diff options
Diffstat (limited to 'kernel/fs/f2fs')
31 files changed, 6113 insertions, 1837 deletions
diff --git a/kernel/fs/f2fs/Kconfig b/kernel/fs/f2fs/Kconfig index 05f0f663f..b0a9dc929 100644 --- a/kernel/fs/f2fs/Kconfig +++ b/kernel/fs/f2fs/Kconfig @@ -45,7 +45,7 @@ config F2FS_FS_POSIX_ACL default y help Posix Access Control Lists (ACLs) support permissions for users and - gourps beyond the owner/group/world scheme. + groups beyond the owner/group/world scheme. To learn more about Access Control Lists, visit the POSIX ACLs for Linux website <http://acl.bestbits.at/>. @@ -72,6 +72,25 @@ config F2FS_CHECK_FS If you want to improve the performance, say N. +config F2FS_FS_ENCRYPTION + bool "F2FS Encryption" + depends on F2FS_FS + depends on F2FS_FS_XATTR + select CRYPTO_AES + select CRYPTO_CBC + select CRYPTO_ECB + select CRYPTO_XTS + select CRYPTO_CTS + select CRYPTO_CTR + select CRYPTO_SHA256 + select KEYS + select ENCRYPTED_KEYS + help + Enable encryption of f2fs files and directories. This + feature is similar to ecryptfs, but it is more memory + efficient since it avoids caching the encrypted and + decrypted pages in the page cache. + config F2FS_IO_TRACE bool "F2FS IO tracer" depends on F2FS_FS diff --git a/kernel/fs/f2fs/Makefile b/kernel/fs/f2fs/Makefile index d92397731..08e101ed9 100644 --- a/kernel/fs/f2fs/Makefile +++ b/kernel/fs/f2fs/Makefile @@ -2,7 +2,10 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o +f2fs-y += shrinker.o extent_cache.o f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o +f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \ + crypto_key.o crypto_fname.o diff --git a/kernel/fs/f2fs/acl.c b/kernel/fs/f2fs/acl.c index 4320ffab3..c8f25f724 100644 --- a/kernel/fs/f2fs/acl.c +++ b/kernel/fs/f2fs/acl.c @@ -334,51 +334,45 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, struct page *dpage) { struct posix_acl *p; + struct posix_acl *clone; int ret; + *acl = NULL; + *default_acl = NULL; + if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) - goto no_acl; + return 0; p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage); - if (IS_ERR(p)) { - if (p == ERR_PTR(-EOPNOTSUPP)) - goto apply_umask; - return PTR_ERR(p); + if (!p || p == ERR_PTR(-EOPNOTSUPP)) { + *mode &= ~current_umask(); + return 0; } + if (IS_ERR(p)) + return PTR_ERR(p); - if (!p) - goto apply_umask; - - *acl = f2fs_acl_clone(p, GFP_NOFS); - if (!*acl) + clone = f2fs_acl_clone(p, GFP_NOFS); + if (!clone) goto no_mem; - ret = f2fs_acl_create_masq(*acl, mode); + ret = f2fs_acl_create_masq(clone, mode); if (ret < 0) goto no_mem_clone; - if (ret == 0) { - posix_acl_release(*acl); - *acl = NULL; - } + if (ret == 0) + posix_acl_release(clone); + else + *acl = clone; - if (!S_ISDIR(*mode)) { + if (!S_ISDIR(*mode)) posix_acl_release(p); - *default_acl = NULL; - } else { + else *default_acl = p; - } - return 0; -apply_umask: - *mode &= ~current_umask(); -no_acl: - *default_acl = NULL; - *acl = NULL; return 0; no_mem_clone: - posix_acl_release(*acl); + posix_acl_release(clone); no_mem: posix_acl_release(p); return -ENOMEM; diff --git a/kernel/fs/f2fs/checkpoint.c b/kernel/fs/f2fs/checkpoint.c index a5e17a2a0..f661d8047 100644 --- a/kernel/fs/f2fs/checkpoint.c +++ b/kernel/fs/f2fs/checkpoint.c @@ -47,15 +47,21 @@ repeat: /* * We guarantee no failure on the returned page. */ -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, + bool is_meta) { struct address_space *mapping = META_MAPPING(sbi); struct page *page; struct f2fs_io_info fio = { + .sbi = sbi, .type = META, .rw = READ_SYNC | REQ_META | REQ_PRIO, .blk_addr = index, + .encrypted_page = NULL, }; + + if (unlikely(!is_meta)) + fio.rw &= ~REQ_META; repeat: page = grab_cache_page(mapping, index); if (!page) { @@ -65,20 +71,42 @@ repeat: if (PageUptodate(page)) goto out; - if (f2fs_submit_page_bio(sbi, page, &fio)) + fio.page = page; + + if (f2fs_submit_page_bio(&fio)) { + f2fs_put_page(page, 1); goto repeat; + } lock_page(page); if (unlikely(page->mapping != mapping)) { f2fs_put_page(page, 1); goto repeat; } + + /* + * if there is any IO error when accessing device, make our filesystem + * readonly and make sure do not write checkpoint with non-uptodate + * meta page. + */ + if (unlikely(!PageUptodate(page))) + f2fs_stop_checkpoint(sbi); out: return page; } -static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi, - block_t blkaddr, int type) +struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +{ + return __get_meta_page(sbi, index, true); +} + +/* for POR only */ +struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) +{ + return __get_meta_page(sbi, index, false); +} + +bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { switch (type) { case META_NAT: @@ -112,16 +140,22 @@ static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi, /* * Readahead CP/NAT/SIT/SSA pages */ -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type) +int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, + int type, bool sync) { block_t prev_blk_addr = 0; struct page *page; block_t blkno = start; struct f2fs_io_info fio = { + .sbi = sbi, .type = META, - .rw = READ_SYNC | REQ_META | REQ_PRIO + .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA, + .encrypted_page = NULL, }; + if (unlikely(type == META_POR)) + fio.rw &= ~REQ_META; + for (; nrpages-- > 0; blkno++) { if (!is_valid_blkaddr(sbi, blkno, type)) @@ -161,7 +195,8 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type continue; } - f2fs_submit_page_mbio(sbi, page, &fio); + fio.page = page; + f2fs_submit_page_mbio(&fio); f2fs_put_page(page, 0); } out: @@ -180,7 +215,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) f2fs_put_page(page, 0); if (readahead) - ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR); + ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true); } static int f2fs_write_meta_page(struct page *page, @@ -241,7 +276,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write) { struct address_space *mapping = META_MAPPING(sbi); - pgoff_t index = 0, end = LONG_MAX; + pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX; struct pagevec pvec; long nwritten = 0; struct writeback_control wbc = { @@ -261,6 +296,13 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + if (prev == LONG_MAX) + prev = page->index - 1; + if (nr_to_write != LONG_MAX && page->index != prev + 1) { + pagevec_release(&pvec); + goto stop; + } + lock_page(page); if (unlikely(page->mapping != mapping)) { @@ -281,13 +323,14 @@ continue_unlock: break; } nwritten++; + prev = page->index; if (unlikely(nwritten >= nr_to_write)) break; } pagevec_release(&pvec); cond_resched(); } - +stop: if (nwritten) f2fs_submit_merged_bio(sbi, type, WRITE); @@ -320,26 +363,18 @@ const struct address_space_operations f2fs_meta_aops = { static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { struct inode_management *im = &sbi->im[type]; - struct ino_entry *e; + struct ino_entry *e, *tmp; + + tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS); retry: - if (radix_tree_preload(GFP_NOFS)) { - cond_resched(); - goto retry; - } + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); spin_lock(&im->ino_lock); - e = radix_tree_lookup(&im->ino_root, ino); if (!e) { - e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC); - if (!e) { - spin_unlock(&im->ino_lock); - radix_tree_preload_end(); - goto retry; - } + e = tmp; if (radix_tree_insert(&im->ino_root, ino, e)) { spin_unlock(&im->ino_lock); - kmem_cache_free(ino_entry_slab, e); radix_tree_preload_end(); goto retry; } @@ -352,6 +387,9 @@ retry: } spin_unlock(&im->ino_lock); radix_tree_preload_end(); + + if (e != tmp) + kmem_cache_free(ino_entry_slab, tmp); } static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) @@ -452,29 +490,39 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) __remove_ino_entry(sbi, ino, ORPHAN_INO); } -static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { - struct inode *inode = f2fs_iget(sbi->sb, ino); - f2fs_bug_on(sbi, IS_ERR(inode)); + struct inode *inode; + + inode = f2fs_iget(sbi->sb, ino); + if (IS_ERR(inode)) { + /* + * there should be a bug that we can't find the entry + * to orphan inode. + */ + f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT); + return PTR_ERR(inode); + } + clear_nlink(inode); /* truncate all the data during iput */ iput(inode); + return 0; } -void recover_orphan_inodes(struct f2fs_sb_info *sbi) +int recover_orphan_inodes(struct f2fs_sb_info *sbi) { block_t start_blk, orphan_blocks, i, j; + int err; if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) - return; - - set_sbi_flag(sbi, SBI_POR_DOING); + return 0; start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); - ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP); + ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); for (i = 0; i < orphan_blocks; i++) { struct page *page = get_meta_page(sbi, start_blk + i); @@ -483,14 +531,17 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi) orphan_blk = (struct f2fs_orphan_block *)page_address(page); for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { nid_t ino = le32_to_cpu(orphan_blk->ino[j]); - recover_orphan_inode(sbi, ino); + err = recover_orphan_inode(sbi, ino); + if (err) { + f2fs_put_page(page, 1); + return err; + } } f2fs_put_page(page, 1); } /* clear Orphan Flag */ clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG); - clear_sbi_flag(sbi, SBI_POR_DOING); - return; + return 0; } static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) @@ -498,7 +549,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) struct list_head *head; struct f2fs_orphan_block *orphan_blk = NULL; unsigned int nentries = 0; - unsigned short index; + unsigned short index = 1; unsigned short orphan_blocks; struct page *page = NULL; struct ino_entry *orphan = NULL; @@ -506,22 +557,20 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num); - for (index = 0; index < orphan_blocks; index++) - grab_meta_page(sbi, start_blk + index); - - index = 1; - spin_lock(&im->ino_lock); + /* + * we don't need to do spin_lock(&im->ino_lock) here, since all the + * orphan inode operations are covered under f2fs_lock_op(). + * And, spin_lock should be avoided due to page operations below. + */ head = &im->ino_list; /* loop for each orphan inode entry and write them in Jornal block */ list_for_each_entry(orphan, head, list) { if (!page) { - page = find_get_page(META_MAPPING(sbi), start_blk++); - f2fs_bug_on(sbi, !page); + page = grab_meta_page(sbi, start_blk++); orphan_blk = (struct f2fs_orphan_block *)page_address(page); memset(orphan_blk, 0, sizeof(*orphan_blk)); - f2fs_put_page(page, 0); } orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino); @@ -550,8 +599,6 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) set_page_dirty(page); f2fs_put_page(page, 1); } - - spin_unlock(&im->ino_lock); } static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, @@ -695,7 +742,8 @@ void update_dirty_page(struct inode *inode, struct page *page) struct inode_entry *new; int ret = 0; - if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && + !S_ISLNK(inode->i_mode)) return; if (!S_ISDIR(inode->i_mode)) { @@ -879,18 +927,19 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; nid_t last_nid = nm_i->next_scan_nid; block_t start_blk; - struct page *cp_page; unsigned int data_sum_blocks, orphan_blocks; __u32 crc32 = 0; - void *kaddr; int i; int cp_payload_blks = __cp_payload(sbi); + block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg); + bool invalidate = false; /* * This avoids to conduct wrong roll-forward operations and uses * metapages, so should be called prior to sync_meta_pages below. */ - discard_next_dnode(sbi, NEXT_FREE_BLKADDR(sbi, curseg)); + if (discard_next_dnode(sbi, discard_blk)) + invalidate = true; /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { @@ -978,20 +1027,17 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk = __start_cp_addr(sbi); + /* need to wait for end_io results */ + wait_on_all_pages_writeback(sbi); + if (unlikely(f2fs_cp_error(sbi))) + return; + /* write out checkpoint buffer at block 0 */ - cp_page = grab_meta_page(sbi, start_blk++); - kaddr = page_address(cp_page); - memcpy(kaddr, ckpt, F2FS_BLKSIZE); - set_page_dirty(cp_page); - f2fs_put_page(cp_page, 1); - - for (i = 1; i < 1 + cp_payload_blks; i++) { - cp_page = grab_meta_page(sbi, start_blk++); - kaddr = page_address(cp_page); - memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE); - set_page_dirty(cp_page); - f2fs_put_page(cp_page, 1); - } + update_meta_page(sbi, ckpt, start_blk++); + + for (i = 1; i < 1 + cp_payload_blks; i++) + update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, + start_blk++); if (orphan_num) { write_orphan_inodes(sbi, start_blk); @@ -1006,11 +1052,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* writeout checkpoint block */ - cp_page = grab_meta_page(sbi, start_blk); - kaddr = page_address(cp_page); - memcpy(kaddr, ckpt, F2FS_BLKSIZE); - set_page_dirty(cp_page); - f2fs_put_page(cp_page, 1); + update_meta_page(sbi, ckpt, start_blk); /* wait for previous submitted node/meta pages writeback */ wait_on_all_pages_writeback(sbi); @@ -1031,12 +1073,20 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* wait for previous submitted meta pages writeback */ wait_on_all_pages_writeback(sbi); + /* + * invalidate meta page which is used temporarily for zeroing out + * block at the end of warm node chain. + */ + if (invalidate) + invalidate_mapping_pages(META_MAPPING(sbi), discard_blk, + discard_blk); + release_dirty_inode(sbi); if (unlikely(f2fs_cp_error(sbi))) return; - clear_prefree_segments(sbi); + clear_prefree_segments(sbi, cpc); clear_sbi_flag(sbi, SBI_IS_DIRTY); } @@ -1051,7 +1101,8 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && - (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC)) + (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC || + (cpc->reason == CP_DISCARD && !sbi->discard_blks))) goto out; if (unlikely(f2fs_cp_error(sbi))) goto out; @@ -1090,6 +1141,9 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (cpc->reason == CP_RECOVERY) f2fs_msg(sbi->sb, KERN_NOTICE, "checkpoint: version = %llx", ckpt_ver); + + /* do checkpoint periodically */ + sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval); out: mutex_unlock(&sbi->cp_mutex); trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); diff --git a/kernel/fs/f2fs/crypto.c b/kernel/fs/f2fs/crypto.c new file mode 100644 index 000000000..4a62ef14e --- /dev/null +++ b/kernel/fs/f2fs/crypto.c @@ -0,0 +1,491 @@ +/* + * linux/fs/f2fs/crypto.c + * + * Copied from linux/fs/ext4/crypto.c + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility + * + * This contains encryption functions for f2fs + * + * Written by Michael Halcrow, 2014. + * + * Filename encryption additions + * Uday Savagaonkar, 2014 + * Encryption policy handling additions + * Ildar Muslukhov, 2014 + * Remove ext4_encrypted_zeroout(), + * add f2fs_restore_and_release_control_page() + * Jaegeuk Kim, 2015. + * + * This has not yet undergone a rigorous security audit. + * + * The usage of AES-XTS should conform to recommendations in NIST + * Special Publication 800-38E and IEEE P1619/D16. + */ +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <keys/user-type.h> +#include <keys/encrypted-type.h> +#include <linux/crypto.h> +#include <linux/ecryptfs.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> +#include <linux/f2fs_fs.h> +#include <linux/ratelimit.h> +#include <linux/bio.h> + +#include "f2fs.h" +#include "xattr.h" + +/* Encryption added and removed here! (L: */ + +static unsigned int num_prealloc_crypto_pages = 32; +static unsigned int num_prealloc_crypto_ctxs = 128; + +module_param(num_prealloc_crypto_pages, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_pages, + "Number of crypto pages to preallocate"); +module_param(num_prealloc_crypto_ctxs, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_ctxs, + "Number of crypto contexts to preallocate"); + +static mempool_t *f2fs_bounce_page_pool; + +static LIST_HEAD(f2fs_free_crypto_ctxs); +static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock); + +static struct workqueue_struct *f2fs_read_workqueue; +static DEFINE_MUTEX(crypto_init); + +static struct kmem_cache *f2fs_crypto_ctx_cachep; +struct kmem_cache *f2fs_crypt_info_cachep; + +/** + * f2fs_release_crypto_ctx() - Releases an encryption context + * @ctx: The encryption context to release. + * + * If the encryption context was allocated from the pre-allocated pool, returns + * it to that pool. Else, frees it. + * + * If there's a bounce page in the context, this frees that. + */ +void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx) +{ + unsigned long flags; + + if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) { + mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool); + ctx->w.bounce_page = NULL; + } + ctx->w.control_page = NULL; + if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { + kmem_cache_free(f2fs_crypto_ctx_cachep, ctx); + } else { + spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags); + list_add(&ctx->free_list, &f2fs_free_crypto_ctxs); + spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags); + } +} + +/** + * f2fs_get_crypto_ctx() - Gets an encryption context + * @inode: The inode for which we are doing the crypto + * + * Allocates and initializes an encryption context. + * + * Return: An allocated and initialized encryption context on success; error + * value or NULL otherwise. + */ +struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode) +{ + struct f2fs_crypto_ctx *ctx = NULL; + unsigned long flags; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (ci == NULL) + return ERR_PTR(-ENOKEY); + + /* + * We first try getting the ctx from a free list because in + * the common case the ctx will have an allocated and + * initialized crypto tfm, so it's probably a worthwhile + * optimization. For the bounce page, we first try getting it + * from the kernel allocator because that's just about as fast + * as getting it from a list and because a cache of free pages + * should generally be a "last resort" option for a filesystem + * to be able to do its job. + */ + spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags); + ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs, + struct f2fs_crypto_ctx, free_list); + if (ctx) + list_del(&ctx->free_list); + spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags); + if (!ctx) { + ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS); + if (!ctx) + return ERR_PTR(-ENOMEM); + ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->flags &= ~F2FS_WRITE_PATH_FL; + return ctx; +} + +/* + * Call f2fs_decrypt on every single page, reusing the encryption + * context. + */ +static void completion_pages(struct work_struct *work) +{ + struct f2fs_crypto_ctx *ctx = + container_of(work, struct f2fs_crypto_ctx, r.work); + struct bio *bio = ctx->r.bio; + struct bio_vec *bv; + int i; + + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + int ret = f2fs_decrypt(ctx, page); + + if (ret) { + WARN_ON_ONCE(1); + SetPageError(page); + } else + SetPageUptodate(page); + unlock_page(page); + } + f2fs_release_crypto_ctx(ctx); + bio_put(bio); +} + +void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio) +{ + INIT_WORK(&ctx->r.work, completion_pages); + ctx->r.bio = bio; + queue_work(f2fs_read_workqueue, &ctx->r.work); +} + +static void f2fs_crypto_destroy(void) +{ + struct f2fs_crypto_ctx *pos, *n; + + list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list) + kmem_cache_free(f2fs_crypto_ctx_cachep, pos); + INIT_LIST_HEAD(&f2fs_free_crypto_ctxs); + if (f2fs_bounce_page_pool) + mempool_destroy(f2fs_bounce_page_pool); + f2fs_bounce_page_pool = NULL; +} + +/** + * f2fs_crypto_initialize() - Set up for f2fs encryption. + * + * We only call this when we start accessing encrypted files, since it + * results in memory getting allocated that wouldn't otherwise be used. + * + * Return: Zero on success, non-zero otherwise. + */ +int f2fs_crypto_initialize(void) +{ + int i, res = -ENOMEM; + + if (f2fs_bounce_page_pool) + return 0; + + mutex_lock(&crypto_init); + if (f2fs_bounce_page_pool) + goto already_initialized; + + for (i = 0; i < num_prealloc_crypto_ctxs; i++) { + struct f2fs_crypto_ctx *ctx; + + ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL); + if (!ctx) + goto fail; + list_add(&ctx->free_list, &f2fs_free_crypto_ctxs); + } + + /* must be allocated at the last step to avoid race condition above */ + f2fs_bounce_page_pool = + mempool_create_page_pool(num_prealloc_crypto_pages, 0); + if (!f2fs_bounce_page_pool) + goto fail; + +already_initialized: + mutex_unlock(&crypto_init); + return 0; +fail: + f2fs_crypto_destroy(); + mutex_unlock(&crypto_init); + return res; +} + +/** + * f2fs_exit_crypto() - Shutdown the f2fs encryption system + */ +void f2fs_exit_crypto(void) +{ + f2fs_crypto_destroy(); + + if (f2fs_read_workqueue) + destroy_workqueue(f2fs_read_workqueue); + if (f2fs_crypto_ctx_cachep) + kmem_cache_destroy(f2fs_crypto_ctx_cachep); + if (f2fs_crypt_info_cachep) + kmem_cache_destroy(f2fs_crypt_info_cachep); +} + +int __init f2fs_init_crypto(void) +{ + int res = -ENOMEM; + + f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0); + if (!f2fs_read_workqueue) + goto fail; + + f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx, + SLAB_RECLAIM_ACCOUNT); + if (!f2fs_crypto_ctx_cachep) + goto fail; + + f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info, + SLAB_RECLAIM_ACCOUNT); + if (!f2fs_crypt_info_cachep) + goto fail; + + return 0; +fail: + f2fs_exit_crypto(); + return res; +} + +void f2fs_restore_and_release_control_page(struct page **page) +{ + struct f2fs_crypto_ctx *ctx; + struct page *bounce_page; + + /* The bounce data pages are unmapped. */ + if ((*page)->mapping) + return; + + /* The bounce data page is unmapped. */ + bounce_page = *page; + ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page); + + /* restore control page */ + *page = ctx->w.control_page; + + f2fs_restore_control_page(bounce_page); +} + +void f2fs_restore_control_page(struct page *data_page) +{ + struct f2fs_crypto_ctx *ctx = + (struct f2fs_crypto_ctx *)page_private(data_page); + + set_page_private(data_page, (unsigned long)NULL); + ClearPagePrivate(data_page); + unlock_page(data_page); + f2fs_release_crypto_ctx(ctx); +} + +/** + * f2fs_crypt_complete() - The completion callback for page encryption + * @req: The asynchronous encryption request context + * @res: The result of the encryption operation + */ +static void f2fs_crypt_complete(struct crypto_async_request *req, int res) +{ + struct f2fs_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +typedef enum { + F2FS_DECRYPT = 0, + F2FS_ENCRYPT, +} f2fs_direction_t; + +static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx, + struct inode *inode, + f2fs_direction_t rw, + pgoff_t index, + struct page *src_page, + struct page *dest_page) +{ + u8 xts_tweak[F2FS_XTS_TWEAK_SIZE]; + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct scatterlist dst, src; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct crypto_ablkcipher *tfm = ci->ci_ctfm; + int res = 0; + + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", + __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback( + req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + f2fs_crypt_complete, &ecr); + + BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index)); + memcpy(xts_tweak, &index, sizeof(index)); + memset(&xts_tweak[sizeof(index)], 0, + F2FS_XTS_TWEAK_SIZE - sizeof(index)); + + sg_init_table(&dst, 1); + sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0); + sg_init_table(&src, 1); + sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0); + ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE, + xts_tweak); + if (rw == F2FS_DECRYPT) + res = crypto_ablkcipher_decrypt(req); + else + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + ablkcipher_request_free(req); + if (res) { + printk_ratelimited(KERN_ERR + "%s: crypto_ablkcipher_encrypt() returned %d\n", + __func__, res); + return res; + } + return 0; +} + +static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx) +{ + ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT); + if (ctx->w.bounce_page == NULL) + return ERR_PTR(-ENOMEM); + ctx->flags |= F2FS_WRITE_PATH_FL; + return ctx->w.bounce_page; +} + +/** + * f2fs_encrypt() - Encrypts a page + * @inode: The inode for which the encryption should take place + * @plaintext_page: The page to encrypt. Must be locked. + * + * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx + * encryption context. + * + * Called on the page write path. The caller must call + * f2fs_restore_control_page() on the returned ciphertext page to + * release the bounce buffer and the encryption context. + * + * Return: An allocated page with the encrypted content on success. Else, an + * error value or NULL. + */ +struct page *f2fs_encrypt(struct inode *inode, + struct page *plaintext_page) +{ + struct f2fs_crypto_ctx *ctx; + struct page *ciphertext_page = NULL; + int err; + + BUG_ON(!PageLocked(plaintext_page)); + + ctx = f2fs_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + return (struct page *)ctx; + + /* The encryption operation will require a bounce page. */ + ciphertext_page = alloc_bounce_page(ctx); + if (IS_ERR(ciphertext_page)) + goto err_out; + + ctx->w.control_page = plaintext_page; + err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index, + plaintext_page, ciphertext_page); + if (err) { + ciphertext_page = ERR_PTR(err); + goto err_out; + } + + SetPagePrivate(ciphertext_page); + set_page_private(ciphertext_page, (unsigned long)ctx); + lock_page(ciphertext_page); + return ciphertext_page; + +err_out: + f2fs_release_crypto_ctx(ctx); + return ciphertext_page; +} + +/** + * f2fs_decrypt() - Decrypts a page in-place + * @ctx: The encryption context. + * @page: The page to decrypt. Must be locked. + * + * Decrypts page in-place using the ctx encryption context. + * + * Called from the read completion callback. + * + * Return: Zero on success, non-zero otherwise. + */ +int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page) +{ + BUG_ON(!PageLocked(page)); + + return f2fs_page_crypto(ctx, page->mapping->host, + F2FS_DECRYPT, page->index, page, page); +} + +/* + * Convenience function which takes care of allocating and + * deallocating the encryption context + */ +int f2fs_decrypt_one(struct inode *inode, struct page *page) +{ + struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode); + int ret; + + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + ret = f2fs_decrypt(ctx, page); + f2fs_release_crypto_ctx(ctx); + return ret; +} + +bool f2fs_valid_contents_enc_mode(uint32_t mode) +{ + return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS); +} + +/** + * f2fs_validate_encryption_key_size() - Validate the encryption key size + * @mode: The key mode. + * @size: The key size to validate. + * + * Return: The validated key size for @mode. Zero if invalid. + */ +uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size) +{ + if (size == f2fs_encryption_key_size(mode)) + return size; + return 0; +} diff --git a/kernel/fs/f2fs/crypto_fname.c b/kernel/fs/f2fs/crypto_fname.c new file mode 100644 index 000000000..ab377d496 --- /dev/null +++ b/kernel/fs/f2fs/crypto_fname.c @@ -0,0 +1,440 @@ +/* + * linux/fs/f2fs/crypto_fname.c + * + * Copied from linux/fs/ext4/crypto.c + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility + * + * This contains functions for filename crypto management in f2fs + * + * Written by Uday Savagaonkar, 2014. + * + * Adjust f2fs dentry structure + * Jaegeuk Kim, 2015. + * + * This has not yet undergone a rigorous security audit. + */ +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <keys/encrypted-type.h> +#include <keys/user-type.h> +#include <linux/crypto.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> +#include <linux/f2fs_fs.h> +#include <linux/ratelimit.h> + +#include "f2fs.h" +#include "f2fs_crypto.h" +#include "xattr.h" + +/** + * f2fs_dir_crypt_complete() - + */ +static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res) +{ + struct f2fs_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +bool f2fs_valid_filenames_enc_mode(uint32_t mode) +{ + return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS); +} + +static unsigned max_name_len(struct inode *inode) +{ + return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize : + F2FS_NAME_LEN; +} + +/** + * f2fs_fname_encrypt() - + * + * This function encrypts the input filename, and returns the length of the + * ciphertext. Errors are returned as negative numbers. We trust the caller to + * allocate sufficient memory to oname string. + */ +static int f2fs_fname_encrypt(struct inode *inode, + const struct qstr *iname, struct f2fs_str *oname) +{ + u32 ciphertext_len; + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct crypto_ablkcipher *tfm = ci->ci_ctfm; + int res = 0; + char iv[F2FS_CRYPTO_BLOCK_SIZE]; + struct scatterlist src_sg, dst_sg; + int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK); + char *workbuf, buf[32], *alloc_buf = NULL; + unsigned lim = max_name_len(inode); + + if (iname->len <= 0 || iname->len > lim) + return -EIO; + + ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ? + F2FS_CRYPTO_BLOCK_SIZE : iname->len; + ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding); + ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len; + + if (ciphertext_len <= sizeof(buf)) { + workbuf = buf; + } else { + alloc_buf = kmalloc(ciphertext_len, GFP_NOFS); + if (!alloc_buf) + return -ENOMEM; + workbuf = alloc_buf; + } + + /* Allocate request */ + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", __func__); + kfree(alloc_buf); + return -ENOMEM; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + f2fs_dir_crypt_complete, &ecr); + + /* Copy the input */ + memcpy(workbuf, iname->name, iname->len); + if (iname->len < ciphertext_len) + memset(workbuf + iname->len, 0, ciphertext_len - iname->len); + + /* Initialize IV */ + memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE); + + /* Create encryption request */ + sg_init_one(&src_sg, workbuf, ciphertext_len); + sg_init_one(&dst_sg, oname->name, ciphertext_len); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv); + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + kfree(alloc_buf); + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited(KERN_ERR + "%s: Error (error code %d)\n", __func__, res); + } + oname->len = ciphertext_len; + return res; +} + +/* + * f2fs_fname_decrypt() + * This function decrypts the input filename, and returns + * the length of the plaintext. + * Errors are returned as negative numbers. + * We trust the caller to allocate sufficient memory to oname string. + */ +static int f2fs_fname_decrypt(struct inode *inode, + const struct f2fs_str *iname, struct f2fs_str *oname) +{ + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct crypto_ablkcipher *tfm = ci->ci_ctfm; + int res = 0; + char iv[F2FS_CRYPTO_BLOCK_SIZE]; + unsigned lim = max_name_len(inode); + + if (iname->len <= 0 || iname->len > lim) + return -EIO; + + /* Allocate request */ + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + f2fs_dir_crypt_complete, &ecr); + + /* Initialize IV */ + memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE); + + /* Create decryption request */ + sg_init_one(&src_sg, iname->name, iname->len); + sg_init_one(&dst_sg, oname->name, oname->len); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); + res = crypto_ablkcipher_decrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited(KERN_ERR + "%s: Error in f2fs_fname_decrypt (error code %d)\n", + __func__, res); + return res; + } + + oname->len = strnlen(oname->name, iname->len); + return oname->len; +} + +static const char *lookup_table = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,"; + +/** + * f2fs_fname_encode_digest() - + * + * Encodes the input digest using characters from the set [a-zA-Z0-9_+]. + * The encoded string is roughly 4/3 times the size of the input string. + */ +static int digest_encode(const char *src, int len, char *dst) +{ + int i = 0, bits = 0, ac = 0; + char *cp = dst; + + while (i < len) { + ac += (((unsigned char) src[i]) << bits); + bits += 8; + do { + *cp++ = lookup_table[ac & 0x3f]; + ac >>= 6; + bits -= 6; + } while (bits >= 6); + i++; + } + if (bits) + *cp++ = lookup_table[ac & 0x3f]; + return cp - dst; +} + +static int digest_decode(const char *src, int len, char *dst) +{ + int i = 0, bits = 0, ac = 0; + const char *p; + char *cp = dst; + + while (i < len) { + p = strchr(lookup_table, src[i]); + if (p == NULL || src[i] == 0) + return -2; + ac += (p - lookup_table) << bits; + bits += 6; + if (bits >= 8) { + *cp++ = ac & 0xff; + ac >>= 8; + bits -= 8; + } + i++; + } + if (ac) + return -1; + return cp - dst; +} + +/** + * f2fs_fname_crypto_round_up() - + * + * Return: The next multiple of block size + */ +u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize) +{ + return ((size + blksize - 1) / blksize) * blksize; +} + +/** + * f2fs_fname_crypto_alloc_obuff() - + * + * Allocates an output buffer that is sufficient for the crypto operation + * specified by the context and the direction. + */ +int f2fs_fname_crypto_alloc_buffer(struct inode *inode, + u32 ilen, struct f2fs_str *crypto_str) +{ + unsigned int olen; + int padding = 16; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (ci) + padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK); + if (padding < F2FS_CRYPTO_BLOCK_SIZE) + padding = F2FS_CRYPTO_BLOCK_SIZE; + olen = f2fs_fname_crypto_round_up(ilen, padding); + crypto_str->len = olen; + if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2) + olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2; + /* Allocated buffer can hold one more character to null-terminate the + * string */ + crypto_str->name = kmalloc(olen + 1, GFP_NOFS); + if (!(crypto_str->name)) + return -ENOMEM; + return 0; +} + +/** + * f2fs_fname_crypto_free_buffer() - + * + * Frees the buffer allocated for crypto operation. + */ +void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str) +{ + if (!crypto_str) + return; + kfree(crypto_str->name); + crypto_str->name = NULL; +} + +/** + * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space + */ +int f2fs_fname_disk_to_usr(struct inode *inode, + f2fs_hash_t *hash, + const struct f2fs_str *iname, + struct f2fs_str *oname) +{ + const struct qstr qname = FSTR_TO_QSTR(iname); + char buf[24]; + int ret; + + if (is_dot_dotdot(&qname)) { + oname->name[0] = '.'; + oname->name[iname->len - 1] = '.'; + oname->len = iname->len; + return oname->len; + } + + if (F2FS_I(inode)->i_crypt_info) + return f2fs_fname_decrypt(inode, iname, oname); + + if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) { + ret = digest_encode(iname->name, iname->len, oname->name); + oname->len = ret; + return ret; + } + if (hash) { + memcpy(buf, hash, 4); + memset(buf + 4, 0, 4); + } else + memset(buf, 0, 8); + memcpy(buf + 8, iname->name + iname->len - 16, 16); + oname->name[0] = '_'; + ret = digest_encode(buf, 24, oname->name + 1); + oname->len = ret + 1; + return ret + 1; +} + +/** + * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space + */ +int f2fs_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct f2fs_str *oname) +{ + int res; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (is_dot_dotdot(iname)) { + oname->name[0] = '.'; + oname->name[iname->len - 1] = '.'; + oname->len = iname->len; + return oname->len; + } + + if (ci) { + res = f2fs_fname_encrypt(inode, iname, oname); + return res; + } + /* Without a proper key, a user is not allowed to modify the filenames + * in a directory. Consequently, a user space name cannot be mapped to + * a disk-space name */ + return -EACCES; +} + +int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct f2fs_filename *fname) +{ + struct f2fs_crypt_info *ci; + int ret = 0, bigname = 0; + + memset(fname, 0, sizeof(struct f2fs_filename)); + fname->usr_fname = iname; + + if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) { + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; + } + ret = f2fs_get_encryption_info(dir); + if (ret) + return ret; + ci = F2FS_I(dir)->i_crypt_info; + if (ci) { + ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len, + &fname->crypto_buf); + if (ret < 0) + return ret; + ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf); + if (ret < 0) + goto errout; + fname->disk_name.name = fname->crypto_buf.name; + fname->disk_name.len = fname->crypto_buf.len; + return 0; + } + if (!lookup) + return -EACCES; + + /* We don't have the key and we are doing a lookup; decode the + * user-supplied name + */ + if (iname->name[0] == '_') + bigname = 1; + if ((bigname && (iname->len != 33)) || + (!bigname && (iname->len > 43))) + return -ENOENT; + + fname->crypto_buf.name = kmalloc(32, GFP_KERNEL); + if (fname->crypto_buf.name == NULL) + return -ENOMEM; + ret = digest_decode(iname->name + bigname, iname->len - bigname, + fname->crypto_buf.name); + if (ret < 0) { + ret = -ENOENT; + goto errout; + } + fname->crypto_buf.len = ret; + if (bigname) { + memcpy(&fname->hash, fname->crypto_buf.name, 4); + } else { + fname->disk_name.name = fname->crypto_buf.name; + fname->disk_name.len = fname->crypto_buf.len; + } + return 0; +errout: + f2fs_fname_crypto_free_buffer(&fname->crypto_buf); + return ret; +} + +void f2fs_fname_free_filename(struct f2fs_filename *fname) +{ + kfree(fname->crypto_buf.name); + fname->crypto_buf.name = NULL; + fname->usr_fname = NULL; + fname->disk_name.name = NULL; +} diff --git a/kernel/fs/f2fs/crypto_key.c b/kernel/fs/f2fs/crypto_key.c new file mode 100644 index 000000000..5de2d866a --- /dev/null +++ b/kernel/fs/f2fs/crypto_key.c @@ -0,0 +1,254 @@ +/* + * linux/fs/f2fs/crypto_key.c + * + * Copied from linux/fs/f2fs/crypto_key.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption key functions for f2fs + * + * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015. + */ +#include <keys/encrypted-type.h> +#include <keys/user-type.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <uapi/linux/keyctl.h> +#include <crypto/hash.