linux/arch/x86/include/asm/uaccess_64.h
Dan Williams 0aed55af88 x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations
The pmem driver has a need to transfer data with a persistent memory
destination and be able to rely on the fact that the destination writes are not
cached. It is sufficient for the writes to be flushed to a cpu-store-buffer
(non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync()
to ensure data-writes have reached a power-fail-safe zone in the platform. The
fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn
around and fence previous writes with an "sfence".

Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and
memcpy_flushcache, that guarantee that the destination buffer is not dirty in
the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines
will be used to replace the "pmem api" (include/linux/pmem.h +
arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache()
and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
config symbol, and fallback to copy_from_iter_nocache() and plain memcpy()
otherwise.

This is meant to satisfy the concern from Linus that if a driver wants to do
something beyond the normal nocache semantics it should be something private to
that driver [1], and Al's concern that anything uaccess related belongs with
the rest of the uaccess code [2].

The first consumer of this interface is a new 'copy_from_iter' dax operation so
that pmem can inject cache maintenance operations without imposing this
overhead on other dax-capable drivers.

[1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html
[2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html

Cc: <x86@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-06-09 09:09:56 -07:00

197 lines
5.2 KiB
C

#ifndef _ASM_X86_UACCESS_64_H
#define _ASM_X86_UACCESS_64_H
/*
* User space memory access functions
*/
#include <linux/compiler.h>
#include <linux/lockdep.h>
#include <linux/kasan-checks.h>
#include <asm/alternative.h>
#include <asm/cpufeatures.h>
#include <asm/page.h>
/*
* Copy To/From Userspace
*/
/* Handles exceptions in both to and from, but doesn't do access_ok */
__must_check unsigned long
copy_user_enhanced_fast_string(void *to, const void *from, unsigned len);
__must_check unsigned long
copy_user_generic_string(void *to, const void *from, unsigned len);
__must_check unsigned long
copy_user_generic_unrolled(void *to, const void *from, unsigned len);
static __always_inline __must_check unsigned long
copy_user_generic(void *to, const void *from, unsigned len)
{
unsigned ret;
/*
* If CPU has ERMS feature, use copy_user_enhanced_fast_string.
* Otherwise, if CPU has rep_good feature, use copy_user_generic_string.
* Otherwise, use copy_user_generic_unrolled.
*/
alternative_call_2(copy_user_generic_unrolled,
copy_user_generic_string,
X86_FEATURE_REP_GOOD,
copy_user_enhanced_fast_string,
X86_FEATURE_ERMS,
ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from),
"=d" (len)),
"1" (to), "2" (from), "3" (len)
: "memory", "rcx", "r8", "r9", "r10", "r11");
return ret;
}
static __always_inline __must_check unsigned long
raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
{
int ret = 0;
if (!__builtin_constant_p(size))
return copy_user_generic(dst, (__force void *)src, size);
switch (size) {
case 1:
__uaccess_begin();
__get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src,
ret, "b", "b", "=q", 1);
__uaccess_end();
return ret;
case 2:
__uaccess_begin();
__get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src,
ret, "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 4:
__uaccess_begin();
__get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
ret, "l", "k", "=r", 4);
__uaccess_end();
return ret;
case 8:
__uaccess_begin();
__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 8);
__uaccess_end();
return ret;
case 10:
__uaccess_begin();
__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 10);
if (likely(!ret))
__get_user_asm_nozero(*(u16 *)(8 + (char *)dst),
(u16 __user *)(8 + (char __user *)src),
ret, "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 16:
__uaccess_begin();
__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 16);
if (likely(!ret))
__get_user_asm_nozero(*(u64 *)(8 + (char *)dst),
(u64 __user *)(8 + (char __user *)src),
ret, "q", "", "=r", 8);
__uaccess_end();
return ret;
default:
return copy_user_generic(dst, (__force void *)src, size);
}
}
static __always_inline __must_check unsigned long
raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
{
int ret = 0;
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst, src, size);
switch (size) {
case 1:
__uaccess_begin();
__put_user_asm(*(u8 *)src, (u8 __user *)dst,
ret, "b", "b", "iq", 1);
__uaccess_end();
return ret;
case 2:
__uaccess_begin();
__put_user_asm(*(u16 *)src, (u16 __user *)dst,
ret, "w", "w", "ir", 2);
__uaccess_end();
return ret;
case 4:
__uaccess_begin();
__put_user_asm(*(u32 *)src, (u32 __user *)dst,
ret, "l", "k", "ir", 4);
__uaccess_end();
return ret;
case 8:
__uaccess_begin();
__put_user_asm(*(u64 *)src, (u64 __user *)dst,
ret, "q", "", "er", 8);
__uaccess_end();
return ret;
case 10:
__uaccess_begin();
__put_user_asm(*(u64 *)src, (u64 __user *)dst,
ret, "q", "", "er", 10);
if (likely(!ret)) {
asm("":::"memory");
__put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst,
ret, "w", "w", "ir", 2);
}
__uaccess_end();
return ret;
case 16:
__uaccess_begin();
__put_user_asm(*(u64 *)src, (u64 __user *)dst,
ret, "q", "", "er", 16);
if (likely(!ret)) {
asm("":::"memory");
__put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
ret, "q", "", "er", 8);
}
__uaccess_end();
return ret;
default:
return copy_user_generic((__force void *)dst, src, size);
}
}
static __always_inline __must_check
unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size)
{
return copy_user_generic((__force void *)dst,
(__force void *)src, size);
}
extern long __copy_user_nocache(void *dst, const void __user *src,
unsigned size, int zerorest);
extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
size_t len);
static inline int
__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
unsigned size)
{
kasan_check_write(dst, size);
return __copy_user_nocache(dst, src, size, 0);
}
static inline int
__copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
{
kasan_check_write(dst, size);
return __copy_user_flushcache(dst, src, size);
}
unsigned long
copy_user_handle_tail(char *to, char *from, unsigned len);
#endif /* _ASM_X86_UACCESS_64_H */