summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
authorJiri Kosina <jkosina@suse.cz>2021-06-30 09:02:28 +0200
committerJiri Kosina <jkosina@suse.cz>2021-06-30 09:02:28 +0200
commit5a94296bc02ac616336da7b5332b86d2ca8827f0 (patch)
treed13c4e7db2b4b01adb87fbf2ea5bafd2dc920b2f /fs/xfs
parent3b770932eefb7c0c6319d332023efee87eb12913 (diff)
parent24a31ea94922d391a96a9dd0a9a830de65423817 (diff)
Merge branch 'for-5.14/amd-sfh' into for-linus
- support for Renoir and Cezanne SoCs - support for Ambient Light Sensor - support for Human Presence Detection sensor all from Basavaraj Natikar
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c46
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c17
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c4
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c12
-rw-r--r--fs/xfs/libxfs/xfs_fs.h4
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c46
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h12
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_sb.c16
-rw-r--r--fs/xfs/libxfs/xfs_trans_inode.c17
-rw-r--r--fs/xfs/scrub/agheader.c7
-rw-r--r--fs/xfs/scrub/common.c4
-rw-r--r--fs/xfs/scrub/fscounters.c40
-rw-r--r--fs/xfs/xfs_aops.c2
-rw-r--r--fs/xfs/xfs_bmap_util.c98
-rw-r--r--fs/xfs/xfs_fsops.c2
-rw-r--r--fs/xfs/xfs_inode.c29
-rw-r--r--fs/xfs/xfs_inode_item.c8
-rw-r--r--fs/xfs/xfs_inode_item_recover.c6
-rw-r--r--fs/xfs/xfs_ioctl.c101
-rw-r--r--fs/xfs/xfs_log.c10
-rw-r--r--fs/xfs/xfs_message.h2
-rw-r--r--fs/xfs/xfs_mount.c15
-rw-r--r--fs/xfs/xfs_mount.h6
-rw-r--r--fs/xfs/xfs_ondisk.h4
-rw-r--r--fs/xfs/xfs_reflink.c3
-rw-r--r--fs/xfs/xfs_trans.c10
-rw-r--r--fs/xfs/xfs_trans.h15
28 files changed, 358 insertions, 180 deletions
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 6c5f8d10589c..bbfea8022a3b 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -253,7 +253,8 @@ xfs_ag_resv_init(
xfs_agnumber_t agno = pag->pag_agno;
xfs_extlen_t ask;
xfs_extlen_t used;
- int error = 0;
+ int error = 0, error2;
+ bool has_resv = false;
/* Create the metadata reservation. */
if (pag->pag_meta_resv.ar_asked == 0) {
@@ -291,6 +292,8 @@ xfs_ag_resv_init(
if (error)
goto out;
}
+ if (ask)
+ has_resv = true;
}
/* Create the RMAPBT metadata reservation */
@@ -304,19 +307,40 @@ xfs_ag_resv_init(
error = __xfs_ag_resv_init(pag, XFS_AG_RESV_RMAPBT, ask, used);
if (error)
goto out;
+ if (ask)
+ has_resv = true;
}
-#ifdef DEBUG
- /* need to read in the AGF for the ASSERT below to work */
- error = xfs_alloc_pagf_init(pag->pag_mount, tp, pag->pag_agno, 0);
- if (error)
- return error;
-
- ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
- xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <=
- pag->pagf_freeblks + pag->pagf_flcount);
-#endif
out:
+ /*
+ * Initialize the pagf if we have at least one active reservation on the
+ * AG. This may have occurred already via reservation calculation, but
+ * fall back to an explicit init to ensure the in-core allocbt usage
+ * counters are initialized as soon as possible. This is important
+ * because filesystems with large perag reservations are susceptible to
+ * free space reservation problems that the allocbt counter is used to
+ * address.
+ */
+ if (has_resv) {
+ error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0);
+ if (error2)
+ return error2;
+
+ /*
+ * If there isn't enough space in the AG to satisfy the
+ * reservation, let the caller know that there wasn't enough
+ * space. Callers are responsible for deciding what to do
+ * next, since (in theory) we can stumble along with
+ * insufficient reservation if data blocks are being freed to
+ * replenish the AG's free space.