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" +#include "xattr.h" + +static void derive_crypt_complete(struct crypto_async_request *req, int rc) +{ + struct f2fs_completion_result *ecr = req->data; + + if (rc == -EINPROGRESS) + return; + + ecr->res = rc; + complete(&ecr->completion); +} + +/** + * f2fs_derive_key_aes() - Derive a key using AES-128-ECB + * @deriving_key: Encryption key used for derivatio. + * @source_key: Source key to which to apply derivation. + * @derived_key: Derived key. + * + * Return: Zero on success; non-zero otherwise. + */ +static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE], + char source_key[F2FS_AES_256_XTS_KEY_SIZE], + char derived_key[F2FS_AES_256_XTS_KEY_SIZE]) +{ + int res = 0; + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0, + 0); + + if (IS_ERR(tfm)) { + res = PTR_ERR(tfm); + tfm = NULL; + goto out; + } + crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + res = -ENOMEM; + goto out; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + derive_crypt_complete, &ecr); + res = crypto_ablkcipher_setkey(tfm, deriving_key, + F2FS_AES_128_ECB_KEY_SIZE); + if (res < 0) + goto out; + + sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE); + sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, + F2FS_AES_256_XTS_KEY_SIZE, NULL); + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } +out: + if (req) + ablkcipher_request_free(req); + if (tfm) + crypto_free_ablkcipher(tfm); + return res; +} + +static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci) +{ + if (!ci) + return; + + key_put(ci->ci_keyring_key); + crypto_free_ablkcipher(ci->ci_ctfm); + kmem_cache_free(f2fs_crypt_info_cachep, ci); +} + +void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_crypt_info *prev; + + if (ci == NULL) + ci = ACCESS_ONCE(fi->i_crypt_info); + if (ci == NULL) + return; + prev = cmpxchg(&fi->i_crypt_info, ci, NULL); + if (prev != ci) + return; + + f2fs_free_crypt_info(ci); +} + +int _f2fs_get_encryption_info(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_crypt_info *crypt_info; + char full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE + + (F2FS_KEY_DESCRIPTOR_SIZE * 2) + 1]; + struct key *keyring_key = NULL; + struct f2fs_encryption_key *master_key; + struct f2fs_encryption_context ctx; + const struct user_key_payload *ukp; + struct crypto_ablkcipher *ctfm; + const char *cipher_str; + char raw_key[F2FS_MAX_KEY_SIZE]; + char mode; + int res; + + res = f2fs_crypto_initialize(); + if (res) + return res; +retry: + crypt_info = ACCESS_ONCE(fi->i_crypt_info); + if (crypt_info) { + if (!crypt_info->ci_keyring_key || + key_validate(crypt_info->ci_keyring_key) == 0) + return 0; + f2fs_free_encryption_info(inode, crypt_info); + goto retry; + } + + res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx), NULL); + if (res < 0) + return res; + else if (res != sizeof(ctx)) + return -EINVAL; + res = 0; + + crypt_info = kmem_cache_alloc(f2fs_crypt_info_cachep, GFP_NOFS); + if (!crypt_info) + return -ENOMEM; + + crypt_info->ci_flags = ctx.flags; + crypt_info->ci_data_mode = ctx.contents_encryption_mode; + crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; + crypt_info->ci_ctfm = NULL; + crypt_info->ci_keyring_key = NULL; + memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, + sizeof(crypt_info->ci_master_key)); + if (S_ISREG(inode->i_mode)) + mode = crypt_info->ci_data_mode; + else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + mode = crypt_info->ci_filename_mode; + else + BUG(); + + switch (mode) { + case F2FS_ENCRYPTION_MODE_AES_256_XTS: + cipher_str = "xts(aes)"; + break; + case F2FS_ENCRYPTION_MODE_AES_256_CTS: + cipher_str = "cts(cbc(aes))"; + break; + default: + printk_once(KERN_WARNING + "f2fs: unsupported key mode %d (ino %u)\n", + mode, (unsigned) inode->i_ino); + res = -ENOKEY; + goto out; + } + + memcpy(full_key_descriptor, F2FS_KEY_DESC_PREFIX, + F2FS_KEY_DESC_PREFIX_SIZE); + sprintf(full_key_descriptor + F2FS_KEY_DESC_PREFIX_SIZE, + "%*phN", F2FS_KEY_DESCRIPTOR_SIZE, + ctx.master_key_descriptor); + full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE + + (2 * F2FS_KEY_DESCRIPTOR_SIZE)] = '\0'; + keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL); + if (IS_ERR(keyring_key)) { + res = PTR_ERR(keyring_key); + keyring_key = NULL; + goto out; + } + crypt_info->ci_keyring_key = keyring_key; + BUG_ON(keyring_key->type != &key_type_logon); + ukp = user_key_payload(keyring_key); + if (ukp->datalen != sizeof(struct f2fs_encryption_key)) { + res = -EINVAL; + goto out; + } + master_key = (struct f2fs_encryption_key *)ukp->data; + BUILD_BUG_ON(F2FS_AES_128_ECB_KEY_SIZE != + F2FS_KEY_DERIVATION_NONCE_SIZE); + BUG_ON(master_key->size != F2FS_AES_256_XTS_KEY_SIZE); + res = f2fs_derive_key_aes(ctx.nonce, master_key->raw, + raw_key); + if (res) + goto out; + + ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0); + if (!ctfm || IS_ERR(ctfm)) { + res = ctfm ? PTR_ERR(ctfm) : -ENOMEM; + printk(KERN_DEBUG + "%s: error %d (inode %u) allocating crypto tfm\n", + __func__, res, (unsigned) inode->i_ino); + goto out; + } + crypt_info->ci_ctfm = ctfm; + crypto_ablkcipher_clear_flags(ctfm, ~0); + crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm), + CRYPTO_TFM_REQ_WEAK_KEY); + res = crypto_ablkcipher_setkey(ctfm, raw_key, + f2fs_encryption_key_size(mode)); + if (res) + goto out; + + memzero_explicit(raw_key, sizeof(raw_key)); + if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) { + f2fs_free_crypt_info(crypt_info); + goto retry; + } + return 0; + +out: + if (res == -ENOKEY && !S_ISREG(inode->i_mode)) + res = 0; + + f2fs_free_crypt_info(crypt_info); + memzero_explicit(raw_key, sizeof(raw_key)); + return res; +} + +int f2fs_has_encryption_key(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + + return (fi->i_crypt_info != NULL); +} diff --git a/kernel/fs/f2fs/crypto_policy.c b/kernel/fs/f2fs/crypto_policy.c new file mode 100644 index 000000000..d4a96af51 --- /dev/null +++ b/kernel/fs/f2fs/crypto_policy.c @@ -0,0 +1,209 @@ +/* + * copied from linux/fs/ext4/crypto_policy.c + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility. + * + * This contains encryption policy functions for f2fs with some modifications + * to support f2fs-specific xattr APIs. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ +#include <linux/random.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" +#include "xattr.h" + +static int f2fs_inode_has_encryption_context(struct inode *inode) +{ + int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0, NULL); + return (res > 0); +} + +/* + * check whether the policy is consistent with the encryption context + * for the inode + */ +static int f2fs_is_encryption_context_consistent_with_policy( + struct inode *inode, const struct f2fs_encryption_policy *policy) +{ + struct f2fs_encryption_context ctx; + int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), NULL); + + if (res != sizeof(ctx)) + return 0; + + return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE) == 0 && + (ctx.flags == policy->flags) && + (ctx.contents_encryption_mode == + policy->contents_encryption_mode) && + (ctx.filenames_encryption_mode == + policy->filenames_encryption_mode)); +} + +static int f2fs_create_encryption_context_from_policy( + struct inode *inode, const struct f2fs_encryption_policy *policy) +{ + struct f2fs_encryption_context ctx; + + ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1; + memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE); + + if (!f2fs_valid_contents_enc_mode(policy->contents_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid contents encryption mode %d\n", __func__, + policy->contents_encryption_mode); + return -EINVAL; + } + + if (!f2fs_valid_filenames_enc_mode(policy->filenames_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid filenames encryption mode %d\n", __func__, + policy->filenames_encryption_mode); + return -EINVAL; + } + + if (policy->flags & ~F2FS_POLICY_FLAGS_VALID) + return -EINVAL; + + ctx.contents_encryption_mode = policy->contents_encryption_mode; + ctx.filenames_encryption_mode = policy->filenames_encryption_mode; + ctx.flags = policy->flags; + BUILD_BUG_ON(sizeof(ctx.nonce) != F2FS_KEY_DERIVATION_NONCE_SIZE); + get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE); + + return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), NULL, XATTR_CREATE); +} + +int f2fs_process_policy(const struct f2fs_encryption_policy *policy, + struct inode *inode) +{ + if (policy->version != 0) + return -EINVAL; + + if (!S_ISDIR(inode->i_mode)) + return -EINVAL; + + if (!f2fs_inode_has_encryption_context(inode)) { + if (!f2fs_empty_dir(inode)) + return -ENOTEMPTY; + return f2fs_create_encryption_context_from_policy(inode, + policy); + } + + if (f2fs_is_encryption_context_consistent_with_policy(inode, policy)) + return 0; + + printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n", + __func__); + return -EINVAL; +} + +int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy) +{ + struct f2fs_encryption_context ctx; + int res; + + if (!f2fs_encrypted_inode(inode)) + return -ENODATA; + + res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx), NULL); + if (res != sizeof(ctx)) + return -ENODATA; + if (ctx.format != F2FS_ENCRYPTION_CONTEXT_FORMAT_V1) + return -EINVAL; + + policy->version = 0; + policy->contents_encryption_mode = ctx.contents_encryption_mode; + policy->filenames_encryption_mode = ctx.filenames_encryption_mode; + policy->flags = ctx.flags; + memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE); + return 0; +} + +int f2fs_is_child_context_consistent_with_parent(struct inode *parent, + struct inode *child) +{ + struct f2fs_crypt_info *parent_ci, *child_ci; + int res; + + if ((parent == NULL) || (child == NULL)) { + pr_err("parent %p child %p\n", parent, child); + BUG_ON(1); + } + + /* no restrictions if the parent directory is not encrypted */ + if (!f2fs_encrypted_inode(parent)) + return 1; + /* if the child directory is not encrypted, this is always a problem */ + if (!f2fs_encrypted_inode(child)) + return 0; + res = f2fs_get_encryption_info(parent); + if (res) + return 0; + res = f2fs_get_encryption_info(child); + if (res) + return 0; + parent_ci = F2FS_I(parent)->i_crypt_info; + child_ci = F2FS_I(child)->i_crypt_info; + if (!parent_ci && !child_ci) + return 1; + if (!parent_ci || !child_ci) + return 0; + + return (memcmp(parent_ci->ci_master_key, + child_ci->ci_master_key, + F2FS_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ci->ci_data_mode == child_ci->ci_data_mode) && + (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) && + (parent_ci->ci_flags == child_ci->ci_flags)); +} + +/** + * f2fs_inherit_context() - Sets a child context from its parent + * @parent: Parent inode from which the context is inherited. + * @child: Child inode that inherits the context from @parent. + * + * Return: Zero on success, non-zero otherwise + */ +int f2fs_inherit_context(struct inode *parent, struct inode *child, + struct page *ipage) +{ + struct f2fs_encryption_context ctx; + struct f2fs_crypt_info *ci; + int res; + + res = f2fs_get_encryption_info(parent); + if (res < 0) + return res; + + ci = F2FS_I(parent)->i_crypt_info; + BUG_ON(ci == NULL); + + ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1; + + ctx.contents_encryption_mode = ci->ci_data_mode; + ctx.filenames_encryption_mode = ci->ci_filename_mode; + ctx.flags = ci->ci_flags; + memcpy(ctx.master_key_descriptor, ci->ci_master_key, + F2FS_KEY_DESCRIPTOR_SIZE); + + get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE); + return f2fs_setxattr(child, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), ipage, XATTR_CREATE); +} diff --git a/kernel/fs/f2fs/data.c b/kernel/fs/f2fs/data.c index 1e1aae669..972eab7ac 100644 --- a/kernel/fs/f2fs/data.c +++ b/kernel/fs/f2fs/data.c @@ -14,10 +14,12 @@ #include <linux/mpage.h> #include <linux/writeback.h> #include <linux/backing-dev.h> +#include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/prefetch.h> #include <linux/uio.h> +#include <linux/cleancache.h> #include "f2fs.h" #include "node.h" @@ -25,18 +27,24 @@ #include "trace.h" #include <trace/events/f2fs.h> -static struct kmem_cache *extent_tree_slab; -static struct kmem_cache *extent_node_slab; - -static void f2fs_read_end_io(struct bio *bio, int err) +static void f2fs_read_end_io(struct bio *bio) { struct bio_vec *bvec; int i; + if (f2fs_bio_encrypted(bio)) { + if (bio->bi_error) { + f2fs_release_crypto_ctx(bio->bi_private); + } else { + f2fs_end_io_crypto_work(bio->bi_private, bio); + return; + } + } + bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (!err) { + if (!bio->bi_error) { SetPageUptodate(page); } else { ClearPageUptodate(page); @@ -47,7 +55,7 @@ static void f2fs_read_end_io(struct bio *bio, int err) bio_put(bio); } -static void f2fs_write_end_io(struct bio *bio, int err) +static void f2fs_write_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = bio->bi_private; struct bio_vec *bvec; @@ -56,7 +64,9 @@ static void f2fs_write_end_io(struct bio *bio, int err) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (unlikely(err)) { + f2fs_restore_and_release_control_page(&page); + + if (unlikely(bio->bi_error)) { set_page_dirty(page); set_bit(AS_EIO, &page->mapping->flags); f2fs_stop_checkpoint(sbi); @@ -80,13 +90,12 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, { struct bio *bio; - /* No failure on bio allocation */ - bio = bio_alloc(GFP_NOIO, npages); + bio = f2fs_bio_alloc(npages); bio->bi_bdev = sbi->sb->s_bdev; bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; - bio->bi_private = sbi; + bio->bi_private = is_read ? NULL : sbi; return bio; } @@ -133,20 +142,19 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, * Fill the locked page with data located in the block address. * Return unlocked page. */ -int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, - struct f2fs_io_info *fio) +int f2fs_submit_page_bio(struct f2fs_io_info *fio) { struct bio *bio; + struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page; trace_f2fs_submit_page_bio(page, fio); - f2fs_trace_ios(page, fio, 0); + f2fs_trace_ios(fio, 0); /* Allocate a new bio */ - bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw)); + bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw)); if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { bio_put(bio); - f2fs_put_page(page, 1); return -EFAULT; } @@ -154,12 +162,13 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, return 0; } -void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page, - struct f2fs_io_info *fio) +void f2fs_submit_page_mbio(struct f2fs_io_info *fio) { + struct f2fs_sb_info *sbi = fio->sbi; enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io; bool is_read = is_read_io(fio->rw); + struct page *bio_page; io = is_read ? &sbi->read_io : &sbi->write_io[btype]; @@ -181,17 +190,19 @@ alloc_new: io->fio = *fio; } - if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) < + bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; + + if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { __submit_merged_bio(io); goto alloc_new; } io->last_block_in_bio = fio->blk_addr; - f2fs_trace_ios(page, fio, 0); + f2fs_trace_ios(fio, 0); up_write(&io->io_rwsem); - trace_f2fs_submit_page_mbio(page, fio); + trace_f2fs_submit_page_mbio(fio->page, fio); } /* @@ -251,661 +262,21 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) return err; } -static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs, - struct extent_info *ei, struct buffer_head *bh_result) -{ - unsigned int blkbits = sb->s_blocksize_bits; - size_t max_size = bh_result->b_size; - size_t mapped_size; - - clear_buffer_new(bh_result); - map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs); - mapped_size = (ei->fofs + ei->len - pgofs) << blkbits; - bh_result->b_size = min(max_size, mapped_size); -} - -static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs, - struct extent_info *ei) -{ - struct f2fs_inode_info *fi = F2FS_I(inode); - pgoff_t start_fofs, end_fofs; - block_t start_blkaddr; - - read_lock(&fi->ext_lock); - if (fi->ext.len == 0) { - read_unlock(&fi->ext_lock); - return false; - } - - stat_inc_total_hit(inode->i_sb); - - start_fofs = fi->ext.fofs; - end_fofs = fi->ext.fofs + fi->ext.len - 1; - start_blkaddr = fi->ext.blk; - - if (pgofs >= start_fofs && pgofs <= end_fofs) { - *ei = fi->ext; - stat_inc_read_hit(inode->i_sb); - read_unlock(&fi->ext_lock); - return true; - } - read_unlock(&fi->ext_lock); - return false; -} - -static bool update_extent_info(struct inode *inode, pgoff_t fofs, - block_t blkaddr) -{ - struct f2fs_inode_info *fi = F2FS_I(inode); - pgoff_t start_fofs, end_fofs; - block_t start_blkaddr, end_blkaddr; - int need_update = true; - - write_lock(&fi->ext_lock); - - start_fofs = fi->ext.fofs; - end_fofs = fi->ext.fofs + fi->ext.len - 1; - start_blkaddr = fi->ext.blk; - end_blkaddr = fi->ext.blk + fi->ext.len - 1; - - /* Drop and initialize the matched extent */ - if (fi->ext.len == 1 && fofs == start_fofs) - fi->ext.len = 0; - - /* Initial extent */ - if (fi->ext.len == 0) { - if (blkaddr != NULL_ADDR) { - fi->ext.fofs = fofs; - fi->ext.blk = blkaddr; - fi->ext.len = 1; - } - goto end_update; - } - - /* Front merge */ - if (fofs == start_fofs - 1 && blkaddr == start_blkaddr - 1) { - fi->ext.fofs--; - fi->ext.blk--; - fi->ext.len++; - goto end_update; - } - - /* Back merge */ - if (fofs == end_fofs + 1 && blkaddr == end_blkaddr + 1) { - fi->ext.len++; - goto end_update; - } - - /* Split the existing extent */ - if (fi->ext.len > 1 && - fofs >= start_fofs && fofs <= end_fofs) { - if ((end_fofs - fofs) < (fi->ext.len >> 1)) { - fi->ext.len = fofs - start_fofs; - } else { - fi->ext.fofs = fofs + 1; - fi->ext.blk = start_blkaddr + fofs - start_fofs + 1; - fi->ext.len -= fofs - start_fofs + 1; - } - } else { - need_update = false; - } - - /* Finally, if the extent is very fragmented, let's drop the cache. */ - if (fi->ext.len < F2FS_MIN_EXTENT_LEN) { - fi->ext.len = 0; - set_inode_flag(fi, FI_NO_EXTENT); - need_update = true; - } -end_update: - write_unlock(&fi->ext_lock); - return need_update; -} - -static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, - struct extent_tree *et, struct extent_info *ei, - struct rb_node *parent, struct rb_node **p) +int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) { - struct extent_node *en; - - en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC); - if (!en) - return NULL; - - en->ei = *ei; - INIT_LIST_HEAD(&en->list); - - rb_link_node(&en->rb_node, parent, p); - rb_insert_color(&en->rb_node, &et->root); - et->count++; - atomic_inc(&sbi->total_ext_node); - return en; -} - -static void __detach_extent_node(struct f2fs_sb_info *sbi, - struct extent_tree *et, struct extent_node *en) -{ - rb_erase(&en->rb_node, &et->root); - et->count--; - atomic_dec(&sbi->total_ext_node); - - if (et->cached_en == en) - et->cached_en = NULL; -} - -static struct extent_tree *__find_extent_tree(struct f2fs_sb_info *sbi, - nid_t ino) -{ - struct extent_tree *et; - - down_read(&sbi->extent_tree_lock); - et = radix_tree_lookup(&sbi->extent_tree_root, ino); - if (!et) { - up_read(&sbi->extent_tree_lock); - return NULL; - } - atomic_inc(&et->refcount); - up_read(&sbi->extent_tree_lock); - - return et; -} - -static struct extent_tree *__grab_extent_tree(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct extent_tree *et; - nid_t ino = inode->i_ino; - - down_write(&sbi->extent_tree_lock); - et = radix_tree_lookup(&sbi->extent_tree_root, ino); - if (!et) { - et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS); - f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et); - memset(et, 0, sizeof(struct extent_tree)); - et->ino = ino; - et->root = RB_ROOT; - et->cached_en = NULL; - rwlock_init(&et->lock); - atomic_set(&et->refcount, 0); - et->count = 0; - sbi->total_ext_tree++; - } - atomic_inc(&et->refcount); - up_write(&sbi->extent_tree_lock); - - return et; -} - -static struct extent_node *__lookup_extent_tree(struct extent_tree *et, - unsigned int fofs) -{ - struct rb_node *node = et->root.rb_node; - struct extent_node *en; - - if (et->cached_en) { - struct extent_info *cei = &et->cached_en->ei; - - if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) - return et->cached_en; - } - - while (node) { - en = rb_entry(node, struct extent_node, rb_node); - - if (fofs < en->ei.fofs) { - node = node->rb_left; - } else if (fofs >= en->ei.fofs + en->ei.len) { - node = node->rb_right; - } else { - et->cached_en = en; - return en; - } - } - return NULL; -} - -static struct extent_node *__try_back_merge(struct f2fs_sb_info *sbi, - struct extent_tree *et, struct extent_node *en) -{ - struct extent_node *prev; - struct rb_node *node; - - node = rb_prev(&en->rb_node); - if (!node) - return NULL; - - prev = rb_entry(node, struct extent_node, rb_node); - if (__is_back_mergeable(&en->ei, &prev->ei)) { - en->ei.fofs = prev->ei.fofs; - en->ei.blk = prev->ei.blk; - en->ei.len += prev->ei.len; - __detach_extent_node(sbi, et, prev); - return prev; - } - return NULL; -} - -static struct extent_node *__try_front_merge(struct f2fs_sb_info *sbi, - struct extent_tree *et, struct extent_node *en) -{ - struct extent_node *next; - struct rb_node *node; - - node = rb_next(&en->rb_node); - if (!node) - return NULL; - - next = rb_entry(node, struct extent_node, rb_node); - if (__is_front_mergeable(&en->ei, &next->ei)) { - en->ei.len += next->ei.len; - __detach_extent_node(sbi, et, next); - return next; - } - return NULL; -} - -static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, - struct extent_tree *et, struct extent_info *ei, - struct extent_node **den) -{ - struct rb_node **p = &et->root.rb_node; - struct rb_node *parent = NULL; - struct extent_node *en; - - while (*p) { - parent = *p; - en = rb_entry(parent, struct extent_node, rb_node); - - if (ei->fofs < en->ei.fofs) { - if (__is_front_mergeable(ei, &en->ei)) { - f2fs_bug_on(sbi, !den); - en->ei.fofs = ei->fofs; - en->ei.blk = ei->blk; - en->ei.len += ei->len; - *den = __try_back_merge(sbi, et, en); - return en; - } - p = &(*p)->rb_left; - } else if (ei->fofs >= en->ei.fofs + en->ei.len) { - if (__is_back_mergeable(ei, &en->ei)) { - f2fs_bug_on(sbi, !den); - en->ei.len += ei->len; - *den = __try_front_merge(sbi, et, en); - return en; - } - p = &(*p)->rb_right; - } else { - f2fs_bug_on(sbi, 1); - } - } - - return __attach_extent_node(sbi, et, ei, parent, p); -} - -static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, - struct extent_tree *et, bool free_all) -{ - struct rb_node *node, *next; - struct extent_node *en; - unsigned int count = et->count; - - node = rb_first(&et->root); - while (node) { - next = rb_next(node); - en = rb_entry(node, struct extent_node, rb_node); - - if (free_all) { - spin_lock(&sbi->extent_lock); - if (!list_empty(&en->list)) - list_del_init(&en->list); - spin_unlock(&sbi->extent_lock); - } - - if (free_all || list_empty(&en->list)) { - __detach_extent_node(sbi, et, en); - kmem_cache_free(extent_node_slab, en); - } - node = next; - } - - return count - et->count; -} - -static void f2fs_init_extent_tree(struct inode *inode, - struct f2fs_extent *i_ext) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct extent_tree *et; - struct extent_node *en; struct extent_info ei; + struct inode *inode = dn->inode; - if (le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN) - return; - - et = __grab_extent_tree(inode); - - write_lock(&et->lock); - if (et->count) - goto out; - - set_extent_info(&ei, le32_to_cpu(i_ext->fofs), - le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len)); - - en = __insert_extent_tree(sbi, et, &ei, NULL); - if (en) { - et->cached_en = en; - - spin_lock(&sbi->extent_lock); - list_add_tail(&en->list, &sbi->extent_list); - spin_unlock(&sbi->extent_lock); - } -out: - write_unlock(&et->lock); - atomic_dec(&et->refcount); -} - -static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, - struct extent_info *ei) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct extent_tree *et; - struct extent_node *en; - - trace_f2fs_lookup_extent_tree_start(inode, pgofs); - - et = __find_extent_tree(sbi, inode->i_ino); - if (!et) - return false; - - read_lock(&et->lock); - en = __lookup_extent_tree(et, pgofs); - if (en) { - *ei = en->ei; - spin_lock(&sbi->extent_lock); - if (!list_empty(&en->list)) - list_move_tail(&en->list, &sbi->extent_list); - spin_unlock(&sbi->extent_lock); - stat_inc_read_hit(sbi->sb); - } - stat_inc_total_hit(sbi->sb); - read_unlock(&et->lock); - - trace_f2fs_lookup_extent_tree_end(inode, pgofs, en); - - atomic_dec(&et->refcount); - return en ? true : false; -} - -static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs, - block_t blkaddr) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct extent_tree *et; - struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL; - struct extent_node *den = NULL; - struct extent_info ei, dei; - unsigned int endofs; - - trace_f2fs_update_extent_tree(inode, fofs, blkaddr); - - et = __grab_extent_tree(inode); - - write_lock(&et->lock); - - /* 1. lookup and remove existing extent info in cache */ - en = __lookup_extent_tree(et, fofs); - if (!en) - goto update_extent; - - dei = en->ei; - __detach_extent_node(sbi, et, en); - - /* 2. if extent can be split more, split and insert the left part */ - if (dei.len > 1) { - /* insert left part of split extent into cache */ - if (fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN) { - set_extent_info(&ei, dei.fofs, dei.blk, - fofs - dei.fofs); - en1 = __insert_extent_tree(sbi, et, &ei, NULL); - } - - /* insert right part of split extent into cache */ - endofs = dei.fofs + dei.len - 1; - if (endofs - fofs >= F2FS_MIN_EXTENT_LEN) { - set_extent_info(&ei, fofs + 1, - fofs - dei.fofs + dei.blk, endofs - fofs); - en2 = __insert_extent_tree(sbi, et, &ei, NULL); - } - } - -update_extent: - /* 3. update extent in extent cache */ - if (blkaddr) { - set_extent_info(&ei, fofs, blkaddr, 1); - en3 = __insert_extent_tree(sbi, et, &ei, &den); - } - - /* 4. update in global extent list */ - spin_lock(&sbi->extent_lock); - if (en && !list_empty(&en->list)) - list_del(&en->list); - /* - * en1 and en2 split from en, they will become more and more smaller - * fragments after splitting several times. So if the length is smaller - * than F2FS_MIN_EXTENT_LEN, we will not add them into extent tree. - */ - if (en1) - list_add_tail(&en1->list, &sbi->extent_list); - if (en2) - list_add_tail(&en2->list, &sbi->extent_list); - if (en3) { - if (list_empty(&en3->list)) - list_add_tail(&en3->list, &sbi->extent_list); - else - list_move_tail(&en3->list, &sbi->extent_list); - } - if (den && !list_empty(&den->list)) - list_del(&den->list); - spin_unlock(&sbi->extent_lock); - - /* 5. release extent node */ - if (en) - kmem_cache_free(extent_node_slab, en); - if (den) - kmem_cache_free(extent_node_slab, den); - - write_unlock(&et->lock); - atomic_dec(&et->refcount); -} - -void f2fs_preserve_extent_tree(struct inode *inode) -{ - struct extent_tree *et; - struct extent_info *ext = &F2FS_I(inode)->ext; - bool sync = false; - - if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) - return; - - et = __find_extent_tree(F2FS_I_SB(inode), inode->i_ino); - if (!et) { - if (ext->len) { - ext->len = 0; - update_inode_page(inode); - } - return; - } - - read_lock(&et->lock); - if (et->count) { - struct extent_node *en; - - if (et->cached_en) { - en = et->cached_en; - } else { - struct rb_node *node = rb_first(&et->root); - - if (!node) - node = rb_last(&et->root); - en = rb_entry(node, struct extent_node, rb_node); - } - - if (__is_extent_same(ext, &en->ei)) - goto out; - - *ext = en->ei; - sync = true; - } else if (ext->len) { - ext->len = 0; - sync = true; - } -out: - read_unlock(&et->lock); - atomic_dec(&et->refcount); - - if (sync) - update_inode_page(inode); -} - -void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) -{ - struct extent_tree *treevec[EXT_TREE_VEC_SIZE]; - struct extent_node *en, *tmp; - unsigned long ino = F2FS_ROOT_INO(sbi); - struct radix_tree_iter iter; - void **slot; - unsigned int found; - unsigned int node_cnt = 0, tree_cnt = 0; - - if (!test_opt(sbi, EXTENT_CACHE)) - return; - - if (available_free_memory(sbi, EXTENT_CACHE)) - return; - - spin_lock(&sbi->extent_lock); - list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) { - if (!nr_shrink--) - break; - list_del_init(&en->list); - } - spin_unlock(&sbi->extent_lock); - - down_read(&sbi->extent_tree_lock); - while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root, - (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { - unsigned i; - - ino = treevec[found - 1]->ino + 1; - for (i = 0; i < found; i++) { - struct extent_tree *et = treevec[i]; - - atomic_inc(&et->refcount); - write_lock(&et->lock); - node_cnt += __free_extent_tree(sbi, et, false); - write_unlock(&et->lock); - atomic_dec(&et->refcount); - } - } - up_read(&sbi->extent_tree_lock); - - down_write(&sbi->extent_tree_lock); - radix_tree_for_each_slot(slot, &sbi->extent_tree_root, &iter, - F2FS_ROOT_INO(sbi)) { - struct extent_tree *et = (struct extent_tree *)*slot; - - if (!atomic_read(&et->refcount) && !et->count) { - radix_tree_delete(&sbi->extent_tree_root, et->ino); - kmem_cache_free(extent_tree_slab, et); - sbi->total_ext_tree--; - tree_cnt++; - } - } - up_write(&sbi->extent_tree_lock); - - trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt); -} - -void f2fs_destroy_extent_tree(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct extent_tree *et; - unsigned int node_cnt = 0; - - if (!test_opt(sbi, EXTENT_CACHE)) - return; - - et = __find_extent_tree(sbi, inode->i_ino); - if (!et) - goto out; - - /* free all extent info belong to this extent tree */ - write_lock(&et->lock); - node_cnt = __free_extent_tree(sbi, et, true); - write_unlock(&et->lock); - - atomic_dec(&et->refcount); - - /* try to find and delete extent tree entry in radix tree */ - down_write(&sbi->extent_tree_lock); - et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino); - if (!et) { - up_write(&sbi->extent_tree_lock); - goto out; + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn->data_blkaddr = ei.blk + index - ei.fofs; + return 0; } - f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count); - radix_tree_delete(&sbi->extent_tree_root, inode->i_ino); - kmem_cache_free(extent_tree_slab, et); - sbi->total_ext_tree--; - up_write(&sbi->extent_tree_lock); -out: - trace_f2fs_destroy_extent_tree(inode, node_cnt); - return; -} - -void f2fs_init_extent_cache(struct inode *inode, struct f2fs_extent *i_ext) -{ - if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) - f2fs_init_extent_tree(inode, i_ext); - - write_lock(&F2FS_I(inode)->ext_lock); - get_extent_info(&F2FS_I(inode)->ext, *i_ext); - write_unlock(&F2FS_I(inode)->ext_lock); -} - -static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, - struct extent_info *ei) -{ - if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) - return false; - - if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) - return f2fs_lookup_extent_tree(inode, pgofs, ei); - return lookup_extent_info(inode, pgofs, ei); + return f2fs_reserve_block(dn, index); } -void f2fs_update_extent_cache(struct dnode_of_data *dn) -{ - struct f2fs_inode_info *fi = F2FS_I(dn->inode); - pgoff_t fofs; - - f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR); - - if (is_inode_flag_set(fi, FI_NO_EXTENT)) - return; - - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + - dn->ofs_in_node; - - if (test_opt(F2FS_I_SB(dn->inode), EXTENT_CACHE)) - return f2fs_update_extent_tree(dn->inode, fofs, - dn->data_blkaddr); - - if (update_extent_info(dn->inode, fofs, dn->data_blkaddr)) - sync_inode_page(dn); -} - -struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) +struct page *get_read_data_page(struct inode *inode, pgoff_t index, + int rw, bool for_write) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; @@ -913,23 +284,19 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) struct extent_info ei; int err; struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(inode), .type = DATA, - .rw = sync ? READ_SYNC : READA, + .rw = rw, + .encrypted_page = NULL, }; - /* - * If sync is false, it needs to check its block allocation. - * This is need and triggered by two flows: - * gc and truncate_partial_data_page. - */ - if (!sync) - goto search; + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return read_mapping_page(mapping, index, NULL); + + page = f2fs_grab_cache_page(mapping, index, for_write); + if (!page) + return ERR_PTR(-ENOMEM); - page = find_get_page(mapping, index); - if (page && PageUptodate(page)) - return page; - f2fs_put_page(page, 0); -search: if (f2fs_lookup_extent_cache(inode, index, &ei)) { dn.data_blkaddr = ei.blk + index - ei.fofs; goto got_it; @@ -938,37 +305,65 @@ search: set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err) - return ERR_PTR(err); + goto put_err; f2fs_put_dnode(&dn); - if (dn.data_blkaddr == NULL_ADDR) - return ERR_PTR(-ENOENT); - - /* By fallocate(), there is no cached page, but with NEW_ADDR */ - if (unlikely(dn.data_blkaddr == NEW_ADDR)) - return ERR_PTR(-EINVAL); - + if (unlikely(dn.data_blkaddr == NULL_ADDR)) { + err = -ENOENT; + goto put_err; + } got_it: - page = grab_cache_page(mapping, index); - if (!page) - return ERR_PTR(-ENOMEM); - if (PageUptodate(page)) { unlock_page(page); return page; } + /* + * A new dentry page is allocated but not able to be written, since its + * new inode page couldn't be allocated due to -ENOSPC. + * In such the case, its blkaddr can be remained as NEW_ADDR. + * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. + */ + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + unlock_page(page); + return page; + } + fio.blk_addr = dn.data_blkaddr; - err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); + fio.page = page; + err = f2fs_submit_page_bio(&fio); if (err) - return ERR_PTR(err); + goto put_err; + return page; - if (sync) { - wait_on_page_locked(page); - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 0); - return ERR_PTR(-EIO); - } +put_err: + f2fs_put_page(page, 1); + return ERR_PTR(err); +} + +struct page *find_data_page(struct inode *inode, pgoff_t index) +{ + struct address_space *mapping = inode->i_mapping; + struct page *page; + + page = find_get_page(mapping, index); + if (page && PageUptodate(page)) + return page; + f2fs_put_page(page, 0); + + page = get_read_data_page(inode, index, READ_SYNC, false); + if (IS_ERR(page)) + return page; + + if (PageUptodate(page)) + return page; + + wait_on_page_locked(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 0); + return ERR_PTR(-EIO); } return page; } @@ -978,61 +373,17 @@ got_it: * Because, the callers, functions in dir.c and GC, should be able to know * whether this page exists or not. */ -struct page *get_lock_data_page(struct inode *inode, pgoff_t index) +struct page *get_lock_data_page(struct inode *inode, pgoff_t index, + bool for_write) { struct address_space *mapping = inode->i_mapping; - struct dnode_of_data dn; struct page *page; - struct extent_info ei; - int err; - struct f2fs_io_info fio = { - .type = DATA, - .rw = READ_SYNC, - }; repeat: - page = grab_cache_page(mapping, index); - if (!page) - return ERR_PTR(-ENOMEM); - - if (f2fs_lookup_extent_cache(inode, index, &ei)) { - dn.data_blkaddr = ei.blk + index - ei.fofs; - goto got_it; - } - - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); - if (err) { - f2fs_put_page(page, 1); - return ERR_PTR(err); - } - f2fs_put_dnode(&dn); - - if (unlikely(dn.data_blkaddr == NULL_ADDR)) { - f2fs_put_page(page, 1); - return ERR_PTR(-ENOENT); - } - -got_it: - if (PageUptodate(page)) - return page; - - /* - * A new dentry page is allocated but not able to be written, since its - * new inode page couldn't be allocated due to -ENOSPC. - * In such the case, its blkaddr can be remained as NEW_ADDR. - * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. - */ - if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); - SetPageUptodate(page); + page = get_read_data_page(inode, index, READ_SYNC, for_write); + if (IS_ERR(page)) return page; - } - - fio.blk_addr = dn.data_blkaddr; - err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); - if (err) - return ERR_PTR(err); + /* wait for read completion */ lock_page(page); if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); @@ -1051,7 +402,8 @@ got_it: * * Also, caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). - * Note that, ipage is set only by make_empty_dir. + * Note that, ipage is set only by make_empty_dir, and if any error occur, + * ipage should be released by this function. */ struct page *get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size) @@ -1060,57 +412,50 @@ struct page *get_new_data_page(struct inode *inode, struct page *page; struct dnode_of_data dn; int err; +repeat: + page = f2fs_grab_cache_page(mapping, index, true); + if (!page) { + /* + * before exiting, we should make sure ipage will be released + * if any error occur. + */ + f2fs_put_page(ipage, 1); + return ERR_PTR(-ENOMEM); + } set_new_dnode(&dn, inode, ipage, NULL, 0); err = f2fs_reserve_block(&dn, index); - if (err) + if (err) { + f2fs_put_page(page, 1); return ERR_PTR(err); -repeat: - page = grab_cache_page(mapping, index); - if (!page) { - err = -ENOMEM; - goto put_err; } + if (!ipage) + f2fs_put_dnode(&dn); if (PageUptodate(page)) - return page; + goto got_it; if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); SetPageUptodate(page); } else { - struct f2fs_io_info fio = { - .type = DATA, - .rw = READ_SYNC, - .blk_addr = dn.data_blkaddr, - }; - err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); - if (err) - goto put_err; + f2fs_put_page(page, 1); - lock_page(page); - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); - err = -EIO; - goto put_err; - } - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); + page = get_read_data_page(inode, index, READ_SYNC, true); + if (IS_ERR(page)) goto repeat; - } - } - if (new_i_size && - i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) { - i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT)); + /* wait for read completion */ + lock_page(page); + } +got_it: + if (new_i_size && i_size_read(inode) < + ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) { + i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)); /* Only the directory inode sets new_i_size */ set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); } return page; - -put_err: - f2fs_put_dnode(&dn); - return ERR_PTR(err); } static int __allocate_data_block(struct dnode_of_data *dn) @@ -1141,15 +486,17 @@ alloc: allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, &sum, seg); - - /* direct IO doesn't use extent cache to maximize the performance */ set_data_blkaddr(dn); /* update i_size */ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + