Boaz Harrosh wrote on 2016-10-26:
> On 10/26/2016 06:50 PM, Brian Boylston wrote:
>> Introduce memcpy_nocache() as a memcpy() that avoids the processor cache
>> if possible. Without arch-specific support, this defaults to just
>> memcpy(). For now, include arch-specific support for x86.
>>
>> Cc: Ross Zwisler <ross.zwis...@linux.intel.com>
>> Cc: Thomas Gleixner <t...@linutronix.de>
>> Cc: Ingo Molnar <mi...@redhat.com>
>> Cc: "H. Peter Anvin" <h...@zytor.com>
>> Cc: <x...@kernel.org>
>> Cc: Al Viro <v...@zeniv.linux.org.uk>
>> Cc: Dan Williams <dan.j.willi...@intel.com>
>> Signed-off-by: Brian Boylston <brian.boyls...@hpe.com>
>> Reviewed-by: Toshi Kani <toshi.k...@hpe.com>
>> Reported-by: Oliver Moreno <oliver.mor...@hpe.com>
>> ---
>> arch/x86/include/asm/string_32.h | 3 +++
>> arch/x86/include/asm/string_64.h | 3 +++
>> arch/x86/lib/misc.c | 12 ++++++++++++
>> include/linux/string.h | 15 +++++++++++++++
>> 4 files changed, 33 insertions(+)
>> diff --git a/arch/x86/include/asm/string_32.h
>> b/arch/x86/include/asm/string_32.h
>> index 3d3e835..64f80c0 100644
>> --- a/arch/x86/include/asm/string_32.h
>> +++ b/arch/x86/include/asm/string_32.h
>> @@ -196,6 +196,9 @@ static inline void *__memcpy3d(void *to, const void
>> *from, size_t len)
>>
>> #endif
>> +#define __HAVE_ARCH_MEMCPY_NOCACHE
>> +extern void *memcpy_nocache(void *dest, const void *src, size_t count);
>> +
>> #define __HAVE_ARCH_MEMMOVE
>> void *memmove(void *dest, const void *src, size_t n);
>> diff --git a/arch/x86/include/asm/string_64.h
>> b/arch/x86/include/asm/string_64.h
>> index 90dbbd9..a8fdd55 100644
>> --- a/arch/x86/include/asm/string_64.h
>> +++ b/arch/x86/include/asm/string_64.h
>> @@ -51,6 +51,9 @@ extern void *__memcpy(void *to, const void *from, size_t
>> len);
>> #define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
>> #endif
>> +#define __HAVE_ARCH_MEMCPY_NOCACHE
>> +extern void *memcpy_nocache(void *dest, const void *src, size_t count);
>> +
>> #define __HAVE_ARCH_MEMSET
>> void *memset(void *s, int c, size_t n);
>> void *__memset(void *s, int c, size_t n);
>> diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c
>> index 76b373a..c993ab3 100644
>> --- a/arch/x86/lib/misc.c
>> +++ b/arch/x86/lib/misc.c
>> @@ -1,3 +1,6 @@
>> +#include <linux/export.h>
>> +#include <linux/uaccess.h>
>> +
>> /*
>> * Count the digits of @val including a possible sign.
>> *
>> @@ -19,3 +22,12 @@ int num_digits(int val)
>> }
>> return d;
>> }
>> +
>> +#ifdef __HAVE_ARCH_MEMCPY_NOCACHE
>> +void *memcpy_nocache(void *dest, const void *src, size_t count)
>> +{
>> + __copy_from_user_inatomic_nocache(dest, src, count);
>> + return dest;
>> +}
>> +EXPORT_SYMBOL(memcpy_nocache);
>> +#endif
>> diff --git a/include/linux/string.h b/include/linux/string.h
>> index 26b6f6a..7f40c41 100644
>> --- a/include/linux/string.h
>> +++ b/include/linux/string.h
>> @@ -102,6 +102,21 @@ extern void * memset(void *,int,__kernel_size_t);
>> #ifndef __HAVE_ARCH_MEMCPY
>> extern void * memcpy(void *,const void *,__kernel_size_t);
>> #endif
>> +
>> +#ifndef __HAVE_ARCH_MEMCPY_NOCACHE
>> +/**
>> + * memcpy_nocache - Copy one area of memory to another, avoiding the
>> + * processor cache if possible
>> + * @dest: Where to copy to
>> + * @src: Where to copy from
>> + * @count: The size of the area.
>> + */
>> +static inline void *memcpy_nocache(void *dest, const void *src, size_t
>> count)
>> +{
>> + return memcpy(dest, src, count);
>> +}
>
> What about memcpy_to_pmem() in linux/pmem.h it already has all the arch
> switches.
>
> Feels bad to add yet just another arch switch over __copy_user_nocache
>
> Just feels like too many things that do the same thing. Sigh
I agree that this looks like a nicer path.
I had considered adjusting copy_from_iter_nocache() to use memcpy_to_pmem(),
but lib/iov_iter.c doesn't currently #include linux/pmem.h. Would it be
acceptable to add it? Also, I wasn't sure if memcpy_to_pmem() would always
mean exactly "memcpy nocache".
I had also considered adjusting copy_from_iter_pmem() (also in linux/pmem.h)
to just use memcpy_to_pmem() directly, but then it can't use the goodness
that is the iterate_and_advance() macro in iov_iter.c.
So, I took a shot with a possibly ill-fated memcpy_nocache(). Thoughts on
either of the above two? Are these even in line with what you were thinking?
Thanks!
Brian
>
> Boaz
>
>> +#endif
>> +
>> #ifndef __HAVE_ARCH_MEMMOVE
>> extern void * memmove(void *,const void *,__kernel_size_t);
>> #endif
