list_head *tmp_list, + struct pnfs_layout_range *recall_range); +bool pnfs_roc(struct inode *ino); +void pnfs_roc_release(struct inode *ino); +void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); +bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task); +void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t); +void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); +int pnfs_layoutcommit_inode(struct inode *inode, bool sync); +int pnfs_generic_sync(struct inode *inode, bool datasync); +int pnfs_nfs_generic_sync(struct inode *inode, bool datasync); +int _pnfs_return_layout(struct inode *); +int pnfs_commit_and_return_layout(struct inode *); +void pnfs_ld_write_done(struct nfs_pgio_header *); +void pnfs_ld_read_done(struct nfs_pgio_header *); +int pnfs_read_resend_pnfs(struct nfs_pgio_header *); +struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, + struct nfs_open_context *ctx, + loff_t pos, + u64 count, + enum pnfs_iomode iomode, + gfp_t gfp_flags); +void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo); + +void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp); +int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *); +int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *); +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void); +void pnfs_error_mark_layout_for_return(struct inode *inode, + struct pnfs_layout_segment *lseg); + +/* nfs4_deviceid_flags */ +enum { + NFS_DEVICEID_INVALID = 0, /* set when MDS clientid recalled */ + NFS_DEVICEID_UNAVAILABLE, /* device temporarily unavailable */ + NFS_DEVICEID_NOCACHE, /* device may not be cached */ +}; + +/* pnfs_dev.c */ +struct nfs4_deviceid_node { + struct hlist_node node; + struct hlist_node tmpnode; + const struct pnfs_layoutdriver_type *ld; + const struct nfs_client *nfs_client; + unsigned long flags; + unsigned long timestamp_unavailable; + struct nfs4_deviceid deviceid; + struct rcu_head rcu; + atomic_t ref; +}; + +struct nfs4_deviceid_node * +nfs4_find_get_deviceid(struct nfs_server *server, + const struct nfs4_deviceid *id, struct rpc_cred *cred, + gfp_t gfp_mask); +void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *); +void nfs4_init_deviceid_node(struct nfs4_deviceid_node *, struct nfs_server *, + const struct nfs4_deviceid *); +bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *); +void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node); +bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node); +void nfs4_deviceid_purge_client(const struct nfs_client *); + +/* pnfs_nfs.c */ +void pnfs_generic_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo); +void pnfs_generic_commit_release(void *calldata); +void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data); +void pnfs_generic_rw_release(void *data); +void pnfs_generic_recover_commit_reqs(struct list_head *dst, + struct nfs_commit_info *cinfo); +int pnfs_generic_commit_pagelist(struct inode *inode, + struct list_head *mds_pages, + int how, + struct nfs_commit_info *cinfo, + int (*initiate_commit)(struct nfs_commit_data *data, + int how)); +int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max); +void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); +void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); +struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, + gfp_t gfp_flags); +void nfs4_pnfs_v3_ds_connect_unload(void); +void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, + struct nfs4_deviceid_node *devid, unsigned int timeo, + unsigned int retrans, u32 version, u32 minor_version, + rpc_authflavor_t au_flavor); +struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, + struct xdr_stream *xdr, + gfp_t gfp_flags); +void pnfs_layout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); + +static inline bool nfs_have_layout(struct inode *inode) +{ + return NFS_I(inode)->layout != NULL; +} + +static inline struct nfs4_deviceid_node * +nfs4_get_deviceid(struct nfs4_deviceid_node *d) +{ + atomic_inc(&d->ref); + return d; +} + +static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) + atomic_inc(&lo->plh_refcount); +} + +static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) { + atomic_dec(&lo->plh_refcount); + /* wake up waiters for LAYOUTRETURN as that is not needed */ + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); + } +} + +static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags); +} + +static inline struct pnfs_layout_segment * +pnfs_get_lseg(struct pnfs_layout_segment *lseg) +{ + if (lseg) { + atomic_inc(&lseg->pls_refcount); + smp_mb__after_atomic(); + } + return lseg; +} + +/* Return true if a layout driver is being used for this mountpoint */ +static inline int pnfs_enabled_sb(struct nfs_server *nfss) +{ + return nfss->pnfs_curr_ld != NULL; +} + +static inline int +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) +{ + if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0) + return PNFS_NOT_ATTEMPTED; + return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo); +} + +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (ld == NULL || ld->get_ds_info == NULL) + return NULL; + return ld->get_ds_info(inode); +} + +static inline void +pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node) +{ + set_bit(NFS_DEVICEID_INVALID, &node->flags); +} + +static inline bool +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, u32 ds_commit_idx) +{ + struct inode *inode = d_inode(req->wb_context->dentry); + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (lseg == NULL || ld->mark_request_commit == NULL) + return false; + ld->mark_request_commit(req, lseg, cinfo, ds_commit_idx); + return true; +} + +static inline bool +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) +{ + struct inode *inode = d_inode(req->wb_context->dentry); + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (ld == NULL || ld->clear_request_commit == NULL) + return false; + ld->clear_request_commit(req, cinfo); + return true; +} + +static inline int +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) +{ + if (cinfo->ds == NULL || cinfo->ds->nwritten == 0) + return 0; + else + return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max); +} + +static inline struct nfs_page * +pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo, + struct page *page) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (ld == NULL || ld->search_commit_reqs == NULL) + return NULL; + return ld->search_commit_reqs(cinfo, page); +} + +/* Should the pNFS client commit and return the layout upon a setattr */ +static inline bool +pnfs_ld_layoutret_on_setattr(struct inode *inode) +{ + if (!pnfs_enabled_sb(NFS_SERVER(inode))) + return false; + return NFS_SERVER(inode)->pnfs_curr_ld->flags & + PNFS_LAYOUTRET_ON_SETATTR; +} + +static inline bool +pnfs_ld_read_whole_page(struct inode *inode) +{ + if (!pnfs_enabled_sb(NFS_SERVER(inode))) + return false; + return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE; +} + +static inline int +pnfs_sync_inode(struct inode *inode, bool datasync) +{ + if (!pnfs_enabled_sb(NFS_SERVER(inode))) + return 0; + return NFS_SERVER(inode)->pnfs_curr_ld->sync(inode, datasync); +} + +static inline bool +pnfs_layoutcommit_outstanding(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + return test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags) != 0 || + test_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags) != 0; +} + +static inline int pnfs_return_layout(struct inode *ino) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct nfs_server *nfss = NFS_SERVER(ino); + + if (pnfs_enabled_sb(nfss) && nfsi->layout) + return _pnfs_return_layout(ino); + + return 0; +} + +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return (dst && src && src->bm != 0 && nfss->pnfs_curr_ld && + nfss->pnfs_curr_ld->id == src->l_type); +} + +#ifdef NFS_DEBUG +void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id); +#else +static inline void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id) +{ +} +#endif /* NFS_DEBUG */ +#else /* CONFIG_NFS_V4_1 */ + +static inline bool nfs_have_layout(struct inode *inode) +{ + return false; +} + +static inline void pnfs_destroy_all_layouts(struct nfs_client *clp) +{ +} + +static inline void pnfs_destroy_layout(struct nfs_inode *nfsi) +{ +} + +static inline struct pnfs_layout_segment * +pnfs_get_lseg(struct pnfs_layout_segment *lseg) +{ + return NULL; +} + +static inline void pnfs_put_lseg(struct pnfs_layout_segment *lseg) +{ +} + +static inline int pnfs_return_layout(struct inode *ino) +{ + return 0; +} + +static inline int pnfs_commit_and_return_layout(struct inode *inode) +{ + return 0; +} + +static inline bool +pnfs_ld_layoutret_on_setattr(struct inode *inode) +{ + return false; +} + +static inline bool +pnfs_ld_read_whole_page(struct inode *inode) +{ + return false; +} + +static inline int +pnfs_sync_inode(struct inode *inode, bool datasync) +{ + return 0; +} + +static inline bool +pnfs_roc(struct inode *ino) +{ + return false; +} + +static inline void +pnfs_roc_release(struct inode *ino) +{ +} + +static inline void +pnfs_roc_set_barrier(struct inode *ino, u32 barrier) +{ +} + +static inline bool +pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) +{ + return false; +} + +static inline void set_pnfs_layoutdriver(struct nfs_server *s, + const struct nfs_fh *mntfh, u32 id) +{ +} + +static inline void unset_pnfs_layoutdriver(struct nfs_server *s) +{ +} + +static inline int +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) +{ + return PNFS_NOT_ATTEMPTED; +} + +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + return NULL; +} + +static inline bool +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, u32 ds_commit_idx) +{ + return false; +} + +static inline bool +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) +{ + return false; +} + +static inline int +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) +{ + return 0; +} + +static inline struct nfs_page * +pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo, + struct page *page) +{ + return NULL; +} + +static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync) +{ + return 0; +} + +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return false; +} + +static inline bool +pnfs_layoutcommit_outstanding(struct inode *inode) +{ + return false; +} + + +static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + return NULL; +} + +static inline void nfs4_pnfs_v3_ds_connect_unload(void) +{ +} + +#endif /* CONFIG_NFS_V4_1 */ + +#endif /* FS_NFS_PNFS_H */ diff --git a/kernel/fs/nfs/pnfs_dev.c b/kernel/fs/nfs/pnfs_dev.c new file mode 100644 index 000000000..2961fcd7a --- /dev/null +++ b/kernel/fs/nfs/pnfs_dev.c @@ -0,0 +1,365 @@ +/* + * Device operations for the pnfs client. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * Garth Goodson <Garth.Goodson@netapp.com> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/export.h> +#include <linux/nfs_fs.h> +#include "nfs4session.h" +#include "internal.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS + +/* + * Device ID RCU cache. A device ID is unique per server and layout type. + */ +#define NFS4_DEVICE_ID_HASH_BITS 5 +#define NFS4_DEVICE_ID_HASH_SIZE (1 << NFS4_DEVICE_ID_HASH_BITS) +#define NFS4_DEVICE_ID_HASH_MASK (NFS4_DEVICE_ID_HASH_SIZE - 1) + +#define PNFS_DEVICE_RETRY_TIMEOUT (120*HZ) + +static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE]; +static DEFINE_SPINLOCK(nfs4_deviceid_lock); + +#ifdef NFS_DEBUG +void +nfs4_print_deviceid(const struct nfs4_deviceid *id) +{ + u32 *p = (u32 *)id; + + dprintk("%s: device id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); +} +EXPORT_SYMBOL_GPL(nfs4_print_deviceid); +#endif + +static inline u32 +nfs4_deviceid_hash(const struct nfs4_deviceid *id) +{ + unsigned char *cptr = (unsigned char *)id->data; + unsigned int nbytes = NFS4_DEVICEID4_SIZE; + u32 x = 0; + + while (nbytes--) { + x *= 37; + x += *cptr++; + } + return x & NFS4_DEVICE_ID_HASH_MASK; +} + +static struct nfs4_deviceid_node * +_lookup_deviceid(const struct pnfs_layoutdriver_type *ld, + const struct nfs_client *clp, const struct nfs4_deviceid *id, + long hash) +{ + struct nfs4_deviceid_node *d; + + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) + if (d->ld == ld && d->nfs_client == clp && + !memcmp(&d->deviceid, id, sizeof(*id))) { + if (atomic_read(&d->ref)) + return d; + else + continue; + } + return NULL; +} + +static struct nfs4_deviceid_node * +nfs4_get_device_info(struct nfs_server *server, + const struct nfs4_deviceid *dev_id, + struct rpc_cred *cred, gfp_t gfp_flags) +{ + struct nfs4_deviceid_node *d = NULL; + struct pnfs_device *pdev = NULL; + struct page **pages = NULL; + u32 max_resp_sz; + int max_pages; + int rc, i; + + /* + * Use the session max response size as the basis for setting + * GETDEVICEINFO's maxcount + */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + if (server->pnfs_curr_ld->max_deviceinfo_size && + server->pnfs_curr_ld->max_deviceinfo_size < max_resp_sz) + max_resp_sz = server->pnfs_curr_ld->max_deviceinfo_size; + max_pages = nfs_page_array_len(0, max_resp_sz); + dprintk("%s: server %p max_resp_sz %u max_pages %d\n", + __func__, server, max_resp_sz, max_pages); + + pdev = kzalloc(sizeof(*pdev), gfp_flags); + if (!pdev) + return NULL; + + pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); + if (!pages) + goto out_free_pdev; + + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) + goto out_free_pages; + } + + memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id)); + pdev->layout_type = server->pnfs_curr_ld->id; + pdev->pages = pages; + pdev->pgbase = 0; + pdev->pglen = max_resp_sz; + pdev->mincount = 0; + pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead; + + rc = nfs4_proc_getdeviceinfo(server, pdev, cred); + dprintk("%s getdevice info returns %d\n", __func__, rc); + if (rc) + goto out_free_pages; + + /* + * Found new device, need to decode it and then add it to the + * list of known devices for this mountpoint. + */ + d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev, + gfp_flags); + if (d && pdev->nocache) + set_bit(NFS_DEVICEID_NOCACHE, &d->flags); + +out_free_pages: + for (i = 0; i < max_pages; i++) + __free_page(pages[i]); + kfree(pages); +out_free_pdev: + kfree(pdev); + dprintk("<-- %s d %p\n", __func__, d); + return d; +} + +/* + * Lookup a deviceid in cache and get a reference count on it if found + * + * @clp nfs_client associated with deviceid + * @id deviceid to look up + */ +static struct nfs4_deviceid_node * +__nfs4_find_get_deviceid(struct nfs_server *server, + const struct nfs4_deviceid *id, long hash) +{ + struct nfs4_deviceid_node *d; + + rcu_read_lock(); + d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id, + hash); + if (d != NULL && !atomic_inc_not_zero(&d->ref)) + d = NULL; + rcu_read_unlock(); + return d; +} + +struct nfs4_deviceid_node * +nfs4_find_get_deviceid(struct nfs_server *server, + const struct nfs4_deviceid *id, struct rpc_cred *cred, + gfp_t gfp_mask) +{ + long hash = nfs4_deviceid_hash(id); + struct nfs4_deviceid_node *d, *new; + + d = __nfs4_find_get_deviceid(server, id, hash); + if (d) + return d; + + new = nfs4_get_device_info(server, id, cred, gfp_mask); + if (!new) + return new; + + spin_lock(&nfs4_deviceid_lock); + d = __nfs4_find_get_deviceid(server, id, hash); + if (d) { + spin_unlock(&nfs4_deviceid_lock); + server->pnfs_curr_ld->free_deviceid_node(new); + return d; + } + hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]); + atomic_inc(&new->ref); + spin_unlock(&nfs4_deviceid_lock); + + return new; +} +EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid); + +/* + * Remove a deviceid from cache + * + * @clp nfs_client associated with deviceid + * @id the deviceid to unhash + * + * @ret the unhashed node, if found and dereferenced to zero, NULL otherwise. + */ +void +nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld, + const struct nfs_client *clp, const struct nfs4_deviceid *id) +{ + struct nfs4_deviceid_node *d; + + spin_lock(&nfs4_deviceid_lock); + rcu_read_lock(); + d = _lookup_deviceid(ld, clp, id, nfs4_deviceid_hash(id)); + rcu_read_unlock(); + if (!d) { + spin_unlock(&nfs4_deviceid_lock); + return; + } + hlist_del_init_rcu(&d->node); + clear_bit(NFS_DEVICEID_NOCACHE, &d->flags); + spin_unlock(&nfs4_deviceid_lock); + + /* balance the initial ref set in pnfs_insert_deviceid */ + nfs4_put_deviceid_node(d); +} +EXPORT_SYMBOL_GPL(nfs4_delete_deviceid); + +void +nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, struct nfs_server *server, + const struct nfs4_deviceid *id) +{ + INIT_HLIST_NODE(&d->node); + INIT_HLIST_NODE(&d->tmpnode); + d->ld = server->pnfs_curr_ld; + d->nfs_client = server->nfs_client; + d->flags = 0; + d->deviceid = *id; + atomic_set(&d->ref, 1); +} +EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node); + +/* + * Dereference a deviceid node and delete it when its reference count drops + * to zero. + * + * @d deviceid node to put + * + * return true iff the node was deleted + * Note that since the test for d->ref == 0 is sufficient to establish + * that the node is no longer hashed in the global device id cache. + */ +bool +nfs4_put_deviceid_node(struct nfs4_deviceid_node *d) +{ + if (test_bit(NFS_DEVICEID_NOCACHE, &d->flags)) { + if (atomic_add_unless(&d->ref, -1, 2)) + return false; + nfs4_delete_deviceid(d->ld, d->nfs_client, &d->deviceid); + } + if (!atomic_dec_and_test(&d->ref)) + return false; + d->ld->free_deviceid_node(d); + return true; +} +EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node); + +void +nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node) +{ + node->timestamp_unavailable = jiffies; + set_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); +} +EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_unavailable); + +bool +nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node) +{ + if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) { + unsigned long start, end; + + end = jiffies; + start = end - PNFS_DEVICE_RETRY_TIMEOUT; + if (time_in_range(node->timestamp_unavailable, start, end)) + return true; + clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); + } + return false; +} +EXPORT_SYMBOL_GPL(nfs4_test_deviceid_unavailable); + +static void +_deviceid_purge_client(const struct nfs_client *clp, long hash) +{ + struct nfs4_deviceid_node *d; + HLIST_HEAD(tmp); + + spin_lock(&nfs4_deviceid_lock); + rcu_read_lock(); + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) + if (d->nfs_client == clp && atomic_read(&d->ref)) { + hlist_del_init_rcu(&d->node); + hlist_add_head(&d->tmpnode, &tmp); + clear_bit(NFS_DEVICEID_NOCACHE, &d->flags); + } + rcu_read_unlock(); + spin_unlock(&nfs4_deviceid_lock); + + if (hlist_empty(&tmp)) + return; + + while (!hlist_empty(&tmp)) { + d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode); + hlist_del(&d->tmpnode); + nfs4_put_deviceid_node(d); + } +} + +void +nfs4_deviceid_purge_client(const struct nfs_client *clp) +{ + long h; + + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_MDS)) + return; + for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++) + _deviceid_purge_client(clp, h); +} + +/* + * Stop use of all deviceids associated with an nfs_client + */ +void +nfs4_deviceid_mark_client_invalid(struct nfs_client *clp) +{ + struct nfs4_deviceid_node *d; + int i; + + rcu_read_lock(); + for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){ + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node) + if (d->nfs_client == clp) + set_bit(NFS_DEVICEID_INVALID, &d->flags); + } + rcu_read_unlock(); +} diff --git a/kernel/fs/nfs/pnfs_nfs.c b/kernel/fs/nfs/pnfs_nfs.c new file mode 100644 index 000000000..f37e25b63 --- /dev/null +++ b/kernel/fs/nfs/pnfs_nfs.c @@ -0,0 +1,880 @@ +/* + * Common NFS I/O operations for the pnfs file based + * layout drivers. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tom Haynes <loghyr@primarydata.com> + */ + +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/sunrpc/addr.h> +#include <linux/module.h> + +#include "nfs4session.h" +#include "internal.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS + +void pnfs_generic_rw_release(void *data) +{ + struct nfs_pgio_header *hdr = data; + + nfs_put_client(hdr->ds_clp); + hdr->mds_ops->rpc_release(data); +} +EXPORT_SYMBOL_GPL(pnfs_generic_rw_release); + +/* Fake up some data that will cause nfs_commit_release to retry the writes. */ +void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data) +{ + struct nfs_page *first = nfs_list_entry(data->pages.next); + + data->task.tk_status = 0; + memcpy(&data->verf.verifier, &first->wb_verf, + sizeof(data->verf.verifier)); + data->verf.verifier.data[0]++; /* ensure verifier mismatch */ +} +EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes); + +void pnfs_generic_write_commit_done(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + /* Note this may cause RPC to be resent */ + wdata->mds_ops->rpc_call_done(task, data); +} +EXPORT_SYMBOL_GPL(pnfs_generic_write_commit_done); + +void pnfs_generic_commit_release(void *calldata) +{ + struct nfs_commit_data *data = calldata; + + data->completion_ops->completion(data); + pnfs_put_lseg(data->lseg); + nfs_put_client(data->ds_clp); + nfs_commitdata_release(data); +} +EXPORT_SYMBOL_GPL(pnfs_generic_commit_release); + +/* The generic layer is about to remove the req from the commit list. + * If this will make the bucket empty, it will need to put the lseg reference. + * Note this must be called holding the inode (/cinfo) lock + */ +void +pnfs_generic_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo) +{ + struct pnfs_layout_segment *freeme = NULL; + + if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) + goto out; + cinfo->ds->nwritten--; + if (list_is_singular(&req->wb_list)) { + struct pnfs_commit_bucket *bucket; + + bucket = list_first_entry(&req->wb_list, + struct pnfs_commit_bucket, + written); + freeme = bucket->wlseg; + bucket->wlseg = NULL; + } +out: + nfs_request_remove_commit_list(req, cinfo); + pnfs_put_lseg_locked(freeme); +} +EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit); + +static int +pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) +{ + struct nfs_page *req, *tmp; + int ret = 0; + + list_for_each_entry_safe(req, tmp, src, wb_list) { + if (!nfs_lock_request(req)) + continue; + kref_get(&req->wb_kref); + if (cond_resched_lock(cinfo->lock)) + list_safe_reset_next(req, tmp, wb_list); + nfs_request_remove_commit_list(req, cinfo); + clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); + nfs_list_add_request(req, dst); + ret++; + if ((ret == max) && !cinfo->dreq) + break; + } + return ret; +} + +static int +pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, + struct nfs_commit_info *cinfo, + int max) +{ + struct list_head *src = &bucket->written; + struct list_head *dst = &bucket->committing; + int ret; + + lockdep_assert_held(cinfo->lock); + ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max); + if (ret) { + cinfo->ds->nwritten -= ret; + cinfo->ds->ncommitting += ret; + bucket->clseg = bucket->wlseg; + if (list_empty(src)) + bucket->wlseg = NULL; + else + pnfs_get_lseg(bucket->clseg); + } + return ret; +} + +/* Move reqs from written to committing lists, returning count + * of number moved. + */ +int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, + int max) +{ + int i, rv = 0, cnt; + + lockdep_assert_held(cinfo->lock); + for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { + cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i], + cinfo, max); + max -= cnt; + rv += cnt; + } + return rv; +} +EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists); + +/* Pull everything off the committing lists and dump into @dst. */ +void pnfs_generic_recover_commit_reqs(struct list_head *dst, + struct nfs_commit_info *cinfo) +{ + struct pnfs_commit_bucket *b; + struct pnfs_layout_segment *freeme; + int i; + + lockdep_assert_held(cinfo->lock); +restart: + for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { + if (pnfs_generic_transfer_commit_list(&b->written, dst, + cinfo, 0)) { + freeme = b->wlseg; + b->wlseg = NULL; + spin_unlock(cinfo->lock); + pnfs_put_lseg(freeme); + spin_lock(cinfo->lock); + goto restart; + } + } + cinfo->ds->nwritten = 0; +} +EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs); + +static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx) +{ + struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; + struct pnfs_commit_bucket *bucket; + struct pnfs_layout_segment *freeme; + int i; + + for (i = idx; i < fl_cinfo->nbuckets; i++) { + bucket = &fl_cinfo->buckets[i]; + if (list_empty(&bucket->committing)) + continue; + nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo, i); + spin_lock(cinfo->lock); + freeme = bucket->clseg; + bucket->clseg = NULL; + spin_unlock(cinfo->lock); + pnfs_put_lseg(freeme); + } +} + +static unsigned int +pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo, + struct list_head *list) +{ + struct pnfs_ds_commit_info *fl_cinfo; + struct pnfs_commit_bucket *bucket; + struct nfs_commit_data *data; + int i; + unsigned int nreq = 0; + + fl_cinfo = cinfo->ds; + bucket = fl_cinfo->buckets; + for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { + if (list_empty(&bucket->committing)) + continue; + data = nfs_commitdata_alloc(); + if (!data) + break; + data->ds_commit_index = i; + spin_lock(cinfo->lock); + data->lseg = bucket->clseg; + bucket->clseg = NULL; + spin_unlock(cinfo->lock); + list_add(&data->pages, list); + nreq++; + } + + /* Clean up on error */ + pnfs_generic_retry_commit(cinfo, i); + return nreq; +} + +/* This follows nfs_commit_list pretty closely */ +int +pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how, struct nfs_commit_info *cinfo, + int (*initiate_commit)(struct nfs_commit_data *data, + int how)) +{ + struct nfs_commit_data *data, *tmp; + LIST_HEAD(list); + unsigned int nreq = 0; + + if (!list_empty(mds_pages)) { + data = nfs_commitdata_alloc(); + if (data != NULL) { + data->lseg = NULL; + list_add(&data->pages, &list); + nreq++; + } else { + nfs_retry_commit(mds_pages, NULL, cinfo, 0); + pnfs_generic_retry_commit(cinfo, 0); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); + return -ENOMEM; + } + } + + nreq += pnfs_generic_alloc_ds_commits(cinfo, &list); + + if (nreq == 0) { + cinfo->completion_ops->error_cleanup(NFS_I(inode)); + goto out; + } + + atomic_add(nreq, &cinfo->mds->rpcs_out); + + list_for_each_entry_safe(data, tmp, &list, pages) { + list_del_init(&data->pages); + if (!data->lseg) { + nfs_init_commit(data, mds_pages, NULL, cinfo); + nfs_initiate_commit(NFS_CLIENT(inode), data, + NFS_PROTO(data->inode), + data->mds_ops, how, 0); + } else { + struct pnfs_commit_bucket *buckets; + + buckets = cinfo->ds->buckets; + nfs_init_commit(data, + &buckets[data->ds_commit_index].committing, + data->lseg, + cinfo); + initiate_commit(data, how); + } + } +out: + cinfo->ds->ncommitting = 0; + return PNFS_ATTEMPTED; +} +EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist); + +/* + * Data server cache + * + * Data servers can be mapped to different device ids. + * nfs4_pnfs_ds reference counting + * - set to 1 on allocation + * - incremented when a device id maps a data server already in the cache. + * - decremented