dn->ofs_in_node; - if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT)) - i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT)); + if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)) + i_size_write(dn->inode, + ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)); + + /* direct IO doesn't use extent cache to maximize the performance */ + f2fs_drop_largest_extent(dn->inode, fofs); return 0; } @@ -1179,6 +526,9 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, while (dn.ofs_in_node < end_offset && len) { block_t blkaddr; + if (unlikely(f2fs_cp_error(sbi))) + goto sync_out; + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) { if (__allocate_data_block(&dn)) @@ -1208,30 +558,36 @@ out: } /* - * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh. + * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with + * f2fs_map_blocks structure. * If original data blocks are allocated, then give them to blockdev. * Otherwise, * a. preallocate requested block addresses * b. do not use extent cache for better performance * c. give the block addresses to blockdev */ -static int __get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create, bool fiemap) +static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, + int create, int flag) { - unsigned int blkbits = inode->i_sb->s_blocksize_bits; - unsigned maxblocks = bh_result->b_size >> blkbits; + unsigned int maxblocks = map->m_len; struct dnode_of_data dn; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; pgoff_t pgofs, end_offset; int err = 0, ofs = 1; struct extent_info ei; bool allocated = false; - /* Get the page offset from the block offset(iblock) */ - pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits)); + map->m_len = 0; + map->m_flags = 0; + + /* it only supports block size == page size */ + pgofs = (pgoff_t)map->m_lblk; if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) { - f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result); + map->m_pblk = ei.blk + pgofs - ei.fofs; + map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs); + map->m_flags = F2FS_MAP_MAPPED; goto out; } @@ -1246,25 +602,40 @@ static int __get_data_block(struct inode *inode, sector_t iblock, err = 0; goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR && !fiemap) - goto put_out; - - if (dn.data_blkaddr != NULL_ADDR) { - clear_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, dn.data_blkaddr); - } else if (create) { - err = __allocate_data_block(&dn); - if (err) - goto put_out; - allocated = true; - set_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, dn.data_blkaddr); - } else { - goto put_out; + + if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) { + if (create) { + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto put_out; + } + err = __allocate_data_block(&dn); + if (err) + goto put_out; + allocated = true; + map->m_flags = F2FS_MAP_NEW; + } else { + if (flag != F2FS_GET_BLOCK_FIEMAP || + dn.data_blkaddr != NEW_ADDR) { + if (flag == F2FS_GET_BLOCK_BMAP) + err = -ENOENT; + goto put_out; + } + + /* + * preallocated unwritten block should be mapped + * for fiemap. + */ + if (dn.data_blkaddr == NEW_ADDR) + map->m_flags = F2FS_MAP_UNWRITTEN; + } } + map->m_flags |= F2FS_MAP_MAPPED; + map->m_pblk = dn.data_blkaddr; + map->m_len = 1; + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); - bh_result->b_size = (((size_t)1) << blkbits); dn.ofs_in_node++; pgofs++; @@ -1282,28 +653,45 @@ get_next: err = 0; goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR && !fiemap) - goto put_out; end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); } - if (maxblocks > (bh_result->b_size >> blkbits)) { + if (maxblocks > map->m_len) { block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); - if (blkaddr == NULL_ADDR && create) { - err = __allocate_data_block(&dn); - if (err) - goto sync_out; - allocated = true; - set_buffer_new(bh_result); - blkaddr = dn.data_blkaddr; + + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { + if (create) { + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto sync_out; + } + err = __allocate_data_block(&dn); + if (err) + goto sync_out; + allocated = true; + map->m_flags |= F2FS_MAP_NEW; + blkaddr = dn.data_blkaddr; + } else { + /* + * we only merge preallocated unwritten blocks + * for fiemap. + */ + if (flag != F2FS_GET_BLOCK_FIEMAP || + blkaddr != NEW_ADDR) + goto sync_out; + } } + /* Give more consecutive addresses for the readahead */ - if (blkaddr == (bh_result->b_blocknr + ofs)) { + if ((map->m_pblk != NEW_ADDR && + blkaddr == (map->m_pblk + ofs)) || + (map->m_pblk == NEW_ADDR && + blkaddr == NEW_ADDR)) { ofs++; dn.ofs_in_node++; pgofs++; - bh_result->b_size += (((size_t)1) << blkbits); + map->m_len++; goto get_next; } } @@ -1316,27 +704,311 @@ unlock_out: if (create) f2fs_unlock_op(F2FS_I_SB(inode)); out: - trace_f2fs_get_data_block(inode, iblock, bh_result, err); + trace_f2fs_map_blocks(inode, map, err); return err; } +static int __get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int create, int flag) +{ + struct f2fs_map_blocks map; + int ret; + + map.m_lblk = iblock; + map.m_len = bh->b_size >> inode->i_blkbits; + + ret = f2fs_map_blocks(inode, &map, create, flag); + if (!ret) { + map_bh(bh, inode->i_sb, map.m_pblk); + bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags; + bh->b_size = map.m_len << inode->i_blkbits; + } + return ret; +} + static int get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create, int flag) +{ + return __get_data_block(inode, iblock, bh_result, create, flag); +} + +static int get_data_block_dio(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { - return __get_data_block(inode, iblock, bh_result, create, false); + return __get_data_block(inode, iblock, bh_result, create, + F2FS_GET_BLOCK_DIO); } -static int get_data_block_fiemap(struct inode *inode, sector_t iblock, +static int get_data_block_bmap(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { - return __get_data_block(inode, iblock, bh_result, create, true); + return __get_data_block(inode, iblock, bh_result, create, + F2FS_GET_BLOCK_BMAP); +} + +static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) +{ + return (offset >> inode->i_blkbits); +} + +static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) +{ + return (blk << inode->i_blkbits); } int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { - return generic_block_fiemap(inode, fieinfo, - start, len, get_data_block_fiemap); + struct buffer_head map_bh; + sector_t start_blk, last_blk; + loff_t isize = i_size_read(inode); + u64 logical = 0, phys = 0, size = 0; + u32 flags = 0; + bool past_eof = false, whole_file = false; + int ret = 0; + + ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); + if (ret) + return ret; + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len); + if (ret != -EAGAIN) + return ret; + } + + mutex_lock(&inode->i_mutex); + + if (len >= isize) { + whole_file = true; + len = isize; + } + + if (logical_to_blk(inode, len) == 0) + len = blk_to_logical(inode, 1); + + start_blk = logical_to_blk(inode, start); + last_blk = logical_to_blk(inode, start + len - 1); +next: + memset(&map_bh, 0, sizeof(struct buffer_head)); + map_bh.b_size = len; + + ret = get_data_block(inode, start_blk, &map_bh, 0, + F2FS_GET_BLOCK_FIEMAP); + if (ret) + goto out; + + /* HOLE */ + if (!buffer_mapped(&map_bh)) { + start_blk++; + + if (!past_eof && blk_to_logical(inode, start_blk) >= isize) + past_eof = 1; + + if (past_eof && size) { + flags |= FIEMAP_EXTENT_LAST; + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + } else if (size) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + size = 0; + } + + /* if we have holes up to/past EOF then we're done */ + if (start_blk > last_blk || past_eof || ret) + goto out; + } else { + if (start_blk > last_blk && !whole_file) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + goto out; + } + + /* + * if size != 0 then we know we already have an extent + * to add, so add it. + */ + if (size) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + if (ret) + goto out; + } + + logical = blk_to_logical(inode, start_blk); + phys = blk_to_logical(inode, map_bh.b_blocknr); + size = map_bh.b_size; + flags = 0; + if (buffer_unwritten(&map_bh)) + flags = FIEMAP_EXTENT_UNWRITTEN; + + start_blk += logical_to_blk(inode, size); + + /* + * If we are past the EOF, then we need to make sure as + * soon as we find a hole that the last extent we found + * is marked with FIEMAP_EXTENT_LAST + */ + if (!past_eof && logical + size >= isize) + past_eof = true; + } + cond_resched(); + if (fatal_signal_pending(current)) + ret = -EINTR; + else + goto next; +out: + if (ret == 1) + ret = 0; + + mutex_unlock(&inode->i_mutex); + return ret; +} + +/* + * This function was originally taken from fs/mpage.c, and customized for f2fs. + * Major change was from block_size == page_size in f2fs by default. + */ +static int f2fs_mpage_readpages(struct address_space *mapping, + struct list_head *pages, struct page *page, + unsigned nr_pages) +{ + struct bio *bio = NULL; + unsigned page_idx; + sector_t last_block_in_bio = 0; + struct inode *inode = mapping->host; + const unsigned blkbits = inode->i_blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t block_nr; + struct block_device *bdev = inode->i_sb->s_bdev; + struct f2fs_map_blocks map; + + map.m_pblk = 0; + map.m_lblk = 0; + map.m_len = 0; + map.m_flags = 0; + + for (page_idx = 0; nr_pages; page_idx++, nr_pages--) { + + prefetchw(&page->flags); + if (pages) { + page = list_entry(pages->prev, struct page, lru); + list_del(&page->lru); + if (add_to_page_cache_lru(page, mapping, + page->index, GFP_KERNEL)) + goto next_page; + } + + block_in_file = (sector_t)page->index; + last_block = block_in_file + nr_pages; + last_block_in_file = (i_size_read(inode) + blocksize - 1) >> + blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + + /* + * Map blocks using the previous result first. + */ + if ((map.m_flags & F2FS_MAP_MAPPED) && + block_in_file > map.m_lblk && + block_in_file < (map.m_lblk + map.m_len)) + goto got_it; + + /* + * Then do more f2fs_map_blocks() calls until we are + * done with this page. + */ + map.m_flags = 0; + + if (block_in_file < last_block) { + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; + + if (f2fs_map_blocks(inode, &map, 0, + F2FS_GET_BLOCK_READ)) + goto set_error_page; + } +got_it: + if ((map.m_flags & F2FS_MAP_MAPPED)) { + block_nr = map.m_pblk + block_in_file - map.m_lblk; + SetPageMappedToDisk(page); + + if (!PageUptodate(page) && !cleancache_get_page(page)) { + SetPageUptodate(page); + goto confused; + } + } else { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + unlock_page(page); + goto next_page; + } + + /* + * This page will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (last_block_in_bio != block_nr - 1)) { +submit_and_realloc: + submit_bio(READ, bio); + bio = NULL; + } + if (bio == NULL) { + struct f2fs_crypto_ctx *ctx = NULL; + + if (f2fs_encrypted_inode(inode) && + S_ISREG(inode->i_mode)) { + + ctx = f2fs_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + goto set_error_page; + + /* wait the page to be moved by cleaning */ + f2fs_wait_on_encrypted_page_writeback( + F2FS_I_SB(inode), block_nr); + } + + bio = bio_alloc(GFP_KERNEL, + min_t(int, nr_pages, BIO_MAX_PAGES)); + if (!bio) { + if (ctx) + f2fs_release_crypto_ctx(ctx); + goto set_error_page; + } + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr); + bio->bi_end_io = f2fs_read_end_io; + bio->bi_private = ctx; + } + + if (bio_add_page(bio, page, blocksize, 0) < blocksize) + goto submit_and_realloc; + + last_block_in_bio = block_nr; + goto next_page; +set_error_page: + SetPageError(page); + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + unlock_page(page); + goto next_page; +confused: + if (bio) { + submit_bio(READ, bio); + bio = NULL; + } + unlock_page(page); +next_page: + if (pages) + page_cache_release(page); + } + BUG_ON(pages && !list_empty(pages)); + if (bio) + submit_bio(READ, bio); + return 0; } static int f2fs_read_data_page(struct file *file, struct page *page) @@ -1350,8 +1022,7 @@ static int f2fs_read_data_page(struct file *file, struct page *page) if (f2fs_has_inline_data(inode)) ret = f2fs_read_inline_data(inode, page); if (ret == -EAGAIN) - ret = mpage_readpage(page, get_data_block); - + ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1); return ret; } @@ -1360,16 +1031,20 @@ static int f2fs_read_data_pages(struct file *file, struct list_head *pages, unsigned nr_pages) { struct inode *inode = file->f_mapping->host; + struct page *page = list_entry(pages->prev, struct page, lru); + + trace_f2fs_readpages(inode, page, nr_pages); /* If the file has inline data, skip readpages */ if (f2fs_has_inline_data(inode)) return 0; - return mpage_readpages(mapping, pages, nr_pages, get_data_block); + return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages); } -int do_write_data_page(struct page *page, struct f2fs_io_info *fio) +int do_write_data_page(struct f2fs_io_info *fio) { + struct page *page = fio->page; struct inode *inode = page->mapping->host; struct dnode_of_data dn; int err = 0; @@ -1387,6 +1062,19 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio) goto out_writepage; } + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + + /* wait for GCed encrypted page writeback */ + f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode), + fio->blk_addr); + + fio->encrypted_page = f2fs_encrypt(inode, fio->page); + if (IS_ERR(fio->encrypted_page)) { + err = PTR_ERR(fio->encrypted_page); + goto out_writepage; + } + } + set_page_writeback(page); /* @@ -1396,11 +1084,11 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio) if (unlikely(fio->blk_addr != NEW_ADDR && !is_cold_data(page) && need_inplace_update(inode))) { - rewrite_data_page(page, fio); + rewrite_data_page(fio); set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE); trace_f2fs_do_write_data_page(page, IPU); } else { - write_data_page(page, &dn, fio); + write_data_page(&dn, fio); set_data_blkaddr(&dn); f2fs_update_extent_cache(&dn); trace_f2fs_do_write_data_page(page, OPU); @@ -1425,8 +1113,11 @@ static int f2fs_write_data_page(struct page *page, bool need_balance_fs = false; int err = 0; struct f2fs_io_info fio = { + .sbi = sbi, .type = DATA, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, + .page = page, + .encrypted_page = NULL, }; trace_f2fs_writepage(page, DATA); @@ -1456,7 +1147,7 @@ write: if (S_ISDIR(inode->i_mode)) { if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; - err = do_write_data_page(page, &fio); + err = do_write_data_page(&fio); goto done; } @@ -1476,7 +1167,7 @@ write: if (f2fs_has_inline_data(inode)) err = f2fs_write_inline_data(inode, page); if (err == -EAGAIN) - err = do_write_data_page(page, &fio); + err = do_write_data_page(&fio); f2fs_unlock_op(sbi); done: if (err && err != -ENOENT) @@ -1508,6 +1199,137 @@ static int __f2fs_writepage(struct page *page, struct writeback_control *wbc, return ret; } +/* + * This function was copied from write_cche_pages from mm/page-writeback.c. + * The major change is making write step of cold data page separately from + * warm/hot data page. + */ +static int f2fs_write_cache_pages(struct address_space *mapping, + struct writeback_control *wbc, writepage_t writepage, + void *data) +{ + int ret = 0; + int done = 0; + struct pagevec pvec; + int nr_pages; + pgoff_t uninitialized_var(writeback_index); + pgoff_t index; + pgoff_t end; /* Inclusive */ + pgoff_t done_index; + int cycled; + int range_whole = 0; + int tag; + int step = 0; + + pagevec_init(&pvec, 0); +next: + if (wbc->range_cyclic) { + writeback_index = mapping->writeback_index; /* prev offset */ + index = writeback_index; + if (index == 0) + cycled = 1; + else + cycled = 0; + end = -1; + } else { + index = wbc->range_start >> PAGE_CACHE_SHIFT; + end = wbc->range_end >> PAGE_CACHE_SHIFT; + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = 1; + cycled = 1; /* ignore range_cyclic tests */ + } + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + tag = PAGECACHE_TAG_TOWRITE; + else + tag = PAGECACHE_TAG_DIRTY; +retry: + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + tag_pages_for_writeback(mapping, index, end); + done_index = index; + while (!done && (index <= end)) { + int i; + + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + if (page->index > end) { + done = 1; + break; + } + + done_index = page->index; + + lock_page(page); + + if (unlikely(page->mapping != mapping)) { +continue_unlock: + unlock_page(page); + continue; + } + + if (!PageDirty(page)) { + /* someone wrote it for us */ + goto continue_unlock; + } + + if (step == is_cold_data(page)) + goto continue_unlock; + + if (PageWriteback(page)) { + if (wbc->sync_mode != WB_SYNC_NONE) + f2fs_wait_on_page_writeback(page, DATA); + else + goto continue_unlock; + } + + BUG_ON(PageWriteback(page)); + if (!clear_page_dirty_for_io(page)) + goto continue_unlock; + + ret = (*writepage)(page, wbc, data); + if (unlikely(ret)) { + if (ret == AOP_WRITEPAGE_ACTIVATE) { + unlock_page(page); + ret = 0; + } else { + done_index = page->index + 1; + done = 1; + break; + } + } + + if (--wbc->nr_to_write <= 0 && + wbc->sync_mode == WB_SYNC_NONE) { + done = 1; + break; + } + } + pagevec_release(&pvec); + cond_resched(); + } + + if (step < 1) { + step++; + goto next; + } + + if (!cycled && !done) { + cycled = 1; + index = 0; + end = writeback_index - 1; + goto retry; + } + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = done_index; + + return ret; +} + static int f2fs_write_data_pages(struct address_space *mapping, struct writeback_control *wbc) { @@ -1523,6 +1345,10 @@ static int f2fs_write_data_pages(struct address_space *mapping, if (!mapping->a_ops->writepage) return 0; + /* skip writing if there is no dirty page in this inode */ + if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE) + return 0; + if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && available_free_memory(sbi, DIRTY_DENTS)) @@ -1538,12 +1364,11 @@ static int f2fs_write_data_pages(struct address_space *mapping, mutex_lock(&sbi->writepages); locked = true; } - ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping); + ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping); + f2fs_submit_merged_bio(sbi, DATA, WRITE); if (locked) mutex_unlock(&sbi->writepages); - f2fs_submit_merged_bio(sbi, DATA, WRITE); - remove_dirty_dir_inode(inode); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); @@ -1570,7 +1395,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *page, *ipage; + struct page *page = NULL; + struct page *ipage; pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; struct dnode_of_data dn; int err = 0; @@ -1620,42 +1446,51 @@ repeat: if (err) goto put_fail; } - err = f2fs_reserve_block(&dn, index); + + err = f2fs_get_block(&dn, index); if (err) goto put_fail; put_next: f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); - if ((len == PAGE_CACHE_SIZE) || PageUptodate(page)) - return 0; - f2fs_wait_on_page_writeback(page, DATA); + /* wait for GCed encrypted page writeback */ + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + + if (len == PAGE_CACHE_SIZE) + goto out_update; + if (PageUptodate(page)) + goto out_clear; + if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { unsigned start = pos & (PAGE_CACHE_SIZE - 1); unsigned end = start + len; /* Reading beyond i_size is simple: memset to zero */ zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); - goto out; + goto out_update; } if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { struct f2fs_io_info fio = { + .sbi = sbi, .type = DATA, .rw = READ_SYNC, .blk_addr = dn.data_blkaddr, + .page = page, + .encrypted_page = NULL, }; - err = f2fs_submit_page_bio(sbi, page, &fio); + err = f2fs_submit_page_bio(&fio); if (err) goto fail; lock_page(page); if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); err = -EIO; goto fail; } @@ -1663,9 +1498,17 @@ put_next: f2fs_put_page(page, 1); goto repeat; } + + /* avoid symlink page */ + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + err = f2fs_decrypt_one(inode, page); + if (err) + goto fail; + } } -out: +out_update: SetPageUptodate(page); +out_clear: clear_cold_data(page); return 0; @@ -1673,8 +1516,8 @@ put_fail: f2fs_put_dnode(&dn); unlock_fail: f2fs_unlock_op(sbi); - f2fs_put_page(page, 1); fail: + f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); return err; } @@ -1705,9 +1548,6 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter, { unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; - if (iov_iter_rw(iter) == READ) - return 0; - if (offset & blocksize_mask) return -EINVAL; @@ -1733,15 +1573,25 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return err; } - if (check_direct_IO(inode, iter, offset)) + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) return 0; + err = check_direct_IO(inode, iter, offset); + if (err) + return err; + trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - if (iov_iter_rw(iter) == WRITE) + if (iov_iter_rw(iter) == WRITE) { __allocate_data_blocks(inode, offset, count); + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + err = -EIO; + goto out; + } + } - err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block); + err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); +out: if (err < 0 && iov_iter_rw(iter) == WRITE) f2fs_write_failed(mapping, offset + count); @@ -1768,6 +1618,11 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, else inode_dec_dirty_pages(inode); } + + /* This is atomic written page, keep Private */ + if (IS_ATOMIC_WRITTEN_PAGE(page)) + return; + ClearPagePrivate(page); } @@ -1777,6 +1632,10 @@ int f2fs_release_page(struct page *page, gfp_t wait) if (PageDirty(page)) return 0; + /* This is atomic written page, keep Private */ + if (IS_ATOMIC_WRITTEN_PAGE(page)) + return 0; + ClearPagePrivate(page); return 1; } @@ -1791,12 +1650,17 @@ static int f2fs_set_data_page_dirty(struct page *page) SetPageUptodate(page); if (f2fs_is_atomic_file(inode)) { - register_inmem_page(inode, page); - return 1; + if (!IS_ATOMIC_WRITTEN_PAGE(page)) { + register_inmem_page(inode, page); + return 1; + } + /* + * Previously, this page has been registered, we just + * return here. + */ + return 0; } - mark_inode_dirty(inode); - if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); update_dirty_page(inode, page); @@ -1809,44 +1673,14 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; - /* we don't need to use inline_data strictly */ - if (f2fs_has_inline_data(inode)) { - int err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } - return generic_block_bmap(mapping, block, get_data_block); -} - -void init_extent_cache_info(struct f2fs_sb_info *sbi) -{ - INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO); - init_rwsem(&sbi->extent_tree_lock); - INIT_LIST_HEAD(&sbi->extent_list); - spin_lock_init(&sbi->extent_lock); - sbi->total_ext_tree = 0; - atomic_set(&sbi->total_ext_node, 0); -} + if (f2fs_has_inline_data(inode)) + return 0; -int __init create_extent_cache(void) -{ - extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", - sizeof(struct extent_tree)); - if (!extent_tree_slab) - return -ENOMEM; - extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node", - sizeof(struct extent_node)); - if (!extent_node_slab) { - kmem_cache_destroy(extent_tree_slab); - return -ENOMEM; - } - return 0; -} + /* make sure allocating whole blocks */ + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + filemap_write_and_wait(mapping); -void destroy_extent_cache(void) -{ - kmem_cache_destroy(extent_node_slab); - kmem_cache_destroy(extent_tree_slab); + return generic_block_bmap(mapping, block, get_data_block_bmap); } const struct address_space_operations f2fs_dblock_aops = { diff --git a/kernel/fs/f2fs/debug.c b/kernel/fs/f2fs/debug.c index f5388f372..478e5d541 100644 --- a/kernel/fs/f2fs/debug.c +++ b/kernel/fs/f2fs/debug.c @@ -33,8 +33,11 @@ static void update_general_status(struct f2fs_sb_info *sbi) int i; /* validation check of the segment numbers */ - si->hit_ext = sbi->read_hit_ext; - si->total_ext = sbi->total_hit_ext; + si->hit_largest = atomic64_read(&sbi->read_hit_largest); + si->hit_cached = atomic64_read(&sbi->read_hit_cached); + si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree); + si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree; + si->total_ext = atomic64_read(&sbi->total_hit_ext); si->ext_tree = sbi->total_ext_tree; si->ext_node = atomic_read(&sbi->total_ext_node); si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); @@ -49,6 +52,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->valid_count = valid_user_blocks(sbi); si->valid_node_count = valid_node_count(sbi); si->valid_inode_count = valid_inode_count(sbi); + si->inline_xattr = atomic_read(&sbi->inline_xattr); si->inline_inode = atomic_read(&sbi->inline_inode); si->inline_dir = atomic_read(&sbi->inline_dir); si->utilization = utilization(sbi); @@ -94,7 +98,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) static void update_sit_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); - unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist; + unsigned long long blks_per_sec, hblks_per_sec, total_vblocks; + unsigned long long bimodal, dist; unsigned int segno, vblocks; int ndirty = 0; @@ -112,10 +117,10 @@ static void update_sit_info(struct f2fs_sb_info *sbi) ndirty++; } } - dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100; - si->bimodal = bimodal / dist; + dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100); + si->bimodal = div64_u64(bimodal, dist); if (si->dirty_count) - si->avg_vblocks = total_vblocks / ndirty; + si->avg_vblocks = div_u64(total_vblocks, ndirty); else si->avg_vblocks = 0; } @@ -143,7 +148,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += sizeof(struct sit_info); si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); - si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += 3 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (sbi->segs_per_sec > 1) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); @@ -193,9 +198,9 @@ get_cache: si->page_mem = 0; npages = NODE_MAPPING(sbi)->nrpages; - si->page_mem += npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; npages = META_MAPPING(sbi)->nrpages; - si->page_mem += npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; } static int stat_show(struct seq_file *s, void *v) @@ -225,6 +230,8 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "Other: %u)\n - Data: %u\n", si->valid_node_count - si->valid_inode_count, si->valid_count - si->valid_node_count); + seq_printf(s, " - Inline_xattr Inode: %u\n", + si->inline_xattr); seq_printf(s, " - Inline_data Inode: %u\n", si->inline_inode); seq_printf(s, " - Inline_dentry Inode: %u\n", @@ -275,10 +282,16 @@ static int stat_show(struct seq_file *s, void *v) si->bg_data_blks); seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, si->bg_node_blks); - seq_printf(s, "\nExtent Hit Ratio: %d / %d\n", - si->hit_ext, si->total_ext); - seq_printf(s, "\nExtent Tree Count: %d\n", si->ext_tree); - seq_printf(s, "\nExtent Node Count: %d\n", si->ext_node); + seq_puts(s, "\nExtent Cache:\n"); + seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", + si->hit_largest, si->hit_cached, + si->hit_rbtree); + seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n", + !si->total_ext ? 0 : + div64_u64(si->hit_total * 100, si->total_ext), + si->hit_total, si->total_ext); + seq_printf(s, " - Inner Struct Count: tree: %d, node: %d\n", + si->ext_tree, si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); seq_printf(s, " - inmem: %4d, wb: %4d\n", si->inmem_pages, si->wb_pages); @@ -320,13 +333,13 @@ static int stat_show(struct seq_file *s, void *v) /* memory footprint */ update_mem_info(si->sbi); - seq_printf(s, "\nMemory: %u KB\n", + seq_printf(s, "\nMemory: %llu KB\n", (si->base_mem + si->cache_mem + si->page_mem) >> 10); - seq_printf(s, " - static: %u KB\n", + seq_printf(s, " - static: %llu KB\n", si->base_mem >> 10); - seq_printf(s, " - cached: %u KB\n", + seq_printf(s, " - cached: %llu KB\n", si->cache_mem >> 10); - seq_printf(s, " - paged : %u KB\n", + seq_printf(s, " - paged : %llu KB\n", si->page_mem >> 10); } mutex_unlock(&f2fs_stat_mutex); @@ -365,6 +378,12 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) si->sbi = sbi; sbi->stat_info = si; + atomic64_set(&sbi->total_hit_ext, 0); + atomic64_set(&sbi->read_hit_rbtree, 0); + atomic64_set(&sbi->read_hit_largest, 0); + atomic64_set(&sbi->read_hit_cached, 0); + + atomic_set(&sbi->inline_xattr, 0); atomic_set(&sbi->inline_inode, 0); atomic_set(&sbi->inline_dir, 0); atomic_set(&sbi->inplace_count, 0); diff --git a/kernel/fs/f2fs/dir.c b/kernel/fs/f2fs/dir.c index 3a3302ab7..7c1678ba8 100644 --- a/kernel/fs/f2fs/dir.c +++ b/kernel/fs/f2fs/dir.c @@ -76,20 +76,10 @@ static unsigned long dir_block_index(unsigned int level, return bidx; } -static bool early_match_name(size_t namelen, f2fs_hash_t namehash, - struct f2fs_dir_entry *de) -{ - if (le16_to_cpu(de->name_len) != namelen) - return false; - - if (de->hash_code != namehash) - return false; - - return true; -} - static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, - struct qstr *name, int *max_slots, + struct f2fs_filename *fname, + f2fs_hash_t namehash, + int *max_slots, struct page **res_page) { struct f2fs_dentry_block *dentry_blk; @@ -98,9 +88,8 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page); - make_dentry_ptr(&d, (void *)dentry_blk, 1); - de = find_target_dentry(name, max_slots, &d); - + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); + de = find_target_dentry(fname, namehash, max_slots, &d); if (de) *res_page = dentry_page; else @@ -114,13 +103,15 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, return de; } -struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, - struct f2fs_dentry_ptr *d) +struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname, + f2fs_hash_t namehash, int *max_slots, + struct f2fs_dentry_ptr *d) { struct f2fs_dir_entry *de; unsigned long bit_pos = 0; - f2fs_hash_t namehash = f2fs_dentry_hash(name); int max_len = 0; + struct f2fs_str de_name = FSTR_INIT(NULL, 0); + struct f2fs_str *name = &fname->disk_name; if (max_slots) *max_slots = 0; @@ -132,8 +123,18 @@ struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, } de = &d->dentry[bit_pos]; - if (early_match_name(name->len, namehash, de) && - !memcmp(d->filename[bit_pos], name->name, name->len)) + + /* encrypted case */ + de_name.name = d->filename[bit_pos]; + de_name.len = le16_to_cpu(de->name_len); + + /* show encrypted name */ + if (fname->hash) { + if (de->hash_code == fname->hash) + goto found; + } else if (de_name.len == name->len && + de->hash_code == namehash && + !memcmp(de_name.name, name->name, name->len)) goto found; if (max_slots && max_len > *max_slots) @@ -155,16 +156,21 @@ found: } static struct f2fs_dir_entry *find_in_level(struct inode *dir, - unsigned int level, struct qstr *name, - f2fs_hash_t namehash, struct page **res_page) + unsigned int level, + struct f2fs_filename *fname, + struct page **res_page) { - int s = GET_DENTRY_SLOTS(name->len); + struct qstr name = FSTR_TO_QSTR(&fname->disk_name); + int s = GET_DENTRY_SLOTS(name.len); unsigned int nbucket, nblock; unsigned int bidx, end_block; struct page *dentry_page; struct f2fs_dir_entry *de = NULL; bool room = false; int max_slots; + f2fs_hash_t namehash; + + namehash = f2fs_dentry_hash(&name); f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); @@ -177,13 +183,14 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, for (; bidx < end_block; bidx++) { /* no need to allocate new dentry pages to all the indices */ - dentry_page = find_data_page(dir, bidx, true); + dentry_page = find_data_page(dir, bidx); if (IS_ERR(dentry_page)) { room = true; continue; } - de = find_in_block(dentry_page, name, &max_slots, res_page); + de = find_in_block(dentry_page, fname, namehash, &max_slots, + res_page); if (de) break; @@ -211,30 +218,34 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, { unsigned long npages = dir_blocks(dir); struct f2fs_dir_entry *de = NULL; - f2fs_hash_t name_hash; unsigned int max_depth; unsigned int level; + struct f2fs_filename fname; + int err; *res_page = NULL; - if (f2fs_has_inline_dentry(dir)) - return find_in_inline_dir(dir, child, res_page); + err = f2fs_fname_setup_filename(dir, child, 1, &fname); + if (err) + return NULL; + + if (f2fs_has_inline_dentry(dir)) { + de = find_in_inline_dir(dir, &fname, res_page); + goto out; + } if (npages == 0) - return NULL; + goto out; - name_hash = f2fs_dentry_hash(child); max_depth = F2FS_I(dir)->i_current_depth; for (level = 0; level < max_depth; level++) { - de = find_in_level(dir, level, child, name_hash, res_page); + de = find_in_level(dir, level, &fname, res_page); if (de) break; } - if (!de && F2FS_I(dir)->chash != name_hash) { - F2FS_I(dir)->chash = name_hash; - F2FS_I(dir)->clevel = level - 1; - } +out: + f2fs_fname_free_filename(&fname); return de; } @@ -247,7 +258,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p) if (f2fs_has_inline_dentry(dir)) return f2fs_parent_inline_dir(dir, p); - page = get_lock_data_page(dir, 0); + page = get_lock_data_page(dir, 0, false); if (IS_ERR(page)) return NULL; @@ -303,10 +314,14 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) set_page_dirty(ipage); } -int update_dent_inode(struct inode *inode, const struct qstr *name) +int update_dent_inode(struct inode *inode, struct inode *to, + const struct qstr *name) { struct page *page; + if (file_enc_name(to)) + return 0; + page = get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(page)) return PTR_ERR(page); @@ -356,7 +371,7 @@ static int make_empty_dir(struct inode *inode, dentry_blk = kmap_atomic(dentry_page); - make_dentry_ptr(&d, (void *)dentry_blk, 1); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); do_make_empty_dir(inode, parent, &d); kunmap_atomic(dentry_blk); @@ -390,6 +405,12 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, err = f2fs_init_security(inode, dir, name, page); if (err) goto put_error; + + if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) { + err = f2fs_inherit_context(dir, inode, page); + if (err) + goto put_error; + } } else { page = get_node_page(F2FS_I_SB(dir), inode->i_ino); if (IS_ERR(page)) @@ -501,24 +522,33 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, unsigned long bidx, block; f2fs_hash_t dentry_hash; unsigned int nbucket, nblock; - size_t namelen = name->len; struct page *dentry_page = NULL; struct f2fs_dentry_block *dentry_blk = NULL; struct f2fs_dentry_ptr d; - int slots = GET_DENTRY_SLOTS(namelen); struct page *page = NULL; - int err = 0; + struct f2fs_filename fname; + struct qstr new_name; + int slots, err; + + err = f2fs_fname_setup_filename(dir, name, 0, &fname); + if (err) + return err; + + new_name.name = fname_name(&fname); + new_name.len = fname_len(&fname); if (f2fs_has_inline_dentry(dir)) { - err = f2fs_add_inline_entry(dir, name, inode, ino, mode); + err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode); if (!err || err != -EAGAIN) - return err; + goto out; else err = 0; } - dentry_hash = f2fs_dentry_hash(name); level = 0; + slots = GET_DENTRY_SLOTS(new_name.len); + dentry_hash = f2fs_dentry_hash(&new_name); + current_depth = F2FS_I(dir)->i_current_depth; if (F2FS_I(dir)->chash == dentry_hash) { level = F2FS_I(dir)->clevel; @@ -526,8 +556,10 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, } start: - if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) - return -ENOSPC; + if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) { + err = -ENOSPC; + goto out; + } /* Increase the depth, if required */ if (level == current_depth) @@ -541,8 +573,10 @@ start: for (block = bidx; block <= (bidx + nblock - 1); block++) { dentry_page = get_new_data_page(dir, NULL, block, true); - if (IS_ERR(dentry_page)) - return PTR_ERR(dentry_page); + if (IS_ERR(dentry_page)) { + err = PTR_ERR(dentry_page); + goto out; + } dentry_blk = kmap(dentry_page); bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, @@ -562,15 +596,17 @@ add_dentry: if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, name, NULL); + page = init_inode_metadata(inode, dir, &new_name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; } + if (f2fs_encrypted_inode(dir)) + file_set_enc_name(inode); } - make_dentry_ptr(&d, (void *)dentry_blk, 1); - f2fs_update_dentry(ino, mode, &d, name, dentry_hash, bit_pos); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); + f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos); set_page_dirty(dentry_page); @@ -592,6 +628,8 @@ fail: } kunmap(dentry_page); f2fs_put_page(dentry_page, 1); +out: + f2fs_fname_free_filename(&fname); return err; } @@ -680,8 +718,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, if (inode) f2fs_drop_nlink(dir, inode, NULL); - if (bit_pos == NR_DENTRY_IN_BLOCK) { - truncate_hole(dir, page->index, page->index + 1); + if (bit_pos == NR_DENTRY_IN_BLOCK && + !truncate_hole(dir, page->index, page->index + 1)) { clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); @@ -702,7 +740,7 @@ bool f2fs_empty_dir(struct inode *dir) return f2fs_empty_inline_dir(dir); for (bidx = 0; bidx < nblock; bidx++) { - dentry_page = get_lock_data_page(dir, bidx); + dentry_page = get_lock_data_page(dir, bidx, false); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) continue; @@ -729,11 +767,12 @@ bool f2fs_empty_dir(struct inode *dir) } bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, - unsigned int start_pos) + unsigned int start_pos, struct f2fs_str *fstr) { unsigned char d_type = DT_UNKNOWN; unsigned int bit_pos; struct f2fs_dir_entry *de = NULL; + struct f2fs_str de_name = FSTR_INIT(NULL, 0); bit_pos = ((unsigned long)ctx->pos % d->max); @@ -747,8 +786,31 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, d_type = f2fs_filetype_table[de->file_type]; else d_type = DT_UNKNOWN; - if (!dir_emit(ctx, d->filename[bit_pos], - le16_to_cpu(de->name_len), + + de_name.name = d->filename[bit_pos]; + de_name.len = le16_to_cpu(de->name_len); + + if (f2fs_encrypted_inode(d->inode)) { + int save_len = fstr->len; + int ret; + + de_name.name = kmalloc(de_name.len, GFP_NOFS); + if (!de_name.name) + return false; + + memcpy(de_name.name, d->filename[bit_pos], de_name.len); + + ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code, + &de_name, fstr); + kfree(de_name.name); + if (ret < 0) + return true; + + de_name = *fstr; + fstr->len = save_len; + } + + if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->ino), d_type)) return true; @@ -767,9 +829,24 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) struct file_ra_state *ra = &file->f_ra; unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); struct f2fs_dentry_ptr d; + struct f2fs_str fstr = FSTR_INIT(NULL, 0); + int err = 0; - if (f2fs_has_inline_dentry(inode)) - return f2fs_read_inline_dir(file, ctx); + if (f2fs_encrypted_inode(inode)) { + err = f2fs_get_encryption_info(inode); + if (err) + return err; + + err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN, + &fstr); + if (err < 0) + return err; + } + + if (f2fs_has_inline_dentry(inode)) { + err = f2fs_read_inline_dir(file, ctx, &fstr); + goto out; + } /* readahead for multi pages of dir */ if (npages - n > 1 && !ra_has_index(ra, n)) @@ -777,15 +854,15 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); for (; n < npages; n++) { - dentry_page = get_lock_data_page(inode, n); + dentry_page = get_lock_data_page(inode, n, false); if (IS_ERR(dentry_page)) continue; dentry_blk = kmap(dentry_page); - make_dentry_ptr(&d, (void *)dentry_blk, 1); + make_dentry_ptr(inode, &d, (void *)dentry_blk, 1); - if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK)) + if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) goto stop; ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; @@ -798,8 +875,9 @@ stop: kunmap(dentry_page); f2fs_put_page(dentry_page, 1); } - - return 0; +out: + f2fs_fname_crypto_free_buffer(&fstr); + return err; } const struct file_operations f2fs_dir_operations = { @@ -808,4 +886,7 @@ const struct file_operations f2fs_dir_operations = { .iterate = f2fs_readdir, .fsync = f2fs_sync_file, .unlocked_ioctl = f2fs_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = f2fs_compat_ioctl, +#endif }; diff --git a/kernel/fs/f2fs/extent_cache.c b/kernel/fs/f2fs/extent_cache.c new file mode 100644 index 000000000..7ddba812e --- /dev/null +++ b/kernel/fs/f2fs/extent_cache.c @@ -0,0 +1,748 @@ +/* + * f2fs extent cache support + * + * Copyright (c) 2015 Motorola Mobility + * Copyright (c) 2015 Samsung Electronics + * Authors: Jaegeuk Kim <jaegeuk@kernel.org> + * Chao Yu <chao2.yu@samsung.