From a1de97fe296c52eafc6590a3506f4bbd44ecb19a Mon Sep 17 00:00:00 2001 From: Yang Xu Date: Wed, 24 Nov 2021 10:06:02 -0800 Subject: [PATCH 1/2] xfs: Fix the free logic of state in xfs_attr_node_hasname When testing xfstests xfs/126 on lastest upstream kernel, it will hang on some machine. Adding a getxattr operation after xattr corrupted, I can reproduce it 100%. The deadlock as below: [983.923403] task:setfattr state:D stack: 0 pid:17639 ppid: 14687 flags:0x00000080 [ 983.923405] Call Trace: [ 983.923410] __schedule+0x2c4/0x700 [ 983.923412] schedule+0x37/0xa0 [ 983.923414] schedule_timeout+0x274/0x300 [ 983.923416] __down+0x9b/0xf0 [ 983.923451] ? xfs_buf_find.isra.29+0x3c8/0x5f0 [xfs] [ 983.923453] down+0x3b/0x50 [ 983.923471] xfs_buf_lock+0x33/0xf0 [xfs] [ 983.923490] xfs_buf_find.isra.29+0x3c8/0x5f0 [xfs] [ 983.923508] xfs_buf_get_map+0x4c/0x320 [xfs] [ 983.923525] xfs_buf_read_map+0x53/0x310 [xfs] [ 983.923541] ? xfs_da_read_buf+0xcf/0x120 [xfs] [ 983.923560] xfs_trans_read_buf_map+0x1cf/0x360 [xfs] [ 983.923575] ? xfs_da_read_buf+0xcf/0x120 [xfs] [ 983.923590] xfs_da_read_buf+0xcf/0x120 [xfs] [ 983.923606] xfs_da3_node_read+0x1f/0x40 [xfs] [ 983.923621] xfs_da3_node_lookup_int+0x69/0x4a0 [xfs] [ 983.923624] ? kmem_cache_alloc+0x12e/0x270 [ 983.923637] xfs_attr_node_hasname+0x6e/0xa0 [xfs] [ 983.923651] xfs_has_attr+0x6e/0xd0 [xfs] [ 983.923664] xfs_attr_set+0x273/0x320 [xfs] [ 983.923683] xfs_xattr_set+0x87/0xd0 [xfs] [ 983.923686] __vfs_removexattr+0x4d/0x60 [ 983.923688] __vfs_removexattr_locked+0xac/0x130 [ 983.923689] vfs_removexattr+0x4e/0xf0 [ 983.923690] removexattr+0x4d/0x80 [ 983.923693] ? __check_object_size+0xa8/0x16b [ 983.923695] ? strncpy_from_user+0x47/0x1a0 [ 983.923696] ? getname_flags+0x6a/0x1e0 [ 983.923697] ? _cond_resched+0x15/0x30 [ 983.923699] ? __sb_start_write+0x1e/0x70 [ 983.923700] ? mnt_want_write+0x28/0x50 [ 983.923701] path_removexattr+0x9b/0xb0 [ 983.923702] __x64_sys_removexattr+0x17/0x20 [ 983.923704] do_syscall_64+0x5b/0x1a0 [ 983.923705] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 983.923707] RIP: 0033:0x7f080f10ee1b When getxattr calls xfs_attr_node_get function, xfs_da3_node_lookup_int fails with EFSCORRUPTED in xfs_attr_node_hasname because we have use blocktrash to random it in xfs/126. So it free state in internal and xfs_attr_node_get doesn't do xfs_buf_trans release job. Then subsequent removexattr will hang because of it. This bug was introduced by kernel commit 07120f1abdff ("xfs: Add xfs_has_attr and subroutines"). It adds xfs_attr_node_hasname helper and said caller will be responsible for freeing the state in this case. But xfs_attr_node_hasname will free state itself instead of caller if xfs_da3_node_lookup_int fails. Fix this bug by moving the step of free state into caller. Also, use "goto error/out" instead of returning error directly in xfs_attr_node_addname_find_attr and xfs_attr_node_removename_setup function because we should free state ourselves. Fixes: 07120f1abdff ("xfs: Add xfs_has_attr and subroutines") Signed-off-by: Yang Xu Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_attr.