summaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
authorChristian Brauner <brauner@kernel.org>2025-10-10 14:27:15 +0300
committerChristian Brauner <brauner@kernel.org>2025-10-20 21:22:28 +0300
commit11f2af2a80b5f9dcfc829c64e0ad176e011ddf60 (patch)
tree25b85b1460f196b0d6c1f2ccffb860edf4863a65 /include/linux
parent31e332b911fca54df467d264d7e2a2ef9317f3ca (diff)
parent2ed81b4bef9b74ae0f095ad4667dbe2ae0b86a91 (diff)
downloadlinux-11f2af2a80b5f9dcfc829c64e0ad176e011ddf60.tar.xz
Merge patch series "hide ->i_state behind accessors"
Mateusz Guzik <mjguzik@gmail.com> says: Open-coded accesses prevent asserting they are done correctly. One obvious aspect is locking, but significantly more can checked. For example it can be detected when the code is clearing flags which are already missing, or is setting flags when it is illegal (e.g., I_FREEING when ->i_count > 0). In order to keep things manageable this patchset merely gets the thing off the ground with only lockdep checks baked in. Current consumers can be trivially converted. Suppose flags I_A and I_B are to be handled. If ->i_lock is held, then: state = inode->i_state => state = inode_state_read(inode) inode->i_state |= (I_A | I_B) => inode_state_set(inode, I_A | I_B) inode->i_state &= ~(I_A | I_B) => inode_state_clear(inode, I_A | I_B) inode->i_state = I_A | I_B => inode_state_assign(inode, I_A | I_B) If ->i_lock is not held or only held conditionally: state = inode->i_state => state = inode_state_read_once(inode) inode->i_state |= (I_A | I_B) => inode_state_set_raw(inode, I_A | I_B) inode->i_state &= ~(I_A | I_B) => inode_state_clear_raw(inode, I_A | I_B) inode->i_state = I_A | I_B => inode_state_assign_raw(inode, I_A | I_B) The "_once" vs "_raw" discrepancy stems from the read variant differing by READ_ONCE as opposed to just lockdep checks. Finally, if you want to atomically clear flags and set new ones, the following: state = inode->i_state; state &= ~I_A; state |= I_B; inode->i_state = state; turns into: inode_state_replace(inode, I_A, I_B); * patches from https://lore.kernel.org/20251009075929.1203950-1-mjguzik@gmail.com: fs: make plain ->i_state access fail to compile xfs: use the new ->i_state accessors nilfs2: use the new ->i_state accessors overlayfs: use the new ->i_state accessors gfs2: use the new ->i_state accessors f2fs: use the new ->i_state accessors smb: use the new ->i_state accessors ceph: use the new ->i_state accessors btrfs: use the new ->i_state accessors Manual conversion to use ->i_state accessors of all places not covered by coccinelle Coccinelle-based conversion to use ->i_state accessors fs: provide accessors for ->i_state fs: spell out fenced ->i_state accesses with explicit smp_wmb/smp_rmb fs: move wait_on_inode() from writeback.h to fs.h Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/backing-dev.h5
-rw-r--r--include/linux/fs.h99
-rw-r--r--include/linux/writeback.h13
3 files changed, 99 insertions, 18 deletions
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 3e64f14739dd..0c8342747cab 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -277,10 +277,11 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
rcu_read_lock();
/*
- * Paired with store_release in inode_switch_wbs_work_fn() and
+ * Paired with a release fence in inode_do_switch_wbs() and
* ensures that we see the new wb if we see cleared I_WB_SWITCH.
*/
- cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+ cookie->locked = inode_state_read_once(inode) & I_WB_SWITCH;
+ smp_rmb();
if (unlikely(cookie->locked))
xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ac62b9d10b00..21c73df3ce75 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -759,7 +759,7 @@ enum inode_state_bits {
/* reserved wait address bit 3 */
};
-enum inode_state_flags_t {
+enum inode_state_flags_enum {
I_NEW = (1U << __I_NEW),
I_SYNC = (1U << __I_SYNC),
I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING),
@@ -786,6 +786,13 @@ enum inode_state_flags_t {
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
/*
+ * Use inode_state_read() & friends to access.
+ */
+struct inode_state_flags {
+ enum inode_state_flags_enum __state;
+};
+
+/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
* of the 'struct inode'
@@ -843,7 +850,7 @@ struct inode {
#endif
/* Misc */
- enum inode_state_flags_t i_state;
+ struct inode_state_flags i_state;
/* 32-bit hole */
struct rw_semaphore i_rwsem;
@@ -902,6 +909,80 @@ struct inode {
void *i_private; /* fs or device private pointer */
} __randomize_layout;
+/*
+ * i_state handling
+ *
+ * We hide all of it behind helpers so that we can validate consumers.
