summaryrefslogtreecommitdiff
path: root/include/linux/stringhash.h
diff options
context:
space:
mode:
authorMauro Carvalho Chehab <mchehab@osg.samsung.com>2016-06-07 13:04:56 -0300
committerMauro Carvalho Chehab <mchehab@osg.samsung.com>2016-06-07 13:04:56 -0300
commitc853f18b640f3e58ba14ffb25e551be8af218209 (patch)
tree89adc65667f124c21f2104422fcaed991da450ab /include/linux/stringhash.h
parentaff093d4bbca91f543e24cde2135f393b8130f4b (diff)
parentaf8c34ce6ae32addda3788d54a7e340cad22516b (diff)
Merge tag 'v4.7-rc2' into v4l_for_linus
Linux 4.7-rc2 * tag 'v4.7-rc2': (10914 commits) Linux 4.7-rc2 devpts: Make each mount of devpts an independent filesystem. parisc: Move die_if_kernel() prototype into traps.h header parisc: Fix pagefault crash in unaligned __get_user() call parisc: Fix printk time during boot parisc: Fix backtrace on PA-RISC mm, page_alloc: recalculate the preferred zoneref if the context can ignore memory policies mm, page_alloc: reset zonelist iterator after resetting fair zone allocation policy mm, oom_reaper: do not use siglock in try_oom_reaper() mm, page_alloc: prevent infinite loop in buffered_rmqueue() checkpatch: reduce git commit description style false positives mm/z3fold.c: avoid modifying HEADLESS page and minor cleanup memcg: add RCU locking around css_for_each_descendant_pre() in memcg_offline_kmem() mm: check the return value of lookup_page_ext for all call sites kdump: fix dmesg gdbmacro to work with record based printk mm: fix overflow in vm_map_ram() Btrfs: deal with duplciates during extent_map insertion in btrfs_get_extent arm64: fix alignment when RANDOMIZE_TEXT_OFFSET is enabled arm64: move {PAGE,CONT}_SHIFT into Kconfig arm64: mm: dump: log span level ...
Diffstat (limited to 'include/linux/stringhash.h')
-rw-r--r--include/linux/stringhash.h76
1 files changed, 76 insertions, 0 deletions
diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h
new file mode 100644
index 000000000000..451771d9b9c0
--- /dev/null
+++ b/include/linux/stringhash.h
@@ -0,0 +1,76 @@
+#ifndef __LINUX_STRINGHASH_H
+#define __LINUX_STRINGHASH_H
+
+#include <linux/compiler.h> /* For __pure */
+#include <linux/types.h> /* For u32, u64 */
+
+/*
+ * Routines for hashing strings of bytes to a 32-bit hash value.
+ *
+ * These hash functions are NOT GUARANTEED STABLE between kernel
+ * versions, architectures, or even repeated boots of the same kernel.
+ * (E.g. they may depend on boot-time hardware detection or be
+ * deliberately randomized.)
+ *
+ * They are also not intended to be secure against collisions caused by
+ * malicious inputs; much slower hash functions are required for that.
+ *
+ * They are optimized for pathname components, meaning short strings.
+ * Even if a majority of files have longer names, the dynamic profile of
+ * pathname components skews short due to short directory names.
+ * (E.g. /usr/lib/libsesquipedalianism.so.3.141.)
+ */
+
+/*
+ * Version 1: one byte at a time. Example of use:
+ *
+ * unsigned long hash = init_name_hash;
+ * while (*p)
+ * hash = partial_name_hash(tolower(*p++), hash);
+ * hash = end_name_hash(hash);
+ *
+ * Although this is designed for bytes, fs/hfsplus/unicode.c
+ * abuses it to hash 16-bit values.
+ */
+
+/* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
+#define init_name_hash() 0
+
+/* partial hash update function. Assume roughly 4 bits per character */
+static inline unsigned long
+partial_name_hash(unsigned long c, unsigned long prevhash)
+{
+ return (prevhash + (c << 4) + (c >> 4)) * 11;
+}
+
+/*
+ * Finally: cut down the number of bits to a int value (and try to avoid
+ * losing bits)
+ */
+static inline unsigned long end_name_hash(unsigned long hash)
+{
+ return (unsigned int)hash;
+}
+
+/*
+ * Version 2: One word (32 or 64 bits) at a time.
+ * If CONFIG_DCACHE_WORD_ACCESS is defined (meaning <asm/word-at-a-time.h>
+ * exists, which describes major Linux platforms like x86 and ARM), then
+ * this computes a different hash function much faster.
+ *
+ * If not set, this falls back to a wrapper around the preceding.
+ */
+extern unsigned int __pure full_name_hash(const char *, unsigned int);
+
+/*
+ * A hash_len is a u64 with the hash of a string in the low
+ * half and the length in the high half.
+ */
+#define hashlen_hash(hashlen) ((u32)(hashlen))
+#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
+#define hashlen_create(hash, len) ((u64)(len)<<32 | (u32)(hash))
+
+/* Return the "hash_len" (hash and length) of a null-terminated string */
+extern u64 __pure hashlen_string(const char *name);
+
+#endif /* __LINUX_STRINGHASH_H */