when deviceid is removed from the cache. + */ +static DEFINE_SPINLOCK(nfs4_ds_cache_lock); +static LIST_HEAD(nfs4_data_server_cache); + +/* Debug routines */ +static void +print_ds(struct nfs4_pnfs_ds *ds) +{ + if (ds == NULL) { + printk(KERN_WARNING "%s NULL device\n", __func__); + return; + } + printk(KERN_WARNING " ds %s\n" + " ref count %d\n" + " client %p\n" + " cl_exchange_flags %x\n", + ds->ds_remotestr, + atomic_read(&ds->ds_count), ds->ds_clp, + ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0); +} + +static bool +same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2) +{ + struct sockaddr_in *a, *b; + struct sockaddr_in6 *a6, *b6; + + if (addr1->sa_family != addr2->sa_family) + return false; + + switch (addr1->sa_family) { + case AF_INET: + a = (struct sockaddr_in *)addr1; + b = (struct sockaddr_in *)addr2; + + if (a->sin_addr.s_addr == b->sin_addr.s_addr && + a->sin_port == b->sin_port) + return true; + break; + + case AF_INET6: + a6 = (struct sockaddr_in6 *)addr1; + b6 = (struct sockaddr_in6 *)addr2; + + /* LINKLOCAL addresses must have matching scope_id */ + if (ipv6_addr_src_scope(&a6->sin6_addr) == + IPV6_ADDR_SCOPE_LINKLOCAL && + a6->sin6_scope_id != b6->sin6_scope_id) + return false; + + if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) && + a6->sin6_port == b6->sin6_port) + return true; + break; + + default: + dprintk("%s: unhandled address family: %u\n", + __func__, addr1->sa_family); + return false; + } + + return false; +} + +static bool +_same_data_server_addrs_locked(const struct list_head *dsaddrs1, + const struct list_head *dsaddrs2) +{ + struct nfs4_pnfs_ds_addr *da1, *da2; + + /* step through both lists, comparing as we go */ + for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node), + da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node); + da1 != NULL && da2 != NULL; + da1 = list_entry(da1->da_node.next, typeof(*da1), da_node), + da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) { + if (!same_sockaddr((struct sockaddr *)&da1->da_addr, + (struct sockaddr *)&da2->da_addr)) + return false; + } + if (da1 == NULL && da2 == NULL) + return true; + + return false; +} + +/* + * Lookup DS by addresses. nfs4_ds_cache_lock is held + */ +static struct nfs4_pnfs_ds * +_data_server_lookup_locked(const struct list_head *dsaddrs) +{ + struct nfs4_pnfs_ds *ds; + + list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) + if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) + return ds; + return NULL; +} + +static void destroy_ds(struct nfs4_pnfs_ds *ds) +{ + struct nfs4_pnfs_ds_addr *da; + + dprintk("--> %s\n", __func__); + ifdebug(FACILITY) + print_ds(ds); + + nfs_put_client(ds->ds_clp); + + while (!list_empty(&ds->ds_addrs)) { + da = list_first_entry(&ds->ds_addrs, + struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + kfree(ds->ds_remotestr); + kfree(ds); +} + +void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds) +{ + if (atomic_dec_and_lock(&ds->ds_count, + &nfs4_ds_cache_lock)) { + list_del_init(&ds->ds_node); + spin_unlock(&nfs4_ds_cache_lock); + destroy_ds(ds); + } +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_put); + +/* + * Create a string with a human readable address and port to avoid + * complicated setup around many dprinks. + */ +static char * +nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags) +{ + struct nfs4_pnfs_ds_addr *da; + char *remotestr; + size_t len; + char *p; + + len = 3; /* '{', '}' and eol */ + list_for_each_entry(da, dsaddrs, da_node) { + len += strlen(da->da_remotestr) + 1; /* string plus comma */ + } + + remotestr = kzalloc(len, gfp_flags); + if (!remotestr) + return NULL; + + p = remotestr; + *(p++) = '{'; + len--; + list_for_each_entry(da, dsaddrs, da_node) { + size_t ll = strlen(da->da_remotestr); + + if (ll > len) + goto out_err; + + memcpy(p, da->da_remotestr, ll); + p += ll; + len -= ll; + + if (len < 1) + goto out_err; + (*p++) = ','; + len--; + } + if (len < 2) + goto out_err; + *(p++) = '}'; + *p = '\0'; + return remotestr; +out_err: + kfree(remotestr); + return NULL; +} + +/* + * Given a list of multipath struct nfs4_pnfs_ds_addr, add it to ds cache if + * uncached and return cached struct nfs4_pnfs_ds. + */ +struct nfs4_pnfs_ds * +nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) +{ + struct nfs4_pnfs_ds *tmp_ds, *ds = NULL; + char *remotestr; + + if (list_empty(dsaddrs)) { + dprintk("%s: no addresses defined\n", __func__); + goto out; + } + + ds = kzalloc(sizeof(*ds), gfp_flags); + if (!ds) + goto out; + + /* this is only used for debugging, so it's ok if its NULL */ + remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags); + + spin_lock(&nfs4_ds_cache_lock); + tmp_ds = _data_server_lookup_locked(dsaddrs); + if (tmp_ds == NULL) { + INIT_LIST_HEAD(&ds->ds_addrs); + list_splice_init(dsaddrs, &ds->ds_addrs); + ds->ds_remotestr = remotestr; + atomic_set(&ds->ds_count, 1); + INIT_LIST_HEAD(&ds->ds_node); + ds->ds_clp = NULL; + list_add(&ds->ds_node, &nfs4_data_server_cache); + dprintk("%s add new data server %s\n", __func__, + ds->ds_remotestr); + } else { + kfree(remotestr); + kfree(ds); + atomic_inc(&tmp_ds->ds_count); + dprintk("%s data server %s found, inc'ed ds_count to %d\n", + __func__, tmp_ds->ds_remotestr, + atomic_read(&tmp_ds->ds_count)); + ds = tmp_ds; + } + spin_unlock(&nfs4_ds_cache_lock); +out: + return ds; +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add); + +static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) +{ + might_sleep(); + wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, + TASK_KILLABLE); +} + +static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) +{ + smp_mb__before_atomic(); + clear_bit(NFS4DS_CONNECTING, &ds->ds_state); + smp_mb__after_atomic(); + wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING); +} + +static struct nfs_client *(*get_v3_ds_connect)( + struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, + int ds_addrlen, + int ds_proto, + unsigned int ds_timeo, + unsigned int ds_retrans, + rpc_authflavor_t au_flavor); + +static bool load_v3_ds_connect(void) +{ + if (!get_v3_ds_connect) { + get_v3_ds_connect = symbol_request(nfs3_set_ds_client); + WARN_ON_ONCE(!get_v3_ds_connect); + } + + return(get_v3_ds_connect != NULL); +} + +void nfs4_pnfs_v3_ds_connect_unload(void) +{ + if (get_v3_ds_connect) { + symbol_put(nfs3_set_ds_client); + get_v3_ds_connect = NULL; + } +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload); + +static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, + struct nfs4_pnfs_ds *ds, + unsigned int timeo, + unsigned int retrans, + rpc_authflavor_t au_flavor) +{ + struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs4_pnfs_ds_addr *da; + int status = 0; + + dprintk("--> %s DS %s au_flavor %d\n", __func__, + ds->ds_remotestr, au_flavor); + + if (!load_v3_ds_connect()) + goto out; + + list_for_each_entry(da, &ds->ds_addrs, da_node) { + dprintk("%s: DS %s: trying address %s\n", + __func__, ds->ds_remotestr, da->da_remotestr); + + clp = get_v3_ds_connect(mds_srv->nfs_client, + (struct sockaddr *)&da->da_addr, + da->da_addrlen, IPPROTO_TCP, + timeo, retrans, au_flavor); + if (!IS_ERR(clp)) + break; + } + + if (IS_ERR(clp)) { + status = PTR_ERR(clp); + goto out; + } + + smp_wmb(); + ds->ds_clp = clp; + dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); +out: + return status; +} + +static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, + struct nfs4_pnfs_ds *ds, + unsigned int timeo, + unsigned int retrans, + u32 minor_version, + rpc_authflavor_t au_flavor) +{ + struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs4_pnfs_ds_addr *da; + int status = 0; + + dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr, + au_flavor); + + list_for_each_entry(da, &ds->ds_addrs, da_node) { + dprintk("%s: DS %s: trying address %s\n", + __func__, ds->ds_remotestr, da->da_remotestr); + + clp = nfs4_set_ds_client(mds_srv->nfs_client, + (struct sockaddr *)&da->da_addr, + da->da_addrlen, IPPROTO_TCP, + timeo, retrans, minor_version, + au_flavor); + if (!IS_ERR(clp)) + break; + } + + if (IS_ERR(clp)) { + status = PTR_ERR(clp); + goto out; + } + + status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time); + if (status) + goto out_put; + + smp_wmb(); + ds->ds_clp = clp; + dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); +out: + return status; +out_put: + nfs_put_client(clp); + goto out; +} + +/* + * Create an rpc connection to the nfs4_pnfs_ds data server. + * Currently only supports IPv4 and IPv6 addresses. + * If connection fails, make devid unavailable. + */ +void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, + struct nfs4_deviceid_node *devid, unsigned int timeo, + unsigned int retrans, u32 version, + u32 minor_version, rpc_authflavor_t au_flavor) +{ + if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { + int err = 0; + + if (version == 3) { + err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, + retrans, au_flavor); + } else if (version == 4) { + err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo, + retrans, minor_version, + au_flavor); + } else { + dprintk("%s: unsupported DS version %d\n", __func__, + version); + err = -EPROTONOSUPPORT; + } + + if (err) + nfs4_mark_deviceid_unavailable(devid); + nfs4_clear_ds_conn_bit(ds); + } else { + nfs4_wait_ds_connect(ds); + } +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect); + +/* + * Currently only supports ipv4, ipv6 and one multi-path address. + */ +struct nfs4_pnfs_ds_addr * +nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags) +{ + struct nfs4_pnfs_ds_addr *da = NULL; + char *buf, *portstr; + __be16 port; + int nlen, rlen; + int tmp[2]; + __be32 *p; + char *netid, *match_netid; + size_t len, match_netid_len; + char *startsep = ""; + char *endsep = ""; + + + /* r_netid */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_err; + nlen = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, nlen); + if (unlikely(!p)) + goto out_err; + + netid = kmalloc(nlen+1, gfp_flags); + if (unlikely(!netid)) + goto out_err; + + netid[nlen] = '\0'; + memcpy(netid, p, nlen); + + /* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_free_netid; + rlen = be32_to_cpup(p); + + p = xdr_inline_decode(xdr, rlen); + if (unlikely(!p)) + goto out_free_netid; + + /* port is ".ABC.DEF", 8 chars max */ + if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) { + dprintk("%s: Invalid address, length %d\n", __func__, + rlen); + goto out_free_netid; + } + buf = kmalloc(rlen + 1, gfp_flags); + if (!buf) { + dprintk("%s: Not enough memory\n", __func__); + goto out_free_netid; + } + buf[rlen] = '\0'; + memcpy(buf, p, rlen); + + /* replace port '.' with '-' */ + portstr = strrchr(buf, '.'); + if (!portstr) { + dprintk("%s: Failed finding expected dot in port\n", + __func__); + goto out_free_buf; + } + *portstr = '-'; + + /* find '.' between address and port */ + portstr = strrchr(buf, '.'); + if (!portstr) { + dprintk("%s: Failed finding expected dot between address and " + "port\n", __func__); + goto out_free_buf; + } + *portstr = '\0'; + + da = kzalloc(sizeof(*da), gfp_flags); + if (unlikely(!da)) + goto out_free_buf; + + INIT_LIST_HEAD(&da->da_node); + + if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr, + sizeof(da->da_addr))) { + dprintk("%s: error parsing address %s\n", __func__, buf); + goto out_free_da; + } + + portstr++; + sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]); + port = htons((tmp[0] << 8) | (tmp[1])); + + switch (da->da_addr.ss_family) { + case AF_INET: + ((struct sockaddr_in *)&da->da_addr)->sin_port = port; + da->da_addrlen = sizeof(struct sockaddr_in); + match_netid = "tcp"; + match_netid_len = 3; + break; + + case AF_INET6: + ((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port; + da->da_addrlen = sizeof(struct sockaddr_in6); + match_netid = "tcp6"; + match_netid_len = 4; + startsep = "["; + endsep = "]"; + break; + + default: + dprintk("%s: unsupported address family: %u\n", + __func__, da->da_addr.ss_family); + goto out_free_da; + } + + if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) { + dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n", + __func__, netid, match_netid); + goto out_free_da; + } + + /* save human readable address */ + len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7; + da->da_remotestr = kzalloc(len, gfp_flags); + + /* NULL is ok, only used for dprintk */ + if (da->da_remotestr) + snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep, + buf, endsep, ntohs(port)); + + dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr); + kfree(buf); + kfree(netid); + return da; + +out_free_da: + kfree(da); +out_free_buf: + dprintk("%s: Error parsing DS addr: %s\n", __func__, buf); + kfree(buf); +out_free_netid: + kfree(netid); +out_err: + return NULL; +} +EXPORT_SYMBOL_GPL(nfs4_decode_mp_ds_addr); + +void +pnfs_layout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) +{ + struct list_head *list; + struct pnfs_commit_bucket *buckets; + + spin_lock(cinfo->lock); + buckets = cinfo->ds->buckets; + list = &buckets[ds_commit_idx].written; + if (list_empty(list)) { + /* Non-empty buckets hold a reference on the lseg. That ref + * is normally transferred to the COMMIT call and released + * there. It could also be released if the last req is pulled + * off due to a rewrite, in which case it will be done in + * pnfs_common_clear_request_commit + */ + WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL); + buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg); + } + set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; + spin_unlock(cinfo->lock); + + nfs_request_add_commit_list(req, list, cinfo); +} +EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit); + +int +pnfs_nfs_generic_sync(struct inode *inode, bool datasync) +{ + if (datasync) + return 0; + return pnfs_layoutcommit_inode(inode, true); +} +EXPORT_SYMBOL_GPL(pnfs_nfs_generic_sync); + diff --git a/kernel/fs/nfs/proc.c b/kernel/fs/nfs/proc.c new file mode 100644 index 000000000..b417bbcd9 --- /dev/null +++ b/kernel/fs/nfs/proc.c @@ -0,0 +1,749 @@ +/* + * linux/fs/nfs/proc.c + * + * Copyright (C) 1992, 1993, 1994 Rick Sladkey + * + * OS-independent nfs remote procedure call functions + * + * Tuned by Alan Cox <A.Cox@swansea.ac.uk> for >3K buffers + * so at last we can have decent(ish) throughput off a + * Sun server. + * + * Coding optimized and cleaned up by Florian La Roche. + * Note: Error returns are optimized for NFS_OK, which isn't translated via + * nfs_stat_to_errno(), but happens to be already the right return code. + * + * Also, the code currently doesn't check the size of the packet, when + * it decodes the packet. + * + * Feel free to fix it and mail me the diffs if it worries you. + * + * Completely rewritten to support the new RPC call interface; + * rewrote and moved the entire XDR stuff to xdr.c + * --Olaf Kirch June 1996 + * + * The code below initializes all auto variables explicitly, otherwise + * it will fail to work as a module (gcc generates a memset call for an + * incomplete struct). + */ + +#include <linux/types.h> +#include <linux/param.h> +#include <linux/time.h> +#include <linux/mm.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/pagemap.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs2.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/lockd/bind.h> +#include <linux/freezer.h> +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_PROC + +/* + * Bare-bones access to getattr: this is for nfs_read_super. + */ +static int +nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + struct nfs_fattr *fattr = info->fattr; + struct nfs2_fsstat fsinfo; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_GETATTR], + .rpc_argp = fhandle, + .rpc_resp = fattr, + }; + int status; + + dprintk("%s: call getattr\n", __func__); + nfs_fattr_init(fattr); + status = rpc_call_sync(server->client, &msg, 0); + /* Retry with default authentication if different */ + if (status && server->nfs_client->cl_rpcclient != server->client) + status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0); + dprintk("%s: reply getattr: %d\n", __func__, status); + if (status) + return status; + dprintk("%s: call statfs\n", __func__); + msg.rpc_proc = &nfs_procedures[NFSPROC_STATFS]; + msg.rpc_resp = &fsinfo; + status = rpc_call_sync(server->client, &msg, 0); + /* Retry with default authentication if different */ + if (status && server->nfs_client->cl_rpcclient != server->client) + status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0); + dprintk("%s: reply statfs: %d\n", __func__, status); + if (status) + return status; + info->rtmax = NFS_MAXDATA; + info->rtpref = fsinfo.tsize; + info->rtmult = fsinfo.bsize; + info->wtmax = NFS_MAXDATA; + info->wtpref = fsinfo.tsize; + info->wtmult = fsinfo.bsize; + info->dtpref = fsinfo.tsize; + info->maxfilesize = 0x7FFFFFFF; + info->lease_time = 0; + return 0; +} + +/* + * One function for each procedure in the NFS protocol. + */ +static int +nfs_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_GETATTR], + .rpc_argp = fhandle, + .rpc_resp = fattr, + }; + int status; + + dprintk("NFS call getattr\n"); + nfs_fattr_init(fattr); + status = rpc_call_sync(server->client, &msg, 0); + dprintk("NFS reply getattr: %d\n", status); + return status; +} + +static int +nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, + struct iattr *sattr) +{ + struct inode *inode = d_inode(dentry); + struct nfs_sattrargs arg = { + .fh = NFS_FH(inode), + .sattr = sattr + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_SETATTR], + .rpc_argp = &arg, + .rpc_resp = fattr, + }; + int status; + + /* Mask out the non-modebit related stuff from attr->ia_mode */ + sattr->ia_mode &= S_IALLUGO; + + dprintk("NFS call setattr\n"); + if (sattr->ia_valid & ATTR_FILE) + msg.rpc_cred = nfs_file_cred(sattr->ia_file); + nfs_fattr_init(fattr); + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + if (status == 0) + nfs_setattr_update_inode(inode, sattr, fattr); + dprintk("NFS reply setattr: %d\n", status); + return status; +} + +static int +nfs_proc_lookup(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + struct nfs_diropargs arg = { + .fh = NFS_FH(dir), + .name = name->name, + .len = name->len + }; + struct nfs_diropok res = { + .fh = fhandle, + .fattr = fattr + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_LOOKUP], + .rpc_argp = &arg, + .rpc_resp = &res, + }; + int status; + + dprintk("NFS call lookup %s\n", name->name); + nfs_fattr_init(fattr); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + dprintk("NFS reply lookup: %d\n", status); + return status; +} + +static int nfs_proc_readlink(struct inode *inode, struct page *page, + unsigned int pgbase, unsigned int pglen) +{ + struct nfs_readlinkargs args = { + .fh = NFS_FH(inode), + .pgbase = pgbase, + .pglen = pglen, + .pages = &page + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_READLINK], + .rpc_argp = &args, + }; + int status; + + dprintk("NFS call readlink\n"); + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + dprintk("NFS reply readlink: %d\n", status); + return status; +} + +struct nfs_createdata { + struct nfs_createargs arg; + struct nfs_diropok res; + struct nfs_fh fhandle; + struct nfs_fattr fattr; +}; + +static struct nfs_createdata *nfs_alloc_createdata(struct inode *dir, + struct dentry *dentry, struct iattr *sattr) +{ + struct nfs_createdata *data; + + data = kmalloc(sizeof(*data), GFP_KERNEL); + + if (data != NULL) { + data->arg.fh = NFS_FH(dir); + data->arg.name = dentry->d_name.name; + data->arg.len = dentry->d_name.len; + data->arg.sattr = sattr; + nfs_fattr_init(&data->fattr); + data->fhandle.size = 0; + data->res.fh = &data->fhandle; + data->res.fattr = &data->fattr; + } + return data; +}; + +static void nfs_free_createdata(const struct nfs_createdata *data) +{ + kfree(data); +} + +static int +nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, + int flags) +{ + struct nfs_createdata *data; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_CREATE], + }; + int status = -ENOMEM; + + dprintk("NFS call create %pd\n", dentry); + data = nfs_alloc_createdata(dir, dentry, sattr); + if (data == NULL) + goto out; + msg.rpc_argp = &data->arg; + msg.rpc_resp = &data->res; + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_mark_for_revalidate(dir); + if (status == 0) + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + nfs_free_createdata(data); +out: + dprintk("NFS reply create: %d\n", status); + return status; +} + +/* + * In NFSv2, mknod is grafted onto the create call. + */ +static int +nfs_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, + dev_t rdev) +{ + struct nfs_createdata *data; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_CREATE], + }; + umode_t mode; + int status = -ENOMEM; + + dprintk("NFS call mknod %pd\n", dentry); + + mode = sattr->ia_mode; + if (S_ISFIFO(mode)) { + sattr->ia_mode = (mode & ~S_IFMT) | S_IFCHR; + sattr->ia_valid &= ~ATTR_SIZE; + } else if (S_ISCHR(mode) || S_ISBLK(mode)) { + sattr->ia_valid |= ATTR_SIZE; + sattr->ia_size = new_encode_dev(rdev);/* get out your barf bag */ + } + + data = nfs_alloc_createdata(dir, dentry, sattr); + if (data == NULL) + goto out; + msg.rpc_argp = &data->arg; + msg.rpc_resp = &data->res; + + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_mark_for_revalidate(dir); + + if (status == -EINVAL && S_ISFIFO(mode)) { + sattr->ia_mode = mode; + nfs_fattr_init(data->res.fattr); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + } + if (status == 0) + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + nfs_free_createdata(data); +out: + dprintk("NFS reply mknod: %d\n", status); + return status; +} + +static int +nfs_proc_remove(struct inode *dir, struct qstr *name) +{ + struct nfs_removeargs arg = { + .fh = NFS_FH(dir), + .name = *name, + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_REMOVE], + .rpc_argp = &arg, + }; + int status; + + dprintk("NFS call remove %s\n", name->name); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_mark_for_revalidate(dir); + + dprintk("NFS reply remove: %d\n", status); + return status; +} + +static void +nfs_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) +{ + msg->rpc_proc = &nfs_procedures[NFSPROC_REMOVE]; +} + +static void nfs_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) +{ + rpc_call_start(task); +} + +static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir) +{ + nfs_mark_for_revalidate(dir); + return 1; +} + +static void +nfs_proc_rename_setup(struct rpc_message *msg, struct inode *dir) +{ + msg->rpc_proc = &nfs_procedures[NFSPROC_RENAME]; +} + +static void nfs_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data) +{ + rpc_call_start(task); +} + +static int +nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir, + struct inode *new_dir) +{ + nfs_mark_for_revalidate(old_dir); + nfs_mark_for_revalidate(new_dir); + return 1; +} + +static int +nfs_proc_link(struct inode *inode, struct inode *dir, struct qstr *name) +{ + struct nfs_linkargs arg = { + .fromfh = NFS_FH(inode), + .tofh = NFS_FH(dir), + .toname = name->name, + .tolen = name->len + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_LINK], + .rpc_argp = &arg, + }; + int status; + + dprintk("NFS call link %s\n", name->name); + status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); + nfs_mark_for_revalidate(inode); + nfs_mark_for_revalidate(dir); + dprintk("NFS reply link: %d\n", status); + return status; +} + +static int +nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, + unsigned int len, struct iattr *sattr) +{ + struct nfs_fh *fh; + struct nfs_fattr *fattr; + struct nfs_symlinkargs arg = { + .fromfh = NFS_FH(dir), + .fromname = dentry->d_name.name, + .fromlen = dentry->d_name.len, + .pages = &page, + .pathlen = len, + .sattr = sattr + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_SYMLINK], + .rpc_argp = &arg, + }; + int status = -ENAMETOOLONG; + + dprintk("NFS call symlink %pd\n", dentry); + + if (len > NFS2_MAXPATHLEN) + goto out; + + fh = nfs_alloc_fhandle(); + fattr = nfs_alloc_fattr(); + status = -ENOMEM; + if (fh == NULL || fattr == NULL) + goto out_free; + + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_mark_for_revalidate(dir); + + /* + * V2 SYMLINK requests don't return any attributes. Setting the + * filehandle size to zero indicates to nfs_instantiate that it + * should fill in the data with a LOOKUP call on the wire. + */ + if (status == 0) + status = nfs_instantiate(dentry, fh, fattr, NULL); + +out_free: + nfs_free_fattr(fattr); + nfs_free_fhandle(fh); +out: + dprintk("NFS reply symlink: %d\n", status); + return status; +} + +static int +nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) +{ + struct nfs_createdata *data; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_MKDIR], + }; + int status = -ENOMEM; + + dprintk("NFS call mkdir %pd\n", dentry); + data = nfs_alloc_createdata(dir, dentry, sattr); + if (data == NULL) + goto out; + msg.rpc_argp = &data->arg; + msg.rpc_resp = &data->res; + + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_mark_for_revalidate(dir); + if (status == 0) + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + nfs_free_createdata(data); +out: + dprintk("NFS reply mkdir: %d\n", status); + return status; +} + +static int +nfs_proc_rmdir(struct inode *dir, struct qstr *name) +{ + struct nfs_diropargs arg = { + .fh = NFS_FH(dir), + .name = name->name, + .len = name->len + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_RMDIR], + .rpc_argp = &arg, + }; + int status; + + dprintk("NFS call rmdir %s\n", name->name); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + nfs_mark_for_revalidate(dir); + dprintk("NFS reply rmdir: %d\n", status); + return status; +} + +/* + * The READDIR implementation is somewhat hackish - we pass a temporary + * buffer to the encode function, which installs it in the receive + * the receive iovec. The decode function just parses the reply to make + * sure it is syntactically correct; the entries itself are decoded + * from nfs_readdir by calling the decode_entry function directly. + */ +static int +nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, + u64 cookie, struct page **pages, unsigned int count, int plus) +{ + struct inode *dir = d_inode(dentry); + struct nfs_readdirargs arg = { + .fh = NFS_FH(dir), + .cookie = cookie, + .count = count, + .pages = pages, + }; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_READDIR], + .rpc_argp = &arg, + .rpc_cred = cred, + }; + int status; + + dprintk("NFS call readdir %d\n", (unsigned int)cookie); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + + nfs_invalidate_atime(dir); + + dprintk("NFS reply readdir: %d\n", status); + return status; +} + +static int +nfs_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsstat *stat) +{ + struct nfs2_fsstat fsinfo; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_STATFS], + .rpc_argp = fhandle, + .rpc_resp = &fsinfo, + }; + int status; + + dprintk("NFS call statfs\n"); + nfs_fattr_init(stat->fattr); + status = rpc_call_sync(server->client, &msg, 0); + dprintk("NFS reply statfs: %d\n", status); + if (status) + goto out; + stat->tbytes = (u64)fsinfo.blocks * fsinfo.bsize; + stat->fbytes = (u64)fsinfo.bfree * fsinfo.bsize; + stat->abytes = (u64)fsinfo.bavail * fsinfo.bsize; + stat->tfiles = 0; + stat->ffiles = 0; + stat->afiles = 0; +out: + return status; +} + +static int +nfs_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) +{ + struct nfs2_fsstat fsinfo; + struct rpc_message msg = { + .rpc_proc = &nfs_procedures[NFSPROC_STATFS], + .rpc_argp = fhandle, + .rpc_resp = &fsinfo, + }; + int status; + + dprintk("NFS call fsinfo\n"); + nfs_fattr_init(info->fattr); + status = rpc_call_sync(server->client, &msg, 0); + dprintk("NFS reply fsinfo: %d\n", status); + if (status) + goto out; + info->rtmax = NFS_MAXDATA; + info->rtpref = fsinfo.tsize; + info->rtmult = fsinfo.bsize; + info->wtmax = NFS_MAXDATA; + info->wtpref = fsinfo.tsize; + info->wtmult = fsinfo.bsize; + info->dtpref = fsinfo.tsize; + info->maxfilesize = 0x7FFFFFFF; + info->lease_time = 0; +out: + return status; +} + +static int +nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_pathconf *info) +{ + info->max_link = 0; + info->max_namelen = NFS2_MAXNAMLEN; + return 0; +} + +static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + struct inode *inode = hdr->inode; + + nfs_invalidate_atime(inode); + if (task->tk_status >= 0) { + nfs_refresh_inode(inode, hdr->res.fattr); + /* Emulate the eof flag, which isn't normally needed in NFSv2 + * as it is guaranteed to always return the file attributes + */ + if (hdr->args.offset + hdr->res.count >= hdr->res.fattr->size) + hdr->res.eof = 1; + } + return 0; +} + +static void nfs_proc_read_setup(struct nfs_pgio_header *hdr, + struct rpc_message *msg) +{ + msg->rpc_proc = &nfs_procedures[NFSPROC_READ]; +} + +static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + rpc_call_start(task); + return 0; +} + +static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + if (task->tk_status >= 0) + nfs_writeback_update_inode(hdr); + return 0; +} + +static void nfs_proc_write_setup(struct nfs_pgio_header *hdr, + struct rpc_message *msg) +{ + /* Note: NFSv2 ignores @stable and always uses NFS_FILE_SYNC */ + hdr->args.stable = NFS_FILE_SYNC; + msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE]; +} + +static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) +{ + BUG(); +} + +static void +nfs_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg) +{ + BUG(); +} + +static int +nfs_proc_lock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = file_inode(filp); + + return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl); +} + +/* Helper functions for NFS lock bounds checking */ +#define NFS_LOCK32_OFFSET_MAX ((__s32)0x7fffffffUL) +static int nfs_lock_check_bounds(const struct file_lock *fl) +{ + __s32 start, end; + + start = (__s32)fl->fl_start; + if ((loff_t)start != fl->fl_start) + goto out_einval; + + if (fl->fl_end != OFFSET_MAX) { + end = (__s32)fl->fl_end; + if ((loff_t)end != fl->fl_end) + goto out_einval; + } else + end = NFS_LOCK32_OFFSET_MAX; + + if (start < 0 || start > end) + goto out_einval; + return 0; +out_einval: + return -EINVAL; +} + +static int nfs_have_delegation(struct inode *inode, fmode_t flags) +{ + return 0; +} + +static int nfs_return_delegation(struct inode *inode) +{ + nfs_wb_all(inode); + return 0; +} + +static const struct inode_operations nfs_dir_inode_operations = { + .create = nfs_create, + .lookup = nfs_lookup, + .link = nfs_link, + .unlink = nfs_unlink, + .symlink = nfs_symlink, + .mkdir = nfs_mkdir, + .rmdir = nfs_rmdir, + .mknod = nfs_mknod, + .rename = nfs_rename, + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +}; + +static const struct inode_operations nfs_file_inode_operations = { + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +}; + +const struct nfs_rpc_ops nfs_v2_clientops = { + .version = 2, /* protocol version */ + .dentry_ops = &nfs_dentry_operations, + .dir_inode_ops = &nfs_dir_inode_operations, + .file_inode_ops = &nfs_file_inode_operations, + .file_ops = &nfs_file_operations, + .getroot = nfs_proc_get_root, + .submount = nfs_submount, + .try_mount = nfs_try_mount, + .getattr = nfs_proc_getattr, + .setattr = nfs_proc_setattr, + .lookup = nfs_proc_lookup, + .access = NULL, /* access */ + .readlink = nfs_proc_readlink, + .create = nfs_proc_create, + .remove = nfs_proc_remove, + .unlink_setup = nfs_proc_unlink_setup, + .unlink_rpc_prepare = nfs_proc_unlink_rpc_prepare, + .unlink_done = nfs_proc_unlink_done, + .rename_setup = nfs_proc_rename_setup, + .rename_rpc_prepare = nfs_proc_rename_rpc_prepare, + .rename_done = nfs_proc_rename_done, + .link = nfs_proc_link, + .symlink = nfs_proc_symlink, + .mkdir = nfs_proc_mkdir, + .rmdir = nfs_proc_rmdir, + .readdir = nfs_proc_readdir, + .mknod = nfs_proc_mknod, + .statfs = nfs_proc_statfs, + .fsinfo = nfs_proc_fsinfo, + .pathconf = nfs_proc_pathconf, + .decode_dirent = nfs2_decode_dirent, + .pgio_rpc_prepare = nfs_proc_pgio_rpc_prepare, + .read_setup = nfs_proc_read_setup, + .read_done = nfs_read_done, + .write_setup = nfs_proc_write_setup, + .write_done = nfs_write_done, + .commit_setup = nfs_proc_commit_setup, + .commit_rpc_prepare = nfs_proc_commit_rpc_prepare, + .lock = nfs_proc_lock, + .lock_check_bounds = nfs_lock_check_bounds, + .close_context = nfs_close_context, + .have_delegation = nfs_have_delegation, + .return_delegation = nfs_return_delegation, + .alloc_client = nfs_alloc_client, + .init_client = nfs_init_client, + .free_client = nfs_free_client, + .create_server = nfs_create_server, + .clone_server = nfs_clone_server, +}; diff --git a/kernel/fs/nfs/read.c b/kernel/fs/nfs/read.c new file mode 100644 index 000000000..ae0ff7a11 --- /dev/null +++ b/kernel/fs/nfs/read.c @@ -0,0 +1,445 @@ +/* + * linux/fs/nfs/read.c + * + * Block I/O for NFS + * + * Partial copy of Linus' read cache modifications to fs/nfs/file.c + * modified for async RPC by okir@monad.swb.de + */ + +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/fcntl.h> +#include <linux/stat.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_page.h> +#include <linux/module.h> + +#include "nfs4_fs.h" +#include "internal.h" +#include "iostat.h" +#include "fscache.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_PAGECACHE + +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; +static const struct nfs_rw_ops nfs_rw_read_ops; + +static struct kmem_cache *nfs_rdata_cachep; + +static struct nfs_pgio_header *nfs_readhdr_alloc(void) +{ + return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); +} + +static void nfs_readhdr_free(struct nfs_pgio_header *rhdr) +{ + kmem_cache_free(nfs_rdata_cachep, rhdr); +} + +static +int nfs_return_empty_page(struct page *page) +{ + zero_user(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + unlock_page(page); + return 0; +} + +void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, bool force_mds, + const struct nfs_pgio_completion_ops *compl_ops) +{ + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops; + +#ifdef CONFIG_NFS_V4_1 + if (server->pnfs_curr_ld && !force_mds) + pg_ops = server->pnfs_curr_ld->pg_read_ops; +#endif + nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops, + server->rsize, 0); +} +EXPORT_SYMBOL_GPL(nfs_pageio_init_read); + +void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) +{ + struct nfs_pgio_mirror *mirror; + + pgio->pg_ops = &nfs_pgio_rw_ops; + + /* read path should never have more than one mirror */ + WARN_ON_ONCE(pgio->pg_mirror_count != 1); + + mirror = &pgio->pg_mirrors[0]; + mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize; +} +EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); + +int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, + struct page *page) +{ + struct nfs_page *new; + unsigned int len; + struct nfs_pageio_descriptor pgio; + struct nfs_pgio_mirror *pgm; + + len = nfs_page_length(page); + if (len == 0) + return nfs_return_empty_page(page); + new = nfs_create_request(ctx, page, NULL, 0, len); + if (IS_ERR(new)) { + unlock_page(page); + return PTR_ERR(new); + } + if (len < PAGE_CACHE_SIZE) + zero_user_segment(page, len, PAGE_CACHE_SIZE); + + nfs_pageio_init_read(&pgio, inode, false, + &nfs_async_read_completion_ops); + nfs_pageio_add_request(&pgio, new); + nfs_pageio_complete(&pgio); + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio.pg_mirror_count != 1); + + pgm = &pgio.pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + + return 0; +} + +static void nfs_readpage_release(struct nfs_page *req) +{ + struct inode *inode = d_inode(req->wb_context->dentry); + + dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), req->wb_bytes, + (long long)req_offset(req)); + + if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { + if (PageUptodate(req->wb_page)) + nfs_readpage_to_fscache(inode, req->wb_page, 0); + + unlock_page(req->wb_page); + } + nfs_release_request(req); +} + +static void nfs_page_group_set_uptodate(struct nfs_page *req) +{ + if (nfs_page_group_sync_on_bit(req, PG_UPTODATE)) + SetPageUptodate(req->wb_page); +} + +static void nfs_read_completion(struct nfs_pgio_header *hdr) +{ + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + unsigned long start = req->wb_pgbase; + unsigned long end = req->wb_pgbase + req->wb_bytes; + + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { + /* note: regions of the page not covered by a + * request are zeroed in nfs_readpage_async / + * readpage_async_filler */ + if (bytes > hdr->good_bytes) { + /* nothing in this request was good, so zero + * the full extent of the request */ + zero_user_segment(page, start, end); + + } else if (hdr->good_bytes - bytes < req->wb_bytes) { + /* part of this request has good bytes, but + * not all. zero the bad bytes */ + start += hdr->good_bytes - bytes; + WARN_ON(start < req->wb_pgbase); + zero_user_segment(page, start, end); + } + } + bytes += req->wb_bytes; + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + if (bytes <= hdr->good_bytes) + nfs_page_group_set_uptodate(req); + } else + nfs_page_group_set_uptodate(req); + nfs_list_remove_request(req); + nfs_readpage_release(req); + } +out: + hdr->release(hdr); +} + +static void nfs_initiate_read(struct nfs_pgio_header *hdr, + struct rpc_message *msg, + const struct nfs_rpc_ops *rpc_ops, + struct rpc_task_setup *task_setup_data, int how) +{ + struct inode *inode = hdr->inode; + int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; + + task_setup_data->flags |= swap_flags; + rpc_ops->read_setup(hdr, msg); +} + +static void +nfs_async_read_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_readpage_release(req); + } +} + +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { + .error_cleanup = nfs_async_read_error, + .completion = nfs_read_completion, +}; + +/* + * This is the callback from RPC telling us whether a reply was + * received or some error occurred (timeout or socket shutdown). + */ +static int nfs_readpage_done(struct rpc_task *task, + struct nfs_pgio_header *hdr, + struct inode *inode) +{ + int status = NFS_PROTO(inode)->read_done(task, hdr); + if (status != 0) + return status; + + nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, hdr->res.count); + + if (task->tk_status == -ESTALE) { + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + nfs_mark_for_revalidate(inode); + } + return 0; +} + +static void nfs_readpage_retry(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct nfs_pgio_args *argp = &hdr->args; + struct nfs_pgio_res *resp = &hdr->res; + + /* This is a short read! */ + nfs_inc_stats(hdr->inode, NFSIOS_SHORTREAD); + /* Has the server at least made some progress? */ + if (resp->count == 0) { + nfs_set_pgio_error(hdr, -EIO, argp->offset); + return; + } + /* Yes, so retry the read at the end of the hdr */ + hdr->mds_offset += resp->count; + argp->offset += resp->count; + argp->pgbase += resp->count; + argp->count -= resp->count; + rpc_restart_call_prepare(task); +} + +static void nfs_readpage_result(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (hdr->res.eof) { + loff_t bound; + + bound = hdr->args.offset + hdr->res.count; + spin_lock(&hdr->lock); + if (bound < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_EOF, &hdr->flags); + clear_bit(NFS_IOHDR_ERROR, &hdr->flags); + hdr->good_bytes = bound - hdr->io_start; + } + spin_unlock(&hdr->lock); + } else if (hdr->res.count != hdr->args.count) + nfs_readpage_retry(task, hdr); +} + +/* + * Read a page over NFS. + * We read the page synchronously in the following case: + * - The error flag is set for this page. This happens only when a + * previous async read operation failed. + */ +int nfs_readpage(struct file *file, struct page *page) +{ + struct nfs_open_context *ctx; + struct inode *inode = page_file_mapping(page)->host; + int error; + + dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", + page, PAGE_CACHE_SIZE, page_file_index(page)); + nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); + nfs_add_stats(inode, NFSIOS_READPAGES, 1); + + /* + * Try to flush any pending writes to the file.. + * + * NOTE! Because we own the page lock, there cannot + * be any new pending writes generated at this point + * for this page (other pages can be written to). + */ + error = nfs_wb_page(inode, page); + if (error) + goto out_unlock; + if (PageUptodate(page)) + goto out_unlock; + + error = -ESTALE; + if (NFS_STALE(inode)) + goto out_unlock; + + if (file == NULL) { + error = -EBADF; + ctx = nfs_find_open_context(inode, NULL, FMODE_READ); + if (ctx == NULL) + goto out_unlock; + } else + ctx = get_nfs_open_context(nfs_file_open_context(file)); + + if (!IS_SYNC(inode)) { + error = nfs_readpage_from_fscache(ctx, inode, page); + if (error == 0) + goto out; + } + + error = nfs_readpage_async(ctx, inode, page); + +out: + put_nfs_open_context(ctx); + return error; +out_unlock: + unlock_page(page); + return error; +} + +struct nfs_readdesc { + struct nfs_pageio_descriptor *pgio; + struct nfs_open_context *ctx; +}; + +static int +readpage_async_filler(void *data, struct page *page) +{ + struct nfs_readdesc *desc = (struct nfs_readdesc *)data; + struct nfs_page *new; + unsigned int len; + int error; + + len = nfs_page_length(page); + if (len == 0) + return nfs_return_empty_page(page); + + new = nfs_create_request(desc->ctx, page, NULL, 0, len); + if (IS_ERR(new)) + goto out_error; + + if (len < PAGE_CACHE_SIZE) + zero_user_segment(page, len, PAGE_CACHE_SIZE); + if (!nfs_pageio_add_request(desc->pgio, new)) { + error = desc->pgio->pg_error; + goto out_unlock; + } + return 0; +out_error: + error = PTR_ERR(new); +out_unlock: + unlock_page(page); + return error; +} + +int nfs_readpages(struct file *filp, struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + struct nfs_pageio_descriptor pgio; + struct nfs_pgio_mirror *pgm; + struct nfs_readdesc desc = { + .pgio = &pgio, + }; + struct inode *inode = mapping->host; + unsigned long npages; + int ret = -ESTALE; + + dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", + inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), + nr_pages); + nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); + + if (NFS_STALE(inode)) + goto out; + + if (filp == NULL) { + desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); + if (desc.ctx == NULL) + return -EBADF; + } else + desc.ctx = get_nfs_open_context(nfs_file_open_context(filp)); + + /* attempt to read as many of the pages as possible from the cache + * - this returns -ENOBUFS immediately if the cookie is negative + */ + ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping, + pages, &nr_pages); + if (ret == 0) + goto read_complete; /* all pages were read */ + + nfs_pageio_init_read(&pgio, inode, false, + &nfs_async_read_completion_ops); + + ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); + nfs_pageio_complete(&pgio); + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio.pg_mirror_count != 1); + + pgm = &pgio.pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; + nfs_add_stats(inode, NFSIOS_READPAGES, npages); +read_complete: + put_nfs_open_context(desc.ctx); +out: + return ret; +} + +int __init nfs_init_readpagecache(void) +{ + nfs_rdata_cachep = kmem_cache_create("nfs_read_data", + sizeof(struct nfs_pgio_header), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (nfs_rdata_cachep == NULL) + return -ENOMEM; + + return 0; +} + +void nfs_destroy_readpagecache(void) +{ + kmem_cache_destroy(nfs_rdata_cachep); +} + +static const struct nfs_rw_ops nfs_rw_read_ops = { + .rw_mode = FMODE_READ, + .rw_alloc_header = nfs_readhdr_alloc, + .rw_free_header = nfs_readhdr_free, + .rw_done = nfs_readpage_done, + .rw_result = nfs_readpage_result, + .rw_initiate = nfs_initiate_read, +}; diff --git a/kernel/fs/nfs/super.c b/kernel/fs/nfs/super.c new file mode 100644 index 000000000..f175b833b --- /dev/null +++ b/kernel/fs/nfs/super.c @@ -0,0 +1,2877 @@ +/* + * linux/fs/nfs/super.c + * + * Copyright (C) 1992 Rick Sladkey + * + * nfs superblock handling functions + * + * Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some + * experimental NFS changes. Modularisation taken straight from SYS5 fs. + * + * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. + * J.S.Peatfield@damtp.cam.ac.uk + * + * Split from inode.c by David Howells <dhowells@redhat.com> + * + * - superblocks are indexed on server only - all inodes, dentries, etc. associated with a + * particular server are held in the same superblock + * - NFS superblocks can have several effective roots to the dentry tree + * - directory type roots are spliced into the tree when a path from one root reaches the root + * of another (see nfs_lookup()) + */ + +#include <linux/module.h> +#include <linux/init.h> + +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> +#include <linux/sunrpc/stats.h> +#include <linux/sunrpc/metrics.h> +#include <linux/sunrpc/xprtsock.h> +#include <linux/sunrpc/xprtrdma.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs4_mount.h> +#include <linux/lockd/bind.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/vfs.h> +#include <linux/inet.h> +#include <linux/in6.h> +#include <linux/slab.h> +#include <net/ipv6.h> +#include <linux/netdevice.h> +#include <linux/nfs_xdr.h> +#include <linux/magic.h> +#include <linux/parser.h> +#include <linux/nsproxy.h> +#include <linux/rcupdate.h> + +#include <asm/uaccess.h> + +#include "nfs4_fs.h" +#include "callback.h" +#include "delegation.h" +#include "iostat.h" +#include "internal.h" +#include "fscache.h" +#include "nfs4session.h" +#include "pnfs.h" +#include "nfs.h" + +#define NFSDBG_FACILITY NFSDBG_VFS +#define NFS_TEXT_DATA 1 + +#if IS_ENABLED(CONFIG_NFS_V3) +#define NFS_DEFAULT_VERSION 3 +#else +#define NFS_DEFAULT_VERSION 2 +#endif + +enum { + /* Mount options that take no arguments */ + Opt_soft, Opt_hard, + Opt_posix, Opt_noposix, + Opt_cto, Opt_nocto, + Opt_ac, Opt_noac, + Opt_lock, Opt_nolock, + Opt_udp, Opt_tcp, Opt_rdma, + Opt_acl, Opt_noacl, + Opt_rdirplus, Opt_nordirplus, + Opt_sharecache, Opt_nosharecache, + Opt_resvport, Opt_noresvport, + Opt_fscache, Opt_nofscache, + Opt_migration, Opt_nomigration, + + /* Mount options that take integer arguments */ + Opt_port, + Opt_rsize, Opt_wsize, Opt_bsize, + Opt_timeo, Opt_retrans, + Opt_acregmin, Opt_acregmax, + Opt_acdirmin, Opt_acdirmax, + Opt_actimeo, + Opt_namelen, + Opt_mountport, + Opt_mountvers, + Opt_minorversion, + + /* Mount options that take string arguments */ + Opt_nfsvers, + Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost, + Opt_addr, Opt_mountaddr, Opt_clientaddr, + Opt_lookupcache, + Opt_fscache_uniq, + Opt_local_lock, + + /* Special mount options */ + Opt_userspace, Opt_deprecated, Opt_sloppy, + + Opt_err +}; + +static const match_table_t nfs_mount_option_tokens = { + { Opt_userspace, "bg" }, + { Opt_userspace, "fg" }, + { Opt_userspace, "retry=%s" }, + + { Opt_sloppy, "sloppy" }, + + { Opt_soft, "soft" }, + { Opt_hard, "hard" }, + { Opt_deprecated, "intr" }, + { Opt_deprecated, "nointr" }, + { Opt_posix, "posix" }, + { Opt_noposix, "noposix" }, + { Opt_cto, "cto" }, + { Opt_nocto, "nocto" }, + { Opt_ac, "ac" }, + { Opt_noac, "noac" }, + { Opt_lock, "lock" }, + { Opt_nolock, "nolock" }, + { Opt_udp, "udp" }, + { Opt_tcp, "tcp" }, + { Opt_rdma, "rdma" }, + { Opt_acl, "acl" }, + { Opt_noacl, "noacl" }, + { Opt_rdirplus, "rdirplus" }, + { Opt_nordirplus, "nordirplus" }, + { Opt_sharecache, "sharecache" }, + { Opt_nosharecache, "nosharecache" }, + { Opt_resvport, "resvport" }, + { Opt_noresvport, "noresvport" }, + { Opt_fscache, "fsc" }, + { Opt_nofscache, "nofsc" }, + { Opt_migration, "migration" }, + { Opt_nomigration, "nomigration" }, + + { Opt_port, "port=%s" }, + { Opt_rsize, "rsize=%s" }, + { Opt_wsize, "wsize=%s" }, + { Opt_bsize, "bsize=%s" }, + { Opt_timeo, "timeo=%s" }, + { Opt_retrans, "retrans=%s" }, + { Opt_acregmin, "acregmin=%s" }, + { Opt_acregmax, "acregmax=%s" }, + { Opt_acdirmin, "acdirmin=%s" }, + { Opt_acdirmax, "acdirmax=%s" }, + { Opt_actimeo, "actimeo=%s" }, + { Opt_namelen, "namlen=%s" }, + { Opt_mountport, "mountport=%s" }, + { Opt_mountvers, "mountvers=%s" }, + { Opt_minorversion, "minorversion=%s" }, + + { Opt_nfsvers, "nfsvers=%s" }, + { Opt_nfsvers, "vers=%s" }, + + { Opt_sec, "sec=%s" }, + { Opt_proto, "proto=%s" }, + { Opt_mountproto, "mountproto=%s" }, + { Opt_addr, "addr=%s" }, + { Opt_clientaddr, "clientaddr=%s" }, + { Opt_mounthost, "mounthost=%s" }, + { Opt_mountaddr, "mountaddr=%s" }, + + { Opt_lookupcache, "lookupcache=%s" }, + { Opt_fscache_uniq, "fsc=%s" }, + { Opt_local_lock, "local_lock=%s" }, + + /* The following needs to be listed after all other options */ + { Opt_nfsvers, "v%s" }, + + { Opt_err, NULL } +}; + +enum { + Opt_xprt_udp, Opt_xprt_udp6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_rdma, + + Opt_xprt_err +}; + +static const match_table_t nfs_xprt_protocol_tokens = { + { Opt_xprt_udp, "udp" }, + { Opt_xprt_udp6, "udp6" }, + { Opt_xprt_tcp, "tcp" }, + { Opt_xprt_tcp6, "tcp6" }, + { Opt_xprt_rdma, "rdma" }, + + { Opt_xprt_err, NULL } +}; + +enum { + Opt_sec_none, Opt_sec_sys, + Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p, + Opt_sec_lkey, Opt_sec_lkeyi, Opt_sec_lkeyp, + Opt_sec_spkm, Opt_sec_spkmi, Opt_sec_spkmp, + + Opt_sec_err +}; + +static const match_table_t nfs_secflavor_tokens = { + { Opt_sec_none, "none" }, + { Opt_sec_none, "null" }, + { Opt_sec_sys, "sys" }, + + { Opt_sec_krb5, "krb5" }, + { Opt_sec_krb5i, "krb5i" }, + { Opt_sec_krb5p, "krb5p" }, + + { Opt_sec_lkey, "lkey" }, + { Opt_sec_lkeyi, "lkeyi" }, + { Opt_sec_lkeyp, "lkeyp" }, + + { Opt_sec_spkm, "spkm3" }, + { Opt_sec_spkmi, "spkm3i" }, + { Opt_sec_spkmp, "spkm3p" }, + + { Opt_sec_err, NULL } +}; + +enum { + Opt_lookupcache_all, Opt_lookupcache_positive, + Opt_lookupcache_none, + + Opt_lookupcache_err +}; + +static match_table_t nfs_lookupcache_tokens = { + { Opt_lookupcache_all, "all" }, + { Opt_lookupcache_positive, "pos" }, + { Opt_lookupcache_positive, "positive" }, + { Opt_lookupcache_none, "none" }, + + { Opt_lookupcache_err, NULL } +}; + +enum { + Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix, + Opt_local_lock_none, + + Opt_local_lock_err +}; + +static match_table_t nfs_local_lock_tokens = { + { Opt_local_lock_all, "all" }, + { Opt_local_lock_flock, "flock" }, + { Opt_local_lock_posix, "posix" }, + { Opt_local_lock_none, "none" }, + + { Opt_local_lock_err, NULL } +}; + +enum { + Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0, + Opt_vers_4_1, Opt_vers_4_2, + + Opt_vers_err +}; + +static match_table_t nfs_vers_tokens = { + { Opt_vers_2, "2" }, + { Opt_vers_3, "3" }, + { Opt_vers_4, "4" }, + { Opt_vers_4_0, "4.0" }, + { Opt_vers_4_1, "4.1" }, + { Opt_vers_4_2, "4.2" }, + + { Opt_vers_err, NULL } +}; + +static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); + +struct file_system_type nfs_fs_type = { + .owner = THIS_MODULE, + .name = "nfs", + .mount = nfs_fs_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; +MODULE_ALIAS_FS("nfs"); +EXPORT_SYMBOL_GPL(nfs_fs_type); + +struct file_system_type nfs_xdev_fs_type = { + .owner = THIS_MODULE, + .name = "nfs", + .mount = nfs_xdev_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; + +const struct super_operations nfs_sops = { + .alloc_inode = nfs_alloc_inode, + .destroy_inode = nfs_destroy_inode, + .write_inode = nfs_write_inode, + .drop_inode = nfs_drop_inode, + .statfs = nfs_statfs, + .evict_inode = nfs_evict_inode, + .umount_begin = nfs_umount_begin, + .show_options = nfs_show_options, + .show_devname = nfs_show_devname, + .show_path = nfs_show_path, + .show_stats = nfs_show_stats, + .remount_fs = nfs_remount, +}; +EXPORT_SYMBOL_GPL(nfs_sops); + +#if IS_ENABLED(CONFIG_NFS_V4) +static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); +static int nfs4_validate_mount_data(void *options, + struct nfs_parsed_mount_data *args, const char *dev_name); + +struct file_system_type nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs_fs_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; +MODULE_ALIAS_FS("nfs4"); +MODULE_ALIAS("nfs4"); +EXPORT_SYMBOL_GPL(nfs4_fs_type); + +static int __init register_nfs4_fs(void) +{ + return register_filesystem(&nfs4_fs_type); +} + +static void unregister_nfs4_fs(void) +{ + unregister_filesystem(&nfs4_fs_type); +} +#else +static int __init register_nfs4_fs(void) +{ + return 0; +} + +static void unregister_nfs4_fs(void) +{ +} +#endif + +static struct shrinker acl_shrinker = { + .count_objects = nfs_access_cache_count, + .scan_objects = nfs_access_cache_scan, + .seeks = DEFAULT_SEEKS, +}; + +/* + * Register the NFS filesystems + */ +int __init register_nfs_fs(void) +{ + int ret; + + ret = register_filesystem(&nfs_fs_type); + if (ret < 0) + goto error_0; + + ret = register_nfs4_fs(); + if (ret < 0) + goto error_1; + + ret = nfs_register_sysctl(); + if (ret < 0) + goto error_2; + register_shrinker(&acl_shrinker); + return 0; + +error_2: + unregister_nfs4_fs(); +error_1: + unregister_filesystem(&nfs_fs_type); +error_0: + return ret; +} + +/* + * Unregister the NFS filesystems + */ +void __exit unregister_nfs_fs(void) +{ + unregister_shrinker(&acl_shrinker); + nfs_unregister_sysctl(); + unregister_nfs4_fs(); + unregister_filesystem(&nfs_fs_type); +} + +bool nfs_sb_active(struct super_block *sb) +{ + struct nfs_server *server = NFS_SB(sb); + + if (!atomic_inc_not_zero(&sb->s_active)) + return false; + if (atomic_inc_return(&server->active) != 1) + atomic_dec(&sb->s_active); + return true; +} +EXPORT_SYMBOL_GPL(nfs_sb_active); + +void nfs_sb_deactive(struct super_block *sb) +{ + struct nfs_server *server = NFS_SB(sb); + + if (atomic_dec_and_test(&server->active)) + deactivate_super(sb); +} +EXPORT_SYMBOL_GPL(nfs_sb_deactive); + +/* + * Deliver file system statistics to userspace + */ +int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct nfs_server *server = NFS_SB(dentry->d_sb); + unsigned char blockbits; + unsigned long blockres; + struct nfs_fh *fh = NFS_FH(d_inode(dentry)); + struct nfs_fsstat res; + int error = -ENOMEM; + + res.fattr = nfs_alloc_fattr(); + if (res.fattr == NULL) + goto out_err; + + error = server->nfs_client->rpc_ops->statfs(server, fh, &res); + if (unlikely(error == -ESTALE)) { + struct dentry *pd_dentry; + + pd_dentry = dget_parent(dentry); + if (pd_dentry != NULL) { + nfs_zap_caches(d_inode(pd_dentry)); + dput(pd_dentry); + } + } + nfs_free_fattr(res.fattr); + if (error < 0) + goto out_err; + + buf->f_type = NFS_SUPER_MAGIC; + + /* + * Current versions of glibc do not correctly handle the + * case where f_frsize != f_bsize. Eventually we want to + * report the value of wtmult in this field. + */ + buf->f_frsize = dentry->d_sb->s_blocksize; + + /* + * On most *nix systems, f_blocks, f_bfree, and f_bavail + * are reported in units of f_frsize. Linux hasn't had + * an f_frsize field in its statfs struct until recently, + * thus historically Linux's sys_statfs reports these + * fields in units of f_bsize. + */ + buf->f_bsize = dentry->d_sb->s_blocksize; + blockbits = dentry->d_sb->s_blocksize_bits; + blockres = (1 << blockbits) - 1; + buf->f_blocks = (res.tbytes + blockres) >> blockbits; + buf->f_bfree = (res.fbytes + blockres) >> blockbits; + buf->f_bavail = (res.abytes + blockres) >> blockbits; + + buf->f_files = res.tfiles; + buf->f_ffree = res.afiles; + + buf->f_namelen = server->namelen; + + return 0; + + out_err: + dprintk("%s: statfs error = %d\n", __func__, -error); + return error; +} +EXPORT_SYMBOL_GPL(nfs_statfs); + +/* + * Map the security flavour number to a name + */ +static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour) +{ + static const struct { + rpc_authflavor_t flavour; + const char *str; + } sec_flavours[NFS_AUTH_INFO_MAX_FLAVORS] = { + /* update NFS_AUTH_INFO_MAX_FLAVORS when this list changes! */ + { RPC_AUTH_NULL, "null" }, + { RPC_AUTH_UNIX, "sys" }, + { RPC_AUTH_GSS_KRB5, "krb5" }, + { RPC_AUTH_GSS_KRB5I, "krb5i" }, + { RPC_AUTH_GSS_KRB5P, "krb5p" }, + { RPC_AUTH_GSS_LKEY, "lkey" }, + { RPC_AUTH_GSS_LKEYI, "lkeyi" }, + { RPC_AUTH_GSS_LKEYP, "lkeyp" }, + { RPC_AUTH_GSS_SPKM, "spkm" }, + { RPC_AUTH_GSS_SPKMI, "spkmi" }, + { RPC_AUTH_GSS_SPKMP, "spkmp" }, + { UINT_MAX, "unknown" } + }; + int i; + + for (i = 0; sec_flavours[i].flavour != UINT_MAX; i++) { + if (sec_flavours[i].flavour == flavour) + break; + } + return sec_flavours[i].str; +} + +static void nfs_show_mountd_netid(struct seq_file *m, struct nfs_server *nfss, + int showdefaults) +{ + struct sockaddr *sap = (struct sockaddr *) &nfss->mountd_address; + + seq_printf(m, ",mountproto="); + switch (sap->sa_family) { + case AF_INET: + switch (nfss->mountd_protocol) { + case IPPROTO_UDP: + seq_printf(m, RPCBIND_NETID_UDP); + break; + case IPPROTO_TCP: + seq_printf(m, RPCBIND_NETID_TCP); + break; + default: + if (showdefaults) + seq_printf(m, "auto"); + } + break; + case AF_INET6: + switch (nfss->mountd_protocol) { + case IPPROTO_UDP: + seq_printf(m, RPCBIND_NETID_UDP6); + break; + case IPPROTO_TCP: + seq_printf(m, RPCBIND_NETID_TCP6); + break; + default: + if (showdefaults) + seq_printf(m, "auto"); + } + break; + default: + if (showdefaults) + seq_printf(m, "auto"); + } +} + +static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss, + int showdefaults) +{ + struct sockaddr *sap = (struct sockaddr *)&nfss->mountd_address; + + if (nfss->flags & NFS_MOUNT_LEGACY_INTERFACE) + return; + + switch (sap->sa_family) { + case AF_INET: { + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + seq_printf(m, ",mountaddr=%pI4", &sin->sin_addr.s_addr); + break; + } + case AF_INET6: { + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + seq_printf(m, ",mountaddr=%pI6c", &sin6->sin6_addr); + break; + } + default: + if (showdefaults) + seq_printf(m, ",mountaddr=unspecified"); + } + + if (nfss->mountd_version || showdefaults) + seq_printf(m, ",mountvers=%u", nfss->mountd_version); + if ((nfss->mountd_port && + nfss->mountd_port != (unsigned short)NFS_UNSPEC_PORT) || + showdefaults) + seq_printf(m, ",mountport=%u", nfss->mountd_port); + + nfs_show_mountd_netid(m, nfss, showdefaults); +} + +#if IS_ENABLED(CONFIG_NFS_V4) +static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss, + int showdefaults) +{ + struct nfs_client *clp = nfss->nfs_client; + + seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr); +} +#else +static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss, + int showdefaults) +{ +} +#endif + +static void nfs_show_nfs_version(struct seq_file *m, + unsigned int version, + unsigned int minorversion) +{ + seq_printf(m, ",vers=%u", version); + if (version == 4) + seq_printf(m, ".