summaryrefslogtreecommitdiffstats
path: root/kernel/fs/xfs/xfs_pnfs.c
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 12:17:53 -0700
committerYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 15:44:42 -0700
commit9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch)
tree1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/fs/xfs/xfs_pnfs.c
parent98260f3884f4a202f9ca5eabed40b1354c489b29 (diff)
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/fs/xfs/xfs_pnfs.c')
-rw-r--r--kernel/fs/xfs/xfs_pnfs.c329
1 files changed, 329 insertions, 0 deletions
diff --git a/kernel/fs/xfs/xfs_pnfs.c b/kernel/fs/xfs/xfs_pnfs.c
new file mode 100644
index 000000000..981a657ec
--- /dev/null
+++ b/kernel/fs/xfs/xfs_pnfs.c
@@ -0,0 +1,329 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include "xfs.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_log.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_error.h"
+#include "xfs_iomap.h"
+#include "xfs_shared.h"
+#include "xfs_bit.h"
+#include "xfs_pnfs.h"
+
+/*
+ * Ensure that we do not have any outstanding pNFS layouts that can be used by
+ * clients to directly read from or write to this inode. This must be called
+ * before every operation that can remove blocks from the extent map.
+ * Additionally we call it during the write operation, where aren't concerned
+ * about exposing unallocated blocks but just want to provide basic
+ * synchronization between a local writer and pNFS clients. mmap writes would
+ * also benefit from this sort of synchronization, but due to the tricky locking
+ * rules in the page fault path we don't bother.
+ */
+int
+xfs_break_layouts(
+ struct inode *inode,
+ uint *iolock,
+ bool with_imutex)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ int error;
+
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+ while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
+ xfs_iunlock(ip, *iolock);
+ if (with_imutex && (*iolock & XFS_IOLOCK_EXCL))
+ mutex_unlock(&inode->i_mutex);
+ error = break_layout(inode, true);
+ *iolock = XFS_IOLOCK_EXCL;
+ if (with_imutex)
+ mutex_lock(&inode->i_mutex);
+ xfs_ilock(ip, *iolock);
+ }
+
+ return error;
+}
+
+/*
+ * Get a unique ID including its location so that the client can identify
+ * the exported device.
+ */
+int
+xfs_fs_get_uuid(
+ struct super_block *sb,
+ u8 *buf,
+ u32 *len,
+ u64 *offset)
+{
+ struct xfs_mount *mp = XFS_M(sb);
+
+ printk_once(KERN_NOTICE
+"XFS (%s): using experimental pNFS feature, use at your own risk!\n",
+ mp->m_fsname);
+
+ if (*len < sizeof(uuid_t))
+ return -EINVAL;
+
+ memcpy(buf, &mp->m_sb.sb_uuid, sizeof(uuid_t));
+ *len = sizeof(uuid_t);
+ *offset = offsetof(struct xfs_dsb, sb_uuid);
+ return 0;
+}
+
+static void
+xfs_bmbt_to_iomap(
+ struct xfs_inode *ip,
+ struct iomap *iomap,
+ struct xfs_bmbt_irec *imap)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ if (imap->br_startblock == HOLESTARTBLOCK) {
+ iomap->blkno = IOMAP_NULL_BLOCK;
+ iomap->type = IOMAP_HOLE;
+ } else if (imap->br_startblock == DELAYSTARTBLOCK) {
+ iomap->blkno = IOMAP_NULL_BLOCK;
+ iomap->type = IOMAP_DELALLOC;
+ } else {
+ iomap->blkno =
+ XFS_FSB_TO_DADDR(ip->i_mount, imap->br_startblock);
+ if (imap->br_state == XFS_EXT_UNWRITTEN)
+ iomap->type = IOMAP_UNWRITTEN;
+ else
+ iomap->type = IOMAP_MAPPED;
+ }
+ iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
+ iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
+}
+
+/*
+ * Get a layout for the pNFS client.
+ */
+int
+xfs_fs_map_blocks(
+ struct inode *inode,
+ loff_t offset,
+ u64 length,
+ struct iomap *iomap,
+ bool write,
+ u32 *device_generation)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_bmbt_irec imap;
+ xfs_fileoff_t offset_fsb, end_fsb;
+ loff_t limit;
+ int bmapi_flags = XFS_BMAPI_ENTIRE;
+ int nimaps = 1;
+ uint lock_flags;
+ int error = 0;
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ /*
+ * We can't export inodes residing on the realtime device. The realtime
+ * device doesn't have a UUID to identify it, so the client has no way
+ * to find it.
+ */
+ if (XFS_IS_REALTIME_INODE(ip))
+ return -ENXIO;
+
+ /*
+ * Lock out any other I/O before we flush and invalidate the pagecache,
+ * and then hand out a layout to the remote system. This is very
+ * similar to direct I/O, except that the synchronization is much more
+ * complicated. See the comment near xfs_break_layouts for a detailed
+ * explanation.