+ */
+ if (!error &&
+ xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
+ xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved >
+ pag->pagf_freeblks + pag->pagf_flcount)
+ error = -ENOSPC;
+ }
+
return error;
}
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index aaa19101bb2a..82b7cbb1f24f 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -718,7 +718,6 @@ xfs_alloc_update_counters(
agbp->b_pag->pagf_freeblks += len;
be32_add_cpu(&agf->agf_freeblks, len);
- xfs_trans_agblocks_delta(tp, len);
if (unlikely(be32_to_cpu(agf->agf_freeblks) >
be32_to_cpu(agf->agf_length))) {
xfs_buf_mark_corrupt(agbp);
@@ -2739,7 +2738,6 @@ xfs_alloc_get_freelist(
pag = agbp->b_pag;
ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, -1);
- xfs_trans_agflist_delta(tp, -1);
pag->pagf_flcount--;
logflags = XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT;
@@ -2846,7 +2844,6 @@ xfs_alloc_put_freelist(
pag = agbp->b_pag;
ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, 1);
- xfs_trans_agflist_delta(tp, 1);
pag->pagf_flcount++;
logflags = XFS_AGF_FLLAST | XFS_AGF_FLCOUNT;
@@ -3036,6 +3033,7 @@ xfs_alloc_read_agf(
struct xfs_agf *agf; /* ag freelist header */
struct xfs_perag *pag; /* per allocation group data */
int error;
+ int allocbt_blks;
trace_xfs_alloc_read_agf(mp, agno);
@@ -3066,6 +3064,19 @@ xfs_alloc_read_agf(
pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
pag->pagf_init = 1;
pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
+
+ /*
+ * Update the in-core allocbt counter. Filter out the rmapbt
+ * subset of the btreeblks counter because the rmapbt is managed
+ * by perag reservation. Subtract one for the rmapbt root block
+ * because the rmap counter includes it while the btreeblks
+ * counter only tracks non-root blocks.
+ */
+ allocbt_blks = pag->pagf_btreeblks;
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+ allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
+ if (allocbt_blks > 0)
+ atomic64_add(allocbt_blks, &mp->m_allocbt_blks);
}
#ifdef DEBUG
else if (!XFS_FORCED_SHUTDOWN(mp)) {
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 8e01231b308e..a43e4c50e69b 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -71,9 +71,9 @@ xfs_allocbt_alloc_block(
return 0;
}
+ atomic64_inc(&cur->bc_mp->m_allocbt_blks);
xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agno, bno, 1, false);
- xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
*stat = 1;
@@ -95,9 +95,9 @@ xfs_allocbt_free_block(
if (error)
return error;
+ atomic64_dec(&cur->bc_mp->m_allocbt_blks);
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
- xfs_trans_agbtree_delta(cur->bc_tp, -1);
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7e3b9b01431e..a3e0e6f672d6 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -605,7 +605,6 @@ xfs_bmap_btree_to_extents(
ASSERT(cur);
ASSERT(whichfork != XFS_COW_FORK);
- ASSERT(!xfs_need_iread_extents(ifp));
ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
ASSERT(be16_to_cpu(rblock->bb_level) == 1);
ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
@@ -5350,7 +5349,6 @@ __xfs_bunmapi(
xfs_fsblock_t sum;
xfs_filblks_t len = *rlen; /* length to unmap in file */
xfs_fileoff_t max_len;
- xfs_agnumber_t prev_agno = NULLAGNUMBER, agno;
xfs_fileoff_t end;
struct xfs_iext_cursor icur;
bool done = false;
@@ -5442,16 +5440,6 @@ __xfs_bunmapi(
del = got;
wasdel = isnullstartblock(del.br_startblock);
- /*
- * Make sure we don't touch multiple AGF headers out of order
- * in a single transaction, as that could cause AB-BA deadlocks.
- */
- if (!wasdel && !isrt) {
- agno = XFS_FSB_TO_AGNO(mp, del.br_startblock);
- if (prev_agno != NULLAGNUMBER && prev_agno > agno)
- break;
- prev_agno = agno;
- }
if (got.br_startoff < start) {
del.br_startoff = start;
del.br_blockcount -= start - got.br_startoff;
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index a83bdd0c47a8..bde2b4c64dbe 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -770,6 +770,8 @@ struct xfs_scrub_metadata {
/*
* ioctl commands that are used by Linux filesystems
*/
+#define XFS_IOC_GETXFLAGS FS_IOC_GETFLAGS
+#define XFS_IOC_SETXFLAGS FS_IOC_SETFLAGS
#define XFS_IOC_GETVERSION FS_IOC_GETVERSION
/*
@@ -780,6 +782,8 @@ struct xfs_scrub_metadata {
#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64)
#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64)
#define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr)
+#define XFS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
+#define XFS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64)
#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64)
#define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap)
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 5c9a7440d9e4..f3254a4f4cb4 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -559,8 +559,17 @@ xfs_dinode_calc_crc(
/*
* Validate di_extsize hint.
*
- * The rules are documented at xfs_ioctl_setattr_check_extsize().
- * These functions must be kept in sync with each other.
+ * 1. Extent size hint is only valid for directories and regular files.
+ * 2. FS_XFLAG_EXTSIZE is only valid for regular files.
+ * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories.
+ * 4. Hint cannot be larger than MAXTEXTLEN.
+ * 5. Can be changed on directories at any time.
+ * 6. Hint value of 0 turns off hints, clears inode flags.
+ * 7. Extent size must be a multiple of the appropriate block size.
+ * For realtime files, this is the rt extent size.
+ * 8. For non-realtime files, the extent size hint must be limited
+ * to half the AG size to avoid alignment extending the extent beyond the
+ * limits of the AG.
