From: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx> commit 3b3c4babd898715926d24ae10aa64778ace33aae upstream. Patch series "Multibyte memset variations", v4. A relatively common idiom we're missing is a function to fill an area of memory with a pattern which is larger than a single byte. I first noticed this with a zram patch which wanted to fill a page with an 'unsigned long' value. There turn out to be quite a few places in the kernel which can benefit from using an optimised function rather than a loop; sometimes text size, sometimes speed, and sometimes both. The optimised PowerPC version (not included here) improves performance by about 30% on POWER8 on just the raw memset_l(). Most of the extra lines of code come from the three testcases I added. This patch (of 8): memset16(), memset32() and memset64() are like memset(), but allow the caller to fill the destination with a value larger than a single byte. memset_l() and memset_p() allow the caller to use unsigned long and pointer values respectively. Link: http://lkml.kernel.org/r/20170720184539.31609-2-willy@xxxxxxxxxxxxx Signed-off-by: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx> Cc: "H. Peter Anvin" <hpa@xxxxxxxxx> Cc: "James E.J. Bottomley" <jejb@xxxxxxxxxxxxxxxxxx> Cc: "Martin K. Petersen" <martin.petersen@xxxxxxxxxx> Cc: David Miller <davem@xxxxxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxx> Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx> Cc: Matt Turner <mattst88@xxxxxxxxx> Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx> Cc: Minchan Kim <minchan@xxxxxxxxxx> Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx> Cc: Richard Henderson <rth@xxxxxxxxxxx> Cc: Russell King <rmk+kernel@xxxxxxxxxxxxxxx> Cc: Sam Ravnborg <sam@xxxxxxxxxxxx> Cc: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Nobuhiro Iwamatsu (CIP) <nobuhiro1.iwamatsu@xxxxxxxxxxxxx> --- include/linux/string.h | 30 +++++++++++++++++++ lib/string.c | 66 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 96 insertions(+) diff --git a/include/linux/string.h b/include/linux/string.h index 66a91f5a344990..dd810d4739ee92 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -103,6 +103,36 @@ extern __kernel_size_t strcspn(const char *,const char *); #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif + +#ifndef __HAVE_ARCH_MEMSET16 +extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); +#endif + +static inline void *memset_l(unsigned long *p, unsigned long v, + __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, v, n); + else + return memset64((uint64_t *)p, v, n); +} + +static inline void *memset_p(void **p, void *v, __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, (uintptr_t)v, n); + else + return memset64((uint64_t *)p, (uintptr_t)v, n); +} + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif diff --git a/lib/string.c b/lib/string.c index 8fe13371aed7ad..ec1ba61b358f21 100644 --- a/lib/string.c +++ b/lib/string.c @@ -754,6 +754,72 @@ void memzero_explicit(void *s, size_t count) } EXPORT_SYMBOL(memzero_explicit); +#ifndef __HAVE_ARCH_MEMSET16 +/** + * memset16() - Fill a memory area with a uint16_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint16_t instead + * of a byte. Remember that @count is the number of uint16_ts to + * store, not the number of bytes. + */ +void *memset16(uint16_t *s, uint16_t v, size_t count) +{ + uint16_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset16); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +/** + * memset32() - Fill a memory area with a uint32_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint32_t instead + * of a byte. Remember that @count is the number of uint32_ts to + * store, not the number of bytes. + */ +void *memset32(uint32_t *s, uint32_t v, size_t count) +{ + uint32_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset32); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +/** + * memset64() - Fill a memory area with a uint64_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint64_t instead + * of a byte. Remember that @count is the number of uint64_ts to + * store, not the number of bytes. + */ +void *memset64(uint64_t *s, uint64_t v, size_t count) +{ + uint64_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset64); +#endif + #ifndef __HAVE_ARCH_MEMCPY /** * memcpy - Copy one area of memory to another -- 2.32.0