+ */
+ xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+ error = -EINVAL;
+ limit = mp->m_super->s_maxbytes;
+ if (!write)
+ limit = max(limit, round_up(i_size_read(inode),
+ inode->i_sb->s_blocksize));
+ if (offset > limit)
+ goto out_unlock;
+ if (offset > limit - length)
+ length = limit - offset;
+
+ error = filemap_write_and_wait(inode->i_mapping);
+ if (error)
+ goto out_unlock;
+ error = invalidate_inode_pages2(inode->i_mapping);
+ if (WARN_ON_ONCE(error))
+ return error;
+
+ end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
+ offset_fsb = XFS_B_TO_FSBT(mp, offset);
+
+ lock_flags = xfs_ilock_data_map_shared(ip);
+ error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
+ &imap, &nimaps, bmapi_flags);
+ xfs_iunlock(ip, lock_flags);
+
+ if (error)
+ goto out_unlock;
+
+ if (write) {
+ enum xfs_prealloc_flags flags = 0;
+
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+
+ if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) {
+ error = xfs_iomap_write_direct(ip, offset, length,
+ &imap, nimaps);
+ if (error)
+ goto out_unlock;
+
+ /*
+ * Ensure the next transaction is committed
+ * synchronously so that the blocks allocated and
+ * handed out to the client are guaranteed to be
+ * present even after a server crash.
+ */
+ flags |= XFS_PREALLOC_SET | XFS_PREALLOC_SYNC;
+ }
+
+ error = xfs_update_prealloc_flags(ip, flags);
+ if (error)
+ goto out_unlock;
+ }
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+
+ xfs_bmbt_to_iomap(ip, iomap, &imap);
+ *device_generation = mp->m_generation;
+ return error;
+out_unlock:
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+}
+
+/*
+ * Ensure the size update falls into a valid allocated block.
+ */
+static int
+xfs_pnfs_validate_isize(
+ struct xfs_inode *ip,
+ xfs_off_t isize)
+{
+ struct xfs_bmbt_irec imap;
+ int nimaps = 1;
+ int error = 0;
+
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ error = xfs_bmapi_read(ip, XFS_B_TO_FSBT(ip->i_mount, isize - 1), 1,
+ &imap, &nimaps, 0);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ if (error)
+ return error;
+
+ if (imap.br_startblock == HOLESTARTBLOCK ||
+ imap.br_startblock == DELAYSTARTBLOCK ||
+ imap.br_state == XFS_EXT_UNWRITTEN)
+ return -EIO;
+ return 0;
+}
+
+/*
+ * Make sure the blocks described by maps are stable on disk. This includes
+ * converting any unwritten extents, flushing the disk cache and updating the
+ * time stamps.
+ *
+ * Note that we rely on the caller to always send us a timestamp update so that
+ * we always commit a transaction here. If that stops being true we will have
+ * to manually flush the cache here similar to what the fsync code path does
+ * for datasyncs on files that have no dirty metadata.
+ */
+int
+xfs_fs_commit_blocks(
+ struct inode *inode,
+ struct iomap *maps,
+ int nr_maps,
+ struct iattr *iattr)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
+ bool update_isize = false;
+ int error, i;
+ loff_t size;
+
+ ASSERT(iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME));
+
+ xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+ size = i_size_read(inode);
+ if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size > size) {
+ update_isize = true;
+ size = iattr->ia_size;
+ }
+
+ for (i = 0; i < nr_maps; i++) {
+ u64 start, length, end;
+
+ start = maps[i].offset;
+ if (start > size)
+ continue;
+
+ end = start + maps[i].length;
+ if (end > size)
+ end = size;
+
+ length = end - start;
+ if (!length)
+ continue;
+
+ /*
+ * Make sure reads through the pagecache see the new data.
+ */
+ error = invalidate_inode_pages2_range(inode->i_mapping,
+ start >> PAGE_CACHE_SHIFT,
+ (end - 1) >> PAGE_CACHE_SHIFT);
+ WARN_ON_ONCE(error);
+
+ error = xfs_iomap_write_unwritten(ip, start, length);
+ if (error)
+ goto out_drop_iolock;
+ }
+
+ if (update_isize) {
+ error = xfs_pnfs_validate_isize(ip, size);
+ if (error)
+ goto out_drop_iolock;
+ }
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ goto out_drop_iolock;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ xfs_setattr_time(ip, iattr);
+ if (update_isize) {
+ i_size_write(inode, iattr->ia_size);
+ ip->i_d.di_size = iattr->ia_size;
+ }
+
+ xfs_trans_set_sync(tp);
+ error = xfs_trans_commit(tp, 0);
+
+out_drop_iolock:
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+}