Add SB_I_NO_DATA_INTEGRITY superblock flag for filesystems that cannot guarantee data persistence on sync (eg fuse) and skip sync(2) inode writeback for superblocks with this flag set. There was a recent report [1] for a suspend-to-RAM hang on fuse-overlayfs with firefox + youtube in wb_wait_for_completion() from the pm_fs_sync_work_fn() path: Workqueue: pm_fs_sync pm_fs_sync_work_fn Call Trace: __schedule+0x457/0x1720 schedule+0x27/0xd0 wb_wait_for_completion+0x97/0xe0 sync_inodes_sb+0xf8/0x2e0 __iterate_supers+0xdc/0x160 ksys_sync+0x43/0xb0 pm_fs_sync_work_fn+0x17/0xa0 process_one_work+0x193/0x350 worker_thread+0x1a1/0x310 kthread+0xfc/0x240 ret_from_fork+0x243/0x280 ret_from_fork_asm+0x1a/0x30 This can happen in two ways: a) systemd freezes the user session cgroups first (which freezes the fuse daemon) before invoking the kernel suspend. The suspend triggers the wb_workfn() -> write_inode() path, where fuse issues a synchronous setattr request to the frozen daemon, which cannot process the request b) if a dirty folio is already under writeback and needs to have writeback issued again, in writeback_get_folio() -> folio_prepare_writeback(), we unconditionally wait on writeback to finish, but for buggy/faulty fuse servers, the request may never be processed The correct fix is for sync(2) to skip the sync_inodes_sb() path entirely for any filesystems that do not have data integrity guarantees. A prior commit (commit f9a49aa302a0 ("fs/writeback: skip AS_NO_DATA_INTEGRITY mappings in wait_sb_inodes()")) added the AS_NO_DATA_INTEGRITY mapping flag to skip sync(2) waits for mappings without data integrity semantics, but it still allowed wb_workfn() worker threads to be kicked off for the writeback. This patch improves upon that by replacing the per-inode AS_NO_DATA_INTEGRITY mapping flag with a flag at the superblock level, and using that superblock flag to skip the sync_inodes_sb() path entirely if there are no data integrity guarantees. The flag belongs at the superblock level because data integrity is a filesystem-wide property, not a per-inode one. Having the flag at the superblock level allows sync_inodes_one_sb() to skip the entire filesystem efficiently, rather than iterating every dirty inode only to skip each one individually. This patch restores fuse to its prior behavior before tmp folios were removed, where sync was essentially a no-op. [1] https://lore.kernel.org/linux-fsdevel/CAJnrk1a-asuvfrbKXbEwwDSctvemF+6zfhdnuzO65Pt8HsFSRw@mail.gmail.com/T/#m632c4648e9cafc4239299887109ebd880ac6c5c1 Fixes: 0c58a97f919c ("fuse: remove tmp folio for writebacks and internal rb tree") Reported-by: John Tested-by: John Cc: Signed-off-by: Joanne Koong --- fs/fs-writeback.c | 7 +------ fs/fuse/file.c | 4 +--- fs/fuse/inode.c | 1 + fs/sync.c | 2 +- include/linux/fs/super_types.h | 1 + include/linux/pagemap.h | 11 ----------- 6 files changed, 5 insertions(+), 21 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 7c75ed7e8979..154249e4e5ce 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2775,13 +2775,8 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. - * - * If the mapping does not have data integrity semantics, - * there's no need to wait for the writeout to complete, as the - * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || - mapping_no_data_integrity(mapping)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a9c836d7f586..f6240f24b814 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3202,10 +3202,8 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) { + if (fc->writeback_cache) mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); - mapping_set_no_data_integrity(&inode->i_data); - } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e57b8af06be9..c795abe47a4f 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1709,6 +1709,7 @@ static void fuse_sb_defaults(struct super_block *sb) sb->s_export_op = &fuse_export_operations; sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE; sb->s_iflags |= SB_I_NOIDMAP; + sb->s_iflags |= SB_I_NO_DATA_INTEGRITY; if (sb->s_user_ns != &init_user_ns) sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER; sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); diff --git a/fs/sync.c b/fs/sync.c index 942a60cfedfb..88c08e2f76b2 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { - if (!sb_rdonly(sb)) + if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_NO_DATA_INTEGRITY)) sync_inodes_sb(sb); } diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h index fa7638b81246..383050e7fdf5 100644 --- a/include/linux/fs/super_types.h +++ b/include/linux/fs/super_types.h @@ -338,5 +338,6 @@ struct super_block { #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ +#define SB_I_NO_DATA_INTEGRITY 0x00008000 /* fs cannot guarantee data persistence on sync */ #endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ec442af3f886..31a848485ad9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,7 +210,6 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ - AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -346,16 +345,6 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline void mapping_set_no_data_integrity(struct address_space *mapping) -{ - set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - -static inline bool mapping_no_data_integrity(const struct address_space *mapping) -{ - return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; -- 2.52.0