From: yangerkun yangerkun@huawei.com

Offering: HULK hulk inclusion category: bugfix bugzilla: 188870, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

Our growfs test trigger mount error show as below:

[ 40.100164] ------------[ cut here ]------------ [ 40.101808] WARNING: CPU: 5 PID: 769 at fs/xfs/xfs_buf.c:615 xfs_buf_find+0x40d/0x510 ... [ 40.127061] Call Trace: [ 40.127502] xfs_buf_get_map+0x45/0x240 [ 40.128205] xfs_buf_read_map+0x54/0x230 [ 40.129854] xlog_recover_buf_commit_pass2+0x14e/0x490 [ 40.131743] xlog_recover_items_pass2+0x4d/0xa0 [ 40.132605] xlog_recover_commit_trans+0x325/0x350 [ 40.133496] xlog_recovery_process_trans+0xa7/0xe0 [ 40.134408] xlog_recover_process_data+0x8e/0x130 [ 40.135288] xlog_do_recovery_pass+0x3a4/0x730 [ 40.136874] xlog_do_log_recovery+0x62/0xb0 [ 40.137672] xlog_do_recover+0x34/0x1b0 [ 40.138392] xlog_recover+0xd9/0x170 [ 40.139072] xfs_log_mount+0x17f/0x2e0 [ 40.139790] xfs_mountfs+0x3de/0x8a0 [ 40.140473] xfs_fc_fill_super+0x485/0x7f0 [ 40.142095] get_tree_bdev+0x169/0x260 [ 40.142771] vfs_get_tree+0x1f/0xb0 [ 40.143438] do_new_mount+0x15e/0x2d0 [ 40.144141] __x64_sys_mount+0x101/0x140 [ 40.144900] do_syscall_64+0x2d/0x40 [ 40.145591] entry_SYSCALL_64_after_hwframe+0x61/0xc6 ... [ 40.158456] ---[ end trace 0fa38b12a77950ba ]--- [ 40.159354] XFS (loop0): log mount/recovery failed: error -117 [ 40.160956] XFS (loop0): log mount failed

---------------------------> time line +-------------------+----------------+------------------+ | growfs sb item ...|new agi item ...|growfs sb item ...| SHUTDOWN +-------------------+----------------+------------------+ CTX1 CTX2 CTX3

The testcase do multi growfs and then fail the IO which shutdown the xfs. Like the upper order, CTX1 add a new ag, CTX2 may log the agi, CTX3 will do another gorwfs. The sb item may still exist in ail after CTX3 iclog bio success, then the item lsn will change, which may change the tail_lsn.

Then, when we mount the img, and when we recover CTX2, the read for new agi will fail since the ag number still keep invalid.

Fix it by pin the sb lsn as CTX1, and then mount will first replay CTX1.

Signed-off-by: yangerkun yangerkun@huawei.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_buf_item.h | 9 ++++++++- fs/xfs/xfs_trans.c | 14 +++++++++++--- 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3a9e006b7220..245d8d1899dd 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -715,7 +715,7 @@ xfs_buf_item_committed(

trace_xfs_buf_item_committed(bip);

- if ((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) && lip->li_lsn != 0) + if ((bip->bli_flags & XFS_BLI_KEEP_LSN) && lip->li_lsn != 0) return lip->li_lsn; return lsn; } diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 50aa0f5ef959..d890fcef4543 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -17,6 +17,12 @@ #define XFS_BLI_STALE_INODE 0x20 #define XFS_BLI_INODE_BUF 0x40 #define XFS_BLI_ORDERED 0x80 +#define XFS_BLI_GROW_SB_BUF 0x100 + +#define XFS_BLI_KEEP_LSN \ + (XFS_BLI_INODE_ALLOC_BUF | \ + XFS_BLI_GROW_SB_BUF) +

#define XFS_BLI_FLAGS \ { XFS_BLI_HOLD, "HOLD" }, \ @@ -26,7 +32,8 @@ { XFS_BLI_INODE_ALLOC_BUF, "INODE_ALLOC" }, \ { XFS_BLI_STALE_INODE, "STALE_INODE" }, \ { XFS_BLI_INODE_BUF, "INODE_BUF" }, \ - { XFS_BLI_ORDERED, "ORDERED" } + { XFS_BLI_ORDERED, "ORDERED" }, \ + { XFS_BLI_GROW_SB_BUF, "GROW_SB" }

struct xfs_buf; diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 8b6617833c58..12b0163d321c 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -24,6 +24,7 @@ #include "xfs_dquot_item.h" #include "xfs_dquot.h" #include "xfs_icache.h" +#include "xfs_buf_item.h"

kmem_zone_t *xfs_trans_zone;

@@ -478,11 +479,14 @@ STATIC void xfs_trans_apply_sb_deltas( xfs_trans_t *tp) { - xfs_dsb_t *sbp; - xfs_buf_t *bp; - int whole = 0; + xfs_dsb_t *sbp; + xfs_buf_t *bp; + struct xfs_buf_log_item *bip; + int whole = 0; + int grow = 0;

bp = xfs_trans_getsb(tp); + bip = bp->b_log_item; sbp = bp->b_addr;

/* @@ -507,10 +511,12 @@ xfs_trans_apply_sb_deltas( if (tp->t_dblocks_delta) { be64_add_cpu(&sbp->sb_dblocks, tp->t_dblocks_delta); whole = 1; + grow = 1; } if (tp->t_agcount_delta) { be32_add_cpu(&sbp->sb_agcount, tp->t_agcount_delta); whole = 1; + grow = 1; } if (tp->t_imaxpct_delta) { sbp->sb_imax_pct += tp->t_imaxpct_delta; @@ -538,6 +544,8 @@ xfs_trans_apply_sb_deltas( }

xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); + if (grow) + bip->bli_flags |= XFS_BLI_GROW_SB_BUF; if (whole) /* * Log the whole thing, the fields are noncontiguous.

Offering: HULK hulk inclusion category: bugfix bugzilla: 188996, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

Our growfs test trigger mount error show as below:

XFS (dm-3): Starting recovery (logdev: internal) XFS (dm-3): Internal error !ino_ok at line 201 of file fs/xfs/libxfs/xfs_dir2.c. Caller xfs_dir_ino_validate+0x54/0xc0 [xfs] CPU: 0 PID: 3719345 Comm: mount Kdump: loaded Not tainted 5.10.0-136.12.0.86.h1036.kasan.eulerosv2r12.aarch64 #1 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: dump_backtrace+0x0/0x3a4 show_stack+0x34/0x4c dump_stack+0x170/0x1dc xfs_corruption_error+0x104/0x11c [xfs] xfs_dir_ino_validate+0x8c/0xc0 [xfs] __xfs_dir3_data_check+0x5e4/0xb60 [xfs] xfs_dir3_block_verify+0x108/0x190 [xfs] xfs_dir3_block_read_verify+0x10c/0x184 [xfs] xlog_recover_buf_commit_pass2+0x388/0x8e0 [xfs] xlog_recover_items_pass2+0xc8/0x160 [xfs] xlog_recover_commit_trans+0x56c/0x58c [xfs] xlog_recovery_process_trans+0x174/0x180 [xfs] xlog_recover_process_ophdr+0x120/0x210 [xfs] xlog_recover_process_data+0xcc/0x1b4 [xfs] xlog_recover_process+0x124/0x25c [xfs] xlog_do_recovery_pass+0x534/0x864 [xfs] xlog_do_log_recovery+0x98/0xc4 [xfs] xlog_do_recover+0x64/0x2ec [xfs] xlog_recover+0x1c4/0x2f0 [xfs] xfs_log_mount+0x1b8/0x550 [xfs] xfs_mountfs+0x768/0xe40 [xfs] xfs_fc_fill_super+0xb54/0xeb0 [xfs] get_tree_bdev+0x240/0x3e0 xfs_fc_get_tree+0x30/0x40 [xfs] vfs_get_tree+0x5c/0x1a4 do_new_mount+0x1c8/0x220 path_mount+0x2a8/0x3f0 __arm64_sys_mount+0x1cc/0x220 el0_svc_common.constprop.0+0xc0/0x2c4 do_el0_svc+0xb4/0xec el0_svc+0x24/0x3c el0_sync_handler+0x160/0x164 el0_sync+0x160/0x180 XFS (dm-3): Corruption detected. Unmount and run xfs_repair XFS (dm-3): Invalid inode number 0xd00082 XFS (dm-3): Metadata corruption detected at __xfs_dir3_data_check+0xa08/0xb60 [xfs], xfs_dir3_block block 0x100070 XFS (dm-3): Unmount and run xfs_repair XFS (dm-3): First 128 bytes of corrupted metadata buffer: 00000000: 58 44 42 33 f3 c3 ae cf 00 00 00 00 00 10 00 70 XDB3...........p 00000010: 00 00 00 01 00 00 0c 3e 85 a6 68 6c 63 b3 42 30 .......>..hlc.B0 00000020: b0 6b d1 b5 9d eb 55 7d 00 00 00 00 00 10 00 90 .k....U}........ 00000030: 03 60 0b 78 01 40 00 40 00 b0 00 40 00 00 00 00 .`.x.@.@...@.... 00000040: 00 00 00 00 00 10 00 90 01 2e 02 00 00 00 00 40 ...............@ 00000050: 00 00 00 00 00 10 00 81 02 2e 2e 02 00 00 00 50 ...............P 00000060: 00 00 00 00 00 10 00 91 02 66 65 01 00 00 00 60 .........fe....` 00000070: 00 00 00 00 00 10 00 92 02 66 66 01 00 00 00 70 .........ff....p

Consider the following log format, dir3 block has 2 items in the log, and the inode number recorded ondisk in diri3 block exceeds the current file system boundary. When replaying log items, it will skipping replay of first dir3 buffer log item due to the log item LSN being behind the ondisk buffer, but verification is still required. Since the superblock hasn't been replayed yet, the inode number in dir3 block exceeds the file system boundary and causes log recovery to fail.

log record: +---------------+----------------+--------------+-------------------+ | dir3 buf item | growfs sb item | inode item | dir3 buf item .. | +---------------+----------------+--------------+-------------------+ lsn X lsn X+A lsn X+A+B lsn X+A+B+C

metadata block: +-----------+-----------+------------+-----------+-----------+ | sb block | ... | dir3 block | ... | inodes | +-----------+-----------+------------+-----------+-----------+ lsn < X lsn X+A+B+C

Remove buffer read verify during log recovry pass2, clear buffer's XBF_DONE flag, so it can be verified in the next buf read after log recover.

Fixes: d38a530e3710 ("xfs: verify buffer contents when we skip log replay") Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_buf_item_recover.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 9cb79a494d06..d214e0f9cc09 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -950,13 +950,10 @@ xlog_recover_buf_commit_pass2(

/* * We're skipping replay of this buffer log item due to the log - * item LSN being behind the ondisk buffer. Verify the buffer - * contents since we aren't going to run the write verifier. + * item LSN being behind the ondisk buffer. clear XBF_DONE flag + * of the buffer to prevent buffer from being used without verify. */ - if (bp->b_ops) { - bp->b_ops->verify_read(bp); - error = bp->b_error; - } + bp->b_flags &= ~XBF_DONE; goto out_release; }

From: Dave Chinner dchinner@redhat.com

stable inclusion from stable-v5.10.167 commit 8cf9400f8948781cc9175f94666421e77622d639 category: bugfix bugzilla: 188220, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=l...

--------------------------------

commit 0b02c8c0d75a738c98c35f02efb36217c170d78c upstream.

[backport for 5.10.y]

Now that we only call xfs_update_prealloc_flags() from xfs_file_fallocate() in the case where we need to set the preallocation flag, do this in xfs_alloc_file_space() where we already have the inode joined into a transaction and get rid of the call to xfs_update_prealloc_flags() from the fallocate code.

This also means that we now correctly avoid setting the XFS_DIFLAG_PREALLOC flag when xfs_is_always_cow_inode() is true, as these inodes will never have preallocated extents.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

Conflicts: fs/xfs/xfs_bmap_util.c

Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_bmap_util.c | 9 +++------ fs/xfs/xfs_file.c | 8 -------- 2 files changed, 3 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 85d3804ebbe7..a44416597880 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -798,9 +798,6 @@ xfs_alloc_file_space( rblocks = 0; }

- /* - * Allocate and setup the transaction. - */ error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, rblocks, false, &tp); if (error) @@ -817,9 +814,9 @@ xfs_alloc_file_space( if (error) goto error;

- /* - * Complete the transaction - */ + ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a6a59bd6c189..9f52365995c7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -894,7 +894,6 @@ xfs_file_fallocate( struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); long error; - enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; loff_t new_size = 0; bool do_file_insert = false; @@ -992,8 +991,6 @@ xfs_file_fallocate( } do_file_insert = true; } else { - flags |= XFS_PREALLOC_SET; - if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -1044,11 +1041,6 @@ xfs_file_fallocate( if (error) goto out_unlock; } - - error = xfs_update_prealloc_flags(ip, XFS_PREALLOC_SET); - if (error) - goto out_unlock; - }

/* Change file size if needed */

From: Gaosheng Cui cuigaosheng1@huawei.com

stable inclusion from stable-v5.10.167 commit daa97e770e780b5e74d85afd236849359711a8d0 category: bugfix bugzilla: 188220, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=l...

--------------------------------

commit b0463b9dd7030a766133ad2f1571f97f204d7bdf upstream.

xfs_setattr_time() has been removed since commit e014f37db1a2 ("xfs: use setattr_copy to set vfs inode attributes"), so remove it.

Signed-off-by: Gaosheng Cui cuigaosheng1@huawei.com Reviewed-by: Carlos Maiolino cmaiolino@redhat.com Signed-off-by: Dave Chinner david@fromorbit.com Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_iops.h | 1 - 1 file changed, 1 deletion(-)

diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index fb3604b68208..42aab2a39a95 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -18,7 +18,6 @@ extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); */ #define XFS_ATTR_NOACL 0x01 /* Don't call posix_acl_chmod */

-extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr); extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap, int flags); extern int xfs_vn_setattr_nonsize(struct dentry *dentry, struct iattr *vap);

From: "Darrick J. Wong" djwong@kernel.org

mainline inclusion from mainline-v5.15-rc4 commit 182696fb021fc196e5cbe641565ca40fcf0f885a category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Now that we've gotten rid of the kmem_zone_t typedef, rename the variables to _cache since that's what they are.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Chandan Babu R chandan.babu@oracle.com

Conflicts: fs/xfs/libxfs/xfs_attr_leaf.c fs/xfs/libxfs/xfs_inode_fork.c fs/xfs/libxfs/xfs_btree.h fs/xfs/libxfs/xfs_ialloc_btree.c fs/xfs/libxfs/xfs_alloc_btree.c fs/xfs/libxfs/xfs_rmap_btree.c fs/xfs/libxfs/xfs_refcount_btree.c fs/xfs/libxfs/xfs_bmap_btree.c fs/xfs/xfs_attr_inactive.c fs/xfs/xfs_bmap_item.c fs/xfs/xfs_icache.c fs/xfs/xfs_icreate_item.c fs/xfs/xfs_refcount_item.c fs/xfs/xfs_rmap_item.c fs/xfs/xfs_super.c Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 6 +- fs/xfs/libxfs/xfs_alloc_btree.c | 2 +- fs/xfs/libxfs/xfs_bmap.c | 6 +- fs/xfs/libxfs/xfs_bmap.h | 2 +- fs/xfs/libxfs/xfs_bmap_btree.c | 2 +- fs/xfs/libxfs/xfs_btree.c | 4 +- fs/xfs/libxfs/xfs_btree.h | 2 +- fs/xfs/libxfs/xfs_da_btree.c | 6 +- fs/xfs/libxfs/xfs_da_btree.h | 3 +- fs/xfs/libxfs/xfs_ialloc_btree.c | 2 +- fs/xfs/libxfs/xfs_inode_fork.c | 4 +- fs/xfs/libxfs/xfs_inode_fork.h | 2 +- fs/xfs/libxfs/xfs_refcount_btree.c | 2 +- fs/xfs/libxfs/xfs_rmap_btree.c | 2 +- fs/xfs/xfs_bmap_item.c | 12 +- fs/xfs/xfs_bmap_item.h | 4 +- fs/xfs/xfs_buf.c | 16 +- fs/xfs/xfs_buf_item.c | 8 +- fs/xfs/xfs_buf_item.h | 2 +- fs/xfs/xfs_dquot.c | 26 ++-- fs/xfs/xfs_extfree_item.c | 18 +-- fs/xfs/xfs_extfree_item.h | 4 +- fs/xfs/xfs_icache.c | 8 +- fs/xfs/xfs_icreate_item.c | 6 +- fs/xfs/xfs_icreate_item.h | 2 +- fs/xfs/xfs_inode.c | 2 +- fs/xfs/xfs_inode.h | 2 +- fs/xfs/xfs_inode_item.c | 6 +- fs/xfs/xfs_inode_item.h | 2 +- fs/xfs/xfs_log.c | 6 +- fs/xfs/xfs_log_priv.h | 2 +- fs/xfs/xfs_mru_cache.c | 2 +- fs/xfs/xfs_qm.h | 2 +- fs/xfs/xfs_refcount_item.c | 12 +- fs/xfs/xfs_refcount_item.h | 4 +- fs/xfs/xfs_rmap_item.c | 12 +- fs/xfs/xfs_rmap_item.h | 4 +- fs/xfs/xfs_super.c | 226 ++++++++++++++--------------- fs/xfs/xfs_trans.c | 8 +- fs/xfs/xfs_trans.h | 2 +- fs/xfs/xfs_trans_dquot.c | 4 +- 41 files changed, 223 insertions(+), 224 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 5a09e343c753..9d1097331b49 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -27,7 +27,7 @@ #include "xfs_ag_resv.h" #include "xfs_bmap.h"

-extern struct kmem_cache *xfs_bmap_free_item_zone; +extern struct kmem_cache *xfs_bmap_free_item_cache;

struct workqueue_struct *xfs_alloc_wq;

@@ -2468,10 +2468,10 @@ xfs_defer_agfl_block( struct xfs_mount *mp = tp->t_mountp; struct xfs_extent_free_item *new; /* new element */

- ASSERT(xfs_bmap_free_item_zone != NULL); + ASSERT(xfs_bmap_free_item_cache != NULL); ASSERT(oinfo != NULL);

- new = kmem_cache_alloc(xfs_bmap_free_item_zone, + new = kmem_cache_alloc(xfs_bmap_free_item_cache, GFP_KERNEL | __GFP_NOFAIL); new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); new->xefi_blockcount = 1; diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 4452b4255917..613a1743fdd5 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -480,7 +480,7 @@ xfs_allocbt_init_common(

ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);

- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL); + cur = kmem_cache_zalloc(xfs_btree_cur_cache, GFP_NOFS | __GFP_NOFAIL);

cur->bc_tp = tp; cur->bc_mp = mp; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 1cfd57809a35..180c212c862b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -37,7 +37,7 @@ #include "xfs_iomap.h"

-struct kmem_cache *xfs_bmap_free_item_zone; +struct kmem_cache *xfs_bmap_free_item_cache;

/* * Miscellaneous helper functions @@ -551,9 +551,9 @@ __xfs_bmap_add_free( ASSERT(len < mp->m_sb.sb_agblocks); ASSERT(agbno + len <= mp->m_sb.sb_agblocks); #endif - ASSERT(xfs_bmap_free_item_zone != NULL); + ASSERT(xfs_bmap_free_item_cache != NULL);