*/
xfs_failaddr_t
xfs_inode_validate_extsize(
@@ -580,6 +589,28 @@ xfs_inode_validate_extsize(
inherit_flag = (flags & XFS_DIFLAG_EXTSZINHERIT);
extsize_bytes = XFS_FSB_TO_B(mp, extsize);
+ /*
+ * This comment describes a historic gap in this verifier function.
+ *
+ * On older kernels, the extent size hint verifier doesn't check that
+ * the extent size hint is an integer multiple of the realtime extent
+ * size on a directory with both RTINHERIT and EXTSZINHERIT flags set.
+ * The verifier has always enforced the alignment rule for regular
+ * files with the REALTIME flag set.
+ *
+ * If a directory with a misaligned extent size hint is allowed to
+ * propagate that hint into a new regular realtime file, the result
+ * is that the inode cluster buffer verifier will trigger a corruption
+ * shutdown the next time it is run.
+ *
+ * Unfortunately, there could be filesystems with these misconfigured
+ * directories in the wild, so we cannot add a check to this verifier
+ * at this time because that will result a new source of directory
+ * corruption errors when reading an existing filesystem. Instead, we
+ * permit the misconfiguration to pass through the verifiers so that
+ * callers of this function can correct and mitigate externally.
+ */
+
if (rt_flag)
blocksize_bytes = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
else
@@ -616,8 +647,15 @@ xfs_inode_validate_extsize(
/*
* Validate di_cowextsize hint.
*
- * The rules are documented at xfs_ioctl_setattr_check_cowextsize().
- * These functions must be kept in sync with each other.
+ * 1. CoW extent size hint can only be set if reflink is enabled on the fs.
+ * The inode does not have to have any shared blocks, but it must be a v3.
+ * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files;
+ * for a directory, the hint is propagated to new files.
+ * 3. Can be changed on files & directories at any time.
+ * 4. Hint value of 0 turns off hints, clears inode flags.
+ * 5. Extent size must be a multiple of the appropriate block size.
+ * 6. The extent size hint must be limited to half the AG size to avoid
+ * alignment extending the extent beyond the limits of the AG.
*/
xfs_failaddr_t
xfs_inode_validate_cowextsize(
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 8bd00da6d2a4..3e15ea29fb8d 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -368,10 +368,10 @@ static inline int xfs_ilog_fdata(int w)
* directly mirrors the xfs_dinode structure as it must contain all the same
* information.
*/
-typedef uint64_t xfs_ictimestamp_t;
+typedef uint64_t xfs_log_timestamp_t;
/* Legacy timestamp encoding format. */
-struct xfs_legacy_ictimestamp {
+struct xfs_log_legacy_timestamp {
int32_t t_sec; /* timestamp seconds */
int32_t t_nsec; /* timestamp nanoseconds */
};
@@ -393,9 +393,9 @@ struct xfs_log_dinode {
uint16_t di_projid_hi; /* higher part of owner's project id */
uint8_t di_pad[6]; /* unused, zeroed space */
uint16_t di_flushiter; /* incremented on flush */
- xfs_ictimestamp_t di_atime; /* time last accessed */
- xfs_ictimestamp_t di_mtime; /* time last modified */
- xfs_ictimestamp_t di_ctime; /* time created/inode modified */
+ xfs_log_timestamp_t di_atime; /* time last accessed */
+ xfs_log_timestamp_t di_mtime; /* time last modified */
+ xfs_log_timestamp_t di_ctime; /* time created/inode modified */
xfs_fsize_t di_size; /* number of bytes in file */
xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */
xfs_extlen_t di_extsize; /* basic/minimum extent size for file */
@@ -420,7 +420,7 @@ struct xfs_log_dinode {
uint8_t di_pad2[12]; /* more padding for future expansion */
/* fields only written to during inode creation */
- xfs_ictimestamp_t di_crtime; /* time created */
+ xfs_log_timestamp_t di_crtime; /* time created */
xfs_ino_t di_ino; /* inode number */
uuid_t di_uuid; /* UUID of the filesystem */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index beb81c84a937..9f5bcbd834c3 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -103,7 +103,6 @@ xfs_rmapbt_alloc_block(
xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agno, bno, 1,
false);
- xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
be32_add_cpu(&agf->agf_rmap_blocks, 1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
@@ -136,7 +135,6 @@ xfs_rmapbt_free_block(
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
- xfs_trans_agbtree_delta(cur->bc_tp, -1);
pag = cur->bc_ag.agbp->b_pag;
xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 60e6d255e5e2..dfbbcbd448c1 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -926,9 +926,19 @@ xfs_log_sb(
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *bp = xfs_trans_getsb(tp);
- mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
- mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
- mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+ /*
+ * Lazy sb counters don't update the in-core superblock so do that now.
+ * If this is at unmount, the counters will be exactly correct, but at
+ * any other time they will only be ballpark correct because of
+ * reservations that have been taken out percpu counters. If we have an
+ * unclean shutdown, this will be corrected by log recovery rebuilding
+ * the counters from the AGF block counts.
