The patch titled
Subject: fs/file.c: don't acquire files->file_lock in fd_install()
has been added to the -mm tree. Its filename is
fs-filec-dont-acquire-files-file_lock-in-fd_install.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/fs-filec-dont-acquire-files-file_lock-in-fd_install.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/fs-filec-dont-acquire-files-file_lock-in-fd_install.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Eric Dumazet <edumazet@xxxxxxxxxx>
Subject: fs/file.c: don't acquire files->file_lock in fd_install()
Mateusz Guzik reported :
Currently obtaining a new file descriptor results in locking fdtable
twice - once in order to reserve a slot and second time to fill it.
Holding the spinlock in __fd_install() is needed in case a resize is
done, or to prevent a resize.
Mateusz provided an RFC patch and a micro benchmark :
http://people.redhat.com/~mguzik/pipebench.c
A resize is an unlikely operation in a process lifetime,
as table size is at least doubled at every resize.
We can use RCU instead of the spinlock :
__fd_install() must wait if a resize is in progress.
The resize must block new __fd_install() callers from starting,
and wait that ongoing install are finished (synchronize_sched())
resize should be attempted by a single thread to not waste resources.
rcu_sched variant is used, as __fd_install() and expand_fdtable() run
from process context.
It gives us a ~30% speedup using pipebench with 16 threads, and a ~10%
speedup with another program using TCP sockets.
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Reported-by: Mateusz Guzik <mguzik@xxxxxxxxxx>
Acked-by: Mateusz Guzik <mguzik@xxxxxxxxxx>
Tested-by: Mateusz Guzik <mguzik@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Yann Droneaud <ydroneaud@xxxxxxxxxx>
Cc: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/file.c | 66 +++++++++++++++++++++++++++-----------
include/linux/fdtable.h | 3 +
2 files changed, 50 insertions(+), 19 deletions(-)
diff -puN fs/file.c~fs-filec-dont-acquire-files-file_lock-in-fd_install fs/file.c
--- a/fs/file.c~fs-filec-dont-acquire-files-file_lock-in-fd_install
+++ a/fs/file.c
@@ -147,6 +147,13 @@ static int expand_fdtable(struct files_s
spin_unlock(&files->file_lock);
new_fdt = alloc_fdtable(nr);
+
+ /* make sure all __fd_install() have seen resize_in_progress
+ * or have finished their rcu_read_lock_sched() section.
+ */
+ if (atomic_read(&files->count) > 1)
+ synchronize_sched();
+
spin_lock(&files->file_lock);
if (!new_fdt)
return -ENOMEM;
@@ -158,21 +165,14 @@ static int expand_fdtable(struct files_s
__free_fdtable(new_fdt);
return -EMFILE;
}
- /*
- * Check again since another task may have expanded the fd table while
- * we dropped the lock
- */
cur_fdt = files_fdtable(files);
- if (nr >= cur_fdt->max_fds) {
- /* Continue as planned */
- copy_fdtable(new_fdt, cur_fdt);
- rcu_assign_pointer(files->fdt, new_fdt);
- if (cur_fdt != &files->fdtab)
- call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
- } else {
- /* Somebody else expanded, so undo our attempt */
- __free_fdtable(new_fdt);
- }
+ BUG_ON(nr < cur_fdt->max_fds);
+ copy_fdtable(new_fdt, cur_fdt);
+ rcu_assign_pointer(files->fdt, new_fdt);
+ if (cur_fdt != &files->fdtab)
+ call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
+ /* coupled with smp_rmb() in __fd_install() */
+ smp_wmb();
return 1;
}
@@ -185,21 +185,38 @@ static int expand_fdtable(struct files_s
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_files(struct files_struct *files, int nr)
+ __releases(files->file_lock)
+ __acquires(files->file_lock)
{
struct fdtable *fdt;
+ int expanded = 0;
+repeat:
fdt = files_fdtable(files);
/* Do we need to expand? */
if (nr < fdt->max_fds)
- return 0;
+ return expanded;
/* Can we expand? */
if (nr >= sysctl_nr_open)
return -EMFILE;
+ if (unlikely(files->resize_in_progress)) {
+ spin_unlock(&files->file_lock);
+ expanded = 1;
+ wait_event(files->resize_wait, !files->resize_in_progress);
+ spin_lock(&files->file_lock);
+ goto repeat;
+ }
+
/* All good, so we try */
- return expand_fdtable(files, nr);
+ files->resize_in_progress = true;
+ expanded = expand_fdtable(files, nr);
+ files->resize_in_progress = false;
+
+ wake_up_all(&files->resize_wait);
+ return expanded;
}
static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
@@ -256,6 +273,8 @@ struct files_struct *dup_fd(struct files
atomic_set(&newf->count, 1);
spin_lock_init(&newf->file_lock);
+ newf->resize_in_progress = false;
+ init_waitqueue_head(&newf->resize_wait);
newf->next_fd = 0;
new_fdt = &newf->fdtab;
new_fdt->max_fds = NR_OPEN_DEFAULT;
@@ -553,11 +572,20 @@ void __fd_install(struct files_struct *f
struct file *file)
{
struct fdtable *fdt;
- spin_lock(&files->file_lock);
- fdt = files_fdtable(files);
+
+ rcu_read_lock_sched();
+
+ while (unlikely(files->resize_in_progress)) {
+ rcu_read_unlock_sched();
+ wait_event(files->resize_wait, !files->resize_in_progress);
+ rcu_read_lock_sched();
+ }
+ /* coupled with smp_wmb() in expand_fdtable() */
+ smp_rmb();
+ fdt = rcu_dereference_sched(files->fdt);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
- spin_unlock(&files->file_lock);
+ rcu_read_unlock_sched();
}
void fd_install(unsigned int fd, struct file *file)
diff -puN include/linux/fdtable.h~fs-filec-dont-acquire-files-file_lock-in-fd_install include/linux/fdtable.h
--- a/include/linux/fdtable.h~fs-filec-dont-acquire-files-file_lock-in-fd_install
+++ a/include/linux/fdtable.h
@@ -47,6 +47,9 @@ struct files_struct {
* read mostly part
*/
atomic_t count;
+ bool resize_in_progress;
+ wait_queue_head_t resize_wait;
+
struct fdtable __rcu *fdt;
struct fdtable fdtab;
/*
_
Patches currently in -mm which might be from edumazet@xxxxxxxxxx are
fs-filec-dont-acquire-files-file_lock-in-fd_install.patch
linux-next.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