- new = kmem_cache_alloc(xfs_bmap_free_item_zone, + new = kmem_cache_alloc(xfs_bmap_free_item_cache, GFP_KERNEL | __GFP_NOFAIL); new->xefi_startblock = bno; new->xefi_blockcount = (xfs_extlen_t)len; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 522d384a1fa7..05c5db07d9fa 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -13,7 +13,7 @@ struct xfs_inode; struct xfs_mount; struct xfs_trans;

-extern struct kmem_cache *xfs_bmap_free_item_zone; +extern struct kmem_cache *xfs_bmap_free_item_cache;

/* * Argument structure for xfs_bmap_alloc. diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 64a3cbcb22a2..65762ae9b40a 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -552,7 +552,7 @@ xfs_bmbt_init_cursor( struct xfs_btree_cur *cur; ASSERT(whichfork != XFS_COW_FORK);

- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL); + cur = kmem_cache_zalloc(xfs_btree_cur_cache, GFP_NOFS | __GFP_NOFAIL);

cur->bc_tp = tp; cur->bc_mp = mp; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index b9bf326a6f59..04ab18e209fb 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -25,7 +25,7 @@ /* * Cursor allocation zone. */ -struct kmem_cache *xfs_btree_cur_zone; +struct kmem_cache *xfs_btree_cur_cache;

/* * Btree magic numbers. @@ -454,7 +454,7 @@ xfs_btree_del_cursor( xfs_is_shutdown(cur->bc_mp) || error != 0); if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) kmem_free(cur->bc_ops); - kmem_cache_free(xfs_btree_cur_zone, cur); + kmem_cache_free(xfs_btree_cur_cache, cur); }

/* diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 08e53dbc8963..d172046ae833 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -12,7 +12,7 @@ struct xfs_mount; struct xfs_trans; struct xfs_ifork;

-extern struct kmem_cache *xfs_btree_cur_zone; +extern struct kmem_cache *xfs_btree_cur_cache;

/* * Generic key, ptr and record wrapper structures. diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index b7e7c24f7092..f1258e294ead 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -72,7 +72,7 @@ STATIC int xfs_da3_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *save_blk);

-struct kmem_cache *xfs_da_state_zone; /* anchor for state struct zone */ +struct kmem_cache *xfs_da_state_cache; /* anchor for dir/attr state */

/* * Allocate a dir-state structure. @@ -84,7 +84,7 @@ xfs_da_state_alloc( { struct xfs_da_state *state;

- state = kmem_cache_zalloc(xfs_da_state_zone, GFP_NOFS | __GFP_NOFAIL); + state = kmem_cache_zalloc(xfs_da_state_cache, GFP_NOFS | __GFP_NOFAIL); state->args = args; state->mp = args->dp->i_mount; return state; @@ -113,7 +113,7 @@ xfs_da_state_free(xfs_da_state_t *state) #ifdef DEBUG memset((char *)state, 0, sizeof(*state)); #endif /* DEBUG */ - kmem_cache_free(xfs_da_state_zone, state); + kmem_cache_free(xfs_da_state_cache, state); }

static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index cf9c5c8d6626..6902fdda184e 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -9,7 +9,6 @@

struct xfs_inode; struct xfs_trans; -struct zone;

/* * Directory/attribute geometry information. There will be one of these for each @@ -238,6 +237,6 @@ void xfs_da3_node_hdr_from_disk(struct xfs_mount *mp, void xfs_da3_node_hdr_to_disk(struct xfs_mount *mp, struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);

-extern struct kmem_cache *xfs_da_state_zone; +extern struct kmem_cache *xfs_da_state_cache;

#endif /* __XFS_DA_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index e554b58abc65..0733270062f6 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -432,7 +432,7 @@ xfs_inobt_init_common( { struct xfs_btree_cur *cur;

- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL); + cur = kmem_cache_zalloc(xfs_btree_cur_cache, GFP_NOFS | __GFP_NOFAIL); cur->bc_tp = tp; cur->bc_mp = mp; cur->bc_btnum = btnum; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index d083654e3197..26a1696e1bce 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -25,7 +25,7 @@ #include "xfs_attr_leaf.h" #include "xfs_types.h"

-struct kmem_cache *xfs_ifork_zone; +struct kmem_cache *xfs_ifork_cache;

void xfs_init_local_fork( @@ -688,7 +688,7 @@ xfs_ifork_init_cow( if (ip->i_cowfp) return;

- ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_zone, + ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_cache, GFP_NOFS | __GFP_NOFAIL); ip->i_cowfp->if_flags = XFS_IFEXTENTS; ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS; diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 910c895ed5a2..fe2324c53855 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -211,7 +211,7 @@ static inline bool xfs_iext_peek_prev_extent(struct xfs_ifork *ifp, xfs_iext_get_extent((ifp), (ext), (got)); \ xfs_iext_next((ifp), (ext)))

-extern struct kmem_cache *xfs_ifork_zone; +extern struct kmem_cache *xfs_ifork_cache;

extern void xfs_ifork_init_cow(struct xfs_inode *ip);

diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 679f5d9763da..59b1fee4f680 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -323,7 +323,7 @@ xfs_refcountbt_init_common( ASSERT(agno != NULLAGNUMBER); ASSERT(agno < mp->m_sb.sb_agcount);

- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL); + cur = kmem_cache_zalloc(xfs_btree_cur_cache, GFP_NOFS | __GFP_NOFAIL); cur->bc_tp = tp; cur->bc_mp = mp; cur->bc_btnum = XFS_BTNUM_REFC; diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 19cb2c11a3a3..97c519ede1d6 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -454,7 +454,7 @@ xfs_rmapbt_init_common( { struct xfs_btree_cur *cur;

- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL); + cur = kmem_cache_zalloc(xfs_btree_cur_cache, GFP_NOFS | __GFP_NOFAIL); cur->bc_tp = tp; cur->bc_mp = mp; /* Overlapping btree; 2 keys per pointer. */ diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 201233a5e19e..ec3c3c43b4f9 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -26,8 +26,8 @@ #include "xfs_log_recover.h" #include "xfs_quota.h"

-struct kmem_cache *xfs_bui_zone; -struct kmem_cache *xfs_bud_zone; +struct kmem_cache *xfs_bui_cache; +struct kmem_cache *xfs_bud_cache;

static const struct xfs_item_ops xfs_bui_item_ops;

@@ -41,7 +41,7 @@ xfs_bui_item_free( struct xfs_bui_log_item *buip) { kmem_free(buip->bui_item.li_lv_shadow); - kmem_cache_free(xfs_bui_zone, buip); + kmem_cache_free(xfs_bui_cache, buip); }

/* @@ -140,7 +140,7 @@ xfs_bui_init( { struct xfs_bui_log_item *buip;

- buip = kmem_cache_zalloc(xfs_bui_zone, GFP_KERNEL | __GFP_NOFAIL); + buip = kmem_cache_zalloc(xfs_bui_cache, GFP_KERNEL | __GFP_NOFAIL);

xfs_log_item_init(mp, &buip->bui_item, XFS_LI_BUI, &xfs_bui_item_ops); buip->bui_format.bui_nextents = XFS_BUI_MAX_FAST_EXTENTS; @@ -201,7 +201,7 @@ xfs_bud_item_release(

xfs_bui_release(budp->bud_buip); kmem_free(budp->bud_item.li_lv_shadow); - kmem_cache_free(xfs_bud_zone, budp); + kmem_cache_free(xfs_bud_cache, budp); }

static const struct xfs_item_ops xfs_bud_item_ops = { @@ -218,7 +218,7 @@ xfs_trans_get_bud( { struct xfs_bud_log_item *budp;

- budp = kmem_cache_zalloc(xfs_bud_zone, GFP_KERNEL | __GFP_NOFAIL); + budp = kmem_cache_zalloc(xfs_bud_cache, GFP_KERNEL | __GFP_NOFAIL); xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD, &xfs_bud_item_ops); budp->bud_buip = buip; diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h index 6af6b02d4b66..3fafd3881a0b 100644 --- a/fs/xfs/xfs_bmap_item.h +++ b/fs/xfs/xfs_bmap_item.h @@ -65,7 +65,7 @@ struct xfs_bud_log_item { struct xfs_bud_log_format bud_format; };

-extern struct kmem_cache *xfs_bui_zone; -extern struct kmem_cache *xfs_bud_zone; +extern struct kmem_cache *xfs_bui_cache; +extern struct kmem_cache *xfs_bud_cache;

#endif /* __XFS_BMAP_ITEM_H__ */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 798a8ce0cc76..af5dc20c5e27 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -21,7 +21,7 @@ #include "xfs_errortag.h" #include "xfs_error.h"

-static struct kmem_cache *xfs_buf_zone; +static struct kmem_cache *xfs_buf_cache;

#define xb_to_gfp(flags) \ ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN) @@ -224,7 +224,7 @@ _xfs_buf_alloc( int i;

*bpp = NULL; - bp = kmem_cache_zalloc(xfs_buf_zone, GFP_NOFS | __GFP_NOFAIL); + bp = kmem_cache_zalloc(xfs_buf_cache, GFP_NOFS | __GFP_NOFAIL);

/* * We don't want certain flags to appear in b_flags unless they are @@ -251,7 +251,7 @@ _xfs_buf_alloc( */ error = xfs_buf_get_maps(bp, nmaps); if (error) { - kmem_cache_free(xfs_buf_zone, bp); + kmem_cache_free(xfs_buf_cache, bp); return error; }

@@ -345,7 +345,7 @@ xfs_buf_free( kmem_free(bp->b_addr); _xfs_buf_free_pages(bp); xfs_buf_free_maps(bp); - kmem_cache_free(xfs_buf_zone, bp); + kmem_cache_free(xfs_buf_cache, bp); }

/* @@ -1005,7 +1005,7 @@ xfs_buf_get_uncached( _xfs_buf_free_pages(bp); fail_free_buf: xfs_buf_free_maps(bp); - kmem_cache_free(xfs_buf_zone, bp); + kmem_cache_free(xfs_buf_cache, bp); fail: return error; } @@ -2344,12 +2344,12 @@ xfs_buf_delwri_pushbuf( int __init xfs_buf_init(void) { - xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, + xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL); - if (!xfs_buf_zone) + if (!xfs_buf_cache) goto out;

return 0; @@ -2361,7 +2361,7 @@ xfs_buf_init(void) void xfs_buf_terminate(void) { - kmem_cache_destroy(xfs_buf_zone); + kmem_cache_destroy(xfs_buf_cache); }

void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 8621b75a7a4f..7826028a5861 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -24,7 +24,7 @@ #include "xfs_log_priv.h"

-struct kmem_cache *xfs_buf_item_zone; +struct kmem_cache *xfs_buf_item_cache;

static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip) { @@ -786,7 +786,7 @@ xfs_buf_item_init( return 0; }

- bip = kmem_cache_zalloc(xfs_buf_item_zone, GFP_KERNEL | __GFP_NOFAIL); + bip = kmem_cache_zalloc(xfs_buf_item_cache, GFP_KERNEL | __GFP_NOFAIL); xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops); bip->bli_buf = bp;

@@ -807,7 +807,7 @@ xfs_buf_item_init( map_size = DIV_ROUND_UP(chunks, NBWORD);

if (map_size > XFS_BLF_DATAMAP_SIZE) { - kmem_cache_free(xfs_buf_item_zone, bip); + kmem_cache_free(xfs_buf_item_cache, bip); xfs_err(mp, "buffer item dirty bitmap (%u uints) too small to reflect %u bytes!", map_size, @@ -984,7 +984,7 @@ xfs_buf_item_free( { xfs_buf_item_free_format(bip); kmem_free(bip->bli_item.li_lv_shadow); - kmem_cache_free(xfs_buf_item_zone, bip); + kmem_cache_free(xfs_buf_item_cache, bip); }

/* diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 7b3db6f5a9f0..30f55e133696 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -78,6 +78,6 @@ static inline void xfs_buf_dquot_io_fail(struct xfs_buf *bp) void xfs_buf_iodone(struct xfs_buf *); bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);

-extern struct kmem_cache *xfs_buf_item_zone; +extern struct kmem_cache *xfs_buf_item_cache;

#endif /* __XFS_BUF_ITEM_H__ */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index a829a79231ec..da8ab127d161 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -38,8 +38,8 @@ * otherwise by the lowest id first, see xfs_dqlock2. */

-struct kmem_cache *xfs_qm_dqtrxzone; -static struct kmem_cache *xfs_qm_dqzone; +struct kmem_cache *xfs_dqtrx_cache; +static struct kmem_cache *xfs_dquot_cache;

static struct lock_class_key xfs_dquot_group_class; static struct lock_class_key xfs_dquot_project_class; @@ -57,7 +57,7 @@ xfs_qm_dqdestroy( mutex_destroy(&dqp->q_qlock);

XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot); - kmem_cache_free(xfs_qm_dqzone, dqp); + kmem_cache_free(xfs_dquot_cache, dqp); }

/* @@ -458,7 +458,7 @@ xfs_dquot_alloc( { struct xfs_dquot *dqp;

- dqp = kmem_cache_zalloc(xfs_qm_dqzone, GFP_KERNEL | __GFP_NOFAIL); + dqp = kmem_cache_zalloc(xfs_dquot_cache, GFP_KERNEL | __GFP_NOFAIL);

dqp->q_type = type; dqp->q_id = id; @@ -1365,22 +1365,22 @@ xfs_dqlock2( int __init xfs_qm_init(void) { - xfs_qm_dqzone = kmem_cache_create("xfs_dquot", + xfs_dquot_cache = kmem_cache_create("xfs_dquot", sizeof(struct xfs_dquot), 0, 0, NULL); - if (!xfs_qm_dqzone) + if (!xfs_dquot_cache) goto out;

- xfs_qm_dqtrxzone = kmem_cache_create("xfs_dqtrx", + xfs_dqtrx_cache = kmem_cache_create("xfs_dqtrx", sizeof(struct xfs_dquot_acct), 0, 0, NULL); - if (!xfs_qm_dqtrxzone) - goto out_free_dqzone; + if (!xfs_dqtrx_cache) + goto out_free_dquot_cache;

return 0;

-out_free_dqzone: - kmem_cache_destroy(xfs_qm_dqzone); +out_free_dquot_cache: + kmem_cache_destroy(xfs_dquot_cache); out: return -ENOMEM; } @@ -1388,8 +1388,8 @@ xfs_qm_init(void) void xfs_qm_exit(void) { - kmem_cache_destroy(xfs_qm_dqtrxzone); - kmem_cache_destroy(xfs_qm_dqzone); + kmem_cache_destroy(xfs_dqtrx_cache); + kmem_cache_destroy(xfs_dquot_cache); }

/* diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index c2430ac399f3..4bcdc363ec12 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -25,8 +25,8 @@ #include "xfs_log_priv.h" #include "xfs_log_recover.h"

-struct kmem_cache *xfs_efi_zone; -struct kmem_cache *xfs_efd_zone; +struct kmem_cache *xfs_efi_cache; +struct kmem_cache *xfs_efd_cache;

static const struct xfs_item_ops xfs_efi_item_ops;

@@ -43,7 +43,7 @@ xfs_efi_item_free( if (efip->efi_format.efi_nextents > XFS_EFI_MAX_FAST_EXTENTS) kmem_free(efip); else - kmem_cache_free(xfs_efi_zone, efip); + kmem_cache_free(xfs_efi_cache, efip); }

/* @@ -161,7 +161,7 @@ xfs_efi_init( (nextents * sizeof(xfs_extent_t))); efip = kmem_zalloc(size, 0); } else { - efip = kmem_cache_zalloc(xfs_efi_zone, + efip = kmem_cache_zalloc(xfs_efi_cache, GFP_KERNEL | __GFP_NOFAIL); }

@@ -246,7 +246,7 @@ xfs_efd_item_free(struct xfs_efd_log_item *efdp) if (efdp->efd_format.efd_nextents > XFS_EFD_MAX_FAST_EXTENTS) kmem_free(efdp); else - kmem_cache_free(xfs_efd_zone, efdp); + kmem_cache_free(xfs_efd_cache, efdp); }

/* @@ -338,7 +338,7 @@ xfs_trans_get_efd( nextents * sizeof(struct xfs_extent), 0); } else { - efdp = kmem_cache_zalloc(xfs_efd_zone, + efdp = kmem_cache_zalloc(xfs_efd_cache, GFP_KERNEL | __GFP_NOFAIL); }

@@ -487,7 +487,7 @@ xfs_extent_free_finish_item( free->xefi_startblock, free->xefi_blockcount, &free->xefi_oinfo, free->xefi_skip_discard); - kmem_cache_free(xfs_bmap_free_item_zone, free); + kmem_cache_free(xfs_bmap_free_item_cache, free); return error; }

@@ -507,7 +507,7 @@ xfs_extent_free_cancel_item( struct xfs_extent_free_item *free;

free = container_of(item, struct xfs_extent_free_item, xefi_list); - kmem_cache_free(xfs_bmap_free_item_zone, free); + kmem_cache_free(xfs_bmap_free_item_cache, free); }

const struct xfs_defer_op_type xfs_extent_free_defer_type = { @@ -569,7 +569,7 @@ xfs_agfl_free_finish_item( extp->ext_len = free->xefi_blockcount; efdp->efd_next_extent++;

- kmem_cache_free(xfs_bmap_free_item_zone, free); + kmem_cache_free(xfs_bmap_free_item_cache, free); return error; }

diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h index e8644945290e..186d0f2137f1 100644 --- a/fs/xfs/xfs_extfree_item.h +++ b/fs/xfs/xfs_extfree_item.h @@ -69,7 +69,7 @@ struct xfs_efd_log_item { */ #define XFS_EFD_MAX_FAST_EXTENTS 16

-extern struct kmem_cache *xfs_efi_zone; -extern struct kmem_cache *xfs_efd_zone; +extern struct kmem_cache *xfs_efi_cache; +extern struct kmem_cache *xfs_efd_cache;

#endif /* __XFS_EXTFREE_ITEM_H__ */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 6847bbb5a735..bdf55ed88680 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -87,10 +87,10 @@ xfs_inode_alloc( * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL * and return NULL here on ENOMEM. */ - ip = kmem_cache_alloc(xfs_inode_zone, GFP_KERNEL | __GFP_NOFAIL); + ip = kmem_cache_alloc(xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL);

if (inode_init_always(mp->m_super, VFS_I(ip))) { - kmem_cache_free(xfs_inode_zone, ip); + kmem_cache_free(xfs_inode_cache, ip); return NULL; }

@@ -141,7 +141,7 @@ xfs_inode_free_callback(

if (ip->i_cowfp) { xfs_idestroy_fork(ip->i_cowfp); - kmem_cache_free(xfs_ifork_zone, ip->i_cowfp); + kmem_cache_free(xfs_ifork_cache, ip->i_cowfp); } if (ip->i_itemp) { ASSERT(!test_bit(XFS_LI_IN_AIL, @@ -150,7 +150,7 @@ xfs_inode_free_callback( ip->i_itemp = NULL; }

- kmem_cache_free(xfs_inode_zone, ip); + kmem_cache_free(xfs_inode_cache, ip); }

static void diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c index 288c3af1b8e9..cd90b4f31495 100644 --- a/fs/xfs/xfs_icreate_item.c +++ b/fs/xfs/xfs_icreate_item.c @@ -20,7 +20,7 @@ #include "xfs_ialloc.h" #include "xfs_trace.h"