+ */
+static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode)
+{
+ return READ_ONCE(inode->i_state.__state);
+}
+
+static inline enum inode_state_flags_enum inode_state_read(struct inode *inode)
+{
+ lockdep_assert_held(&inode->i_lock);
+ return inode->i_state.__state;
+}
+
+static inline void inode_state_set_raw(struct inode *inode,
+ enum inode_state_flags_enum flags)
+{
+ WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags);
+}
+
+static inline void inode_state_set(struct inode *inode,
+ enum inode_state_flags_enum flags)
+{
+ lockdep_assert_held(&inode->i_lock);
+ inode_state_set_raw(inode, flags);
+}
+
+static inline void inode_state_clear_raw(struct inode *inode,
+ enum inode_state_flags_enum flags)
+{
+ WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags);
+}
+
+static inline void inode_state_clear(struct inode *inode,
+ enum inode_state_flags_enum flags)
+{
+ lockdep_assert_held(&inode->i_lock);
+ inode_state_clear_raw(inode, flags);
+}
+
+static inline void inode_state_assign_raw(struct inode *inode,
+ enum inode_state_flags_enum flags)
+{
+ WRITE_ONCE(inode->i_state.__state, flags);
+}
+
+static inline void inode_state_assign(struct inode *inode,
+ enum inode_state_flags_enum flags)
+{
+ lockdep_assert_held(&inode->i_lock);
+ inode_state_assign_raw(inode, flags);
+}
+
+static inline void inode_state_replace_raw(struct inode *inode,
+ enum inode_state_flags_enum clearflags,
+ enum inode_state_flags_enum setflags)
+{
+ enum inode_state_flags_enum flags;
+ flags = inode->i_state.__state;
+ flags &= ~clearflags;
+ flags |= setflags;
+ inode_state_assign_raw(inode, flags);
+}
+
+static inline void inode_state_replace(struct inode *inode,
+ enum inode_state_flags_enum clearflags,
+ enum inode_state_flags_enum setflags)
+{
+ lockdep_assert_held(&inode->i_lock);
+ inode_state_replace_raw(inode, clearflags, setflags);
+}
+
static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
{
VFS_WARN_ON_INODE(strlen(link) != linklen, inode);
@@ -949,6 +1030,16 @@ static inline void inode_fake_hash(struct inode *inode)
hlist_add_fake(&inode->i_hash);
}
+static inline void wait_on_inode(struct inode *inode)
+{
+ wait_var_event(inode_state_wait_address(inode, __I_NEW),
+ !(inode_state_read_once(inode) & I_NEW));
+ /*
+ * Pairs with routines clearing I_NEW.
+ */
+ smp_rmb();
+}
+
/*
* inode->i_rwsem nesting subclasses for the lock validator:
*
@@ -2635,8 +2726,8 @@ static inline int icount_read(const struct inode *inode)
*/
static inline bool inode_is_dirtytime_only(struct inode *inode)
{
- return (inode->i_state & (I_DIRTY_TIME | I_NEW |
- I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
+ return (inode_state_read_once(inode) &
+ (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
}
extern void inc_nlink(struct inode *inode);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index e1e1231a6830..102071ffedcb 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -189,17 +189,6 @@ void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
void inode_wait_for_writeback(struct inode *inode);
void inode_io_list_del(struct inode *inode);
-/* writeback.h requires fs.h; it, too, is not included from here. */
-static inline void wait_on_inode(struct inode *inode)
-{
- wait_var_event(inode_state_wait_address(inode, __I_NEW),
- !(READ_ONCE(inode->i_state) & I_NEW));
- /*
- * Pairs with routines clearing I_NEW.
- */
- smp_rmb();
-}
-
#ifdef CONFIG_CGROUP_WRITEBACK
#include <linux/cgroup.h>
@@ -238,7 +227,7 @@ static inline void inode_attach_wb(struct inode *inode, struct folio *folio)
static inline void inode_detach_wb(struct inode *inode)
{
if (inode->i_wb) {
- WARN_ON_ONCE(!(inode->i_state & I_CLEAR));
+ WARN_ON_ONCE(!(inode_state_read_once(inode) & I_CLEAR));
wb_put(inode->i_wb);
inode->i_wb = NULL;
}