+ */
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb)) {
+ mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+ mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
+ mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+ }
xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 78324e043e25..8d595a5c4abd 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -143,6 +143,23 @@ xfs_trans_log_inode(
}
/*
+ * Inode verifiers on older kernels don't check that the extent size
+ * hint is an integer multiple of the rt extent size on a directory
+ * with both rtinherit and extszinherit flags set. If we're logging a
+ * directory that is misconfigured in this way, clear the hint.
+ */
+ if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+ (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
+ (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) {
+ xfs_info_once(ip->i_mount,
+ "Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino);
+ ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
+ XFS_DIFLAG_EXTSZINHERIT);
+ ip->i_extsize = 0;
+ flags |= XFS_ILOG_CORE;
+ }
+
+ /*
* Record the specific change for fdatasync optimisation. This allows
* fdatasync to skip log forces for inodes that are only timestamp
* dirty.
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 749faa17f8e2..7a2f9b5f2db5 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -416,6 +416,10 @@ xchk_agf_xref_btreeblks(
xfs_agblock_t btreeblks;
int error;
+ /* agf_btreeblks didn't exist before lazysbcount */
+ if (!xfs_sb_version_haslazysbcount(&sc->mp->m_sb))
+ return;
+
/* Check agf_rmap_blocks; set up for agf_btreeblks check */
if (sc->sa.rmap_cur) {
error = xfs_btree_count_blocks(sc->sa.rmap_cur, &blocks);
@@ -581,7 +585,8 @@ xchk_agf(
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
if (pag->pagf_flcount != be32_to_cpu(agf->agf_flcount))
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
- if (pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks))
+ if (xfs_sb_version_haslazysbcount(&sc->mp->m_sb) &&
+ pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks))
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
xfs_perag_put(pag);
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index aa874607618a..be38c960da85 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -74,7 +74,9 @@ __xchk_process_error(
return true;
case -EDEADLOCK:
/* Used to restart an op with deadlock avoidance. */
- trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
+ trace_xchk_deadlock_retry(
+ sc->ip ? sc->ip : XFS_I(file_inode(sc->file)),
+ sc->sm, *error);
break;
case -EFSBADCRC:
case -EFSCORRUPTED:
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 7b4386c78fbf..f1d1a8c58853 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -13,6 +13,7 @@
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_health.h"
+#include "xfs_btree.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -143,6 +144,35 @@ xchk_setup_fscounters(
return xchk_trans_alloc(sc, 0);
}
+/* Count free space btree blocks manually for pre-lazysbcount filesystems. */
+static int
+xchk_fscount_btreeblks(
+ struct xfs_scrub *sc,
+ struct xchk_fscounters *fsc,
+ xfs_agnumber_t agno)
+{
+ xfs_extlen_t blocks;
+ int error;
+
+ error = xchk_ag_init(sc, agno, &sc->sa);
+ if (error)
+ return error;
+
+ error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
+ if (error)
+ goto out_free;
+ fsc->fdblocks += blocks - 1;
+
+ error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
+ if (error)
+ goto out_free;
+ fsc->fdblocks += blocks - 1;
+
+out_free:
+ xchk_ag_free(sc, &sc->sa);
+ return error;
+}
+
/*
* Calculate what the global in-core counters ought to be from the incore
* per-AG structure. Callers can compare this to the actual in-core counters
@@ -182,7 +212,15 @@ retry:
/* Add up the free/freelist/bnobt/cntbt blocks */
fsc->fdblocks += pag->pagf_freeblks;
fsc->fdblocks += pag->pagf_flcount;
- fsc->fdblocks += pag->pagf_btreeblks;
+ if (xfs_sb_version_haslazysbcount(&sc->mp->m_sb)) {
+ fsc->fdblocks += pag->pagf_btreeblks;
+ } else {
+ error = xchk_fscount_btreeblks(sc, fsc, agno);
+ if (error) {
+ xfs_perag_put(pag);
+ break;
+ }
+ }
/*
* Per-AG reservations are taken out of the incore counters,
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 9b08db45ce85..826caa6b4a5a 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -146,7 +146,7 @@ xfs_end_io(
while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
io_list))) {
list_del_init(&ioend->io_list);
- iomap_ioend_try_merge(ioend, &tmp, NULL);
+ iomap_ioend_try_merge(ioend, &tmp);
xfs_end_ioend(ioend);
}
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a5e9d7d34023..0936f3a96fe6 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -71,18 +71,24 @@ xfs_zero_extent(
#ifdef CONFIG_XFS_RT
int
xfs_bmap_rtalloc(
- struct xfs_bmalloca *ap) /* bmap alloc argument struct */
+ struct xfs_bmalloca *ap)
{
- int error; /* error return value */
- xfs_mount_t *mp; /* mount point structure */
- xfs_extlen_t prod = 0; /* product factor for allocators */
- xfs_extlen_t mod = 0; /* product factor for allocators */
- xfs_extlen_t ralen = 0; /* realtime allocation length */
- xfs_extlen_t align; /* minimum allocation alignment */
- xfs_rtblock_t rtb;
-
- mp = ap->ip->i_mount;
+ struct xfs_mount *mp = ap->ip->i_mount;
+ xfs_fileoff_t orig_offset = ap->offset;
+ xfs_rtblock_t rtb;
+ xfs_extlen_t prod = 0; /* product factor for allocators */
+ xfs_extlen_t mod = 0; /* product factor for allocators */
+ xfs_extlen_t ralen = 0; /* realtime allocation length */
+ xfs_extlen_t align; /* minimum allocation alignment */
+ xfs_extlen_t orig_length = ap->length;
+ xfs_extlen_t minlen = mp->m_sb.sb_rextsize;
+ xfs_extlen_t raminlen;
+ bool rtlocked = false;
+ bool ignore_locality = false;
+ int error;
+
align = xfs_get_extsz_hint(ap->ip);
+retry:
prod = align / mp->m_sb.sb_rextsize;
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
align, 1, ap->eof, 0,
@@ -93,6 +99,15 @@ xfs_bmap_rtalloc(
ASSERT(ap->length % mp->m_sb.sb_rextsize == 0);
/*
+ * If we shifted the file offset downward to satisfy an extent size
+ * hint, increase minlen by that amount so that the allocator won't
+ * give us an allocation that's too short to cover at least one of the
+ * blocks that the caller asked for.