-struct kmem_cache *xfs_icreate_zone; /* inode create item zone */ +struct kmem_cache *xfs_icreate_cache; /* inode create item */

static inline struct xfs_icreate_item *ICR_ITEM(struct xfs_log_item *lip) { @@ -64,7 +64,7 @@ xfs_icreate_item_release( struct xfs_log_item *lip) { kmem_free(ICR_ITEM(lip)->ic_item.li_lv_shadow); - kmem_cache_free(xfs_icreate_zone, ICR_ITEM(lip)); + kmem_cache_free(xfs_icreate_cache, ICR_ITEM(lip)); }

static const struct xfs_item_ops xfs_icreate_item_ops = { @@ -98,7 +98,7 @@ xfs_icreate_log( { struct xfs_icreate_item *icp;

- icp = kmem_cache_zalloc(xfs_icreate_zone, GFP_KERNEL | __GFP_NOFAIL); + icp = kmem_cache_zalloc(xfs_icreate_cache, GFP_KERNEL | __GFP_NOFAIL);

xfs_log_item_init(tp->t_mountp, &icp->ic_item, XFS_LI_ICREATE, &xfs_icreate_item_ops); diff --git a/fs/xfs/xfs_icreate_item.h b/fs/xfs/xfs_icreate_item.h index 944427b33645..64992823108a 100644 --- a/fs/xfs/xfs_icreate_item.h +++ b/fs/xfs/xfs_icreate_item.h @@ -12,7 +12,7 @@ struct xfs_icreate_item { struct xfs_icreate_log ic_format; };

-extern struct kmem_cache *xfs_icreate_zone; /* inode create item zone */ +extern struct kmem_cache *xfs_icreate_cache; /* inode create item */

void xfs_icreate_log(struct xfs_trans *tp, xfs_agnumber_t agno, xfs_agblock_t agbno, unsigned int count, diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 9f7cafc6f737..268bbc2d978b 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -37,7 +37,7 @@ #include "xfs_reflink.h" #include "xfs_log_priv.h"

-struct kmem_cache *xfs_inode_zone; +struct kmem_cache *xfs_inode_cache;

/* * Used in xfs_itruncate_extents(). This is the maximum number of extents diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index e320f1e0290f..b552daae323f 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -546,7 +546,7 @@ static inline void xfs_setup_existing_inode(struct xfs_inode *ip)

void xfs_irele(struct xfs_inode *ip);

-extern struct kmem_cache *xfs_inode_zone; +extern struct kmem_cache *xfs_inode_cache;

/* The default CoW extent size hint. */ #define XFS_DEFAULT_COWEXTSZ_HINT 32 diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index c3ffb9536393..9f496cdcde3b 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -22,7 +22,7 @@

#include <linux/iversion.h>

-struct kmem_cache *xfs_ili_zone; /* inode log item zone */ +struct kmem_cache *xfs_ili_cache; /* inode log item */

static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip) { @@ -661,7 +661,7 @@ xfs_inode_item_init( struct xfs_inode_log_item *iip;

ASSERT(ip->i_itemp == NULL); - iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_zone, + iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_cache, GFP_KERNEL | __GFP_NOFAIL);

iip->ili_inode = ip; @@ -683,7 +683,7 @@ xfs_inode_item_destroy(

ip->i_itemp = NULL; kmem_free(iip->ili_item.li_lv_shadow); - kmem_cache_free(xfs_ili_zone, iip); + kmem_cache_free(xfs_ili_cache, iip); }

diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 35f2be490287..bbd836a44ff0 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -48,6 +48,6 @@ extern void xfs_iflush_shutdown_abort(struct xfs_inode *); extern int xfs_inode_item_format_convert(xfs_log_iovec_t *, struct xfs_inode_log_format *);

-extern struct kmem_cache *xfs_ili_zone; +extern struct kmem_cache *xfs_ili_cache;

#endif /* __XFS_INODE_ITEM_H__ */ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 8cd7bf27f965..c9bfafd0b9f5 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -21,7 +21,7 @@ #include "xfs_sb.h" #include "xfs_health.h"

-struct kmem_cache *xfs_log_ticket_zone; +struct kmem_cache *xfs_log_ticket_cache;

/* Local miscellaneous function prototypes */ STATIC struct xlog * @@ -3397,7 +3397,7 @@ xfs_log_ticket_put( { ASSERT(atomic_read(&ticket->t_ref) > 0); if (atomic_dec_and_test(&ticket->t_ref)) - kmem_cache_free(xfs_log_ticket_zone, ticket); + kmem_cache_free(xfs_log_ticket_cache, ticket); }

xlog_ticket_t * @@ -3521,7 +3521,7 @@ xlog_ticket_alloc( struct xlog_ticket *tic; int unit_res;

- tic = kmem_cache_zalloc(xfs_log_ticket_zone, GFP_NOFS | __GFP_NOFAIL); + tic = kmem_cache_zalloc(xfs_log_ticket_cache, GFP_NOFS | __GFP_NOFAIL);

unit_res = xlog_calc_unit_res(log, unit_bytes);

diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index fe399acc0463..ee004a779d36 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -502,7 +502,7 @@ xlog_recover_cancel(struct xlog *); extern __le32 xlog_cksum(struct xlog *log, struct xlog_rec_header *rhead, char *dp, int size);

-extern struct kmem_cache *xfs_log_ticket_zone; +extern struct kmem_cache *xfs_log_ticket_cache; struct xlog_ticket * xlog_ticket_alloc( struct xlog *log, diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index 34c3b16f834f..f85e3b07ab44 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -219,7 +219,7 @@ _xfs_mru_cache_list_insert( * When destroying or reaping, all the elements that were migrated to the reap * list need to be deleted. For each element this involves removing it from the * data store, removing it from the reap list, calling the client's free - * function and deleting the element from the element zone. + * function and deleting the element from the element cache. * * We get called holding the mru->lock, which we drop and then reacquire. * Sparse need special help with this to tell it we know what we are doing. diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 5e8b70526538..5bb12717ea28 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -11,7 +11,7 @@

struct xfs_inode;

-extern struct kmem_cache *xfs_qm_dqtrxzone; +extern struct kmem_cache *xfs_dqtrx_cache;

/* * Number of bmaps that we ask from bmapi when doing a quotacheck. diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index ccfcc91d616e..09efa723ddfa 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -21,8 +21,8 @@ #include "xfs_log_priv.h" #include "xfs_log_recover.h"

-struct kmem_cache *xfs_cui_zone; -struct kmem_cache *xfs_cud_zone; +struct kmem_cache *xfs_cui_cache; +struct kmem_cache *xfs_cud_cache;

static const struct xfs_item_ops xfs_cui_item_ops;

@@ -39,7 +39,7 @@ xfs_cui_item_free( if (cuip->cui_format.cui_nextents > XFS_CUI_MAX_FAST_EXTENTS) kmem_free(cuip); else - kmem_cache_free(xfs_cui_zone, cuip); + kmem_cache_free(xfs_cui_cache, cuip); }

/* @@ -144,7 +144,7 @@ xfs_cui_init( cuip = kmem_zalloc(xfs_cui_log_item_sizeof(nextents), 0); else - cuip = kmem_cache_zalloc(xfs_cui_zone, + cuip = kmem_cache_zalloc(xfs_cui_cache, GFP_KERNEL | __GFP_NOFAIL);

xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops); @@ -206,7 +206,7 @@ xfs_cud_item_release(

xfs_cui_release(cudp->cud_cuip); kmem_free(cudp->cud_item.li_lv_shadow); - kmem_cache_free(xfs_cud_zone, cudp); + kmem_cache_free(xfs_cud_cache, cudp); }

static const struct xfs_item_ops xfs_cud_item_ops = { @@ -223,7 +223,7 @@ xfs_trans_get_cud( { struct xfs_cud_log_item *cudp;

- cudp = kmem_cache_zalloc(xfs_cud_zone, GFP_KERNEL | __GFP_NOFAIL); + cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL); xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD, &xfs_cud_item_ops); cudp->cud_cuip = cuip; diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h index 22c69c5a8394..eb0ab13682d0 100644 --- a/fs/xfs/xfs_refcount_item.h +++ b/fs/xfs/xfs_refcount_item.h @@ -68,7 +68,7 @@ struct xfs_cud_log_item { struct xfs_cud_log_format cud_format; };

-extern struct kmem_cache *xfs_cui_zone; -extern struct kmem_cache *xfs_cud_zone; +extern struct kmem_cache *xfs_cui_cache; +extern struct kmem_cache *xfs_cud_cache;

#endif /* __XFS_REFCOUNT_ITEM_H__ */ diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 597e55668cb5..52e3f983821a 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -21,8 +21,8 @@ #include "xfs_log_priv.h" #include "xfs_log_recover.h"

-struct kmem_cache *xfs_rui_zone; -struct kmem_cache *xfs_rud_zone; +struct kmem_cache *xfs_rui_cache; +struct kmem_cache *xfs_rud_cache;

static const struct xfs_item_ops xfs_rui_item_ops;

@@ -39,7 +39,7 @@ xfs_rui_item_free( if (ruip->rui_format.rui_nextents > XFS_RUI_MAX_FAST_EXTENTS) kmem_free(ruip); else - kmem_cache_free(xfs_rui_zone, ruip); + kmem_cache_free(xfs_rui_cache, ruip); }

/* @@ -142,7 +142,7 @@ xfs_rui_init( if (nextents > XFS_RUI_MAX_FAST_EXTENTS) ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0); else - ruip = kmem_cache_zalloc(xfs_rui_zone, + ruip = kmem_cache_zalloc(xfs_rui_cache, GFP_KERNEL | __GFP_NOFAIL);

xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops); @@ -204,7 +204,7 @@ xfs_rud_item_release(

xfs_rui_release(rudp->rud_ruip); kmem_free(rudp->rud_item.li_lv_shadow); - kmem_cache_free(xfs_rud_zone, rudp); + kmem_cache_free(xfs_rud_cache, rudp); }

static const struct xfs_item_ops xfs_rud_item_ops = { @@ -221,7 +221,7 @@ xfs_trans_get_rud( { struct xfs_rud_log_item *rudp;

- rudp = kmem_cache_zalloc(xfs_rud_zone, GFP_KERNEL | __GFP_NOFAIL); + rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL); xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD, &xfs_rud_item_ops); rudp->rud_ruip = ruip; diff --git a/fs/xfs/xfs_rmap_item.h b/fs/xfs/xfs_rmap_item.h index b062b983a82f..802e5119eaca 100644 --- a/fs/xfs/xfs_rmap_item.h +++ b/fs/xfs/xfs_rmap_item.h @@ -68,7 +68,7 @@ struct xfs_rud_log_item { struct xfs_rud_log_format rud_format; };

-extern struct kmem_cache *xfs_rui_zone; -extern struct kmem_cache *xfs_rud_zone; +extern struct kmem_cache *xfs_rui_cache; +extern struct kmem_cache *xfs_rud_cache;

#endif /* __XFS_RMAP_ITEM_H__ */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e83af9027131..935cd48df9a2 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1989,196 +1989,196 @@ static struct file_system_type xfs_fs_type = { MODULE_ALIAS_FS("xfs");

STATIC int __init -xfs_init_zones(void) +xfs_init_caches(void) { - xfs_log_ticket_zone = kmem_cache_create("xfs_log_ticket", + xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket", sizeof(struct xlog_ticket), 0, 0, NULL); - if (!xfs_log_ticket_zone) + if (!xfs_log_ticket_cache) goto out;

- xfs_bmap_free_item_zone = kmem_cache_create("xfs_bmap_free_item", + xfs_bmap_free_item_cache = kmem_cache_create("xfs_bmap_free_item", sizeof(struct xfs_extent_free_item), 0, 0, NULL); - if (!xfs_bmap_free_item_zone) - goto out_destroy_log_ticket_zone; + if (!xfs_bmap_free_item_cache) + goto out_destroy_log_ticket_cache;

- xfs_btree_cur_zone = kmem_cache_create("xfs_btree_cur", + xfs_btree_cur_cache = kmem_cache_create("xfs_btree_cur", sizeof(struct xfs_btree_cur), 0, 0, NULL); - if (!xfs_btree_cur_zone) - goto out_destroy_bmap_free_item_zone; + if (!xfs_btree_cur_cache) + goto out_destroy_bmap_free_item_cache;

- xfs_da_state_zone = kmem_cache_create("xfs_da_state", + xfs_da_state_cache = kmem_cache_create("xfs_da_state", sizeof(struct xfs_da_state), 0, 0, NULL); - if (!xfs_da_state_zone) - goto out_destroy_btree_cur_zone; + if (!xfs_da_state_cache) + goto out_destroy_btree_cur_cache;

- xfs_ifork_zone = kmem_cache_create("xfs_ifork", + xfs_ifork_cache = kmem_cache_create("xfs_ifork", sizeof(struct xfs_ifork), 0, 0, NULL); - if (!xfs_ifork_zone) - goto out_destroy_da_state_zone; + if (!xfs_ifork_cache) + goto out_destroy_da_state_cache;

- xfs_trans_zone = kmem_cache_create("xfs_trans", + xfs_trans_cache = kmem_cache_create("xfs_trans", sizeof(struct xfs_trans), 0, 0, NULL); - if (!xfs_trans_zone) - goto out_destroy_ifork_zone; + if (!xfs_trans_cache) + goto out_destroy_ifork_cache;

/* - * The size of the zone allocated buf log item is the maximum + * The size of the cache-allocated buf log item is the maximum * size possible under XFS. This wastes a little bit of memory, * but it is much faster. */ - xfs_buf_item_zone = kmem_cache_create("xfs_buf_item", + xfs_buf_item_cache = kmem_cache_create("xfs_buf_item", sizeof(struct xfs_buf_log_item), 0, 0, NULL); - if (!xfs_buf_item_zone) - goto out_destroy_trans_zone; + if (!xfs_buf_item_cache) + goto out_destroy_trans_cache;

- xfs_efd_zone = kmem_cache_create("xfs_efd_item", + xfs_efd_cache = kmem_cache_create("xfs_efd_item", (sizeof(struct xfs_efd_log_item) + XFS_EFD_MAX_FAST_EXTENTS * sizeof(struct xfs_extent)), 0, 0, NULL); - if (!xfs_efd_zone) - goto out_destroy_buf_item_zone; + if (!xfs_efd_cache) + goto out_destroy_buf_item_cache;

- xfs_efi_zone = kmem_cache_create("xfs_efi_item", + xfs_efi_cache = kmem_cache_create("xfs_efi_item", (sizeof(struct xfs_efi_log_item) + XFS_EFI_MAX_FAST_EXTENTS * sizeof(struct xfs_extent)), 0, 0, NULL); - if (!xfs_efi_zone) - goto out_destroy_efd_zone; + if (!xfs_efi_cache) + goto out_destroy_efd_cache;

- xfs_inode_zone = kmem_cache_create("xfs_inode", + xfs_inode_cache = kmem_cache_create("xfs_inode", sizeof(struct xfs_inode), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT), xfs_fs_inode_init_once); - if (!xfs_inode_zone) - goto out_destroy_efi_zone; + if (!xfs_inode_cache) + goto out_destroy_efi_cache;

- xfs_ili_zone = kmem_cache_create("xfs_ili", + xfs_ili_cache = kmem_cache_create("xfs_ili", sizeof(struct xfs_inode_log_item), 0, SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL); - if (!xfs_ili_zone) - goto out_destroy_inode_zone; + if (!xfs_ili_cache) + goto out_destroy_inode_cache;

- xfs_icreate_zone = kmem_cache_create("xfs_icr", + xfs_icreate_cache = kmem_cache_create("xfs_icr", sizeof(struct xfs_icreate_item), 0, 0, NULL); - if (!xfs_icreate_zone) - goto out_destroy_ili_zone; + if (!xfs_icreate_cache) + goto out_destroy_ili_cache;

- xfs_rud_zone = kmem_cache_create("xfs_rud_item", + xfs_rud_cache = kmem_cache_create("xfs_rud_item", sizeof(struct xfs_rud_log_item), 0, 0, NULL); - if (!xfs_rud_zone) - goto out_destroy_icreate_zone; + if (!xfs_rud_cache) + goto out_destroy_icreate_cache;

- xfs_rui_zone = kmem_cache_create("xfs_rui_item", + xfs_rui_cache = kmem_cache_create("xfs_rui_item", xfs_rui_log_item_sizeof(XFS_RUI_MAX_FAST_EXTENTS), 0, 0, NULL); - if (!xfs_rui_zone) - goto out_destroy_rud_zone; + if (!xfs_rui_cache) + goto out_destroy_rud_cache;

- xfs_cud_zone = kmem_cache_create("xfs_cud_item", + xfs_cud_cache = kmem_cache_create("xfs_cud_item", sizeof(struct xfs_cud_log_item), 0, 0, NULL); - if (!xfs_cud_zone) - goto out_destroy_rui_zone; + if (!xfs_cud_cache) + goto out_destroy_rui_cache;

- xfs_cui_zone = kmem_cache_create("xfs_cui_item", + xfs_cui_cache = kmem_cache_create("xfs_cui_item", xfs_cui_log_item_sizeof(XFS_CUI_MAX_FAST_EXTENTS), 0, 0, NULL); - if (!xfs_cui_zone) - goto out_destroy_cud_zone; + if (!xfs_cui_cache) + goto out_destroy_cud_cache;

- xfs_bud_zone = kmem_cache_create("xfs_bud_item", + xfs_bud_cache = kmem_cache_create("xfs_bud_item", sizeof(struct xfs_bud_log_item), 0, 0, NULL); - if (!xfs_bud_zone) - goto out_destroy_cui_zone; + if (!xfs_bud_cache) + goto out_destroy_cui_cache;

- xfs_bui_zone = kmem_cache_create("xfs_bui_item", + xfs_bui_cache = kmem_cache_create("xfs_bui_item", xfs_bui_log_item_sizeof(XFS_BUI_MAX_FAST_EXTENTS), 0, 0, NULL); - if (!xfs_bui_zone) - goto out_destroy_bud_zone; + if (!xfs_bui_cache) + goto out_destroy_bud_cache;

return 0;

