From: "Darrick J. Wong" djwong@kernel.org
mainline-inclusion from mainline-v5.13-rc4 commit ff7bebeb91f8cc2e26e7dabbf301da5ec0e9328c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4KIAO CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
-------------------------------------------------
Hoist the code in xfs_iget_cache_hit that restores the VFS inode state to an xfs_inode that was previously vfs-destroyed. The next patch will add a new set of state flags, so we need the helper to avoid duplication.
Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Dave Chinner dchinner@redhat.com Signed-off-by: Lihong Kou koulihong@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- fs/xfs/xfs_icache.c | 143 +++++++++++++++++++++++++------------------- fs/xfs/xfs_trace.h | 4 +- 2 files changed, 83 insertions(+), 64 deletions(-)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 84f408fabb95..5fcda72f5367 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -354,14 +354,14 @@ xfs_reinit_inode( struct xfs_mount *mp, struct inode *inode) { - int error; - uint32_t nlink = inode->i_nlink; - uint32_t generation = inode->i_generation; - uint64_t version = inode_peek_iversion(inode); - umode_t mode = inode->i_mode; - dev_t dev = inode->i_rdev; - kuid_t uid = inode->i_uid; - kgid_t gid = inode->i_gid; + int error; + uint32_t nlink = inode->i_nlink; + uint32_t generation = inode->i_generation; + uint64_t version = inode_peek_iversion(inode); + umode_t mode = inode->i_mode; + dev_t dev = inode->i_rdev; + kuid_t uid = inode->i_uid; + kgid_t gid = inode->i_gid;
error = inode_init_always(mp->m_super, inode);
@@ -375,6 +375,74 @@ xfs_reinit_inode( return error; }
+/* + * Carefully nudge an inode whose VFS state has been torn down back into a + * usable state. Drops the i_flags_lock and the rcu read lock. + */ +static int +xfs_iget_recycle( + struct xfs_perag *pag, + struct xfs_inode *ip) __releases(&ip->i_flags_lock) +{ + struct xfs_mount *mp = ip->i_mount; + struct inode *inode = VFS_I(ip); + int error; + + trace_xfs_iget_recycle(ip); + + /* + * We need to make it look like the inode is being reclaimed to prevent + * the actual reclaim workers from stomping over us while we recycle + * the inode. We can't clear the radix tree tag yet as it requires + * pag_ici_lock to be held exclusive. + */ + ip->i_flags |= XFS_IRECLAIM; + + spin_unlock(&ip->i_flags_lock); + rcu_read_unlock(); + + 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(); + + trace_xfs_iget_recycle_fail(ip); + return error; + } + + spin_lock(&pag->pag_ici_lock); + spin_lock(&ip->i_flags_lock); + + /* + * Clear the per-lifetime state in the inode as we are now effectively + * a new inode and need to return to the initial state before reuse + * occurs. + */ + ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS; + ip->i_flags |= XFS_INEW; + xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), + XFS_ICI_RECLAIM_TAG); + inode->i_state = I_NEW; + spin_unlock(&ip->i_flags_lock); + spin_unlock(&pag->pag_ici_lock); + + return 0; +} + /* * If we are allocating a new inode, then check what was returned is * actually a free, empty inode. If we are not allocating an inode, @@ -449,7 +517,7 @@ xfs_iget_cache_hit( /* * If we are racing with another cache hit that is currently * instantiating this inode or currently recycling it out of - * reclaimabe state, wait for the initialisation to complete + * reclaimable state, wait for the initialisation to complete * before continuing. * * XXX(hch): eventually we should do something equivalent to @@ -471,64 +539,16 @@ xfs_iget_cache_hit( if (error) goto out_error;
- /* - * If IRECLAIMABLE is set, we've torn down the VFS inode already. - * Need to carefully get it back into useable state. - */ if (ip->i_flags & XFS_IRECLAIMABLE) { - trace_xfs_iget_reclaim(ip); - if (flags & XFS_IGET_INCORE) { error = -EAGAIN; goto out_error; }
- /* - * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode - * from stomping over us while we recycle the inode. We can't - * clear the radix tree reclaimable tag yet as it requires - * pag_ici_lock to be held exclusive. - */ - ip->i_flags |= XFS_IRECLAIM; - - spin_unlock(&ip->i_flags_lock); - rcu_read_unlock(); - - 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); - trace_xfs_iget_reclaim_fail(ip); - goto out_error; - } - - spin_lock(&pag->pag_ici_lock); - spin_lock(&ip->i_flags_lock); - - /* - * Clear the per-lifetime state in the inode as we are now - * effectively a new inode and need to return to the initial - * state before reuse occurs. - */ - ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS; - ip->i_flags |= XFS_INEW; - xfs_perag_clear_inode_tag(pag, - XFS_INO_TO_AGINO(pag->pag_mount, ino), - XFS_ICI_RECLAIM_TAG); - inode->i_state = I_NEW; - spin_unlock(&ip->i_flags_lock); - spin_unlock(&pag->pag_ici_lock); + /* Drops i_flags_lock and RCU read lock. */ + error = xfs_iget_recycle(pag, ip); + if (error) + return error; } else { /* If the VFS inode is being torn down, pause and try again. */ if (!igrab(inode)) { @@ -558,7 +578,6 @@ xfs_iget_cache_hit( return error; }
- static int xfs_iget_cache_miss( struct xfs_mount *mp, diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index d025b7df7158..8fa6d8bb4312 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -613,8 +613,8 @@ DEFINE_EVENT(xfs_inode_class, name, \ TP_PROTO(struct xfs_inode *ip), \ TP_ARGS(ip)) DEFINE_INODE_EVENT(xfs_iget_skip); -DEFINE_INODE_EVENT(xfs_iget_reclaim); -DEFINE_INODE_EVENT(xfs_iget_reclaim_fail); +DEFINE_INODE_EVENT(xfs_iget_recycle); +DEFINE_INODE_EVENT(xfs_iget_recycle_fail); DEFINE_INODE_EVENT(xfs_iget_hit); DEFINE_INODE_EVENT(xfs_iget_miss);