Replace the global part of the lglock with a percpu-rwsem.
Since fcl_lock is a spinlock and itself nests under i_lock, which too
is a spinlock we cannot acquire sleeping locks at
locks_{insert,remove}_global_locks().
We can however wrap all fcl_lock acquisitions with percpu_down_read
such that all invocations of locks_{insert,remove}_global_locks() have
that read lock held.
This allows us to replace the lg_global part of the lglock with the
write side of the rwsem.
In the absense of writers, percpu_{down,up}_read() are free of atomic
instructions. This further avoids the very long preempt-disable
regions caused by lglock on larger machines.
Cc: Al Viro <v...@zeniv.linux.org.uk>
Cc: Oleg Nesterov <o...@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>
---
fs/locks.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -165,6 +165,7 @@ int lease_break_time = 45;
*/
DEFINE_STATIC_LGLOCK(file_lock_lglock);
static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
+static struct percpu_rw_semaphore file_rwsem;
/*
* The blocked_hash is used to find POSIX lock loops for deadlock detection.
@@ -556,6 +557,8 @@ static int posix_same_owner(struct file_
/* Must be called with the flc_lock held! */
static void locks_insert_global_locks(struct file_lock *fl)
{
+ lockdep_assert_held_percpu_rwsem(&file_rwsem);
+
lg_local_lock(&file_lock_lglock);
fl->fl_link_cpu = smp_processor_id();
hlist_add_head(&fl->fl_link, this_cpu_ptr(&file_lock_list));
@@ -565,6 +568,8 @@ static void locks_insert_global_locks(st
/* Must be called with the flc_lock held! */
static void locks_delete_global_locks(struct file_lock *fl)
{
+ lockdep_assert_held_percpu_rwsem(&file_rwsem);
+
/*
* Avoid taking lock if already unhashed. This is safe since this check
* is done while holding the flc_lock, and new insertions into the list
@@ -885,6 +890,7 @@ static int flock_lock_file(struct file *
return -ENOMEM;
}
+ percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
if (request->fl_flags & FL_ACCESS)
goto find_conflict;
@@ -925,6 +931,7 @@ static int flock_lock_file(struct file *
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read(&file_rwsem);
if (new_fl)
locks_free_lock(new_fl);
locks_dispose_list(&dispose);
@@ -960,6 +967,7 @@ static int __posix_lock_file(struct inod
new_fl2 = locks_alloc_lock();
}
+ percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
/*
* New lock request. Walk all POSIX locks and look for conflicts. If
@@ -1131,6 +1139,7 @@ static int __posix_lock_file(struct inod
}
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read(&file_rwsem);
/*
* Free any unused locks.
*/
@@ -1407,6 +1416,7 @@ int __break_lease(struct inode *inode, u
return error;
}
+ percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
@@ -1477,6 +1487,7 @@ int __break_lease(struct inode *inode, u
}
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
locks_free_lock(new_fl);
return error;
@@ -1630,6 +1641,7 @@ generic_add_lease(struct file *filp, lon
return -EINVAL;
}
+ percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
error = check_conflicting_open(dentry, arg, lease->fl_flags);
@@ -1700,6 +1712,7 @@ generic_add_lease(struct file *filp, lon
lease->fl_lmops->lm_setup(lease, priv);
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
if (is_deleg)
mutex_unlock(&inode->i_mutex);
@@ -1722,6 +1735,7 @@ static int generic_delete_lease(struct f
return error;
}
+ percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (fl->fl_file == filp &&
@@ -1734,6 +1748,7 @@ static int generic_delete_lease(struct f
if (victim)
error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
spin_unlock(&ctx->flc_lock);
+ percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
return error;
}
@@ -2634,6 +2649,7 @@ static void *locks_start(struct seq_file
struct locks_iterator *iter = f->private;
iter->li_pos = *pos + 1;
+ percpu_down_write(&file_rwsem);
lg_global_lock(&file_lock_lglock);
spin_lock(&blocked_lock_lock);
return seq_hlist_start_percpu(&file_lock_list, &iter->li_cpu, *pos);
@@ -2652,6 +2668,7 @@ static void locks_stop(struct seq_file *
{
spin_unlock(&blocked_lock_lock);
lg_global_unlock(&file_lock_lglock);
+ percpu_up_write(&file_rwsem);
}
static const struct seq_operations locks_seq_operations = {
@@ -2693,6 +2710,7 @@ static int __init filelock_init(void)
sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
lg_lock_init(&file_lock_lglock, "file_lock_lglock");
+ percpu_init_rwsem(&file_rwsem);
for_each_possible_cpu(i)
INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i));
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
Please read the FAQ at http://www.tux.org/lkml/
