summaryrefslogtreecommitdiff
path: root/include/linux/fs.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-09-29 09:42:30 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2025-09-29 09:42:30 -0700
commit56e7b310717697109998966cb3c4d3e490d09200 (patch)
tree24075d8293ba26a84877205799d62218db2d8477 /include/linux/fs.h
parent3a2a5b278fb8d4cdb3154b8e4a38352b945f96fd (diff)
parentc3c616c53dbabddf32a0485bd133d8d3b9f6656a (diff)
downloadlwn-56e7b310717697109998966cb3c4d3e490d09200.tar.gz
lwn-56e7b310717697109998966cb3c4d3e490d09200.zip
Merge tag 'vfs-6.18-rc1.inode' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs inode updates from Christian Brauner: "This contains a series I originally wrote and that Eric brought over the finish line. It moves out the i_crypt_info and i_verity_info pointers out of 'struct inode' and into the fs-specific part of the inode. So now the few filesytems that actually make use of this pay the price in their own private inode storage instead of forcing it upon every user of struct inode. The pointer for the crypt and verity info is simply found by storing an offset to its address in struct fsverity_operations and struct fscrypt_operations. This shrinks struct inode by 16 bytes. I hope to move a lot more out of it in the future so that struct inode becomes really just about very core stuff that we need, much like struct dentry and struct file, instead of the dumping ground it has become over the years. On top of this are a various changes associated with the ongoing inode lifetime handling rework that multiple people are pushing forward: - Stop accessing inode->i_count directly in f2fs and gfs2. They simply should use the __iget() and iput() helpers - Make the i_state flags an enum - Rework the iput() logic Currently, if we are the last iput, and we have the I_DIRTY_TIME bit set, we will grab a reference on the inode again and then mark it dirty and then redo the put. This is to make sure we delay the time update for as long as possible We can rework this logic to simply dec i_count if it is not 1, and if it is do the time update while still holding the i_count reference Then we can replace the atomic_dec_and_lock with locking the ->i_lock and doing atomic_dec_and_test, since we did the atomic_add_unless above - Add an icount_read() helper and convert everyone that accesses inode->i_count directly for this purpose to use the helper - Expand dump_inode() to dump more information about an inode helping in debugging - Add some might_sleep() annotations to iput() and associated helpers" * tag 'vfs-6.18-rc1.inode' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: fs: add might_sleep() annotation to iput() and more fs: expand dump_inode() inode: fix whitespace issues fs: add an icount_read helper fs: rework iput logic fs: make the i_state flags an enum fs: stop accessing ->i_count directly in f2fs and gfs2 fsverity: check IS_VERITY() in fsverity_cleanup_inode() fs: remove inode::i_verity_info btrfs: move verity info pointer to fs-specific part of inode f2fs: move verity info pointer to fs-specific part of inode ext4: move verity info pointer to fs-specific part of inode fsverity: add support for info in fs-specific part of inode fs: remove inode::i_crypt_info ceph: move crypt info pointer to fs-specific part of inode ubifs: move crypt info pointer to fs-specific part of inode f2fs: move crypt info pointer to fs-specific part of inode ext4: move crypt info pointer to fs-specific part of inode fscrypt: add support for info in fs-specific part of inode fscrypt: replace raw loads of info pointer with helper function
Diffstat (limited to 'include/linux/fs.h')
-rw-r--r--include/linux/fs.h246
1 files changed, 124 insertions, 122 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5265b76759f1..a854f2910cd9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -72,9 +72,7 @@ struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;
-struct fscrypt_inode_info;
struct fscrypt_operations;
-struct fsverity_info;
struct fsverity_operations;
struct fsnotify_mark_connector;
struct fsnotify_sb_info;
@@ -669,6 +667,124 @@ is_uncached_acl(struct posix_acl *acl)
#define IOP_CACHED_LINK 0x0040
/*
+ * Inode state bits. Protected by inode->i_lock
+ *
+ * Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
+ * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
+ *
+ * Four bits define the lifetime of an inode. Initially, inodes are I_NEW,
+ * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at
+ * various stages of removing an inode.
+ *
+ * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
+ *
+ * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
+ * fdatasync() (unless I_DIRTY_DATASYNC is also set).
+ * Timestamp updates are the usual cause.
+ * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of
+ * these changes separately from I_DIRTY_SYNC so that we
+ * don't have to write inode on fdatasync() when only
+ * e.g. the timestamps have changed.
+ * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
+ * I_DIRTY_TIME The inode itself has dirty timestamps, and the
+ * lazytime mount option is enabled. We keep track of this
+ * separately from I_DIRTY_SYNC in order to implement
+ * lazytime. This gets cleared if I_DIRTY_INODE
+ * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
+ * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
+ * in place because writeback might already be in progress
+ * and we don't want to lose the time update
+ * I_NEW Serves as both a mutex and completion notification.
+ * New inodes set I_NEW. If two processes both create
+ * the same inode, one of them will release its inode and
+ * wait for I_NEW to be released before returning.
+ * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
+ * also cause waiting on I_NEW, without I_NEW actually
+ * being set. find_inode() uses this to prevent returning
+ * nearly-dead inodes.
+ * I_WILL_FREE Must be set when calling write_inode_now() if i_count
+ * is zero. I_FREEING must be set when I_WILL_FREE is
+ * cleared.
+ * I_FREEING Set when inode is about to be freed but still has dirty
+ * pages or buffers attached or the inode itself is still
+ * dirty.
+ * I_CLEAR Added by clear_inode(). In this state the inode is
+ * clean and can be destroyed. Inode keeps I_FREEING.
+ *
+ * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
+ * prohibited for many purposes. iget() must wait for
+ * the inode to be completely released, then create it
+ * anew. Other functions will just ignore such inodes,
+ * if appropriate. I_NEW is used for waiting.
+ *
+ * I_SYNC Writeback of inode is running. The bit is set during
+ * data writeback, and cleared with a wakeup on the bit
+ * address once it is done. The bit is also used to pin
+ * the inode in memory for flusher thread.
+ *
+ * I_REFERENCED Marks the inode as recently references on the LRU list.
+ *
+ * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to
+ * synchronize competing switching instances and to tell
+ * wb stat updates to grab the i_pages lock. See
+ * inode_switch_wbs_work_fn() for details.
+ *
+ * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper
+ * and work dirs among overlayfs mounts.
+ *
+ * I_CREATING New object's inode in the middle of setting up.
+ *
+ * I_DONTCACHE Evict inode as soon as it is not used anymore.
+ *
+ * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists.
+ * Used to detect that mark_inode_dirty() should not move
+ * inode between dirty lists.
+ *
+ * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback.
+ *
+ * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding
+ * i_count.
+ *
+ * Q: What is the difference between I_WILL_FREE and I_FREEING?
+ *
+ * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait
+ * upon. There's one free address left.
+ */
+
+enum inode_state_bits {
+ __I_NEW = 0U,
+ __I_SYNC = 1U,
+ __I_LRU_ISOLATING = 2U
+ /* reserved wait address bit 3 */
+};
+
+enum inode_state_flags_t {
+ I_NEW = (1U << __I_NEW),
+ I_SYNC = (1U << __I_SYNC),
+ I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING),
+ /* reserved flag bit 3 */
+ I_DIRTY_SYNC = (1U << 4),
+ I_DIRTY_DATASYNC = (1U << 5),
+ I_DIRTY_PAGES = (1U << 6),
+ I_WILL_FREE = (1U << 7),
+ I_FREEING = (1U << 8),
+ I_CLEAR = (1U << 9),
+ I_REFERENCED = (1U << 10),
+ I_LINKABLE = (1U << 11),
+ I_DIRTY_TIME = (1U << 12),
+ I_WB_SWITCH = (1U << 13),
+ I_OVL_INUSE = (1U << 14),
+ I_CREATING = (1U << 15),
+ I_DONTCACHE = (1U << 16),
+ I_SYNC_QUEUED = (1U << 17),
+ I_PINNING_NETFS_WB = (1U << 18)
+};
+
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
+#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
+#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
+
+/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
* of the 'struct inode'
@@ -726,7 +842,7 @@ struct inode {
#endif
/* Misc */
- u32 i_state;
+ enum inode_state_flags_t i_state;
/* 32-bit hole */
struct rw_semaphore i_rwsem;
@@ -782,14 +898,6 @@ struct inode {
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
-#ifdef CONFIG_FS_ENCRYPTION
- struct fscrypt_inode_info *i_crypt_info;
-#endif
-
-#ifdef CONFIG_FS_VERITY
- struct fsverity_info *i_verity_info;
-#endif
-
void *i_private; /* fs or device private pointer */
} __randomize_layout;
@@ -2492,117 +2600,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
};
}
-/*
- * Inode state bits. Protected by inode->i_lock
- *
- * Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
- * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
- *
- * Four bits define the lifetime of an inode. Initially, inodes are I_NEW,
- * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at
- * various stages of removing an inode.