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index fbc9d816882c..23523b802539 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1077,21 +1077,18 @@ xfs_attr_node_hasname( state = xfs_da_state_alloc(args); if (statep != NULL) - *statep = NULL; + *statep = state; /* * Search to see if name exists, and get back a pointer to it. */ error = xfs_da3_node_lookup_int(state, &retval); - if (error) { - xfs_da_state_free(state); - return error; - } + if (error) + retval = error; - if (statep != NULL) - *statep = state; - else + if (!statep) xfs_da_state_free(state); + return retval; } @@ -1112,7 +1109,7 @@ xfs_attr_node_addname_find_attr( */ retval = xfs_attr_node_hasname(args, &dac->da_state); if (retval != -ENOATTR && retval != -EEXIST) - return retval; + goto error; if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE)) goto error; @@ -1337,7 +1334,7 @@ int xfs_attr_node_removename_setup( error = xfs_attr_node_hasname(args, state); if (error != -EEXIST) - return error; + goto out; error = 0; ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL); From 1090427bf18f9835b3ccbd36edf43f2509444e27 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Nov 2021 10:06:02 -0800 Subject: [PATCH 2/2] xfs: remove xfs_inew_wait With the remove of xfs_dqrele_all_inodes, xfs_inew_wait and all the infrastructure used to wake the XFS_INEW bit waitqueue is unused. Reported-by: kernel test robot Fixes: 777eb1fa857e ("xfs: remove xfs_dqrele_all_inodes") Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_icache.c | 21 --------------------- fs/xfs/xfs_inode.h | 4 +--- 2 files changed, 1 insertion(+), 24 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e1472004170e..da4af2142a2b 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -289,22 +289,6 @@ xfs_perag_clear_inode_tag( trace_xfs_perag_clear_inode_tag(mp, pag->pag_agno, tag, _RET_IP_); } -static inline void -xfs_inew_wait( - struct xfs_inode *ip) -{ - wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT); - DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT); - - do { - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - if (!xfs_iflags_test(ip, XFS_INEW)) - break; - schedule(); - } while (true); - finish_wait(wq, &wait.wq_entry); -} - /* * When we recycle a reclaimable inode, we need to re-initialise the VFS inode * part of the structure. This is made more complex by the fact we store @@ -368,18 +352,13 @@ xfs_iget_recycle( ASSERT(!rwsem_is_locked(&inode->i_rwsem)); error = xfs_reinit_inode(mp, inode); if (error) { - bool wake; - /* * Re-initializing the inode failed, and we are in deep * trouble. Try to re-add it to the reclaim list. */ rcu_read_lock(); spin_lock(&ip->i_flags_lock); - wake = !!__xfs_iflags_test(ip, XFS_INEW); ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); - if (wake) - wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); ASSERT(ip->i_flags & XFS_IRECLAIMABLE); spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index e635a3d64cba..c447bf04205a 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -231,8 +231,7 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip) #define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ #define XFS_ISTALE (1 << 1) /* inode has been staled */ #define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ -#define __XFS_INEW_BIT 3 /* inode has just been allocated */ -#define XFS_INEW (1 << __XFS_INEW_BIT) +#define XFS_INEW (1 << 3) /* inode has just been allocated */ #define XFS_IPRESERVE_DM_FIELDS (1 << 4) /* has legacy DMAPI fields set */ #define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ #define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ @@ -492,7 +491,6 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip) xfs_iflags_clear(ip, XFS_INEW); barrier(); unlock_new_inode(VFS_I(ip)); - wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); } static inline void xfs_setup_existing_inode(struct xfs_inode *ip)