summaryrefslogtreecommitdiffstats
path: root/fs/open.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-08 19:26:35 +0200
committerChristian Brauner <brauner@kernel.org>2023-08-08 19:36:51 +0200
commit021a160abf62c19aff36c920566efb4f690e964a (patch)
tree2d6ffba249909d4c17edcadc3dda5b3318a20429 /fs/open.c
parentfile: mostly eliminate spurious relocking in __range_close (diff)
downloadlinux-021a160abf62c19aff36c920566efb4f690e964a.tar.xz
linux-021a160abf62c19aff36c920566efb4f690e964a.zip
fs: use __fput_sync in close(2)
close(2) is a special case which guarantees a shallow kernel stack, making delegation to task_work machinery unnecessary. Said delegation is problematic as it involves atomic ops and interrupt masking trips, none of which are cheap on x86-64. Forcing close(2) to do it looks like an oversight in the original work. Moreover presence of CONFIG_RSEQ adds an additional overhead as fput() -> task_work_add(..., TWA_RESUME) -> set_notify_resume() makes the thread returning to userspace land in resume_user_mode_work(), where rseq_handle_notify_resume takes a SMAP round-trip if rseq is enabled for the thread (and it is by default with contemporary glibc). Sample result when benchmarking open1_processes -t 1 from will-it-scale (that's an open + close loop) + tmpfs on /tmp, running on the Sapphire Rapid CPU (ops/s): stock+RSEQ: 1329857 stock-RSEQ: 1421667 (+7%) patched: 1523521 (+14.5% / +7%) (with / without rseq) Patched result is the same regardless of rseq as the codepath is avoided. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to '')
-rw-r--r--fs/open.c27
1 files changed, 24 insertions, 3 deletions
diff --git a/fs/open.c b/fs/open.c
index 0c55c8e7f837..455fdddbe9aa 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1503,7 +1503,7 @@ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
* "id" is the POSIX thread ID. We use the
* files pointer for this..
*/
-int filp_close(struct file *filp, fl_owner_t id)
+static int filp_flush(struct file *filp, fl_owner_t id)
{
int retval = 0;
@@ -1520,10 +1520,18 @@ int filp_close(struct file *filp, fl_owner_t id)
dnotify_flush(filp, id);
locks_remove_posix(filp, id);
}
- fput(filp);
return retval;
}
+int filp_close(struct file *filp, fl_owner_t id)
+{
+ int retval;
+
+ retval = filp_flush(filp, id);
+ fput(filp);
+
+ return retval;
+}
EXPORT_SYMBOL(filp_close);
/*
@@ -1533,7 +1541,20 @@ EXPORT_SYMBOL(filp_close);
*/
SYSCALL_DEFINE1(close, unsigned int, fd)
{
- int retval = close_fd(fd);
+ int retval;
+ struct file *file;
+
+ file = close_fd_get_file(fd);
+ if (!file)
+ return -EBADF;
+
+ retval = filp_flush(file, current->files);
+
+ /*
+ * We're returning to user space. Don't bother
+ * with any delayed fput() cases.
+ */
+ __fput_sync(file);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||