%u", minorversion); +} + +/* + * Describe the mount options in force on this server representation + */ +static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, + int showdefaults) +{ + static const struct proc_nfs_info { + int flag; + const char *str; + const char *nostr; + } nfs_info[] = { + { NFS_MOUNT_SOFT, ",soft", ",hard" }, + { NFS_MOUNT_POSIX, ",posix", "" }, + { NFS_MOUNT_NOCTO, ",nocto", "" }, + { NFS_MOUNT_NOAC, ",noac", "" }, + { NFS_MOUNT_NONLM, ",nolock", "" }, + { NFS_MOUNT_NOACL, ",noacl", "" }, + { NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" }, + { NFS_MOUNT_UNSHARED, ",nosharecache", "" }, + { NFS_MOUNT_NORESVPORT, ",noresvport", "" }, + { 0, NULL, NULL } + }; + const struct proc_nfs_info *nfs_infop; + struct nfs_client *clp = nfss->nfs_client; + u32 version = clp->rpc_ops->version; + int local_flock, local_fcntl; + + nfs_show_nfs_version(m, version, clp->cl_minorversion); + seq_printf(m, ",rsize=%u", nfss->rsize); + seq_printf(m, ",wsize=%u", nfss->wsize); + if (nfss->bsize != 0) + seq_printf(m, ",bsize=%u", nfss->bsize); + seq_printf(m, ",namlen=%u", nfss->namelen); + if (nfss->acregmin != NFS_DEF_ACREGMIN*HZ || showdefaults) + seq_printf(m, ",acregmin=%u", nfss->acregmin/HZ); + if (nfss->acregmax != NFS_DEF_ACREGMAX*HZ || showdefaults) + seq_printf(m, ",acregmax=%u", nfss->acregmax/HZ); + if (nfss->acdirmin != NFS_DEF_ACDIRMIN*HZ || showdefaults) + seq_printf(m, ",acdirmin=%u", nfss->acdirmin/HZ); + if (nfss->acdirmax != NFS_DEF_ACDIRMAX*HZ || showdefaults) + seq_printf(m, ",acdirmax=%u", nfss->acdirmax/HZ); + for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) { + if (nfss->flags & nfs_infop->flag) + seq_puts(m, nfs_infop->str); + else + seq_puts(m, nfs_infop->nostr); + } + rcu_read_lock(); + seq_printf(m, ",proto=%s", + rpc_peeraddr2str(nfss->client, RPC_DISPLAY_NETID)); + rcu_read_unlock(); + if (version == 4) { + if (nfss->port != NFS_PORT) + seq_printf(m, ",port=%u", nfss->port); + } else + if (nfss->port) + seq_printf(m, ",port=%u", nfss->port); + + seq_printf(m, ",timeo=%lu", 10U * nfss->client->cl_timeout->to_initval / HZ); + seq_printf(m, ",retrans=%u", nfss->client->cl_timeout->to_retries); + seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor)); + + if (version != 4) + nfs_show_mountd_options(m, nfss, showdefaults); + else + nfs_show_nfsv4_options(m, nfss, showdefaults); + + if (nfss->options & NFS_OPTION_FSCACHE) + seq_printf(m, ",fsc"); + + if (nfss->options & NFS_OPTION_MIGRATION) + seq_printf(m, ",migration"); + + if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) { + if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) + seq_printf(m, ",lookupcache=none"); + else + seq_printf(m, ",lookupcache=pos"); + } + + local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK; + local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL; + + if (!local_flock && !local_fcntl) + seq_printf(m, ",local_lock=none"); + else if (local_flock && local_fcntl) + seq_printf(m, ",local_lock=all"); + else if (local_flock) + seq_printf(m, ",local_lock=flock"); + else + seq_printf(m, ",local_lock=posix"); +} + +/* + * Describe the mount options on this VFS mountpoint + */ +int nfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct nfs_server *nfss = NFS_SB(root->d_sb); + + nfs_show_mount_options(m, nfss, 0); + + rcu_read_lock(); + seq_printf(m, ",addr=%s", + rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient, + RPC_DISPLAY_ADDR)); + rcu_read_unlock(); + + return 0; +} +EXPORT_SYMBOL_GPL(nfs_show_options); + +#if IS_ENABLED(CONFIG_NFS_V4) +#ifdef CONFIG_NFS_V4_1 +static void show_sessions(struct seq_file *m, struct nfs_server *server) +{ + if (nfs4_has_session(server->nfs_client)) + seq_printf(m, ",sessions"); +} +#else +static void show_sessions(struct seq_file *m, struct nfs_server *server) {} +#endif +#endif + +#ifdef CONFIG_NFS_V4_1 +static void show_pnfs(struct seq_file *m, struct nfs_server *server) +{ + seq_printf(m, ",pnfs="); + if (server->pnfs_curr_ld) + seq_printf(m, "%s", server->pnfs_curr_ld->name); + else + seq_printf(m, "not configured"); +} + +static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) +{ + if (nfss->nfs_client && nfss->nfs_client->cl_implid) { + struct nfs41_impl_id *impl_id = nfss->nfs_client->cl_implid; + seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s'," + "date='%llu,%u'", + impl_id->name, impl_id->domain, + impl_id->date.seconds, impl_id->date.nseconds); + } +} +#else +#if IS_ENABLED(CONFIG_NFS_V4) +static void show_pnfs(struct seq_file *m, struct nfs_server *server) +{ +} +#endif +static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) +{ +} +#endif + +int nfs_show_devname(struct seq_file *m, struct dentry *root) +{ + char *page = (char *) __get_free_page(GFP_KERNEL); + char *devname, *dummy; + int err = 0; + if (!page) + return -ENOMEM; + devname = nfs_path(&dummy, root, page, PAGE_SIZE, 0); + if (IS_ERR(devname)) + err = PTR_ERR(devname); + else + seq_escape(m, devname, " \t\n\\"); + free_page((unsigned long)page); + return err; +} +EXPORT_SYMBOL_GPL(nfs_show_devname); + +int nfs_show_path(struct seq_file *m, struct dentry *dentry) +{ + seq_puts(m, "/"); + return 0; +} +EXPORT_SYMBOL_GPL(nfs_show_path); + +/* + * Present statistical information for this VFS mountpoint + */ +int nfs_show_stats(struct seq_file *m, struct dentry *root) +{ + int i, cpu; + struct nfs_server *nfss = NFS_SB(root->d_sb); + struct rpc_auth *auth = nfss->client->cl_auth; + struct nfs_iostats totals = { }; + + seq_printf(m, "statvers=%s", NFS_IOSTAT_VERS); + + /* + * Display all mount option settings + */ + seq_printf(m, "\n\topts:\t"); + seq_puts(m, root->d_sb->s_flags & MS_RDONLY ? "ro" : "rw"); + seq_puts(m, root->d_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : ""); + seq_puts(m, root->d_sb->s_flags & MS_NOATIME ? ",noatime" : ""); + seq_puts(m, root->d_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : ""); + nfs_show_mount_options(m, nfss, 1); + + seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); + + show_implementation_id(m, nfss); + + seq_printf(m, "\n\tcaps:\t"); + seq_printf(m, "caps=0x%x", nfss->caps); + seq_printf(m, ",wtmult=%u", nfss->wtmult); + seq_printf(m, ",dtsize=%u", nfss->dtsize); + seq_printf(m, ",bsize=%u", nfss->bsize); + seq_printf(m, ",namlen=%u", nfss->namelen); + +#if IS_ENABLED(CONFIG_NFS_V4) + if (nfss->nfs_client->rpc_ops->version == 4) { + seq_printf(m, "\n\tnfsv4:\t"); + seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]); + seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]); + seq_printf(m, ",bm2=0x%x", nfss->attr_bitmask[2]); + seq_printf(m, ",acl=0x%x", nfss->acl_bitmask); + show_sessions(m, nfss); + show_pnfs(m, nfss); + } +#endif + + /* + * Display security flavor in effect for this mount + */ + seq_printf(m, "\n\tsec:\tflavor=%u", auth->au_ops->au_flavor); + if (auth->au_flavor) + seq_printf(m, ",pseudoflavor=%u", auth->au_flavor); + + /* + * Display superblock I/O counters + */ + for_each_possible_cpu(cpu) { + struct nfs_iostats *stats; + + preempt_disable(); + stats = per_cpu_ptr(nfss->io_stats, cpu); + + for (i = 0; i < __NFSIOS_COUNTSMAX; i++) + totals.events[i] += stats->events[i]; + for (i = 0; i < __NFSIOS_BYTESMAX; i++) + totals.bytes[i] += stats->bytes[i]; +#ifdef CONFIG_NFS_FSCACHE + for (i = 0; i < __NFSIOS_FSCACHEMAX; i++) + totals.fscache[i] += stats->fscache[i]; +#endif + + preempt_enable(); + } + + seq_printf(m, "\n\tevents:\t"); + for (i = 0; i < __NFSIOS_COUNTSMAX; i++) + seq_printf(m, "%lu ", totals.events[i]); + seq_printf(m, "\n\tbytes:\t"); + for (i = 0; i < __NFSIOS_BYTESMAX; i++) + seq_printf(m, "%Lu ", totals.bytes[i]); +#ifdef CONFIG_NFS_FSCACHE + if (nfss->options & NFS_OPTION_FSCACHE) { + seq_printf(m, "\n\tfsc:\t"); + for (i = 0; i < __NFSIOS_FSCACHEMAX; i++) + seq_printf(m, "%Lu ", totals.bytes[i]); + } +#endif + seq_printf(m, "\n"); + + rpc_print_iostats(m, nfss->client); + + return 0; +} +EXPORT_SYMBOL_GPL(nfs_show_stats); + +/* + * Begin unmount by attempting to remove all automounted mountpoints we added + * in response to xdev traversals and referrals + */ +void nfs_umount_begin(struct super_block *sb) +{ + struct nfs_server *server; + struct rpc_clnt *rpc; + + server = NFS_SB(sb); + /* -EIO all pending I/O */ + rpc = server->client_acl; + if (!IS_ERR(rpc)) + rpc_killall_tasks(rpc); + rpc = server->client; + if (!IS_ERR(rpc)) + rpc_killall_tasks(rpc); +} +EXPORT_SYMBOL_GPL(nfs_umount_begin); + +static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) +{ + struct nfs_parsed_mount_data *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data) { + data->acregmin = NFS_DEF_ACREGMIN; + data->acregmax = NFS_DEF_ACREGMAX; + data->acdirmin = NFS_DEF_ACDIRMIN; + data->acdirmax = NFS_DEF_ACDIRMAX; + data->mount_server.port = NFS_UNSPEC_PORT; + data->nfs_server.port = NFS_UNSPEC_PORT; + data->nfs_server.protocol = XPRT_TRANSPORT_TCP; + data->selected_flavor = RPC_AUTH_MAXFLAVOR; + data->minorversion = 0; + data->need_mount = true; + data->net = current->nsproxy->net_ns; + security_init_mnt_opts(&data->lsm_opts); + } + return data; +} + +static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data) +{ + if (data) { + kfree(data->client_address); + kfree(data->mount_server.hostname); + kfree(data->nfs_server.export_path); + kfree(data->nfs_server.hostname); + kfree(data->fscache_uniq); + security_free_mnt_opts(&data->lsm_opts); + kfree(data); + } +} + +/* + * Sanity-check a server address provided by the mount command. + * + * Address family must be initialized, and address must not be + * the ANY address for that family. + */ +static int nfs_verify_server_address(struct sockaddr *addr) +{ + switch (addr->sa_family) { + case AF_INET: { + struct sockaddr_in *sa = (struct sockaddr_in *)addr; + return sa->sin_addr.s_addr != htonl(INADDR_ANY); + } + case AF_INET6: { + struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr; + return !ipv6_addr_any(sa); + } + } + + dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); + return 0; +} + +/* + * Select between a default port value and a user-specified port value. + * If a zero value is set, then autobind will be used. + */ +static void nfs_set_port(struct sockaddr *sap, int *port, + const unsigned short default_port) +{ + if (*port == NFS_UNSPEC_PORT) + *port = default_port; + + rpc_set_port(sap, *port); +} + +/* + * Sanity check the NFS transport protocol. + * + */ +static void nfs_validate_transport_protocol(struct nfs_parsed_mount_data *mnt) +{ + switch (mnt->nfs_server.protocol) { + case XPRT_TRANSPORT_UDP: + case XPRT_TRANSPORT_TCP: + case XPRT_TRANSPORT_RDMA: + break; + default: + mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP; + } +} + +/* + * For text based NFSv2/v3 mounts, the mount protocol transport default + * settings should depend upon the specified NFS transport. + */ +static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) +{ + nfs_validate_transport_protocol(mnt); + + if (mnt->mount_server.protocol == XPRT_TRANSPORT_UDP || + mnt->mount_server.protocol == XPRT_TRANSPORT_TCP) + return; + switch (mnt->nfs_server.protocol) { + case XPRT_TRANSPORT_UDP: + mnt->mount_server.protocol = XPRT_TRANSPORT_UDP; + break; + case XPRT_TRANSPORT_TCP: + case XPRT_TRANSPORT_RDMA: + mnt->mount_server.protocol = XPRT_TRANSPORT_TCP; + } +} + +/* + * Add 'flavor' to 'auth_info' if not already present. + * Returns true if 'flavor' ends up in the list, false otherwise + */ +static bool nfs_auth_info_add(struct nfs_auth_info *auth_info, + rpc_authflavor_t flavor) +{ + unsigned int i; + unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors); + + /* make sure this flavor isn't already in the list */ + for (i = 0; i < auth_info->flavor_len; i++) { + if (flavor == auth_info->flavors[i]) + return true; + } + + if (auth_info->flavor_len + 1 >= max_flavor_len) { + dfprintk(MOUNT, "NFS: too many sec= flavors\n"); + return false; + } + + auth_info->flavors[auth_info->flavor_len++] = flavor; + return true; +} + +/* + * Return true if 'match' is in auth_info or auth_info is empty. + * Return false otherwise. + */ +bool nfs_auth_info_match(const struct nfs_auth_info *auth_info, + rpc_authflavor_t match) +{ + int i; + + if (!auth_info->flavor_len) + return true; + + for (i = 0; i < auth_info->flavor_len; i++) { + if (auth_info->flavors[i] == match) + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(nfs_auth_info_match); + +/* + * Parse the value of the 'sec=' option. + */ +static int nfs_parse_security_flavors(char *value, + struct nfs_parsed_mount_data *mnt) +{ + substring_t args[MAX_OPT_ARGS]; + rpc_authflavor_t pseudoflavor; + char *p; + + dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value); + + while ((p = strsep(&value, ":")) != NULL) { + switch (match_token(p, nfs_secflavor_tokens, args)) { + case Opt_sec_none: + pseudoflavor = RPC_AUTH_NULL; + break; + case Opt_sec_sys: + pseudoflavor = RPC_AUTH_UNIX; + break; + case Opt_sec_krb5: + pseudoflavor = RPC_AUTH_GSS_KRB5; + break; + case Opt_sec_krb5i: + pseudoflavor = RPC_AUTH_GSS_KRB5I; + break; + case Opt_sec_krb5p: + pseudoflavor = RPC_AUTH_GSS_KRB5P; + break; + case Opt_sec_lkey: + pseudoflavor = RPC_AUTH_GSS_LKEY; + break; + case Opt_sec_lkeyi: + pseudoflavor = RPC_AUTH_GSS_LKEYI; + break; + case Opt_sec_lkeyp: + pseudoflavor = RPC_AUTH_GSS_LKEYP; + break; + case Opt_sec_spkm: + pseudoflavor = RPC_AUTH_GSS_SPKM; + break; + case Opt_sec_spkmi: + pseudoflavor = RPC_AUTH_GSS_SPKMI; + break; + case Opt_sec_spkmp: + pseudoflavor = RPC_AUTH_GSS_SPKMP; + break; + default: + dfprintk(MOUNT, + "NFS: sec= option '%s' not recognized\n", p); + return 0; + } + + if (!nfs_auth_info_add(&mnt->auth_info, pseudoflavor)) + return 0; + } + + return 1; +} + +static int nfs_parse_version_string(char *string, + struct nfs_parsed_mount_data *mnt, + substring_t *args) +{ + mnt->flags &= ~NFS_MOUNT_VER3; + switch (match_token(string, nfs_vers_tokens, args)) { + case Opt_vers_2: + mnt->version = 2; + break; + case Opt_vers_3: + mnt->flags |= NFS_MOUNT_VER3; + mnt->version = 3; + break; + case Opt_vers_4: + /* Backward compatibility option. In future, + * the mount program should always supply + * a NFSv4 minor version number. + */ + mnt->version = 4; + break; + case Opt_vers_4_0: + mnt->version = 4; + mnt->minorversion = 0; + break; + case Opt_vers_4_1: + mnt->version = 4; + mnt->minorversion = 1; + break; + case Opt_vers_4_2: + mnt->version = 4; + mnt->minorversion = 2; + break; + default: + return 0; + } + return 1; +} + +static int nfs_get_option_str(substring_t args[], char **option) +{ + kfree(*option); + *option = match_strdup(args); + return !*option; +} + +static int nfs_get_option_ul(substring_t args[], unsigned long *option) +{ + int rc; + char *string; + + string = match_strdup(args); + if (string == NULL) + return -ENOMEM; + rc = kstrtoul(string, 10, option); + kfree(string); + + return rc; +} + +/* + * Error-check and convert a string of mount options from user space into + * a data structure. The whole mount string is processed; bad options are + * skipped as they are encountered. If there were no errors, return 1; + * otherwise return 0 (zero). + */ +static int nfs_parse_mount_options(char *raw, + struct nfs_parsed_mount_data *mnt) +{ + char *p, *string, *secdata; + int rc, sloppy = 0, invalid_option = 0; + unsigned short protofamily = AF_UNSPEC; + unsigned short mountfamily = AF_UNSPEC; + + if (!raw) { + dfprintk(MOUNT, "NFS: mount options string was NULL.\n"); + return 1; + } + dfprintk(MOUNT, "NFS: nfs mount opts='%s'\n", raw); + + secdata = alloc_secdata(); + if (!secdata) + goto out_nomem; + + rc = security_sb_copy_data(raw, secdata); + if (rc) + goto out_security_failure; + + rc = security_sb_parse_opts_str(secdata, &mnt->lsm_opts); + if (rc) + goto out_security_failure; + + free_secdata(secdata); + + while ((p = strsep(&raw, ",")) != NULL) { + substring_t args[MAX_OPT_ARGS]; + unsigned long option; + int token; + + if (!*p) + continue; + + dfprintk(MOUNT, "NFS: parsing nfs mount option '%s'\n", p); + + token = match_token(p, nfs_mount_option_tokens, args); + switch (token) { + + /* + * boolean options: foo/nofoo + */ + case Opt_soft: + mnt->flags |= NFS_MOUNT_SOFT; + break; + case Opt_hard: + mnt->flags &= ~NFS_MOUNT_SOFT; + break; + case Opt_posix: + mnt->flags |= NFS_MOUNT_POSIX; + break; + case Opt_noposix: + mnt->flags &= ~NFS_MOUNT_POSIX; + break; + case Opt_cto: + mnt->flags &= ~NFS_MOUNT_NOCTO; + break; + case Opt_nocto: + mnt->flags |= NFS_MOUNT_NOCTO; + break; + case Opt_ac: + mnt->flags &= ~NFS_MOUNT_NOAC; + break; + case Opt_noac: + mnt->flags |= NFS_MOUNT_NOAC; + break; + case Opt_lock: + mnt->flags &= ~NFS_MOUNT_NONLM; + mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + case Opt_nolock: + mnt->flags |= NFS_MOUNT_NONLM; + mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + case Opt_udp: + mnt->flags &= ~NFS_MOUNT_TCP; + mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP; + break; + case Opt_tcp: + mnt->flags |= NFS_MOUNT_TCP; + mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP; + break; + case Opt_rdma: + mnt->flags |= NFS_MOUNT_TCP; /* for side protocols */ + mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA; + xprt_load_transport(p); + break; + case Opt_acl: + mnt->flags &= ~NFS_MOUNT_NOACL; + break; + case Opt_noacl: + mnt->flags |= NFS_MOUNT_NOACL; + break; + case Opt_rdirplus: + mnt->flags &= ~NFS_MOUNT_NORDIRPLUS; + break; + case Opt_nordirplus: + mnt->flags |= NFS_MOUNT_NORDIRPLUS; + break; + case Opt_sharecache: + mnt->flags &= ~NFS_MOUNT_UNSHARED; + break; + case Opt_nosharecache: + mnt->flags |= NFS_MOUNT_UNSHARED; + break; + case Opt_resvport: + mnt->flags &= ~NFS_MOUNT_NORESVPORT; + break; + case Opt_noresvport: + mnt->flags |= NFS_MOUNT_NORESVPORT; + break; + case Opt_fscache: + mnt->options |= NFS_OPTION_FSCACHE; + kfree(mnt->fscache_uniq); + mnt->fscache_uniq = NULL; + break; + case Opt_nofscache: + mnt->options &= ~NFS_OPTION_FSCACHE; + kfree(mnt->fscache_uniq); + mnt->fscache_uniq = NULL; + break; + case Opt_migration: + mnt->options |= NFS_OPTION_MIGRATION; + break; + case Opt_nomigration: + mnt->options &= NFS_OPTION_MIGRATION; + break; + + /* + * options that take numeric values + */ + case Opt_port: + if (nfs_get_option_ul(args, &option) || + option > USHRT_MAX) + goto out_invalid_value; + mnt->nfs_server.port = option; + break; + case Opt_rsize: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->rsize = option; + break; + case Opt_wsize: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->wsize = option; + break; + case Opt_bsize: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->bsize = option; + break; + case Opt_timeo: + if (nfs_get_option_ul(args, &option) || option == 0) + goto out_invalid_value; + mnt->timeo = option; + break; + case Opt_retrans: + if (nfs_get_option_ul(args, &option) || option == 0) + goto out_invalid_value; + mnt->retrans = option; + break; + case Opt_acregmin: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->acregmin = option; + break; + case Opt_acregmax: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->acregmax = option; + break; + case Opt_acdirmin: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->acdirmin = option; + break; + case Opt_acdirmax: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->acdirmax = option; + break; + case Opt_actimeo: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->acregmin = mnt->acregmax = + mnt->acdirmin = mnt->acdirmax = option; + break; + case Opt_namelen: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + mnt->namlen = option; + break; + case Opt_mountport: + if (nfs_get_option_ul(args, &option) || + option > USHRT_MAX) + goto out_invalid_value; + mnt->mount_server.port = option; + break; + case Opt_mountvers: + if (nfs_get_option_ul(args, &option) || + option < NFS_MNT_VERSION || + option > NFS_MNT3_VERSION) + goto out_invalid_value; + mnt->mount_server.version = option; + break; + case Opt_minorversion: + if (nfs_get_option_ul(args, &option)) + goto out_invalid_value; + if (option > NFS4_MAX_MINOR_VERSION) + goto out_invalid_value; + mnt->minorversion = option; + break; + + /* + * options that take text values + */ + case Opt_nfsvers: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + rc = nfs_parse_version_string(string, mnt, args); + kfree(string); + if (!rc) + goto out_invalid_value; + break; + case Opt_sec: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + rc = nfs_parse_security_flavors(string, mnt); + kfree(string); + if (!rc) { + dfprintk(MOUNT, "NFS: unrecognized " + "security flavor\n"); + return 0; + } + break; + case Opt_proto: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + token = match_token(string, + nfs_xprt_protocol_tokens, args); + + protofamily = AF_INET; + switch (token) { + case Opt_xprt_udp6: + protofamily = AF_INET6; + case Opt_xprt_udp: + mnt->flags &= ~NFS_MOUNT_TCP; + mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP; + break; + case Opt_xprt_tcp6: + protofamily = AF_INET6; + case Opt_xprt_tcp: + mnt->flags |= NFS_MOUNT_TCP; + mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP; + break; + case Opt_xprt_rdma: + /* vector side protocols to TCP */ + mnt->flags |= NFS_MOUNT_TCP; + mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA; + xprt_load_transport(string); + break; + default: + dfprintk(MOUNT, "NFS: unrecognized " + "transport protocol\n"); + kfree(string); + return 0; + } + kfree(string); + break; + case Opt_mountproto: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + token = match_token(string, + nfs_xprt_protocol_tokens, args); + kfree(string); + + mountfamily = AF_INET; + switch (token) { + case Opt_xprt_udp6: + mountfamily = AF_INET6; + case Opt_xprt_udp: + mnt->mount_server.protocol = XPRT_TRANSPORT_UDP; + break; + case Opt_xprt_tcp6: + mountfamily = AF_INET6; + case Opt_xprt_tcp: + mnt->mount_server.protocol = XPRT_TRANSPORT_TCP; + break; + case Opt_xprt_rdma: /* not used for side protocols */ + default: + dfprintk(MOUNT, "NFS: unrecognized " + "transport protocol\n"); + return 0; + } + break; + case Opt_addr: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + mnt->nfs_server.addrlen = + rpc_pton(mnt->net, string, strlen(string), + (struct sockaddr *) + &mnt->nfs_server.address, + sizeof(mnt->nfs_server.address)); + kfree(string); + if (mnt->nfs_server.addrlen == 0) + goto out_invalid_address; + break; + case Opt_clientaddr: + if (nfs_get_option_str(args, &mnt->client_address)) + goto out_nomem; + break; + case Opt_mounthost: + if (nfs_get_option_str(args, + &mnt->mount_server.hostname)) + goto out_nomem; + break; + case Opt_mountaddr: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + mnt->mount_server.addrlen = + rpc_pton(mnt->net, string, strlen(string), + (struct sockaddr *) + &mnt->mount_server.address, + sizeof(mnt->mount_server.address)); + kfree(string); + if (mnt->mount_server.addrlen == 0) + goto out_invalid_address; + break; + case Opt_lookupcache: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + token = match_token(string, + nfs_lookupcache_tokens, args); + kfree(string); + switch (token) { + case Opt_lookupcache_all: + mnt->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE); + break; + case Opt_lookupcache_positive: + mnt->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE; + mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG; + break; + case Opt_lookupcache_none: + mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE; + break; + default: + dfprintk(MOUNT, "NFS: invalid " + "lookupcache argument\n"); + return 0; + }; + break; + case Opt_fscache_uniq: + if (nfs_get_option_str(args, &mnt->fscache_uniq)) + goto out_nomem; + mnt->options |= NFS_OPTION_FSCACHE; + break; + case Opt_local_lock: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + token = match_token(string, nfs_local_lock_tokens, + args); + kfree(string); + switch (token) { + case Opt_local_lock_all: + mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + case Opt_local_lock_flock: + mnt->flags |= NFS_MOUNT_LOCAL_FLOCK; + break; + case Opt_local_lock_posix: + mnt->flags |= NFS_MOUNT_LOCAL_FCNTL; + break; + case Opt_local_lock_none: + mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + default: + dfprintk(MOUNT, "NFS: invalid " + "local_lock argument\n"); + return 0; + }; + break; + + /* + * Special options + */ + case Opt_sloppy: + sloppy = 1; + dfprintk(MOUNT, "NFS: relaxing parsing rules\n"); + break; + case Opt_userspace: + case Opt_deprecated: + dfprintk(MOUNT, "NFS: ignoring mount option " + "'%s'\n", p); + break; + + default: + invalid_option = 1; + dfprintk(MOUNT, "NFS: unrecognized mount option " + "'%s'\n", p); + } + } + + if (!sloppy && invalid_option) + return 0; + + if (mnt->minorversion && mnt->version != 4) + goto out_minorversion_mismatch; + + if (mnt->options & NFS_OPTION_MIGRATION && + (mnt->version != 4 || mnt->minorversion != 0)) + goto out_migration_misuse; + + /* + * verify that any proto=/mountproto= options match the address + * families in the addr=/mountaddr= options. + */ + if (protofamily != AF_UNSPEC && + protofamily != mnt->nfs_server.address.ss_family) + goto out_proto_mismatch; + + if (mountfamily != AF_UNSPEC) { + if (mnt->mount_server.addrlen) { + if (mountfamily != mnt->mount_server.address.ss_family) + goto out_mountproto_mismatch; + } else { + if (mountfamily != mnt->nfs_server.address.ss_family) + goto out_mountproto_mismatch; + } + } + + return 1; + +out_mountproto_mismatch: + printk(KERN_INFO "NFS: mount server address does not match mountproto= " + "option\n"); + return 0; +out_proto_mismatch: + printk(KERN_INFO "NFS: server address does not match proto= option\n"); + return 0; +out_invalid_address: + printk(KERN_INFO "NFS: bad IP address specified: %s\n", p); + return 0; +out_invalid_value: + printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p); + return 0; +out_minorversion_mismatch: + printk(KERN_INFO "NFS: mount option vers=%u does not support " + "minorversion=%u\n", mnt->version, mnt->minorversion); + return 0; +out_migration_misuse: + printk(KERN_INFO + "NFS: 'migration' not supported for this NFS version\n"); + return 0; +out_nomem: + printk(KERN_INFO "NFS: not enough memory to parse option\n"); + return 0; +out_security_failure: + free_secdata(secdata); + printk(KERN_INFO "NFS: security options invalid: %d\n", rc); + return 0; +} + +/* + * Ensure that a specified authtype in args->auth_info is supported by + * the server. Returns 0 and sets args->selected_flavor if it's ok, and + * -EACCES if not. + */ +static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, + rpc_authflavor_t *server_authlist, unsigned int count) +{ + rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; + unsigned int i; + + /* + * If the sec= mount option is used, the specified flavor or AUTH_NULL + * must be in the list returned by the server. + * + * AUTH_NULL has a special meaning when it's in the server list - it + * means that the server will ignore the rpc creds, so any flavor + * can be used. + */ + for (i = 0; i < count; i++) { + flavor = server_authlist[i]; + + if (nfs_auth_info_match(&args->auth_info, flavor) || + flavor == RPC_AUTH_NULL) + goto out; + } + + dfprintk(MOUNT, + "NFS: specified auth flavors not supported by server\n"); + return -EACCES; + +out: + args->selected_flavor = flavor; + dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor); + return 0; +} + +/* + * Use the remote server's MOUNT service to request the NFS file handle + * corresponding to the provided path. + */ +static int nfs_request_mount(struct nfs_parsed_mount_data *args, + struct nfs_fh *root_fh, + rpc_authflavor_t *server_authlist, + unsigned int *server_authlist_len) +{ + struct nfs_mount_request request = { + .sap = (struct sockaddr *) + &args->mount_server.address, + .dirpath = args->nfs_server.export_path, + .protocol = args->mount_server.protocol, + .fh = root_fh, + .noresvport = args->flags & NFS_MOUNT_NORESVPORT, + .auth_flav_len = server_authlist_len, + .auth_flavs = server_authlist, + .net = args->net, + }; + int status; + + if (args->mount_server.version == 0) { + switch (args->version) { + default: + args->mount_server.version = NFS_MNT3_VERSION; + break; + case 2: + args->mount_server.version = NFS_MNT_VERSION; + } + } + request.version = args->mount_server.version; + + if (args->mount_server.hostname) + request.hostname = args->mount_server.hostname; + else + request.hostname = args->nfs_server.hostname; + + /* + * Construct the mount server's address. + */ + if (args->mount_server.address.ss_family == AF_UNSPEC) { + memcpy(request.sap, &args->nfs_server.address, + args->nfs_server.addrlen); + args->mount_server.addrlen = args->nfs_server.addrlen; + } + request.salen = args->mount_server.addrlen; + nfs_set_port(request.sap, &args->mount_server.port, 0); + + /* + * Now ask the mount server to map our export path + * to a file handle. + */ + status = nfs_mount(&request); + if (status != 0) { + dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", + request.hostname, status); + return status; + } + + return 0; +} + +static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + int status; + unsigned int i; + bool tried_auth_unix = false; + bool auth_null_in_list = false; + struct nfs_server *server = ERR_PTR(-EACCES); + struct nfs_parsed_mount_data *args = mount_info->parsed; + rpc_authflavor_t authlist[NFS_MAX_SECFLAVORS]; + unsigned int authlist_len = ARRAY_SIZE(authlist); + + status = nfs_request_mount(args, mount_info->mntfh, authlist, + &authlist_len); + if (status) + return ERR_PTR(status); + + /* + * Was a sec= authflavor specified in the options? First, verify + * whether the server supports it, and then just try to use it if so. + */ + if (args->auth_info.flavor_len > 0) { + status = nfs_verify_authflavors(args, authlist, authlist_len); + dfprintk(MOUNT, "NFS: using auth flavor %u\n", + args->selected_flavor); + if (status) + return ERR_PTR(status); + return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); + } + + /* + * No sec= option was provided. RFC 2623, section 2.7 suggests we + * SHOULD prefer the flavor listed first. However, some servers list + * AUTH_NULL first. Avoid ever choosing AUTH_NULL. + */ + for (i = 0; i < authlist_len; ++i) { + rpc_authflavor_t flavor; + struct rpcsec_gss_info info; + + flavor = authlist[i]; + switch (flavor) { + case RPC_AUTH_UNIX: + tried_auth_unix = true; + break; + case RPC_AUTH_NULL: + auth_null_in_list = true; + continue; + default: + if (rpcauth_get_gssinfo(flavor, &info) != 0) + continue; + /* Fallthrough */ + } + dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor); + args->selected_flavor = flavor; + server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); + if (!IS_ERR(server)) + return server; + } + + /* + * Nothing we tried so far worked. At this point, give up if we've + * already tried AUTH_UNIX or if the server's list doesn't contain + * AUTH_NULL + */ + if (tried_auth_unix || !auth_null_in_list) + return server; + + /* Last chance! Try AUTH_UNIX */ + dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; + return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); +} + +struct dentry *nfs_try_mount(int flags, const char *dev_name, + struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct nfs_server *server; + + if (mount_info->parsed->need_mount) + server = nfs_try_mount_request(mount_info, nfs_mod); + else + server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); + + if (IS_ERR(server)) + return ERR_CAST(server); + + return nfs_fs_mount_common(server, flags, dev_name, mount_info, nfs_mod); +} +EXPORT_SYMBOL_GPL(nfs_try_mount); + +/* + * Split "dev_name" into "hostname:export_path". + * + * The leftmost colon demarks the split between the server's hostname + * and the export path. If the hostname starts with a left square + * bracket, then it may contain colons. + * + * Note: caller frees hostname and export path, even on error. + */ +static int nfs_parse_devname(const char *dev_name, + char **hostname, size_t maxnamlen, + char **export_path, size_t maxpathlen) +{ + size_t len; + char *end; + + /* Is the host name protected with square brakcets? */ + if (*dev_name == '[') { + end = strchr(++dev_name, ']'); + if (end == NULL || end[1] != ':') + goto out_bad_devname; + + len = end - dev_name; + end++; + } else { + char *comma; + + end = strchr(dev_name, ':'); + if (end == NULL) + goto out_bad_devname; + len = end - dev_name; + + /* kill possible hostname list: not supported */ + comma = strchr(dev_name, ','); + if (comma != NULL && comma < end) + *comma = 0; + } + + if (len > maxnamlen) + goto out_hostname; + + /* N.B. caller will free nfs_server.hostname in all cases */ + *hostname = kstrndup(dev_name, len, GFP_KERNEL); + if (*hostname == NULL) + goto out_nomem; + len = strlen(++end); + if (len > maxpathlen) + goto out_path; + *export_path = kstrndup(end, len, GFP_KERNEL); + if (!*export_path) + goto out_nomem; + + dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", *export_path); + return 0; + +out_bad_devname: + dfprintk(MOUNT, "NFS: device name not in host:path format\n"); + return -EINVAL; + +out_nomem: + dfprintk(MOUNT, "NFS: not enough memory to parse device name\n"); + return -ENOMEM; + +out_hostname: + dfprintk(MOUNT, "NFS: server hostname too long\n"); + return -ENAMETOOLONG; + +out_path: + dfprintk(MOUNT, "NFS: export pathname too long\n"); + return -ENAMETOOLONG; +} + +/* + * Validate the NFS2/NFS3 mount data + * - fills in the mount root filehandle + * + * For option strings, user space handles the following behaviors: + * + * + DNS: mapping server host name to IP address ("addr=" option) + * + * + failure mode: how to behave if a mount request can't be handled + * immediately ("fg/bg" option) + * + * + retry: how often to retry a mount request ("retry=" option) + * + * + breaking back: trying proto=udp after proto=tcp, v2 after v3, + * mountproto=tcp after mountproto=udp, and so on + */ +static int nfs23_validate_mount_data(void *options, + struct nfs_parsed_mount_data *args, + struct nfs_fh *mntfh, + const char *dev_name) +{ + struct nfs_mount_data *data = (struct nfs_mount_data *)options; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; + + if (data == NULL) + goto out_no_data; + + args->version = NFS_DEFAULT_VERSION; + switch (data->version) { + case 1: + data->namlen = 0; + case 2: + data->bsize = 0; + case 3: + if (data->flags & NFS_MOUNT_VER3) + goto out_no_v3; + data->root.size = NFS2_FHSIZE; + memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); + /* Turn off security negotiation */ + extra_flags |= NFS_MOUNT_SECFLAVOUR; + case 4: + if (data->flags & NFS_MOUNT_SECFLAVOUR) + goto out_no_sec; + case 5: + memset(data->context, 0, sizeof(data->context)); + case 6: + if (data->flags & NFS_MOUNT_VER3) { + if (data->root.size > NFS3_FHSIZE || data->root.size == 0) + goto out_invalid_fh; + mntfh->size = data->root.size; + args->version = 3; + } else { + mntfh->size = NFS2_FHSIZE; + args->version = 2; + } + + + memcpy(mntfh->data, data->root.data, mntfh->size); + if (mntfh->size < sizeof(mntfh->data)) + memset(mntfh->data + mntfh->size, 0, + sizeof(mntfh->data) - mntfh->size); + + /* + * Translate to nfs_parsed_mount_data, which nfs_fill_super + * can deal with. + */ + args->flags = data->flags & NFS_MOUNT_FLAGMASK; + args->flags |= extra_flags; + args->rsize = data->rsize; + args->wsize = data->wsize; + args->timeo = data->timeo; + args->retrans = data->retrans; + args->acregmin = data->acregmin; + args->acregmax = data->acregmax; + args->acdirmin = data->acdirmin; + args->acdirmax = data->acdirmax; + args->need_mount = false; + + memcpy(sap, &data->addr, sizeof(data->addr)); + args->nfs_server.addrlen = sizeof(data->addr); + args->nfs_server.port = ntohs(data->addr.sin_port); + if (!nfs_verify_server_address(sap)) + goto out_no_address; + + if (!(data->flags & NFS_MOUNT_TCP)) + args->nfs_server.protocol = XPRT_TRANSPORT_UDP; + /* N.B. caller will free nfs_server.hostname in all cases */ + args->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL); + args->namlen = data->namlen; + args->bsize = data->bsize; + + if (data->flags & NFS_MOUNT_SECFLAVOUR) + args->selected_flavor = data->pseudoflavor; + else + args->selected_flavor = RPC_AUTH_UNIX; + if (!args->nfs_server.hostname) + goto out_nomem; + + if (!(data->flags & NFS_MOUNT_NONLM)) + args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK| + NFS_MOUNT_LOCAL_FCNTL); + else + args->flags |= (NFS_MOUNT_LOCAL_FLOCK| + NFS_MOUNT_LOCAL_FCNTL); + /* + * The legacy version 6 binary mount data from userspace has a + * field used only to transport selinux information into the + * the kernel. To continue to support that functionality we + * have a touch of selinux knowledge here in the NFS code. The + * userspace code converted context=blah to just blah so we are + * converting back to the full string selinux understands. + */ + if (data->context[0]){ +#ifdef CONFIG_SECURITY_SELINUX + int rc; + char *opts_str = kmalloc(sizeof(data->context) + 8, GFP_KERNEL); + if (!opts_str) + return -ENOMEM; + strcpy(opts_str, "context="); + data->context[NFS_MAX_CONTEXT_LEN] = '\0'; + strcat(opts_str, &data->context[0]); + rc = security_sb_parse_opts_str(opts_str, &args->lsm_opts); + kfree(opts_str); + if (rc) + return rc; +#else + return -EINVAL; +#endif + } + + break; + default: + return NFS_TEXT_DATA; + } + + return 0; + +out_no_data: + dfprintk(MOUNT, "NFS: mount program didn't pass any mount data\n"); + return -EINVAL; + +out_no_v3: + dfprintk(MOUNT, "NFS: nfs_mount_data version %d does not support v3\n", + data->version); + return -EINVAL; + +out_no_sec: + dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n"); + return -EINVAL; + +out_nomem: + dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n"); + return -ENOMEM; + +out_no_address: + dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); + return -EINVAL; + +out_invalid_fh: + dfprintk(MOUNT, "NFS: invalid root filehandle\n"); + return -EINVAL; +} + +#if IS_ENABLED(CONFIG_NFS_V4) +static int nfs_validate_mount_data(struct file_system_type *fs_type, + void *options, + struct nfs_parsed_mount_data *args, + struct nfs_fh *mntfh, + const char *dev_name) +{ + if (fs_type == &nfs_fs_type) + return nfs23_validate_mount_data(options, args, mntfh, dev_name); + return nfs4_validate_mount_data(options, args, dev_name); +} +#else +static int nfs_validate_mount_data(struct file_system_type *fs_type, + void *options, + struct nfs_parsed_mount_data *args, + struct nfs_fh *mntfh, + const char *dev_name) +{ + return nfs23_validate_mount_data(options, args, mntfh, dev_name); +} +#endif + +static int nfs_validate_text_mount_data(void *options, + struct nfs_parsed_mount_data *args, + const char *dev_name) +{ + int port = 0; + int max_namelen = PAGE_SIZE; + int max_pathlen = NFS_MAXPATHLEN; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + + if (nfs_parse_mount_options((char *)options, args) == 0) + return -EINVAL; + + if (!nfs_verify_server_address(sap)) + goto out_no_address; + + if (args->version == 4) { +#if IS_ENABLED(CONFIG_NFS_V4) + port = NFS_PORT; + max_namelen = NFS4_MAXNAMLEN; + max_pathlen = NFS4_MAXPATHLEN; + nfs_validate_transport_protocol(args); + if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; + nfs4_validate_mount_flags(args); +#else + goto out_v4_not_compiled; +#endif /* CONFIG_NFS_V4 */ + } else + nfs_set_mount_transport_protocol(args); + + nfs_set_port(sap, &args->nfs_server.port, port); + + return nfs_parse_devname(dev_name, + &args->nfs_server.hostname, + max_namelen, + &args->nfs_server.export_path, + max_pathlen); + +#if !IS_ENABLED(CONFIG_NFS_V4) +out_v4_not_compiled: + dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); + return -EPROTONOSUPPORT; +#else +out_invalid_transport_udp: + dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n"); + return -EINVAL; +#endif /* !CONFIG_NFS_V4 */ + +out_no_address: + dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); + return -EINVAL; +} + +#define NFS_REMOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \ + | NFS_MOUNT_SECURE \ + | NFS_MOUNT_TCP \ + | NFS_MOUNT_VER3 \ + | NFS_MOUNT_KERBEROS \ + | NFS_MOUNT_NONLM \ + | NFS_MOUNT_BROKEN_SUID \ + | NFS_MOUNT_STRICTLOCK \ + | NFS_MOUNT_LEGACY_INTERFACE) + +#define NFS_MOUNT_CMP_FLAGMASK (NFS_REMOUNT_CMP_FLAGMASK & \ + ~(NFS_MOUNT_UNSHARED | NFS_MOUNT_NORESVPORT)) + +static int +nfs_compare_remount_data(struct nfs_server *nfss, + struct nfs_parsed_mount_data *data) +{ + if ((data->flags ^ nfss->flags) & NFS_REMOUNT_CMP_FLAGMASK || + data->rsize != nfss->rsize || + data->wsize != nfss->wsize || + data->version != nfss->nfs_client->rpc_ops->version || + data->minorversion != nfss->nfs_client->cl_minorversion || + data->retrans != nfss->client->cl_timeout->to_retries || + !nfs_auth_info_match(&data->auth_info, nfss->client->cl_auth->au_flavor) || + data->acregmin != nfss->acregmin / HZ || + data->acregmax != nfss->acregmax / HZ || + data->acdirmin != nfss->acdirmin / HZ || + data->acdirmax != nfss->acdirmax / HZ || + data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) || + data->nfs_server.port != nfss->port || + data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen || + !rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address, + (struct sockaddr *)&nfss->nfs_client->cl_addr)) + return -EINVAL; + + return 0; +} + +int +nfs_remount(struct super_block *sb, int *flags, char *raw_data) +{ + int error; + struct nfs_server *nfss = sb->s_fs_info; + struct nfs_parsed_mount_data *data; + struct nfs_mount_data *options = (struct nfs_mount_data *)raw_data; + struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data; + u32 nfsvers = nfss->nfs_client->rpc_ops->version; + + sync_filesystem(sb); + + /* + * Userspace mount programs that send binary options generally send + * them populated with default values. We have no way to know which + * ones were explicitly specified. Fall back to legacy behavior and + * just return success. + */ + if ((nfsvers == 4 && (!options4 || options4->version == 1)) || + (nfsvers <= 3 && (!options || (options->version >= 1 && + options->version <= 6)))) + return 0; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + /* fill out struct with values from existing mount */ + data->flags = nfss->flags; + data->rsize = nfss->rsize; + data->wsize = nfss->wsize; + data->retrans = nfss->client->cl_timeout->to_retries; + data->selected_flavor = nfss->client->cl_auth->au_flavor; + data->acregmin = nfss->acregmin / HZ; + data->acregmax = nfss->acregmax / HZ; + data->acdirmin = nfss->acdirmin / HZ; + data->acdirmax = nfss->acdirmax / HZ; + data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; + data->nfs_server.port = nfss->port; + data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; + data->version = nfsvers; + data->minorversion = nfss->nfs_client->cl_minorversion; + data->net = current->nsproxy->net_ns; + memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr, + data->nfs_server.addrlen); + + /* overwrite those values with any that were specified */ + error = -EINVAL; + if (!nfs_parse_mount_options((char *)options, data)) + goto out; + + /* + * noac is a special case. It implies -o sync, but that's not + * necessarily reflected in the mtab options. do_remount_sb + * will clear MS_SYNCHRONOUS if -o sync wasn't specified in the + * remount options, so we have to explicitly reset it. + */ + if (data->flags & NFS_MOUNT_NOAC) + *flags |= MS_SYNCHRONOUS; + + /* compare new mount options with old ones */ + error = nfs_compare_remount_data(nfss, data); +out: + kfree(data); + return error; +} +EXPORT_SYMBOL_GPL(nfs_remount); + +/* + * Initialise the common bits of the superblock + */ +inline void nfs_initialise_sb(struct super_block *sb) +{ + struct nfs_server *server = NFS_SB(sb); + + sb->s_magic = NFS_SUPER_MAGIC; + + /* We probably want something more informative here */ + snprintf(sb->s_id, sizeof(sb->s_id), + "%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev)); + + if (sb->s_blocksize == 0) + sb->s_blocksize = nfs_block_bits(server->wsize, + &sb->s_blocksize_bits); + + sb->s_bdi = &server->backing_dev_info; + + nfs_super_set_maxbytes(sb, server->maxfilesize); +} + +/* + * Finish setting up an NFS2/3 superblock + */ +void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) +{ + struct nfs_parsed_mount_data *data = mount_info->parsed; + struct nfs_server *server = NFS_SB(sb); + + sb->s_blocksize_bits = 0; + sb->s_blocksize = 0; + sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr; + sb->s_op = server->nfs_client->cl_nfs_mod->sops; + if (data && data->bsize) + sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits); + + if (server->nfs_client->rpc_ops->version != 2) { + /* The VFS shouldn't apply the umask to mode bits. We will do + * so ourselves when necessary. + */ + sb->s_flags |= MS_POSIXACL; + sb->s_time_gran = 1; + } + + nfs_initialise_sb(sb); +} +EXPORT_SYMBOL_GPL(nfs_fill_super); + +/* + * Finish setting up a cloned NFS2/3/4 superblock + */ +void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) +{ + const struct super_block *old_sb = mount_info->cloned->sb; + struct nfs_server *server = NFS_SB(sb); + + sb->s_blocksize_bits = old_sb->s_blocksize_bits; + sb->s_blocksize = old_sb->s_blocksize; + sb->s_maxbytes = old_sb->s_maxbytes; + sb->s_xattr = old_sb->s_xattr; + sb->s_op = old_sb->s_op; + sb->s_time_gran = 1; + + if (server->nfs_client->rpc_ops->version != 2) { + /* The VFS shouldn't apply the umask to mode bits. We will do + * so ourselves when necessary. + */ + sb->s_flags |= MS_POSIXACL; + } + + nfs_initialise_sb(sb); +} + +static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags) +{ + const struct nfs_server *a = s->s_fs_info; + const struct rpc_clnt *clnt_a = a->client; + const struct rpc_clnt *clnt_b = b->client; + + if ((s->s_flags & NFS_MS_MASK) != (flags & NFS_MS_MASK)) + goto Ebusy; + if (a->nfs_client != b->nfs_client) + goto Ebusy; + if ((a->flags ^ b->flags) & NFS_MOUNT_CMP_FLAGMASK) + goto Ebusy; + if (a->wsize != b->wsize) + goto Ebusy; + if (a->rsize != b->rsize) + goto Ebusy; + if (a->acregmin != b->acregmin) + goto Ebusy; + if (a->acregmax != b->acregmax) + goto Ebusy; + if (a->acdirmin != b->acdirmin) + goto Ebusy; + if (a->acdirmax != b->acdirmax) + goto Ebusy; + if (b->auth_info.flavor_len > 0 && + clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) + goto Ebusy; + return 1; +Ebusy: + return 0; +} + +struct nfs_sb_mountdata { + struct nfs_server *server; + int mntflags; +}; + +static int nfs_set_super(struct super_block *s, void *data) +{ + struct nfs_sb_mountdata *sb_mntdata = data; + struct nfs_server *server = sb_mntdata->server; + int ret; + + s->s_flags = sb_mntdata->mntflags; + s->s_fs_info = server; + s->s_d_op = server->nfs_client->rpc_ops->dentry_ops; + ret = set_anon_super(s, server); + if (ret == 0) + server->s_dev = s->s_dev; + return ret; +} + +static int nfs_compare_super_address(struct nfs_server *server1, + struct nfs_server *server2) +{ + struct sockaddr *sap1, *sap2; + + sap1 = (struct sockaddr *)&server1->nfs_client->cl_addr; + sap2 = (struct sockaddr *)&server2->nfs_client->cl_addr; + + if (sap1->sa_family != sap2->sa_family) + return 0; + + switch (sap1->sa_family) { + case AF_INET: { + struct sockaddr_in *sin1 = (struct sockaddr_in *)sap1; + struct sockaddr_in *sin2 = (struct sockaddr_in *)sap2; + if (sin1->sin_addr.s_addr != sin2->sin_addr.s_addr) + return 0; + if (sin1->sin_port != sin2->sin_port) + return 0; + break; + } + case AF_INET6: { + struct sockaddr_in6 *sin1 = (struct sockaddr_in6 *)sap1; + struct sockaddr_in6 *sin2 = (struct sockaddr_in6 *)sap2; + if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) + return 0; + if (sin1->sin6_port != sin2->sin6_port) + return 0; + break; + } + default: + return 0; + } + + return 1; +} + +static int nfs_compare_super(struct super_block *sb, void *data) +{ + struct nfs_sb_mountdata *sb_mntdata = data; + struct nfs_server *server = sb_mntdata->server, *old = NFS_SB(sb); + int mntflags = sb_mntdata->mntflags; + + if (!nfs_compare_super_address(old, server)) + return 0; + /* Note: NFS_MOUNT_UNSHARED == NFS4_MOUNT_UNSHARED */ + if (old->flags & NFS_MOUNT_UNSHARED) + return 0; + if (memcmp(&old->fsid, &server->fsid, sizeof(old->fsid)) != 0) + return 0; + return nfs_compare_mount_options(sb, server, mntflags); +} + +#ifdef CONFIG_NFS_FSCACHE +static void nfs_get_cache_cookie(struct super_block *sb, + struct nfs_parsed_mount_data *parsed, + struct nfs_clone_mount *cloned) +{ + struct nfs_server *nfss = NFS_SB(sb); + char *uniq = NULL; + int ulen = 0; + + nfss->fscache_key = NULL; + nfss->fscache = NULL; + + if (parsed) { + if (!(parsed->options & NFS_OPTION_FSCACHE)) + return; + if (parsed->fscache_uniq) { + uniq = parsed->fscache_uniq; + ulen = strlen(parsed->fscache_uniq); + } + } else if (cloned) { + struct nfs_server *mnt_s = NFS_SB(cloned->sb); + if (!(mnt_s->options & NFS_OPTION_FSCACHE)) + return; + if (mnt_s->fscache_key) { + uniq = mnt_s->fscache_key->key.uniquifier; + ulen = mnt_s->fscache_key->key.uniq_len; + }; + } else + return; + + nfs_fscache_get_super_cookie(sb, uniq, ulen); +} +#else +static void nfs_get_cache_cookie(struct super_block *sb, + struct nfs_parsed_mount_data *parsed, + struct nfs_clone_mount *cloned) +{ +} +#endif + +static int nfs_bdi_register(struct nfs_server *server) +{ + return bdi_register_dev(&server->backing_dev_info, server->s_dev); +} + +int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, + struct nfs_mount_info *mount_info) +{ + int error; + unsigned long kflags = 0, kflags_out = 0; + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) + kflags |= SECURITY_LSM_NATIVE_LABELS; + + error = security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts, + kflags, &kflags_out); + if (error) + goto err; + + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL && + !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) + NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL; +err: + return error; +} +EXPORT_SYMBOL_GPL(nfs_set_sb_security); + +int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, + struct nfs_mount_info *mount_info) +{ + /* clone any lsm security options from the parent to the new sb */ + if (d_inode(mntroot)->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) + return -ESTALE; + return security_sb_clone_mnt_opts(mount_info->cloned->sb, s); +} +EXPORT_SYMBOL_GPL(nfs_clone_sb_security); + +struct dentry *nfs_fs_mount_common(struct nfs_server *server, + int flags, const char *dev_name, + struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct super_block *s; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + int (*compare_super)(struct super_block *, void *) = nfs_compare_super; + struct nfs_sb_mountdata sb_mntdata = { + .mntflags = flags, + .server = server, + }; + int error; + + if (server->flags & NFS_MOUNT_UNSHARED) + compare_super = NULL; + + /* -o noac implies -o sync */ + if (server->flags & NFS_MOUNT_NOAC) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + + if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL) + if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + + /* Get a superblock - note that we may end up sharing one that already exists */ + s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata); + if (IS_ERR(s)) { + mntroot = ERR_CAST(s); + goto out_err_nosb; + } + + if (s->s_fs_info != server) { + nfs_free_server(server); + server = NULL; + } else { + error = nfs_bdi_register(server); + if (error) { + mntroot = ERR_PTR(error); + goto error_splat_super; + } + server->super = s; + } + + if (!s->s_root) { + /* initial superblock/root creation */ + mount_info->fill_super(s, mount_info); + nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); + } + + mntroot = nfs_get_root(s, mount_info->mntfh, dev_name); + if (IS_ERR(mntroot)) + goto error_splat_super; + + error = mount_info->set_security(s, mntroot, mount_info); + if (error) + goto error_splat_root; + + s->s_flags |= MS_ACTIVE; + +out: + return mntroot; + +out_err_nosb: + nfs_free_server(server); + goto out; + +error_splat_root: + dput(mntroot); + mntroot = ERR_PTR(error); +error_splat_super: + deactivate_locked_super(s); + goto out; +} +EXPORT_SYMBOL_GPL(nfs_fs_mount_common); + +struct dentry *nfs_fs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_mount_info mount_info = { + .fill_super = nfs_fill_super, + .set_security = nfs_set_sb_security, + }; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + struct nfs_subversion *nfs_mod; + int error; + + mount_info.parsed = nfs_alloc_parsed_mount_data(); + mount_info.mntfh = nfs_alloc_fhandle(); + if (mount_info.parsed == NULL || mount_info.mntfh == NULL) + goto out; + + /* Validate the mount data */ + error = nfs_validate_mount_data(fs_type, raw_data, mount_info.parsed, mount_info.mntfh, dev_name); + if (error == NFS_TEXT_DATA) + error = nfs_validate_text_mount_data(raw_data, mount_info.parsed, dev_name); + if (error < 0) { + mntroot = ERR_PTR(error); + goto out; + } + + nfs_mod = get_nfs_version(mount_info.parsed->version); + if (IS_ERR(nfs_mod)) { + mntroot = ERR_CAST(nfs_mod); + goto out; + } + + mntroot = nfs_mod->rpc_ops->try_mount(flags, dev_name, &mount_info, nfs_mod); + + put_nfs_version(nfs_mod); +out: + nfs_free_parsed_mount_data(mount_info.parsed); + nfs_free_fhandle(mount_info.mntfh); + return mntroot; +} +EXPORT_SYMBOL_GPL(nfs_fs_mount); + +/* + * Destroy an NFS2/3 superblock + */ +void nfs_kill_super(struct super_block *s) +{ + struct nfs_server *server = NFS_SB(s); + dev_t dev = s->s_dev; + + generic_shutdown_super(s); + + nfs_fscache_release_super_cookie(s); + + nfs_free_server(server); + free_anon_bdev(dev); +} +EXPORT_SYMBOL_GPL(nfs_kill_super); + +/* + * Clone an NFS2/3/4 server record on xdev traversal (FSID-change) + */ +static struct dentry * +nfs_xdev_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + struct nfs_clone_mount *data = raw_data; + struct nfs_mount_info mount_info = { + .fill_super = nfs_clone_super, + .set_security = nfs_clone_sb_security, + .cloned = data, + }; + struct nfs_server *server; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod; + + dprintk("--> nfs_xdev_mount()\n"); + + mount_info.mntfh = mount_info.cloned->fh; + + /* create a new volume representation */ + server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); + + if (IS_ERR(server)) + mntroot = ERR_CAST(server); + else + mntroot = nfs_fs_mount_common(server, flags, + dev_name, &mount_info, nfs_mod); + + dprintk("<-- nfs_xdev_mount() = %ld\n", + IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L); + return mntroot; +} + +#if IS_ENABLED(CONFIG_NFS_V4) + +static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) +{ + args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3| + NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL); +} + +/* + * Validate NFSv4 mount options + */ +static int nfs4_validate_mount_data(void *options, + struct nfs_parsed_mount_data *args, + const char *dev_name) +{ + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; + char *c; + + if (data == NULL) + goto out_no_data; + + args->version = 4; + + switch (data->version) { + case 1: + if (data->host_addrlen > sizeof(args->nfs_server.address)) + goto out_no_address; + if (data->host_addrlen == 0) + goto out_no_address; + args->nfs_server.addrlen = data->host_addrlen; + if (copy_from_user(sap, data->host_addr, data->host_addrlen)) + return -EFAULT; + if (!nfs_verify_server_address(sap)) + goto out_no_address; + args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); + + if (data->auth_flavourlen) { + rpc_authflavor_t pseudoflavor; + if (data->auth_flavourlen > 1) + goto out_inval_auth; + if (copy_from_user(&pseudoflavor, + data->auth_flavours, + sizeof(pseudoflavor))) + return -EFAULT; + args->selected_flavor = pseudoflavor; + } else + args->selected_flavor = RPC_AUTH_UNIX; + + c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); + if (IS_ERR(c)) + return PTR_ERR(c); + args->nfs_server.hostname = c; + + c = strndup_user(data->mnt_path.data, NFS4_MAXPATHLEN); + if (IS_ERR(c)) + return PTR_ERR(c); + args->nfs_server.export_path = c; + dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", c); + + c = strndup_user(data->client_addr.data, 16); + if (IS_ERR(c)) + return PTR_ERR(c); + args->client_address = c; + + /* + * Translate to nfs_parsed_mount_data, which nfs4_fill_super + * can deal with. + */ + + args->flags = data->flags & NFS4_MOUNT_FLAGMASK; + args->rsize = data->rsize; + args->wsize = data->wsize; + args->timeo = data->timeo; + args->retrans = data->retrans; + args->acregmin = data->acregmin; + args->acregmax = data->acregmax; + args->acdirmin = data->acdirmin; + args->acdirmax = data->acdirmax; + args->nfs_server.protocol = data->proto; + nfs_validate_transport_protocol(args); + if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; + + break; + default: + return NFS_TEXT_DATA; + } + + return 0; + +out_no_data: + dfprintk(MOUNT, "NFS4: mount program didn't pass any mount data\n"); + return -EINVAL; + +out_inval_auth: + dfprintk(MOUNT, "NFS4: Invalid number of RPC auth flavours %d\n", + data->auth_flavourlen); + return -EINVAL; + +out_no_address: + dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n"); + return -EINVAL; + +out_invalid_transport_udp: + dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n"); + return -EINVAL; +} + +/* + * NFS v4 module parameters need to stay in the + * NFS client for backwards compatibility + */ +unsigned int nfs_callback_set_tcpport; +unsigned short nfs_callback_tcpport; +/* Default cache timeout is 10 minutes */ +unsigned int nfs_idmap_cache_timeout = 600; +/* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */ +bool nfs4_disable_idmapping = true; +unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE; +unsigned short send_implementation_id = 1; +char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = ""; +bool recover_lost_locks = false; + +EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport); +EXPORT_SYMBOL_GPL(nfs_callback_tcpport); +EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout); +EXPORT_SYMBOL_GPL(nfs4_disable_idmapping); +EXPORT_SYMBOL_GPL(max_session_slots); +EXPORT_SYMBOL_GPL(send_implementation_id); +EXPORT_SYMBOL_GPL(nfs4_client_id_uniquifier); +EXPORT_SYMBOL_GPL(recover_lost_locks); + +#define NFS_CALLBACK_MAXPORTNR (65535U) + +static int param_set_portnr(const char *val, const struct kernel_param *kp) +{ + unsigned long num; + int ret; + + if (!val) + return -EINVAL; + ret = kstrtoul(val, 0, &num); + if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; +} +static struct kernel_param_ops param_ops_portnr = { + .set = param_set_portnr, + .get = param_get_uint, +}; +#define param_check_portnr(name, p) __param_check(name, p, unsigned int); + +module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); +module_param(nfs_idmap_cache_timeout, int, 0644); +module_param(nfs4_disable_idmapping, bool, 0644); +module_param_string(nfs4_unique_id, nfs4_client_id_uniquifier, + NFS4_CLIENT_ID_UNIQ_LEN, 0600); +MODULE_PARM_DESC(nfs4_disable_idmapping, + "Turn off NFSv4 idmapping when using 'sec=sys'"); +module_param(max_session_slots, ushort, 0644); +MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 " + "requests the client will negotiate"); +module_param(send_implementation_id, ushort, 0644); +MODULE_PARM_DESC(send_implementation_id, + "Send implementation ID with NFSv4.1 exchange_id"); +MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string"); + +module_param(recover_lost_locks, bool, 0644); +MODULE_PARM_DESC(recover_lost_locks, + "If the server reports that a lock might be lost, " + "try to recover it risking data corruption."); + + +#endif /* CONFIG_NFS_V4 */ diff --git a/kernel/fs/nfs/symlink.c b/kernel/fs/nfs/symlink.c new file mode 100644 index 000000000..2d5620065 --- /dev/null +++ b/kernel/fs/nfs/symlink.c @@ -0,0 +1,78 @@ +/* + * linux/fs/nfs/symlink.c + * + * Copyright (C) 1992 Rick Sladkey + * + * Optimization changes Copyright (C) 1994 Florian La Roche + * + * Jun 7 1999, cache symlink lookups in the page cache. -DaveM + * + * nfs symlink handling code + */ + +#include <linux/time.h> +#include <linux/errno.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs.h> +#include <linux/nfs2.h> +#include <linux/nfs_fs.h> +#include <linux/pagemap.h> +#include <linux/stat.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/namei.h> + +/* Symlink caching in the page cache is even more simplistic + * and straight-forward than readdir caching. + */ + +static int nfs_symlink_filler(struct inode *inode, struct page *page) +{ + int error; + + error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE); + if (error < 0) + goto error; + SetPageUptodate(page); + unlock_page(page); + return 0; + +error: + SetPageError(page); + unlock_page(page); + return -EIO; +} + +static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = d_inode(dentry); + struct page *page; + void *err; + + err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); + if (err) + goto read_failed; + page = read_cache_page(&inode->i_data, 0, + (filler_t *)nfs_symlink_filler, inode); + if (IS_ERR(page)) { + err = page; + goto read_failed; + } + nd_set_link(nd, kmap(page)); + return page; + +read_failed: + nd_set_link(nd, err); + return NULL; +} + +/* + * symlinks can't do much... + */ +const struct inode_operations nfs_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = nfs_follow_link, + .put_link = page_put_link, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +}; diff --git a/kernel/fs/nfs/sysctl.c b/kernel/fs/nfs/sysctl.c new file mode 100644 index 000000000..bb6ed810f --- /dev/null +++ b/kernel/fs/nfs/sysctl.c @@ -0,0 +1,64 @@ +/* + * linux/fs/nfs/sysctl.c + * + * Sysctl interface to NFS parameters + */ +#include <linux/types.h> +#include <linux/linkage.h> +#include <linux/ctype.h> +#include <linux/fs.h> +#include <linux/sysctl.h> +#include <linux/module.h> +#include <linux/nfs_fs.h> + +static struct ctl_table_header *nfs_callback_sysctl_table; + +static struct ctl_table nfs_cb_sysctls[] = { + { + .procname = "nfs_mountpoint_timeout", + .data = &nfs_mountpoint_expiry_timeout, + .maxlen = sizeof(nfs_mountpoint_expiry_timeout), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "nfs_congestion_kb", + .data = &nfs_congestion_kb, + .maxlen = sizeof(nfs_congestion_kb), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static struct ctl_table nfs_cb_sysctl_dir[] = { + { + .procname = "nfs", + .mode = 0555, + .child = nfs_cb_sysctls, + }, + { } +}; + +static struct ctl_table nfs_cb_sysctl_root[] = { + { + .procname = "fs", + .mode = 0555, + .child = nfs_cb_sysctl_dir, + }, + { } +}; + +int nfs_register_sysctl(void) +{ + nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root); + if (nfs_callback_sysctl_table == NULL) + return -ENOMEM; + return 0; +} + +void nfs_unregister_sysctl(void) +{ + unregister_sysctl_table(nfs_callback_sysctl_table); + nfs_callback_sysctl_table = NULL; +} diff --git a/kernel/fs/nfs/unlink.c b/kernel/fs/nfs/unlink.c new file mode 100644 index 000000000..fa538b2ba --- /dev/null +++ b/kernel/fs/nfs/unlink.c @@ -0,0 +1,604 @@ +/* + * linux/fs/nfs/unlink.c + * + * nfs sillydelete handling + * + */ + +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/dcache.h> +#include <linux/sunrpc/sched.h> +#include <linux/sunrpc/clnt.h> +#include <linux/nfs_fs.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/namei.h> +#include <linux/fsnotify.h> + +#include "internal.h" +#include "nfs4_fs.h" +#include "iostat.h" +#include "delegation.h" + +#include "nfstrace.h" + +/** + * nfs_free_unlinkdata - release data from a sillydelete operation. + * @data: pointer to unlink structure. + */ +static void +nfs_free_unlinkdata(struct nfs_unlinkdata *data) +{ + iput(data->dir); + put_rpccred(data->cred); + kfree(data->args.name.name); + kfree(data); +} + +#define NAME_ALLOC_LEN(len) ((len+16) & ~15) +/** + * nfs_copy_dname - copy dentry name to data structure + * @dentry: pointer to dentry + * @data: nfs_unlinkdata + */ +static int nfs_copy_dname(struct dentry *dentry, struct nfs_unlinkdata *data) +{ + char *str; + int len = dentry->d_name.len; + + str = kmemdup(dentry->d_name.name, NAME_ALLOC_LEN(len), GFP_KERNEL); + if (!str) + return -ENOMEM; + data->args.name.len = len; + data->args.name.name = str; + return 0; +} + +static void nfs_free_dname(struct nfs_unlinkdata *data) +{ + kfree(data->args.name.name); + data->args.name.name = NULL; + data->args.name.len = 0; +} + +static void nfs_dec_sillycount(struct inode *dir) +{ + struct nfs_inode *nfsi = NFS_I(dir); + if (atomic_dec_return(&nfsi->silly_count) == 1) + wake_up(&nfsi->waitqueue); +} + +/** + * nfs_async_unlink_done - Sillydelete post-processing + * @task: rpc_task of the sillydelete + * + * Do the directory attribute update. + */ +static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) +{ + struct nfs_unlinkdata *data = calldata; + struct inode *dir = data->dir; + + trace_nfs_sillyrename_unlink(data, task->tk_status); + if (!NFS_PROTO(dir)->unlink_done(task, dir)) + rpc_restart_call_prepare(task); +} + +/** + * nfs_async_unlink_release - Release the sillydelete data. + * @task: rpc_task of the sillydelete + * + * We need to call nfs_put_unlinkdata as a 'tk_release' task since the + * rpc_task would be freed too. + */ +static void nfs_async_unlink_release(void *calldata) +{ + struct nfs_unlinkdata *data = calldata; + struct super_block *sb = data->dir->i_sb; + + nfs_dec_sillycount(data->dir); + nfs_free_unlinkdata(data); + nfs_sb_deactive(sb); +} + +static void nfs_unlink_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_unlinkdata *data = calldata; + NFS_PROTO(data->dir)->unlink_rpc_prepare(task, data); +} + +static const struct rpc_call_ops nfs_unlink_ops = { + .rpc_call_done = nfs_async_unlink_done, + .rpc_release = nfs_async_unlink_release, + .rpc_call_prepare = nfs_unlink_prepare, +}; + +static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data) +{ + struct rpc_message msg = { + .rpc_argp = &data->args, + .rpc_resp = &data->res, + .rpc_cred = data->cred, + }; + struct rpc_task_setup task_setup_data = { + .rpc_message = &msg, + .callback_ops = &nfs_unlink_ops, + .callback_data = data, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC, + }; + struct rpc_task *task; + struct dentry *alias; + + alias = d_lookup(parent, &data->args.name); + if (alias != NULL) { + int ret; + void *devname_garbage = NULL; + + /* + * Hey, we raced with lookup... See if we need to transfer + * the sillyrename information to the aliased dentry. + */ + nfs_free_dname(data); + ret = nfs_copy_dname(alias, data); + spin_lock(&alias->d_lock); + if (ret == 0 && d_really_is_positive(alias) && + !(alias->d_flags & DCACHE_NFSFS_RENAMED)) { + devname_garbage = alias->d_fsdata; + alias->d_fsdata = data; + alias->d_flags |= DCACHE_NFSFS_RENAMED; + ret = 1; + } else + ret = 0; + spin_unlock(&alias->d_lock); + nfs_dec_sillycount(dir); + dput(alias); + /* + * If we'd displaced old cached devname, free it. At that + * point dentry is definitely not a root, so we won't need + * that anymore. + */ + kfree(devname_garbage); + return ret; + } + data->dir = igrab(dir); + if (!data->dir) { + nfs_dec_sillycount(dir); + return 0; + } + nfs_sb_active(dir->i_sb); + data->args.fh = NFS_FH(dir); + nfs_fattr_init(data->res.dir_attr); + + NFS_PROTO(dir)->unlink_setup(&msg, dir); + + task_setup_data.rpc_client = NFS_CLIENT(dir); + task = rpc_run_task(&task_setup_data); + if (!IS_ERR(task)) + rpc_put_task_async(task); + return 1; +} + +static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data) +{ + struct dentry *parent; + struct inode *dir; + int ret = 0; + + + parent = dget_parent(dentry); + if (parent == NULL) + goto out_free; + dir = d_inode(parent); + /* Non-exclusive lock protects against concurrent lookup() calls */ + spin_lock(&dir->i_lock); + if (atomic_inc_not_zero(&NFS_I(dir)->silly_count) == 0) { + /* Deferred delete */ + hlist_add_head(&data->list, &NFS_I(dir)->silly_list); + spin_unlock(&dir->i_lock); + ret = 1; + goto out_dput; + } + spin_unlock(&dir->i_lock); + ret = nfs_do_call_unlink(parent, dir, data); +out_dput: + dput(parent); +out_free: + return ret; +} + +void nfs_wait_on_sillyrename(struct dentry *dentry) +{ + struct nfs_inode *nfsi = NFS_I(d_inode(dentry)); + + wait_event(nfsi->waitqueue, atomic_read(&nfsi->silly_count) <= 1); +} + +void nfs_block_sillyrename(struct dentry *dentry) +{ + struct nfs_inode *nfsi = NFS_I(d_inode(dentry)); + + wait_event(nfsi->waitqueue, atomic_cmpxchg(&nfsi->silly_count, 1, 0) == 1); +} + +void nfs_unblock_sillyrename(struct dentry *dentry) +{ + struct inode *dir = d_inode(dentry); + struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_unlinkdata *data; + + atomic_inc(&nfsi->silly_count); + spin_lock(&dir->i_lock); + while (!hlist_empty(&nfsi->silly_list)) { + if (!atomic_inc_not_zero(&nfsi->silly_count)) + break; + data = hlist_entry(nfsi->silly_list.first, struct nfs_unlinkdata, list); + hlist_del(&data->list); + spin_unlock(&dir->i_lock); + if (nfs_do_call_unlink(dentry, dir, data) == 0) + nfs_free_unlinkdata(data); + spin_lock(&dir->i_lock); + } + spin_unlock(&dir->i_lock); +} + +/** + * nfs_async_unlink - asynchronous unlinking of a file + * @dir: parent directory of dentry + * @dentry: dentry to unlink + */ +static int +nfs_async_unlink(struct inode *dir, struct dentry *dentry) +{ + struct nfs_unlinkdata *data; + int status = -ENOMEM; + void *devname_garbage = NULL; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + goto out; + + data->cred = rpc_lookup_cred(); + if (IS_ERR(data->cred)) { + status = PTR_ERR(data->cred); + goto out_free; + } + data->res.dir_attr = &data->dir_attr; + + status = -EBUSY; + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + goto out_unlock; + dentry->d_flags |= DCACHE_NFSFS_RENAMED; + devname_garbage = dentry->d_fsdata; + dentry->d_fsdata = data; + spin_unlock(&dentry->d_lock); + /* + * If we'd displaced old cached devname, free it. At that + * point dentry is definitely not a root, so we won't need + * that anymore. + */ + kfree(devname_garbage); + return 0; +out_unlock: + spin_unlock(&dentry->d_lock); + put_rpccred(data->cred); +out_free: + kfree(data); +out: + return status; +} + +/** + * nfs_complete_unlink - Initialize completion of the sillydelete + * @dentry: dentry to delete + * @inode: inode + * + * Since we're most likely to be called by dentry_iput(), we + * only use the dentry to find the sillydelete. We then copy the name + * into the qstr. + */ +void +nfs_complete_unlink(struct dentry *dentry, struct inode *inode) +{ + struct nfs_unlinkdata *data = NULL; + + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + dentry->d_flags &= ~DCACHE_NFSFS_RENAMED; + data = dentry->d_fsdata; + dentry->d_fsdata = NULL; + } + spin_unlock(&dentry->d_lock); + + if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data))) + nfs_free_unlinkdata(data); +} + +/* Cancel a queued async unlink. Called when a sillyrename run fails. */ +static void +nfs_cancel_async_unlink(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + struct nfs_unlinkdata *data = dentry->d_fsdata; + + dentry->d_flags &= ~DCACHE_NFSFS_RENAMED; + dentry->d_fsdata = NULL; + spin_unlock(&dentry->d_lock); + nfs_free_unlinkdata(data); + return; + } + spin_unlock(&dentry->d_lock); +} + +/** + * nfs_async_rename_done - Sillyrename post-processing + * @task: rpc_task of the sillyrename + * @calldata: nfs_renamedata for the sillyrename + * + * Do the directory attribute updates and the d_move + */ +static void nfs_async_rename_done(struct rpc_task *task, void *calldata) +{ + struct nfs_renamedata *data = calldata; + struct inode *old_dir = data->old_dir; + struct inode *new_dir = data->new_dir; + struct dentry *old_dentry = data->old_dentry; + + trace_nfs_sillyrename_rename(old_dir, old_dentry, + new_dir, data->new_dentry, task->tk_status); + if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) { + rpc_restart_call_prepare(task); + return; + } + + if (data->complete) + data->complete(task, data); +} + +/** + * nfs_async_rename_release - Release the sillyrename data. + * @calldata: the struct nfs_renamedata to be released + */ +static void nfs_async_rename_release(void *calldata) +{ + struct nfs_renamedata *data = calldata; + struct super_block *sb = data->old_dir->i_sb; + + if (d_really_is_positive(data->old_dentry)) + nfs_mark_for_revalidate(d_inode(data->old_dentry)); + + dput(data->old_dentry); + dput(data->new_dentry); + iput(data->old_dir); + iput(data->new_dir); + nfs_sb_deactive(sb); + put_rpccred(data->cred); + kfree(data); +} + +static void nfs_rename_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_renamedata *data = calldata; + NFS_PROTO(data->old_dir)->rename_rpc_prepare(task, data); +} + +static const struct rpc_call_ops nfs_rename_ops = { + .rpc_call_done = nfs_async_rename_done, + .rpc_release = nfs_async_rename_release, + .rpc_call_prepare = nfs_rename_prepare, +}; + +/** + * nfs_async_rename - perform an asynchronous rename operation + * @old_dir: directory that currently holds the dentry to be renamed + * @new_dir: target directory for the rename + * @old_dentry: original dentry to be renamed + * @new_dentry: dentry to which the old_dentry should be renamed + * + * It's expected that valid references to the dentries and inodes are held + */ +struct rpc_task * +nfs_async_rename(struct inode *old_dir, struct inode *new_dir, + struct dentry *old_dentry, struct dentry *new_dentry, + void (*complete)(struct rpc_task *, struct nfs_renamedata *)) +{ + struct nfs_renamedata *data; + struct rpc_message msg = { }; + struct rpc_task_setup task_setup_data = { + .rpc_message = &msg, + .callback_ops = &nfs_rename_ops, + .workqueue = nfsiod_workqueue, + .rpc_client = NFS_CLIENT(old_dir), + .flags = RPC_TASK_ASYNC, + }; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + return ERR_PTR(-ENOMEM); + task_setup_data.callback_data = data; + + data->cred = rpc_lookup_cred(); + if (IS_ERR(data->cred)) { + struct rpc_task *task = ERR_CAST(data->cred); + kfree(data); + return task; + } + + msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + msg.rpc_cred = data->cred; + + /* set up nfs_renamedata */ + data->old_dir = old_dir; + ihold(old_dir); + data->new_dir = new_dir; + ihold(new_dir); + data->old_dentry = dget(old_dentry); + data->new_dentry = dget(new_dentry); + nfs_fattr_init(&data->old_fattr); + nfs_fattr_init(&data->new_fattr); + data->complete = complete; + + /* set up nfs_renameargs */ + data->args.old_dir = NFS_FH(old_dir); + data->args.old_name = &old_dentry->d_name; + data->args.new_dir = NFS_FH(new_dir); + data->args.new_name = &new_dentry->d_name; + + /* set up nfs_renameres */ + data->res.old_fattr = &data->old_fattr; + data->res.new_fattr = &data->new_fattr; + + nfs_sb_active(old_dir->i_sb); + + NFS_PROTO(data->old_dir)->rename_setup(&msg, old_dir); + + return rpc_run_task(&task_setup_data); +} + +/* + * Perform tasks needed when a sillyrename is done such as cancelling the + * queued async unlink if it failed. + */ +static void +nfs_complete_sillyrename(struct rpc_task *task, struct nfs_renamedata *data) +{ + struct dentry *dentry = data->old_dentry; + + if (task->tk_status != 0) { + nfs_cancel_async_unlink(dentry); + return; + } + + /* + * vfs_unlink and the like do not issue this when a file is + * sillyrenamed, so do it here. + */ + fsnotify_nameremove(dentry, 0); +} + +#define SILLYNAME_PREFIX ".nfs" +#define SILLYNAME_PREFIX_LEN ((unsigned)sizeof(SILLYNAME_PREFIX) - 1) +#define SILLYNAME_FILEID_LEN ((unsigned)sizeof(u64) << 1) +#define SILLYNAME_COUNTER_LEN ((unsigned)sizeof(unsigned int) << 1) +#define SILLYNAME_LEN (SILLYNAME_PREFIX_LEN + \ + SILLYNAME_FILEID_LEN + \ + SILLYNAME_COUNTER_LEN) + +/** + * nfs_sillyrename - Perform a silly-rename of a dentry + * @dir: inode of directory that contains dentry + * @dentry: dentry to be sillyrenamed + * + * NFSv2/3 is stateless and the server doesn't know when the client is + * holding a file open. To prevent application problems when a file is + * unlinked while it's still open, the client performs a "silly-rename". + * That is, it renames the file to a hidden file in the same directory, + * and only performs the unlink once the last reference to it is put. + * + * The final cleanup is done during dentry_iput. + * + * (Note: NFSv4 is stateful, and has opens, so in theory an NFSv4 server + * could take responsibility for keeping open files referenced. The server + * would also need to ensure that opened-but-deleted files were kept over + * reboots. However, we may not assume a server does so. (RFC 5661 + * does provide an OPEN4_RESULT_PRESERVE_UNLINKED flag that a server can + * use to advertise that it does this; some day we may take advantage of + * it.)) + */ +int +nfs_sillyrename(struct inode *dir, struct dentry *dentry) +{ + static unsigned int sillycounter; + unsigned char silly[SILLYNAME_LEN + 1]; + unsigned long long fileid; + struct dentry *sdentry; + struct rpc_task *task; + int error = -EBUSY; + + dfprintk(VFS, "NFS: silly-rename(%pd2, ct=%d)\n", + dentry, d_count(dentry)); + nfs_inc_stats(dir, NFSIOS_SILLYRENAME); + + /* + * We don't allow a dentry to be silly-renamed twice. + */ + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + goto out; + + fileid = NFS_FILEID(d_inode(dentry)); + + /* Return delegation in anticipation of the rename */ + NFS_PROTO(d_inode(dentry))->return_delegation(d_inode(dentry)); + + sdentry = NULL; + do { + int slen; + dput(sdentry); + sillycounter++; + slen = scnprintf(silly, sizeof(silly), + SILLYNAME_PREFIX "%0*llx%0*x", + SILLYNAME_FILEID_LEN, fileid, + SILLYNAME_COUNTER_LEN, sillycounter); + + dfprintk(VFS, "NFS: trying to rename %pd to %s\n", + dentry, silly); + + sdentry = lookup_one_len(silly, dentry->d_parent, slen); + /* + * N.B. Better to return EBUSY here ... it could be + * dangerous to delete the file while it's in use. + */ + if (IS_ERR(sdentry)) + goto out; + } while (d_inode(sdentry) != NULL); /* need negative lookup */ + + /* queue unlink first. Can't do this from rpc_release as it + * has to allocate memory + */ + error = nfs_async_unlink(dir, dentry); + if (error) + goto out_dput; + + /* populate unlinkdata with the right dname */ + error = nfs_copy_dname(sdentry, + (struct nfs_unlinkdata *)dentry->d_fsdata); + if (error) { + nfs_cancel_async_unlink(dentry); + goto out_dput; + } + + /* run the rename task, undo unlink if it fails */ + task = nfs_async_rename(dir, dir, dentry, sdentry, + nfs_complete_sillyrename); + if (IS_ERR(task)) { + error = -EBUSY; + nfs_cancel_async_unlink(dentry); + goto out_dput; + } + + /* wait for the RPC task to complete, unless a SIGKILL intervenes */ + error = rpc_wait_for_completion_task(task); + if (error == 0) + error = task->tk_status; + switch (error) { + case 0: + /* The rename succeeded */ + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + d_move(dentry, sdentry); + break; + case -ERESTARTSYS: + /* The result of the rename is unknown. Play it safe by + * forcing a new lookup */ + d_drop(dentry); + d_drop(sdentry); + } + rpc_put_task(task); +out_dput: + dput(sdentry); +out: + return error; +} diff --git a/kernel/fs/nfs/write.c b/kernel/fs/nfs/write.c new file mode 100644 index 000000000..dfc19f157 --- /dev/null +++ b/kernel/fs/nfs/write.c @@ -0,0 +1,2019 @@ +/* + * linux/fs/nfs/write.c + * + * Write file data over NFS. + * + * Copyright (C) 1996, 1997, Olaf Kirch <okir@monad.swb.de> + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/file.h> +#include <linux/writeback.h> +#include <linux/swap.h> +#include <linux/migrate.h> + +#include <linux/sunrpc/clnt.