+ */
+ if (ap->offset != orig_offset)
+ minlen += orig_offset - ap->offset;
+
+ /*
* If the offset & length are not perfectly aligned
* then kill prod, it will just get us in trouble.
*/
@@ -116,10 +131,13 @@ xfs_bmap_rtalloc(
/*
* Lock out modifications to both the RT bitmap and summary inodes
*/
- xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
- xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
- xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
- xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
+ if (!rtlocked) {
+ xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
+ xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+ xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
+ xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
+ rtlocked = true;
+ }
/*
* If it's an allocation to an empty file at offset 0,
@@ -141,33 +159,59 @@ xfs_bmap_rtalloc(
/*
* Realtime allocation, done through xfs_rtallocate_extent.
*/
- do_div(ap->blkno, mp->m_sb.sb_rextsize);
+ if (ignore_locality)
+ ap->blkno = 0;
+ else
+ do_div(ap->blkno, mp->m_sb.sb_rextsize);
rtb = ap->blkno;
ap->length = ralen;
- error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
- &ralen, ap->wasdel, prod, &rtb);
+ raminlen = max_t(xfs_extlen_t, 1, minlen / mp->m_sb.sb_rextsize);
+ error = xfs_rtallocate_extent(ap->tp, ap->blkno, raminlen, ap->length,
+ &ralen, ap->wasdel, prod, &rtb);
if (error)
return error;
- ap->blkno = rtb;
- if (ap->blkno != NULLFSBLOCK) {
- ap->blkno *= mp->m_sb.sb_rextsize;
- ralen *= mp->m_sb.sb_rextsize;
- ap->length = ralen;
- ap->ip->i_nblocks += ralen;
+ if (rtb != NULLRTBLOCK) {
+ ap->blkno = rtb * mp->m_sb.sb_rextsize;
+ ap->length = ralen * mp->m_sb.sb_rextsize;
+ ap->ip->i_nblocks += ap->length;
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel)
- ap->ip->i_delayed_blks -= ralen;
+ ap->ip->i_delayed_blks -= ap->length;
/*
* Adjust the disk quota also. This was reserved
* earlier.
*/
xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
- XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
- } else {
- ap->length = 0;
+ XFS_TRANS_DQ_RTBCOUNT, ap->length);
+ return 0;
}
+
+ if (align > mp->m_sb.sb_rextsize) {
+ /*
+ * We previously enlarged the request length to try to satisfy
+ * an extent size hint. The allocator didn't return anything,
+ * so reset the parameters to the original values and try again
+ * without alignment criteria.
+ */
+ ap->offset = orig_offset;
+ ap->length = orig_length;
+ minlen = align = mp->m_sb.sb_rextsize;
+ goto retry;
+ }
+
+ if (!ignore_locality && ap->blkno != 0) {
+ /*
+ * If we can't allocate near a specific rt extent, try again
+ * without locality criteria.
+ */
+ ignore_locality = true;
+ goto retry;
+ }
+
+ ap->blkno = NULLFSBLOCK;
+ ap->length = 0;
return 0;
}
#endif /* CONFIG_XFS_RT */
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index b33c894b6cf3..be9cf88d2ad7 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -69,8 +69,6 @@ xfs_resizefs_init_new_ags(
if (error)
return error;
- xfs_trans_agblocks_delta(tp, id->nfree);
-
if (delta) {
*lastag_extended = true;
error = xfs_ag_extend_space(mp, tp, id, delta);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0369eb22c1bb..e4c2da4566f1 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -690,6 +690,7 @@ xfs_inode_inherit_flags(
const struct xfs_inode *pip)
{
unsigned int di_flags = 0;
+ xfs_failaddr_t failaddr;
umode_t mode = VFS_I(ip)->i_mode;
if (S_ISDIR(mode)) {
@@ -729,6 +730,24 @@ xfs_inode_inherit_flags(
di_flags |= XFS_DIFLAG_FILESTREAM;
ip->i_diflags |= di_flags;
+
+ /*
+ * Inode verifiers on older kernels only check that the extent size
+ * hint is an integer multiple of the rt extent size on realtime files.