- out_destroy_bud_zone: - kmem_cache_destroy(xfs_bud_zone); - out_destroy_cui_zone: - kmem_cache_destroy(xfs_cui_zone); - out_destroy_cud_zone: - kmem_cache_destroy(xfs_cud_zone); - out_destroy_rui_zone: - kmem_cache_destroy(xfs_rui_zone); - out_destroy_rud_zone: - kmem_cache_destroy(xfs_rud_zone); - out_destroy_icreate_zone: - kmem_cache_destroy(xfs_icreate_zone); - out_destroy_ili_zone: - kmem_cache_destroy(xfs_ili_zone); - out_destroy_inode_zone: - kmem_cache_destroy(xfs_inode_zone); - out_destroy_efi_zone: - kmem_cache_destroy(xfs_efi_zone); - out_destroy_efd_zone: - kmem_cache_destroy(xfs_efd_zone); - out_destroy_buf_item_zone: - kmem_cache_destroy(xfs_buf_item_zone); - out_destroy_trans_zone: - kmem_cache_destroy(xfs_trans_zone); - out_destroy_ifork_zone: - kmem_cache_destroy(xfs_ifork_zone); - out_destroy_da_state_zone: - kmem_cache_destroy(xfs_da_state_zone); - out_destroy_btree_cur_zone: - kmem_cache_destroy(xfs_btree_cur_zone); - out_destroy_bmap_free_item_zone: - kmem_cache_destroy(xfs_bmap_free_item_zone); - out_destroy_log_ticket_zone: - kmem_cache_destroy(xfs_log_ticket_zone); + out_destroy_bud_cache: + kmem_cache_destroy(xfs_bud_cache); + out_destroy_cui_cache: + kmem_cache_destroy(xfs_cui_cache); + out_destroy_cud_cache: + kmem_cache_destroy(xfs_cud_cache); + out_destroy_rui_cache: + kmem_cache_destroy(xfs_rui_cache); + out_destroy_rud_cache: + kmem_cache_destroy(xfs_rud_cache); + out_destroy_icreate_cache: + kmem_cache_destroy(xfs_icreate_cache); + out_destroy_ili_cache: + kmem_cache_destroy(xfs_ili_cache); + out_destroy_inode_cache: + kmem_cache_destroy(xfs_inode_cache); + out_destroy_efi_cache: + kmem_cache_destroy(xfs_efi_cache); + out_destroy_efd_cache: + kmem_cache_destroy(xfs_efd_cache); + out_destroy_buf_item_cache: + kmem_cache_destroy(xfs_buf_item_cache); + out_destroy_trans_cache: + kmem_cache_destroy(xfs_trans_cache); + out_destroy_ifork_cache: + kmem_cache_destroy(xfs_ifork_cache); + out_destroy_da_state_cache: + kmem_cache_destroy(xfs_da_state_cache); + out_destroy_btree_cur_cache: + kmem_cache_destroy(xfs_btree_cur_cache); + out_destroy_bmap_free_item_cache: + kmem_cache_destroy(xfs_bmap_free_item_cache); + out_destroy_log_ticket_cache: + kmem_cache_destroy(xfs_log_ticket_cache); out: return -ENOMEM; }

STATIC void -xfs_destroy_zones(void) +xfs_destroy_caches(void) { /* * Make sure all delayed rcu free are flushed before we * destroy caches. */ rcu_barrier(); - kmem_cache_destroy(xfs_bui_zone); - kmem_cache_destroy(xfs_bud_zone); - kmem_cache_destroy(xfs_cui_zone); - kmem_cache_destroy(xfs_cud_zone); - kmem_cache_destroy(xfs_rui_zone); - kmem_cache_destroy(xfs_rud_zone); - kmem_cache_destroy(xfs_icreate_zone); - kmem_cache_destroy(xfs_ili_zone); - kmem_cache_destroy(xfs_inode_zone); - kmem_cache_destroy(xfs_efi_zone); - kmem_cache_destroy(xfs_efd_zone); - kmem_cache_destroy(xfs_buf_item_zone); - kmem_cache_destroy(xfs_trans_zone); - kmem_cache_destroy(xfs_ifork_zone); - kmem_cache_destroy(xfs_da_state_zone); - kmem_cache_destroy(xfs_btree_cur_zone); - kmem_cache_destroy(xfs_bmap_free_item_zone); - kmem_cache_destroy(xfs_log_ticket_zone); + kmem_cache_destroy(xfs_bui_cache); + kmem_cache_destroy(xfs_bud_cache); + kmem_cache_destroy(xfs_cui_cache); + kmem_cache_destroy(xfs_cud_cache); + kmem_cache_destroy(xfs_rui_cache); + kmem_cache_destroy(xfs_rud_cache); + kmem_cache_destroy(xfs_icreate_cache); + kmem_cache_destroy(xfs_ili_cache); + kmem_cache_destroy(xfs_inode_cache); + kmem_cache_destroy(xfs_efi_cache); + kmem_cache_destroy(xfs_efd_cache); + kmem_cache_destroy(xfs_buf_item_cache); + kmem_cache_destroy(xfs_trans_cache); + kmem_cache_destroy(xfs_ifork_cache); + kmem_cache_destroy(xfs_da_state_cache); + kmem_cache_destroy(xfs_btree_cur_cache); + kmem_cache_destroy(xfs_bmap_free_item_cache); + kmem_cache_destroy(xfs_log_ticket_cache); }

STATIC int __init @@ -2271,13 +2271,13 @@ init_xfs_fs(void) if (error) goto out;

- error = xfs_init_zones(); + error = xfs_init_caches(); if (error) goto out_destroy_hp;

error = xfs_init_workqueues(); if (error) - goto out_destroy_zones; + goto out_destroy_caches;

error = xfs_mru_cache_init(); if (error) @@ -2352,8 +2352,8 @@ init_xfs_fs(void) xfs_mru_cache_uninit(); out_destroy_wq: xfs_destroy_workqueues(); - out_destroy_zones: - xfs_destroy_zones(); + out_destroy_caches: + xfs_destroy_caches(); out_destroy_hp: xfs_cpu_hotplug_destroy(); out: @@ -2376,7 +2376,7 @@ exit_xfs_fs(void) xfs_buf_terminate(); xfs_mru_cache_uninit(); xfs_destroy_workqueues(); - xfs_destroy_zones(); + xfs_destroy_caches(); xfs_uuid_table_free(); xfs_cpu_hotplug_destroy(); } diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index fa5132bf9180..36a894a2128a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -26,7 +26,7 @@ #include "xfs_icache.h" #include "xfs_buf_item.h"

-struct kmem_cache *xfs_trans_zone; +struct kmem_cache *xfs_trans_cache;

#if defined(CONFIG_TRACEPOINTS) static void @@ -77,7 +77,7 @@ xfs_trans_free( if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT)) sb_end_intwrite(tp->t_mountp->m_super); xfs_trans_free_dqinfo(tp); - kmem_cache_free(xfs_trans_zone, tp); + kmem_cache_free(xfs_trans_cache, tp); }

/* @@ -96,7 +96,7 @@ xfs_trans_dup(

trace_xfs_trans_dup(tp, _RET_IP_);

- ntp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL); + ntp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL);

/* * Initialize the new transaction structure. @@ -264,7 +264,7 @@ xfs_trans_alloc( * by doing GFP_KERNEL allocations inside sb_start_intwrite(). */ retry: - tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL); + tp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL); if (!(flags & XFS_TRANS_NO_WRITECOUNT)) sb_start_intwrite(mp->m_super); xfs_trans_set_context(tp); diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index a9ea901d7449..731af3f04c83 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -244,7 +244,7 @@ void xfs_trans_buf_set_type(struct xfs_trans *, struct xfs_buf *, void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp, struct xfs_buf *src_bp);

-extern struct kmem_cache *xfs_trans_zone; +extern struct kmem_cache *xfs_trans_cache;

static inline struct xfs_log_item * xfs_trans_item_relog( diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index d91a8ecf01ff..e29b77a71664 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -866,7 +866,7 @@ STATIC void xfs_trans_alloc_dqinfo( xfs_trans_t *tp) { - tp->t_dqinfo = kmem_cache_zalloc(xfs_qm_dqtrxzone, + tp->t_dqinfo = kmem_cache_zalloc(xfs_dqtrx_cache, GFP_KERNEL | __GFP_NOFAIL); }

@@ -876,6 +876,6 @@ xfs_trans_free_dqinfo( { if (!tp->t_dqinfo) return; - kmem_cache_free(xfs_qm_dqtrxzone, tp->t_dqinfo); + kmem_cache_free(xfs_dqtrx_cache, tp->t_dqinfo); tp->t_dqinfo = NULL; }

From: "Darrick J. Wong" djwong@kernel.org

mainline inclusion from mainline-v5.15-rc4 commit f3c799c22c661e181c71a0d9914fc923023f65fb category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Create slab caches for the high-level structures that coordinate deferred intent items, since they're used fairly heavily.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Chandan Babu R chandan.babu@oracle.com

Conflicts: fs/xfs/libxfs/xfs_defer.c fs/xfs/xfs_super.c Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_bmap.c | 21 ++++++++++-- fs/xfs/libxfs/xfs_bmap.h | 5 +++ fs/xfs/libxfs/xfs_defer.c | 65 +++++++++++++++++++++++++++++++++--- fs/xfs/libxfs/xfs_defer.h | 3 ++ fs/xfs/libxfs/xfs_refcount.c | 23 +++++++++++-- fs/xfs/libxfs/xfs_refcount.h | 5 +++ fs/xfs/libxfs/xfs_rmap.c | 21 +++++++++++- fs/xfs/libxfs/xfs_rmap.h | 5 +++ fs/xfs/xfs_bmap_item.c | 4 +-- fs/xfs/xfs_refcount_item.c | 4 +-- fs/xfs/xfs_rmap_item.c | 4 +-- fs/xfs/xfs_super.c | 12 ++++++- 12 files changed, 156 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 180c212c862b..19761b909128 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -36,7 +36,7 @@ #include "xfs_icache.h" #include "xfs_iomap.h"

- +struct kmem_cache *xfs_bmap_intent_cache; struct kmem_cache *xfs_bmap_free_item_cache;

/* @@ -6137,7 +6137,7 @@ __xfs_bmap_add( bmap->br_blockcount, bmap->br_state);

- bi = kmem_alloc(sizeof(struct xfs_bmap_intent), KM_NOFS); + bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL); INIT_LIST_HEAD(&bi->bi_list); bi->bi_type = type; bi->bi_owner = ip; @@ -6259,3 +6259,20 @@ xfs_bmap_validate_extent( return __this_address; return NULL; } + +int __init +xfs_bmap_intent_init_cache(void) +{ + xfs_bmap_intent_cache = kmem_cache_create("xfs_bmap_intent", + sizeof(struct xfs_bmap_intent), + 0, 0, NULL); + + return xfs_bmap_intent_cache != NULL ? 0 : -ENOMEM; +} + +void +xfs_bmap_intent_destroy_cache(void) +{ + kmem_cache_destroy(xfs_bmap_intent_cache); + xfs_bmap_intent_cache = NULL; +} diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index aa6f45a7ee69..6903013e14e5 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -291,4 +291,9 @@ int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock, int flags);

+extern struct kmem_cache *xfs_bmap_intent_cache; + +int __init xfs_bmap_intent_init_cache(void); +void xfs_bmap_intent_destroy_cache(void); + #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 168b8798625f..9d0abdac423f 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -18,6 +18,11 @@ #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_log.h" +#include "xfs_rmap.h" +#include "xfs_refcount.h" +#include "xfs_bmap.h" + +static struct kmem_cache *xfs_defer_pending_cache;

/* * Deferred Operations in XFS @@ -349,7 +354,7 @@ xfs_defer_cancel_list( ops->cancel_item(pwi); } ASSERT(dfp->dfp_count == 0); - kmem_free(dfp); + kmem_cache_free(xfs_defer_pending_cache, dfp); } }

@@ -446,7 +451,7 @@ xfs_defer_finish_one(

/* Done with the dfp, free it. */ list_del(&dfp->dfp_list); - kmem_free(dfp); + kmem_cache_free(xfs_defer_pending_cache, dfp); out: if (ops->finish_cleanup) ops->finish_cleanup(tp, state, error); @@ -580,8 +585,8 @@ xfs_defer_add( dfp = NULL; } if (!dfp) { - dfp = kmem_alloc(sizeof(struct xfs_defer_pending), - KM_NOFS); + dfp = kmem_cache_zalloc(xfs_defer_pending_cache, + GFP_NOFS | __GFP_NOFAIL); dfp->dfp_type = type; dfp->dfp_intent = NULL; dfp->dfp_done = NULL; @@ -750,3 +755,55 @@ xfs_defer_ops_continue(

kmem_free(dfc); } + +static inline int __init +xfs_defer_init_cache(void) +{ + xfs_defer_pending_cache = kmem_cache_create("xfs_defer_pending", + sizeof(struct xfs_defer_pending), + 0, 0, NULL); + + return xfs_defer_pending_cache != NULL ? 0 : -ENOMEM; +} + +static inline void +xfs_defer_destroy_cache(void) +{ + kmem_cache_destroy(xfs_defer_pending_cache); + xfs_defer_pending_cache = NULL; +} + +/* Set up caches for deferred work items. */ +int __init +xfs_defer_init_item_caches(void) +{ + int error; + + error = xfs_defer_init_cache(); + if (error) + return error; + error = xfs_rmap_intent_init_cache(); + if (error) + goto err; + error = xfs_refcount_intent_init_cache(); + if (error) + goto err; + error = xfs_bmap_intent_init_cache(); + if (error) + goto err; + + return 0; +err: + xfs_defer_destroy_item_caches(); + return error; +} + +/* Destroy all the deferred work item caches, if they've been allocated. */ +void +xfs_defer_destroy_item_caches(void) +{ + xfs_bmap_intent_destroy_cache(); + xfs_refcount_intent_destroy_cache(); + xfs_rmap_intent_destroy_cache(); + xfs_defer_destroy_cache(); +} diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index df0312679ca7..edc23cc324de 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -101,4 +101,7 @@ void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp, struct xfs_inode **captured_ipp); void xfs_defer_ops_release(struct xfs_mount *mp, struct xfs_defer_capture *d);

+int __init xfs_defer_init_item_caches(void); +void xfs_defer_destroy_item_caches(void); + #endif /* __XFS_DEFER_H__ */ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 1ab15910e402..ed21426f9a44 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -23,6 +23,8 @@ #include "xfs_refcount.h" #include "xfs_rmap.h"

+struct kmem_cache *xfs_refcount_intent_cache; + /* Allowable refcount adjustment amounts. */ enum xfs_refc_adjust_op { XFS_REFCOUNT_ADJUST_INCREASE = 1, @@ -1241,8 +1243,8 @@ __xfs_refcount_add( type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), blockcount);

- ri = kmem_alloc(sizeof(struct xfs_refcount_intent), - KM_NOFS); + ri = kmem_cache_alloc(xfs_refcount_intent_cache, + GFP_NOFS | __GFP_NOFAIL); INIT_LIST_HEAD(&ri->ri_list); ri->ri_type = type; ri->ri_startblock = startblock; @@ -1787,3 +1789,20 @@ xfs_refcount_has_record(

return xfs_btree_has_record(cur, &low, &high, exists); } + +int __init +xfs_refcount_intent_init_cache(void) +{ + xfs_refcount_intent_cache = kmem_cache_create("xfs_refc_intent", + sizeof(struct xfs_refcount_intent), + 0, 0, NULL); + + return xfs_refcount_intent_cache != NULL ? 0 : -ENOMEM; +} + +void +xfs_refcount_intent_destroy_cache(void) +{ + kmem_cache_destroy(xfs_refcount_intent_cache); + xfs_refcount_intent_cache = NULL; +} diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index d43e276b6883..d86a1afca0b7 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -76,4 +76,9 @@ extern void xfs_refcount_btrec_to_irec(union xfs_btree_rec *rec, extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat);

+extern struct kmem_cache *xfs_refcount_intent_cache; + +int __init xfs_refcount_intent_init_cache(void); +void xfs_refcount_intent_destroy_cache(void); + #endif /* __XFS_REFCOUNT_H__ */ diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index e6caa25c9e18..64bfb4f319be 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -22,6 +22,8 @@ #include "xfs_error.h" #include "xfs_inode.h"

+struct kmem_cache *xfs_rmap_intent_cache; + /* * Lookup the first record less than or equal to [bno, len, owner, offset] * in the btree given by cur. @@ -2487,7 +2489,7 @@ __xfs_rmap_add( bmap->br_blockcount, bmap->br_state);

- ri = kmem_alloc(sizeof(struct xfs_rmap_intent), KM_NOFS); + ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL); INIT_LIST_HEAD(&ri->ri_list); ri->ri_type = type; ri->ri_owner = owner; @@ -2781,3 +2783,20 @@ const struct xfs_owner_info XFS_RMAP_OINFO_REFC = { const struct xfs_owner_info XFS_RMAP_OINFO_COW = { .oi_owner = XFS_RMAP_OWN_COW, }; + +int __init +xfs_rmap_intent_init_cache(void) +{ + xfs_rmap_intent_cache = kmem_cache_create("xfs_rmap_intent", + sizeof(struct xfs_rmap_intent), + 0, 0, NULL); + + return xfs_rmap_intent_cache != NULL ? 0 : -ENOMEM; +} + +void +xfs_rmap_intent_destroy_cache(void) +{ + kmem_cache_destroy(xfs_rmap_intent_cache); + xfs_rmap_intent_cache = NULL; +} diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 8a4f106c9ff4..9befe4894359 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -212,4 +212,9 @@ extern const struct xfs_owner_info XFS_RMAP_OINFO_INODES; extern const struct xfs_owner_info XFS_RMAP_OINFO_REFC; extern const struct xfs_owner_info XFS_RMAP_OINFO_COW;

+extern struct kmem_cache *xfs_rmap_intent_cache; + +int __init xfs_rmap_intent_init_cache(void); +void xfs_rmap_intent_destroy_cache(void); + #endif /* __XFS_RMAP_H__ */ diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index ec3c3c43b4f9..a68ed8f36b47 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -387,7 +387,7 @@ xfs_bmap_update_finish_item( bmap->bi_bmap.br_blockcount = count; return -EAGAIN; } - kmem_free(bmap); + kmem_cache_free(xfs_bmap_intent_cache, bmap); return error; }

@@ -407,7 +407,7 @@ xfs_bmap_update_cancel_item( struct xfs_bmap_intent *bmap;

bmap = container_of(item, struct xfs_bmap_intent, bi_list); - kmem_free(bmap); + kmem_cache_free(xfs_bmap_intent_cache, bmap); }

const struct xfs_defer_op_type xfs_bmap_update_defer_type = { diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 09efa723ddfa..1d3036fcfbf4 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -386,7 +386,7 @@ xfs_refcount_update_finish_item( refc->ri_blockcount = new_aglen; return -EAGAIN; } - kmem_free(refc); + kmem_cache_free(xfs_refcount_intent_cache, refc); return error; }

@@ -406,7 +406,7 @@ xfs_refcount_update_cancel_item( struct xfs_refcount_intent *refc;

refc = container_of(item, struct xfs_refcount_intent, ri_list); - kmem_free(refc); + kmem_cache_free(xfs_refcount_intent_cache, refc); }

const struct xfs_defer_op_type xfs_refcount_update_defer_type = { diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 52e3f983821a..aafbb6589ebc 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -404,7 +404,7 @@ xfs_rmap_update_finish_item( rmap->ri_bmap.br_startoff, rmap->ri_bmap.br_startblock, rmap->ri_bmap.br_blockcount, rmap->ri_bmap.br_state, state); - kmem_free(rmap); + kmem_cache_free(xfs_rmap_intent_cache, rmap); return error; }

@@ -424,7 +424,7 @@ xfs_rmap_update_cancel_item( struct xfs_rmap_intent *rmap;

rmap = container_of(item, struct xfs_rmap_intent, ri_list); - kmem_free(rmap); + kmem_cache_free(xfs_rmap_intent_cache, rmap); }

const struct xfs_defer_op_type xfs_rmap_update_defer_type = { diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 935cd48df9a2..b5021e9c3aaf 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -36,6 +36,7 @@ #include "xfs_bmap_item.h" #include "xfs_reflink.h" #include "xfs_pwork.h" +#include "xfs_defer.h"

