From d09b710da49100d2def6ba853c3a3093aa452644 Mon Sep 17 00:00:00 2001
From: Niels Dossche <7771979+nielsdos@users.noreply.github.com>
Date: Sun, 23 Apr 2023 18:14:31 +0200
Subject: [PATCH] Change realpath cache hash algorithm to the regular string
 hash algorithm

Right now the FNV-1 algorithm is used for determine the realpath cache
key. For applications that are light-weight, but have lots of files
(e.g. WordPress), the realpath cache key computation shows up in the
Callgrind profile. The reason is that we do a simple byte-by-byte loop.
Furthermore, we always use the 32-bit prime and offset values, even in a
64-bit environment which reduces the diffusion property of the hash.
This hinders the distribution of keys a bit (although probably not a lot
since we have only limited entries in the cache).

I propose to switch to our regular string hashing algorithm, which is
better optimised than a byte-per-byte loop, and has better diffusion on
64-bit systems.

I don't know why FNV-1 was chosen over the DJB33X algorithm we use in the
normal string hashing. Also, I don't know why FNV-1A wasn't chosen
instead of FNV-1, which would be a simple modification and would
distribute the hashes better than FNV-1.
The only thing I can think of is that typically FNV-1A has a better
distribution than DJB33X algorithms like what we use for string hashing
[1]. But I doubt that makes a difference here, and if it does then we
should perhaps look into changing the string hash algorithm from DJB33X to
FNV-1A.

[1] https://softwareengineering.stackexchange.com/questions/49550/which-hashing-algorithm-is-best-for-uniqueness-and-speed
---
 Zend/zend_virtual_cwd.c | 25 +++++--------------------
 1 file changed, 5 insertions(+), 20 deletions(-)

diff --git a/Zend/zend_virtual_cwd.c b/Zend/zend_virtual_cwd.c
index 6bff2ad984d02..7806002d37294 100644
--- a/Zend/zend_virtual_cwd.c
+++ b/Zend/zend_virtual_cwd.c
@@ -317,23 +317,16 @@ CWD_API char *virtual_getcwd(char *buf, size_t size) /* {{{ */
 #ifdef ZEND_WIN32
 static inline zend_ulong realpath_cache_key(const char *path, size_t path_len) /* {{{ */
 {
-	zend_ulong h;
 	size_t bucket_key_len;
-	const char *bucket_key_start = tsrm_win32_get_path_sid_key(path, path_len, &bucket_key_len);
-	const char *bucket_key = bucket_key_start;
-	const char *e;
+	const char *bucket_key = tsrm_win32_get_path_sid_key(path, path_len, &bucket_key_len);
 
 	if (!bucket_key) {
 		return 0;
 	}
 
-	e = bucket_key + bucket_key_len;
-	for (h = Z_UL(2166136261); bucket_key < e;) {
-		h *= Z_UL(16777619);
-		h ^= *bucket_key++;
-	}
-	if (bucket_key_start != path) {
-		HeapFree(GetProcessHeap(), 0, (LPVOID)bucket_key_start);
+	zend_ulong h = zend_hash_func(bucket_key, bucket_key_len);
+	if (bucket_key != path) {
+		HeapFree(GetProcessHeap(), 0, (LPVOID)bucket_key);
 	}
 	return h;
 }
@@ -341,15 +334,7 @@ static inline zend_ulong realpath_cache_key(const char *path, size_t path_len) /
 #else
 static inline zend_ulong realpath_cache_key(const char *path, size_t path_len) /* {{{ */
 {
-	zend_ulong h;
-	const char *e = path + path_len;
-
-	for (h = Z_UL(2166136261); path < e;) {
-		h *= Z_UL(16777619);
-		h ^= *path++;
-	}
-
-	return h;
+	return zend_hash_func(path, path_len);
 }
 /* }}} */
 #endif /* defined(ZEND_WIN32) */