summaryrefslogtreecommitdiffstats
path: root/fs/namei.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2011-08-06 22:45:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-08-06 22:53:23 -0700
commit3ddcd0569cd68f00f3beae9a7959b72918bb91f4 (patch)
tree3f7c591316560b1c22e2cc0700fbcd29aa3fbd7f /fs/namei.c
parent830c0f0edca67403d361fe976a25b17356c11f19 (diff)
downloadop-kernel-dev-3ddcd0569cd68f00f3beae9a7959b72918bb91f4.zip
op-kernel-dev-3ddcd0569cd68f00f3beae9a7959b72918bb91f4.tar.gz
vfs: optimize inode cache access patterns
The inode structure layout is largely random, and some of the vfs paths really do care. The path lookup in particular is already quite D$ intensive, and profiles show that accessing the 'inode->i_op->xyz' fields is quite costly. We already optimized the dcache to not unnecessarily load the d_op structure for members that are often NULL using the DCACHE_OP_xyz bits in dentry->d_flags, and this does something very similar for the inode ops that are used during pathname lookup. It also re-orders the fields so that the fields accessed by 'stat' are together at the beginning of the inode structure, and roughly in the order accessed. The effect of this seems to be in the 1-2% range for an empty kernel "make -j" run (which is fairly kernel-intensive, mostly in filename lookup), so it's visible. The numbers are fairly noisy, though, and likely depend a lot on exact microarchitecture. So there's more tuning to be done. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/namei.c')
-rw-r--r--fs/namei.c76
1 files changed, 66 insertions, 10 deletions
diff --git a/fs/namei.c b/fs/namei.c
index 3d607bd..4a98bf1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -308,6 +308,26 @@ int generic_permission(struct inode *inode, int mask)
return -EACCES;
}
+/*
+ * We _really_ want to just do "generic_permission()" without
+ * even looking at the inode->i_op values. So we keep a cache
+ * flag in inode->i_opflags, that says "this has not special
+ * permission function, use the fast case".
+ */
+static inline int do_inode_permission(struct inode *inode, int mask)
+{
+ if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
+ if (likely(inode->i_op->permission))
+ return inode->i_op->permission(inode, mask);
+
+ /* This gets set once for the inode lifetime */
+ spin_lock(&inode->i_lock);
+ inode->i_opflags |= IOP_FASTPERM;
+ spin_unlock(&inode->i_lock);
+ }
+ return generic_permission(inode, mask);
+}
+
/**
* inode_permission - check for access rights to a given inode
* @inode: inode to check permission on
@@ -322,7 +342,7 @@ int inode_permission(struct inode *inode, int mask)
{
int retval;
- if (mask & MAY_WRITE) {
+ if (unlikely(mask & MAY_WRITE)) {
umode_t mode = inode->i_mode;
/*
@@ -339,11 +359,7 @@ int inode_permission(struct inode *inode, int mask)
return -EACCES;
}
- if (inode->i_op->permission)
- retval = inode->i_op->permission(inode, mask);
- else
- retval = generic_permission(inode, mask);
-
+ retval = do_inode_permission(inode, mask);
if (retval)
return retval;
@@ -1245,6 +1261,26 @@ static void terminate_walk(struct nameidata *nd)
}
}
+/*
+ * Do we need to follow links? We _really_ want to be able
+ * to do this check without having to look at inode->i_op,
+ * so we keep a cache of "no, this doesn't need follow_link"
+ * for the common case.
+ */
+static inline int do_follow_link(struct inode *inode, int follow)
+{
+ if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
+ if (likely(inode->i_op->follow_link))
+ return follow;
+
+ /* This gets set once for the inode lifetime */
+ spin_lock(&inode->i_lock);
+ inode->i_opflags |= IOP_NOFOLLOW;
+ spin_unlock(&inode->i_lock);
+ }
+ return 0;
+}
+
static inline int walk_component(struct nameidata *nd, struct path *path,
struct qstr *name, int type, int follow)
{
@@ -1267,7 +1303,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
terminate_walk(nd);
return -ENOENT;
}
- if (unlikely(inode->i_op->follow_link) && follow) {
+ if (do_follow_link(inode, follow)) {
if (nd->flags & LOOKUP_RCU) {
if (unlikely(unlazy_walk(nd, path->dentry))) {
terminate_walk(nd);
@@ -1320,6 +1356,26 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
}
/*
+ * We really don't want to look at inode->i_op->lookup
+ * when we don't have to. So we keep a cache bit in
+ * the inode ->i_opflags field that says "yes, we can
+ * do lookup on this inode".
+ */
+static inline int can_lookup(struct inode *inode)
+{
+ if (likely(inode->i_opflags & IOP_LOOKUP))
+ return 1;
+ if (likely(!inode->i_op->lookup))
+ return 0;
+
+ /* We do this once for the lifetime of the inode */
+ spin_lock(&inode->i_lock);
+ inode->i_opflags |= IOP_LOOKUP;
+ spin_unlock(&inode->i_lock);
+ return 1;
+}
+
+/*
* Name resolution.
* This is the basic name resolution function, turning a pathname into
* the final dentry. We expect 'base' to be positive and a directory.
@@ -1398,10 +1454,10 @@ static int link_path_walk(const char *name, struct nameidata *nd)
if (err)
return err;
}
+ if (can_lookup(nd->inode))
+ continue;
err = -ENOTDIR;
- if (!nd->inode->i_op->lookup)
- break;
- continue;
+ break;
/* here ends the main loop */
last_component:
OpenPOWER on IntegriCloud