#include <linux/magic.h> #include <linux/fs_context.h> @@ -1991,6 +1992,8 @@ MODULE_ALIAS_FS("xfs"); STATIC int __init xfs_init_caches(void) { + int error; + xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket", sizeof(struct xlog_ticket), 0, 0, NULL); @@ -2009,11 +2012,15 @@ xfs_init_caches(void) if (!xfs_btree_cur_cache) goto out_destroy_bmap_free_item_cache;

+ error = xfs_defer_init_item_caches(); + if (error) + goto out_destroy_btree_cur_cache; + xfs_da_state_cache = kmem_cache_create("xfs_da_state", sizeof(struct xfs_da_state), 0, 0, NULL); if (!xfs_da_state_cache) - goto out_destroy_btree_cur_cache; + goto out_destroy_defer_item_cache;

xfs_ifork_cache = kmem_cache_create("xfs_ifork", sizeof(struct xfs_ifork), @@ -2143,6 +2150,8 @@ xfs_init_caches(void) kmem_cache_destroy(xfs_ifork_cache); out_destroy_da_state_cache: kmem_cache_destroy(xfs_da_state_cache); + out_destroy_defer_item_cache: + xfs_defer_destroy_item_caches(); out_destroy_btree_cur_cache: kmem_cache_destroy(xfs_btree_cur_cache); out_destroy_bmap_free_item_cache: @@ -2177,6 +2186,7 @@ xfs_destroy_caches(void) kmem_cache_destroy(xfs_ifork_cache); kmem_cache_destroy(xfs_da_state_cache); kmem_cache_destroy(xfs_btree_cur_cache); + xfs_defer_destroy_item_caches(); kmem_cache_destroy(xfs_bmap_free_item_cache); kmem_cache_destroy(xfs_log_ticket_cache); }

From: "Darrick J. Wong" djwong@kernel.org

mainline inclusion from mainline-v5.15-rc4 commit b3b5ff412ab04afd99173bb12d3cc146ee478ae7 category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

We only use EFIs to free metadata blocks -- not regular data/attr fork extents. Remove all the fields that we never use, for a net reduction of 16 bytes.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 25 ++++++++++++++++--------- fs/xfs/libxfs/xfs_alloc.h | 8 ++++++-- fs/xfs/xfs_extfree_item.c | 13 ++++++++++--- 3 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index d06097660d89..1079c98e166c 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2471,12 +2471,11 @@ xfs_defer_agfl_block( ASSERT(xfs_extfree_item_cache != NULL); ASSERT(oinfo != NULL);

- new = kmem_cache_alloc(xfs_extfree_item_cache, + new = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); new->xefi_blockcount = 1; - new->xefi_oinfo = *oinfo; - new->xefi_skip_discard = false; + new->xefi_owner = oinfo->oi_owner;

trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);

@@ -2514,15 +2513,23 @@ __xfs_free_extent_later( #endif ASSERT(xfs_extfree_item_cache != NULL);

- new = kmem_cache_alloc(xfs_extfree_item_cache, + new = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); new->xefi_startblock = bno; new->xefi_blockcount = (xfs_extlen_t)len; - if (oinfo) - new->xefi_oinfo = *oinfo; - else - new->xefi_oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; - new->xefi_skip_discard = skip_discard; + if (skip_discard) + new->xefi_flags |= XFS_EFI_SKIP_DISCARD; + if (oinfo) { + ASSERT(oinfo->oi_offset == 0); + + if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK) + new->xefi_flags |= XFS_EFI_ATTR_FORK; + if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK) + new->xefi_flags |= XFS_EFI_BMBT_BLOCK; + new->xefi_owner = oinfo->oi_owner; + } else { + new->xefi_owner = XFS_RMAP_OWN_NULL; + } trace_xfs_bmap_free_defer(tp->t_mountp, XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0, XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 36c346a0f608..b65e933ebabe 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -256,12 +256,16 @@ void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, */ struct xfs_extent_free_item { struct list_head xefi_list; + uint64_t xefi_owner; xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ - bool xefi_skip_discard; - struct xfs_owner_info xefi_oinfo; /* extent owner */ + unsigned int xefi_flags; };

+#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */ +#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ +#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */ + static inline void xfs_free_extent_later( struct xfs_trans *tp, diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 5211b91883b1..445dc083873b 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -479,14 +479,20 @@ xfs_extent_free_finish_item( struct list_head *item, struct xfs_btree_cur **state) { + struct xfs_owner_info oinfo = { }; struct xfs_extent_free_item *free; int error;

free = container_of(item, struct xfs_extent_free_item, xefi_list); + oinfo.oi_owner = free->xefi_owner; + if (free->xefi_flags & XFS_EFI_ATTR_FORK) + oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; + if (free->xefi_flags & XFS_EFI_BMBT_BLOCK) + oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; error = xfs_trans_free_extent(tp, EFD_ITEM(done), free->xefi_startblock, free->xefi_blockcount, - &free->xefi_oinfo, free->xefi_skip_discard); + &oinfo, free->xefi_flags & XFS_EFI_SKIP_DISCARD); kmem_cache_free(xfs_extfree_item_cache, free); return error; } @@ -530,6 +536,7 @@ xfs_agfl_free_finish_item( struct list_head *item, struct xfs_btree_cur **state) { + struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_efd_log_item *efdp = EFD_ITEM(done); struct xfs_extent_free_item *free; @@ -544,13 +551,13 @@ xfs_agfl_free_finish_item( ASSERT(free->xefi_blockcount == 1); agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock); agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock); + oinfo.oi_owner = free->xefi_owner;

trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount);

error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (!error) - error = xfs_free_agfl_block(tp, agno, agbno, agbp, - &free->xefi_oinfo); + error = xfs_free_agfl_block(tp, agno, agbno, agbp, &oinfo);

/* * Mark the transaction dirty, even on error. This ensures the

From: "Darrick J. Wong" djwong@kernel.org

mainline inclusion from mainline-v6.2-rc6 commit 72ba455599ad13d08c29dafa22a32360e07b1961 category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Pass the incore xfs_extent_free_item through the EFI logging code instead of repeatedly boxing and unboxing parameters.

Signed-off-by: Darrick J. Wong djwong@kernel.org

Conflicts: fs/xfs/xfs_extfree_item.c Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_extfree_item.c | 53 +++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 445dc083873b..100a21fe0527 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -361,23 +361,30 @@ static int xfs_trans_free_extent( struct xfs_trans *tp, struct xfs_efd_log_item *efdp, - xfs_fsblock_t start_block, - xfs_extlen_t ext_len, - const struct xfs_owner_info *oinfo, - bool skip_discard) + struct xfs_extent_free_item *free) { + struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_extent *extp; uint next_extent; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, start_block); + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, + free->xefi_startblock); xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, - start_block); + free->xefi_startblock); int error;

- trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len); + oinfo.oi_owner = free->xefi_owner; + if (free->xefi_flags & XFS_EFI_ATTR_FORK) + oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; + if (free->xefi_flags & XFS_EFI_BMBT_BLOCK) + oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; + + trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, + free->xefi_blockcount);

- error = __xfs_free_extent(tp, start_block, ext_len, - oinfo, XFS_AG_RESV_NONE, skip_discard); + error = __xfs_free_extent(tp, free->xefi_startblock, + free->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE, + free->xefi_flags & XFS_EFI_SKIP_DISCARD); /* * Mark the transaction dirty, even on error. This ensures the * transaction is aborted, which: @@ -391,8 +398,8 @@ xfs_trans_free_extent( next_extent = efdp->efd_next_extent; ASSERT(next_extent < efdp->efd_format.efd_nextents); extp = &(efdp->efd_format.efd_extents[next_extent]); - extp->ext_start = start_block; - extp->ext_len = ext_len; + extp->ext_start = free->xefi_startblock; + extp->ext_len = free->xefi_blockcount; efdp->efd_next_extent++;

return error; @@ -479,20 +486,12 @@ xfs_extent_free_finish_item( struct list_head *item, struct xfs_btree_cur **state) { - struct xfs_owner_info oinfo = { }; struct xfs_extent_free_item *free; int error;

free = container_of(item, struct xfs_extent_free_item, xefi_list); - oinfo.oi_owner = free->xefi_owner; - if (free->xefi_flags & XFS_EFI_ATTR_FORK) - oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; - if (free->xefi_flags & XFS_EFI_BMBT_BLOCK) - oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; - error = xfs_trans_free_extent(tp, EFD_ITEM(done), - free->xefi_startblock, - free->xefi_blockcount, - &oinfo, free->xefi_flags & XFS_EFI_SKIP_DISCARD); + + error = xfs_trans_free_extent(tp, EFD_ITEM(done), free); kmem_cache_free(xfs_extfree_item_cache, free); return error; } @@ -630,10 +629,16 @@ xfs_efi_item_recover( efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);

for (i = 0; i < efip->efi_format.efi_nextents; i++) { + struct xfs_extent_free_item fake = { + .xefi_owner = XFS_RMAP_OWN_UNKNOWN, + }; + extp = &efip->efi_format.efi_extents[i]; - error = xfs_trans_free_extent(tp, efdp, extp->ext_start, - extp->ext_len, - &XFS_RMAP_OINFO_ANY_OWNER, false); + + fake.xefi_startblock = extp->ext_start; + fake.xefi_blockcount = extp->ext_len; + + error = xfs_trans_free_extent(tp, efdp, &fake); if (error) goto abort_error;

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.4-rc5 commit 7dfee17b13e5024c5c0ab1911859ded4182de3e5 category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Bad things happen in defered extent freeing operations if it is passed a bad block number in the xefi. This can come from a bogus agno/agbno pair from deferred agfl freeing, or just a bad fsbno being passed to __xfs_free_extent_later(). Either way, it's very difficult to diagnose where a null perag oops in EFI creation is coming from when the operation that queued the xefi has already been completed and there's no longer any trace of it around....

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Dave Chinner david@fromorbit.com

Conflicts: fs/xfs/libxfs/xfs_ag.c fs/xfs/libxfs/xfs_alloc.c fs/xfs/libxfs/xfs_bmap.c fs/xfs/libxfs/xfs_bmap_btree.c fs/xfs/libxfs/xfs_ialloc.c Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 18 ++++++++++++++---- fs/xfs/libxfs/xfs_alloc.h | 6 +++--- fs/xfs/libxfs/xfs_bmap.c | 10 ++++++++-- fs/xfs/libxfs/xfs_bmap_btree.c | 5 ++++- fs/xfs/libxfs/xfs_ialloc.c | 24 ++++++++++++++++-------- fs/xfs/libxfs/xfs_refcount.c | 13 ++++++++++--- fs/xfs/libxfs/xfs_types.c | 23 +++++++++++++++++++++++ fs/xfs/libxfs/xfs_types.h | 2 ++ fs/xfs/xfs_reflink.c | 4 +++- 9 files changed, 83 insertions(+), 22 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 7ffccfc1320c..ebfaf5f48010 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2458,7 +2458,7 @@ xfs_agfl_reset( * the real allocation can proceed. Deferring the free disconnects freeing up * the AGFL slot from freeing the block. */ -STATIC void +static int xfs_defer_agfl_block( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -2477,16 +2477,20 @@ xfs_defer_agfl_block( new->xefi_blockcount = 1; new->xefi_owner = oinfo->oi_owner;

+ if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, new->xefi_startblock))) + return -EFSCORRUPTED; + trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);

xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list); + return 0; }

/* * Add the extent to the list of extents to be free at transaction end. * The list is maintained sorted (by block number). */ -void +int __xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, @@ -2495,8 +2499,8 @@ __xfs_free_extent_later( bool skip_discard) { struct xfs_extent_free_item *new; /* new element */ -#ifdef DEBUG struct xfs_mount *mp = tp->t_mountp; +#ifdef DEBUG xfs_agnumber_t agno; xfs_agblock_t agbno;

@@ -2513,6 +2517,9 @@ __xfs_free_extent_later( #endif ASSERT(xfs_extfree_item_cache != NULL);

+ if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) + return -EFSCORRUPTED; + new = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); new->xefi_startblock = bno; @@ -2534,6 +2541,7 @@ __xfs_free_extent_later( XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0, XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list); + return 0; }

/* @@ -2648,7 +2656,9 @@ xfs_alloc_fix_freelist( goto out_agbp_relse;

/* defer agfl frees */ - xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + if (error) + goto out_agbp_relse; }

targs.tp = tp; diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index b65e933ebabe..0fd02e889216 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -246,7 +246,7 @@ xfs_buf_to_agfl_bno( return bp->b_addr; }

-void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, +int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, bool skip_discard);

@@ -266,14 +266,14 @@ struct xfs_extent_free_item { #define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ #define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */

-static inline void +static inline int xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo) { - __xfs_free_extent_later(tp, bno, len, oinfo, false); + return __xfs_free_extent_later(tp, bno, len, oinfo, false); }

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 2387d6c3add6..3eb1d31df6e1 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -570,8 +570,12 @@ xfs_bmap_btree_to_extents( cblock = XFS_BUF_TO_BLOCK(cbp); if ((error = xfs_btree_check_block(cur, cblock, 0, cbp))) return error; + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + if (error) + return error; + ip->i_d.di_nblocks--; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); xfs_trans_binval(tp, cbp); @@ -5188,10 +5192,12 @@ xfs_bmap_del_extent_real( if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { xfs_refcount_decrease_extent(tp, del); } else { - __xfs_free_extent_later(tp, del->br_startblock, + error = __xfs_free_extent_later(tp, del->br_startblock, del->br_blockcount, NULL, (bflags & XFS_BMAPI_NODISCARD) || del->br_state == XFS_EXT_UNWRITTEN); + if (error) + goto done; } }

diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 945a9c2f751a..021afb43c56b 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -284,9 +284,12 @@ xfs_bmbt_free_block( struct xfs_trans *tp = cur->bc_tp; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); struct xfs_owner_info oinfo; + int error;

xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); + if (error) + return error; ip->i_d.di_nblocks--;

xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 7b3a86fe5db5..d26f966b0901 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1851,7 +1851,7 @@ xfs_dialloc( * might be sparse and only free the regions that are allocated as part of the * chunk. */ -STATIC void +static int xfs_difree_inode_chunk( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -1868,10 +1868,10 @@ xfs_difree_inode_chunk(

if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); - return; + return xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, sagbno), + M_IGEO(mp)->ialloc_blks, + &XFS_RMAP_OINFO_INODES); }

/* holemask is only 16-bits (fits in an unsigned long) */ @@ -1888,6 +1888,8 @@ xfs_difree_inode_chunk( XFS_INOBT_HOLEMASK_BITS); nextbit = startidx + 1; while (startidx < XFS_INOBT_HOLEMASK_BITS) { + int error; + nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS, nextbit); /* @@ -1913,8 +1915,11 @@ xfs_difree_inode_chunk(

ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + error = xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, agbno), + contigblk, &XFS_RMAP_OINFO_INODES); + if (error) + return error;

/* reset range to current bit and carry on... */ startidx = endidx = nextbit; @@ -1922,6 +1927,7 @@ xfs_difree_inode_chunk( next: nextbit++; } + return 0; }

STATIC int @@ -2021,7 +2027,9 @@ xfs_difree_inobt( goto error0; }

- xfs_difree_inode_chunk(tp, agno, &rec); + error = xfs_difree_inode_chunk(tp, agno, &rec); + if (error) + goto error0; } else { xic->deleted = false;

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 5b39759af829..0e1a9f047b12 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -974,8 +974,10 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.agno, tmp.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, + error = xfs_free_extent_later(cur->bc_tp, fsbno, tmp.rc_blockcount, NULL); + if (error) + goto out_error; }

(*agbno) += tmp.rc_blockcount; @@ -1019,8 +1021,10 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.agno, ext.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, + error = xfs_free_extent_later(cur->bc_tp, fsbno, ext.rc_blockcount, NULL); + if (error) + goto out_error; }

skip: @@ -1746,7 +1750,10 @@ xfs_refcount_recover_cow_leftovers( rr->rr_rrec.rc_blockcount);

/* Free the block. */ - xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL); + error = xfs_free_extent_later(tp, fsb, + rr->rr_rrec.rc_blockcount, NULL); + if (error) + goto out_trans;

error = xfs_trans_commit(tp); if (error) diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c index 86cb4b764897..19eabad06f92 100644 --- a/fs/xfs/libxfs/xfs_types.c +++ b/fs/xfs/libxfs/xfs_types.c @@ -61,6 +61,29 @@ xfs_verify_fsbno( return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno)); }

+/* + * Verify that a data device extent is fully contained inside the filesystem, + * does not cross an AG boundary, and does not point at static metadata. + */ +bool +xfs_verify_fsbext( + struct xfs_mount *mp, + xfs_fsblock_t fsbno, + xfs_fsblock_t len) +{ + if (fsbno + len <= fsbno) + return false; + + if (!xfs_verify_fsbno(mp, fsbno)) + return false; + + if (!xfs_verify_fsbno(mp, fsbno + len - 1)) + return false; + + return XFS_FSB_TO_AGNO(mp, fsbno) == + XFS_FSB_TO_AGNO(mp, fsbno + len - 1); +} + /* Calculate the first and last possible inode number in an AG. */ void xfs_agino_range( diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 1ce06173c2f5..f76fa8498749 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -186,6 +186,8 @@ bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno); bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);

+bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno, + xfs_fsblock_t len); void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t *first, xfs_agino_t *last); bool xfs_verify_agino(struct xfs_mount *mp, xfs_agnumber_t agno, diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index e9aaf730f784..e20aa87fed21 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -484,8 +484,10 @@ xfs_reflink_cancel_cow_blocks( xfs_refcount_free_cow_extent(*tpp, del.br_startblock, del.br_blockcount);

- xfs_free_extent_later(*tpp, del.br_startblock, + error = xfs_free_extent_later(*tpp, del.br_startblock, del.br_blockcount, NULL); + if (error) + break;

/* Roll the transaction */ error = xfs_defer_finish(tpp);

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.4-rc6 commit b742d7b4f0e03df25c2a772adcded35044b625ca category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Btrees that aren't freespace management trees use the normal extent allocation and freeing routines for their blocks. Hence when a btree block is freed, a direct call to xfs_free_extent() is made and the extent is immediately freed. This puts the entire free space management btrees under this path, so we are stacking btrees on btrees in the call stack. The inobt, finobt and refcount btrees all do this.

However, the bmap btree does not do this - it calls xfs_free_extent_later() to defer the extent free operation via an XEFI and hence it gets processed in deferred operation processing during the commit of the primary transaction (i.e. via intent chaining).

We need to change xfs_free_extent() to behave in a non-blocking manner so that we can avoid deadlocks with busy extents near ENOSPC in transactions that free multiple extents. Inserting or removing a record from a btree can cause a multi-level tree merge operation and that will free multiple blocks from the btree in a single transaction. i.e. we can call xfs_free_extent() multiple times, and hence the btree manipulation transaction is vulnerable to this busy extent deadlock vector.

