diff options
author | Christian Brauner <brauner@kernel.org> | 2025-03-05 18:26:07 +0100 |
---|---|---|
committer | Christian Brauner <brauner@kernel.org> | 2025-03-05 18:31:24 +0100 |
commit | dba2e3b788f5ac70ebf717523433e1ceae3f0834 (patch) | |
tree | d1a0540a062e74fb8b3f8907e7b1494368328206 /fs/file.c | |
parent | 23e490336467fcdaf95e1efcf8f58067b59f647b (diff) | |
parent | 606623de503f4eaa4ca505650bbd2da1f5fb5e6a (diff) |
Merge patch series "avoid the extra atomic on a ref when closing a fd"
Mateusz Guzik <mjguzik@gmail.com> says:
The stock kernel transitioning the file to no refs held penalizes the
caller with an extra atomic to block any increments.
For cases where the file is highly likely to be going away this is
easily avoidable.
In the open+close case the win is very modest because of the following
problems:
- kmem and memcg having terrible performance
- putname using an atomic (I have a wip to whack that)
- open performing an extra ref/unref on the dentry (there are patches to
do it, including by Al. I mailed about them in [1])
- creds using atomics (I have a wip to whack that)
- apparmor using atomics (ditto, same mechanism)
On top of that I have a WIP patch to dodge some of the work at lookup
itself.
All in all there is several % avoidably lost here.
stats colected during a kernel build with:
bpftrace -e 'kprobe:filp_close,kprobe:fput,kprobe:fput_close* { @[probe] = hist(((struct file *)arg0)->f_ref.refcnt.counter > 0); }'
@[kprobe:filp_close]:
[0] 32195 |@@@@@@@@@@ |
[1] 164567 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
@[kprobe:fput]:
[0] 339240 |@@@@@@ |
[1] 2888064 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
@[kprobe:fput_close]:
[0] 5116767 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[1] 164544 |@ |
@[kprobe:fput_close_sync]:
[0] 5340660 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[1] 358943 |@@@ |
0 indicates the last reference, 1 that there is more.
filp_close is largely skewed because of close_on_exec.
vast majority of last fputs are from remove_vma. I think that code wants
to be patched to batch them (as in something like fput_many should be
added -- something for later).
[1] https://lore.kernel.org/linux-fsdevel/20250304165728.491785-1-mjguzik@gmail.com/T/#u
* patches from https://lore.kernel.org/r/20250305123644.554845-1-mjguzik@gmail.com:
fs: use fput_close() in path_openat()
fs: use fput_close() in filp_close()
fs: use fput_close_sync() in close()
file: add fput and file_ref_put routines optimized for use when closing a fd
Link: https://lore.kernel.org/r/20250305123644.554845-1-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'fs/file.c')
-rw-r--r-- | fs/file.c | 41 |
1 files changed, 23 insertions, 18 deletions
diff --git a/fs/file.c b/fs/file.c index d868cdb95d1e..3fef798b96e5 100644 --- a/fs/file.c +++ b/fs/file.c @@ -26,6 +26,28 @@ #include "internal.h" +bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt) +{ + /* + * If the reference count was already in the dead zone, then this + * put() operation is imbalanced. Warn, put the reference count back to + * DEAD and tell the caller to not deconstruct the object. + */ + if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { + atomic_long_set(&ref->refcnt, FILE_REF_DEAD); + return false; + } + + /* + * This is a put() operation on a saturated refcount. Restore the + * mean saturation value and tell the caller to not deconstruct the + * object. + */ + if (cnt > FILE_REF_MAXREF) + atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); + return false; +} + /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count @@ -67,24 +89,7 @@ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) return true; } - /* - * If the reference count was already in the dead zone, then this - * put() operation is imbalanced. Warn, put the reference count back to - * DEAD and tell the caller to not deconstruct the object. - */ - if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { - atomic_long_set(&ref->refcnt, FILE_REF_DEAD); - return false; - } - - /* - * This is a put() operation on a saturated refcount. Restore the - * mean saturation value and tell the caller to not deconstruct the - * object. - */ - if (cnt > FILE_REF_MAXREF) - atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); - return false; + return __file_ref_put_badval(ref, cnt); } EXPORT_SYMBOL_GPL(__file_ref_put); |