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 as + * published by the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" +#include "node.h" +#include <trace/events/f2fs.h> + +static struct kmem_cache *extent_tree_slab; +static struct kmem_cache *extent_node_slab; + +static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct rb_node *parent, struct rb_node **p) +{ + struct extent_node *en; + + en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC); + if (!en) + return NULL; + + en->ei = *ei; + INIT_LIST_HEAD(&en->list); + + rb_link_node(&en->rb_node, parent, p); + rb_insert_color(&en->rb_node, &et->root); + et->count++; + atomic_inc(&sbi->total_ext_node); + return en; +} + +static void __detach_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + rb_erase(&en->rb_node, &et->root); + et->count--; + atomic_dec(&sbi->total_ext_node); + + if (et->cached_en == en) + et->cached_en = NULL; +} + +static struct extent_tree *__grab_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + nid_t ino = inode->i_ino; + + down_write(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, ino); + if (!et) { + et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS); + f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et); + memset(et, 0, sizeof(struct extent_tree)); + et->ino = ino; + et->root = RB_ROOT; + et->cached_en = NULL; + rwlock_init(&et->lock); + atomic_set(&et->refcount, 0); + et->count = 0; + sbi->total_ext_tree++; + } + atomic_inc(&et->refcount); + up_write(&sbi->extent_tree_lock); + + /* never died until evict_inode */ + F2FS_I(inode)->extent_tree = et; + + return et; +} + +static struct extent_node *__lookup_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, unsigned int fofs) +{ + struct rb_node *node = et->root.rb_node; + struct extent_node *en = et->cached_en; + + if (en) { + struct extent_info *cei = &en->ei; + + if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) { + stat_inc_cached_node_hit(sbi); + return en; + } + } + + while (node) { + en = rb_entry(node, struct extent_node, rb_node); + + if (fofs < en->ei.fofs) { + node = node->rb_left; + } else if (fofs >= en->ei.fofs + en->ei.len) { + node = node->rb_right; + } else { + stat_inc_rbtree_node_hit(sbi); + return en; + } + } + return NULL; +} + +static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei) +{ + struct rb_node **p = &et->root.rb_node; + struct extent_node *en; + + en = __attach_extent_node(sbi, et, ei, NULL, p); + if (!en) + return NULL; + + et->largest = en->ei; + et->cached_en = en; + return en; +} + +static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, bool free_all) +{ + struct rb_node *node, *next; + struct extent_node *en; + unsigned int count = et->count; + + node = rb_first(&et->root); + while (node) { + next = rb_next(node); + en = rb_entry(node, struct extent_node, rb_node); + + if (free_all) { + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) + list_del_init(&en->list); + spin_unlock(&sbi->extent_lock); + } + + if (free_all || list_empty(&en->list)) { + __detach_extent_node(sbi, et, en); + kmem_cache_free(extent_node_slab, en); + } + node = next; + } + + return count - et->count; +} + +static void __drop_largest_extent(struct inode *inode, + pgoff_t fofs, unsigned int len) +{ + struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest; + + if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) + largest->len = 0; +} + +void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs) +{ + if (!f2fs_may_extent_tree(inode)) + return; + + __drop_largest_extent(inode, fofs, 1); +} + +void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en; + struct extent_info ei; + + if (!f2fs_may_extent_tree(inode)) + return; + + et = __grab_extent_tree(inode); + + if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN) + return; + + set_extent_info(&ei, le32_to_cpu(i_ext->fofs), + le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len)); + + write_lock(&et->lock); + if (et->count) + goto out; + + en = __init_extent_tree(sbi, et, &ei); + if (en) { + spin_lock(&sbi->extent_lock); + list_add_tail(&en->list, &sbi->extent_list); + spin_unlock(&sbi->extent_lock); + } +out: + write_unlock(&et->lock); +} + +static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree; + struct extent_node *en; + bool ret = false; + + f2fs_bug_on(sbi, !et); + + trace_f2fs_lookup_extent_tree_start(inode, pgofs); + + read_lock(&et->lock); + + if (et->largest.fofs <= pgofs && + et->largest.fofs + et->largest.len > pgofs) { + *ei = et->largest; + ret = true; + stat_inc_largest_node_hit(sbi); + goto out; + } + + en = __lookup_extent_tree(sbi, et, pgofs); + if (en) { + *ei = en->ei; + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) + list_move_tail(&en->list, &sbi->extent_list); + et->cached_en = en; + spin_unlock(&sbi->extent_lock); + ret = true; + } +out: + stat_inc_total_hit(sbi); + read_unlock(&et->lock); + + trace_f2fs_lookup_extent_tree_end(inode, pgofs, ei); + return ret; +} + + +/* + * lookup extent at @fofs, if hit, return the extent + * if not, return NULL and + * @prev_ex: extent before fofs + * @next_ex: extent after fofs + * @insert_p: insert point for new extent at fofs + * in order to simpfy the insertion after. + * tree must stay unchanged between lookup and insertion. + */ +static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et, + unsigned int fofs, + struct extent_node **prev_ex, + struct extent_node **next_ex, + struct rb_node ***insert_p, + struct rb_node **insert_parent) +{ + struct rb_node **pnode = &et->root.rb_node; + struct rb_node *parent = NULL, *tmp_node; + struct extent_node *en = et->cached_en; + + *insert_p = NULL; + *insert_parent = NULL; + *prev_ex = NULL; + *next_ex = NULL; + + if (RB_EMPTY_ROOT(&et->root)) + return NULL; + + if (en) { + struct extent_info *cei = &en->ei; + + if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) + goto lookup_neighbors; + } + + while (*pnode) { + parent = *pnode; + en = rb_entry(*pnode, struct extent_node, rb_node); + + if (fofs < en->ei.fofs) + pnode = &(*pnode)->rb_left; + else if (fofs >= en->ei.fofs + en->ei.len) + pnode = &(*pnode)->rb_right; + else + goto lookup_neighbors; + } + + *insert_p = pnode; + *insert_parent = parent; + + en = rb_entry(parent, struct extent_node, rb_node); + tmp_node = parent; + if (parent && fofs > en->ei.fofs) + tmp_node = rb_next(parent); + *next_ex = tmp_node ? + rb_entry(tmp_node, struct extent_node, rb_node) : NULL; + + tmp_node = parent; + if (parent && fofs < en->ei.fofs) + tmp_node = rb_prev(parent); + *prev_ex = tmp_node ? + rb_entry(tmp_node, struct extent_node, rb_node) : NULL; + return NULL; + +lookup_neighbors: + if (fofs == en->ei.fofs) { + /* lookup prev node for merging backward later */ + tmp_node = rb_prev(&en->rb_node); + *prev_ex = tmp_node ? + rb_entry(tmp_node, struct extent_node, rb_node) : NULL; + } + if (fofs == en->ei.fofs + en->ei.len - 1) { + /* lookup next node for merging frontward later */ + tmp_node = rb_next(&en->rb_node); + *next_ex = tmp_node ? + rb_entry(tmp_node, struct extent_node, rb_node) : NULL; + } + return en; +} + +static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct extent_node **den, + struct extent_node *prev_ex, + struct extent_node *next_ex) +{ + struct extent_node *en = NULL; + + if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) { + prev_ex->ei.len += ei->len; + ei = &prev_ex->ei; + en = prev_ex; + } + + if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) { + if (en) { + __detach_extent_node(sbi, et, prev_ex); + *den = prev_ex; + } + next_ex->ei.fofs = ei->fofs; + next_ex->ei.blk = ei->blk; + next_ex->ei.len += ei->len; + en = next_ex; + } + + if (en) { + __try_update_largest_extent(et, en); + et->cached_en = en; + } + return en; +} + +static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct rb_node **insert_p, + struct rb_node *insert_parent) +{ + struct rb_node **p = &et->root.rb_node; + struct rb_node *parent = NULL; + struct extent_node *en = NULL; + + if (insert_p && insert_parent) { + parent = insert_parent; + p = insert_p; + goto do_insert; + } + + while (*p) { + parent = *p; + en = rb_entry(parent, struct extent_node, rb_node); + + if (ei->fofs < en->ei.fofs) + p = &(*p)->rb_left; + else if (ei->fofs >= en->ei.fofs + en->ei.len) + p = &(*p)->rb_right; + else + f2fs_bug_on(sbi, 1); + } +do_insert: + en = __attach_extent_node(sbi, et, ei, parent, p); + if (!en) + return NULL; + + __try_update_largest_extent(et, en); + et->cached_en = en; + return en; +} + +static unsigned int f2fs_update_extent_tree_range(struct inode *inode, + pgoff_t fofs, block_t blkaddr, unsigned int len) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree; + struct extent_node *en = NULL, *en1 = NULL; + struct extent_node *prev_en = NULL, *next_en = NULL; + struct extent_info ei, dei, prev; + struct rb_node **insert_p = NULL, *insert_parent = NULL; + unsigned int end = fofs + len; + unsigned int pos = (unsigned int)fofs; + + if (!et) + return false; + + trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len); + + write_lock(&et->lock); + + if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) { + write_unlock(&et->lock); + return false; + } + + prev = et->largest; + dei.len = 0; + + /* + * drop largest extent before lookup, in case it's already + * been shrunk from extent tree + */ + __drop_largest_extent(inode, fofs, len); + + /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ + en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en, + &insert_p, &insert_parent); + if (!en) + en = next_en; + + /* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */ + while (en && en->ei.fofs < end) { + unsigned int org_end; + int parts = 0; /* # of parts current extent split into */ + + next_en = en1 = NULL; + + dei = en->ei; + org_end = dei.fofs + dei.len; + f2fs_bug_on(sbi, pos >= org_end); + + if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) { + en->ei.len = pos - en->ei.fofs; + prev_en = en; + parts = 1; + } + + if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) { + if (parts) { + set_extent_info(&ei, end, + end - dei.fofs + dei.blk, + org_end - end); + en1 = __insert_extent_tree(sbi, et, &ei, + NULL, NULL); + next_en = en1; + } else { + en->ei.fofs = end; + en->ei.blk += end - dei.fofs; + en->ei.len -= end - dei.fofs; + next_en = en; + } + parts++; + } + + if (!next_en) { + struct rb_node *node = rb_next(&en->rb_node); + + next_en = node ? + rb_entry(node, struct extent_node, rb_node) + : NULL; + } + + if (parts) + __try_update_largest_extent(et, en); + else + __detach_extent_node(sbi, et, en); + + /* + * if original extent is split into zero or two parts, extent + * tree has been altered by deletion or insertion, therefore + * invalidate pointers regard to tree. + */ + if (parts != 1) { + insert_p = NULL; + insert_parent = NULL; + } + + /* update in global extent list */ + spin_lock(&sbi->extent_lock); + if (!parts && !list_empty(&en->list)) + list_del(&en->list); + if (en1) + list_add_tail(&en1->list, &sbi->extent_list); + spin_unlock(&sbi->extent_lock); + + /* release extent node */ + if (!parts) + kmem_cache_free(extent_node_slab, en); + + en = next_en; + } + + /* 3. update extent in extent cache */ + if (blkaddr) { + struct extent_node *den = NULL; + + set_extent_info(&ei, fofs, blkaddr, len); + en1 = __try_merge_extent_node(sbi, et, &ei, &den, + prev_en, next_en); + if (!en1) + en1 = __insert_extent_tree(sbi, et, &ei, + insert_p, insert_parent); + + /* give up extent_cache, if split and small updates happen */ + if (dei.len >= 1 && + prev.len < F2FS_MIN_EXTENT_LEN && + et->largest.len < F2FS_MIN_EXTENT_LEN) { + et->largest.len = 0; + set_inode_flag(F2FS_I(inode), FI_NO_EXTENT); + } + + spin_lock(&sbi->extent_lock); + if (en1) { + if (list_empty(&en1->list)) + list_add_tail(&en1->list, &sbi->extent_list); + else + list_move_tail(&en1->list, &sbi->extent_list); + } + if (den && !list_empty(&den->list)) + list_del(&den->list); + spin_unlock(&sbi->extent_lock); + + if (den) + kmem_cache_free(extent_node_slab, den); + } + + if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) + __free_extent_tree(sbi, et, true); + + write_unlock(&et->lock); + + return !__is_extent_same(&prev, &et->largest); +} + +unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct extent_tree *treevec[EXT_TREE_VEC_SIZE]; + struct extent_node *en, *tmp; + unsigned long ino = F2FS_ROOT_INO(sbi); + struct radix_tree_root *root = &sbi->extent_tree_root; + unsigned int found; + unsigned int node_cnt = 0, tree_cnt = 0; + int remained; + + if (!test_opt(sbi, EXTENT_CACHE)) + return 0; + + if (!down_write_trylock(&sbi->extent_tree_lock)) + goto out; + + /* 1. remove unreferenced extent tree */ + while ((found = radix_tree_gang_lookup(root, + (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { + unsigned i; + + ino = treevec[found - 1]->ino + 1; + for (i = 0; i < found; i++) { + struct extent_tree *et = treevec[i]; + + if (!atomic_read(&et->refcount)) { + write_lock(&et->lock); + node_cnt += __free_extent_tree(sbi, et, true); + write_unlock(&et->lock); + + radix_tree_delete(root, et->ino); + kmem_cache_free(extent_tree_slab, et); + sbi->total_ext_tree--; + tree_cnt++; + + if (node_cnt + tree_cnt >= nr_shrink) + goto unlock_out; + } + } + } + up_write(&sbi->extent_tree_lock); + + /* 2. remove LRU extent entries */ + if (!down_write_trylock(&sbi->extent_tree_lock)) + goto out; + + remained = nr_shrink - (node_cnt + tree_cnt); + + spin_lock(&sbi->extent_lock); + list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) { + if (!remained--) + break; + list_del_init(&en->list); + } + spin_unlock(&sbi->extent_lock); + + /* + * reset ino for searching victims from beginning of global extent tree. + */ + ino = F2FS_ROOT_INO(sbi); + + while ((found = radix_tree_gang_lookup(root, + (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { + unsigned i; + + ino = treevec[found - 1]->ino + 1; + for (i = 0; i < found; i++) { + struct extent_tree *et = treevec[i]; + + write_lock(&et->lock); + node_cnt += __free_extent_tree(sbi, et, false); + write_unlock(&et->lock); + + if (node_cnt + tree_cnt >= nr_shrink) + goto unlock_out; + } + } +unlock_out: + up_write(&sbi->extent_tree_lock); +out: + trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt); + + return node_cnt + tree_cnt; +} + +unsigned int f2fs_destroy_extent_node(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree; + unsigned int node_cnt = 0; + + if (!et) + return 0; + + write_lock(&et->lock); + node_cnt = __free_extent_tree(sbi, et, true); + write_unlock(&et->lock); + + return node_cnt; +} + +void f2fs_destroy_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree; + unsigned int node_cnt = 0; + + if (!et) + return; + + if (inode->i_nlink && !is_bad_inode(inode) && et->count) { + atomic_dec(&et->refcount); + return; + } + + /* free all extent info belong to this extent tree */ + node_cnt = f2fs_destroy_extent_node(inode); + + /* delete extent tree entry in radix tree */ + down_write(&sbi->extent_tree_lock); + atomic_dec(&et->refcount); + f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count); + radix_tree_delete(&sbi->extent_tree_root, inode->i_ino); + kmem_cache_free(extent_tree_slab, et); + sbi->total_ext_tree--; + up_write(&sbi->extent_tree_lock); + + F2FS_I(inode)->extent_tree = NULL; + + trace_f2fs_destroy_extent_tree(inode, node_cnt); +} + +bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + if (!f2fs_may_extent_tree(inode)) + return false; + + return f2fs_lookup_extent_tree(inode, pgofs, ei); +} + +void f2fs_update_extent_cache(struct dnode_of_data *dn) +{ + struct f2fs_inode_info *fi = F2FS_I(dn->inode); + pgoff_t fofs; + + if (!f2fs_may_extent_tree(dn->inode)) + return; + + f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR); + + + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + dn->ofs_in_node; + + if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1)) + sync_inode_page(dn); +} + +void f2fs_update_extent_cache_range(struct dnode_of_data *dn, + pgoff_t fofs, block_t blkaddr, unsigned int len) + +{ + if (!f2fs_may_extent_tree(dn->inode)) + return; + + if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len)) + sync_inode_page(dn); +} + +void init_extent_cache_info(struct f2fs_sb_info *sbi) +{ + INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO); + init_rwsem(&sbi->extent_tree_lock); + INIT_LIST_HEAD(&sbi->extent_list); + spin_lock_init(&sbi->extent_lock); + sbi->total_ext_tree = 0; + atomic_set(&sbi->total_ext_node, 0); +} + +int __init create_extent_cache(void) +{ + extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", + sizeof(struct extent_tree)); + if (!extent_tree_slab) + return -ENOMEM; + extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node", + sizeof(struct extent_node)); + if (!extent_node_slab) { + kmem_cache_destroy(extent_tree_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_extent_cache(void) +{ + kmem_cache_destroy(extent_node_slab); + kmem_cache_destroy(extent_tree_slab); +} diff --git a/kernel/fs/f2fs/f2fs.h b/kernel/fs/f2fs/f2fs.h index 8de34ab6d..5951c495d 100644 --- a/kernel/fs/f2fs/f2fs.h +++ b/kernel/fs/f2fs/f2fs.h @@ -19,10 +19,11 @@ #include <linux/magic.h> #include <linux/kobject.h> #include <linux/sched.h> +#include <linux/vmalloc.h> +#include <linux/bio.h> #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) -#define f2fs_down_write(x, y) down_write_nest_lock(x, y) #else #define f2fs_bug_on(sbi, condition) \ do { \ @@ -31,7 +32,6 @@ set_sbi_flag(sbi, SBI_NEED_FSCK); \ } \ } while (0) -#define f2fs_down_write(x, y) down_write(x) #endif /* @@ -51,6 +51,7 @@ #define F2FS_MOUNT_NOBARRIER 0x00000800 #define F2FS_MOUNT_FASTBOOT 0x00001000 #define F2FS_MOUNT_EXTENT_CACHE 0x00002000 +#define F2FS_MOUNT_FORCE_FG_GC 0x00004000 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -70,6 +71,15 @@ struct f2fs_mount_info { unsigned int opt; }; +#define F2FS_FEATURE_ENCRYPT 0x0001 + +#define F2FS_HAS_FEATURE(sb, mask) \ + ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) +#define F2FS_SET_FEATURE(sb, mask) \ + F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask) +#define F2FS_CLEAR_FEATURE(sb, mask) \ + F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask) + #define CRCPOLY_LE 0xedb88320 static inline __u32 f2fs_crc32(void *buf, size_t len) @@ -110,6 +120,9 @@ enum { #define DEF_BATCHED_TRIM_SECTIONS 32 #define BATCHED_TRIM_SEGMENTS(sbi) \ (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec) +#define BATCHED_TRIM_BLOCKS(sbi) \ + (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) +#define DEF_CP_INTERVAL 60 /* 60 secs */ struct cp_control { int reason; @@ -217,6 +230,15 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3) #define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) #define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) +#define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6) +#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7) + +#define F2FS_IOC_SET_ENCRYPTION_POLICY \ + _IOR('f', 19, struct f2fs_encryption_policy) +#define F2FS_IOC_GET_ENCRYPTION_PWSALT \ + _IOW('f', 20, __u8[16]) +#define F2FS_IOC_GET_ENCRYPTION_POLICY \ + _IOW('f', 21, struct f2fs_encryption_policy) /* * should be same as XFS_IOC_GOINGDOWN. @@ -226,6 +248,7 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */ #define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */ #define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */ +#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */ #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -239,16 +262,38 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, * For INODE and NODE manager */ /* for directory operations */ +struct f2fs_str { + unsigned char *name; + u32 len; +}; + +struct f2fs_filename { + const struct qstr *usr_fname; + struct f2fs_str disk_name; + f2fs_hash_t hash; +#ifdef CONFIG_F2FS_FS_ENCRYPTION + struct f2fs_str crypto_buf; +#endif +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + struct f2fs_dentry_ptr { + struct inode *inode; const void *bitmap; struct f2fs_dir_entry *dentry; __u8 (*filename)[F2FS_SLOT_LEN]; int max; }; -static inline void make_dentry_ptr(struct f2fs_dentry_ptr *d, - void *src, int type) +static inline void make_dentry_ptr(struct inode *inode, + struct f2fs_dentry_ptr *d, void *src, int type) { + d->inode = inode; + if (type == 1) { struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src; d->max = NR_DENTRY_IN_BLOCK; @@ -280,7 +325,7 @@ enum { */ }; -#define F2FS_LINK_MAX 32000 /* maximum link count per file */ +#define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ @@ -309,16 +354,64 @@ struct extent_tree { nid_t ino; /* inode number */ struct rb_root root; /* root of extent info rb-tree */ struct extent_node *cached_en; /* recently accessed extent node */ + struct extent_info largest; /* largested extent info */ rwlock_t lock; /* protect extent info rb-tree */ atomic_t refcount; /* reference count of rb-tree */ unsigned int count; /* # of extent node in rb-tree*/ }; /* + * This structure is taken from ext4_map_blocks. + * + * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks(). + */ +#define F2FS_MAP_NEW (1 << BH_New) +#define F2FS_MAP_MAPPED (1 << BH_Mapped) +#define F2FS_MAP_UNWRITTEN (1 << BH_Unwritten) +#define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\ + F2FS_MAP_UNWRITTEN) + +struct f2fs_map_blocks { + block_t m_pblk; + block_t m_lblk; + unsigned int m_len; + unsigned int m_flags; +}; + +/* for flag in get_data_block */ +#define F2FS_GET_BLOCK_READ 0 +#define F2FS_GET_BLOCK_DIO 1 +#define F2FS_GET_BLOCK_FIEMAP 2 +#define F2FS_GET_BLOCK_BMAP 3 + +/* * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. */ #define FADVISE_COLD_BIT 0x01 #define FADVISE_LOST_PINO_BIT 0x02 +#define FADVISE_ENCRYPT_BIT 0x04 +#define FADVISE_ENC_NAME_BIT 0x08 + +#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) +#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) +#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) +#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) +#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) +#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) +#define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT) +#define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT) +#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT) +#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT) +#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) + +/* Encryption algorithms */ +#define F2FS_ENCRYPTION_MODE_INVALID 0 +#define F2FS_ENCRYPTION_MODE_AES_256_XTS 1 +#define F2FS_ENCRYPTION_MODE_AES_256_GCM 2 +#define F2FS_ENCRYPTION_MODE_AES_256_CBC 3 +#define F2FS_ENCRYPTION_MODE_AES_256_CTS 4 + +#include "f2fs_crypto.h" #define DEF_DIR_LEVEL 0 @@ -339,13 +432,17 @@ struct f2fs_inode_info { unsigned int clevel; /* maximum level of given file name */ nid_t i_xattr_nid; /* node id that contains xattrs */ unsigned long long xattr_ver; /* cp version of xattr modification */ - struct extent_info ext; /* in-memory extent cache entry */ - rwlock_t ext_lock; /* rwlock for single extent cache */ struct inode_entry *dirty_dir; /* the pointer of dirty dir */ - struct radix_tree_root inmem_root; /* radix tree for inmem pages */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct mutex inmem_lock; /* lock for inmemory pages */ + + struct extent_tree *extent_tree; /* cached extent_tree entry */ + +#ifdef CONFIG_F2FS_FS_ENCRYPTION + /* Encryption params */ + struct f2fs_crypt_info *i_crypt_info; +#endif }; static inline void get_extent_info(struct extent_info *ext, @@ -398,12 +495,20 @@ static inline bool __is_front_mergeable(struct extent_info *cur, return __is_extent_mergeable(cur, front); } +static inline void __try_update_largest_extent(struct extent_tree *et, + struct extent_node *en) +{ + if (en->ei.len > et->largest.len) + et->largest = en->ei; +} + struct f2fs_nm_info { block_t nat_blkaddr; /* base disk address of NAT */ nid_t max_nid; /* maximum possible node ids */ nid_t available_nids; /* maximum available node ids */ nid_t next_scan_nid; /* the next nid to be scanned */ unsigned int ram_thresh; /* control the memory footprint */ + unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */ /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ @@ -571,9 +676,12 @@ enum page_type { }; struct f2fs_io_info { + struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */ block_t blk_addr; /* block address to be written */ + struct page *page; /* page to be written */ + struct page *encrypted_page; /* encrypted page */ }; #define is_read_io(rw) (((rw) & 1) == READ) @@ -627,6 +735,7 @@ struct f2fs_sb_info { struct rw_semaphore node_write; /* locking node writes */ struct mutex writepages; /* mutex for writepages() */ wait_queue_head_t cp_wait; + long cp_expires, cp_interval; /* next expected periodic cp */ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ @@ -666,6 +775,7 @@ struct f2fs_sb_info { block_t user_block_count; /* # of user blocks */ block_t total_valid_block_count; /* # of valid blocks */ block_t alloc_valid_block_count; /* # of allocated blocks */ + block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ u32 s_next_generation; /* for NFS support */ atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */ @@ -689,7 +799,11 @@ struct f2fs_sb_info { unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ atomic_t inplace_count; /* # of inplace update */ - int total_hit_ext, read_hit_ext; /* extent cache hit ratio */ + atomic64_t total_hit_ext; /* # of lookup extent cache */ + atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */ + atomic64_t read_hit_largest; /* # of hit largest extent node */ + atomic64_t read_hit_cached; /* # of hit cached extent node */ + atomic_t inline_xattr; /* # of inline_xattr inodes */ atomic_t inline_inode; /* # of inline_data inodes */ atomic_t inline_dir; /* # of inline_dentry inodes */ int bg_gc; /* background gc calls */ @@ -701,6 +815,11 @@ struct f2fs_sb_info { /* For sysfs suppport */ struct kobject s_kobj; struct completion s_kobj_unregister; + + /* For shrinker support */ + struct list_head s_list; + struct mutex umount_mutex; + unsigned int shrinker_run_no; }; /* @@ -838,7 +957,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { - f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex); + down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) @@ -949,7 +1068,8 @@ static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) static inline void inode_dec_dirty_pages(struct inode *inode) { - if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && + !S_ISLNK(inode->i_mode)) return; atomic_dec(&F2FS_I(inode)->dirty_pages); @@ -1112,6 +1232,24 @@ static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi) return sbi->total_valid_inode_count; } +static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, + pgoff_t index, bool for_write) +{ + if (!for_write) + return grab_cache_page(mapping, index); + return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); +} + +static inline void f2fs_copy_page(struct page *src, struct page *dst) +{ + char *src_kaddr = kmap(src); + char *dst_kaddr = kmap(dst); + + memcpy(dst_kaddr, src_kaddr, PAGE_SIZE); + kunmap(dst); + kunmap(src); +} + static inline void f2fs_put_page(struct page *page, int unlock) { if (!page) @@ -1144,16 +1282,24 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *entry; -retry: - entry = kmem_cache_alloc(cachep, flags); - if (!entry) { - cond_resched(); - goto retry; - } + entry = kmem_cache_alloc(cachep, flags); + if (!entry) + entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL); return entry; } +static inline struct bio *f2fs_bio_alloc(int npages) +{ + struct bio *bio; + + /* No failure on bio allocation */ + bio = bio_alloc(GFP_NOIO, npages); + if (!bio) + bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages); + return bio; +} + static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { @@ -1193,6 +1339,24 @@ static inline int f2fs_test_bit(unsigned int nr, char *addr) return mask & *addr; } +static inline void f2fs_set_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + *addr |= mask; +} + +static inline void f2fs_clear_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + *addr &= ~mask; +} + static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) { int mask; @@ -1234,6 +1398,7 @@ enum { FI_INC_LINK, /* need to increment i_nlink */ FI_ACL_MODE, /* indicate acl mode */ FI_NO_ALLOC, /* should not allocate any blocks */ + FI_FREE_NID, /* free allocated nide */ FI_UPDATE_DIR, /* should update inode block for consistency */ FI_DELAY_IPUT, /* used for the recovery */ FI_NO_EXTENT, /* not to use the extent cache */ @@ -1391,6 +1556,21 @@ static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) kunmap(page); } +static inline int is_file(struct inode *inode, int type) +{ + return F2FS_I(inode)->i_advise & type; +} + +static inline void set_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise |= type; +} + +static inline void clear_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise &= ~type; +} + static inline int f2fs_readonly(struct super_block *sb) { return sb->s_flags & MS_RDONLY; @@ -1407,6 +1587,48 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi) sbi->sb->s_flags |= MS_RDONLY; } +static inline bool is_dot_dotdot(const struct qstr *str) +{ + if (str->len == 1 && str->name[0] == '.') + return true; + + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; +} + +static inline bool f2fs_may_extent_tree(struct inode *inode) +{ + mode_t mode = inode->i_mode; + + if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) || + is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) + return false; + + return S_ISREG(mode); +} + +static inline void *f2fs_kvmalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kmalloc(size, flags | __GFP_NOWARN); + if (!ret) + ret = __vmalloc(size, flags, PAGE_KERNEL); + return ret; +} + +static inline void *f2fs_kvzalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kzalloc(size, flags | __GFP_NOWARN); + if (!ret) + ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); + return ret; +} + #define get_inode_mode(i) \ ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -1423,7 +1645,7 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi) int f2fs_sync_file(struct file *, loff_t, loff_t, int); void truncate_data_blocks(struct dnode_of_data *); int truncate_blocks(struct inode *, u64, bool); -void f2fs_truncate(struct inode *); +int f2fs_truncate(struct inode *, bool); int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *); int f2fs_setattr(struct dentry *, struct iattr *); int truncate_hole(struct inode *, pgoff_t, pgoff_t); @@ -1453,10 +1675,11 @@ struct dentry *f2fs_get_parent(struct dentry *child); */ extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; void set_de_type(struct f2fs_dir_entry *, umode_t); -struct f2fs_dir_entry *find_target_dentry(struct qstr *, int *, - struct f2fs_dentry_ptr *); + +struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *, + f2fs_hash_t, int *, struct f2fs_dentry_ptr *); bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, - unsigned int); + unsigned int, struct f2fs_str *); void do_make_empty_dir(struct inode *, struct inode *, struct f2fs_dentry_ptr *); struct page *init_inode_metadata(struct inode *, struct inode *, @@ -1470,7 +1693,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); ino_t f2fs_inode_by_name(struct inode *, struct qstr *); void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, struct page *, struct inode *); -int update_dent_inode(struct inode *, const struct qstr *); +int update_dent_inode(struct inode *, struct inode *, const struct qstr *); void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *, const struct qstr *, f2fs_hash_t , unsigned int); int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, @@ -1478,7 +1701,6 @@ int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); int f2fs_do_tmpfile(struct inode *, struct inode *); -int f2fs_make_empty(struct inode *, struct inode *); bool f2fs_empty_dir(struct inode *); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) @@ -1490,6 +1712,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) /* * super.c */ +int f2fs_commit_super(struct f2fs_sb_info *, bool); int f2fs_sync_fs(struct super_block *, int); extern __printf(3, 4) void f2fs_msg(struct super_block *, const char *, const char *, ...); @@ -1506,15 +1729,15 @@ struct dnode_of_data; struct node_info; bool available_free_memory(struct f2fs_sb_info *, int); +int need_dentry_mark(struct f2fs_sb_info *, nid_t); bool is_checkpointed_node(struct f2fs_sb_info *, nid_t); -bool has_fsynced_inode(struct f2fs_sb_info *, nid_t); bool need_inode_block_update(struct f2fs_sb_info *, nid_t); void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); int truncate_inode_blocks(struct inode *, pgoff_t); int truncate_xattr_node(struct inode *, struct page *); int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t); -void remove_inode_page(struct inode *); +int remove_inode_page(struct inode *); struct page *new_inode_page(struct inode *); struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *); void ra_node_page(struct f2fs_sb_info *, nid_t); @@ -1525,6 +1748,7 @@ int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *); bool alloc_nid(struct f2fs_sb_info *, nid_t *); void alloc_nid_done(struct f2fs_sb_info *, nid_t); void alloc_nid_failed(struct f2fs_sb_info *, nid_t); +int try_to_free_nids(struct f2fs_sb_info *, int); void recover_inline_xattr(struct inode *, struct page *); void recover_xattr_data(struct inode *, struct page *, block_t); int recover_inode_page(struct f2fs_sb_info *, struct page *); @@ -1540,32 +1764,33 @@ void destroy_node_manager_caches(void); * segment.c */ void register_inmem_page(struct inode *, struct page *); -void commit_inmem_pages(struct inode *, bool); +int commit_inmem_pages(struct inode *, bool); void f2fs_balance_fs(struct f2fs_sb_info *); void f2fs_balance_fs_bg(struct f2fs_sb_info *); int f2fs_issue_flush(struct f2fs_sb_info *); int create_flush_cmd_control(struct f2fs_sb_info *); void destroy_flush_cmd_control(struct f2fs_sb_info *); void invalidate_blocks(struct f2fs_sb_info *, block_t); +bool is_checkpointed_data(struct f2fs_sb_info *, block_t); void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t); -void clear_prefree_segments(struct f2fs_sb_info *); +void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *); void release_discard_addrs(struct f2fs_sb_info *); -void discard_next_dnode(struct f2fs_sb_info *, block_t); +bool discard_next_dnode(struct f2fs_sb_info *, block_t); int npages_for_summary_flush(struct f2fs_sb_info *, bool); void allocate_new_segments(struct f2fs_sb_info *); int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *); struct page *get_sum_page(struct f2fs_sb_info *, unsigned int); +void update_meta_page(struct f2fs_sb_info *, void *, block_t); void write_meta_page(struct f2fs_sb_info *, struct page *); -void write_node_page(struct f2fs_sb_info *, struct page *, - unsigned int, struct f2fs_io_info *); -void write_data_page(struct page *, struct dnode_of_data *, - struct f2fs_io_info *); -void rewrite_data_page(struct page *, struct f2fs_io_info *); -void recover_data_page(struct f2fs_sb_info *, struct page *, - struct f2fs_summary *, block_t, block_t); +void write_node_page(unsigned int, struct f2fs_io_info *); +void write_data_page(struct dnode_of_data *, struct f2fs_io_info *); +void rewrite_data_page(struct f2fs_io_info *); +void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *, + block_t, block_t, unsigned char, bool); void allocate_data_block(struct f2fs_sb_info *, struct page *, block_t, block_t *, struct f2fs_summary *, int); void f2fs_wait_on_page_writeback(struct page *, enum page_type); +void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t); void write_data_summaries(struct f2fs_sb_info *, block_t); void write_node_summaries(struct f2fs_sb_info *, block_t); int lookup_journal_in_cursum(struct f2fs_summary_block *, @@ -1581,7 +1806,9 @@ void destroy_segment_manager_caches(void); */ struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); -int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int); +struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t); +bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int); +int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool); void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type); @@ -1592,7 +1819,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *); void release_orphan_inode(struct f2fs_sb_info *); void add_orphan_inode(struct f2fs_sb_info *, nid_t); void remove_orphan_inode(struct f2fs_sb_info *, nid_t); -void recover_orphan_inodes(struct f2fs_sb_info *); +int recover_orphan_inodes(struct f2fs_sb_info *); int get_valid_checkpoint(struct f2fs_sb_info *); void update_dirty_page(struct inode *, struct page *); void add_dirty_dir_inode(struct inode *); @@ -1607,26 +1834,18 @@ void destroy_checkpoint_caches(void); * data.c */ void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int); -int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, - struct f2fs_io_info *); -void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, - struct f2fs_io_info *); +int f2fs_submit_page_bio(struct f2fs_io_info *); +void f2fs_submit_page_mbio(struct f2fs_io_info *); void set_data_blkaddr(struct dnode_of_data *); int reserve_new_block(struct dnode_of_data *); +int f2fs_get_block(struct dnode_of_data *, pgoff_t); int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); -void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int); -void f2fs_destroy_extent_tree(struct inode *); -void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *); -void f2fs_update_extent_cache(struct dnode_of_data *); -void f2fs_preserve_extent_tree(struct inode *); -struct page *find_data_page(struct inode *, pgoff_t, bool); -struct page *get_lock_data_page(struct inode *, pgoff_t); +struct page *get_read_data_page(struct inode *, pgoff_t, int, bool); +struct page *find_data_page(struct inode *, pgoff_t); +struct page *get_lock_data_page(struct inode *, pgoff_t, bool); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); -int do_write_data_page(struct page *, struct f2fs_io_info *); +int do_write_data_page(struct f2fs_io_info *); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); -void init_extent_cache_info(struct f2fs_sb_info *); -int __init create_extent_cache(void); -void destroy_extent_cache(void); void f2fs_invalidate_page(struct page *, unsigned int, unsigned int); int f2fs_release_page(struct page *, gfp_t); @@ -1636,7 +1855,7 @@ int f2fs_release_page(struct page *, gfp_t); int start_gc_thread(struct f2fs_sb_info *); void stop_gc_thread(struct f2fs_sb_info *); block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *); -int f2fs_gc(struct f2fs_sb_info *); +int f2fs_gc(struct f2fs_sb_info *, bool); void build_gc_manager(struct f2fs_sb_info *); /* @@ -1654,11 +1873,14 @@ struct f2fs_stat_info { struct f2fs_sb_info *sbi; int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; int main_area_segs, main_area_sections, main_area_zones; - int hit_ext, total_ext, ext_tree, ext_node; + unsigned long long hit_largest, hit_cached, hit_rbtree; + unsigned long long hit_total, total_ext; + int ext_tree, ext_node; int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; int nats, dirty_nats, sits, dirty_sits, fnids; int total_count, utilization; - int bg_gc, inline_inode, inline_dir, inmem_pages, wb_pages; + int bg_gc, inmem_pages, wb_pages; + int inline_xattr, inline_inode, inline_dir; unsigned int valid_count, valid_node_count, valid_inode_count; unsigned int bimodal, avg_vblocks; int util_free, util_valid, util_invalid; @@ -1676,7 +1898,7 @@ struct f2fs_stat_info { unsigned int segment_count[2]; unsigned int block_count[2]; unsigned int inplace_count; - unsigned base_mem, cache_mem, page_mem; + unsigned long long base_mem, cache_mem, page_mem; }; static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) @@ -1689,8 +1911,20 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) #define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++) #define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--) -#define stat_inc_total_hit(sb) ((F2FS_SB(sb))->total_hit_ext++) -#define stat_inc_read_hit(sb) ((F2FS_SB(sb))->read_hit_ext++) +#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) +#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree)) +#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest)) +#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached)) +#define stat_inc_inline_xattr(inode) \ + do { \ + if (f2fs_has_inline_xattr(inode)) \ + (atomic_inc(&F2FS_I_SB(inode)->inline_xattr)); \ + } while (0) +#define stat_dec_inline_xattr(inode) \ + do { \ + if (f2fs_has_inline_xattr(inode)) \ + (atomic_dec(&F2FS_I_SB(inode)->inline_xattr)); \ + } while (0) #define stat_inc_inline_inode(inode) \ do { \ if (f2fs_has_inline_data(inode)) \ @@ -1760,7 +1994,11 @@ void f2fs_destroy_root_stats(void); #define stat_inc_dirty_dir(sbi) #define stat_dec_dirty_dir(sbi) #define stat_inc_total_hit(sb) -#define stat_inc_read_hit(sb) +#define stat_inc_rbtree_node_hit(sb) +#define stat_inc_largest_node_hit(sbi) +#define stat_inc_cached_node_hit(sbi) +#define stat_inc_inline_xattr(inode) +#define stat_dec_inline_xattr(inode) #define stat_inc_inline_inode(inode) #define stat_dec_inline_inode(inode) #define stat_inc_inline_dir(inode) @@ -1787,13 +2025,15 @@ extern const struct address_space_operations f2fs_node_aops; extern const struct address_space_operations f2fs_meta_aops; extern const struct inode_operations f2fs_dir_inode_operations; extern const struct inode_operations f2fs_symlink_inode_operations; +extern const struct inode_operations f2fs_encrypted_symlink_inode_operations; extern const struct inode_operations f2fs_special_inode_operations; extern struct kmem_cache *inode_entry_slab; /* * inline.c */ -bool f2fs_may_inline(struct inode *); +bool f2fs_may_inline_data(struct inode *); +bool f2fs_may_inline_dentry(struct inode *); void read_inline_data(struct page *, struct page *); bool truncate_inline_inode(struct page *, u64); int f2fs_read_inline_data(struct inode *, struct page *); @@ -1801,8 +2041,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *, struct page *); int f2fs_convert_inline_inode(struct inode *); int f2fs_write_inline_data(struct inode *, struct page *); bool recover_inline_data(struct inode *, struct page *); -struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *, - struct page **); +struct f2fs_dir_entry *find_in_inline_dir(struct inode *, + struct f2fs_filename *, struct page **); struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **); int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *); int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, @@ -1810,5 +2050,163 @@ int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); bool f2fs_empty_inline_dir(struct inode *); -int f2fs_read_inline_dir(struct file *, struct dir_context *); +int f2fs_read_inline_dir(struct file *, struct dir_context *, + struct f2fs_str *); +int f2fs_inline_data_fiemap(struct inode *, + struct fiemap_extent_info *, __u64, __u64); + +/* + * shrinker.c + */ +unsigned long f2fs_shrink_count(struct shrinker *, struct shrink_control *); +unsigned long f2fs_shrink_scan(struct shrinker *, struct shrink_control *); +void f2fs_join_shrinker(struct f2fs_sb_info *); +void f2fs_leave_shrinker(struct f2fs_sb_info *); + +/* + * extent_cache.c + */ +unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int); +void f2fs_drop_largest_extent(struct inode *, pgoff_t); +void f2fs_init_extent_tree(struct inode *, struct f2fs_extent *); +unsigned int f2fs_destroy_extent_node(struct inode *); +void f2fs_destroy_extent_tree(struct inode *); +bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *); +void f2fs_update_extent_cache(struct dnode_of_data *); +void f2fs_update_extent_cache_range(struct dnode_of_data *dn, + pgoff_t, block_t, unsigned int); +void init_extent_cache_info(struct f2fs_sb_info *); +int __init create_extent_cache(void); +void destroy_extent_cache(void); + +/* + * crypto support + */ +static inline int f2fs_encrypted_inode(struct inode *inode) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + return file_is_encrypt(inode); +#else + return 0; +#endif +} + +static inline void f2fs_set_encrypted_inode(struct inode *inode) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + file_set_encrypt(inode); +#endif +} + +static inline bool f2fs_bio_encrypted(struct bio *bio) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + return unlikely(bio->bi_private != NULL); +#else + return false; +#endif +} + +static inline int f2fs_sb_has_crypto(struct super_block *sb) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT); +#else + return 0; +#endif +} + +static inline bool f2fs_may_encrypt(struct inode *inode) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + mode_t mode = inode->i_mode; + + return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); +#else + return 0; +#endif +} + +/* crypto_policy.c */ +int f2fs_is_child_context_consistent_with_parent(struct inode *, + struct inode *); +int f2fs_inherit_context(struct inode *, struct inode *, struct page *); +int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *); +int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *); + +/* crypt.c */ +extern struct kmem_cache *f2fs_crypt_info_cachep; +bool f2fs_valid_contents_enc_mode(uint32_t); +uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t); +struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *); +void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *); +struct page *f2fs_encrypt(struct inode *, struct page *); +int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *); +int f2fs_decrypt_one(struct inode *, struct page *); +void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *); + +/* crypto_key.c */ +void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *); +int _f2fs_get_encryption_info(struct inode *inode); + +/* crypto_fname.c */ +bool f2fs_valid_filenames_enc_mode(uint32_t); +u32 f2fs_fname_crypto_round_up(u32, u32); +int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *); +int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *, + const struct f2fs_str *, struct f2fs_str *); +int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *, + struct f2fs_str *); + +#ifdef CONFIG_F2FS_FS_ENCRYPTION +void f2fs_restore_and_release_control_page(struct page **); +void f2fs_restore_control_page(struct page *); + +int __init f2fs_init_crypto(void); +int f2fs_crypto_initialize(void); +void f2fs_exit_crypto(void); + +int f2fs_has_encryption_key(struct inode *); + +static inline int f2fs_get_encryption_info(struct inode *inode) +{ + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (!ci || + (ci->ci_keyring_key && + (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED) | + (1 << KEY_FLAG_DEAD))))) + return _f2fs_get_encryption_info(inode); + return 0; +} + +void f2fs_fname_crypto_free_buffer(struct f2fs_str *); +int f2fs_fname_setup_filename(struct inode *, const struct qstr *, + int lookup, struct f2fs_filename *); +void f2fs_fname_free_filename(struct f2fs_filename *); +#else +static inline void f2fs_restore_and_release_control_page(struct page **p) { } +static inline void f2fs_restore_control_page(struct page *p) { } + +static inline int __init f2fs_init_crypto(void) { return 0; } +static inline void f2fs_exit_crypto(void) { } + +static inline int f2fs_has_encryption_key(struct inode *i) { return 0; } +static inline int f2fs_get_encryption_info(struct inode *i) { return 0; } +static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { } + +static inline int f2fs_fname_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct f2fs_filename *fname) +{ + memset(fname, 0, sizeof(struct f2fs_filename)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { } +#endif #endif diff --git a/kernel/fs/f2fs/f2fs_crypto.h b/kernel/fs/f2fs/f2fs_crypto.h new file mode 100644 index 000000000..c2c1c2b63 --- /dev/null +++ b/kernel/fs/f2fs/f2fs_crypto.h @@ -0,0 +1,151 @@ +/* + * linux/fs/f2fs/f2fs_crypto.h + * + * Copied from linux/fs/ext4/ext4_crypto.h + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption header content for f2fs + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ +#ifndef _F2FS_CRYPTO_H +#define _F2FS_CRYPTO_H + +#include <linux/fs.h> + +#define F2FS_KEY_DESCRIPTOR_SIZE 8 + +/* Policy provided via an ioctl on the topmost directory */ +struct f2fs_encryption_policy { + char version; + char contents_encryption_mode; + char filenames_encryption_mode; + char flags; + char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE]; +} __attribute__((__packed__)); + +#define F2FS_ENCRYPTION_CONTEXT_FORMAT_V1 1 +#define F2FS_KEY_DERIVATION_NONCE_SIZE 16 + +#define F2FS_POLICY_FLAGS_PAD_4 0x00 +#define F2FS_POLICY_FLAGS_PAD_8 0x01 +#define F2FS_POLICY_FLAGS_PAD_16 0x02 +#define F2FS_POLICY_FLAGS_PAD_32 0x03 +#define F2FS_POLICY_FLAGS_PAD_MASK 0x03 +#define F2FS_POLICY_FLAGS_VALID 0x03 + +/** + * Encryption context for inode + * + * Protector format: + * 1 byte: Protector format (1 = this version) + * 1 byte: File contents encryption mode + * 1 byte: File names encryption mode + * 1 byte: Flags + * 8 bytes: Master Key descriptor + * 16 bytes: Encryption Key derivation nonce + */ +struct f2fs_encryption_context { + char format; + char contents_encryption_mode; + char filenames_encryption_mode; + char flags; + char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE]; + char nonce[F2FS_KEY_DERIVATION_NONCE_SIZE]; +} __attribute__((__packed__)); + +/* Encryption parameters */ +#define F2FS_XTS_TWEAK_SIZE 16 +#define F2FS_AES_128_ECB_KEY_SIZE 16 +#define F2FS_AES_256_GCM_KEY_SIZE 32 +#define F2FS_AES_256_CBC_KEY_SIZE 32 +#define F2FS_AES_256_CTS_KEY_SIZE 32 +#define F2FS_AES_256_XTS_KEY_SIZE 64 +#define F2FS_MAX_KEY_SIZE 64 + +#define F2FS_KEY_DESC_PREFIX "f2fs:" +#define F2FS_KEY_DESC_PREFIX_SIZE 5 + +struct f2fs_encryption_key { + __u32 mode; + char raw[F2FS_MAX_KEY_SIZE]; + __u32 size; +} __attribute__((__packed__)); + +struct f2fs_crypt_info { + char ci_data_mode; + char ci_filename_mode; + char ci_flags; + struct crypto_ablkcipher *ci_ctfm; + struct key *ci_keyring_key; + char ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE]; +}; + +#define F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 +#define F2FS_WRITE_PATH_FL 0x00000002 + +struct f2fs_crypto_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + char flags; /* Flags */ +}; + +struct f2fs_completion_result { + struct completion completion; + int res; +}; + +#define DECLARE_F2FS_COMPLETION_RESULT(ecr) \ + struct f2fs_completion_result ecr = { \ + COMPLETION_INITIALIZER((ecr).completion), 0 } + +static inline int f2fs_encryption_key_size(int mode) +{ + switch (mode) { + case F2FS_ENCRYPTION_MODE_AES_256_XTS: + return F2FS_AES_256_XTS_KEY_SIZE; + case F2FS_ENCRYPTION_MODE_AES_256_GCM: + return F2FS_AES_256_GCM_KEY_SIZE; + case F2FS_ENCRYPTION_MODE_AES_256_CBC: + return F2FS_AES_256_CBC_KEY_SIZE; + case F2FS_ENCRYPTION_MODE_AES_256_CTS: + return F2FS_AES_256_CTS_KEY_SIZE; + default: + BUG(); + } + return 0; +} + +#define F2FS_FNAME_NUM_SCATTER_ENTRIES 4 +#define F2FS_CRYPTO_BLOCK_SIZE 16 +#define F2FS_FNAME_CRYPTO_DIGEST_SIZE 32 + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct f2fs_encrypted_symlink_data { + __le16 len; + char encrypted_path[1]; +} __attribute__((__packed__)); + +/** + * This function is used to calculate the disk space required to + * store a filename of length l in encrypted symlink format. + */ +static inline u32 encrypted_symlink_data_len(u32 l) +{ + return (l + sizeof(struct f2fs_encrypted_symlink_data) - 1); +} +#endif /* _F2FS_CRYPTO_H */ diff --git a/kernel/fs/f2fs/file.c b/kernel/fs/f2fs/file.c index 2b52e48d7..a197215ad 100644 --- a/kernel/fs/f2fs/file.c +++ b/kernel/fs/f2fs/file.c @@ -20,12 +20,14 @@ #include <linux/uaccess.h> #include <linux/mount.h> #include <linux/pagevec.h> +#include <linux/random.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" #include "acl.h" +#include "gc.h" #include "trace.h" #include <trace/events/f2fs.h> @@ -72,7 +74,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, goto mapped; /* page is wholly or partially inside EOF */ - if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) { + if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) > + i_size_read(inode)) { unsigned offset; offset = i_size_read(inode) & ~PAGE_CACHE_MASK; zero_user_segment(page, offset, PAGE_CACHE_SIZE); @@ -84,6 +87,13 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, mapped: /* fill the page */ f2fs_wait_on_page_writeback(page, DATA); + + /* wait for GCed encrypted page writeback */ + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + + /* if gced page is attached, don't write to cold segment */ + clear_cold_data(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(err); @@ -105,7 +115,7 @@ static int get_parent_ino(struct inode *inode, nid_t *pino) if (!dentry) return 0; - if (update_dent_inode(inode, &dentry->d_name)) { + if (update_dent_inode(inode, inode, &dentry->d_name)) { dput(dentry); return 0; } @@ -122,6 +132,8 @@ static inline bool need_do_checkpoint(struct inode *inode) if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) need_cp = true; + else if (file_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino)) + need_cp = true; else if (file_wrong_pino(inode)) need_cp = true; else if (!space_for_roll_forward(sbi)) @@ -200,8 +212,8 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } /* if the inode is dirty, let's recover all the time */ - if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) { - update_inode_page(inode); + if (!datasync) { + f2fs_write_inode(inode, NULL); goto go_write; } @@ -271,7 +283,7 @@ flush_out: ret = f2fs_issue_flush(sbi); out: trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); - f2fs_trace_ios(NULL, NULL, 1); + f2fs_trace_ios(NULL, 1); return ret; } @@ -337,7 +349,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); - for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) { + for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA); if (err && err != -ENOENT) { @@ -407,6 +419,12 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + if (f2fs_encrypted_inode(inode)) { + int err = f2fs_get_encryption_info(inode); + if (err) + return 0; + } + /* we don't need to use inline_data strictly */ if (f2fs_has_inline_data(inode)) { int err = f2fs_convert_inline_inode(inode); @@ -419,11 +437,23 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) return 0; } +static int f2fs_file_open(struct inode *inode, struct file *filp) +{ + int ret = generic_file_open(inode, filp); + + if (!ret && f2fs_encrypted_inode(inode)) { + ret = f2fs_get_encryption_info(inode); + if (ret) + ret = -EACCES; + } + return ret; +} + int truncate_data_blocks_range(struct dnode_of_data *dn, int count) { - int nr_free = 0, ofs = dn->ofs_in_node; struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct f2fs_node *raw_node; + int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; raw_node = F2FS_NODE(dn->node_page); @@ -436,14 +466,22 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) dn->data_blkaddr = NULL_ADDR; set_data_blkaddr(dn); - f2fs_update_extent_cache(dn); invalidate_blocks(sbi, blkaddr); if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) clear_inode_flag(F2FS_I(dn->inode), FI_FIRST_BLOCK_WRITTEN); nr_free++; } + if (nr_free) { + pgoff_t fofs; + /* + * once we invalidate valid blkaddr in range [ofs, ofs + count], + * we will invalidate all blkaddr in the whole range. + */ + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), + F2FS_I(dn->inode)) + ofs; + f2fs_update_extent_cache_range(dn, fofs, 0, len); dec_valid_block_count(sbi, dn->inode, nr_free); set_page_dirty(dn->node_page); sync_inode_page(dn); @@ -461,28 +499,32 @@ void truncate_data_blocks(struct dnode_of_data *dn) } static int truncate_partial_data_page(struct inode *inode, u64 from, - bool force) + bool cache_only) { unsigned offset = from & (PAGE_CACHE_SIZE - 1); + pgoff_t index = from >> PAGE_CACHE_SHIFT; + struct address_space *mapping = inode->i_mapping; struct page *page; - if (!offset && !force) + if (!offset && !cache_only) return 0; - page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force); - if (IS_ERR(page)) + if (cache_only) { + page = f2fs_grab_cache_page(mapping, index, false); + if (page && PageUptodate(page)) + goto truncate_out; + f2fs_put_page(page, 1); return 0; + } - lock_page(page); - if (unlikely(!PageUptodate(page) || - page->mapping != inode->i_mapping)) - goto out; - + page = get_lock_data_page(inode, index, true); + if (IS_ERR(page)) + return 0; +truncate_out: f2fs_wait_on_page_writeback(page, DATA); zero_user(page, offset, PAGE_CACHE_SIZE - offset); - if (!force) + if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode)) set_page_dirty(page); -out: f2fs_put_page(page, 1); return 0; } @@ -551,24 +593,30 @@ out: return err; } -void f2fs_truncate(struct inode *inode) +int f2fs_truncate(struct inode *inode, bool lock) { + int err; + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) - return; + return 0; trace_f2fs_truncate(inode); /* we should check inline_data size */ - if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) { - if (f2fs_convert_inline_inode(inode)) - return; + if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; } - if (!truncate_blocks(inode, i_size_read(inode), true)) { - inode->i_mtime = inode->i_ctime = CURRENT_TIME; - mark_inode_dirty(inode); - } + err = truncate_blocks(inode, i_size_read(inode), lock); + if (err) + return err; + + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + return 0; } int f2fs_getattr(struct vfsmount *mnt, @@ -622,16 +670,23 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) return err; if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size != i_size_read(inode)) { + if (f2fs_encrypted_inode(inode) && + f2fs_get_encryption_info(inode)) + return -EACCES; + + if (attr->ia_size <= i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); - f2fs_truncate(inode); + err = f2fs_truncate(inode, true); + if (err) + return err; f2fs_balance_fs(F2FS_I_SB(inode)); } else { /* - * giving a chance to truncate blocks past EOF which - * are fallocated with FALLOC_FL_KEEP_SIZE. + * do not trim all blocks after i_size if target size is + * larger than i_size. */ - f2fs_truncate(inode); + truncate_setsize(inode, attr->ia_size); + inode->i_mtime = inode->i_ctime = CURRENT_TIME; } } @@ -663,14 +718,14 @@ const struct inode_operations f2fs_file_inode_operations = { .fiemap = f2fs_fiemap, }; -static void fill_zero(struct inode *inode, pgoff_t index, +static int fill_zero(struct inode *inode, pgoff_t index, loff_t start, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page; if (!len) - return; + return 0; f2fs_balance_fs(sbi); @@ -678,33 +733,43 @@ static void fill_zero(struct inode *inode, pgoff_t index, page = get_new_data_page(inode, NULL, index, false); f2fs_unlock_op(sbi); - if (!IS_ERR(page)) { - f2fs_wait_on_page_writeback(page, DATA); - zero_user(page, start, len); - set_page_dirty(page); - f2fs_put_page(page, 1); - } + if (IS_ERR(page)) + return PTR_ERR(page); + + f2fs_wait_on_page_writeback(page, DATA); + zero_user(page, start, len); + set_page_dirty(page); + f2fs_put_page(page, 1); + return 0; } int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) { - pgoff_t index; int err; - for (index = pg_start; index < pg_end; index++) { + while (pg_start < pg_end) { struct dnode_of_data dn; + pgoff_t end_offset, count; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); if (err) { - if (err == -ENOENT) + if (err == -ENOENT) { + pg_start++; continue; + } return err; } - if (dn.data_blkaddr != NULL_ADDR) - truncate_data_blocks_range(&dn, 1); + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); + + f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); + + truncate_data_blocks_range(&dn, count); f2fs_put_dnode(&dn); + + pg_start += count; } return 0; } @@ -715,13 +780,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) loff_t off_start, off_end; int ret = 0; - if (!S_ISREG(inode->i_mode)) - return -EOPNOTSUPP; - - /* skip punching hole beyond i_size */ - if (offset >= inode->i_size) - return ret; - if (f2fs_has_inline_data(inode)) { ret = f2fs_convert_inline_inode(inode); if (ret) @@ -735,14 +793,22 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); if (pg_start == pg_end) { - fill_zero(inode, pg_start, off_start, + ret = fill_zero(inode, pg_start, off_start, off_end - off_start); + if (ret) + return ret; } else { - if (off_start) - fill_zero(inode, pg_start++, off_start, - PAGE_CACHE_SIZE - off_start); - if (off_end) - fill_zero(inode, pg_end, 0, off_end); + if (off_start) { + ret = fill_zero(inode, pg_start++, off_start, + PAGE_CACHE_SIZE - off_start); + if (ret) + return ret; + } + if (off_end) { + ret = fill_zero(inode, pg_end, 0, off_end); + if (ret) + return ret; + } if (pg_start < pg_end) { struct address_space *mapping = inode->i_mapping; @@ -751,8 +817,8 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi); - blk_start = pg_start << PAGE_CACHE_SHIFT; - blk_end = pg_end << PAGE_CACHE_SHIFT; + blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT; + blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT; truncate_inode_pages_range(mapping, blk_start, blk_end - 1); @@ -765,6 +831,320 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) return ret; } +static int __exchange_data_block(struct inode *inode, pgoff_t src, + pgoff_t dst, bool full) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + block_t new_addr; + bool do_replace = false; + int ret; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA); + if (ret && ret != -ENOENT) { + return ret; + } else if (ret == -ENOENT) { + new_addr = NULL_ADDR; + } else { + new_addr = dn.data_blkaddr; + if (!is_checkpointed_data(sbi, new_addr)) { + dn.data_blkaddr = NULL_ADDR; + /* do not invalidate this block address */ + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + do_replace = true; + } + f2fs_put_dnode(&dn); + } + + if (new_addr == NULL_ADDR) + return full ? truncate_hole(inode, dst, dst + 1) : 0; + + if (do_replace) { + struct page *ipage = get_node_page(sbi, inode->i_ino); + struct node_info ni; + + if (IS_ERR(ipage)) { + ret = PTR_ERR(ipage); + goto err_out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); + ret = f2fs_reserve_block(&dn, dst); + if (ret) + goto err_out; + + truncate_data_blocks_range(&dn, 1); + + get_node_info(sbi, dn.nid, &ni); + f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr, + ni.version, true); + f2fs_put_dnode(&dn); + } else { + struct page *psrc, *pdst; + + psrc = get_lock_data_page(inode, src, true); + if (IS_ERR(psrc)) + return PTR_ERR(psrc); + pdst = get_new_data_page(inode, NULL, dst, false); + if (IS_ERR(pdst)) { + f2fs_put_page(psrc, 1); + return PTR_ERR(pdst); + } + f2fs_copy_page(psrc, pdst); + set_page_dirty(pdst); + f2fs_put_page(pdst, 1); + f2fs_put_page(psrc, 1); + + return truncate_hole(inode, src, src + 1); + } + return 0; + +err_out: + if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) { + dn.data_blkaddr = new_addr; + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + f2fs_put_dnode(&dn); + } + return ret; +} + +static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + int ret = 0; + + for (; end < nrpages; start++, end++) { + f2fs_balance_fs(sbi); + f2fs_lock_op(sbi); + ret = __exchange_data_block(inode, end, start, true); + f2fs_unlock_op(sbi); + if (ret) + break; + } + return ret; +} + +static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) +{ + pgoff_t pg_start, pg_end; + loff_t new_size; + int ret; + + if (offset + len >= i_size_read(inode)) + return -EINVAL; + + /* collapse range should be aligned to block size of f2fs. */ + if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) + return -EINVAL; + + f2fs_balance_fs(F2FS_I_SB(inode)); + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } + + pg_start = offset >> PAGE_CACHE_SHIFT; + pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + + /* write out all dirty pages from offset */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + if (ret) + return ret; + + truncate_pagecache(inode, offset); + + ret = f2fs_do_collapse(inode, pg_start, pg_end); + if (ret) + return ret; + + /* write out all moved pages, if possible */ + filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + truncate_pagecache(inode, offset); + + new_size = i_size_read(inode) - len; + truncate_pagecache(inode, new_size); + + ret = truncate_blocks(inode, new_size, true); + if (!ret) + i_size_write(inode, new_size); + + return ret; +} + +static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, + int mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; + pgoff_t index, pg_start, pg_end; + loff_t new_size = i_size_read(inode); + loff_t off_start, off_end; + int ret = 0; + + ret = inode_newsize_ok(inode, (len + offset)); + if (ret) + return ret; + + f2fs_balance_fs(sbi); + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } + + ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); + if (ret) + return ret; + + truncate_pagecache_range(inode, offset, offset + len - 1); + + pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + + off_start = offset & (PAGE_CACHE_SIZE - 1); + off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + + if (pg_start == pg_end) { + ret = fill_zero(inode, pg_start, off_start, + off_end - off_start); + if (ret) + return ret; + + if (offset + len > new_size) + new_size = offset + len; + new_size = max_t(loff_t, new_size, offset + len); + } else { + if (off_start) { + ret = fill_zero(inode, pg_start++, off_start, + PAGE_CACHE_SIZE - off_start); + if (ret) + return ret; + + new_size = max_t(loff_t, new_size, + (loff_t)pg_start << PAGE_CACHE_SHIFT); + } + + for (index = pg_start; index < pg_end; index++) { + struct dnode_of_data dn; + struct page *ipage; + + f2fs_lock_op(sbi); + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + ret = PTR_ERR(ipage); + f2fs_unlock_op(sbi); + goto out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); + ret = f2fs_reserve_block(&dn, index); + if (ret) { + f2fs_unlock_op(sbi); + goto out; + } + + if (dn.data_blkaddr != NEW_ADDR) { + invalidate_blocks(sbi, dn.data_blkaddr); + + dn.data_blkaddr = NEW_ADDR; + set_data_blkaddr(&dn); + + dn.data_blkaddr = NULL_ADDR; + f2fs_update_extent_cache(&dn); + } + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + + new_size = max_t(loff_t, new_size, + (loff_t)(index + 1) << PAGE_CACHE_SHIFT); + } + + if (off_end) { + ret = fill_zero(inode, pg_end, 0, off_end); + if (ret) + goto out; + + new_size = max_t(loff_t, new_size, offset + len); + } + } + +out: + if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) { + i_size_write(inode, new_size); + mark_inode_dirty(inode); + update_inode_page(inode); + } + + return ret; +} + +static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t pg_start, pg_end, delta, nrpages, idx; + loff_t new_size; + int ret = 0; + + new_size = i_size_read(inode) + len; + if (new_size > inode->i_sb->s_maxbytes) + return -EFBIG; + + if (offset >= i_size_read(inode)) + return -EINVAL; + + /* insert range should be aligned to block size of f2fs. */ + if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) + return -EINVAL; + + f2fs_balance_fs(sbi); + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } + + ret = truncate_blocks(inode, i_size_read(inode), true); + if (ret) + return ret; + + /* write out all dirty pages from offset */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + if (ret) + return ret; + + truncate_pagecache(inode, offset); + + pg_start = offset >> PAGE_CACHE_SHIFT; + pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + delta = pg_end - pg_start; + nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + + for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) { + f2fs_lock_op(sbi); + ret = __exchange_data_block(inode, idx, idx + delta, false); + f2fs_unlock_op(sbi); + if (ret) + break; + } + + /* write out all moved pages, if possible */ + filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + truncate_pagecache(inode, offset); + + if (!ret) + i_size_write(inode, new_size); + return ret; +} + static int expand_inode_data(struct inode *inode, loff_t offset, loff_t len, int mode) { @@ -808,9 +1188,10 @@ noalloc: if (pg_start == pg_end) new_size = offset + len; else if (index == pg_start && off_start) - new_size = (index + 1) << PAGE_CACHE_SHIFT; + new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT; else if (index == pg_end) - new_size = (index << PAGE_CACHE_SHIFT) + off_end; + new_size = ((loff_t)index << PAGE_CACHE_SHIFT) + + off_end; else new_size += PAGE_CACHE_SIZE; } @@ -830,23 +1211,44 @@ static long f2fs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); - long ret; + long ret = 0; + + /* f2fs only support ->fallocate for regular file */ + if (!S_ISREG(inode->i_mode)) + return -EINVAL; - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + if (f2fs_encrypted_inode(inode) && + (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) + return -EOPNOTSUPP; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | + FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; mutex_lock(&inode->i_mutex); - if (mode & FALLOC_FL_PUNCH_HOLE) + if (mode & FALLOC_FL_PUNCH_HOLE) { + if (offset >= inode->i_size) + goto out; + ret = punch_hole(inode, offset, len); - else + } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { + ret = f2fs_collapse_range(inode, offset, len); + } else if (mode & FALLOC_FL_ZERO_RANGE) { + ret = f2fs_zero_range(inode, offset, len, mode); + } else if (mode & FALLOC_FL_INSERT_RANGE) { + ret = f2fs_insert_range(inode, offset, len); + } else { ret = expand_inode_data(inode, offset, len, mode); + } if (!ret) { inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); } +out: mutex_unlock(&inode->i_mutex); trace_f2fs_fallocate(inode, mode, offset, len, ret); @@ -946,6 +1348,7 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) static int f2fs_ioc_start_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + int ret; if (!inode_owner_or_capable(inode)) return -EACCES; @@ -955,9 +1358,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) if (f2fs_is_atomic_file(inode)) return 0; - set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; - return f2fs_convert_inline_inode(inode); + set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + return 0; } static int f2fs_ioc_commit_atomic_write(struct file *filp) @@ -975,18 +1381,23 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) if (ret) return ret; - if (f2fs_is_atomic_file(inode)) - commit_inmem_pages(inode, false); + if (f2fs_is_atomic_file(inode)) { + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + ret = commit_inmem_pages(inode, false); + if (ret) + goto err_out; + } - ret = f2fs_sync_file(filp, 0, LONG_MAX, 0); + ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0); +err_out: mnt_drop_write_file(filp); - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); return ret; } static int f2fs_ioc_start_volatile_write(struct file *filp) { struct inode *inode = file_inode(filp); + int ret; if (!inode_owner_or_capable(inode)) return -EACCES; @@ -994,9 +1405,12 @@ static int f2fs_ioc_start_volatile_write(struct file *filp) if (f2fs_is_volatile_file(inode)) return 0; - set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; - return f2fs_convert_inline_inode(inode); + set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + return 0; } static int f2fs_ioc_release_volatile_write(struct file *filp) @@ -1012,8 +1426,7 @@ static int f2fs_ioc_release_volatile_write(struct file *filp) if (!f2fs_is_first_block_written(inode)) return truncate_partial_data_page(inode, 0, true); - punch_hole(inode, 0, F2FS_BLKSIZE); - return 0; + return punch_hole(inode, 0, F2FS_BLKSIZE); } static int f2fs_ioc_abort_volatile_write(struct file *filp) @@ -1030,16 +1443,10 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) f2fs_balance_fs(F2FS_I_SB(inode)); - if (f2fs_is_atomic_file(inode)) { - commit_inmem_pages(inode, false); - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - } + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + commit_inmem_pages(inode, true); - if (f2fs_is_volatile_file(inode)) { - clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - filemap_fdatawrite(inode->i_mapping); - set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - } mnt_drop_write_file(filp); return ret; } @@ -1073,6 +1480,10 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) case F2FS_GOING_DOWN_NOSYNC: f2fs_stop_checkpoint(sbi); break; + case F2FS_GOING_DOWN_METAFLUSH: + sync_meta_pages(sbi, META, LONG_MAX); + f2fs_stop_checkpoint(sbi); + break; default: return -EINVAL; } @@ -1109,6 +1520,132 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) return 0; } +static bool uuid_is_nonzero(__u8 u[16]) +{ + int i; + + for (i = 0; i < 16; i++) + if (u[i]) + return true; + return false; +} + +static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + struct f2fs_encryption_policy policy; + struct inode *inode = file_inode(filp); + + if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg, + sizeof(policy))) + return -EFAULT; + + return f2fs_process_policy(&policy, inode); +#else + return -EOPNOTSUPP; +#endif +} + +static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + struct f2fs_encryption_policy policy; + struct inode *inode = file_inode(filp); + int err; + + err = f2fs_get_policy(inode, &policy); + if (err) + return err; + + if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy, + sizeof(policy))) + return -EFAULT; + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int err; + + if (!f2fs_sb_has_crypto(inode->i_sb)) + return -EOPNOTSUPP; + + if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) + goto got_it; + + err = mnt_want_write_file(filp); + if (err) + return err; + + /* update superblock with uuid */ + generate_random_uuid(sbi->raw_super->encrypt_pw_salt); + + err = f2fs_commit_super(sbi, false); + + mnt_drop_write_file(filp); + if (err) { + /* undo new data */ + memset(sbi->raw_super->encrypt_pw_salt, 0, 16); + return err; + } +got_it: + if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, + 16)) + return -EFAULT; + return 0; +} + +static int f2fs_ioc_gc(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + __u32 sync; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(sync, (__u32 __user *)arg)) + return -EFAULT; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + if (!sync) { + if (!mutex_trylock(&sbi->gc_mutex)) + return -EBUSY; + } else { + mutex_lock(&sbi->gc_mutex); + } + + return f2fs_gc(sbi, sync); +} + +static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct cp_control cpc; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + cpc.reason = __get_cp_reason(sbi); + + mutex_lock(&sbi->gc_mutex); + write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); + + return 0; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { @@ -1132,11 +1669,33 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); + case F2FS_IOC_SET_ENCRYPTION_POLICY: + return f2fs_ioc_set_encryption_policy(filp, arg); + case F2FS_IOC_GET_ENCRYPTION_POLICY: + return f2fs_ioc_get_encryption_policy(filp, arg); + case F2FS_IOC_GET_ENCRYPTION_PWSALT: + return f2fs_ioc_get_encryption_pwsalt(filp, arg); + case F2FS_IOC_GARBAGE_COLLECT: + return f2fs_ioc_gc(filp, arg); + case F2FS_IOC_WRITE_CHECKPOINT: + return f2fs_ioc_write_checkpoint(filp, arg); default: return -ENOTTY; } } +static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + if (f2fs_encrypted_inode(inode) && + !f2fs_has_encryption_key(inode) && + f2fs_get_encryption_info(inode)) + return -EACCES; + + return generic_file_write_iter(iocb, from); +} + #ifdef CONFIG_COMPAT long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -1157,8 +1716,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations f2fs_file_operations = { .llseek = f2fs_llseek, .read_iter = generic_file_read_iter, - .write_iter = generic_file_write_iter, - .open = generic_file_open, + .write_iter = f2fs_file_write_iter, + .open = f2fs_file_open, .release = f2fs_release_file, .mmap = f2fs_file_mmap, .fsync = f2fs_sync_file, diff --git a/kernel/fs/f2fs/gc.c b/kernel/fs/f2fs/gc.c index ed58211fe..fedbf67a0 100644 --- a/kernel/fs/f2fs/gc.c +++ b/kernel/fs/f2fs/gc.c @@ -78,9 +78,12 @@ static int gc_thread_func(void *data) stat_inc_bggc_count(sbi); /* if return value is not zero, no victim was selected */ - if (f2fs_gc(sbi)) + if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC))) wait_ms = gc_th->no_gc_sleep_time; + trace_f2fs_background_gc(sbi->sb, wait_ms, + prefree_segments(sbi), free_segments(sbi)); + /* balancing f2fs's metadata periodically */ f2fs_balance_fs_bg(sbi); @@ -257,6 +260,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct victim_sel_policy p; unsigned int secno, max_cost; + unsigned int last_segment = MAIN_SEGS(sbi); int nsearched = 0; mutex_lock(&dirty_i->seglist_lock); @@ -267,6 +271,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, p.min_segno = NULL_SEGNO; p.min_cost = max_cost = get_max_cost(sbi, &p); + if (p.max_search == 0) + goto out; + if (p.alloc_mode == LFS && gc_type == FG_GC) { p.min_segno = check_bg_victims(sbi); if (p.min_segno != NULL_SEGNO) @@ -277,9 +284,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, unsigned long cost; unsigned int segno; - segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset); - if (segno >= MAIN_SEGS(sbi)) { + segno = find_next_bit(p.dirty_segmap, last_segment, p.offset); + if (segno >= last_segment) { if (sbi->last_victim[p.gc_mode]) { + last_segment = sbi->last_victim[p.gc_mode]; sbi->last_victim[p.gc_mode] = 0; p.offset = 0; continue; @@ -327,6 +335,7 @@ got_it: sbi->cur_victim_sec, prefree_segments(sbi), free_segments(sbi)); } +out: mutex_unlock(&dirty_i->seglist_lock); return (p.min_segno == NULL_SEGNO) ? 