diff mbox series

[v3,07/68] fscache: Implement a hash function

Message ID 163967082342.1823006.8915671045444488742.stgit@warthog.procyon.org.uk (mailing list archive)
State New, archived
Headers show
Series fscache, cachefiles: Rewrite | expand

Commit Message

David Howells Dec. 16, 2021, 4:07 p.m. UTC
Implement a function to generate hashes.  It needs to be stable over time
and endianness-independent as the hashes will appear on disk in future
patches.  It can assume that its input is a multiple of four bytes in size
and alignment.

This is borrowed from the VFS and simplified.  le32_to_cpu() is added to
make it endianness-independent.

Changes
=======
ver #3:
 - Read the data being hashed in an endianness-independent way[1].
 - Change the size parameter to be in bytes rather than words.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-cachefs@redhat.com
Link: https://lore.kernel.org/r/CAHk-=whtkzB446+hX0zdLsdcUJsJ=8_-0S1mE_R+YurThfUbLA@mail.gmail.com [1]
Link: https://lore.kernel.org/r/163819586113.215744.1699465806130102367.stgit@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/163906888735.143852.10944614318596881429.stgit@warthog.procyon.org.uk/ # v2
---

 fs/fscache/internal.h |    2 ++
 fs/fscache/main.c     |   40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+)
diff mbox series

Patch

diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index ea52f8594a77..f345bdb018ba 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -22,6 +22,8 @@ 
  */
 extern unsigned fscache_debug;
 
+extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
+
 /*
  * proc.c
  */
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
index 819de2ee1276..687b34903d5b 100644
--- a/fs/fscache/main.c
+++ b/fs/fscache/main.c
@@ -24,6 +24,46 @@  MODULE_PARM_DESC(fscache_debug,
 struct workqueue_struct *fscache_wq;
 EXPORT_SYMBOL(fscache_wq);
 
+/*
+ * Mixing scores (in bits) for (7,20):
+ * Input delta: 1-bit      2-bit
+ * 1 round:     330.3     9201.6
+ * 2 rounds:   1246.4    25475.4
+ * 3 rounds:   1907.1    31295.1
+ * 4 rounds:   2042.3    31718.6
+ * Perfect:    2048      31744
+ *            (32*64)   (32*31/2 * 64)
+ */
+#define HASH_MIX(x, y, a)	\
+	(	x ^= (a),	\
+	y ^= x,	x = rol32(x, 7),\
+	x += y,	y = rol32(y,20),\
+	y *= 9			)
+
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
+{
+	/* Use arch-optimized multiply if one exists */
+	return __hash_32(y ^ __hash_32(x));
+}
+
+/*
+ * Generate a hash.  This is derived from full_name_hash(), but we want to be
+ * sure it is arch independent and that it doesn't change as bits of the
+ * computed hash value might appear on disk.  The caller must guarantee that
+ * the source data is a multiple of four bytes in size.
+ */
+unsigned int fscache_hash(unsigned int salt, const void *data, size_t len)
+{
+	const __le32 *p = data;
+	unsigned int a, x = 0, y = salt, n = len / sizeof(__le32);
+
+	for (; n; n--) {
+		a = le32_to_cpu(*p++);
+		HASH_MIX(x, y, a);
+	}
+	return fold_hash(x, y);
+}
+
 /*
  * initialise the fs caching module
  */