- *
- * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
- *
- * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
- * fdatasync() (unless I_DIRTY_DATASYNC is also set).
- * Timestamp updates are the usual cause.
- * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of
- * these changes separately from I_DIRTY_SYNC so that we
- * don't have to write inode on fdatasync() when only
- * e.g. the timestamps have changed.
- * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
- * I_DIRTY_TIME The inode itself has dirty timestamps, and the
- * lazytime mount option is enabled. We keep track of this
- * separately from I_DIRTY_SYNC in order to implement
- * lazytime. This gets cleared if I_DIRTY_INODE
- * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
- * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
- * in place because writeback might already be in progress
- * and we don't want to lose the time update
- * I_NEW Serves as both a mutex and completion notification.
- * New inodes set I_NEW. If two processes both create
- * the same inode, one of them will release its inode and
- * wait for I_NEW to be released before returning.
- * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
- * also cause waiting on I_NEW, without I_NEW actually
- * being set. find_inode() uses this to prevent returning
- * nearly-dead inodes.
- * I_WILL_FREE Must be set when calling write_inode_now() if i_count
- * is zero. I_FREEING must be set when I_WILL_FREE is
- * cleared.
- * I_FREEING Set when inode is about to be freed but still has dirty
- * pages or buffers attached or the inode itself is still
- * dirty.
- * I_CLEAR Added by clear_inode(). In this state the inode is
- * clean and can be destroyed. Inode keeps I_FREEING.
- *
- * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
- * prohibited for many purposes. iget() must wait for
- * the inode to be completely released, then create it
- * anew. Other functions will just ignore such inodes,
- * if appropriate. I_NEW is used for waiting.
- *
- * I_SYNC Writeback of inode is running. The bit is set during
- * data writeback, and cleared with a wakeup on the bit
- * address once it is done. The bit is also used to pin
- * the inode in memory for flusher thread.
- *
- * I_REFERENCED Marks the inode as recently references on the LRU list.
- *
- * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to
- * synchronize competing switching instances and to tell
- * wb stat updates to grab the i_pages lock. See
- * inode_switch_wbs_work_fn() for details.
- *
- * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper
- * and work dirs among overlayfs mounts.
- *
- * I_CREATING New object's inode in the middle of setting up.
- *
- * I_DONTCACHE Evict inode as soon as it is not used anymore.
- *
- * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists.
- * Used to detect that mark_inode_dirty() should not move
- * inode between dirty lists.
- *
- * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback.
- *
- * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding
- * i_count.
- *
- * Q: What is the difference between I_WILL_FREE and I_FREEING?
- *
- * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait
- * upon. There's one free address left.
- */
-#define __I_NEW 0
-#define I_NEW (1 << __I_NEW)
-#define __I_SYNC 1
-#define I_SYNC (1 << __I_SYNC)
-#define __I_LRU_ISOLATING 2
-#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING)
-
-#define I_DIRTY_SYNC (1 << 3)
-#define I_DIRTY_DATASYNC (1 << 4)
-#define I_DIRTY_PAGES (1 << 5)
-#define I_WILL_FREE (1 << 6)
-#define I_FREEING (1 << 7)
-#define I_CLEAR (1 << 8)
-#define I_REFERENCED (1 << 9)
-#define I_LINKABLE (1 << 10)
-#define I_DIRTY_TIME (1 << 11)
-#define I_WB_SWITCH (1 << 12)
-#define I_OVL_INUSE (1 << 13)
-#define I_CREATING (1 << 14)
-#define I_DONTCACHE (1 << 15)
-#define I_SYNC_QUEUED (1 << 16)
-#define I_PINNING_NETFS_WB (1 << 17)
-
-#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
-#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
-#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
-
extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
{
@@ -2614,6 +2611,11 @@ static inline void mark_inode_dirty_sync(struct inode *inode)
__mark_inode_dirty(inode, I_DIRTY_SYNC);
}
+static inline int icount_read(const struct inode *inode)
+{
+ return atomic_read(&inode->i_count);
+}
+
/*
* Returns true if the given inode itself only has dirty timestamps (its pages
* may still be dirty) and isn't currently being allocated or freed.