From: Nick Piggin <npiggin@kernel.dk>
Date: Fri, 7 Jan 2011 06:50:09 +0000 (+1100)
Subject: fs: implement faster dentry memcmp
X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=9d55c369bb5e695e629bc35cba2ef607755b3bee;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git

fs: implement faster dentry memcmp

The standard memcmp function on a Westmere system shows up hot in
profiles in the `git diff` workload (both parallel and single threaded),
and it is likely due to the costs associated with trapping into
microcode, and little opportunity to improve memory access (dentry
name is not likely to take up more than a cacheline).

So replace it with an open-coded byte comparison. This increases code
size by 8 bytes in the critical __d_lookup_rcu function, but the
speedup is huge, averaging 10 runs of each:

git diff st   user   sys   elapsed  CPU
before        1.15   2.57  3.82      97.1
after         1.14   2.35  3.61      96.8

git diff mt   user   sys   elapsed  CPU
before        1.27   3.85  1.46     349
after         1.26   3.54  1.43     333

Elapsed time for single threaded git diff at 95.0% confidence:
        -0.21  +/- 0.01
        -5.45% +/- 0.24%

It's -0.66% +/- 0.06% elapsed time on my Opteron, so rep cmp costs on the
fam10h seem to be relatively smaller, but there is still a win.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---

diff --git a/fs/dcache.c b/fs/dcache.c
index 2a4ce7dc2306..5699d4c027cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1454,9 +1454,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
 			continue;
 		if (alias->d_parent != entry->d_parent)
 			continue;
-		if (qstr->len != len)
-			continue;
-		if (memcmp(qstr->name, name, len))
+		if (dentry_cmp(qstr->name, qstr->len, name, len))
 			continue;
 		__dget(alias);
 		return alias;
@@ -1810,9 +1808,7 @@ seqretry:
 						tlen, tname, name))
 				continue;
 		} else {
-			if (tlen != len)
-				continue;
-			if (memcmp(tname, str, tlen))
+			if (dentry_cmp(tname, tlen, str, len))
 				continue;
 		}
 		/*
@@ -1925,9 +1921,7 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
 						tlen, tname, name))
 				goto next;
 		} else {
-			if (tlen != len)
-				goto next;
-			if (memcmp(tname, str, tlen))
+			if (dentry_cmp(tname, tlen, str, len))
 				goto next;
 		}
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index c0a2ca97c72f..bd07758943e0 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -47,6 +47,27 @@ struct dentry_stat_t {
 };
 extern struct dentry_stat_t dentry_stat;
 
+/*
+ * Compare 2 name strings, return 0 if they match, otherwise non-zero.
+ * The strings are both count bytes long, and count is non-zero.
+ */
+static inline int dentry_cmp(const unsigned char *cs, size_t scount,
+				const unsigned char *ct, size_t tcount)
+{
+	int ret;
+	if (scount != tcount)
+		return 1;
+	do {
+		ret = (*cs != *ct);
+		if (ret)
+			break;
+		cs++;
+		ct++;
+		tcount--;
+	} while (tcount);
+	return ret;
+}
+
 /* Name hashing routines. Initial hash value */
 /* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
 #define init_name_hash()		0