To fix this, convert all the remaining callers of xfs_free_extent() to use xfs_free_extent_later() to queue XEFIs and hence defer processing of the extent frees to a context that can be safely restarted if a deadlock condition is detected.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Chandan Babu R chandan.babu@oracle.com

Conflicts: fs/xfs/libxfs/xfs_ag.c fs/xfs/libxfs/xfs_alloc.c fs/xfs/libxfs/xfs_ialloc_btree.c fs/xfs/libxfs/xfs_refcount_btree.c fs/xfs/xfs_extfree_item.c Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 4 ++++ fs/xfs/libxfs/xfs_alloc.h | 8 +++++--- fs/xfs/libxfs/xfs_bmap.c | 8 +++++--- fs/xfs/libxfs/xfs_bmap_btree.c | 3 ++- fs/xfs/libxfs/xfs_ialloc.c | 8 ++++---- fs/xfs/libxfs/xfs_ialloc_btree.c | 6 ++++-- fs/xfs/libxfs/xfs_refcount.c | 9 ++++++--- fs/xfs/libxfs/xfs_refcount_btree.c | 9 ++------- fs/xfs/xfs_extfree_item.c | 3 ++- fs/xfs/xfs_reflink.c | 3 ++- 10 files changed, 36 insertions(+), 25 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index ebfaf5f48010..2e7d442c117b 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2476,6 +2476,7 @@ xfs_defer_agfl_block( new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); new->xefi_blockcount = 1; new->xefi_owner = oinfo->oi_owner; + new->xefi_agresv = XFS_AG_RESV_AGFL;

if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, new->xefi_startblock))) return -EFSCORRUPTED; @@ -2496,6 +2497,7 @@ __xfs_free_extent_later( xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type, bool skip_discard) { struct xfs_extent_free_item *new; /* new element */ @@ -2516,6 +2518,7 @@ __xfs_free_extent_later( ASSERT(agbno + len <= mp->m_sb.sb_agblocks); #endif ASSERT(xfs_extfree_item_cache != NULL); + ASSERT(type != XFS_AG_RESV_AGFL);

if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) return -EFSCORRUPTED; @@ -2524,6 +2527,7 @@ __xfs_free_extent_later( GFP_KERNEL | __GFP_NOFAIL); new->xefi_startblock = bno; new->xefi_blockcount = (xfs_extlen_t)len; + new->xefi_agresv = type; if (skip_discard) new->xefi_flags |= XFS_EFI_SKIP_DISCARD; if (oinfo) { diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 0fd02e889216..cfacb88e22d3 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -248,7 +248,7 @@ xfs_buf_to_agfl_bno(

int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, - bool skip_discard); + enum xfs_ag_resv_type type, bool skip_discard);

/* * List of extents to be free "later". @@ -260,6 +260,7 @@ struct xfs_extent_free_item { xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ unsigned int xefi_flags; + enum xfs_ag_resv_type xefi_agresv; };

#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */ @@ -271,9 +272,10 @@ xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, - const struct xfs_owner_info *oinfo) + const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type) { - return __xfs_free_extent_later(tp, bno, len, oinfo, false); + return __xfs_free_extent_later(tp, bno, len, oinfo, type, false); }

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 3eb1d31df6e1..c5d784daed8b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -572,7 +572,8 @@ xfs_bmap_btree_to_extents( return error;

xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo, + XFS_AG_RESV_NONE); if (error) return error;

@@ -5194,8 +5195,9 @@ xfs_bmap_del_extent_real( } else { error = __xfs_free_extent_later(tp, del->br_startblock, del->br_blockcount, NULL, - (bflags & XFS_BMAPI_NODISCARD) || - del->br_state == XFS_EXT_UNWRITTEN); + XFS_AG_RESV_NONE, + ((bflags & XFS_BMAPI_NODISCARD) || + del->br_state == XFS_EXT_UNWRITTEN)); if (error) goto done; } diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 021afb43c56b..4118c4c1443a 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -287,7 +287,8 @@ xfs_bmbt_free_block( int error;

xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo, + XFS_AG_RESV_NONE); if (error) return error; ip->i_d.di_nblocks--; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d26f966b0901..1861fc71f028 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1870,8 +1870,8 @@ xfs_difree_inode_chunk( /* not sparse, calculate extent info directly */ return xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); + M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES, + XFS_AG_RESV_NONE); }

/* holemask is only 16-bits (fits in an unsigned long) */ @@ -1916,8 +1916,8 @@ xfs_difree_inode_chunk( ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); error = xfs_free_extent_later(tp, - XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + XFS_AGB_TO_FSB(mp, agno, agbno), contigblk, + &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE); if (error) return error;

diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 0733270062f6..5150010ca4c6 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -154,9 +154,11 @@ __xfs_inobt_free_block( struct xfs_buf *bp, enum xfs_ag_resv_type resv) { + xfs_fsblock_t fsbno; + xfs_inobt_mod_blockcount(cur, -1); - return xfs_free_extent(cur->bc_tp, - XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)), 1, + fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)); + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_INOBT, resv); }

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 0e1a9f047b12..4191548b4736 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -975,7 +975,8 @@ xfs_refcount_adjust_extents( cur->bc_ag.agno, tmp.rc_startblock); error = xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL); + tmp.rc_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) goto out_error; } @@ -1022,7 +1023,8 @@ xfs_refcount_adjust_extents( cur->bc_ag.agno, ext.rc_startblock); error = xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL); + ext.rc_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) goto out_error; } @@ -1751,7 +1753,8 @@ xfs_refcount_recover_cow_leftovers(

/* Free the block. */ error = xfs_free_extent_later(tp, fsb, - rr->rr_rrec.rc_blockcount, NULL); + rr->rr_rrec.rc_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) goto out_trans;

diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 59b1fee4f680..3e0d82f1802b 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -103,18 +103,13 @@ xfs_refcountbt_free_block( struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); - int error;

trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.agno, XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1); be32_add_cpu(&agf->agf_refcount_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS); - error = xfs_free_extent(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_REFC, - XFS_AG_RESV_METADATA); - if (error) - return error; - - return error; + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, + &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA); }

STATIC int diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 100a21fe0527..c9c648a618d6 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -383,7 +383,7 @@ xfs_trans_free_extent( free->xefi_blockcount);

error = __xfs_free_extent(tp, free->xefi_startblock, - free->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE, + free->xefi_blockcount, &oinfo, free->xefi_agresv, free->xefi_flags & XFS_EFI_SKIP_DISCARD); /* * Mark the transaction dirty, even on error. This ensures the @@ -631,6 +631,7 @@ xfs_efi_item_recover( for (i = 0; i < efip->efi_format.efi_nextents; i++) { struct xfs_extent_free_item fake = { .xefi_owner = XFS_RMAP_OWN_UNKNOWN, + .xefi_agresv = XFS_AG_RESV_NONE, };

extp = &efip->efi_format.efi_extents[i]; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index e20aa87fed21..551cc92b049d 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -485,7 +485,8 @@ xfs_reflink_cancel_cow_blocks( del.br_blockcount);

error = xfs_free_extent_later(*tpp, del.br_startblock, - del.br_blockcount, NULL); + del.br_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) break;

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.4-rc6 commit 6a2a9d776c4ae24a797e25eed2b9f7f33f756296 category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

To avoid blocking in xfs_extent_busy_flush() when freeing extents and the only busy extents are held by the current transaction, we need to pass the XFS_ALLOC_FLAG_FREEING flag context all the way into xfs_extent_busy_flush().

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Chandan Babu R chandan.babu@oracle.com

Conflicts: fs/xfs/libxfs/xfs_alloc.c fs/xfs/libxfs/xfs_alloc.h Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 90 +++++++++++++++++++++------------------ fs/xfs/libxfs/xfs_alloc.h | 2 +- fs/xfs/xfs_extent_busy.c | 3 +- fs/xfs/xfs_extent_busy.h | 2 +- 4 files changed, 52 insertions(+), 45 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index ce3dcd57e756..11de77ff02b1 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -37,8 +37,8 @@ struct workqueue_struct *xfs_alloc_wq; #define XFSA_FIXUP_CNT_OK 2

STATIC int xfs_alloc_ag_vextent_exact(xfs_alloc_arg_t *); -STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *); -STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *); +STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *, uint32_t); +STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *, uint32_t);

/* * Size of the AGFL. For CRC-enabled filesystes we steal a couple of slots in @@ -1127,7 +1127,8 @@ xfs_alloc_ag_vextent_small( */ STATIC int /* error */ xfs_alloc_ag_vextent( - xfs_alloc_arg_t *args) /* argument structure for allocation */ + xfs_alloc_arg_t *args, /* argument structure for allocation */ + uint32_t alloc_flags) { int error=0;

@@ -1143,10 +1144,10 @@ xfs_alloc_ag_vextent( args->wasfromfl = 0; switch (args->type) { case XFS_ALLOCTYPE_THIS_AG: - error = xfs_alloc_ag_vextent_size(args); + error = xfs_alloc_ag_vextent_size(args, alloc_flags); break; case XFS_ALLOCTYPE_NEAR_BNO: - error = xfs_alloc_ag_vextent_near(args); + error = xfs_alloc_ag_vextent_near(args, alloc_flags); break; case XFS_ALLOCTYPE_THIS_BNO: error = xfs_alloc_ag_vextent_exact(args); @@ -1554,7 +1555,8 @@ xfs_alloc_ag_vextent_lastblock( */ STATIC int xfs_alloc_ag_vextent_near( - struct xfs_alloc_arg *args) + struct xfs_alloc_arg *args, + uint32_t alloc_flags) { struct xfs_alloc_cur acur = {}; int error; /* error code */ @@ -1630,7 +1632,7 @@ xfs_alloc_ag_vextent_near( if (acur.busy) { trace_xfs_alloc_near_busy(args); xfs_extent_busy_flush(args->mp, args->pag, - acur.busy_gen); + acur.busy_gen, alloc_flags); goto restart; } trace_xfs_alloc_size_neither(args); @@ -1653,21 +1655,22 @@ xfs_alloc_ag_vextent_near( * and of the form k * prod + mod unless there's nothing that large. * Return the starting a.g. block, or NULLAGBLOCK if we can't do it. */ -STATIC int /* error */ +static int xfs_alloc_ag_vextent_size( - xfs_alloc_arg_t *args) /* allocation argument structure */ + struct xfs_alloc_arg *args, + uint32_t alloc_flags) { - struct xfs_agf *agf = args->agbp->b_addr; - xfs_btree_cur_t *bno_cur; /* cursor for bno btree */ - xfs_btree_cur_t *cnt_cur; /* cursor for cnt btree */ - int error; /* error result */ - xfs_agblock_t fbno; /* start of found freespace */ - xfs_extlen_t flen; /* length of found freespace */ - int i; /* temp status variable */ - xfs_agblock_t rbno; /* returned block number */ - xfs_extlen_t rlen; /* length of returned extent */ - bool busy; - unsigned busy_gen; + struct xfs_agf *agf = args->agbp->b_addr; + struct xfs_btree_cur *bno_cur; + struct xfs_btree_cur *cnt_cur; + xfs_agblock_t fbno; /* start of found freespace */ + xfs_extlen_t flen; /* length of found freespace */ + xfs_agblock_t rbno; /* returned block number */ + xfs_extlen_t rlen; /* length of returned extent */ + bool busy; + unsigned busy_gen; + int error; + int i;

restart: /* @@ -1736,8 +1739,8 @@ xfs_alloc_ag_vextent_size( xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, - args->pag, busy_gen); + xfs_extent_busy_flush(args->mp, args->pag, + busy_gen, alloc_flags); goto restart; } } @@ -1821,7 +1824,8 @@ xfs_alloc_ag_vextent_size( if (busy) { xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, busy_gen); + xfs_extent_busy_flush(args->mp, args->pag, busy_gen, + alloc_flags); goto restart; } goto out_nominleft; @@ -2545,7 +2549,7 @@ __xfs_free_extent_later( int /* error */ xfs_alloc_fix_freelist( struct xfs_alloc_arg *args, /* allocation argument structure */ - int flags) /* XFS_ALLOC_FLAG_... */ + uint32_t alloc_flags) { struct xfs_mount *mp = args->mp; struct xfs_perag *pag = args->pag; @@ -2561,7 +2565,7 @@ xfs_alloc_fix_freelist( ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);

if (!pag->pagf_init) { - error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); + error = xfs_alloc_read_agf(mp, tp, args->agno, alloc_flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2576,8 +2580,8 @@ xfs_alloc_fix_freelist( * point */ if (pag->pagf_metadata && (args->datatype & XFS_ALLOC_USERDATA) && - (flags & XFS_ALLOC_FLAG_TRYLOCK)) { - ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); + (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)) { + ASSERT(!(alloc_flags & XFS_ALLOC_FLAG_FREEING)); goto out_agbp_relse; }

@@ -2587,7 +2591,7 @@ xfs_alloc_fix_freelist( * transaction if needed. */ need = xfs_alloc_min_freelist(mp, pag) * (1 + args->postallocs); - if (!xfs_alloc_space_available(args, need, flags | + if (!xfs_alloc_space_available(args, need, alloc_flags | XFS_ALLOC_FLAG_CHECK)) goto out_agbp_relse;

@@ -2596,7 +2600,7 @@ xfs_alloc_fix_freelist( * Can fail if we're not blocking on locks, and it's held. */ if (!agbp) { - error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); + error = xfs_alloc_read_agf(mp, tp, args->agno, alloc_flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2611,7 +2615,7 @@ xfs_alloc_fix_freelist(

/* If there isn't enough total space or single-extent, reject it. */ need = xfs_alloc_min_freelist(mp, pag) * (1 + args->postallocs); - if (!xfs_alloc_space_available(args, need, flags)) + if (!xfs_alloc_space_available(args, need, alloc_flags)) goto out_agbp_relse;

/* @@ -2640,11 +2644,12 @@ xfs_alloc_fix_freelist( */ memset(&targs, 0, sizeof(targs)); /* struct copy below */ - if (flags & XFS_ALLOC_FLAG_NORMAP) + if (alloc_flags & XFS_ALLOC_FLAG_NORMAP) targs.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; else targs.oinfo = XFS_RMAP_OINFO_AG; - while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) { + while (!(alloc_flags & XFS_ALLOC_FLAG_NOSHRINK) && + pag->pagf_flcount > need) { error = xfs_alloc_get_freelist(tp, agbp, &bno, 0); if (error) goto out_agbp_relse; @@ -2673,7 +2678,7 @@ xfs_alloc_fix_freelist( targs.resv = XFS_AG_RESV_AGFL;

/* Allocate as many blocks as possible at once. */ - error = xfs_alloc_ag_vextent(&targs); + error = xfs_alloc_ag_vextent(&targs, alloc_flags); if (error) goto out_agflbp_relse;

@@ -2683,7 +2688,7 @@ xfs_alloc_fix_freelist( * on a completely full ag. */ if (targs.agbno == NULLAGBLOCK) { - if (flags & XFS_ALLOC_FLAG_FREEING) + if (alloc_flags & XFS_ALLOC_FLAG_FREEING) break; goto out_agflbp_relse; } @@ -3130,7 +3135,7 @@ xfs_alloc_vextent( { xfs_agblock_t agsize; /* allocation group size */ int error; - int flags; /* XFS_ALLOC_FLAG_... locking flags */ + uint32_t alloc_flags; /* XFS_ALLOC_FLAG_... locking flags */ struct xfs_mount *mp; /* mount structure pointer */ xfs_agnumber_t sagno; /* starting allocation group number */ xfs_alloctype_t type; /* input allocation type */ @@ -3183,7 +3188,7 @@ xfs_alloc_vextent( break; } args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno); - if ((error = xfs_alloc_ag_vextent(args))) + if ((error = xfs_alloc_ag_vextent(args, 0))) goto error0; break; case XFS_ALLOCTYPE_START_BNO: @@ -3212,13 +3217,13 @@ xfs_alloc_vextent( args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno); args->type = XFS_ALLOCTYPE_THIS_AG; sagno = 0; - flags = 0; + alloc_flags = 0; } else { /* * Start with the given allocation group. */ args->agno = sagno = XFS_FSB_TO_AGNO(mp, args->fsbno); - flags = XFS_ALLOC_FLAG_TRYLOCK; + alloc_flags = XFS_ALLOC_FLAG_TRYLOCK; } /* * Loop over allocation groups twice; first time with @@ -3226,7 +3231,7 @@ xfs_alloc_vextent( */ for (;;) { args->pag = xfs_perag_get(mp, args->agno); - error = xfs_alloc_fix_freelist(args, flags); + error = xfs_alloc_fix_freelist(args, alloc_flags); if (error) { trace_xfs_alloc_vextent_nofix(args); goto error0; @@ -3235,7 +3240,8 @@ xfs_alloc_vextent( * If we get a buffer back then the allocation will fly. */ if (args->agbp) { - if ((error = xfs_alloc_ag_vextent(args))) + if ((error = xfs_alloc_ag_vextent(args, + alloc_flags))) goto error0; break; } @@ -3266,13 +3272,13 @@ xfs_alloc_vextent( * or switch to non-trylock mode. */ if (args->agno == sagno) { - if (flags == 0) { + if (alloc_flags == 0) { args->agbno = NULLAGBLOCK; trace_xfs_alloc_vextent_allfailed(args); break; }

- flags = 0; + alloc_flags = 0; if (type == XFS_ALLOCTYPE_START_BNO) { args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index cfacb88e22d3..8435d02622cc 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -211,7 +211,7 @@ int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp); int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t, struct xfs_buf *, struct xfs_owner_info *); -int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags); +int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags); int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **agbp);

diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 26680444969c..914011cf8c14 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -583,7 +583,8 @@ void xfs_extent_busy_flush( struct xfs_mount *mp, struct xfs_perag *pag, - unsigned busy_gen) + unsigned busy_gen, + uint32_t alloc_flags) { DEFINE_WAIT (wait); int error; diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index 8aea07100092..d70d395ce642 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -52,7 +52,7 @@ xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,

void xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag, - unsigned busy_gen); + unsigned busy_gen, uint32_t alloc_flags);

void xfs_extent_busy_wait_all(struct xfs_mount *mp);

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.4-rc6 commit 8ebbf262d4684e035af5e7aa2a71cab636673a9b category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

If the current transaction holds a busy extent and we are trying to allocate a new extent to fix up the free list, we can deadlock if the AG is entirely empty except for the busy extent held by the transaction.

