summaryrefslogtreecommitdiff
path: root/fs/locks.c
diff options
context:
space:
mode:
authorMateusz Guzik <mjguzik@gmail.com>2025-12-03 10:48:37 +0100
committerChristian Brauner <brauner@kernel.org>2025-12-15 14:33:38 +0100
commit887e97745ec336c2f49b6c0af3c4cc00a5df3211 (patch)
tree98ee23214c9bcfea4556a378b089a9b2bc71784a /fs/locks.c
parent1fa4e69a54a250fa17d2afd9c5b54a59329033c1 (diff)
fs: track the inode having file locks with a flag in ->i_opflags
Opening and closing an inode dirties the ->i_readcount field. Depending on the alignment of the inode, it may happen to false-share with other fields loaded both for both operations to various extent. This notably concerns the ->i_flctx field. Since most inodes don't have the field populated, this bit can be managed with a flag in ->i_opflags instead which bypasses the problem. Here are results I obtained while opening a file read-only in a loop with 24 cores doing the work on Sapphire Rapids. Utilizing the flag as opposed to reading ->i_flctx field was toggled at runtime as the benchmark was running, to make sure both results come from the same alignment. before: 3233740 after: 3373346 (+4%) before: 3284313 after: 3518711 (+7%) before: 3505545 after: 4092806 (+16%) Or to put it differently, this varies wildly depending on how (un)lucky you get. The primary bottleneck before and after is the avoidable lockref trip in do_dentry_open(). Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Mateusz Guzik <mjguzik@gmail.com> Link: https://patch.msgid.link/20251203094837.290654-2-mjguzik@gmail.com Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'fs/locks.c')
-rw-r--r--fs/locks.c14
1 files changed, 12 insertions, 2 deletions
diff --git a/fs/locks.c b/fs/locks.c
index 9f565802a88c..7a63fa3ca9b4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -178,7 +178,6 @@ locks_get_lock_context(struct inode *inode, int type)
{
struct file_lock_context *ctx;
- /* paired with cmpxchg() below */
ctx = locks_inode_context(inode);
if (likely(ctx) || type == F_UNLCK)
goto out;
@@ -196,7 +195,18 @@ locks_get_lock_context(struct inode *inode, int type)
* Assign the pointer if it's not already assigned. If it is, then
* free the context we just allocated.
*/
- if (cmpxchg(&inode->i_flctx, NULL, ctx)) {
+ spin_lock(&inode->i_lock);
+ if (!(inode->i_opflags & IOP_FLCTX)) {
+ VFS_BUG_ON_INODE(inode->i_flctx, inode);
+ WRITE_ONCE(inode->i_flctx, ctx);
+ /*
+ * Paired with locks_inode_context().
+ */
+ smp_store_release(&inode->i_opflags, inode->i_opflags | IOP_FLCTX);
+ spin_unlock(&inode->i_lock);
+ } else {
+ VFS_BUG_ON_INODE(!inode->i_flctx, inode);
+ spin_unlock(&inode->i_lock);
kmem_cache_free(flctx_cache, ctx);
ctx = locks_inode_context(inode);
}