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs_page.h> +#include <linux/backing-dev.h> +#include <linux/export.h> + +#include <asm/uaccess.h> + +#include "delegation.h" +#include "internal.h" +#include "iostat.h" +#include "nfs4_fs.h" +#include "fscache.h" +#include "pnfs.h" + +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_PAGECACHE + +#define MIN_POOL_WRITE (32) +#define MIN_POOL_COMMIT (4) + +/* + * Local function declarations + */ +static void nfs_redirty_request(struct nfs_page *req); +static const struct rpc_call_ops nfs_commit_ops; +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; +static const struct nfs_commit_completion_ops nfs_commit_completion_ops; +static const struct nfs_rw_ops nfs_rw_write_ops; +static void nfs_clear_request_commit(struct nfs_page *req); +static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, + struct inode *inode); +static struct nfs_page * +nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, + struct page *page); + +static struct kmem_cache *nfs_wdata_cachep; +static mempool_t *nfs_wdata_mempool; +static struct kmem_cache *nfs_cdata_cachep; +static mempool_t *nfs_commit_mempool; + +struct nfs_commit_data *nfs_commitdata_alloc(void) +{ + struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO); + + if (p) { + memset(p, 0, sizeof(*p)); + INIT_LIST_HEAD(&p->pages); + } + return p; +} +EXPORT_SYMBOL_GPL(nfs_commitdata_alloc); + +void nfs_commit_free(struct nfs_commit_data *p) +{ + mempool_free(p, nfs_commit_mempool); +} +EXPORT_SYMBOL_GPL(nfs_commit_free); + +static struct nfs_pgio_header *nfs_writehdr_alloc(void) +{ + struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO); + + if (p) + memset(p, 0, sizeof(*p)); + return p; +} + +static void nfs_writehdr_free(struct nfs_pgio_header *hdr) +{ + mempool_free(hdr, nfs_wdata_mempool); +} + +static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) +{ + ctx->error = error; + smp_wmb(); + set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); +} + +/* + * nfs_page_find_head_request_locked - find head request associated with @page + * + * must be called while holding the inode lock. + * + * returns matching head request with reference held, or NULL if not found. + */ +static struct nfs_page * +nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page) +{ + struct nfs_page *req = NULL; + + if (PagePrivate(page)) + req = (struct nfs_page *)page_private(page); + else if (unlikely(PageSwapCache(page))) + req = nfs_page_search_commits_for_head_request_locked(nfsi, + page); + + if (req) { + WARN_ON_ONCE(req->wb_head != req); + kref_get(&req->wb_kref); + } + + return req; +} + +/* + * nfs_page_find_head_request - find head request associated with @page + * + * returns matching head request with reference held, or NULL if not found. + */ +static struct nfs_page *nfs_page_find_head_request(struct page *page) +{ + struct inode *inode = page_file_mapping(page)->host; + struct nfs_page *req = NULL; + + spin_lock(&inode->i_lock); + req = nfs_page_find_head_request_locked(NFS_I(inode), page); + spin_unlock(&inode->i_lock); + return req; +} + +/* Adjust the file length if we're writing beyond the end */ +static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count) +{ + struct inode *inode = page_file_mapping(page)->host; + loff_t end, i_size; + pgoff_t end_index; + + spin_lock(&inode->i_lock); + i_size = i_size_read(inode); + end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; + if (i_size > 0 && page_file_index(page) < end_index) + goto out; + end = page_file_offset(page) + ((loff_t)offset+count); + if (i_size >= end) + goto out; + i_size_write(inode, end); + nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); +out: + spin_unlock(&inode->i_lock); +} + +/* A writeback failed: mark the page as bad, and invalidate the page cache */ +static void nfs_set_pageerror(struct page *page) +{ + nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); +} + +/* + * nfs_page_group_search_locked + * @head - head request of page group + * @page_offset - offset into page + * + * Search page group with head @head to find a request that contains the + * page offset @page_offset. + * + * Returns a pointer to the first matching nfs request, or NULL if no + * match is found. + * + * Must be called with the page group lock held + */ +static struct nfs_page * +nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) +{ + struct nfs_page *req; + + WARN_ON_ONCE(head != head->wb_head); + WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_head->wb_flags)); + + req = head; + do { + if (page_offset >= req->wb_pgbase && + page_offset < (req->wb_pgbase + req->wb_bytes)) + return req; + + req = req->wb_this_page; + } while (req != head); + + return NULL; +} + +/* + * nfs_page_group_covers_page + * @head - head request of page group + * + * Return true if the page group with head @head covers the whole page, + * returns false otherwise + */ +static bool nfs_page_group_covers_page(struct nfs_page *req) +{ + struct nfs_page *tmp; + unsigned int pos = 0; + unsigned int len = nfs_page_length(req->wb_page); + + nfs_page_group_lock(req, false); + + do { + tmp = nfs_page_group_search_locked(req->wb_head, pos); + if (tmp) { + /* no way this should happen */ + WARN_ON_ONCE(tmp->wb_pgbase != pos); + pos += tmp->wb_bytes - (pos - tmp->wb_pgbase); + } + } while (tmp && pos < len); + + nfs_page_group_unlock(req); + WARN_ON_ONCE(pos > len); + return pos == len; +} + +/* We can set the PG_uptodate flag if we see that a write request + * covers the full page. + */ +static void nfs_mark_uptodate(struct nfs_page *req) +{ + if (PageUptodate(req->wb_page)) + return; + if (!nfs_page_group_covers_page(req)) + return; + SetPageUptodate(req->wb_page); +} + +static int wb_priority(struct writeback_control *wbc) +{ + int ret = 0; + if (wbc->for_reclaim) + return FLUSH_HIGHPRI | FLUSH_STABLE; + if (wbc->sync_mode == WB_SYNC_ALL) + ret = FLUSH_COND_STABLE; + if (wbc->for_kupdate || wbc->for_background) + ret |= FLUSH_LOWPRI; + return ret; +} + +/* + * NFS congestion control + */ + +int nfs_congestion_kb; + +#define NFS_CONGESTION_ON_THRESH (nfs_congestion_kb >> (PAGE_SHIFT-10)) +#define NFS_CONGESTION_OFF_THRESH \ + (NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2)) + +static void nfs_set_page_writeback(struct page *page) +{ + struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host); + int ret = test_set_page_writeback(page); + + WARN_ON_ONCE(ret != 0); + + if (atomic_long_inc_return(&nfss->writeback) > + NFS_CONGESTION_ON_THRESH) { + set_bdi_congested(&nfss->backing_dev_info, + BLK_RW_ASYNC); + } +} + +static void nfs_end_page_writeback(struct nfs_page *req) +{ + struct inode *inode = page_file_mapping(req->wb_page)->host; + struct nfs_server *nfss = NFS_SERVER(inode); + + if (!nfs_page_group_sync_on_bit(req, PG_WB_END)) + return; + + end_page_writeback(req->wb_page); + if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) + clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); +} + + +/* nfs_page_group_clear_bits + * @req - an nfs request + * clears all page group related bits from @req + */ +static void +nfs_page_group_clear_bits(struct nfs_page *req) +{ + clear_bit(PG_TEARDOWN, &req->wb_flags); + clear_bit(PG_UNLOCKPAGE, &req->wb_flags); + clear_bit(PG_UPTODATE, &req->wb_flags); + clear_bit(PG_WB_END, &req->wb_flags); + clear_bit(PG_REMOVE, &req->wb_flags); +} + + +/* + * nfs_unroll_locks_and_wait - unlock all newly locked reqs and wait on @req + * + * this is a helper function for nfs_lock_and_join_requests + * + * @inode - inode associated with request page group, must be holding inode lock + * @head - head request of page group, must be holding head lock + * @req - request that couldn't lock and needs to wait on the req bit lock + * @nonblock - if true, don't actually wait + * + * NOTE: this must be called holding page_group bit lock and inode spin lock + * and BOTH will be released before returning. + * + * returns 0 on success, < 0 on error. + */ +static int +nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head, + struct nfs_page *req, bool nonblock) + __releases(&inode->i_lock) +{ + struct nfs_page *tmp; + int ret; + + /* relinquish all the locks successfully grabbed this run */ + for (tmp = head ; tmp != req; tmp = tmp->wb_this_page) + nfs_unlock_request(tmp); + + WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags)); + + /* grab a ref on the request that will be waited on */ + kref_get(&req->wb_kref); + + nfs_page_group_unlock(head); + spin_unlock(&inode->i_lock); + + /* release ref from nfs_page_find_head_request_locked */ + nfs_release_request(head); + + if (!nonblock) + ret = nfs_wait_on_request(req); + else + ret = -EAGAIN; + nfs_release_request(req); + + return ret; +} + +/* + * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests + * + * @destroy_list - request list (using wb_this_page) terminated by @old_head + * @old_head - the old head of the list + * + * All subrequests must be locked and removed from all lists, so at this point + * they are only "active" in this function, and possibly in nfs_wait_on_request + * with a reference held by some other context. + */ +static void +nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, + struct nfs_page *old_head) +{ + while (destroy_list) { + struct nfs_page *subreq = destroy_list; + + destroy_list = (subreq->wb_this_page == old_head) ? + NULL : subreq->wb_this_page; + + WARN_ON_ONCE(old_head != subreq->wb_head); + + /* make sure old group is not used */ + subreq->wb_head = subreq; + subreq->wb_this_page = subreq; + + /* subreq is now totally disconnected from page group or any + * write / commit lists. last chance to wake any waiters */ + nfs_unlock_request(subreq); + + if (!test_bit(PG_TEARDOWN, &subreq->wb_flags)) { + /* release ref on old head request */ + nfs_release_request(old_head); + + nfs_page_group_clear_bits(subreq); + + /* release the PG_INODE_REF reference */ + if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) + nfs_release_request(subreq); + else + WARN_ON_ONCE(1); + } else { + WARN_ON_ONCE(test_bit(PG_CLEAN, &subreq->wb_flags)); + /* zombie requests have already released the last + * reference and were waiting on the rest of the + * group to complete. Since it's no longer part of a + * group, simply free the request */ + nfs_page_group_clear_bits(subreq); + nfs_free_request(subreq); + } + } +} + +/* + * nfs_lock_and_join_requests - join all subreqs to the head req and return + * a locked reference, cancelling any pending + * operations for this page. + * + * @page - the page used to lookup the "page group" of nfs_page structures + * @nonblock - if true, don't block waiting for request locks + * + * This function joins all sub requests to the head request by first + * locking all requests in the group, cancelling any pending operations + * and finally updating the head request to cover the whole range covered by + * the (former) group. All subrequests are removed from any write or commit + * lists, unlinked from the group and destroyed. + * + * Returns a locked, referenced pointer to the head request - which after + * this call is guaranteed to be the only request associated with the page. + * Returns NULL if no requests are found for @page, or a ERR_PTR if an + * error was encountered. + */ +static struct nfs_page * +nfs_lock_and_join_requests(struct page *page, bool nonblock) +{ + struct inode *inode = page_file_mapping(page)->host; + struct nfs_page *head, *subreq; + struct nfs_page *destroy_list = NULL; + unsigned int total_bytes; + int ret; + +try_again: + total_bytes = 0; + + WARN_ON_ONCE(destroy_list); + + spin_lock(&inode->i_lock); + + /* + * A reference is taken only on the head request which acts as a + * reference to the whole page group - the group will not be destroyed + * until the head reference is released. + */ + head = nfs_page_find_head_request_locked(NFS_I(inode), page); + + if (!head) { + spin_unlock(&inode->i_lock); + return NULL; + } + + /* holding inode lock, so always make a non-blocking call to try the + * page group lock */ + ret = nfs_page_group_lock(head, true); + if (ret < 0) { + spin_unlock(&inode->i_lock); + + if (!nonblock && ret == -EAGAIN) { + nfs_page_group_lock_wait(head); + nfs_release_request(head); + goto try_again; + } + + nfs_release_request(head); + return ERR_PTR(ret); + } + + /* lock each request in the page group */ + subreq = head; + do { + /* + * Subrequests are always contiguous, non overlapping + * and in order - but may be repeated (mirrored writes). + */ + if (subreq->wb_offset == (head->wb_offset + total_bytes)) { + /* keep track of how many bytes this group covers */ + total_bytes += subreq->wb_bytes; + } else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset || + ((subreq->wb_offset + subreq->wb_bytes) > + (head->wb_offset + total_bytes)))) { + nfs_page_group_unlock(head); + spin_unlock(&inode->i_lock); + return ERR_PTR(-EIO); + } + + if (!nfs_lock_request(subreq)) { + /* releases page group bit lock and + * inode spin lock and all references */ + ret = nfs_unroll_locks_and_wait(inode, head, + subreq, nonblock); + + if (ret == 0) + goto try_again; + + return ERR_PTR(ret); + } + + subreq = subreq->wb_this_page; + } while (subreq != head); + + /* Now that all requests are locked, make sure they aren't on any list. + * Commit list removal accounting is done after locks are dropped */ + subreq = head; + do { + nfs_clear_request_commit(subreq); + subreq = subreq->wb_this_page; + } while (subreq != head); + + /* unlink subrequests from head, destroy them later */ + if (head->wb_this_page != head) { + /* destroy list will be terminated by head */ + destroy_list = head->wb_this_page; + head->wb_this_page = head; + + /* change head request to cover whole range that + * the former page group covered */ + head->wb_bytes = total_bytes; + } + + /* + * prepare head request to be added to new pgio descriptor + */ + nfs_page_group_clear_bits(head); + + /* + * some part of the group was still on the inode list - otherwise + * the group wouldn't be involved in async write. + * grab a reference for the head request, iff it needs one. + */ + if (!test_and_set_bit(PG_INODE_REF, &head->wb_flags)) + kref_get(&head->wb_kref); + + nfs_page_group_unlock(head); + + /* drop lock to clean uprequests on destroy list */ + spin_unlock(&inode->i_lock); + + nfs_destroy_unlinked_subrequests(destroy_list, head); + + /* still holds ref on head from nfs_page_find_head_request_locked + * and still has lock on head from lock loop */ + return head; +} + +/* + * Find an associated nfs write request, and prepare to flush it out + * May return an error if the user signalled nfs_wait_on_request(). + */ +static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, + struct page *page, bool nonblock) +{ + struct nfs_page *req; + int ret = 0; + + req = nfs_lock_and_join_requests(page, nonblock); + if (!req) + goto out; + ret = PTR_ERR(req); + if (IS_ERR(req)) + goto out; + + nfs_set_page_writeback(page); + WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); + + ret = 0; + if (!nfs_pageio_add_request(pgio, req)) { + nfs_redirty_request(req); + ret = pgio->pg_error; + } +out: + return ret; +} + +static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) +{ + struct inode *inode = page_file_mapping(page)->host; + int ret; + + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); + nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); + + nfs_pageio_cond_complete(pgio, page_file_index(page)); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); + if (ret == -EAGAIN) { + redirty_page_for_writepage(wbc, page); + ret = 0; + } + return ret; +} + +/* + * Write an mmapped page to the server. + */ +static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) +{ + struct nfs_pageio_descriptor pgio; + int err; + + nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + false, &nfs_async_write_completion_ops); + err = nfs_do_writepage(page, wbc, &pgio); + nfs_pageio_complete(&pgio); + if (err < 0) + return err; + if (pgio.pg_error < 0) + return pgio.pg_error; + return 0; +} + +int nfs_writepage(struct page *page, struct writeback_control *wbc) +{ + int ret; + + ret = nfs_writepage_locked(page, wbc); + unlock_page(page); + return ret; +} + +static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data) +{ + int ret; + + ret = nfs_do_writepage(page, wbc, data); + unlock_page(page); + return ret; +} + +int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) +{ + struct inode *inode = mapping->host; + unsigned long *bitlock = &NFS_I(inode)->flags; + struct nfs_pageio_descriptor pgio; + int err; + + /* Stop dirtying of new pages while we sync */ + err = wait_on_bit_lock_action(bitlock, NFS_INO_FLUSHING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (err) + goto out_err; + + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); + + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, + &nfs_async_write_completion_ops); + err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); + nfs_pageio_complete(&pgio); + + clear_bit_unlock(NFS_INO_FLUSHING, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_INO_FLUSHING); + + if (err < 0) + goto out_err; + err = pgio.pg_error; + if (err < 0) + goto out_err; + return 0; +out_err: + return err; +} + +/* + * Insert a write request into an inode + */ +static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + WARN_ON_ONCE(req->wb_this_page != req); + + /* Lock the request! */ + nfs_lock_request(req); + + spin_lock(&inode->i_lock); + if (!nfsi->nrequests && + NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) + inode->i_version++; + /* + * Swap-space should not get truncated. Hence no need to plug the race + * with invalidate/truncate. + */ + if (likely(!PageSwapCache(req->wb_page))) { + set_bit(PG_MAPPED, &req->wb_flags); + SetPagePrivate(req->wb_page); + set_page_private(req->wb_page, (unsigned long)req); + } + nfsi->nrequests++; + /* this a head request for a page group - mark it as having an + * extra reference so sub groups can follow suit. + * This flag also informs pgio layer when to bump nrequests when + * adding subrequests. */ + WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); + kref_get(&req->wb_kref); + spin_unlock(&inode->i_lock); +} + +/* + * Remove a write request from an inode + */ +static void nfs_inode_remove_request(struct nfs_page *req) +{ + struct inode *inode = d_inode(req->wb_context->dentry); + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_page *head; + + if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { + head = req->wb_head; + + spin_lock(&inode->i_lock); + if (likely(!PageSwapCache(head->wb_page))) { + set_page_private(head->wb_page, 0); + ClearPagePrivate(head->wb_page); + smp_mb__after_atomic(); + wake_up_page(head->wb_page, PG_private); + clear_bit(PG_MAPPED, &head->wb_flags); + } + nfsi->nrequests--; + spin_unlock(&inode->i_lock); + } else { + spin_lock(&inode->i_lock); + nfsi->nrequests--; + spin_unlock(&inode->i_lock); + } + + if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) + nfs_release_request(req); +} + +static void +nfs_mark_request_dirty(struct nfs_page *req) +{ + __set_page_dirty_nobuffers(req->wb_page); +} + +/* + * nfs_page_search_commits_for_head_request_locked + * + * Search through commit lists on @inode for the head request for @page. + * Must be called while holding the inode (which is cinfo) lock. + * + * Returns the head request if found, or NULL if not found. + */ +static struct nfs_page * +nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, + struct page *page) +{ + struct nfs_page *freq, *t; + struct nfs_commit_info cinfo; + struct inode *inode = &nfsi->vfs_inode; + + nfs_init_cinfo_from_inode(&cinfo, inode); + + /* search through pnfs commit lists */ + freq = pnfs_search_commit_reqs(inode, &cinfo, page); + if (freq) + return freq->wb_head; + + /* Linearly search the commit list for the correct request */ + list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) { + if (freq->wb_page == page) + return freq->wb_head; + } + + return NULL; +} + +/** + * nfs_request_add_commit_list - add request to a commit list + * @req: pointer to a struct nfs_page + * @dst: commit list head + * @cinfo: holds list lock and accounting info + * + * This sets the PG_CLEAN bit, updates the cinfo count of + * number of outstanding requests requiring a commit as well as + * the MM page stats. + * + * The caller must _not_ hold the cinfo->lock, but must be + * holding the nfs_page lock. + */ +void +nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo) +{ + set_bit(PG_CLEAN, &(req)->wb_flags); + spin_lock(cinfo->lock); + nfs_list_add_request(req, dst); + cinfo->mds->ncommit++; + spin_unlock(cinfo->lock); + if (!cinfo->dreq) + nfs_mark_page_unstable(req->wb_page); +} +EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); + +/** + * nfs_request_remove_commit_list - Remove request from a commit list + * @req: pointer to a nfs_page + * @cinfo: holds list lock and accounting info + * + * This clears the PG_CLEAN bit, and updates the cinfo's count of + * number of outstanding requests requiring a commit + * It does not update the MM page stats. + * + * The caller _must_ hold the cinfo->lock and the nfs_page lock. + */ +void +nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo) +{ + if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) + return; + nfs_list_remove_request(req); + cinfo->mds->ncommit--; +} +EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list); + +static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, + struct inode *inode) +{ + cinfo->lock = &inode->i_lock; + cinfo->mds = &NFS_I(inode)->commit_info; + cinfo->ds = pnfs_get_ds_info(inode); + cinfo->dreq = NULL; + cinfo->completion_ops = &nfs_commit_completion_ops; +} + +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq) +{ + if (dreq) + nfs_init_cinfo_from_dreq(cinfo, dreq); + else + nfs_init_cinfo_from_inode(cinfo, inode); +} +EXPORT_SYMBOL_GPL(nfs_init_cinfo); + +/* + * Add a request to the inode's commit list. + */ +void +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, u32 ds_commit_idx) +{ + if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx)) + return; + nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); +} + +static void +nfs_clear_page_commit(struct page *page) +{ + dec_zone_page_state(page, NR_UNSTABLE_NFS); + dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE); +} + +/* Called holding inode (/cinfo) lock */ +static void +nfs_clear_request_commit(struct nfs_page *req) +{ + if (test_bit(PG_CLEAN, &req->wb_flags)) { + struct inode *inode = d_inode(req->wb_context->dentry); + struct nfs_commit_info cinfo; + + nfs_init_cinfo_from_inode(&cinfo, inode); + if (!pnfs_clear_request_commit(req, &cinfo)) { + nfs_request_remove_commit_list(req, &cinfo); + } + nfs_clear_page_commit(req->wb_page); + } +} + +int nfs_write_need_commit(struct nfs_pgio_header *hdr) +{ + if (hdr->verf.committed == NFS_DATA_SYNC) + return hdr->lseg == NULL; + return hdr->verf.committed != NFS_FILE_SYNC; +} + +static void nfs_write_completion(struct nfs_pgio_header *hdr) +{ + struct nfs_commit_info cinfo; + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + nfs_init_cinfo_from_inode(&cinfo, hdr->inode); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + bytes += req->wb_bytes; + nfs_list_remove_request(req); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && + (hdr->good_bytes < bytes)) { + nfs_set_pageerror(req->wb_page); + nfs_context_set_write_error(req->wb_context, hdr->error); + goto remove_req; + } + if (nfs_write_need_commit(hdr)) { + memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf)); + nfs_mark_request_commit(req, hdr->lseg, &cinfo, + hdr->pgio_mirror_idx); + goto next; + } +remove_req: + nfs_inode_remove_request(req); +next: + nfs_unlock_request(req); + nfs_end_page_writeback(req); + nfs_release_request(req); + } +out: + hdr->release(hdr); +} + +unsigned long +nfs_reqs_to_commit(struct nfs_commit_info *cinfo) +{ + return cinfo->mds->ncommit; +} + +/* cinfo->lock held by caller */ +int +nfs_scan_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) +{ + struct nfs_page *req, *tmp; + int ret = 0; + + list_for_each_entry_safe(req, tmp, src, wb_list) { + if (!nfs_lock_request(req)) + continue; + kref_get(&req->wb_kref); + if (cond_resched_lock(cinfo->lock)) + list_safe_reset_next(req, tmp, wb_list); + nfs_request_remove_commit_list(req, cinfo); + nfs_list_add_request(req, dst); + ret++; + if ((ret == max) && !cinfo->dreq) + break; + } + return ret; +} + +/* + * nfs_scan_commit - Scan an inode for commit requests + * @inode: NFS inode to scan + * @dst: mds destination list + * @cinfo: mds and ds lists of reqs ready to commit + * + * Moves requests from the inode's 'commit' request list. + * The requests are *not* checked to ensure that they form a contiguous set. + */ +int +nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) +{ + int ret = 0; + + spin_lock(cinfo->lock); + if (cinfo->mds->ncommit > 0) { + const int max = INT_MAX; + + ret = nfs_scan_commit_list(&cinfo->mds->list, dst, + cinfo, max); + ret += pnfs_scan_commit_lists(inode, cinfo, max - ret); + } + spin_unlock(cinfo->lock); + return ret; +} + +/* + * Search for an existing write request, and attempt to update + * it to reflect a new dirty region on a given page. + * + * If the attempt fails, then the existing