This can occur at runtime processing an XEFI with multiple extents in this path:

__schedule+0x22f at ffffffff81f75e8f schedule+0x46 at ffffffff81f76366 xfs_extent_busy_flush+0x69 at ffffffff81477d99 xfs_alloc_ag_vextent_size+0x16a at ffffffff8141711a xfs_alloc_ag_vextent+0x19b at ffffffff81417edb xfs_alloc_fix_freelist+0x22f at ffffffff8141896f xfs_free_extent_fix_freelist+0x6a at ffffffff8141939a __xfs_free_extent+0x99 at ffffffff81419499 xfs_trans_free_extent+0x3e at ffffffff814a6fee xfs_extent_free_finish_item+0x24 at ffffffff814a70d4 xfs_defer_finish_noroll+0x1f7 at ffffffff81441407 xfs_defer_finish+0x11 at ffffffff814417e1 xfs_itruncate_extents_flags+0x13d at ffffffff8148b7dd xfs_inactive_truncate+0xb9 at ffffffff8148bb89 xfs_inactive+0x227 at ffffffff8148c4f7 xfs_fs_destroy_inode+0xb8 at ffffffff81496898 destroy_inode+0x3b at ffffffff8127d2ab do_unlinkat+0x1d1 at ffffffff81270df1 do_syscall_64+0x40 at ffffffff81f6b5f0 entry_SYSCALL_64_after_hwframe+0x44 at ffffffff8200007c

This can also happen in log recovery when processing an EFI with multiple extents through this path:

context_switch() kernel/sched/core.c:3881 __schedule() kernel/sched/core.c:5111 schedule() kernel/sched/core.c:5186 xfs_extent_busy_flush() fs/xfs/xfs_extent_busy.c:598 xfs_alloc_ag_vextent_size() fs/xfs/libxfs/xfs_alloc.c:1641 xfs_alloc_ag_vextent() fs/xfs/libxfs/xfs_alloc.c:828 xfs_alloc_fix_freelist() fs/xfs/libxfs/xfs_alloc.c:2362 xfs_free_extent_fix_freelist() fs/xfs/libxfs/xfs_alloc.c:3029 __xfs_free_extent() fs/xfs/libxfs/xfs_alloc.c:3067 xfs_trans_free_extent() fs/xfs/xfs_extfree_item.c:370 xfs_efi_recover() fs/xfs/xfs_extfree_item.c:626 xlog_recover_process_efi() fs/xfs/xfs_log_recover.c:4605 xlog_recover_process_intents() fs/xfs/xfs_log_recover.c:4893 xlog_recover_finish() fs/xfs/xfs_log_recover.c:5824 xfs_log_mount_finish() fs/xfs/xfs_log.c:764 xfs_mountfs() fs/xfs/xfs_mount.c:978 xfs_fs_fill_super() fs/xfs/xfs_super.c:1908 mount_bdev() fs/super.c:1417 xfs_fs_mount() fs/xfs/xfs_super.c:1985 legacy_get_tree() fs/fs_context.c:647 vfs_get_tree() fs/super.c:1547 do_new_mount() fs/namespace.c:2843 do_mount() fs/namespace.c:3163 ksys_mount() fs/namespace.c:3372 __do_sys_mount() fs/namespace.c:3386 __se_sys_mount() fs/namespace.c:3383 __x64_sys_mount() fs/namespace.c:3383 do_syscall_64() arch/x86/entry/common.c:296 entry_SYSCALL_64() arch/x86/entry/entry_64.S:180

To avoid this deadlock, we should not block in xfs_extent_busy_flush() if we hold a busy extent in the current transaction.

Now that the EFI processing code can handle requeuing a partially completed EFI, we can detect this situation in xfs_extent_busy_flush() and return -EAGAIN rather than going to sleep forever. The -EAGAIN get propagated back out to the xfs_trans_free_extent() context, where the EFD is populated and the transaction is rolled, thereby moving the busy extents into the CIL.

At this point, we can retry the extent free operation again with a clean transaction. If we hit the same "all free extents are busy" situation when trying to fix up the free list, we can safely call xfs_extent_busy_flush() and wait for the busy extents to resolve and wake us. At this point, the allocation search can make progress again and we can fix up the free list.

This deadlock was first reported by Chandan in mid-2021, but I couldn't make myself understood during review, and didn't have time to fix it myself.

It was reported again in March 2023, and again I have found myself unable to explain the complexities of the solution needed during review.

As such, I don't have hours more time to waste trying to get the fix written the way it needs to be written, so I'm just doing it myself. This patchset is largely based on Wengang Wang's last patch, but with all the unnecessary stuff removed, split up into multiple patches and cleaned up somewhat.

Reported-by: Chandan Babu R chandanrlinux@gmail.com Reported-by: Wengang Wang wen.gang.wang@oracle.com Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 68 ++++++++++++++++++++++++++++----------- fs/xfs/libxfs/xfs_alloc.h | 11 ++++--- fs/xfs/xfs_extent_busy.c | 33 ++++++++++++++++--- fs/xfs/xfs_extent_busy.h | 6 ++-- 4 files changed, 88 insertions(+), 30 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 11de77ff02b1..0c99287d0d89 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1575,6 +1575,8 @@ xfs_alloc_ag_vextent_near( if (args->agbno > args->max_agbno) args->agbno = args->max_agbno;

+ /* Retry once quickly if we find busy extents before blocking. */ + alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH; restart: len = 0;

@@ -1630,9 +1632,20 @@ xfs_alloc_ag_vextent_near( */ if (!acur.len) { if (acur.busy) { + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ trace_xfs_alloc_near_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, - acur.busy_gen, alloc_flags); + error = xfs_extent_busy_flush(args->tp, args->pag, + acur.busy_gen, alloc_flags); + if (error) + goto out; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; goto restart; } trace_xfs_alloc_size_neither(args); @@ -1672,6 +1685,8 @@ xfs_alloc_ag_vextent_size( int error; int i;

+ /* Retry once quickly if we find busy extents before blocking. */ + alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH; restart: /* * Allocate and initialize a cursor for the by-size btree. @@ -1730,19 +1745,25 @@ xfs_alloc_ag_vextent_size( error = xfs_btree_increment(cnt_cur, 0, &i); if (error) goto error0; - if (i == 0) { - /* - * Our only valid extents must have been busy. - * Make it unbusy by forcing the log out and - * retrying. - */ - xfs_btree_del_cursor(cnt_cur, - XFS_BTREE_NOERROR); - trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, - busy_gen, alloc_flags); - goto restart; - } + if (i) + continue; + + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ + trace_xfs_alloc_size_busy(args); + error = xfs_extent_busy_flush(args->tp, args->pag, + busy_gen, alloc_flags); + if (error) + goto error0; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + goto restart; } }

@@ -1822,10 +1843,21 @@ xfs_alloc_ag_vextent_size( args->len = rlen; if (rlen < args->minlen) { if (busy) { - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, busy_gen, - alloc_flags); + error = xfs_extent_busy_flush(args->tp, args->pag, + busy_gen, alloc_flags); + if (error) + goto error0; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); goto restart; } goto out_nominleft; diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 8435d02622cc..6ae1ade607cd 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -38,11 +38,12 @@ typedef unsigned int xfs_alloctype_t; /* * Flags for xfs_alloc_fix_freelist. */ -#define XFS_ALLOC_FLAG_TRYLOCK 0x00000001 /* use trylock for buffer locking */ -#define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/ -#define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */ -#define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */ -#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */ +#define XFS_ALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */ +#define XFS_ALLOC_FLAG_FREEING (1U << 1) /* indicate caller is freeing extents*/ +#define XFS_ALLOC_FLAG_NORMAP (1U << 2) /* don't modify the rmapbt */ +#define XFS_ALLOC_FLAG_NOSHRINK (1U << 3) /* don't shrink the freelist */ +#define XFS_ALLOC_FLAG_CHECK (1U << 4) /* test only, don't modify args */ +#define XFS_ALLOC_FLAG_TRYFLUSH (1U << 5) /* don't wait in busy extent flush */

/* * Argument structure for xfs_alloc routines. diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 914011cf8c14..3b71e1714514 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -578,10 +578,21 @@ xfs_extent_busy_clear(

/* * Flush out all busy extents for this AG. + * + * If the current transaction is holding busy extents, the caller may not want + * to wait for committed busy extents to resolve. If we are being told just to + * try a flush or progress has been made since we last skipped a busy extent, + * return immediately to allow the caller to try again. + * + * If we are freeing extents, we might actually be holding the only free extents + * in the transaction busy list and the log force won't resolve that situation. + * In this case, we must return -EAGAIN to avoid a deadlock by informing the + * caller it needs to commit the busy extents it holds before retrying the + * extent free operation. */ -void +int xfs_extent_busy_flush( - struct xfs_mount *mp, + struct xfs_trans *tp, struct xfs_perag *pag, unsigned busy_gen, uint32_t alloc_flags) @@ -589,10 +600,23 @@ xfs_extent_busy_flush( DEFINE_WAIT (wait); int error;

- error = xfs_log_force(mp, XFS_LOG_SYNC); + error = xfs_log_force(tp->t_mountp, XFS_LOG_SYNC); if (error) - return; + return error; + + /* Avoid deadlocks on uncommitted busy extents. */ + if (!list_empty(&tp->t_busy)) { + if (alloc_flags & XFS_ALLOC_FLAG_TRYFLUSH) + return 0; + + if (busy_gen != READ_ONCE(pag->pagb_gen)) + return 0; + + if (alloc_flags & XFS_ALLOC_FLAG_FREEING) + return -EAGAIN; + }

+ /* Wait for committed busy extents to resolve. */ do { prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE); if (busy_gen != READ_ONCE(pag->pagb_gen)) @@ -601,6 +625,7 @@ xfs_extent_busy_flush( } while (1);

finish_wait(&pag->pagb_wait, &wait); + return 0; }

void diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index d70d395ce642..f145d5320519 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -50,9 +50,9 @@ bool xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno, xfs_extlen_t *len, unsigned *busy_gen);

-void -xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag, - unsigned busy_gen, uint32_t alloc_flags); +int +xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag, + unsigned busy_gen, uint32_t alloc_flags);

void xfs_extent_busy_wait_all(struct xfs_mount *mp);

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.4-rc6 commit edd8276dd70279c29d412d99b99c2c0cac1b2cdd category: bugfix bugzilla: 188883, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

The AGF verifier does not check that the AGF length field is within known good bounds. This has never been checked by runtime kernel code (i.e. the lack of verification goes back to 1993) yet we assume in many places that it is correct and verify other metdata against it.

Add length verification to the AGF verifier. The length of the AGF must be equal to the size of the AG specified in the superblock, unless it is the last AG in the filesystem. In that case, it must be less than or equal to sb->sb_agblocks and greater than XFS_MIN_AG_BLOCKS, which is the smallest AG a growfs operation will allow to exist.

This requires a bit of rework of the verifier function. We want to verify metadata before we use it to verify other metadata. Hence we need to verify the AGF sequence numbers before using them to verify the length of the AGF. Then we can verify the AGF length before we verify AGFL fields. Then we can verifier other fields that are bounds limited by the AGF length.

And, finally, by calculating agf_length only once into a local variable, we can collapse repeated "if (xfs_has_foo() &&" conditionaly checks into single checks. This makes the code much easier to follow as all the checks for a given feature are obviously in the same place.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org

Conflicts: fs/xfs/libxfs/xfs_alloc.c Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 89 ++++++++++++++++++++++++--------------- 1 file changed, 56 insertions(+), 33 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 0c99287d0d89..4a139583a905 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2939,6 +2939,7 @@ xfs_agf_verify( { struct xfs_mount *mp = bp->b_mount; struct xfs_agf *agf = bp->b_addr; + uint32_t agf_length = be32_to_cpu(agf->agf_length);

if (xfs_has_crc(mp)) { if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid)) @@ -2950,18 +2951,49 @@ xfs_agf_verify( if (!xfs_verify_magic(bp, agf->agf_magicnum)) return __this_address;

- if (!(XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) && - be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) && - be32_to_cpu(agf->agf_flfirst) < xfs_agfl_size(mp) && - be32_to_cpu(agf->agf_fllast) < xfs_agfl_size(mp) && - be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp))) + if (!XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum))) return __this_address;

- if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks) + /* + * Both agf_seqno and agf_length need to validated before anything else + * block number related in the AGF or AGFL can be checked. + * + * During growfs operations, the perag is not fully initialised, + * so we can't use it for any useful checking. growfs ensures we can't + * use it by using uncached buffers that don't have the perag attached + * so we can detect and avoid this problem. + */ + if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno) + return __this_address; + + /* + * Only the last AGF in the filesytsem is allowed to be shorter + * than the AG size recorded in the superblock. + */ + if (agf_length != mp->m_sb.sb_agblocks) { + /* + * During growfs, the new last AGF can get here before we + * have updated the superblock. Give it a pass on the seqno + * check. + */ + if (bp->b_pag && + be32_to_cpu(agf->agf_seqno) != mp->m_sb.sb_agcount - 1) + return __this_address; + if (agf_length < XFS_MIN_AG_BLOCKS) + return __this_address; + if (agf_length > mp->m_sb.sb_agblocks) + return __this_address; + } + + if (be32_to_cpu(agf->agf_flfirst) >= xfs_agfl_size(mp)) + return __this_address; + if (be32_to_cpu(agf->agf_fllast) >= xfs_agfl_size(mp)) + return __this_address; + if (be32_to_cpu(agf->agf_flcount) > xfs_agfl_size(mp)) return __this_address;

if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) || - be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length)) + be32_to_cpu(agf->agf_freeblks) > agf_length) return __this_address;

if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 || @@ -2970,37 +3002,28 @@ xfs_agf_verify( be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > XFS_BTREE_MAXLEVELS) return __this_address;

- if (xfs_has_rmapbt(mp) && - (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 || - be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS)) - return __this_address; - - if (xfs_has_rmapbt(mp) && - be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length)) + if (xfs_has_lazysbcount(mp) && + be32_to_cpu(agf->agf_btreeblks) > agf_length) return __this_address;

- /* - * during growfs operations, the perag is not fully initialised, - * so we can't use it for any useful checking. growfs ensures we can't - * use it by using uncached buffers that don't have the perag attached - * so we can detect and avoid this problem. - */ - if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno) - return __this_address; + if (xfs_has_rmapbt(mp)) { + if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length) + return __this_address;

- if (xfs_has_lazysbcount(mp) && - be32_to_cpu(agf->agf_btreeblks) > be32_to_cpu(agf->agf_length)) - return __this_address; + if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 || + be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > + mp->m_rmap_maxlevels) + return __this_address; + }

- if (xfs_has_reflink(mp) && - be32_to_cpu(agf->agf_refcount_blocks) > - be32_to_cpu(agf->agf_length)) - return __this_address; + if (xfs_has_reflink(mp)) { + if (be32_to_cpu(agf->agf_refcount_blocks) > agf_length) + return __this_address;

- if (xfs_has_reflink(mp) && - (be32_to_cpu(agf->agf_refcount_level) < 1 || - be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS)) - return __this_address; + if (be32_to_cpu(agf->agf_refcount_level) < 1 || + be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels) + return __this_address; + }

return NULL;

Offering: HULK hulk inclusion category: bugfix bugzilla: 188734, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

The following error occurred when do IO fault injection test:

XFS: Assertion failed: xlog_is_shutdown(lip->li_log), file: fs/xfs/xfs_inode_item.c, line: 748

commit "3c4cb76bce43 xfs: xfs_trans_commit() path must check for log shutdown" fix a problem that dirty transaction was canceled before log shutdown, because of the log is still running, it result dirty and unlogged inode item that isn't in the AIL in memory that can be flushed to disk via writeback clustering.

xfs_trans_cancel() has the same problem, if a shut down races with xfs_trans_cancel() and we have shut down the filesystem but not the log, we will still cancel the transaction before log shutdown. So xfs_trans_cancel() needs to check log state for shutdown, not mount.

Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_trans.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 36a894a2128a..609ddada6fd7 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -985,7 +985,7 @@ xfs_trans_cancel( * progress, so we only need to check against the mount shutdown state * here. */ - if (dirty && !xfs_is_shutdown(mp)) { + if (dirty && !(xfs_is_shutdown(mp) && xlog_is_shutdown(log))) { XFS_ERROR_REPORT("xfs_trans_cancel", XFS_ERRLEVEL_LOW, mp); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); }

From: Colin Ian King colin.i.king@gmail.com

mainline inclusion from mainline-v6.1-rc1 commit fc93812c725068e6a491ce574f058a4530130c00 category: bugfix bugzilla: 189095, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

The assignment to pointer lip is not really required, the pointer lip is redundant and can be removed.

Cleans up clang-scan warning: warning: Although the value stored to 'lip' is used in the enclosing expression, the value is never actually read from 'lip' [deadcode.DeadStores]

Signed-off-by: Colin Ian King colin.i.king@gmail.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_trans_ail.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 0f9d4527dc7d..11a938652f22 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -730,11 +730,10 @@ void xfs_ail_push_all_sync( struct xfs_ail *ailp) { - struct xfs_log_item *lip; DEFINE_WAIT(wait);

spin_lock(&ailp->ail_lock); - while ((lip = xfs_ail_max(ailp)) != NULL) { + while (xfs_ail_max(ailp) != NULL) { prepare_to_wait(&ailp->ail_empty, &wait, TASK_UNINTERRUPTIBLE); wake_up_process(ailp->ail_task); spin_unlock(&ailp->ail_lock);

Offering: HULK hulk inclusion category: bugfix bugzilla: 189177, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

The following corruption is reported when log recovery:

XFS (loop0): Metadata corruption detected at xfs_agf_verify+0x386/0xb70, xfs_agf block 0x64001 XFS (loop0): Unmount and run xfs_repair XFS (loop0): First 128 bytes of corrupted metadata buffer: 00000000: 58 41 47 46 00 00 00 01 00 00 00 02 00 00 4b 88 XAGF..........K. 00000010: 00 00 00 01 00 00 00 02 00 00 00 00 00 00 00 01 ................ 00000020: 00 00 00 01 00 00 00 00 00 00 00 01 00 00 00 04 ................ 00000030: 00 00 00 04 00 00 4b 7e 00 00 4b 7e 00 00 00 00 ......K~..K~.... 00000040: 3a 9d 97 6d b5 a0 42 13 a3 b3 7f 28 2a ac 3f e8 :..m..B....(*.?. 00000050: 00 00 00 00 00 00 00 01 00 00 00 05 00 00 00 01 ................ 00000060: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000070: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ XFS (loop0): Corruption of in-memory data (0x8) detected at _xfs_buf_ioapply+0xbc9/0xe60 (fs/xfs/xfs_buf.c:1593). Shutting down filesystem. XFS (loop0): Please unmount the filesystem and rectify the problem(s) XFS (loop0): log mount/recovery failed: error -117 XFS (loop0): log mount failed

This problem occurs during agf write verify, where the AG's agf_length is smaller than sb_agblocks, and it is not the last AG. Consider the following situation, the file system has 3 AG, and the last AG is not full size, now the file system is growfs twice. In the first growfs, only AG2 is increased some blocks. In the second growfs, AG2 is extent to the full AG size and an AG3 is added.

pre growfs:

|----------|----------|-----|

First growfs:

|----------|----------|--------|

Second growfs:

|----------|----------|----------|-------| AG0 AG1 AG2 AG3

During each growfs, agf in AG2 and sb will be modified, if sb has already written to metadata and agf has not yet, then a shutdown occurs. The next time we mount the disk, the sb changes from the second growfs will have taken effect in memory, when we recovery the agf from the first growfs will report the above problem.

Fixes: b0c25a61d4c0 ("xfs: AGF length has never been bounds checked") Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index fc60013ffba9..433798f5d935 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2970,7 +2970,8 @@ xfs_agf_verify( * Only the last AGF in the filesytsem is allowed to be shorter * than the AG size recorded in the superblock. */ - if (agf_length != mp->m_sb.sb_agblocks) { + if (agf_length != mp->m_sb.sb_agblocks && + !(bp->b_flags & _XBF_LOGRECOVERY)) { /* * During growfs, the new last AGF can get here before we * have updated the superblock. Give it a pass on the seqno

From: Guo Xuenan guoxuenan@huawei.com

Offering: HULK hulk inclusion category: bugfix bugzilla: 188788, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

In DEBUG mode may do sparse inode allocations randomly, but forget to set the remaining space correctly for the inode btree to split. It's OK for most cases, only under DEBUG mode and AG space is running out may bring something bad.