0 : 1; @@ -391,23 +400,27 @@ static int check_valid_map(struct f2fs_sb_info *sbi, * On validity, copy that node with cold status, otherwise (invalid node) * ignore that. */ -static void gc_node_segment(struct f2fs_sb_info *sbi, +static int gc_node_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, unsigned int segno, int gc_type) { bool initial = true; struct f2fs_summary *entry; + block_t start_addr; int off; + start_addr = START_BLOCK(sbi, segno); + next_step: entry = sum; for (off = 0; off < sbi->blocks_per_seg; off++, entry++) { nid_t nid = le32_to_cpu(entry->nid); struct page *node_page; + struct node_info ni; /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0)) - return; + return 0; if (check_valid_map(sbi, segno, off) == 0) continue; @@ -426,6 +439,12 @@ next_step: continue; } + get_node_info(sbi, nid, &ni); + if (ni.blk_addr != start_addr + off) { + f2fs_put_page(node_page, 1); + continue; + } + /* set page dirty and write it */ if (gc_type == FG_GC) { f2fs_wait_on_page_writeback(node_page, NODE); @@ -451,13 +470,11 @@ next_step: }; sync_node_pages(sbi, 0, &wbc); - /* - * In the case of FG_GC, it'd be better to reclaim this victim - * completely. - */ - if (get_valid_blocks(sbi, segno, 1) != 0) - goto next_step; + /* return 1 only if FG_GC succefully reclaimed one */ + if (get_valid_blocks(sbi, segno, 1) == 0) + return 1; } + return 0; } /* @@ -487,7 +504,7 @@ block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi) return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi); } -static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct node_info *dni, block_t blkaddr, unsigned int *nofs) { struct page *node_page; @@ -500,13 +517,13 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, node_page = get_node_page(sbi, nid); if (IS_ERR(node_page)) - return 0; + return false; get_node_info(sbi, nid, dni); if (sum->version != dni->version) { f2fs_put_page(node_page, 1); - return 0; + return false; } *nofs = ofs_of_node(node_page); @@ -514,16 +531,106 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, f2fs_put_page(node_page, 1); if (source_blkaddr != blkaddr) - return 0; - return 1; + return false; + return true; } -static void move_data_page(struct inode *inode, struct page *page, int gc_type) +static void move_encrypted_block(struct inode *inode, block_t bidx) { struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(inode), .type = DATA, - .rw = WRITE_SYNC, + .rw = READ_SYNC, + .encrypted_page = NULL, }; + struct dnode_of_data dn; + struct f2fs_summary sum; + struct node_info ni; + struct page *page; + int err; + + /* do not read out */ + page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); + if (!page) + return; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE); + if (err) + goto out; + + if (unlikely(dn.data_blkaddr == NULL_ADDR)) { + ClearPageUptodate(page); + goto put_out; + } + + /* + * don't cache encrypted data into meta inode until previous dirty + * data were writebacked to avoid racing between GC and flush. + */ + f2fs_wait_on_page_writeback(page, DATA); + + get_node_info(fio.sbi, dn.nid, &ni); + set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); + + /* read page */ + fio.page = page; + fio.blk_addr = dn.data_blkaddr; + + fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), + fio.blk_addr, + FGP_LOCK|FGP_CREAT, + GFP_NOFS); + if (!fio.encrypted_page) + goto put_out; + + err = f2fs_submit_page_bio(&fio); + if (err) + goto put_page_out; + + /* write page */ + lock_page(fio.encrypted_page); + + if (unlikely(!PageUptodate(fio.encrypted_page))) + goto put_page_out; + if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) + goto put_page_out; + + set_page_dirty(fio.encrypted_page); + f2fs_wait_on_page_writeback(fio.encrypted_page, DATA); + if (clear_page_dirty_for_io(fio.encrypted_page)) + dec_page_count(fio.sbi, F2FS_DIRTY_META); + + set_page_writeback(fio.encrypted_page); + + /* allocate block address */ + f2fs_wait_on_page_writeback(dn.node_page, NODE); + allocate_data_block(fio.sbi, NULL, fio.blk_addr, + &fio.blk_addr, &sum, CURSEG_COLD_DATA); + fio.rw = WRITE_SYNC; + f2fs_submit_page_mbio(&fio); + + dn.data_blkaddr = fio.blk_addr; + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + if (page->index == 0) + set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); +put_page_out: + f2fs_put_page(fio.encrypted_page, 1); +put_out: + f2fs_put_dnode(&dn); +out: + f2fs_put_page(page, 1); +} + +static void move_data_page(struct inode *inode, block_t bidx, int gc_type) +{ + struct page *page; + + page = get_lock_data_page(inode, bidx, true); + if (IS_ERR(page)) + return; if (gc_type == BG_GC) { if (PageWriteback(page)) @@ -531,12 +638,19 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type) set_page_dirty(page); set_cold_data(page); } else { + struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(inode), + .type = DATA, + .rw = WRITE_SYNC, + .page = page, + .encrypted_page = NULL, + }; + set_page_dirty(page); f2fs_wait_on_page_writeback(page, DATA); - if (clear_page_dirty_for_io(page)) inode_dec_dirty_pages(inode); set_cold_data(page); - do_write_data_page(page, &fio); + do_write_data_page(&fio); clear_cold_data(page); } out: @@ -550,7 +664,7 @@ out: * If the parent node is not valid or the data block address is different, * the victim data block is ignored. */ -static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct gc_inode_list *gc_list, unsigned int segno, int gc_type) { struct super_block *sb = sbi->sb; @@ -573,7 +687,7 @@ next_step: /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0)) - return; + return 0; if (check_valid_map(sbi, segno, off) == 0) continue; @@ -584,7 +698,7 @@ next_step: } /* Get an inode by ino with checking validity */ - if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0) + if (!is_alive(sbi, entry, &dni, start_addr + off, &nofs)) continue; if (phase == 1) { @@ -599,10 +713,16 @@ next_step: if (IS_ERR(inode) || is_bad_inode(inode)) continue; - start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + /* if encrypted inode, let's go phase 3 */ + if (f2fs_encrypted_inode(inode) && + S_ISREG(inode->i_mode)) { + add_gc_inode(gc_list, inode); + continue; + } - data_page = find_data_page(inode, - start_bidx + ofs_in_node, false); + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + data_page = get_read_data_page(inode, + start_bidx + ofs_in_node, READA, true); if (IS_ERR(data_page)) { iput(inode); continue; @@ -616,12 +736,12 @@ next_step: /* phase 3 */ inode = find_gc_inode(gc_list, dni.ino); if (inode) { - start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); - data_page = get_lock_data_page(inode, - start_bidx + ofs_in_node); - if (IS_ERR(data_page)) - continue; - move_data_page(inode, data_page, gc_type); + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)) + + ofs_in_node; + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + move_encrypted_block(inode, start_bidx); + else + move_data_page(inode, start_bidx, gc_type); stat_inc_data_blk_count(sbi, 1, gc_type); } } @@ -632,15 +752,11 @@ next_step: if (gc_type == FG_GC) { f2fs_submit_merged_bio(sbi, DATA, WRITE); - /* - * In the case of FG_GC, it'd be better to reclaim this victim - * completely. - */ - if (get_valid_blocks(sbi, segno, 1) != 0) { - phase = 2; - goto next_step; - } + /* return 1 only if FG_GC succefully reclaimed one */ + if (get_valid_blocks(sbi, segno, 1) == 0) + return 1; } + return 0; } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, @@ -656,12 +772,13 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, return ret; } -static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, +static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, struct gc_inode_list *gc_list, int gc_type) { struct page *sum_page; struct f2fs_summary_block *sum; struct blk_plug plug; + int nfree = 0; /* read segment summary of victim */ sum_page = get_sum_page(sbi, segno); @@ -670,12 +787,22 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, sum = page_address(sum_page); + /* + * this is to avoid deadlock: + * - lock_page(sum_page) - f2fs_replace_block + * - check_valid_map() - mutex_lock(sentry_lock) + * - mutex_lock(sentry_lock) - change_curseg() + * - lock_page(sum_page) + */ + unlock_page(sum_page); + switch (GET_SUM_TYPE((&sum->footer))) { case SUM_TYPE_NODE: - gc_node_segment(sbi, sum->entries, segno, gc_type); + nfree = gc_node_segment(sbi, sum->entries, segno, gc_type); break; case SUM_TYPE_DATA: - gc_data_segment(sbi, sum->entries, gc_list, segno, gc_type); + nfree = gc_data_segment(sbi, sum->entries, gc_list, + segno, gc_type); break; } blk_finish_plug(&plug); @@ -683,15 +810,16 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type); stat_inc_call_count(sbi->stat_info); - f2fs_put_page(sum_page, 1); + f2fs_put_page(sum_page, 0); + return nfree; } -int f2fs_gc(struct f2fs_sb_info *sbi) +int f2fs_gc(struct f2fs_sb_info *sbi, bool sync) { unsigned int segno, i; - int gc_type = BG_GC; - int nfree = 0; - int ret = -1; + int gc_type = sync ? FG_GC : BG_GC; + int sec_freed = 0; + int ret = -EINVAL; struct cp_control cpc; struct gc_inode_list gc_list = { .ilist = LIST_HEAD_INIT(gc_list.ilist), @@ -700,43 +828,58 @@ int f2fs_gc(struct f2fs_sb_info *sbi) cpc.reason = __get_cp_reason(sbi); gc_more: + segno = NULL_SEGNO; + if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) goto stop; if (unlikely(f2fs_cp_error(sbi))) goto stop; - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) { + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) { gc_type = FG_GC; - write_checkpoint(sbi, &cpc); + if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi)) + write_checkpoint(sbi, &cpc); } - if (!__get_victim(sbi, &segno, gc_type)) + if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type)) goto stop; ret = 0; /* readahead multi ssa blocks those have contiguous address */ if (sbi->segs_per_sec > 1) ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec, - META_SSA); + META_SSA, true); - for (i = 0; i < sbi->segs_per_sec; i++) - do_garbage_collect(sbi, segno + i, &gc_list, gc_type); - - if (gc_type == FG_GC) { - sbi->cur_victim_sec = NULL_SEGNO; - nfree++; - WARN_ON(get_valid_blocks(sbi, segno, sbi->segs_per_sec)); + for (i = 0; i < sbi->segs_per_sec; i++) { + /* + * for FG_GC case, halt gcing left segments once failed one + * of segments in selected section to avoid long latency. + */ + if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) && + gc_type == FG_GC) + break; } - if (has_not_enough_free_secs(sbi, nfree)) - goto gc_more; + if (i == sbi->segs_per_sec && gc_type == FG_GC) + sec_freed++; if (gc_type == FG_GC) - write_checkpoint(sbi, &cpc); + sbi->cur_victim_sec = NULL_SEGNO; + + if (!sync) { + if (has_not_enough_free_secs(sbi, sec_freed)) + goto gc_more; + + if (gc_type == FG_GC) + write_checkpoint(sbi, &cpc); + } stop: mutex_unlock(&sbi->gc_mutex); put_gc_inode(&gc_list); + + if (sync) + ret = sec_freed ? 0 : -EAGAIN; return ret; } diff --git a/kernel/fs/f2fs/hash.c b/kernel/fs/f2fs/hash.c index a844fcfb9..71b7206c4 100644 --- a/kernel/fs/f2fs/hash.c +++ b/kernel/fs/f2fs/hash.c @@ -79,8 +79,7 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info) const unsigned char *name = name_info->name; size_t len = name_info->len; - if ((len <= 2) && (name[0] == '.') && - (name[1] == '.' || name[1] == '\0')) + if (is_dot_dotdot(name_info)) return 0; /* Initialize the default seed for the hash checksum functions */ diff --git a/kernel/fs/f2fs/inline.c b/kernel/fs/f2fs/inline.c index 8140e4f0e..bda712646 100644 --- a/kernel/fs/f2fs/inline.c +++ b/kernel/fs/f2fs/inline.c @@ -12,8 +12,9 @@ #include <linux/f2fs_fs.h> #include "f2fs.h" +#include "node.h" -bool f2fs_may_inline(struct inode *inode) +bool f2fs_may_inline_data(struct inode *inode) { if (!test_opt(F2FS_I_SB(inode), INLINE_DATA)) return false; @@ -27,6 +28,20 @@ bool f2fs_may_inline(struct inode *inode) if (i_size_read(inode) > MAX_INLINE_DATA) return false; + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return false; + + return true; +} + +bool f2fs_may_inline_dentry(struct inode *inode) +{ + if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY)) + return false; + + if (!S_ISDIR(inode->i_mode)) + return false; + return true; } @@ -95,8 +110,11 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) { void *src_addr, *dst_addr; struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(dn->inode), .type = DATA, .rw = WRITE_SYNC | REQ_PRIO, + .page = page, + .encrypted_page = NULL, }; int dirty, err; @@ -124,13 +142,15 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) kunmap_atomic(dst_addr); SetPageUptodate(page); no_update: + set_page_dirty(page); + /* clear dirty state */ dirty = clear_page_dirty_for_io(page); /* write data page to try to make data consistent */ set_page_writeback(page); fio.blk_addr = dn->data_blkaddr; - write_data_page(page, dn, &fio); + write_data_page(dn, &fio); set_data_blkaddr(dn); f2fs_update_extent_cache(dn); f2fs_wait_on_page_writeback(page, DATA); @@ -255,35 +275,40 @@ process_inline: if (f2fs_has_inline_data(inode)) { ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - truncate_inline_inode(ipage, 0); + if (!truncate_inline_inode(ipage, 0)) + return false; f2fs_clear_inline_inode(inode); update_inode(inode, ipage); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - truncate_blocks(inode, 0, false); + if (truncate_blocks(inode, 0, false)) + return false; goto process_inline; } return false; } struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, - struct qstr *name, struct page **res_page) + struct f2fs_filename *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); struct f2fs_inline_dentry *inline_dentry; + struct qstr name = FSTR_TO_QSTR(&fname->disk_name); struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; struct page *ipage; + f2fs_hash_t namehash; ipage = get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return NULL; - inline_dentry = inline_data_addr(ipage); + namehash = f2fs_dentry_hash(&name); - make_dentry_ptr(&d, (void *)inline_dentry, 2); - de = find_target_dentry(name, NULL, &d); + inline_dentry = inline_data_addr(ipage); + make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2); + de = find_target_dentry(fname, namehash, NULL, &d); unlock_page(ipage); if (de) *res_page = ipage; @@ -325,7 +350,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, dentry_blk = inline_data_addr(ipage); - make_dentry_ptr(&d, (void *)dentry_blk, 2); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2); do_make_empty_dir(inode, parent, &d); set_page_dirty(ipage); @@ -338,6 +363,10 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, return 0; } +/* + * NOTE: ipage is grabbed by caller, but if any error occurs, we should + * release ipage in this function. + */ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, struct f2fs_inline_dentry *inline_dentry) { @@ -347,8 +376,10 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, int err; page = grab_cache_page(dir->i_mapping, 0); - if (!page) + if (!page) { + f2fs_put_page(ipage, 1); return -ENOMEM; + } set_new_dnode(&dn, dir, ipage, NULL, 0); err = f2fs_reserve_block(&dn, 0); @@ -356,13 +387,21 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, goto out; f2fs_wait_on_page_writeback(page, DATA); - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); dentry_blk = kmap_atomic(page); /* copy data from inline dentry block to new dentry block */ memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap, INLINE_DENTRY_BITMAP_SIZE); + memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0, + SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE); + /* + * we do not need to zero out remainder part of dentry and filename + * field, since we have used bitmap for marking the usage status of + * them, besides, we can also ignore copying/zeroing reserved space + * of dentry block, because them haven't been used so far. + */ memcpy(dentry_blk->dentry, inline_dentry->dentry, sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY); memcpy(dentry_blk->filename, inline_dentry->filename, @@ -412,8 +451,9 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, slots, NR_INLINE_DENTRY); if (bit_pos >= NR_INLINE_DENTRY) { err = f2fs_convert_inline_dir(dir, ipage, dentry_blk); - if (!err) - err = -EAGAIN; + if (err) + return err; + err = -EAGAIN; goto out; } @@ -429,7 +469,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, f2fs_wait_on_page_writeback(ipage, NODE); name_hash = f2fs_dentry_hash(name); - make_dentry_ptr(&d, (void *)dentry_blk, 2); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2); f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos); set_page_dirty(ipage); @@ -506,7 +546,8 @@ bool f2fs_empty_inline_dir(struct inode *dir) return true; } -int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx) +int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, + struct f2fs_str *fstr) { struct inode *inode = file_inode(file); struct f2fs_inline_dentry *inline_dentry = NULL; @@ -522,11 +563,46 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx) inline_dentry = inline_data_addr(ipage); - make_dentry_ptr(&d, (void *)inline_dentry, 2); + make_dentry_ptr(inode, &d, (void *)inline_dentry, 2); - if (!f2fs_fill_dentries(ctx, &d, 0)) + if (!f2fs_fill_dentries(ctx, &d, 0, fstr)) ctx->pos = NR_INLINE_DENTRY; f2fs_put_page(ipage, 1); return 0; } + +int f2fs_inline_data_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) +{ + __u64 byteaddr, ilen; + __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED | + FIEMAP_EXTENT_LAST; + struct node_info ni; + struct page *ipage; + int err = 0; + + ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + if (!f2fs_has_inline_data(inode)) { + err = -EAGAIN; + goto out; + } + + ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode)); + if (start >= ilen) + goto out; + if (start + len < ilen) + ilen = start + len; + ilen -= start; + + get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); + byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; + byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage); + err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags); +out: + f2fs_put_page(ipage, 1); + return err; +} diff --git a/kernel/fs/f2fs/inode.c b/kernel/fs/f2fs/inode.c index e622ec954..97e20deca 100644 --- a/kernel/fs/f2fs/inode.c +++ b/kernel/fs/f2fs/inode.c @@ -12,7 +12,6 @@ #include <linux/f2fs_fs.h> #include <linux/buffer_head.h> #include <linux/writeback.h> -#include <linux/bitops.h> #include "f2fs.h" #include "node.h" @@ -34,8 +33,8 @@ void f2fs_set_inode_flags(struct inode *inode) new_fl |= S_NOATIME; if (flags & FS_DIRSYNC_FL) new_fl |= S_DIRSYNC; - set_mask_bits(&inode->i_flags, - S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl); + inode_set_flags(inode, new_fl, + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); } static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) @@ -139,7 +138,7 @@ static int do_read_inode(struct inode *inode) fi->i_pino = le32_to_cpu(ri->i_pino); fi->i_dir_level = ri->i_dir_level; - f2fs_init_extent_cache(inode, &ri->i_ext); + f2fs_init_extent_tree(inode, &ri->i_ext); get_inline_info(fi, ri); @@ -155,6 +154,7 @@ static int do_read_inode(struct inode *inode) f2fs_put_page(node_page, 1); + stat_inc_inline_xattr(inode); stat_inc_inline_inode(inode); stat_inc_inline_dir(inode); @@ -198,7 +198,10 @@ make_now: inode->i_mapping->a_ops = &f2fs_dblock_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); } else if (S_ISLNK(inode->i_mode)) { - inode->i_op = &f2fs_symlink_inode_operations; + if (f2fs_encrypted_inode(inode)) + inode->i_op = &f2fs_encrypted_symlink_inode_operations; + else + inode->i_op = &f2fs_symlink_inode_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { @@ -234,10 +237,11 @@ void update_inode(struct inode *inode, struct page *node_page) ri->i_size = cpu_to_le64(i_size_read(inode)); ri->i_blocks = cpu_to_le64(inode->i_blocks); - read_lock(&F2FS_I(inode)->ext_lock); - set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext); - read_unlock(&F2FS_I(inode)->ext_lock); - + if (F2FS_I(inode)->extent_tree) + set_raw_extent(&F2FS_I(inode)->extent_tree->largest, + &ri->i_ext); + else + memset(&ri->i_ext, 0, sizeof(ri->i_ext)); set_raw_inline(F2FS_I(inode), ri); ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec); @@ -292,16 +296,12 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) return 0; /* - * We need to lock here to prevent from producing dirty node pages + * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. */ - f2fs_lock_op(sbi); update_inode_page(inode); - f2fs_unlock_op(sbi); - - if (wbc) - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi); return 0; } @@ -311,7 +311,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) void f2fs_evict_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - nid_t xnid = F2FS_I(inode)->i_xattr_nid; + struct f2fs_inode_info *fi = F2FS_I(inode); + nid_t xnid = fi->i_xattr_nid; + int err = 0; /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) @@ -327,38 +329,63 @@ void f2fs_evict_inode(struct inode *inode) f2fs_bug_on(sbi, get_dirty_pages(inode)); remove_dirty_dir_inode(inode); + f2fs_destroy_extent_tree(inode); + if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; sb_start_intwrite(inode->i_sb); - set_inode_flag(F2FS_I(inode), FI_NO_ALLOC); + set_inode_flag(fi, FI_NO_ALLOC); i_size_write(inode, 0); if (F2FS_HAS_BLOCKS(inode)) - f2fs_truncate(inode); + err = f2fs_truncate(inode, true); - f2fs_lock_op(sbi); - remove_inode_page(inode); - f2fs_unlock_op(sbi); + if (!err) { + f2fs_lock_op(sbi); + err = remove_inode_page(inode); + f2fs_unlock_op(sbi); + } sb_end_intwrite(inode->i_sb); no_delete: + stat_dec_inline_xattr(inode); stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); - /* update extent info in inode */ - if (inode->i_nlink) - f2fs_preserve_extent_tree(inode); - f2fs_destroy_extent_tree(inode); - invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino); if (xnid) invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); - if (is_inode_flag_set(F2FS_I(inode), FI_APPEND_WRITE)) + if (is_inode_flag_set(fi, FI_APPEND_WRITE)) add_dirty_inode(sbi, inode->i_ino, APPEND_INO); - if (is_inode_flag_set(F2FS_I(inode), FI_UPDATE_WRITE)) + if (is_inode_flag_set(fi, FI_UPDATE_WRITE)) add_dirty_inode(sbi, inode->i_ino, UPDATE_INO); + if (is_inode_flag_set(fi, FI_FREE_NID)) { + if (err && err != -ENOENT) + alloc_nid_done(sbi, inode->i_ino); + else + alloc_nid_failed(sbi, inode->i_ino); + clear_inode_flag(fi, FI_FREE_NID); + } + + if (err && err != -ENOENT) { + if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) { + /* + * get here because we failed to release resource + * of inode previously, reminder our user to run fsck + * for fixing. + */ + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "inode (ino:%lu) resource leak, run fsck " + "to fix this issue!", inode->i_ino); + } + } out_clear: +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (fi->i_crypt_info) + f2fs_free_encryption_info(inode, fi->i_crypt_info); +#endif clear_inode(inode); } @@ -366,6 +393,7 @@ out_clear: void handle_failed_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int err = 0; clear_nlink(inode); make_bad_inode(inode); @@ -373,13 +401,29 @@ void handle_failed_inode(struct inode *inode) i_size_write(inode, 0); if (F2FS_HAS_BLOCKS(inode)) - f2fs_truncate(inode); + err = f2fs_truncate(inode, false); + + if (!err) + err = remove_inode_page(inode); - remove_inode_page(inode); + /* + * if we skip truncate_node in remove_inode_page bacause we failed + * before, it's better to find another way to release resource of + * this inode (e.g. valid block count, node block or nid). Here we + * choose to add this inode to orphan list, so that we can call iput + * for releasing in orphan recovery flow. + * + * Note: we should add inode to orphan list before f2fs_unlock_op() + * so we can prevent losing this orphan when encoutering checkpoint + * and following suddenly power-off. + */ + if (err && err != -ENOENT) { + err = acquire_orphan_inode(sbi); + if (!err) + add_orphan_inode(sbi, inode->i_ino); + } - clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - clear_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); - alloc_nid_failed(sbi, inode->i_ino); + set_inode_flag(F2FS_I(inode), FI_FREE_NID); f2fs_unlock_op(sbi); /* iput will drop the inode object */ diff --git a/kernel/fs/f2fs/namei.c b/kernel/fs/f2fs/namei.c index 658e8079a..2c32110f9 100644 --- a/kernel/fs/f2fs/namei.c +++ b/kernel/fs/f2fs/namei.c @@ -53,27 +53,34 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) { err = -EINVAL; nid_free = true; - goto out; + goto fail; } - if (f2fs_may_inline(inode)) + /* If the directory encrypted, then we should encrypt the inode. */ + if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) + f2fs_set_encrypted_inode(inode); + + if (f2fs_may_inline_data(inode)) set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode)) + if (f2fs_may_inline_dentry(inode)) set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); + f2fs_init_extent_tree(inode, NULL); + + stat_inc_inline_xattr(inode); + stat_inc_inline_inode(inode); + stat_inc_inline_dir(inode); + trace_f2fs_new_inode(inode, 0); mark_inode_dirty(inode); return inode; -out: - clear_nlink(inode); - unlock_new_inode(inode); fail: trace_f2fs_new_inode(inode, err); make_bad_inode(inode); - iput(inode); if (nid_free) - alloc_nid_failed(sbi, ino); + set_inode_flag(F2FS_I(inode), FI_FREE_NID); + iput(inode); return ERR_PTR(err); } @@ -82,7 +89,14 @@ static int is_multimedia_file(const unsigned char *s, const char *sub) size_t slen = strlen(s); size_t sublen = strlen(sub); - if (sublen > slen) + /* + * filename format of multimedia file should be defined as: + * "filename + '.' + extension". + */ + if (slen < sublen + 2) + return 0; + + if (s[slen - sublen - 1] != '.') return 0; return !strncasecmp(s + slen - sublen, sub, sublen); @@ -136,7 +150,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, alloc_nid_done(sbi, ino); - stat_inc_inline_inode(inode); d_instantiate(dentry, inode); unlock_new_inode(inode); @@ -155,6 +168,10 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, struct f2fs_sb_info *sbi = F2FS_I_SB(dir); int err; + if (f2fs_encrypted_inode(dir) && + !f2fs_is_child_context_consistent_with_parent(dir, inode)) + return -EPERM; + f2fs_balance_fs(sbi); inode->i_ctime = CURRENT_TIME; @@ -232,32 +249,34 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, struct inode *inode = NULL; struct f2fs_dir_entry *de; struct page *page; + nid_t ino; + int err = 0; if (dentry->d_name.len > F2FS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); de = f2fs_find_entry(dir, &dentry->d_name, &page); - if (de) { - nid_t ino = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, page); - f2fs_put_page(page, 0); + if (!de) + return d_splice_alias(inode, dentry); - inode = f2fs_iget(dir->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); + ino = le32_to_cpu(de->ino); + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); - if (f2fs_has_inline_dots(inode)) { - int err; + inode = f2fs_iget(dir->i_sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); - err = __recover_dot_dentries(inode, dir->i_ino); - if (err) { - iget_failed(inode); - return ERR_PTR(err); - } - } + if (f2fs_has_inline_dots(inode)) { + err = __recover_dot_dentries(inode, dir->i_ino); + if (err) + goto err_out; } - return d_splice_alias(inode, dentry); + +err_out: + iget_failed(inode); + return ERR_PTR(err); } static int f2fs_unlink(struct inode *dir, struct dentry *dentry) @@ -296,19 +315,15 @@ fail: return err; } -static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd) +static const char *f2fs_follow_link(struct dentry *dentry, void **cookie) { - struct page *page = page_follow_link_light(dentry, nd); - - if (IS_ERR_OR_NULL(page)) - return page; - - /* this is broken symlink case */ - if (*nd_get_link(nd) == 0) { - page_put_link(dentry, nd, page); - return ERR_PTR(-ENOENT); + const char *link = page_follow_link_light(dentry, cookie); + if (!IS_ERR(link) && !*link) { + /* this is broken symlink case */ + page_put_link(NULL, *cookie); + link = ERR_PTR(-ENOENT); } - return page; + return link; } static int f2fs_symlink(struct inode *dir, struct dentry *dentry, @@ -316,16 +331,26 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; - size_t symlen = strlen(symname) + 1; + size_t len = strlen(symname); + size_t p_len; + char *p_str; + struct f2fs_str disk_link = FSTR_INIT(NULL, 0); + struct f2fs_encrypted_symlink_data *sd = NULL; int err; + if (len > dir->i_sb->s_blocksize) + return -ENAMETOOLONG; + f2fs_balance_fs(sbi); inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO); if (IS_ERR(inode)) return PTR_ERR(inode); - inode->i_op = &f2fs_symlink_inode_operations; + if (f2fs_encrypted_inode(inode)) + inode->i_op = &f2fs_encrypted_symlink_inode_operations; + else + inode->i_op = &f2fs_symlink_inode_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); @@ -333,10 +358,46 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (err) goto out; f2fs_unlock_op(sbi); - - err = page_symlink(inode, symname, symlen); alloc_nid_done(sbi, inode->i_ino); + if (f2fs_encrypted_inode(dir)) { + struct qstr istr = QSTR_INIT(symname, len); + + err = f2fs_get_encryption_info(inode); + if (err) + goto err_out; + + err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link); + if (err) + goto err_out; + + err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link); + if (err < 0) + goto err_out; + + p_len = encrypted_symlink_data_len(disk_link.len) + 1; + + if (p_len > dir->i_sb->s_blocksize) { + err = -ENAMETOOLONG; + goto err_out; + } + + sd = kzalloc(p_len, GFP_NOFS); + if (!sd) { + err = -ENOMEM; + goto err_out; + } + memcpy(sd->encrypted_path, disk_link.name, disk_link.len); + sd->len = cpu_to_le16(disk_link.len); + p_str = (char *)sd; + } else { + p_len = len + 1; + p_str = (char *)symname; + } + + err = page_symlink(inode, p_str, p_len); + +err_out: d_instantiate(dentry, inode); unlock_new_inode(inode); @@ -349,10 +410,17 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, * If the symlink path is stored into inline_data, there is no * performance regression. */ - filemap_write_and_wait_range(inode->i_mapping, 0, symlen - 1); + if (!err) { + filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1); - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + } else { + f2fs_unlink(dir, dentry); + } + + kfree(sd); + f2fs_fname_crypto_free_buffer(&disk_link); return err; out: handle_failed_inode(inode); @@ -383,7 +451,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; f2fs_unlock_op(sbi); - stat_inc_inline_dir(inode); alloc_nid_done(sbi, inode->i_ino); d_instantiate(dentry, inode); @@ -414,9 +481,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err = 0; - if (!new_valid_dev(rdev)) - return -EINVAL; - f2fs_balance_fs(sbi); inode = f2fs_new_inode(dir, mode); @@ -445,19 +509,101 @@ out: return err; } +static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, + umode_t mode, struct inode **whiteout) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + int err; + + if (!whiteout) + f2fs_balance_fs(sbi); + + inode = f2fs_new_inode(dir, mode); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + if (whiteout) { + init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); + inode->i_op = &f2fs_special_inode_operations; + } else { + inode->i_op = &f2fs_file_inode_operations; + inode->i_fop = &f2fs_file_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + } + + f2fs_lock_op(sbi); + err = acquire_orphan_inode(sbi); + if (err) + goto out; + + err = f2fs_do_tmpfile(inode, dir); + if (err) + goto release_out; + + /* + * add this non-linked tmpfile to orphan list, in this way we could + * remove all unused data of tmpfile after abnormal power-off. + */ + add_orphan_inode(sbi, inode->i_ino); + f2fs_unlock_op(sbi); + + alloc_nid_done(sbi, inode->i_ino); + + if (whiteout) { + inode_dec_link_count(inode); + *whiteout = inode; + } else { + d_tmpfile(dentry, inode); + } + unlock_new_inode(inode); + return 0; + +release_out: + release_orphan_inode(sbi); +out: + handle_failed_inode(inode); + return err; +} + +static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + if (f2fs_encrypted_inode(dir)) { + int err = f2fs_get_encryption_info(dir); + if (err) + return err; + } + + return __f2fs_tmpfile(dir, dentry, mode, NULL); +} + +static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout) +{ + return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout); +} + static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir); struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); + struct inode *whiteout = NULL; struct page *old_dir_page; - struct page *old_page, *new_page; + struct page *old_page, *new_page = NULL; struct f2fs_dir_entry *old_dir_entry = NULL; struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; int err = -ENOENT; + if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) && + !f2fs_is_child_context_consistent_with_parent(new_dir, + old_inode)) { + err = -EPERM; + goto out; + } + f2fs_balance_fs(sbi); old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); @@ -471,17 +617,23 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_old; } + if (flags & RENAME_WHITEOUT) { + err = f2fs_create_whiteout(old_dir, &whiteout); + if (err) + goto out_dir; + } + if (new_inode) { err = -ENOTEMPTY; if (old_dir_entry && !f2fs_empty_dir(new_inode)) - goto out_dir; + goto out_whiteout; err = -ENOENT; new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page); if (!new_entry) - goto out_dir; + goto out_whiteout; f2fs_lock_op(sbi); @@ -489,7 +641,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto put_out_dir; - if (update_dent_inode(old_inode, &new_dentry->d_name)) { + if (update_dent_inode(old_inode, new_inode, + &new_dentry->d_name)) { release_orphan_inode(sbi); goto put_out_dir; } @@ -518,7 +671,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, err = f2fs_add_link(new_dentry, old_inode); if (err) { f2fs_unlock_op(sbi); - goto out_dir; + goto out_whiteout; } if (old_dir_entry) { @@ -529,6 +682,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, down_write(&F2FS_I(old_inode)->i_sem); file_lost_pino(old_inode); + if (new_inode && file_enc_name(new_inode)) + file_set_enc_name(old_inode); up_write(&F2FS_I(old_inode)->i_sem); old_inode->i_ctime = CURRENT_TIME; @@ -536,8 +691,18 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_delete_entry(old_entry, old_page, old_dir, NULL); + if (whiteout) { + whiteout->i_state |= I_LINKABLE; + set_inode_flag(F2FS_I(whiteout), FI_INC_LINK); + err = f2fs_add_link(old_dentry, whiteout); + if (err) + goto put_out_dir; + whiteout->i_state &= ~I_LINKABLE; + iput(whiteout); + } + if (old_dir_entry) { - if (old_dir != new_dir) { + if (old_dir != new_dir && !whiteout) { f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); update_inode_page(old_inode); @@ -558,8 +723,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, put_out_dir: f2fs_unlock_op(sbi); - f2fs_dentry_kunmap(new_dir, new_page); - f2fs_put_page(new_page, 0); + if (new_page) { + f2fs_dentry_kunmap(new_dir, new_page); + f2fs_put_page(new_page, 0); + } +out_whiteout: + if (whiteout) + iput(whiteout); out_dir: if (old_dir_entry) { f2fs_dentry_kunmap(old_inode, old_dir_page); @@ -585,6 +755,14 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, int old_nlink = 0, new_nlink = 0; int err = -ENOENT; + if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) && + (old_dir != new_dir) && + (!f2fs_is_child_context_consistent_with_parent(new_dir, + old_inode) || + !f2fs_is_child_context_consistent_with_parent(old_dir, + new_inode))) + return -EPERM; + f2fs_balance_fs(sbi); old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); @@ -631,13 +809,17 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_lock_op(sbi); - err = update_dent_inode(old_inode, &new_dentry->d_name); + err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name); if (err) goto out_unlock; + if (file_enc_name(new_inode)) + file_set_enc_name(old_inode); - err = update_dent_inode(new_inode, &old_dentry->d_name); + err = update_dent_inode(new_inode, old_inode, &old_dentry->d_name); if (err) goto out_undo; + if (file_enc_name(old_inode)) + file_set_enc_name(new_inode); /* update ".." directory entry info of old dentry */ if (old_dir_entry) @@ -695,8 +877,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_sync_fs(sbi->sb, 1); return 0; out_undo: - /* Still we may fail to recover name info of f2fs_inode here */ - update_dent_inode(old_inode, &old_dentry->d_name); + /* + * Still we may fail to recover name info of f2fs_inode here + * Drop it, once its name is set as encrypted + */ + update_dent_inode(old_inode, old_inode, &old_dentry->d_name); out_unlock: f2fs_unlock_op(sbi); out_new_dir: @@ -723,7 +908,7 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) { @@ -734,53 +919,93 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, * VFS has already handled the new dentry existence case, * here, we just deal with "RENAME_NOREPLACE" as regular rename. */ - return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry); + return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } -static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +#ifdef CONFIG_F2FS_FS_ENCRYPTION +static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie) { - struct f2fs_sb_info *sbi = F2FS_I_SB(dir); - struct inode *inode; - int err; - - inode = f2fs_new_inode(dir, mode); - if (IS_ERR(inode)) - return PTR_ERR(inode); - - inode->i_op = &f2fs_file_inode_operations; - inode->i_fop = &f2fs_file_operations; - inode->i_mapping->a_ops = &f2fs_dblock_aops; - - f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); - if (err) - goto out; - - err = f2fs_do_tmpfile(inode, dir); - if (err) - goto release_out; - - /* - * add this non-linked tmpfile to orphan list, in this way we could - * remove all unused data of tmpfile after abnormal power-off. - */ - add_orphan_inode(sbi, inode->i_ino); - f2fs_unlock_op(sbi); - - alloc_nid_done(sbi, inode->i_ino); + struct page *cpage = NULL; + char *caddr, *paddr = NULL; + struct f2fs_str cstr; + struct f2fs_str pstr = FSTR_INIT(NULL, 0); + struct inode *inode = d_inode(dentry); + struct f2fs_encrypted_symlink_data *sd; + loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); + u32 max_size = inode->i_sb->s_blocksize; + int res; + + res = f2fs_get_encryption_info(inode); + if (res) + return ERR_PTR(res); + + cpage = read_mapping_page(inode->i_mapping, 0, NULL); + if (IS_ERR(cpage)) + return ERR_CAST(cpage); + caddr = kmap(cpage); + caddr[size] = 0; + + /* Symlink is encrypted */ + sd = (struct f2fs_encrypted_symlink_data *)caddr; + cstr.len = le16_to_cpu(sd->len); + cstr.name = kmalloc(cstr.len, GFP_NOFS); + if (!cstr.name) { + res = -ENOMEM; + goto errout; + } + memcpy(cstr.name, sd->encrypted_path, cstr.len); - stat_inc_inline_inode(inode); - d_tmpfile(dentry, inode); - unlock_new_inode(inode); - return 0; + /* this is broken symlink case */ + if (cstr.name[0] == 0 && cstr.len == 0) { + res = -ENOENT; + goto errout; + } -release_out: - release_orphan_inode(sbi); -out: - handle_failed_inode(inode); - return err; + if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) > + max_size) { + /* Symlink data on the disk is corrupted */ + res = -EIO; + goto errout; + } + res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr); + if (res) + goto errout; + + res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr); + if (res < 0) + goto errout; + + kfree(cstr.name); + + paddr = pstr.name; + + /* Null-terminate the name */ + paddr[res] = '\0'; + + kunmap(cpage); + page_cache_release(cpage); + return *cookie = paddr; +errout: + kfree(cstr.name); + f2fs_fname_crypto_free_buffer(&pstr); + kunmap(cpage); + page_cache_release(cpage); + return ERR_PTR(res); } +const struct inode_operations f2fs_encrypted_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = f2fs_encrypted_follow_link, + .put_link = kfree_put_link, + .getattr = f2fs_getattr, + .setattr = f2fs_setattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +}; +#endif + const struct inode_operations f2fs_dir_inode_operations = { .create = f2fs_create, .lookup = f2fs_lookup, diff --git a/kernel/fs/f2fs/node.c b/kernel/fs/f2fs/node.c index 8ab0cf193..7bcbc6e9c 100644 --- a/kernel/fs/f2fs/node.c +++ b/kernel/fs/f2fs/node.c @@ -53,7 +53,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == DIRTY_DENTS) { - if (sbi->sb->s_bdi->dirty_exceeded) + if (sbi->sb->s_bdi->wb.dirty_exceeded) return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); @@ -70,7 +70,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { - if (sbi->sb->s_bdi->dirty_exceeded) + if (sbi->sb->s_bdi->wb.dirty_exceeded) return false; } return res; @@ -159,7 +159,7 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, head = radix_tree_lookup(&nm_i->nat_set_root, set); if (!head) { - head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC); + head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS); INIT_LIST_HEAD(&head->entry_list); INIT_LIST_HEAD(&head->set_list); @@ -195,32 +195,35 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, start, nr); } -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - bool is_cp = true; + bool need = false; down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); - if (e && !get_nat_flag(e, IS_CHECKPOINTED)) - is_cp = false; + if (e) { + if (!get_nat_flag(e, IS_CHECKPOINTED) && + !get_nat_flag(e, HAS_FSYNCED_INODE)) + need = true; + } up_read(&nm_i->nat_tree_lock); - return is_cp; + return need; } -bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino) +bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - bool fsynced = false; + bool is_cp = true; down_read(&nm_i->nat_tree_lock); - e = __lookup_nat_cache(nm_i, ino); - if (e && get_nat_flag(e, HAS_FSYNCED_INODE)) - fsynced = true; + e = __lookup_nat_cache(nm_i, nid); + if (e && !get_nat_flag(e, IS_CHECKPOINTED)) + is_cp = false; up_read(&nm_i->nat_tree_lock); - return fsynced; + return is_cp; } bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) @@ -243,7 +246,7 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) { struct nat_entry *new; - new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC); + new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS); f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); memset(new, 0, sizeof(struct nat_entry)); nat_set_nid(new, nid); @@ -303,6 +306,10 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) { unsigned char version = nat_get_version(e); nat_set_version(e, inc_node_version(version)); + + /* in order to reuse the nid */ + if (nm_i->next_scan_nid > ni->nid) + nm_i->next_scan_nid = ni->nid; } /* change address */ @@ -312,7 +319,8 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, __set_nat_cache_dirty(nm_i, e); /* update fsync_mark if its inode nat entry is still alive */ - e = __lookup_nat_cache(nm_i, ni->ino); + if (ni->nid != ni->ino) + e = __lookup_nat_cache(nm_i, ni->ino); if (e) { if (fsync_done && ni->nid == ni->ino) set_nat_flag(e, HAS_FSYNCED_INODE, true); @@ -324,11 +332,11 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); + int nr = nr_shrink; - if (available_free_memory(sbi, NAT_ENTRIES)) + if (!down_write_trylock(&nm_i->nat_tree_lock)) return 0; - down_write(&nm_i->nat_tree_lock); while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; ne = list_first_entry(&nm_i->nat_entries, @@ -337,7 +345,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) nr_shrink--; } up_write(&nm_i->nat_tree_lock); - return nr_shrink; + return nr - nr_shrink; } /* @@ -894,17 +902,20 @@ int truncate_xattr_node(struct inode *inode, struct page *page) * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ -void remove_inode_page(struct inode *inode) +int remove_inode_page(struct inode *inode) { struct dnode_of_data dn; + int err; set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); - if (get_dnode_of_data(&dn, 0, LOOKUP_NODE)) - return; + err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + if (err) + return err; - if (truncate_xattr_node(inode, dn.inode_page)) { + err = truncate_xattr_node(inode, dn.inode_page); + if (err) { f2fs_put_dnode(&dn); - return; + return err; } /* remove potential inline_data blocks */ @@ -918,6 +929,7 @@ void remove_inode_page(struct inode *inode) /* will put inode & node pages */ truncate_node(&dn); + return 0; } struct page *new_inode_page(struct inode *inode) @@ -987,23 +999,24 @@ fail: /* * Caller should do after getting the following values. * 0: f2fs_put_page(page, 0) - * LOCKED_PAGE: f2fs_put_page(page, 1) - * error: nothing + * LOCKED_PAGE or error: f2fs_put_page(page, 1) */ static int read_node_page(struct page *page, int rw) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); struct node_info ni; struct f2fs_io_info fio = { + .sbi = sbi, .type = NODE, .rw = rw, + .page = page, + .encrypted_page = NULL, }; get_node_info(sbi, page->index, &ni); if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); - f2fs_put_page(page, 1); return -ENOENT; } @@ -1011,7 +1024,7 @@ static int read_node_page(struct page *page, int rw) return LOCKED_PAGE; fio.blk_addr = ni.blk_addr; - return f2fs_submit_page_bio(sbi, page, &fio); + return f2fs_submit_page_bio(&fio); } /* @@ -1034,10 +1047,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) return; err = read_node_page(apage, READA); - if (err == 0) - f2fs_put_page(apage, 0); - else if (err == LOCKED_PAGE) - f2fs_put_page(apage, 1); + f2fs_put_page(apage, err ? 1 : 0); } struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) @@ -1050,10 +1060,12 @@ repeat: return ERR_PTR(-ENOMEM); err = read_node_page(page, READ_SYNC); - if (err < 0) + if (err < 0) { + f2fs_put_page(page, 1); return ERR_PTR(err); - else if (err != LOCKED_PAGE) + } else if (err != LOCKED_PAGE) { lock_page(page); + } if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) { ClearPageUptodate(page); @@ -1089,10 +1101,12 @@ repeat: return ERR_PTR(-ENOMEM); err = read_node_page(page, READ_SYNC); - if (err < 0) + if (err < 0) { + f2fs_put_page(page, 1); return ERR_PTR(err); - else if (err == LOCKED_PAGE) + } else if (err == LOCKED_PAGE) { goto page_hit; + } blk_start_plug(&plug); @@ -1204,13 +1218,9 @@ continue_unlock: /* called by fsync() */ if (ino && IS_DNODE(page)) { set_fsync_mark(page, 1); - if (IS_INODE(page)) { - if (!is_checkpointed_node(sbi, ino) && - !has_fsynced_inode(sbi, ino)) - set_dentry_mark(page, 1); - else - set_dentry_mark(page, 0); - } + if (IS_INODE(page)) + set_dentry_mark(page, + need_dentry_mark(sbi, ino)); nwritten++; } else { set_fsync_mark(page, 0); @@ -1293,8 +1303,11 @@ static int f2fs_write_node_page(struct page *page, nid_t nid; struct node_info ni; struct f2fs_io_info fio = { + .sbi = sbi, .type = NODE, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, + .page = page, + .encrypted_page = NULL, }; trace_f2fs_writepage(page, NODE); @@ -1310,26 +1323,27 @@ static int f2fs_write_node_page(struct page *page, nid = nid_of_node(page); f2fs_bug_on(sbi, page->index != nid); + if (wbc->for_reclaim) { + if (!down_read_trylock(&sbi->node_write)) + goto redirty_out; + } else { + down_read(&sbi->node_write); + } + get_node_info(sbi, nid, &ni); /* This page is already truncated */ if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); dec_page_count(sbi, F2FS_DIRTY_NODES); + up_read(&sbi->node_write); unlock_page(page); return 0; } - if (wbc->for_reclaim) { - if (!down_read_trylock(&sbi->node_write)) - goto redirty_out; - } else { - down_read(&sbi->node_write); - } - set_page_writeback(page); fio.blk_addr = ni.blk_addr; - write_node_page(sbi, page, nid, &fio); + write_node_page(nid, &fio); set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); @@ -1515,7 +1529,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi) return; /* readahead nat pages to be scanned */ - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT); + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, + META_NAT, true); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1527,7 +1542,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi) if (unlikely(nid >= nm_i->max_nid)) nid = 0; - if (i++ == FREE_NID_PAGES) + if (++i >= FREE_NID_PAGES) break; } @@ -1545,6 +1560,9 @@ static void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } mutex_unlock(&curseg->curseg_mutex); + + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), + nm_i->ra_nid_pages, META_NAT, false); } /* @@ -1564,6 +1582,8 @@ retry: /* We should not use stale free nids created by build_free_nids */ if (nm_i->fcnt && !on_build_free_nids(nm_i)) { + struct node_info ni; + f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); list_for_each_entry(i, &nm_i->free_nid_list, list) if (i->state == NID_NEW) @@ -1574,6 +1594,13 @@ retry: i->state = NID_ALLOC; nm_i->fcnt--; spin_unlock(&nm_i->free_nid_list_lock); + + /* check nid is allocated already */ + get_node_info(sbi, *nid, &ni); + if (ni.blk_addr != NULL_ADDR) { + alloc_nid_done(sbi, *nid); + goto retry; + } return true; } spin_unlock(&nm_i->free_nid_list_lock); @@ -1630,6 +1657,32 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) kmem_cache_free(free_nid_slab, i); } +int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i, *next; + int nr = nr_shrink; + + if (!mutex_trylock(&nm_i->build_lock)) + return 0; + + spin_lock(&nm_i->free_nid_list_lock); + list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) { + if (nr_shrink <= 0 || nm_i->fcnt <= NAT_ENTRY_PER_BLOCK) + break; + if (i->state == NID_ALLOC) + continue; + __del_from_free_nid_list(nm_i, i); + kmem_cache_free(free_nid_slab, i); + nm_i->fcnt--; + nr_shrink--; + } + spin_unlock(&nm_i->free_nid_list_lock); + mutex_unlock(&nm_i->build_lock); + + return nr - nr_shrink; +} + void recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; @@ -1755,10 +1808,10 @@ int restore_node_summary(struct f2fs_sb_info *sbi, nrpages = min(last_offset - i, bio_blocks); /* readahead node pages */ - ra_meta_pages(sbi, addr, nrpages, META_POR); + ra_meta_pages(sbi, addr, nrpages, META_POR, true); for (idx = addr; idx < addr + nrpages; idx++) { - struct page *page = get_meta_page(sbi, idx); + struct page *page = get_tmp_page(sbi, idx); rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; @@ -1952,6 +2005,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) nm_i->fcnt = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; + nm_i->ra_nid_pages = DEF_RA_NID_PAGES; INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); INIT_LIST_HEAD(&nm_i->free_nid_list); diff --git a/kernel/fs/f2fs/node.h b/kernel/fs/f2fs/node.h index c56026f17..e4fffd2d9 100644 --- a/kernel/fs/f2fs/node.h +++ b/kernel/fs/f2fs/node.h @@ -14,9 +14,11 @@ /* node block offset on the NAT area dedicated to the given start node id */ #define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK) -/* # of pages to perform readahead before building free nids */ +/* # of pages to perform synchronous readahead before building free nids */ #define FREE_NID_PAGES 4 +#define DEF_RA_NID_PAGES 4 /* # of nid pages to be readaheaded */ + /* maximum readahead size for node during getting data blocks */ #define MAX_RA_NODE 128 @@ -343,28 +345,6 @@ static inline nid_t get_nid(struct page *p, int off, bool i) * - Mark cold node blocks in their node footer * - Mark cold data pages in page cache */ -static inline int is_file(struct inode *inode, int type) -{ - return F2FS_I(inode)->i_advise & type; -} - -static inline void set_file(struct inode *inode, int type) -{ - F2FS_I(inode)->i_advise |= type; -} - -static inline void clear_file(struct inode *inode, int type) -{ - F2FS_I(inode)->i_advise &= ~type; -} - -#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) -#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) -#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) -#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) -#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) -#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) - static inline int is_cold_data(struct page *page) { return PageChecked(page); diff --git a/kernel/fs/f2fs/recovery.c b/kernel/fs/f2fs/recovery.c index 8d8ea99f2..cbf74f47c 100644 --- a/kernel/fs/f2fs/recovery.c +++ b/kernel/fs/f2fs/recovery.c @@ -83,6 +83,11 @@ static int recover_dentry(struct inode *inode, struct page *ipage) goto out; } + if (file_enc_name(inode)) { + iput(dir); + return 0; + } + name.len = le32_to_cpu(raw_inode->i_namelen); name.name = raw_inode->i_name; @@ -143,6 +148,7 @@ out: static void recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); + char *name; inode->i_mode = le16_to_cpu(raw->i_mode); i_size_write(inode, le64_to_cpu(raw->i_size)); @@ -153,8 +159,13 @@ static void recover_inode(struct inode *inode, struct page *page) inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + if (file_enc_name(inode)) + name = "<encrypted>"; + else + name = F2FS_INODE(page)->i_name; + f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s", - ino_of_node(page), F2FS_INODE(page)->i_name); + ino_of_node(page), name); } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) @@ -169,15 +180,15 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); - ra_meta_pages(sbi, blkaddr, 1, META_POR); + ra_meta_pages(sbi, blkaddr, 1, META_POR, true); while (1) { struct fsync_inode_entry *entry; - if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) + if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) return 0; - page = get_meta_page(sbi, blkaddr); + page = get_tmp_page(sbi, blkaddr); if (cp_ver != cpver_of_node(page)) break; @@ -349,7 +360,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int start, end; struct dnode_of_data dn; - struct f2fs_summary sum; struct node_info ni; int err = 0, recovered = 0; @@ -373,15 +383,11 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, start = start_bidx_of_node(ofs_of_node(page), fi); end = start + ADDRS_PER_PAGE(page, fi); - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, start, ALLOC_NODE); - if (err) { - f2fs_unlock_op(sbi); + if (err) goto out; - } f2fs_wait_on_page_writeback(dn.node_page, NODE); @@ -389,14 +395,35 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page)); - for (; start < end; start++) { + for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; src = datablock_addr(dn.node_page, dn.ofs_in_node); dest = datablock_addr(page, dn.ofs_in_node); - if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR && - dest >= MAIN_BLKADDR(sbi) && dest < MAX_BLKADDR(sbi)) { + /* skip recovering if dest is the same as src */ + if (src == dest) + continue; + + /* dest is invalid, just invalidate src block */ + if (dest == NULL_ADDR) { + truncate_data_blocks_range(&dn, 1); + continue; + } + + /* + * dest is reserved block, invalidate src block + * and then reserve one new block in dnode page. + */ + if (dest == NEW_ADDR) { + truncate_data_blocks_range(&dn, 1); + err = reserve_new_block(&dn); + f2fs_bug_on(sbi, err); + continue; + } + + /* dest is valid block, try to recover from src to dest */ + if (is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { err = reserve_new_block(&dn); @@ -409,16 +436,11 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, if (err) goto err; - set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); - /* write dummy data page */ - recover_data_page(sbi, NULL, &sum, src, dest); - dn.data_blkaddr = dest; - set_data_blkaddr(&dn); - f2fs_update_extent_cache(&dn); + f2fs_replace_block(sbi, &dn, src, dest, + ni.version, false); recovered++; } - dn.ofs_in_node++; } if (IS_INODE(dn.node_page)) @@ -430,7 +452,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, set_page_dirty(dn.node_page); err: f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); out: f2fs_msg(sbi->sb, KERN_NOTICE, "recover_data: ino = %lx, recovered = %d blocks, err = %d", @@ -454,12 +475,12 @@ static int recover_data(struct f2fs_sb_info *sbi, while (1) { struct fsync_inode_entry *entry; - if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) + if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) break; ra_meta_pages_cond(sbi, blkaddr); - page = get_meta_page(sbi, blkaddr); + page = get_tmp_page(sbi, blkaddr); if (cp_ver != cpver_of_node(page)) { f2fs_put_page(page, 1); @@ -519,14 +540,12 @@ int recover_fsync_data(struct f2fs_sb_info *sbi) INIT_LIST_HEAD(&inode_list); - /* step #1: find fsynced inode numbers */ - set_sbi_flag(sbi, SBI_POR_DOING); - /* prevent checkpoint */ mutex_lock(&sbi->cp_mutex); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + /* step #1: find fsynced inode numbers */ err = find_fsync_dnodes(sbi, &inode_list); if (err) goto out; @@ -546,7 +565,7 @@ out: /* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), - MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); + (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); @@ -555,11 +574,20 @@ out: clear_sbi_flag(sbi, SBI_POR_DOING); if (err) { - discard_next_dnode(sbi, blkaddr); + bool invalidate = false; + + if (discard_next_dnode(sbi, blkaddr)) + invalidate = true; /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) sync_meta_pages(sbi, META, LONG_MAX); + + /* invalidate temporary meta page */ + if (invalidate) + invalidate_mapping_pages(META_MAPPING(sbi), + blkaddr, blkaddr); + set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); mutex_unlock(&sbi->cp_mutex); } else if (need_writecp) { diff --git a/kernel/fs/f2fs/segment.c b/kernel/fs/f2fs/segment.c index f93966094..f77b32584 100644 --- a/kernel/fs/f2fs/segment.c +++ b/kernel/fs/f2fs/segment.c @@ -14,8 +14,8 @@ #include <linux/blkdev.h> #include <linux/prefetch.h> #include <linux/kthread.h> -#include <linux/vmalloc.h> #include <linux/swap.h> +#include <linux/timer.h> #include "f2fs.h" #include "segment.h" @@ -29,6 +29,21 @@ static struct kmem_cache *discard_entry_slab; static struct kmem_cache *sit_entry_set_slab; static struct kmem_cache *inmem_entry_slab; +static unsigned long __reverse_ulong(unsigned char *str) +{ + unsigned long tmp = 0; + int shift = 24, idx = 0; + +#if BITS_PER_LONG == 64 + shift = 56; +#endif + while (shift >= 0) { + tmp |= (unsigned long)str[idx++] << shift; + shift -= BITS_PER_BYTE; + } + return tmp; +} + /* * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since * MSB and LSB are reversed in a byte by f2fs_set_bit. @@ -38,27 +53,31 @@ static inline unsigned long __reverse_ffs(unsigned long word) int num = 0; #if BITS_PER_LONG == 64 - if ((word & 0xffffffff) == 0) { + if ((word & 0xffffffff00000000UL) == 0) num += 32; + else word >>= 32; - } #endif - if ((word & 0xffff) == 0) { + if ((word & 0xffff0000) == 0) num += 16; + else word >>= 16; - } - if ((word & 0xff) == 0) { + + if ((word & 0xff00) == 0) num += 8; + else word >>= 8; - } + if ((word & 0xf0) == 0) num += 4; else word >>= 4; + if ((word & 0xc) == 0) num += 2; else word >>= 2; + if ((word & 0x2) == 0) num += 1; return num; @@ -68,9 +87,9 @@ static inline unsigned long __reverse_ffs(unsigned long word) * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because * f2fs_set_bit makes MSB and LSB reversed in a byte. * Example: - * LSB <--> MSB - * f2fs_set_bit(0, bitmap) => 0000 0001 - * f2fs_set_bit(7, bitmap) => 1000 0000 + * MSB <--> LSB + * f2fs_set_bit(0, bitmap) => 1000 0000 + * f2fs_set_bit(7, bitmap) => 0000 0001 */ static unsigned long __find_rev_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) @@ -78,8 +97,6 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG - 1); unsigned long tmp; - unsigned long mask, submask; - unsigned long quot, rest; if (offset >= size) return size; @@ -89,14 +106,9 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, if (!offset) goto aligned; - tmp = *(p++); - quot = (offset >> 3) << 3; - rest = offset & 0x7; - mask = ~0UL << quot; - submask = (unsigned char)(0xff << rest) >> rest; - submask <<= quot; - mask &= submask; - tmp &= mask; + tmp = __reverse_ulong((unsigned char *)p); + tmp &= ~0UL >> offset; + if (size < BITS_PER_LONG) goto found_first; if (tmp) @@ -104,20 +116,23 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, size -= BITS_PER_LONG; result += BITS_PER_LONG; + p++; aligned: while (size & ~(BITS_PER_LONG-1)) { - tmp = *(p++); + tmp = __reverse_ulong((unsigned char *)p); if (tmp) goto found_middle; result += BITS_PER_LONG; size -= BITS_PER_LONG; + p++; } if (!size) return result; - tmp = *p; + + tmp = __reverse_ulong((unsigned char *)p); found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ + tmp &= (~0UL << (BITS_PER_LONG - size)); + if (!tmp) /* Are any bits set? */ return result + size; /* Nope. */ found_middle: return result + __reverse_ffs(tmp); @@ -129,8 +144,6 @@ static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG - 1); unsigned long tmp; - unsigned long mask, submask; - unsigned long quot, rest; if (offset >= size) return size; @@ -140,36 +153,33 @@ static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, if (!offset) goto aligned; - tmp = *(p++); - quot = (offset >> 3) << 3; - rest = offset & 0x7; - mask = ~(~0UL << quot); - submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest); - submask <<= quot; - mask += submask; - tmp |= mask; + tmp = __reverse_ulong((unsigned char *)p); + tmp |= ~((~0UL << offset) >> offset); + if (size < BITS_PER_LONG) goto found_first; - if (~tmp) + if (tmp != ~0UL) goto found_middle; size -= BITS_PER_LONG; result += BITS_PER_LONG; + p++; aligned: while (size & ~(BITS_PER_LONG - 1)) { - tmp = *(p++); - if (~tmp) + tmp = __reverse_ulong((unsigned char *)p); + if (tmp != ~0UL) goto found_middle; result += BITS_PER_LONG; size -= BITS_PER_LONG; + p++; } if (!size) return result; - tmp = *p; + tmp = __reverse_ulong((unsigned char *)p); found_first: - tmp |= ~0UL << size; - if (tmp == ~0UL) /* Are any bits zero? */ + tmp |= ~(~0UL << (BITS_PER_LONG - size)); + if (tmp == ~0UL) /* Are any bits zero? */ return result + size; /* Nope. */ found_middle: return result + __reverse_ffz(tmp); @@ -179,28 +189,20 @@ void register_inmem_page(struct inode *inode, struct page *page) { struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *new; - int err; - SetPagePrivate(page); f2fs_trace_pid(page); + set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); + SetPagePrivate(page); + new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); /* add atomic page indices to the list */ new->page = page; INIT_LIST_HEAD(&new->list); -retry: + /* increase reference count with clean state */ mutex_lock(&fi->inmem_lock); - err = radix_tree_insert(&fi->inmem_root, page->index, new); - if (err == -EEXIST) { - mutex_unlock(&fi->inmem_lock); - kmem_cache_free(inmem_entry_slab, new); - return; - } else if (err) { - mutex_unlock(&fi->inmem_lock); - goto retry; - } get_page(page); list_add_tail(&new->list, &fi->inmem_pages); inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); @@ -209,16 +211,19 @@ retry: trace_f2fs_register_inmem_page(page, INMEM); } -void commit_inmem_pages(struct inode *inode, bool abort) +int commit_inmem_pages(struct inode *inode, bool abort) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *cur, *tmp; bool submit_bio = false; struct f2fs_io_info fio = { + .sbi = sbi, .type = DATA, .rw = WRITE_SYNC | REQ_PRIO, + .encrypted_page = NULL, }; + int err = 0; /* * The abort is true only when f2fs_evict_inode is called. @@ -234,22 +239,30 @@ void commit_inmem_pages(struct inode *inode, bool abort) mutex_lock(&fi->inmem_lock); list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) { + lock_page(cur->page); if (!abort) { - lock_page(cur->page); if (cur->page->mapping == inode->i_mapping) { + set_page_dirty(cur->page); f2fs_wait_on_page_writeback(cur->page, DATA); if (clear_page_dirty_for_io(cur->page)) inode_dec_dirty_pages(inode); trace_f2fs_commit_inmem_page(cur->page, INMEM); - do_write_data_page(cur->page, &fio); + fio.page = cur->page; + err = do_write_data_page(&fio); + if (err) { + unlock_page(cur->page); + break; + } + clear_cold_data(cur->page); submit_bio = true; } - f2fs_put_page(cur->page, 1); } else { trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP); - put_page(cur->page); } - radix_tree_delete(&fi->inmem_root, cur->page->index); + set_page_private(cur->page, 0); + ClearPagePrivate(cur->page); + f2fs_put_page(cur->page, 1); + list_del(&cur->list); kmem_cache_free(inmem_entry_slab, cur); dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); @@ -261,6 +274,7 @@ void commit_inmem_pages(struct inode *inode, bool abort) if (submit_bio) f2fs_submit_merged_bio(sbi, DATA, WRITE); } + return err; } /* @@ -275,19 +289,28 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi) */ if (has_not_enough_free_secs(sbi, 0)) { mutex_lock(&sbi->gc_mutex); - f2fs_gc(sbi); + f2fs_gc(sbi, false); } } void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) { /* try to shrink extent cache when there is no enough memory */ - f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); + if (!available_free_memory(sbi, EXTENT_CACHE)) + f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); + + /* check the # of cached NAT entries */ + if (!available_free_memory(sbi, NAT_ENTRIES)) + try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); + + if (!available_free_memory(sbi, FREE_NIDS)) + try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES); - /* check the # of cached NAT entries and prefree segments */ - if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) || + /* checkpoint is the only way to shrink partial cached entries */ + if (!available_free_memory(sbi, NAT_ENTRIES) || excess_prefree_segs(sbi) || - !available_free_memory(sbi, INO_ENTRIES)) + !available_free_memory(sbi, INO_ENTRIES) || + jiffies > sbi->cp_expires) f2fs_sync_fs(sbi->sb, true); } @@ -301,10 +324,12 @@ repeat: return 0; if (!llist_empty(&fcc->issue_list)) { - struct bio *bio = bio_alloc(GFP_NOIO, 0); + struct bio *bio; struct flush_cmd *cmd, *next; int ret; + bio = f2fs_bio_alloc(0); + fcc->dispatch_list = llist_del_all(&fcc->issue_list); fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list); @@ -336,8 +361,15 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) if (test_opt(sbi, NOBARRIER)) return 0; - if (!test_opt(sbi, FLUSH_MERGE)) - return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL); + if (!test_opt(sbi, FLUSH_MERGE)) { + struct bio *bio = f2fs_bio_alloc(0); + int ret; + + bio->bi_bdev = sbi->sb->s_bdev; + ret = submit_bio_wait(WRITE_FLUSH, bio); + bio_put(bio); + return ret; + } init_completion(&cmd.wait); @@ -466,22 +498,46 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi, { sector_t start = SECTOR_FROM_BLOCK(blkstart); sector_t len = SECTOR_FROM_BLOCK(blklen); + struct seg_entry *se; + unsigned int offset; + block_t i; + + for (i = blkstart; i < blkstart + blklen; i++) { + se = get_seg_entry(sbi, GET_SEGNO(sbi, i)); + offset = GET_BLKOFF_FROM_SEG0(sbi, i); + + if (!f2fs_test_and_set_bit(offset, se->discard_map)) + sbi->discard_blks--; + } trace_f2fs_issue_discard(sbi->sb, blkstart, blklen); return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0); } -void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr) +bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr) { - if (f2fs_issue_discard(sbi, blkaddr, 1)) { - struct page *page = grab_meta_page(sbi, blkaddr); - /* zero-filled page */ - set_page_dirty(page); - f2fs_put_page(page, 1); + int err = -ENOTSUPP; + + if (test_opt(sbi, DISCARD)) { + struct seg_entry *se = get_seg_entry(sbi, + GET_SEGNO(sbi, blkaddr)); + unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + + if (f2fs_test_bit(offset, se->discard_map)) + return false; + + err = f2fs_issue_discard(sbi, blkaddr, 1); } + + if (err) { + update_meta_page(sbi, NULL, blkaddr); + return true; + } + return false; } static void __add_discard_entry(struct f2fs_sb_info *sbi, - struct cp_control *cpc, unsigned int start, unsigned int end) + struct cp_control *cpc, struct seg_entry *se, + unsigned int start, unsigned int end) { struct list_head *head = &SM_I(sbi)->discard_list; struct discard_entry *new, *last; @@ -502,7 +558,6 @@ static void __add_discard_entry(struct f2fs_sb_info *sbi, list_add_tail(&new->list, head); done: SM_I(sbi)->nr_discards += end - start; - cpc->trimmed += end - start; } static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) @@ -512,41 +567,24 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start); unsigned long *cur_map = (unsigned long *)se->cur_valid_map; unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; + unsigned long *discard_map = (unsigned long *)se->discard_map; unsigned long *dmap = SIT_I(sbi)->tmp_map; unsigned int start = 0, end = -1; bool force = (cpc->reason == CP_DISCARD); int i; - if (!force && (!test_opt(sbi, DISCARD) || - SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)) + if (se->valid_blocks == max_blocks) return; - if (force && !se->valid_blocks) { - struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - /* - * if this segment is registered in the prefree list, then - * we should skip adding a discard candidate, and let the - * checkpoint do that later. - */ - mutex_lock(&dirty_i->seglist_lock); - if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) { - mutex_unlock(&dirty_i->seglist_lock); - cpc->trimmed += sbi->blocks_per_seg; + if (!force) { + if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards) return; - } - mutex_unlock(&dirty_i->seglist_lock); - - __add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg); - return; } - /* zero block will be discarded through the prefree list */ - if (!se->valid_blocks || se->valid_blocks == max_blocks) - return; - /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */ for (i = 0; i < entries; i++) - dmap[i] = force ? ~ckpt_map[i] : + dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] : (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i]; while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) { @@ -555,11 +593,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) break; end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); - - if (force && end - start < cpc->trim_minlen) - continue; - - __add_discard_entry(sbi, cpc, start, end); + __add_discard_entry(sbi, cpc, se, start, end); } } @@ -589,7 +623,7 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) mutex_unlock(&dirty_i->seglist_lock); } -void clear_prefree_segments(struct f2fs_sb_info *sbi) +void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct list_head *head = &(SM_I(sbi)->discard_list); struct discard_entry *entry, *this; @@ -622,7 +656,11 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi) /* send small discards */ list_for_each_entry_safe(entry, this, head, list) { + if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen) + goto skip; f2fs_issue_discard(sbi, entry->blkaddr, entry->len); + cpc->trimmed += entry->len; +skip: list_del(&entry->list); SM_I(sbi)->nr_discards -= entry->len; kmem_cache_free(discard_entry_slab, entry); @@ -673,9 +711,13 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) if (del > 0) { if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); + if (!f2fs_test_and_set_bit(offset, se->discard_map)) + sbi->discard_blks--; } else { if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); + if (f2fs_test_and_clear_bit(offset, se->discard_map)) + sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks += del; @@ -719,6 +761,30 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) mutex_unlock(&sit_i->sentry_lock); } +bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int segno, offset; + struct seg_entry *se; + bool is_cp = false; + + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) + return true; + + mutex_lock(&sit_i->sentry_lock); + + segno = GET_SEGNO(sbi, blkaddr); + se = get_seg_entry(sbi, segno); + offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + + if (f2fs_test_bit(offset, se->ckpt_valid_map)) + is_cp = true; + + mutex_unlock(&sit_i->sentry_lock); + + return is_cp; +} + /* * This function should be resided under the curseg_mutex lock */ @@ -769,16 +835,25 @@ struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); } -static void write_sum_page(struct f2fs_sb_info *sbi, - struct f2fs_summary_block *sum_blk, block_t blk_addr) +void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) { struct page *page = grab_meta_page(sbi, blk_addr); - void *kaddr = page_address(page); - memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE); + void *dst = page_address(page); + + if (src) + memcpy(dst, src, PAGE_CACHE_SIZE); + else + memset(dst, 0, PAGE_CACHE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } +static void write_sum_page(struct f2fs_sb_info *sbi, + struct f2fs_summary_block *sum_blk, block_t blk_addr) +{ + update_meta_page(sbi, (void *)sum_blk, blk_addr); +} + static int is_next_segment_free(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -1060,8 +1135,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) unsigned int start_segno, end_segno; struct cp_control cpc; - if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) || - range->len < sbi->blocksize) + if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; cpc.trimmed = 0; @@ -1073,12 +1147,19 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : GET_SEGNO(sbi, end); cpc.reason = CP_DISCARD; - cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen); + cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen)); /* do checkpoint to issue discard commands safely */ for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) { cpc.trim_start = start_segno; - cpc.trim_end = min_t(unsigned int, rounddown(start_segno + + + if (sbi->discard_blks == 0) + break; + else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi)) + cpc.trim_end = end_segno; + else + cpc.trim_end = min_t(unsigned int, + rounddown(start_segno + BATCHED_TRIM_SEGMENTS(sbi), sbi->segs_per_sec) - 1, end_segno); @@ -1174,7 +1255,8 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, mutex_lock(&sit_i->sentry_lock); /* direct_io'ed data is aligned to the segment for better performance */ - if (direct_io && curseg->next_blkoff) + if (direct_io && curseg->next_blkoff && + !has_not_enough_free_secs(sbi, 0)) __allocate_new_segments(sbi, type); *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); @@ -1206,84 +1288,98 