Skip to contentSkip to conversation

vfs: use RCU in ilookup

PATCH Applied Mateusz Guzik 4 participants 5 messages Jul 15, 2024 – Jul 16, 2024 VFS

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 vfs: use RCU in ilookup

A soft lockup in ilookup was reported when stress-testing a 512-way system [1] (see [2] for full context) and it was verified that not taking the lock shifts issues back to mm.

[1] https://lore.kernel.org/linux-mm/[email protected]/
[2] https://lore.kernel.org/linux-mm/[email protected]/

---

fwiw the originally sent patch to the reporter performs a lockless lookup first and falls back to the locked variant, but that was me playing overfly safe.

I would add tested-by but patches are not the same in the end.

This is the only spot which can get this fixup, everything else taking the lock is also using custom callbacks, so filesystems invoking such code will need to get patched up on case-by-case basis (but realistically they probably already can do RCU-only operation).

 fs/inode.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
fs/inode.c +1 -3
index f356fe2ec2b6..52ca063c552c 100644
@@ -1525,9 +1525,7 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
 	struct inode *inode;
 again:
-	spin_lock(&inode_hash_lock);
-	inode = find_inode_fast(sb, head, ino, true);
-	spin_unlock(&inode_hash_lock);
+	inode = find_inode_fast(sb, head, ino, false);
 
 	if (inode) {
 		if (IS_ERR(inode))
Signature · 1 line
2.43.0
#1 lore raw
Quoted 5 lines · Mateusz Guzik

A soft lockup in ilookup was reported when stress-testing a 512-way system [1] (see [2] for full context) and it was verified that not taking the lock shifts issues back to mm.

[1] https://lore.kernel.org/linux-mm/[email protected]/

Mateusz,

Just want to mention explicitly that in addition to the lockless lookup changes that you suggested in [1], the test run also included your other commit https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git/commit/?h=vfs.inode.rcu&id=7180f8d91fcbf252de572d9ffacc945effed0060 as you had suggested.

Regards,
Bharata.

#2 lore raw
Quoted 8 lines · Bharata B Rao
Quoted 5 lines · Mateusz Guzik

A soft lockup in ilookup was reported when stress-testing a 512-way system [1] (see [2] for full context) and it was verified that not taking the lock shifts issues back to mm.

[1] https://lore.kernel.org/linux-mm/[email protected]/

Quoted 8 lines

Mateusz,

Just want to mention explicitly that in addition to the lockless lookup changes that you suggested in [1], the test run also included your other commit
https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git/commit/?h=vfs.inode.rcu&id=7180f8d91fcbf252de572d9ffacc945effed0060
as you had suggested.

That commit is needed to have this compile to begin with, so it was kind of implied. :)

Signature · 1 line
Mateusz Guzik <mjguzik gmail.com>
maintainer Applied
#3 lore raw
In reply to Mateusz Guzik
Quoted 8 lines · Mateusz Guzik

A soft lockup in ilookup was reported when stress-testing a 512-way system [1] (see [2] for full context) and it was verified that not taking the lock shifts issues back to mm.

[1] https://lore.kernel.org/linux-mm/[email protected]/
[2] https://lore.kernel.org/linux-mm/[email protected]/

[...]

Applied to the vfs.inode.rcu branch of the vfs/vfs.git tree. Patches in the vfs.inode.rcu branch should appear in linux-next soon.

Please report any outstanding bugs that were missed during review in a new review to the original patch series allowing us to drop it.

It's encouraged to provide Acked-bys and Reviewed-bys even though the patch has now been applied. If possible patch trailers will be updated.

Note that commit hashes shown below are subject to change due to rebase, trailer updates or similar. If in doubt, please check the listed branch.

tree:   https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git
branch: vfs.inode.rcu

[1/1] vfs: use RCU in ilookup

      https://git.kernel.org/vfs/vfs/c/2eae762dece6
reviewer Reviewed-by on v1 1/1
#4 lore raw
In reply to Mateusz Guzik
Quoted 8 lines · Mateusz Guzik

A soft lockup in ilookup was reported when stress-testing a 512-way system [1] (see [2] for full context) and it was verified that not taking the lock shifts issues back to mm.

[1] https://lore.kernel.org/linux-mm/[email protected]/
[2] https://lore.kernel.org/linux-mm/[email protected]/

Looks good to me. Feel free to add:

Honza

Quoted 34 lines

---

fwiw the originally sent patch to the reporter performs a lockless lookup first and falls back to the locked variant, but that was me playing overfly safe.

I would add tested-by but patches are not the same in the end.

This is the only spot which can get this fixup, everything else taking the lock is also using custom callbacks, so filesystems invoking such code will need to get patched up on case-by-case basis (but realistically they probably already can do RCU-only operation).

 fs/inode.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
fs/inode.c +1 -3
index f356fe2ec2b6..52ca063c552c 100644
@@ -1525,9 +1525,7 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
 	struct inode *inode;
 again:
-	spin_lock(&inode_hash_lock);
-	inode = find_inode_fast(sb, head, ino, true);
-	spin_unlock(&inode_hash_lock);
+	inode = find_inode_fast(sb, head, ino, false);
 
 	if (inode) {
 		if (IS_ERR(inode))
Signature · 1 line
2.43.0
Signature · 2 lines
Jan Kara <[email protected]>
SUSE Labs, CR