+ * They did not check the hint alignment on a directory with both
+ * rtinherit and extszinherit flags set. If the misaligned hint is
+ * propagated from a directory into a new realtime file, new file
+ * allocations will fail due to math errors in the rt allocator and/or
+ * trip the verifiers. Validate the hint settings in the new file so
+ * that we don't let broken hints propagate.
+ */
+ failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize,
+ VFS_I(ip)->i_mode, ip->i_diflags);
+ if (failaddr) {
+ ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
+ XFS_DIFLAG_EXTSZINHERIT);
+ ip->i_extsize = 0;
+ }
}
/* Propagate di_flags2 from a parent inode to a child inode. */
@@ -737,12 +756,22 @@ xfs_inode_inherit_flags2(
struct xfs_inode *ip,
const struct xfs_inode *pip)
{
+ xfs_failaddr_t failaddr;
+
if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) {
ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
ip->i_cowextsize = pip->i_cowextsize;
}
if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
ip->i_diflags2 |= XFS_DIFLAG2_DAX;
+
+ /* Don't let invalid cowextsize hints propagate. */
+ failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
+ VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2);
+ if (failaddr) {
+ ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE;
+ ip->i_cowextsize = 0;
+ }
}
/*
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index c1b32680f71c..6764d12342da 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -299,18 +299,18 @@ xfs_inode_item_format_attr_fork(
* Convert an incore timestamp to a log timestamp. Note that the log format
* specifies host endian format!
*/
-static inline xfs_ictimestamp_t
+static inline xfs_log_timestamp_t
xfs_inode_to_log_dinode_ts(
struct xfs_inode *ip,
const struct timespec64 tv)
{
- struct xfs_legacy_ictimestamp *lits;
- xfs_ictimestamp_t its;
+ struct xfs_log_legacy_timestamp *lits;
+ xfs_log_timestamp_t its;
if (xfs_inode_has_bigtime(ip))
return xfs_inode_encode_bigtime(tv);
- lits = (struct xfs_legacy_ictimestamp *)&its;
+ lits = (struct xfs_log_legacy_timestamp *)&its;
lits->t_sec = tv.tv_sec;
lits->t_nsec = tv.tv_nsec;
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index cb44f7653f03..7b79518b6c20 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -125,17 +125,17 @@ static inline bool xfs_log_dinode_has_bigtime(const struct xfs_log_dinode *ld)
static inline xfs_timestamp_t
xfs_log_dinode_to_disk_ts(
struct xfs_log_dinode *from,
- const xfs_ictimestamp_t its)
+ const xfs_log_timestamp_t its)
{
struct xfs_legacy_timestamp *lts;
- struct xfs_legacy_ictimestamp *lits;
+ struct xfs_log_legacy_timestamp *lits;
xfs_timestamp_t ts;
if (xfs_log_dinode_has_bigtime(from))
return cpu_to_be64(its);
lts = (struct xfs_legacy_timestamp *)&ts;
- lits = (struct xfs_legacy_ictimestamp *)&its;
+ lits = (struct xfs_log_legacy_timestamp *)&its;
lts->t_sec = cpu_to_be32(lits->t_sec);
lts->t_nsec = cpu_to_be32(lits->t_nsec);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 3925bfcb2365..1fe4c1fc0aea 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1267,20 +1267,8 @@ out_error:
}
/*
- * extent size hint validation is somewhat cumbersome. Rules are:
- *
- * 1. extent size hint is only valid for directories and regular files
- * 2. FS_XFLAG_EXTSIZE is only valid for regular files
- * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories.
- * 4. can only be changed on regular files if no extents are allocated
- * 5. can be changed on directories at any time
- * 6. extsize hint of 0 turns off hints, clears inode flags.
- * 7. Extent size must be a multiple of the appropriate block size.
- * 8. for non-realtime files, the extent size hint must be limited
- * to half the AG size to avoid alignment extending the extent beyond the
- * limits of the AG.
- *
- * Please keep this function in sync with xfs_scrub_inode_extsize.
+ * Validate a proposed extent size hint. For regular files, the hint can only
+ * be changed if no extents are allocated.
*/
static int
xfs_ioctl_setattr_check_extsize(
@@ -1288,86 +1276,65 @@ xfs_ioctl_setattr_check_extsize(
struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
- xfs_extlen_t size;
- xfs_fsblock_t extsize_fsb;
+ xfs_failaddr_t failaddr;
+ uint16_t new_diflags;
if (!fa->fsx_valid)
return 0;
if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents &&
- ((ip->i_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
+ XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize)
return -EINVAL;
- if (fa->fsx_extsize == 0)
- return 0;
-
- extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
- if (extsize_fsb > MAXEXTLEN)
+ if (fa->fsx_extsize & mp->m_blockmask)
return -EINVAL;
- if (XFS_IS_REALTIME_INODE(ip) ||
- (fa->fsx_xflags & FS_XFLAG_REALTIME)) {
- size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
- } else {
- size = mp->m_sb.sb_blocksize;
- if (extsize_fsb > mp->m_sb.sb_agblocks / 2)
+ new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
+
+ /*
+ * Inode verifiers on older kernels don't check that the extent size
+ * hint is an integer multiple of the rt extent size on a directory
+ * with both rtinherit and extszinherit flags set. Don't let sysadmins
+ * misconfigure directories.