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, mutex_unlock(&curseg->curseg_mutex); } -static void do_write_page(struct f2fs_sb_info *sbi, struct page *page, - struct f2fs_summary *sum, - struct f2fs_io_info *fio) +static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { - int type = __get_segment_type(page, fio->type); + int type = __get_segment_type(fio->page, fio->type); - allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type); + allocate_data_block(fio->sbi, fio->page, fio->blk_addr, + &fio->blk_addr, sum, type); /* writeout dirty page into bdev */ - f2fs_submit_page_mbio(sbi, page, fio); + f2fs_submit_page_mbio(fio); } void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_io_info fio = { + .sbi = sbi, .type = META, .rw = WRITE_SYNC | REQ_META | REQ_PRIO, .blk_addr = page->index, + .page = page, + .encrypted_page = NULL, }; + if (unlikely(page->index >= MAIN_BLKADDR(sbi))) + fio.rw &= ~REQ_META; + set_page_writeback(page); - f2fs_submit_page_mbio(sbi, page, &fio); + f2fs_submit_page_mbio(&fio); } -void write_node_page(struct f2fs_sb_info *sbi, struct page *page, - unsigned int nid, struct f2fs_io_info *fio) +void write_node_page(unsigned int nid, struct f2fs_io_info *fio) { struct f2fs_summary sum; + set_summary(&sum, nid, 0, 0); - do_write_page(sbi, page, &sum, fio); + do_write_page(&sum, fio); } -void write_data_page(struct page *page, struct dnode_of_data *dn, - struct f2fs_io_info *fio) +void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) { - struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct f2fs_sb_info *sbi = fio->sbi; struct f2fs_summary sum; struct node_info ni; f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); - do_write_page(sbi, page, &sum, fio); + do_write_page(&sum, fio); dn->data_blkaddr = fio->blk_addr; } -void rewrite_data_page(struct page *page, struct f2fs_io_info *fio) +void rewrite_data_page(struct f2fs_io_info *fio) { - stat_inc_inplace_blocks(F2FS_P_SB(page)); - f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio); + stat_inc_inplace_blocks(fio->sbi); + f2fs_submit_page_mbio(fio); } -void recover_data_page(struct f2fs_sb_info *sbi, - struct page *page, struct f2fs_summary *sum, - block_t old_blkaddr, block_t new_blkaddr) +static void __f2fs_replace_block(struct f2fs_sb_info *sbi, + struct f2fs_summary *sum, + block_t old_blkaddr, block_t new_blkaddr, + bool recover_curseg) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg; unsigned int segno, old_cursegno; struct seg_entry *se; int type; + unsigned short old_blkoff; segno = GET_SEGNO(sbi, new_blkaddr); se = get_seg_entry(sbi, segno); type = se->type; - if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { - if (old_blkaddr == NULL_ADDR) - type = CURSEG_COLD_DATA; - else + if (!recover_curseg) { + /* for recovery flow */ + if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { + if (old_blkaddr == NULL_ADDR) + type = CURSEG_COLD_DATA; + else + type = CURSEG_WARM_DATA; + } + } else { + if (!IS_CURSEG(sbi, segno)) type = CURSEG_WARM_DATA; } + curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); mutex_lock(&sit_i->sentry_lock); old_cursegno = curseg->segno; + old_blkoff = curseg->next_blkoff; /* change the current segment */ if (segno != curseg->segno) { @@ -1294,33 +1390,77 @@ void recover_data_page(struct f2fs_sb_info *sbi, curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); __add_sum_entry(sbi, type, sum); - refresh_sit_entry(sbi, old_blkaddr, new_blkaddr); + if (!recover_curseg) + update_sit_entry(sbi, new_blkaddr, 1); + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + update_sit_entry(sbi, old_blkaddr, -1); + + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr)); + locate_dirty_segment(sbi, old_cursegno); + if (recover_curseg) { + if (old_cursegno != curseg->segno) { + curseg->next_segno = old_cursegno; + change_curseg(sbi, type, true); + } + curseg->next_blkoff = old_blkoff; + } + mutex_unlock(&sit_i->sentry_lock); mutex_unlock(&curseg->curseg_mutex); } +void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, + block_t old_addr, block_t new_addr, + unsigned char version, bool recover_curseg) +{ + struct f2fs_summary sum; + + set_summary(&sum, dn->nid, dn->ofs_in_node, version); + + __f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg); + + dn->data_blkaddr = new_addr; + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); +} + static inline bool is_merged_page(struct f2fs_sb_info *sbi, struct page *page, enum page_type type) { enum page_type btype = PAGE_TYPE_OF_BIO(type); struct f2fs_bio_info *io = &sbi->write_io[btype]; struct bio_vec *bvec; + struct page *target; int i; down_read(&io->io_rwsem); - if (!io->bio) - goto out; + if (!io->bio) { + up_read(&io->io_rwsem); + return false; + } bio_for_each_segment_all(bvec, io->bio, i) { - if (page == bvec->bv_page) { + + if (bvec->bv_page->mapping) { + target = bvec->bv_page; + } else { + struct f2fs_crypto_ctx *ctx; + + /* encrypted page */ + ctx = (struct f2fs_crypto_ctx *)page_private( + bvec->bv_page); + target = ctx->w.control_page; + } + + if (page == target) { up_read(&io->io_rwsem); return true; } } -out: up_read(&io->io_rwsem); return false; } @@ -1337,6 +1477,23 @@ void f2fs_wait_on_page_writeback(struct page *page, } } +void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi, + block_t blkaddr) +{ + struct page *cpage; + + if (blkaddr == NEW_ADDR) + return; + + f2fs_bug_on(sbi, blkaddr == NULL_ADDR); + + cpage = find_lock_page(META_MAPPING(sbi), blkaddr); + if (cpage) { + f2fs_wait_on_page_writeback(cpage, DATA); + f2fs_put_page(cpage, 1); + } +} + static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1474,7 +1631,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) if (npages >= 2) ra_meta_pages(sbi, start_sum_block(sbi), npages, - META_CP); + META_CP, true); /* restore for compacted data summary */ if (read_compacted_summaries(sbi)) @@ -1484,7 +1641,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) if (__exist_node_summaries(sbi)) ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), - NR_CURSEG_TYPE - type, META_CP); + NR_CURSEG_TYPE - type, META_CP, true); for (; type <= CURSEG_COLD_NODE; type++) { err = read_normal_summaries(sbi, type); @@ -1641,7 +1798,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, static struct sit_entry_set *grab_sit_entry_set(void) { struct sit_entry_set *ses = - f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_ATOMIC); + f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_NOFS); ses->entry_cnt = 0; INIT_LIST_HEAD(&ses->set_list); @@ -1843,12 +2000,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi) SM_I(sbi)->sit_info = sit_i; - sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry)); + sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) * + sizeof(struct seg_entry), GFP_KERNEL); if (!sit_i->sentries) return -ENOMEM; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL); + sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL); if (!sit_i->dirty_sentries_bitmap) return -ENOMEM; @@ -1857,8 +2015,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi) = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); sit_i->sentries[start].ckpt_valid_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].cur_valid_map - || !sit_i->sentries[start].ckpt_valid_map) + sit_i->sentries[start].discard_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + if (!sit_i->sentries[start].cur_valid_map || + !sit_i->sentries[start].ckpt_valid_map || + !sit_i->sentries[start].discard_map) return -ENOMEM; } @@ -1867,8 +2028,8 @@ static int build_sit_info(struct f2fs_sb_info *sbi) return -ENOMEM; if (sbi->segs_per_sec > 1) { - sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) * - sizeof(struct sec_entry)); + sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) * + sizeof(struct sec_entry), GFP_KERNEL); if (!sit_i->sec_entries) return -ENOMEM; } @@ -1913,12 +2074,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi) SM_I(sbi)->free_info = free_i; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL); + free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL); if (!free_i->free_segmap) return -ENOMEM; sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL); + free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL); if (!free_i->free_secmap) return -ENOMEM; @@ -1967,7 +2128,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi) int nrpages = MAX_BIO_BLOCKS(sbi); do { - readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT); + readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true); start = start_blk * sit_i->sents_per_block; end = (start_blk + readed) * sit_i->sents_per_block; @@ -1996,6 +2157,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi) got_it: check_block_count(sbi, start, &sit); seg_info_from_raw_sit(se, &sit); + + /* build discard map only one time */ + memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks; + if (sbi->segs_per_sec > 1) { struct sec_entry *e = get_sec_entry(sbi, start); e->valid_blocks += se->valid_blocks; @@ -2054,7 +2220,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi) struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL); + dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL); if (!dirty_i->victim_secmap) return -ENOMEM; return 0; @@ -2076,7 +2242,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); for (i = 0; i < NR_DIRTY_TYPE; i++) { - dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL); + dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL); if (!dirty_i->dirty_segmap[i]) return -ENOMEM; } @@ -2181,7 +2347,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi, struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); mutex_lock(&dirty_i->seglist_lock); - kfree(dirty_i->dirty_segmap[dirty_type]); + kvfree(dirty_i->dirty_segmap[dirty_type]); dirty_i->nr_dirty[dirty_type] = 0; mutex_unlock(&dirty_i->seglist_lock); } @@ -2189,7 +2355,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi, static void destroy_victim_secmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - kfree(dirty_i->victim_secmap); + kvfree(dirty_i->victim_secmap); } static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) @@ -2228,8 +2394,8 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi) if (!free_i) return; SM_I(sbi)->free_info = NULL; - kfree(free_i->free_segmap); - kfree(free_i->free_secmap); + kvfree(free_i->free_segmap); + kvfree(free_i->free_secmap); kfree(free_i); } @@ -2245,13 +2411,14 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi) for (start = 0; start < MAIN_SEGS(sbi); start++) { kfree(sit_i->sentries[start].cur_valid_map); kfree(sit_i->sentries[start].ckpt_valid_map); + kfree(sit_i->sentries[start].discard_map); } } kfree(sit_i->tmp_map); - vfree(sit_i->sentries); - vfree(sit_i->sec_entries); - kfree(sit_i->dirty_sentries_bitmap); + kvfree(sit_i->sentries); + kvfree(sit_i->sec_entries); + kvfree(sit_i->dirty_sentries_bitmap); SM_I(sbi)->sit_info = NULL; kfree(sit_i->sit_bitmap); diff --git a/kernel/fs/f2fs/segment.h b/kernel/fs/f2fs/segment.h index 85d7fa751..ee44d346e 100644 --- a/kernel/fs/f2fs/segment.h +++ b/kernel/fs/f2fs/segment.h @@ -9,6 +9,7 @@ * published by the Free Software Foundation. */ #include <linux/blkdev.h> +#include <linux/backing-dev.h> /* constant macro */ #define NULL_SEGNO ((unsigned int)(~0)) @@ -136,10 +137,12 @@ enum { /* * BG_GC means the background cleaning job. * FG_GC means the on-demand cleaning job. + * FORCE_FG_GC means on-demand cleaning job in background. */ enum { BG_GC = 0, - FG_GC + FG_GC, + FORCE_FG_GC, }; /* for a function parameter to select a victim segment */ @@ -163,6 +166,7 @@ struct seg_entry { */ unsigned short ckpt_valid_blocks; unsigned char *ckpt_valid_map; + unsigned char *discard_map; unsigned char type; /* segment type like CURSEG_XXX_TYPE */ unsigned long long mtime; /* modification time of the segment */ }; @@ -175,6 +179,15 @@ struct segment_allocation { void (*allocate_segment)(struct f2fs_sb_info *, int, bool); }; +/* + * this value is set in page as a private data which indicate that + * the page is atomically written, and it is in inmem_pages list. + */ +#define ATOMIC_WRITTEN_PAGE 0x0000ffff + +#define IS_ATOMIC_WRITTEN_PAGE(page) \ + (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE) + struct inmem_pages { struct list_head list; struct page *page; @@ -553,16 +566,15 @@ static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type) return curseg->next_blkoff; } -#ifdef CONFIG_F2FS_CHECK_FS static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) { - BUG_ON(segno > TOTAL_SEGS(sbi) - 1); + f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1); } static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) { - BUG_ON(blk_addr < SEG0_BLKADDR(sbi)); - BUG_ON(blk_addr >= MAX_BLKADDR(sbi)); + f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi) + || blk_addr >= MAX_BLKADDR(sbi)); } /* @@ -571,16 +583,11 @@ static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) static inline void check_block_count(struct f2fs_sb_info *sbi, int segno, struct f2fs_sit_entry *raw_sit) { +#ifdef CONFIG_F2FS_CHECK_FS bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; int valid_blocks = 0; int cur_pos = 0, next_pos; - /* check segment usage */ - BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg); - - /* check boundary of a given segment number */ - BUG_ON(segno > TOTAL_SEGS(sbi) - 1); - /* check bitmap with valid block count */ do { if (is_valid) { @@ -596,35 +603,11 @@ static inline void check_block_count(struct f2fs_sb_info *sbi, is_valid = !is_valid; } while (cur_pos < sbi->blocks_per_seg); BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks); -} -#else -static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) -{ - if (segno > TOTAL_SEGS(sbi) - 1) - set_sbi_flag(sbi, SBI_NEED_FSCK); -} - -static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) -{ - if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi)) - set_sbi_flag(sbi, SBI_NEED_FSCK); -} - -/* - * Summary block is always treated as an invalid block - */ -static inline void check_block_count(struct f2fs_sb_info *sbi, - int segno, struct f2fs_sit_entry *raw_sit) -{ - /* check segment usage */ - if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg) - set_sbi_flag(sbi, SBI_NEED_FSCK); - - /* check boundary of a given segment number */ - if (segno > TOTAL_SEGS(sbi) - 1) - set_sbi_flag(sbi, SBI_NEED_FSCK); -} #endif + /* check segment usage, and check boundary of a given segment number */ + f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg + || segno > TOTAL_SEGS(sbi) - 1); +} static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi, unsigned int start) @@ -713,7 +696,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi) */ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) { - if (sbi->sb->s_bdi->dirty_exceeded) + if (sbi->sb->s_bdi->wb.dirty_exceeded) return 0; if (type == DATA) diff --git a/kernel/fs/f2fs/shrinker.c b/kernel/fs/f2fs/shrinker.c new file mode 100644 index 000000000..da0d8e0b5 --- /dev/null +++ b/kernel/fs/f2fs/shrinker.c @@ -0,0 +1,139 @@ +/* + * f2fs shrinker support + * the basic infra was copied from fs/ubifs/shrinker.c + * + * Copyright (c) 2015 Motorola Mobility + * Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" + +static LIST_HEAD(f2fs_list); +static DEFINE_SPINLOCK(f2fs_list_lock); +static unsigned int shrinker_run_no; + +static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi) +{ + return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt; +} + +static unsigned long __count_free_nids(struct f2fs_sb_info *sbi) +{ + if (NM_I(sbi)->fcnt > NAT_ENTRY_PER_BLOCK) + return NM_I(sbi)->fcnt - NAT_ENTRY_PER_BLOCK; + return 0; +} + +static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi) +{ + return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node); +} + +unsigned long f2fs_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct f2fs_sb_info *sbi; + struct list_head *p; + unsigned long count = 0; + + spin_lock(&f2fs_list_lock); + p = f2fs_list.next; + while (p != &f2fs_list) { + sbi = list_entry(p, struct f2fs_sb_info, s_list); + + /* stop f2fs_put_super */ + if (!mutex_trylock(&sbi->umount_mutex)) { + p = p->next; + continue; + } + spin_unlock(&f2fs_list_lock); + + /* count extent cache entries */ + count += __count_extent_cache(sbi); + + /* shrink clean nat cache entries */ + count += __count_nat_entries(sbi); + + /* count free nids cache entries */ + count += __count_free_nids(sbi); + + spin_lock(&f2fs_list_lock); + p = p->next; + mutex_unlock(&sbi->umount_mutex); + } + spin_unlock(&f2fs_list_lock); + return count; +} + +unsigned long f2fs_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long nr = sc->nr_to_scan; + struct f2fs_sb_info *sbi; + struct list_head *p; + unsigned int run_no; + unsigned long freed = 0; + + spin_lock(&f2fs_list_lock); + do { + run_no = ++shrinker_run_no; + } while (run_no == 0); + p = f2fs_list.next; + while (p != &f2fs_list) { + sbi = list_entry(p, struct f2fs_sb_info, s_list); + + if (sbi->shrinker_run_no == run_no) + break; + + /* stop f2fs_put_super */ + if (!mutex_trylock(&sbi->umount_mutex)) { + p = p->next; + continue; + } + spin_unlock(&f2fs_list_lock); + + sbi->shrinker_run_no = run_no; + + /* shrink extent cache entries */ + freed += f2fs_shrink_extent_tree(sbi, nr >> 1); + + /* shrink clean nat cache entries */ + if (freed < nr) + freed += try_to_free_nats(sbi, nr - freed); + + /* shrink free nids cache entries */ + if (freed < nr) + freed += try_to_free_nids(sbi, nr - freed); + + spin_lock(&f2fs_list_lock); + p = p->next; + list_move_tail(&sbi->s_list, &f2fs_list); + mutex_unlock(&sbi->umount_mutex); + if (freed >= nr) + break; + } + spin_unlock(&f2fs_list_lock); + return freed; +} + +void f2fs_join_shrinker(struct f2fs_sb_info *sbi) +{ + spin_lock(&f2fs_list_lock); + list_add_tail(&sbi->s_list, &f2fs_list); + spin_unlock(&f2fs_list_lock); +} + +void f2fs_leave_shrinker(struct f2fs_sb_info *sbi) +{ + f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi)); + + spin_lock(&f2fs_list_lock); + list_del(&sbi->s_list); + spin_unlock(&f2fs_list_lock); +} diff --git a/kernel/fs/f2fs/super.c b/kernel/fs/f2fs/super.c index b2dd1b01f..3a65e0132 100644 --- a/kernel/fs/f2fs/super.c +++ b/kernel/fs/f2fs/super.c @@ -39,6 +39,13 @@ static struct proc_dir_entry *f2fs_proc_root; static struct kmem_cache *f2fs_inode_cachep; static struct kset *f2fs_kset; +/* f2fs-wide shrinker description */ +static struct shrinker f2fs_shrinker_info = { + .scan_objects = f2fs_shrink_scan, + .count_objects = f2fs_shrink_count, + .seeks = DEFAULT_SEEKS, +}; + enum { Opt_gc_background, Opt_disable_roll_forward, @@ -58,6 +65,7 @@ enum { Opt_nobarrier, Opt_fastboot, Opt_extent_cache, + Opt_noextent_cache, Opt_noinline_data, Opt_err, }; @@ -81,6 +89,7 @@ static match_table_t f2fs_tokens = { {Opt_nobarrier, "nobarrier"}, {Opt_fastboot, "fastboot"}, {Opt_extent_cache, "extent_cache"}, + {Opt_noextent_cache, "noextent_cache"}, {Opt_noinline_data, "noinline_data"}, {Opt_err, NULL}, }; @@ -204,8 +213,10 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -222,6 +233,8 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(max_victim_search), ATTR_LIST(dir_level), ATTR_LIST(ram_thresh), + ATTR_LIST(ra_nid_pages), + ATTR_LIST(cp_interval), NULL, }; @@ -258,6 +271,7 @@ static void init_once(void *foo) static int parse_options(struct super_block *sb, char *options) { struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct request_queue *q; substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; @@ -282,11 +296,16 @@ static int parse_options(struct super_block *sb, char *options) if (!name) return -ENOMEM; - if (strlen(name) == 2 && !strncmp(name, "on", 2)) + if (strlen(name) == 2 && !strncmp(name, "on", 2)) { set_opt(sbi, BG_GC); - else if (strlen(name) == 3 && !strncmp(name, "off", 3)) + clear_opt(sbi, FORCE_FG_GC); + } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) { clear_opt(sbi, BG_GC); - else { + clear_opt(sbi, FORCE_FG_GC); + } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) { + set_opt(sbi, BG_GC); + set_opt(sbi, FORCE_FG_GC); + } else { kfree(name); return -EINVAL; } @@ -302,7 +321,14 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; break; case Opt_discard: - set_opt(sbi, DISCARD); + q = bdev_get_queue(sb->s_bdev); + if (blk_queue_discard(q)) { + set_opt(sbi, DISCARD); + } else { + f2fs_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but " + "the device does not support discard"); + } break; case Opt_noheap: set_opt(sbi, NOHEAP); @@ -374,6 +400,9 @@ static int parse_options(struct super_block *sb, char *options) case Opt_extent_cache: set_opt(sbi, EXTENT_CACHE); break; + case Opt_noextent_cache: + clear_opt(sbi, EXTENT_CACHE); + break; case Opt_noinline_data: clear_opt(sbi, INLINE_DATA); break; @@ -402,9 +431,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) atomic_set(&fi->dirty_pages, 0); fi->i_current_depth = 1; fi->i_advise = 0; - rwlock_init(&fi->ext_lock); init_rwsem(&fi->i_sem); - INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS); INIT_LIST_HEAD(&fi->inmem_pages); mutex_init(&fi->inmem_lock); @@ -416,6 +443,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; +#ifdef CONFIG_F2FS_FS_ENCRYPTION + fi->i_crypt_info = NULL; +#endif return &fi->vfs_inode; } @@ -428,8 +458,37 @@ static int f2fs_drop_inode(struct inode *inode) * - f2fs_gc -> iput -> evict * - inode_wait_for_writeback(inode) */ - if (!inode_unhashed(inode) && inode->i_state & I_SYNC) + if (!inode_unhashed(inode) && inode->i_state & I_SYNC) { + if (!inode->i_nlink && !is_bad_inode(inode)) { + /* to avoid evict_inode call simultaneously */ + atomic_inc(&inode->i_count); + spin_unlock(&inode->i_lock); + + /* some remained atomic pages should discarded */ + if (f2fs_is_atomic_file(inode)) + commit_inmem_pages(inode, true); + + /* should remain fi->extent_tree for writepage */ + f2fs_destroy_extent_node(inode); + + sb_start_intwrite(inode->i_sb); + i_size_write(inode, 0); + + if (F2FS_HAS_BLOCKS(inode)) + f2fs_truncate(inode, true); + + sb_end_intwrite(inode->i_sb); + +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (F2FS_I(inode)->i_crypt_info) + f2fs_free_encryption_info(inode, + F2FS_I(inode)->i_crypt_info); +#endif + spin_lock(&inode->i_lock); + atomic_dec(&inode->i_count); + } return 0; + } return generic_drop_inode(inode); } @@ -464,9 +523,11 @@ static void f2fs_put_super(struct super_block *sb) } kobject_del(&sbi->s_kobj); - f2fs_destroy_stats(sbi); stop_gc_thread(sbi); + /* prevent remaining shrinker jobs */ + mutex_lock(&sbi->umount_mutex); + /* * We don't need to do checkpoint when superblock is clean. * But, the previous checkpoint was not done by umount, it needs to do @@ -480,6 +541,9 @@ static void f2fs_put_super(struct super_block *sb) write_checkpoint(sbi, &cpc); } + /* write_checkpoint can update stat informaion */ + f2fs_destroy_stats(sbi); + /* * normally superblock is clean, so we need to release this. * In addition, EIO will skip do checkpoint, we need this as well. @@ -487,6 +551,9 @@ static void f2fs_put_super(struct super_block *sb) release_dirty_inode(sbi); release_discard_addrs(sbi); + f2fs_leave_shrinker(sbi); + mutex_unlock(&sbi->umount_mutex); + iput(sbi->node_inode); iput(sbi->meta_inode); @@ -520,7 +587,7 @@ int f2fs_sync_fs(struct super_block *sb, int sync) } else { f2fs_balance_fs(sbi); } - f2fs_trace_ios(NULL, NULL, 1); + f2fs_trace_ios(NULL, 1); return 0; } @@ -573,10 +640,14 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) { struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); - if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) - seq_printf(seq, ",background_gc=%s", "on"); - else + if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) { + if (test_opt(sbi, FORCE_FG_GC)) + seq_printf(seq, ",background_gc=%s", "sync"); + else + seq_printf(seq, ",background_gc=%s", "on"); + } else { seq_printf(seq, ",background_gc=%s", "off"); + } if (test_opt(sbi, DISABLE_ROLL_FORWARD)) seq_puts(seq, ",disable_roll_forward"); if (test_opt(sbi, DISCARD)) @@ -613,6 +684,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",fastboot"); if (test_opt(sbi, EXTENT_CACHE)) seq_puts(seq, ",extent_cache"); + else + seq_puts(seq, ",noextent_cache"); seq_printf(seq, ",active_logs=%u", sbi->active_logs); return 0; @@ -633,7 +706,7 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset) struct seg_entry *se = get_seg_entry(sbi, i); if ((i % 10) == 0) - seq_printf(seq, "%-5d", i); + seq_printf(seq, "%-10d", i); seq_printf(seq, "%d|%-3u", se->type, get_valid_blocks(sbi, i, 1)); if ((i % 10) == 9 || i == (total_segs - 1)) @@ -658,6 +731,23 @@ static const struct file_operations f2fs_seq_segment_info_fops = { .release = single_release, }; +static void default_options(struct f2fs_sb_info *sbi) +{ + /* init some FS parameters */ + sbi->active_logs = NR_CURSEG_TYPE; + + set_opt(sbi, BG_GC); + set_opt(sbi, INLINE_DATA); + set_opt(sbi, EXTENT_CACHE); + +#ifdef CONFIG_F2FS_FS_XATTR + set_opt(sbi, XATTR_USER); +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + set_opt(sbi, POSIX_ACL); +#endif +} + static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -665,6 +755,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) int err, active_logs; bool need_restart_gc = false; bool need_stop_gc = false; + bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); sync_filesystem(sb); @@ -676,7 +767,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) active_logs = sbi->active_logs; sbi->mount_opt.opt = 0; - sbi->active_logs = NR_CURSEG_TYPE; + default_options(sbi); /* parse mount options */ err = parse_options(sb, data); @@ -690,6 +781,14 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) if (f2fs_readonly(sb) && (*flags & MS_RDONLY)) goto skip; + /* disallow enable/disable extent_cache dynamically */ + if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) { + err = -EINVAL; + f2fs_msg(sbi->sb, KERN_WARNING, + "switch extent_cache option is not allowed"); + goto restore_opts; + } + /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount @@ -919,7 +1018,11 @@ static void init_sb_info(struct f2fs_sb_info *sbi) atomic_set(&sbi->nr_pages[i], 0); sbi->dir_level = DEF_DIR_LEVEL; + sbi->cp_interval = DEF_CP_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); + + INIT_LIST_HEAD(&sbi->s_list); + mutex_init(&sbi->umount_mutex); } /* @@ -929,29 +1032,36 @@ static void init_sb_info(struct f2fs_sb_info *sbi) */ static int read_raw_super_block(struct super_block *sb, struct f2fs_super_block **raw_super, - struct buffer_head **raw_super_buf) + struct buffer_head **raw_super_buf, + int *recovery) { int block = 0; + struct buffer_head *buffer; + struct f2fs_super_block *super; + int err = 0; retry: - *raw_super_buf = sb_bread(sb, block); - if (!*raw_super_buf) { + buffer = sb_bread(sb, block); + if (!buffer) { + *recovery = 1; f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", block + 1); if (block == 0) { block++; goto retry; } else { - return -EIO; + err = -EIO; + goto out; } } - *raw_super = (struct f2fs_super_block *) - ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET); + super = (struct f2fs_super_block *) + ((char *)(buffer)->b_data + F2FS_SUPER_OFFSET); /* sanity checking of raw super */ - if (sanity_check_raw_super(sb, *raw_super)) { - brelse(*raw_super_buf); + if (sanity_check_raw_super(sb, super)) { + brelse(buffer); + *recovery = 1; f2fs_msg(sb, KERN_ERR, "Can't find valid F2FS filesystem in %dth superblock", block + 1); @@ -959,25 +1069,76 @@ retry: block++; goto retry; } else { - return -EINVAL; + err = -EINVAL; + goto out; } } + if (!*raw_super) { + *raw_super_buf = buffer; + *raw_super = super; + } else { + /* already have a valid superblock */ + brelse(buffer); + } + + /* check the validity of the second superblock */ + if (block == 0) { + block++; + goto retry; + } + +out: + /* No valid superblock */ + if (!*raw_super) + return err; + return 0; } +int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) +{ + struct buffer_head *sbh = sbi->raw_super_buf; + sector_t block = sbh->b_blocknr; + int err; + + /* write back-up superblock first */ + sbh->b_blocknr = block ? 0 : 1; + mark_buffer_dirty(sbh); + err = sync_dirty_buffer(sbh); + + sbh->b_blocknr = block; + + /* if we are in recovery path, skip writing valid superblock */ + if (recover || err) + goto out; + + /* write current valid superblock */ + mark_buffer_dirty(sbh); + err = sync_dirty_buffer(sbh); +out: + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + return err; +} + static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; - struct f2fs_super_block *raw_super = NULL; + struct f2fs_super_block *raw_super; struct buffer_head *raw_super_buf; struct inode *root; - long err = -EINVAL; + long err; bool retry = true, need_fsck = false; char *options = NULL; - int i; + int recovery, i; try_onemore: + err = -EINVAL; + raw_super = NULL; + raw_super_buf = NULL; + recovery = 0; + /* allocate memory for f2fs-specific super block info */ sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL); if (!sbi) @@ -989,23 +1150,12 @@ try_onemore: goto free_sbi; } - err = read_raw_super_block(sb, &raw_super, &raw_super_buf); + err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery); if (err) goto free_sbi; sb->s_fs_info = sbi; - /* init some FS parameters */ - sbi->active_logs = NR_CURSEG_TYPE; - - set_opt(sbi, BG_GC); - set_opt(sbi, INLINE_DATA); - -#ifdef CONFIG_F2FS_FS_XATTR - set_opt(sbi, XATTR_USER); -#endif -#ifdef CONFIG_F2FS_FS_POSIX_ACL - set_opt(sbi, POSIX_ACL); -#endif + default_options(sbi); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); if (data && !options) { @@ -1038,7 +1188,9 @@ try_onemore: mutex_init(&sbi->writepages); mutex_init(&sbi->cp_mutex); init_rwsem(&sbi->node_write); - clear_sbi_flag(sbi, SBI_POR_DOING); + + /* disallow all the data/node/meta page writes */ + set_sbi_flag(sbi, SBI_POR_DOING); spin_lock_init(&sbi->stat_lock); init_rwsem(&sbi->read_io.io_rwsem); @@ -1115,8 +1267,12 @@ try_onemore: goto free_nm; } + f2fs_join_shrinker(sbi); + /* if there are nt orphan nodes free them */ - recover_orphan_inodes(sbi); + err = recover_orphan_inodes(sbi); + if (err) + goto free_node_inode; /* read root inode and dentry */ root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); @@ -1148,14 +1304,6 @@ try_onemore: proc_create_data("segment_info", S_IRUGO, sbi->s_proc, &f2fs_seq_segment_info_fops, sb); - if (test_opt(sbi, DISCARD)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - f2fs_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } - sbi->s_kobj.kset = f2fs_kset; init_completion(&sbi->s_kobj_unregister); err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL, @@ -1186,6 +1334,8 @@ try_onemore: goto free_kobj; } } + /* recover_fsync_data() cleared this already */ + clear_sbi_flag(sbi, SBI_POR_DOING); /* * If filesystem is not mounted as read-only then @@ -1198,6 +1348,15 @@ try_onemore: goto free_kobj; } kfree(options); + + /* recover broken superblock */ + if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) { + f2fs_msg(sb, KERN_INFO, "Recover invalid superblock"); + f2fs_commit_super(sbi, true); + } + + sbi->cp_expires = round_jiffies_up(jiffies); + return 0; free_kobj: @@ -1212,7 +1371,10 @@ free_root_inode: dput(sb->s_root); sb->s_root = NULL; free_node_inode: + mutex_lock(&sbi->umount_mutex); + f2fs_leave_shrinker(sbi); iput(sbi->node_inode); + mutex_unlock(&sbi->umount_mutex); free_nm: destroy_node_manager(sbi); free_sm: @@ -1305,13 +1467,25 @@ static int __init init_f2fs_fs(void) err = -ENOMEM; goto free_extent_cache; } - err = register_filesystem(&f2fs_fs_type); + err = f2fs_init_crypto(); if (err) goto free_kset; + + err = register_shrinker(&f2fs_shrinker_info); + if (err) + goto free_crypto; + + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_shrinker; f2fs_create_root_stats(); f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); return 0; +free_shrinker: + unregister_shrinker(&f2fs_shrinker_info); +free_crypto: + f2fs_exit_crypto(); free_kset: kset_unregister(f2fs_kset); free_extent_cache: @@ -1332,7 +1506,9 @@ static void __exit exit_f2fs_fs(void) { remove_proc_entry("fs/f2fs", NULL); f2fs_destroy_root_stats(); + unregister_shrinker(&f2fs_shrinker_info); unregister_filesystem(&f2fs_fs_type); + f2fs_exit_crypto(); destroy_extent_cache(); destroy_checkpoint_caches(); destroy_segment_manager_caches(); diff --git a/kernel/fs/f2fs/trace.c b/kernel/fs/f2fs/trace.c index 875aa8179..145fb659a 100644 --- a/kernel/fs/f2fs/trace.c +++ b/kernel/fs/f2fs/trace.c @@ -80,7 +80,7 @@ out: radix_tree_preload_end(); } -void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush) +void f2fs_trace_ios(struct f2fs_io_info *fio, int flush) { struct inode *inode; pid_t pid; @@ -91,8 +91,8 @@ void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush) return; } - inode = page->mapping->host; - pid = page_private(page); + inode = fio->page->mapping->host; + pid = page_private(fio->page); major = MAJOR(inode->i_sb->s_dev); minor = MINOR(inode->i_sb->s_dev); diff --git a/kernel/fs/f2fs/trace.h b/kernel/fs/f2fs/trace.h index 1041dbeb5..67db24ac1 100644 --- a/kernel/fs/f2fs/trace.h +++ b/kernel/fs/f2fs/trace.h @@ -33,12 +33,12 @@ struct last_io_info { }; extern void f2fs_trace_pid(struct page *); -extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int); +extern void f2fs_trace_ios(struct f2fs_io_info *, int); extern void f2fs_build_trace_ios(void); extern void f2fs_destroy_trace_ios(void); #else #define f2fs_trace_pid(p) -#define f2fs_trace_ios(p, i, n) +#define f2fs_trace_ios(i, n) #define f2fs_build_trace_ios() #define f2fs_destroy_trace_ios() diff --git a/kernel/fs/f2fs/xattr.c b/kernel/fs/f2fs/xattr.c index 9757f65a0..862368a32 100644 --- a/kernel/fs/f2fs/xattr.c +++ b/kernel/fs/f2fs/xattr.c @@ -25,49 +25,45 @@ #include "f2fs.h" #include "xattr.h" -static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t len, int type) +static size_t f2fs_xattr_generic_list(const struct xattr_handler *handler, + struct dentry *dentry, char *list, size_t list_size, + const char *name, size_t len) { struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - int total_len, prefix_len = 0; - const char *prefix = NULL; + int total_len, prefix_len; - switch (type) { + switch (handler->flags) { case F2FS_XATTR_INDEX_USER: if (!test_opt(sbi, XATTR_USER)) return -EOPNOTSUPP; - prefix = XATTR_USER_PREFIX; - prefix_len = XATTR_USER_PREFIX_LEN; break; case F2FS_XATTR_INDEX_TRUSTED: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - prefix = XATTR_TRUSTED_PREFIX; - prefix_len = XATTR_TRUSTED_PREFIX_LEN; break; case F2FS_XATTR_INDEX_SECURITY: - prefix = XATTR_SECURITY_PREFIX; - prefix_len = XATTR_SECURITY_PREFIX_LEN; break; default: return -EINVAL; } + prefix_len = strlen(handler->prefix); total_len = prefix_len + len + 1; if (list && total_len <= list_size) { - memcpy(list, prefix, prefix_len); + memcpy(list, handler->prefix, prefix_len); memcpy(list + prefix_len, name, len); list[prefix_len + len] = '\0'; } return total_len; } -static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int f2fs_xattr_generic_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, void *buffer, + size_t size) { struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - switch (type) { + switch (handler->flags) { case F2FS_XATTR_INDEX_USER: if (!test_opt(sbi, XATTR_USER)) return -EOPNOTSUPP; @@ -83,15 +79,17 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, } if (strcmp(name, "") == 0) return -EINVAL; - return f2fs_getxattr(d_inode(dentry), type, name, buffer, size, NULL); + return f2fs_getxattr(d_inode(dentry), handler->flags, name, + buffer, size, NULL); } -static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int f2fs_xattr_generic_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - switch (type) { + switch (handler->flags) { case F2FS_XATTR_INDEX_USER: if (!test_opt(sbi, XATTR_USER)) return -EOPNOTSUPP; @@ -108,27 +106,26 @@ static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name, if (strcmp(name, "") == 0) return -EINVAL; - return f2fs_setxattr(d_inode(dentry), type, name, + return f2fs_setxattr(d_inode(dentry), handler->flags, name, value, size, NULL, flags); } -static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t len, int type) +static size_t f2fs_xattr_advise_list(const struct xattr_handler *handler, + struct dentry *dentry, char *list, size_t list_size, + const char *name, size_t len) { const char *xname = F2FS_SYSTEM_ADVISE_PREFIX; size_t size; - if (type != F2FS_XATTR_INDEX_ADVISE) - return 0; - size = strlen(xname) + 1; if (list && size <= list_size) memcpy(list, xname, size); return size; } -static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int f2fs_xattr_advise_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, void *buffer, + size_t size) { struct inode *inode = d_inode(dentry); @@ -140,8 +137,9 @@ static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name, return sizeof(char); } -static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int f2fs_xattr_advise_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { struct inode *inode = d_inode(dentry); @@ -462,8 +460,8 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!handler) continue; - size = handler->list(dentry, buffer, rest, entry->e_name, - entry->e_name_len, handler->flags); + size = handler->list(handler, dentry, buffer, rest, + entry->e_name, entry->e_name_len); if (buffer && size > rest) { error = -ERANGE; goto cleanup; @@ -499,9 +497,12 @@ static int __f2fs_setxattr(struct inode *inode, int index, len = strlen(name); - if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode)) + if (len > F2FS_NAME_LEN) return -ERANGE; + if (size > MAX_VALUE_LEN(inode)) + return -E2BIG; + base_addr = read_all_xattrs(inode, ipage); if (!base_addr) goto exit; @@ -584,6 +585,9 @@ static int __f2fs_setxattr(struct inode *inode, int index, inode->i_ctime = CURRENT_TIME; clear_inode_flag(fi, FI_ACL_MODE); } + if (index == F2FS_XATTR_INDEX_ENCRYPTION && + !strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT)) + f2fs_set_encrypted_inode(inode); if (ipage) update_inode(inode, ipage); diff --git a/kernel/fs/f2fs/xattr.h b/kernel/fs/f2fs/xattr.h index 969d792ca..71a7100d5 100644 --- a/kernel/fs/f2fs/xattr.h +++ b/kernel/fs/f2fs/xattr.h @@ -35,6 +35,10 @@ #define F2FS_XATTR_INDEX_LUSTRE 5 #define F2FS_XATTR_INDEX_SECURITY 6 #define F2FS_XATTR_INDEX_ADVISE 7 +/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */ +#define F2FS_XATTR_INDEX_ENCRYPTION 9 + +#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT "c" struct f2fs_xattr_header { __le32 h_magic; /* magic number for identification */ |