diff options
| author | Mateusz Guzik <mjguzik@gmail.com> | 2025-11-20 01:38:03 +0100 |
|---|---|---|
| committer | Christian Brauner <brauner@kernel.org> | 2025-11-26 14:52:02 +0100 |
| commit | 177fdbae39ecccb441d45e5e5ab146ea35b03d49 (patch) | |
| tree | 9209c892885d74f9afc55be334969bb17ab61d0d | |
| parent | 9d2a6211a7b972563d20edebccaae42994c429fb (diff) | |
| download | tip-177fdbae39ecccb441d45e5e5ab146ea35b03d49.tar.gz | |
fs: inline step_into() and walk_component()
The primary consumer is link_path_walk(), calling walk_component() every
time which in turn calls step_into().
Inlining these saves overhead of 2 function calls per path component,
along with allowing the compiler to do better job optimizing them in place.
step_into() had absolutely atrocious assembly to facilitate the
slowpath. In order to lessen the burden at the callsite all the hard
work is moved into step_into_slowpath() and instead an inline-able
fastpath is implemented for rcu-walk.
The new fastpath is a stripped down step_into() RCU handling with a
d_managed() check from handle_mounts().
Benchmarked as follows on Sapphire Rapids:
1. the "before" was a kernel with not-yet-merged optimizations (notably
elision of calls to security_inode_permission() and marking ext4
inodes as not having acls as applicable)
2. "after" is the same + the prep patch + this patch
3. benchmark consists of issuing 205 calls to access(2) in a loop with
pathnames lifted out of gcc and the linker building real code, most
of which have several path components and 118 of which fail with
-ENOENT.
Result in terms of ops/s:
before: 21619
after: 22536 (+4%)
profile before:
20.25% [kernel] [k] __d_lookup_rcu
10.54% [kernel] [k] link_path_walk
10.22% [kernel] [k] entry_SYSCALL_64
6.50% libc.so.6 [.] __GI___access
6.35% [kernel] [k] strncpy_from_user
4.87% [kernel] [k] step_into
3.68% [kernel] [k] kmem_cache_alloc_noprof
2.88% [kernel] [k] walk_component
2.86% [kernel] [k] kmem_cache_free
2.14% [kernel] [k] set_root
2.08% [kernel] [k] lookup_fast
after:
23.38% [kernel] [k] __d_lookup_rcu
11.27% [kernel] [k] entry_SYSCALL_64
10.89% [kernel] [k] link_path_walk
7.00% libc.so.6 [.] __GI___access
6.88% [kernel] [k] strncpy_from_user
3.50% [kernel] [k] kmem_cache_alloc_noprof
2.01% [kernel] [k] kmem_cache_free
2.00% [kernel] [k] set_root
1.99% [kernel] [k] lookup_fast
1.81% [kernel] [k] do_syscall_64
1.69% [kernel] [k] entry_SYSCALL_64_safe_stack
While walk_component() and step_into() of course disappear from the
profile, the link_path_walk() barely gets more overhead despite the
inlining thanks to the fast path added and while completing more walks
per second.
I did not investigate why overhead grew a lot on __d_lookup_rcu().
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://patch.msgid.link/20251120003803.2979978-2-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
| -rw-r--r-- | fs/namei.c | 31 |
1 files changed, 28 insertions, 3 deletions
diff --git a/fs/namei.c b/fs/namei.c index 5fee8afa510ede..8281dfe5047f44 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1951,7 +1951,7 @@ static noinline const char *pick_link(struct nameidata *nd, struct path *link, int error; if (nd->flags & LOOKUP_RCU) { - /* make sure that d_is_symlink from step_into() matches the inode */ + /* make sure that d_is_symlink from step_into_slowpath() matches the inode */ if (read_seqcount_retry(&link->dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); } else { @@ -2033,7 +2033,7 @@ all_done: // pure jump * * NOTE: dentry must be what nd->next_seq had been sampled from. */ -static const char *step_into(struct nameidata *nd, int flags, +static noinline const char *step_into_slowpath(struct nameidata *nd, int flags, struct dentry *dentry) { struct path path; @@ -2066,6 +2066,31 @@ static const char *step_into(struct nameidata *nd, int flags, return pick_link(nd, &path, inode, flags); } +static __always_inline const char *step_into(struct nameidata *nd, int flags, + struct dentry *dentry) +{ + /* + * In the common case we are in rcu-walk and traversing over a non-mounted on + * directory (as opposed to e.g., a symlink). + * + * We can handle that and negative entries with the checks below. + */ + if (likely((nd->flags & LOOKUP_RCU) && + !d_managed(dentry) && !d_is_symlink(dentry))) { + struct inode *inode = dentry->d_inode; + if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) + return ERR_PTR(-ECHILD); + if (unlikely(!inode)) + return ERR_PTR(-ENOENT); + nd->path.dentry = dentry; + /* nd->path.mnt is retained on purpose */ + nd->inode = inode; + nd->seq = nd->next_seq; + return NULL; + } + return step_into_slowpath(nd, flags, dentry); +} + static struct dentry *follow_dotdot_rcu(struct nameidata *nd) { struct dentry *parent, *old; @@ -2176,7 +2201,7 @@ static const char *handle_dots(struct nameidata *nd, int type) return NULL; } -static const char *walk_component(struct nameidata *nd, int flags) +static __always_inline const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; /* |