+ */
+ if ((new_diflags & XFS_DIFLAG_RTINHERIT) &&
+ (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) {
+ unsigned int rtextsize_bytes;
+
+ rtextsize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize);
+ if (fa->fsx_extsize % rtextsize_bytes)
return -EINVAL;
}
- if (fa->fsx_extsize % size)
- return -EINVAL;
-
- return 0;
+ failaddr = xfs_inode_validate_extsize(ip->i_mount,
+ XFS_B_TO_FSB(mp, fa->fsx_extsize),
+ VFS_I(ip)->i_mode, new_diflags);
+ return failaddr != NULL ? -EINVAL : 0;
}
-/*
- * CoW extent size hint validation rules are:
- *
- * 1. CoW extent size hint can only be set if reflink is enabled on the fs.
- * The inode does not have to have any shared blocks, but it must be a v3.
- * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files;
- * for a directory, the hint is propagated to new files.
- * 3. Can be changed on files & directories at any time.
- * 4. CoW extsize hint of 0 turns off hints, clears inode flags.
- * 5. Extent size must be a multiple of the appropriate block size.
- * 6. The extent size hint must be limited to half the AG size to avoid
- * alignment extending the extent beyond the limits of the AG.
- *
- * Please keep this function in sync with xfs_scrub_inode_cowextsize.
- */
static int
xfs_ioctl_setattr_check_cowextsize(
struct xfs_inode *ip,
struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
- xfs_extlen_t size;
- xfs_fsblock_t cowextsize_fsb;
+ xfs_failaddr_t failaddr;
+ uint64_t new_diflags2;
+ uint16_t new_diflags;
if (!fa->fsx_valid)
return 0;
- if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE))
- return 0;
-
- if (!xfs_sb_version_hasreflink(&ip->i_mount->m_sb))
+ if (fa->fsx_cowextsize & mp->m_blockmask)
return -EINVAL;
- if (fa->fsx_cowextsize == 0)
- return 0;
+ new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
+ new_diflags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
- cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
- if (cowextsize_fsb > MAXEXTLEN)
- return -EINVAL;
-
- size = mp->m_sb.sb_blocksize;
- if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2)
- return -EINVAL;
-
- if (fa->fsx_cowextsize % size)
- return -EINVAL;
-
- return 0;
+ failaddr = xfs_inode_validate_cowextsize(ip->i_mount,
+ XFS_B_TO_FSB(mp, fa->fsx_cowextsize),
+ VFS_I(ip)->i_mode, new_diflags, new_diflags2);
+ return failaddr != NULL ? -EINVAL : 0;
}
static int
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 06041834daa3..c19a82adea1e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -355,13 +355,15 @@ xfs_log_writable(
struct xfs_mount *mp)
{
/*
- * Never write to the log on norecovery mounts, if the block device is
- * read-only, or if the filesystem is shutdown. Read-only mounts still
- * allow internal writes for log recovery and unmount purposes, so don't
- * restrict that case here.
+ * Do not write to the log on norecovery mounts, if the data or log
+ * devices are read-only, or if the filesystem is shutdown. Read-only
+ * mounts allow internal writes for log recovery and unmount purposes,
+ * so don't restrict that case.
*/
if (mp->m_flags & XFS_MOUNT_NORECOVERY)
return false;
+ if (xfs_readonly_buftarg(mp->m_ddev_targp))
+ return false;
if (xfs_readonly_buftarg(mp->m_log->l_targ))
return false;
if (XFS_FORCED_SHUTDOWN(mp))
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index 3c392b1512ac..7ec1a9207517 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -73,6 +73,8 @@ do { \
xfs_printk_once(xfs_warn, dev, fmt, ##__VA_ARGS__)
#define xfs_notice_once(dev, fmt, ...) \
xfs_printk_once(xfs_notice, dev, fmt, ##__VA_ARGS__)
+#define xfs_info_once(dev, fmt, ...) \
+ xfs_printk_once(xfs_info, dev, fmt, ##__VA_ARGS__)
void assfail(struct xfs_mount *mp, char *expr, char *f, int l);
void asswarn(struct xfs_mount *mp, char *expr, char *f, int l);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index cb1e2c4702c3..bdfee1943796 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1188,6 +1188,7 @@ xfs_mod_fdblocks(
int64_t lcounter;
long long res_used;
s32 batch;
+ uint64_t set_aside;
if (delta > 0) {
/*
@@ -1227,8 +1228,20 @@ xfs_mod_fdblocks(
else
batch = XFS_FDBLOCKS_BATCH;
+ /*
+ * Set aside allocbt blocks because these blocks are tracked as free
+ * space but not available for allocation. Technically this means that a
+ * single reservation cannot consume all remaining free space, but the
+ * ratio of allocbt blocks to usable free blocks should be rather small.