request is flushed out + * to disk. + */ +static struct nfs_page *nfs_try_to_update_request(struct inode *inode, + struct page *page, + unsigned int offset, + unsigned int bytes) +{ + struct nfs_page *req; + unsigned int rqend; + unsigned int end; + int error; + + if (!PagePrivate(page)) + return NULL; + + end = offset + bytes; + spin_lock(&inode->i_lock); + + for (;;) { + req = nfs_page_find_head_request_locked(NFS_I(inode), page); + if (req == NULL) + goto out_unlock; + + /* should be handled by nfs_flush_incompatible */ + WARN_ON_ONCE(req->wb_head != req); + WARN_ON_ONCE(req->wb_this_page != req); + + rqend = req->wb_offset + req->wb_bytes; + /* + * Tell the caller to flush out the request if + * the offsets are non-contiguous. + * Note: nfs_flush_incompatible() will already + * have flushed out requests having wrong owners. + */ + if (offset > rqend + || end < req->wb_offset) + goto out_flushme; + + if (nfs_lock_request(req)) + break; + + /* The request is locked, so wait and then retry */ + spin_unlock(&inode->i_lock); + error = nfs_wait_on_request(req); + nfs_release_request(req); + if (error != 0) + goto out_err; + spin_lock(&inode->i_lock); + } + + /* Okay, the request matches. Update the region */ + if (offset < req->wb_offset) { + req->wb_offset = offset; + req->wb_pgbase = offset; + } + if (end > rqend) + req->wb_bytes = end - req->wb_offset; + else + req->wb_bytes = rqend - req->wb_offset; +out_unlock: + if (req) + nfs_clear_request_commit(req); + spin_unlock(&inode->i_lock); + return req; +out_flushme: + spin_unlock(&inode->i_lock); + nfs_release_request(req); + error = nfs_wb_page(inode, page); +out_err: + return ERR_PTR(error); +} + +/* + * Try to update an existing write request, or create one if there is none. + * + * Note: Should always be called with the Page Lock held to prevent races + * if we have to add a new request. Also assumes that the caller has + * already called nfs_flush_incompatible() if necessary. + */ +static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx, + struct page *page, unsigned int offset, unsigned int bytes) +{ + struct inode *inode = page_file_mapping(page)->host; + struct nfs_page *req; + + req = nfs_try_to_update_request(inode, page, offset, bytes); + if (req != NULL) + goto out; + req = nfs_create_request(ctx, page, NULL, offset, bytes); + if (IS_ERR(req)) + goto out; + nfs_inode_add_request(inode, req); +out: + return req; +} + +static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, + unsigned int offset, unsigned int count) +{ + struct nfs_page *req; + + req = nfs_setup_write_request(ctx, page, offset, count); + if (IS_ERR(req)) + return PTR_ERR(req); + /* Update file length */ + nfs_grow_file(page, offset, count); + nfs_mark_uptodate(req); + nfs_mark_request_dirty(req); + nfs_unlock_and_release_request(req); + return 0; +} + +int nfs_flush_incompatible(struct file *file, struct page *page) +{ + struct nfs_open_context *ctx = nfs_file_open_context(file); + struct nfs_lock_context *l_ctx; + struct file_lock_context *flctx = file_inode(file)->i_flctx; + struct nfs_page *req; + int do_flush, status; + /* + * Look for a request corresponding to this page. If there + * is one, and it belongs to another file, we flush it out + * before we try to copy anything into the page. Do this + * due to the lack of an ACCESS-type call in NFSv2. + * Also do the same if we find a request from an existing + * dropped page. + */ + do { + req = nfs_page_find_head_request(page); + if (req == NULL) + return 0; + l_ctx = req->wb_lock_context; + do_flush = req->wb_page != page || req->wb_context != ctx; + /* for now, flush if more than 1 request in page_group */ + do_flush |= req->wb_this_page != req; + if (l_ctx && flctx && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock))) { + do_flush |= l_ctx->lockowner.l_owner != current->files + || l_ctx->lockowner.l_pid != current->tgid; + } + nfs_release_request(req); + if (!do_flush) + return 0; + status = nfs_wb_page(page_file_mapping(page)->host, page); + } while (status == 0); + return status; +} + +/* + * Avoid buffered writes when a open context credential's key would + * expire soon. + * + * Returns -EACCES if the key will expire within RPC_KEY_EXPIRE_FAIL. + * + * Return 0 and set a credential flag which triggers the inode to flush + * and performs NFS_FILE_SYNC writes if the key will expired within + * RPC_KEY_EXPIRE_TIMEO. + */ +int +nfs_key_timeout_notify(struct file *filp, struct inode *inode) +{ + struct nfs_open_context *ctx = nfs_file_open_context(filp); + struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; + + return rpcauth_key_timeout_notify(auth, ctx->cred); +} + +/* + * Test if the open context credential key is marked to expire soon. + */ +bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx) +{ + return rpcauth_cred_key_to_expire(ctx->cred); +} + +/* + * If the page cache is marked as unsafe or invalid, then we can't rely on + * the PageUptodate() flag. In this case, we will need to turn off + * write optimisations that depend on the page contents being correct. + */ +static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + if (nfs_have_delegated_attributes(inode)) + goto out; + if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) + return false; + smp_rmb(); + if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) + return false; +out: + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + return false; + return PageUptodate(page) != 0; +} + +static bool +is_whole_file_wrlock(struct file_lock *fl) +{ + return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX && + fl->fl_type == F_WRLCK; +} + +/* If we know the page is up to date, and we're not using byte range locks (or + * if we have the whole file locked for writing), it may be more efficient to + * extend the write to cover the entire page in order to avoid fragmentation + * inefficiencies. + * + * If the file is opened for synchronous writes then we can just skip the rest + * of the checks. + */ +static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) +{ + int ret; + struct file_lock_context *flctx = inode->i_flctx; + struct file_lock *fl; + + if (file->f_flags & O_DSYNC) + return 0; + if (!nfs_write_pageuptodate(page, inode)) + return 0; + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) + return 1; + if (!flctx || (list_empty_careful(&flctx->flc_flock) && + list_empty_careful(&flctx->flc_posix))) + return 0; + + /* Check to see if there are whole file write locks */ + ret = 0; + spin_lock(&flctx->flc_lock); + if (!list_empty(&flctx->flc_posix)) { + fl = list_first_entry(&flctx->flc_posix, struct file_lock, + fl_list); + if (is_whole_file_wrlock(fl)) + ret = 1; + } else if (!list_empty(&flctx->flc_flock)) { + fl = list_first_entry(&flctx->flc_flock, struct file_lock, + fl_list); + if (fl->fl_type == F_WRLCK) + ret = 1; + } + spin_unlock(&flctx->flc_lock); + return ret; +} + +/* + * Update and possibly write a cached page of an NFS file. + * + * XXX: Keep an eye on generic_file_read to make sure it doesn't do bad + * things with a page scheduled for an RPC call (e.g. invalidate it). + */ +int nfs_updatepage(struct file *file, struct page *page, + unsigned int offset, unsigned int count) +{ + struct nfs_open_context *ctx = nfs_file_open_context(file); + struct inode *inode = page_file_mapping(page)->host; + int status = 0; + + nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); + + dprintk("NFS: nfs_updatepage(%pD2 %d@%lld)\n", + file, count, (long long)(page_file_offset(page) + offset)); + + if (nfs_can_extend_write(file, page, inode)) { + count = max(count + offset, nfs_page_length(page)); + offset = 0; + } + + status = nfs_writepage_setup(ctx, page, offset, count); + if (status < 0) + nfs_set_pageerror(page); + else + __set_page_dirty_nobuffers(page); + + dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n", + status, (long long)i_size_read(inode)); + return status; +} + +static int flush_task_priority(int how) +{ + switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) { + case FLUSH_HIGHPRI: + return RPC_PRIORITY_HIGH; + case FLUSH_LOWPRI: + return RPC_PRIORITY_LOW; + } + return RPC_PRIORITY_NORMAL; +} + +static void nfs_initiate_write(struct nfs_pgio_header *hdr, + struct rpc_message *msg, + const struct nfs_rpc_ops *rpc_ops, + struct rpc_task_setup *task_setup_data, int how) +{ + int priority = flush_task_priority(how); + + task_setup_data->priority = priority; + rpc_ops->write_setup(hdr, msg); + + nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client, + &task_setup_data->rpc_client, msg, hdr); +} + +/* If a nfs_flush_* function fails, it should remove reqs from @head and + * call this on each, which will prepare them to be retried on next + * writeback using standard nfs. + */ +static void nfs_redirty_request(struct nfs_page *req) +{ + nfs_mark_request_dirty(req); + nfs_unlock_request(req); + nfs_end_page_writeback(req); + nfs_release_request(req); +} + +static void nfs_async_write_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_redirty_request(req); + } +} + +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { + .error_cleanup = nfs_async_write_error, + .completion = nfs_write_completion, +}; + +void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, + struct inode *inode, int ioflags, bool force_mds, + const struct nfs_pgio_completion_ops *compl_ops) +{ + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops; + +#ifdef CONFIG_NFS_V4_1 + if (server->pnfs_curr_ld && !force_mds) + pg_ops = server->pnfs_curr_ld->pg_write_ops; +#endif + nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops, + server->wsize, ioflags); +} +EXPORT_SYMBOL_GPL(nfs_pageio_init_write); + +void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) +{ + struct nfs_pgio_mirror *mirror; + + pgio->pg_ops = &nfs_pgio_rw_ops; + + nfs_pageio_stop_mirroring(pgio); + + mirror = &pgio->pg_mirrors[0]; + mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; +} +EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); + + +void nfs_commit_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_commit_data *data = calldata; + + NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); +} + +static void nfs_writeback_release_common(struct nfs_pgio_header *hdr) +{ + /* do nothing! */ +} + +/* + * Special version of should_remove_suid() that ignores capabilities. + */ +static int nfs_should_remove_suid(const struct inode *inode) +{ + umode_t mode = inode->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && S_ISREG(mode))) + return kill; + + return 0; +} + +static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, + struct nfs_fattr *fattr) +{ + struct nfs_pgio_args *argp = &hdr->args; + struct nfs_pgio_res *resp = &hdr->res; + + if (!(fattr->valid & NFS_ATTR_FATTR_SIZE)) + return; + if (argp->offset + resp->count != fattr->size) + return; + if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) + return; + /* Set attribute barrier */ + nfs_fattr_set_barrier(fattr); +} + +void nfs_writeback_update_inode(struct nfs_pgio_header *hdr) +{ + struct nfs_fattr *fattr = hdr->res.fattr; + struct inode *inode = hdr->inode; + + if (fattr == NULL) + return; + spin_lock(&inode->i_lock); + nfs_writeback_check_extend(hdr, fattr); + nfs_post_op_update_inode_force_wcc_locked(inode, fattr); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL_GPL(nfs_writeback_update_inode); + +/* + * This function is called when the WRITE call is complete. + */ +static int nfs_writeback_done(struct rpc_task *task, + struct nfs_pgio_header *hdr, + struct inode *inode) +{ + int status; + + /* + * ->write_done will attempt to use post-op attributes to detect + * conflicting writes by other clients. A strict interpretation + * of close-to-open would allow us to continue caching even if + * another writer had changed the file, but some applications + * depend on tighter cache coherency when writing. + */ + status = NFS_PROTO(inode)->write_done(task, hdr); + if (status != 0) + return status; + nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); + + if (hdr->res.verf->committed < hdr->args.stable && + task->tk_status >= 0) { + /* We tried a write call, but the server did not + * commit data to stable storage even though we + * requested it. + * Note: There is a known bug in Tru64 < 5.0 in which + * the server reports NFS_DATA_SYNC, but performs + * NFS_FILE_SYNC. We therefore implement this checking + * as a dprintk() in order to avoid filling syslog. + */ + static unsigned long complain; + + /* Note this will print the MDS for a DS write */ + if (time_before(complain, jiffies)) { + dprintk("NFS: faulty NFS server %s:" + " (committed = %d) != (stable = %d)\n", + NFS_SERVER(inode)->nfs_client->cl_hostname, + hdr->res.verf->committed, hdr->args.stable); + complain = jiffies + 300 * HZ; + } + } + + /* Deal with the suid/sgid bit corner case */ + if (nfs_should_remove_suid(inode)) + nfs_mark_for_revalidate(inode); + return 0; +} + +/* + * This function is called when the WRITE call is complete. + */ +static void nfs_writeback_result(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct nfs_pgio_args *argp = &hdr->args; + struct nfs_pgio_res *resp = &hdr->res; + + if (resp->count < argp->count) { + static unsigned long complain; + + /* This a short write! */ + nfs_inc_stats(hdr->inode, NFSIOS_SHORTWRITE); + + /* Has the server at least made some progress? */ + if (resp->count == 0) { + if (time_before(complain, jiffies)) { + printk(KERN_WARNING + "NFS: Server wrote zero bytes, expected %u.\n", + argp->count); + complain = jiffies + 300 * HZ; + } + nfs_set_pgio_error(hdr, -EIO, argp->offset); + task->tk_status = -EIO; + return; + } + /* Was this an NFSv2 write or an NFSv3 stable write? */ + if (resp->verf->committed != NFS_UNSTABLE) { + /* Resend from where the server left off */ + hdr->mds_offset += resp->count; + argp->offset += resp->count; + argp->pgbase += resp->count; + argp->count -= resp->count; + } else { + /* Resend as a stable write in order to avoid + * headaches in the case of a server crash. + */ + argp->stable = NFS_FILE_SYNC; + } + rpc_restart_call_prepare(task); + } +} + + +static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) +{ + int ret; + + if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags)) + return 1; + if (!may_wait) + return 0; + ret = out_of_line_wait_on_bit_lock(&nfsi->flags, + NFS_INO_COMMIT, + nfs_wait_bit_killable, + TASK_KILLABLE); + return (ret < 0) ? ret : 1; +} + +static void nfs_commit_clear_lock(struct nfs_inode *nfsi) +{ + clear_bit(NFS_INO_COMMIT, &nfsi->flags); + smp_mb__after_atomic(); + wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); +} + +void nfs_commitdata_release(struct nfs_commit_data *data) +{ + put_nfs_open_context(data->context); + nfs_commit_free(data); +} +EXPORT_SYMBOL_GPL(nfs_commitdata_release); + +int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, + const struct nfs_rpc_ops *nfs_ops, + const struct rpc_call_ops *call_ops, + int how, int flags) +{ + struct rpc_task *task; + int priority = flush_task_priority(how); + struct rpc_message msg = { + .rpc_argp = &data->args, + .rpc_resp = &data->res, + .rpc_cred = data->cred, + }; + struct rpc_task_setup task_setup_data = { + .task = &data->task, + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = call_ops, + .callback_data = data, + .workqueue = nfsiod_workqueue, + .flags = RPC_TASK_ASYNC | flags, + .priority = priority, + }; + /* Set up the initial task struct. */ + nfs_ops->commit_setup(data, &msg); + + dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid); + + nfs4_state_protect(NFS_SERVER(data->inode)->nfs_client, + NFS_SP4_MACH_CRED_COMMIT, &task_setup_data.rpc_client, &msg); + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + if (how & FLUSH_SYNC) + rpc_wait_for_completion_task(task); + rpc_put_task(task); + return 0; +} +EXPORT_SYMBOL_GPL(nfs_initiate_commit); + +static loff_t nfs_get_lwb(struct list_head *head) +{ + loff_t lwb = 0; + struct nfs_page *req; + + list_for_each_entry(req, head, wb_list) + if (lwb < (req_offset(req) + req->wb_bytes)) + lwb = req_offset(req) + req->wb_bytes; + + return lwb; +} + +/* + * Set up the argument/result storage required for the RPC call. + */ +void nfs_init_commit(struct nfs_commit_data *data, + struct list_head *head, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) +{ + struct nfs_page *first = nfs_list_entry(head->next); + struct inode *inode = d_inode(first->wb_context->dentry); + + /* Set up the RPC argument and reply structs + * NB: take care not to mess about with data->commit et al. */ + + list_splice_init(head, &data->pages); + + data->inode = inode; + data->cred = first->wb_context->cred; + data->lseg = lseg; /* reference transferred */ + /* only set lwb for pnfs commit */ + if (lseg) + data->lwb = nfs_get_lwb(&data->pages); + data->mds_ops = &nfs_commit_ops; + data->completion_ops = cinfo->completion_ops; + data->dreq = cinfo->dreq; + + data->args.fh = NFS_FH(data->inode); + /* Note: we always request a commit of the entire inode */ + data->args.offset = 0; + data->args.count = 0; + data->context = get_nfs_open_context(first->wb_context); + data->res.fattr = &data->fattr; + data->res.verf = &data->verf; + nfs_fattr_init(&data->fattr); +} +EXPORT_SYMBOL_GPL(nfs_init_commit); + +void nfs_retry_commit(struct list_head *page_list, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) +{ + struct nfs_page *req; + + while (!list_empty(page_list)) { + req = nfs_list_entry(page_list->next); + nfs_list_remove_request(req); + nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx); + if (!cinfo->dreq) + nfs_clear_page_commit(req->wb_page); + nfs_unlock_and_release_request(req); + } +} +EXPORT_SYMBOL_GPL(nfs_retry_commit); + +/* + * Commit dirty pages + */ +static int +nfs_commit_list(struct inode *inode, struct list_head *head, int how, + struct nfs_commit_info *cinfo) +{ + struct nfs_commit_data *data; + + data = nfs_commitdata_alloc(); + + if (!data) + goto out_bad; + + /* Set up the argument struct */ + nfs_init_commit(data, head, NULL, cinfo); + atomic_inc(&cinfo->mds->rpcs_out); + return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), + data->mds_ops, how, 0); + out_bad: + nfs_retry_commit(head, NULL, cinfo, 0); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); + return -ENOMEM; +} + +/* + * COMMIT call returned + */ +static void nfs_commit_done(struct rpc_task *task, void *calldata) +{ + struct nfs_commit_data *data = calldata; + + dprintk("NFS: %5u nfs_commit_done (status %d)\n", + task->tk_pid, task->tk_status); + + /* Call the NFS version-specific code */ + NFS_PROTO(data->inode)->commit_done(task, data); +} + +static void nfs_commit_release_pages(struct nfs_commit_data *data) +{ + struct nfs_page *req; + int status = data->task.tk_status; + struct nfs_commit_info cinfo; + struct nfs_server *nfss; + + while (!list_empty(&data->pages)) { + req = nfs_list_entry(data->pages.next); + nfs_list_remove_request(req); + nfs_clear_page_commit(req->wb_page); + + dprintk("NFS: commit (%s/%llu %d@%lld)", + req->wb_context->dentry->d_sb->s_id, + (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)), + req->wb_bytes, + (long long)req_offset(req)); + if (status < 0) { + nfs_context_set_write_error(req->wb_context, status); + nfs_inode_remove_request(req); + dprintk(", error = %d\n", status); + goto next; + } + + /* Okay, COMMIT succeeded, apparently. Check the verifier + * returned by the server against all stored verfs. */ + if (!memcmp(&req->wb_verf, &data->verf.verifier, sizeof(req->wb_verf))) { + /* We have a match */ + nfs_inode_remove_request(req); + dprintk(" OK\n"); + goto next; + } + /* We have a mismatch. Write the page again */ + dprintk(" mismatch\n"); + nfs_mark_request_dirty(req); + set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags); + next: + nfs_unlock_and_release_request(req); + } + nfss = NFS_SERVER(data->inode); + if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) + clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); + + nfs_init_cinfo(&cinfo, data->inode, data->dreq); + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + nfs_commit_clear_lock(NFS_I(data->inode)); +} + +static void nfs_commit_release(void *calldata) +{ + struct nfs_commit_data *data = calldata; + + data->completion_ops->completion(data); + nfs_commitdata_release(calldata); +} + +static const struct rpc_call_ops nfs_commit_ops = { + .rpc_call_prepare = nfs_commit_prepare, + .rpc_call_done = nfs_commit_done, + .rpc_release = nfs_commit_release, +}; + +static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { + .completion = nfs_commit_release_pages, + .error_cleanup = nfs_commit_clear_lock, +}; + +int nfs_generic_commit_list(struct inode *inode, struct list_head *head, + int how, struct nfs_commit_info *cinfo) +{ + int status; + + status = pnfs_commit_list(inode, head, how, cinfo); + if (status == PNFS_NOT_ATTEMPTED) + status = nfs_commit_list(inode, head, how, cinfo); + return status; +} + +int nfs_commit_inode(struct inode *inode, int how) +{ + LIST_HEAD(head); + struct nfs_commit_info cinfo; + int may_wait = how & FLUSH_SYNC; + int res; + + res = nfs_commit_set_lock(NFS_I(inode), may_wait); + if (res <= 0) + goto out_mark_dirty; + nfs_init_cinfo_from_inode(&cinfo, inode); + res = nfs_scan_commit(inode, &head, &cinfo); + if (res) { + int error; + + error = nfs_generic_commit_list(inode, &head, how, &cinfo); + if (error < 0) + return error; + if (!may_wait) + goto out_mark_dirty; + error = wait_on_bit_action(&NFS_I(inode)->flags, + NFS_INO_COMMIT, + nfs_wait_bit_killable, + TASK_KILLABLE); + if (error < 0) + return error; + } else + nfs_commit_clear_lock(NFS_I(inode)); + return res; + /* Note: If we exit without ensuring that the commit is complete, + * we must mark the inode as dirty. Otherwise, future calls to + * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure + * that the data is on the disk. + */ +out_mark_dirty: + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + return res; +} + +static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc) +{ + struct nfs_inode *nfsi = NFS_I(inode); + int flags = FLUSH_SYNC; + int ret = 0; + + /* no commits means nothing needs to be done */ + if (!nfsi->commit_info.ncommit) + return ret; + + if (wbc->sync_mode == WB_SYNC_NONE) { + /* Don't commit yet if this is a non-blocking flush and there + * are a lot of outstanding writes for this mapping. + */ + if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1)) + goto out_mark_dirty; + + /* don't wait for the COMMIT response */ + flags = 0; + } + + ret = nfs_commit_inode(inode, flags); + if (ret >= 0) { + if (wbc->sync_mode == WB_SYNC_NONE) { + if (ret < wbc->nr_to_write) + wbc->nr_to_write -= ret; + else + wbc->nr_to_write = 0; + } + return 0; + } +out_mark_dirty: + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + return ret; +} + +int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + return nfs_commit_unstable_pages(inode, wbc); +} +EXPORT_SYMBOL_GPL(nfs_write_inode); + +/* + * flush the inode to disk. + */ +int nfs_wb_all(struct inode *inode) +{ + int ret; + + trace_nfs_writeback_inode_enter(inode); + + ret = filemap_write_and_wait(inode->i_mapping); + if (ret) + goto out; + ret = nfs_commit_inode(inode, FLUSH_SYNC); + if (ret < 0) + goto out; + pnfs_sync_inode(inode, true); + ret = 0; + +out: + trace_nfs_writeback_inode_exit(inode, ret); + return ret; +} +EXPORT_SYMBOL_GPL(nfs_wb_all); + +int nfs_wb_page_cancel(struct inode *inode, struct page *page) +{ + struct nfs_page *req; + int ret = 0; + + wait_on_page_writeback(page); + + /* blocking call to cancel all requests and join to a single (head) + * request */ + req = nfs_lock_and_join_requests(page, false); + + if (IS_ERR(req)) { + ret = PTR_ERR(req); + } else if (req) { + /* all requests from this page have been cancelled by + * nfs_lock_and_join_requests, so just remove the head + * request from the inode / page_private pointer and + * release it */ + nfs_inode_remove_request(req); + nfs_unlock_and_release_request(req); + } + + return ret; +} + +/* + * Write back all requests on one page - we do this before reading it. + */ +int nfs_wb_page(struct inode *inode, struct page *page) +{ + loff_t range_start = page_file_offset(page); + loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_end, + }; + int ret; + + trace_nfs_writeback_page_enter(inode); + + for (;;) { + wait_on_page_writeback(page); + if (clear_page_dirty_for_io(page)) { + ret = nfs_writepage_locked(page, &wbc); + if (ret < 0) + goto out_error; + continue; + } + ret = 0; + if (!PagePrivate(page)) + break; + ret = nfs_commit_inode(inode, FLUSH_SYNC); + if (ret < 0) + goto out_error; + } +out_error: + trace_nfs_writeback_page_exit(inode, ret); + return ret; +} + +#ifdef CONFIG_MIGRATION +int nfs_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ + /* + * If PagePrivate is set, then the page is currently associated with + * an in-progress read or write request. Don't try to migrate it. + * + * FIXME: we could do this in principle, but we'll need a way to ensure + * that we can safely release the inode reference while holding + * the page lock. + */ + if (PagePrivate(page)) + return -EBUSY; + + if (!nfs_fscache_release_page(page, GFP_KERNEL)) + return -EBUSY; + + return migrate_page(mapping, newpage, page, mode); +} +#endif + +int __init nfs_init_writepagecache(void) +{ + nfs_wdata_cachep = kmem_cache_create("nfs_write_data", + sizeof(struct nfs_pgio_header), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (nfs_wdata_cachep == NULL) + return -ENOMEM; + + nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE, + nfs_wdata_cachep); + if (nfs_wdata_mempool == NULL) + goto out_destroy_write_cache; + + nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", + sizeof(struct nfs_commit_data), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (nfs_cdata_cachep == NULL) + goto out_destroy_write_mempool; + + nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, + nfs_cdata_cachep); + if (nfs_commit_mempool == NULL) + goto out_destroy_commit_cache; + + /* + * NFS congestion size, scale with available memory. + * + * 64MB: 8192k + * 128MB: 11585k + * 256MB: 16384k + * 512MB: 23170k + * 1GB: 32768k + * 2GB: 46340k + * 4GB: 65536k + * 8GB: 92681k + * 16GB: 131072k + * + * This allows larger machines to have larger/more transfers. + * Limit the default to 256M + */ + nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10); + if (nfs_congestion_kb > 256*1024) + nfs_congestion_kb = 256*1024; + + return 0; + +out_destroy_commit_cache: + kmem_cache_destroy(nfs_cdata_cachep); +out_destroy_write_mempool: + mempool_destroy(nfs_wdata_mempool); +out_destroy_write_cache: + kmem_cache_destroy(nfs_wdata_cachep); + return -ENOMEM; +} + +void nfs_destroy_writepagecache(void) +{ + mempool_destroy(nfs_commit_mempool); + kmem_cache_destroy(nfs_cdata_cachep); + mempool_destroy(nfs_wdata_mempool); + kmem_cache_destroy(nfs_wdata_cachep); +} + +static const struct nfs_rw_ops nfs_rw_write_ops = { + .rw_mode = FMODE_WRITE, + .rw_alloc_header = nfs_writehdr_alloc, + .rw_free_header = nfs_writehdr_free, + .rw_release = nfs_writeback_release_common, + .rw_done = nfs_writeback_done, + .rw_result = nfs_writeback_result, + .rw_initiate = nfs_initiate_write, +}; |