Fixes: 1cdadee11f8d ("xfs: randomly do sparse inode allocations in DEBUG mode") Signed-off-by: Guo Xuenan guoxuenan@huawei.com Signed-off-by: yangerkun yangerkun@huawei.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_ialloc.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 1861fc71f028..0c2b7a6601a0 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -768,6 +768,8 @@ xfs_ialloc_ag_alloc( args.alignment = args.mp->m_sb.sb_spino_align; args.prod = 1;

+ /* Allow space for the inode btree to split */ + args.minleft = igeo->inobt_maxlevels; args.minlen = igeo->ialloc_min_blks; args.maxlen = args.minlen;

From: yangerkun yangerkun@huawei.com

Offering: HULK hulk inclusion category: bugfix bugzilla: 188788, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

Twice fixup for the same ag may happen within exact one tp, and the consume of agfl after first fixup may trigger failure of second fixup, which is a unintended behavior and then xfs shutdown[1][2].

Gao Xiang describe one solution that we can reserve more blocks when first fixup, but there is some logical error:

- we may first see postallocs as 1 and second as 0, this can trigger pointless agfl filling or shortening - upper case(postallocs first equals to 1, second equals to 0) give us examples that we need shorten the agfl, but xfs_alloc_fix_freelist can only free agfl after success freespace check. Besides, the filling or shortening of agfl won't change fdblocks, so we can fall into that we can see fdblocks(or resblocks) but ag fixup will reject us, and then xfs can shutdown too - once postallocs equals to 1, it can also change the logical of xfs_alloc_ag_max_usable, which will change the block allocation logical(found this problem by check each ag's freeblocks after we fallocate a huge file) - once postallocs equals to 1, we reserve 2 * xfs_alloc_min_freelist(), but sometimes it seems not enough once bnt/cnt grow and the second fixup need more reserve...

This patch fix all bug above by using m_ag_maxlevels to reserve more blocks, and adapt xfs_alloc_set_aside/xfs_alloc_ag_max_usable to match this more reserve. Besides, we just reserve more, won't fill or shorten agfl according to that reserve.

[1] https://www.spinics.net/lists/linux-xfs/msg66440.html [2] https://lore.kernel.org/linux-xfs/20221228133204.4021519-1-guoxuenan@huawei....

Fixes: 53f85096f93e ("xfs: account extra freespace btree splits for multiple allocations") Signed-off-by: yangerkun yangerkun@huawei.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_alloc.c | 41 ++++++++++++++++++++++++++++++++++----- fs/xfs/xfs_mount.c | 9 +++++++++ 2 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 433798f5d935..d4d7a99114c7 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -81,6 +81,25 @@ xfs_prealloc_blocks( return XFS_IBT_BLOCK(mp) + 1; }

+/* + * Twice fixup for the same ag may happen within exact one tp, and the consume + * of agfl after first fixup may trigger second fixup's failure, then xfs will + * shutdown. To avoid that, we reserve blocks which can satisfy the second + * fixup. + */ +xfs_extlen_t +xfs_ag_fixup_aside( + struct xfs_mount *mp) +{ + xfs_extlen_t ret; + + ret = 2 * mp->m_ag_maxlevels; + if (xfs_has_rmapbt(mp)) + ret += mp->m_rmap_maxlevels; + + return ret; +} + /* * In order to avoid ENOSPC-related deadlock caused by out-of-order locking of * AGF buffer (PV 947395), we place constraints on the relationship among @@ -95,12 +114,15 @@ xfs_prealloc_blocks( * * We need to reserve 4 fsbs _per AG_ for the freelist and 4 more to handle a * potential split of the file's bmap btree. + * + * Besides, comment for xfs_ag_fixup_aside show why we reserve more blocks. */ unsigned int xfs_alloc_set_aside( struct xfs_mount *mp) { - return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4); + return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + + 4 + xfs_ag_fixup_aside(mp)); }

/* @@ -133,6 +155,8 @@ xfs_alloc_ag_max_usable( if (xfs_has_reflink(mp)) blocks++; /* refcount root block */

+ blocks += xfs_ag_fixup_aside(mp); + return mp->m_sb.sb_agblocks - blocks; }

@@ -2591,6 +2615,7 @@ xfs_alloc_fix_freelist( struct xfs_alloc_arg targs; /* local allocation arguments */ xfs_agblock_t bno; /* freelist block */ xfs_extlen_t need; /* total blocks needed in freelist */ + xfs_extlen_t minfree; int error = 0;

/* deferred ops (AGFL block frees) require permanent transactions */ @@ -2622,8 +2647,11 @@ xfs_alloc_fix_freelist( * blocks to perform multiple allocations from a single AG and * transaction if needed. */ - need = xfs_alloc_min_freelist(mp, pag) * (1 + args->postallocs); - if (!xfs_alloc_space_available(args, need, alloc_flags | + minfree = need = xfs_alloc_min_freelist(mp, pag); + if (args->postallocs) + minfree += xfs_ag_fixup_aside(mp); + + if (!xfs_alloc_space_available(args, minfree, alloc_flags | XFS_ALLOC_FLAG_CHECK)) goto out_agbp_relse;

@@ -2646,8 +2674,11 @@ xfs_alloc_fix_freelist( xfs_agfl_reset(tp, agbp, pag);

/* If there isn't enough total space or single-extent, reject it. */ - need = xfs_alloc_min_freelist(mp, pag) * (1 + args->postallocs); - if (!xfs_alloc_space_available(args, need, alloc_flags)) + minfree = need = xfs_alloc_min_freelist(mp, pag); + if (args->postallocs) + minfree += xfs_ag_fixup_aside(mp); + + if (!xfs_alloc_space_available(args, minfree, alloc_flags)) goto out_agbp_relse;

/* diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 3f7044611286..04b347fe1b59 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -778,6 +778,15 @@ xfs_mountfs( xfs_rmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp);

+ /* + * We now need m_ag_maxlevels/m_rmap_maxlevels to initialize + * m_alloc_set_aside/m_ag_max_usable. And when we first do the + * init in xfs_sb_mount_common, m_alloc_set_aside/m_ag_max_usable + * still equals to 0. Redo it now. + */ + mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); + mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); + /* * Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks * is NOT aligned turn off m_dalign since allocator alignment is within

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.1-rc4 commit 198dd8aedee6a7d2de0dfa739f9a008a938f6848 category: bugfix bugzilla: 189079, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

xfs_buffered_write_iomap_end() has a comment about the safety of punching delalloc extents based holding the IOLOCK_EXCL. This comment is wrong, and punching delalloc extents is not race free.

When we punch out a delalloc extent after a write failure in xfs_buffered_write_iomap_end(), we punch out the page cache with truncate_pagecache_range() before we punch out the delalloc extents. At this point, we only hold the IOLOCK_EXCL, so there is nothing stopping mmap() write faults racing with this cleanup operation, reinstantiating a folio over the range we are about to punch and hence requiring the delalloc extent to be kept.

If this race condition is hit, we can end up with a dirty page in the page cache that has no delalloc extent or space reservation backing it. This leads to bad things happening at writeback time.

To avoid this race condition, we need the page cache truncation to be atomic w.r.t. the extent manipulation. We can do this by holding the mapping->invalidate_lock exclusively across this operation - this will prevent new pages from being inserted into the page cache whilst we are removing the pages and the backing extent and space reservation.

Taking the mapping->invalidate_lock exclusively in the buffered write IO path is safe - it naturally nests inside the IOLOCK (see truncate and fallocate paths). iomap_zero_range() can be called from under the mapping->invalidate_lock (from the truncate path via either xfs_zero_eof() or xfs_truncate_page(), but iomap_zero_iter() will not instantiate new delalloc pages (because it skips holes) and hence will not ever need to punch out delalloc extents on failure.

Fix the locking issue, and clean up the code logic a little to avoid unnecessary work if we didn't allocate the delalloc extent or wrote the entire region we allocated.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Long Li leo.lilong@huawei.com

Conflicts: fs/xfs/xfs_iomap.c --- fs/xfs/xfs_iomap.c | 41 +++++++++++++++++++++++------------------ 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 892a9ea714ab..d96c003a29d3 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1138,6 +1138,10 @@ xfs_buffered_write_iomap_end( written = 0; }

+ /* If we didn't reserve the blocks, we're not allowed to punch them. */ + if (!(iomap->flags & IOMAP_F_NEW)) + return 0; + /* * start_fsb refers to the first unused block after a short write. If * nothing was written, round offset down to point at the first block in @@ -1149,27 +1153,28 @@ xfs_buffered_write_iomap_end( start_fsb = XFS_B_TO_FSB(mp, offset + written); end_fsb = XFS_B_TO_FSB(mp, offset + length);

+ /* Nothing to do if we've written the entire delalloc extent */ + if (start_fsb >= end_fsb) + return 0; + /* - * Trim delalloc blocks if they were allocated by this write and we - * didn't manage to write the whole range. - * - * We don't need to care about racing delalloc as we hold i_mutex - * across the reserve/allocate/unreserve calls. If there are delalloc - * blocks in the range, they are ours. + * Lock the mapping to avoid races with page faults re-instantiating + * folios and dirtying them via ->page_mkwrite between the page cache + * truncation and the delalloc extent removal. Failing to do this can + * leave dirty pages with no space reservation in the cache. */ - if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) { - truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), - XFS_FSB_TO_B(mp, end_fsb) - 1); - - error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - end_fsb - start_fsb); - if (error && !xfs_is_shutdown(mp)) { - xfs_alert(mp, "%s: unable to clean up ino %lld", - __func__, ip->i_ino); - return error; - } + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), + XFS_FSB_TO_B(mp, end_fsb) - 1); + + error = xfs_bmap_punch_delalloc_range(ip, start_fsb, + end_fsb - start_fsb); + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + if (error && !xfs_is_shutdown(mp)) { + xfs_alert(mp, "%s: unable to clean up ino %lld", + __func__, ip->i_ino); + return error; } - return 0; }

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.1-rc4 commit 9c7babf94a0d686b552e53aded8d4703d1b8b92b category: bugfix bugzilla: 189079, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Because that's what Christoph wants for this error handling path only XFS uses.

It requires a new iomap export for handling errors over delalloc ranges. This is basically the XFS code as is stands, but even though Christoph wants this as iomap funcitonality, we still have to call it from the filesystem specific ->iomap_end callback, and call into the iomap code with yet another filesystem specific callback to punch the delalloc extent within the defined ranges.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Long Li leo.lilong@huawei.com

Conflicts: fs/xfs/xfs_iomap.c fs/iomap/buffered-io.c include/linux/iomap.h --- fs/xfs/xfs_iomap.c | 83 +++++++++++++++++++++++++++++++--------------- 1 file changed, 57 insertions(+), 26 deletions(-)

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 1ddc1a33effd..f4203e9d7635 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1114,58 +1114,62 @@ xfs_buffered_write_iomap_begin( static int xfs_buffered_write_delalloc_punch( struct inode *inode, - loff_t start_byte, - loff_t end_byte) + loff_t offset, + loff_t length) { struct xfs_mount *mp = XFS_M(inode->i_sb); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, start_byte); - xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end_byte); + xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length);

return xfs_bmap_punch_delalloc_range(XFS_I(inode), start_fsb, end_fsb - start_fsb); }

+/* + * When a short write occurs, the filesystem may need to remove reserved space + * that was allocated in ->iomap_begin from it's ->iomap_end method. For + * filesystems that use delayed allocation, we need to punch out delalloc + * extents from the range that are not dirty in the page cache. As the write can + * race with page faults, there can be dirty pages over the delalloc extent + * outside the range of a short write but still within the delalloc extent + * allocated for this iomap. + * + * This function uses [start_byte, end_byte) intervals (i.e. open ended) to + * simplify range iterations, but converts them back to {offset,len} tuples for + * the punch callback. + */ static int -xfs_buffered_write_iomap_end( - struct inode *inode, - loff_t offset, - loff_t length, - ssize_t written, - unsigned flags, - struct iomap *iomap) +xfs_iomap_file_buffered_write_punch_delalloc( + struct inode *inode, + struct iomap *iomap, + loff_t pos, + loff_t length, + ssize_t written, + int (*punch)(struct inode *inode, loff_t pos, loff_t length)) { - struct xfs_mount *mp = XFS_M(inode->i_sb); struct xfs_inode *ip = XFS_I(inode); loff_t start_byte; loff_t end_byte; + int blocksize = i_blocksize(inode); int error = 0;

if (iomap->type != IOMAP_DELALLOC) return 0;

- /* - * Behave as if the write failed if drop writes is enabled. Set the NEW - * flag to force delalloc cleanup. - */ - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) { - iomap->flags |= IOMAP_F_NEW; - written = 0; - } - /* If we didn't reserve the blocks, we're not allowed to punch them. */ if (!(iomap->flags & IOMAP_F_NEW)) return 0;

/* - * start_fsb refers to the first unused block after a short write. If + * start_byte refers to the first unused block after a short write. If * nothing was written, round offset down to point at the first block in * the range. */ if (unlikely(!written)) - start_byte = round_down(offset, mp->m_sb.sb_blocksize); + start_byte = round_down(pos, blocksize); else - start_byte = round_up(offset + written, mp->m_sb.sb_blocksize); - end_byte = round_up(offset + length, mp->m_sb.sb_blocksize); + start_byte = round_up(pos + written, blocksize); + end_byte = round_up(pos + length, blocksize);

/* Nothing to do if we've written the entire delalloc extent */ if (start_byte >= end_byte) @@ -1179,8 +1183,35 @@ xfs_buffered_write_iomap_end( */ xfs_ilock(ip, XFS_MMAPLOCK_EXCL); truncate_pagecache_range(inode, start_byte, end_byte - 1); - error = xfs_buffered_write_delalloc_punch(inode, start_byte, end_byte); + error = punch(inode, start_byte, end_byte - start_byte); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + + return error; +} + +static int +xfs_buffered_write_iomap_end( + struct inode *inode, + loff_t offset, + loff_t length, + ssize_t written, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_mount *mp = XFS_M(inode->i_sb); + int error; + + /* + * Behave as if the write failed if drop writes is enabled. Set the NEW + * flag to force delalloc cleanup. + */ + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) { + iomap->flags |= IOMAP_F_NEW; + written = 0; + } + + error = xfs_iomap_file_buffered_write_punch_delalloc(inode, iomap, offset, + length, written, &xfs_buffered_write_delalloc_punch); if (error && !xfs_is_shutdown(mp)) { xfs_alert(mp, "%s: unable to clean up ino 0x%llx", __func__, XFS_I(inode)->i_ino);

From: Dave Chinner dchinner@redhat.com

mainline inclusion from mainline-v6.1-rc4 commit 7348b322332d8602a4133f0b861334ea021b134a category: bugfix bugzilla: 189079, https://gitee.com/openeuler/kernel/issues/I76JSK CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

All the callers of xfs_bmap_punch_delalloc_range() jump through hoops to convert a byte range to filesystem blocks before calling xfs_bmap_punch_delalloc_range(). Instead, pass the byte range to xfs_bmap_punch_delalloc_range() and have it do the conversion to filesystem blocks internally.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org

Conflicts: fs/xfs/xfs_aops.c

Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_aops.c | 15 +++++---------- fs/xfs/xfs_bmap_util.c | 10 ++++++---- fs/xfs/xfs_bmap_util.h | 2 +- fs/xfs/xfs_iomap.c | 8 ++------ 4 files changed, 14 insertions(+), 21 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index fe8c19814f1d..aa2e166a4fdc 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -150,9 +150,8 @@ xfs_end_ioend( if (unlikely(error)) { if (ioend->io_flags & IOMAP_F_SHARED) { xfs_reflink_cancel_cow_range(ip, offset, size, true); - xfs_bmap_punch_delalloc_range(ip, - XFS_B_TO_FSBT(mp, offset), - XFS_B_TO_FSB(mp, size)); + xfs_bmap_punch_delalloc_range(ip, offset, + offset + size); } goto done; } @@ -516,12 +515,8 @@ xfs_discard_page( struct page *page, loff_t fileoff) { - struct inode *inode = page->mapping->host; - struct xfs_inode *ip = XFS_I(inode); + struct xfs_inode *ip = XFS_I(page->mapping->host); struct xfs_mount *mp = ip->i_mount; - unsigned int pageoff = offset_in_page(fileoff); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, fileoff); - xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff); int error;

if (xfs_is_shutdown(mp)) @@ -531,8 +526,8 @@ xfs_discard_page( "page discard on page "PTR_FMT", inode 0x%llx, offset %llu.", page, ip->i_ino, fileoff);

- error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - i_blocks_per_page(inode, page) - pageoff_fsb); + error = xfs_bmap_punch_delalloc_range(ip, fileoff, + round_up(fileoff, thp_size(page))); if (error && !xfs_is_shutdown(mp)) xfs_alert(mp, "page discard unable to remove delalloc mapping."); } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a44416597880..edf62092125c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -551,11 +551,13 @@ xfs_getbmap( int xfs_bmap_punch_delalloc_range( struct xfs_inode *ip, - xfs_fileoff_t start_fsb, - xfs_fileoff_t length) + xfs_off_t start_byte, + xfs_off_t end_byte) { + struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = &ip->i_df; - xfs_fileoff_t end_fsb = start_fsb + length; + xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, start_byte); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end_byte); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; int error = 0; @@ -568,7 +570,7 @@ xfs_bmap_punch_delalloc_range(

while (got.br_startoff + got.br_blockcount > start_fsb) { del = got; - xfs_trim_extent(&del, start_fsb, length); + xfs_trim_extent(&del, start_fsb, end_fsb - start_fsb);

/* * A delete can push the cursor forward. Step back to the diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 9f993168b55b..ca9000d38b90 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -31,7 +31,7 @@ xfs_bmap_rtalloc(struct xfs_bmalloca *ap) #endif /* CONFIG_XFS_RT */

int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, - xfs_fileoff_t start_fsb, xfs_fileoff_t length); + xfs_off_t start_byte, xfs_off_t end_byte);

struct kgetbmap { __s64 bmv_offset; /* file offset of segment in blocks */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 25b968e85774..ae96ac52c974 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1117,12 +1117,8 @@ xfs_buffered_write_delalloc_punch( loff_t offset, loff_t length) { - struct xfs_mount *mp = XFS_M(inode->i_sb); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, offset); - xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length); - - return xfs_bmap_punch_delalloc_range(XFS_I(inode), start_fsb, - end_fsb - start_fsb); + return xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, + offset + length); }

/*

From: yangerkun yangerkun@huawei.com

Offering: HULK hulk inclusion category: bugfix bugzilla: 189240, https://gitee.com/openeuler/kernel/issues/I76JSK

--------------------------------

Once we free exact one inode twice in xfs_difree_inobt, this lead to that ir_freecount does not match ir_free(ir_freecount will add twice, but ir_free will change only once), and the latter xfs_inobt_get_rec will bark for the mismatch of the ir_freecount and ir_free. Once we call xfs_inobt_get_rec when we process AGI unlinked lists, this will fail xfs mount.

We has not found the root cause why we free exact one inode twice, but we really should reject this for the purpose to not spread mistakes.

Signed-off-by: yangerkun yangerkun@huawei.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_ialloc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 0c2b7a6601a0..a1319f9c8ed8 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1989,7 +1989,11 @@ xfs_difree_inobt( */ off = agino - rec.ir_startino; ASSERT(off >= 0 && off < XFS_INODES_PER_CHUNK); - ASSERT(!(rec.ir_free & XFS_INOBT_MASK(off))); + + if (XFS_IS_CORRUPT(mp, rec.ir_free & XFS_INOBT_MASK(off))) { + error = -EFSCORRUPTED; + goto error0; + } /* * Mark the inode free & increment the count. */