+ * The tradeoff without this is that filesystems that maintain high
+ * perag block reservations can over reserve physical block availability
+ * and fail physical allocation, which leads to much more serious
+ * problems (i.e. transaction abort, pagecache discards, etc.) than
+ * slightly premature -ENOSPC.
+ */
+ set_aside = mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
percpu_counter_add_batch(&mp->m_fdblocks, delta, batch);
- if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside,
+ if (__percpu_counter_compare(&mp->m_fdblocks, set_aside,
XFS_FDBLOCKS_BATCH) >= 0) {
/* we had space! */
return 0;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 81829d19596e..bb67274ee23f 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -170,6 +170,12 @@ typedef struct xfs_mount {
* extents or anything related to the rt device.
*/
struct percpu_counter m_delalloc_blks;
+ /*
+ * Global count of allocation btree blocks in use across all AGs. Only
+ * used when perag reservation is enabled. Helps prevent block
+ * reservation from attempting to reserve allocation btree blocks.
+ */
+ atomic64_t m_allocbt_blks;
struct radix_tree_root m_perag_tree; /* per-ag accounting info */
spinlock_t m_perag_lock; /* lock for m_perag_tree */
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index 0aa87c210104..25991923c1a8 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -126,8 +126,8 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode, 176);
XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28);
- XFS_CHECK_STRUCT_SIZE(xfs_ictimestamp_t, 8);
- XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_ictimestamp, 8);
+ XFS_CHECK_STRUCT_SIZE(xfs_log_timestamp_t, 8);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_log_legacy_timestamp, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52);
XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56);
XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 4dd4af6ac2ef..060695d6d56a 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1522,7 +1522,8 @@ xfs_reflink_unshare(
if (error)
goto out;
- error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
+ error = filemap_write_and_wait_range(inode->i_mapping, offset,
+ offset + len - 1);
if (error)
goto out;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index bcc978011869..586f2992b789 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -488,13 +488,6 @@ xfs_trans_apply_sb_deltas(
sbp = bp->b_addr;
/*
- * Check that superblock mods match the mods made to AGF counters.
- */
- ASSERT((tp->t_fdblocks_delta + tp->t_res_fdblocks_delta) ==
- (tp->t_ag_freeblks_delta + tp->t_ag_flist_delta +
- tp->t_ag_btree_delta));
-
- /*
* Only update the superblock counters if we are logging them
*/
if (!xfs_sb_version_haslazysbcount(&(tp->t_mountp->m_sb))) {
@@ -629,6 +622,9 @@ xfs_trans_unreserve_and_mod_sb(
/* apply remaining deltas */
spin_lock(&mp->m_sb_lock);
+ mp->m_sb.sb_fdblocks += tp->t_fdblocks_delta + tp->t_res_fdblocks_delta;
+ mp->m_sb.sb_icount += idelta;
+ mp->m_sb.sb_ifree += ifreedelta;
mp->m_sb.sb_frextents += rtxdelta;
mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
mp->m_sb.sb_agcount += tp->t_agcount_delta;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 9dd745cf77c9..ee42d98d9011 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -140,11 +140,6 @@ typedef struct xfs_trans {
int64_t t_res_fdblocks_delta; /* on-disk only chg */
int64_t t_frextents_delta;/* superblock freextents chg*/
int64_t t_res_frextents_delta; /* on-disk only chg */
-#if defined(DEBUG) || defined(XFS_WARN)
- int64_t t_ag_freeblks_delta; /* debugging counter */
- int64_t t_ag_flist_delta; /* debugging counter */
- int64_t t_ag_btree_delta; /* debugging counter */
-#endif
int64_t t_dblocks_delta;/* superblock dblocks change */
int64_t t_agcount_delta;/* superblock agcount change */
int64_t t_imaxpct_delta;/* superblock imaxpct change */
@@ -165,16 +160,6 @@ typedef struct xfs_trans {
*/
#define xfs_trans_set_sync(tp) ((tp)->t_flags |= XFS_TRANS_SYNC)
-#if defined(DEBUG) || defined(XFS_WARN)
-#define xfs_trans_agblocks_delta(tp, d) ((tp)->t_ag_freeblks_delta += (int64_t)d)
-#define xfs_trans_agflist_delta(tp, d) ((tp)->t_ag_flist_delta += (int64_t)d)
-#define xfs_trans_agbtree_delta(tp, d) ((tp)->t_ag_btree_delta += (int64_t)d)
-#else
-#define xfs_trans_agblocks_delta(tp, d)
-#define xfs_trans_agflist_delta(tp, d)
-#define xfs_trans_agbtree_delta(tp, d)
-#endif
-
/*
* XFS transaction mechanism exported interfaces.
*/