OpenCloudOS-Kernel/arch/x86/lib/copy_user_64.S

346 lines
7.7 KiB
ArmAsm
Raw Normal View History

/*
* Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
* Copyright 2002 Andi Kleen, SuSE Labs.
* Subject to the GNU Public License v2.
*
* Functions to copy from and to user space.
*/
#include <linux/linkage.h>
#include <asm/current.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/export.h>
/*
* copy_user_generic_unrolled - memory copy with exception handling.
* This version is for CPUs like P4 that don't have efficient micro
* code for rep movsq
*
* Input:
* rdi destination
* rsi source
* rdx count
*
* Output:
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_unrolled)
ASM_STAC
cmpl $8,%edx
jb 20f /* less then 8 bytes, go to byte copy loop */
ALIGN_DESTINATION
movl %edx,%ecx
andl $63,%edx
shrl $6,%ecx
x86/uaccess: Optimize copy_user_enhanced_fast_string() for short strings According to the Intel datasheet, the REP MOVSB instruction exposes a pretty heavy setup cost (50 ticks), which hurts short string copy operations. This change tries to avoid this cost by calling the explicit loop available in the unrolled code for strings shorter than 64 bytes. The 64 bytes cutoff value is arbitrary from the code logic point of view - it has been selected based on measurements, as the largest value that still ensures a measurable gain. Micro benchmarks of the __copy_from_user() function with lengths in the [0-63] range show this performance gain (shorter the string, larger the gain): - in the [55%-4%] range on Intel Xeon(R) CPU E5-2690 v4 - in the [72%-9%] range on Intel Core i7-4810MQ Other tested CPUs - namely Intel Atom S1260 and AMD Opteron 8216 - show no difference, because they do not expose the ERMS feature bit. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/4533a1d101fd460f80e21329a34928fad521c1d4.1498744345.git.pabeni@redhat.com [ Clarified the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-29 21:55:58 +08:00
jz .L_copy_short_string
1: movq (%rsi),%r8
2: movq 1*8(%rsi),%r9
3: movq 2*8(%rsi),%r10
4: movq 3*8(%rsi),%r11
5: movq %r8,(%rdi)
6: movq %r9,1*8(%rdi)
7: movq %r10,2*8(%rdi)
8: movq %r11,3*8(%rdi)
9: movq 4*8(%rsi),%r8
10: movq 5*8(%rsi),%r9
11: movq 6*8(%rsi),%r10
12: movq 7*8(%rsi),%r11
13: movq %r8,4*8(%rdi)
14: movq %r9,5*8(%rdi)
15: movq %r10,6*8(%rdi)
16: movq %r11,7*8(%rdi)
leaq 64(%rsi),%rsi
leaq 64(%rdi),%rdi
decl %ecx
jnz 1b
x86/uaccess: Optimize copy_user_enhanced_fast_string() for short strings According to the Intel datasheet, the REP MOVSB instruction exposes a pretty heavy setup cost (50 ticks), which hurts short string copy operations. This change tries to avoid this cost by calling the explicit loop available in the unrolled code for strings shorter than 64 bytes. The 64 bytes cutoff value is arbitrary from the code logic point of view - it has been selected based on measurements, as the largest value that still ensures a measurable gain. Micro benchmarks of the __copy_from_user() function with lengths in the [0-63] range show this performance gain (shorter the string, larger the gain): - in the [55%-4%] range on Intel Xeon(R) CPU E5-2690 v4 - in the [72%-9%] range on Intel Core i7-4810MQ Other tested CPUs - namely Intel Atom S1260 and AMD Opteron 8216 - show no difference, because they do not expose the ERMS feature bit. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/4533a1d101fd460f80e21329a34928fad521c1d4.1498744345.git.pabeni@redhat.com [ Clarified the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-29 21:55:58 +08:00
.L_copy_short_string:
movl %edx,%ecx
andl $7,%edx
shrl $3,%ecx
jz 20f
18: movq (%rsi),%r8
19: movq %r8,(%rdi)
leaq 8(%rsi),%rsi
leaq 8(%rdi),%rdi
decl %ecx
jnz 18b
20: andl %edx,%edx
jz 23f
movl %edx,%ecx
21: movb (%rsi),%al
22: movb %al,(%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz 21b
23: xor %eax,%eax
ASM_CLAC
ret
.section .fixup,"ax"
30: shll $6,%ecx
addl %ecx,%edx
jmp 60f
40: leal (%rdx,%rcx,8),%edx
jmp 60f
50: movl %ecx,%edx
60: jmp copy_user_handle_tail /* ecx is zerorest also */
.previous
_ASM_EXTABLE(1b,30b)
_ASM_EXTABLE(2b,30b)
_ASM_EXTABLE(3b,30b)
_ASM_EXTABLE(4b,30b)
_ASM_EXTABLE(5b,30b)
_ASM_EXTABLE(6b,30b)
_ASM_EXTABLE(7b,30b)
_ASM_EXTABLE(8b,30b)
_ASM_EXTABLE(9b,30b)
_ASM_EXTABLE(10b,30b)
_ASM_EXTABLE(11b,30b)
_ASM_EXTABLE(12b,30b)
_ASM_EXTABLE(13b,30b)
_ASM_EXTABLE(14b,30b)
_ASM_EXTABLE(15b,30b)
_ASM_EXTABLE(16b,30b)
_ASM_EXTABLE(18b,40b)
_ASM_EXTABLE(19b,40b)
_ASM_EXTABLE(21b,50b)
_ASM_EXTABLE(22b,50b)
ENDPROC(copy_user_generic_unrolled)
EXPORT_SYMBOL(copy_user_generic_unrolled)
/* Some CPUs run faster using the string copy instructions.
* This is also a lot simpler. Use them when possible.
*
* Only 4GB of copy is supported. This shouldn't be a problem
* because the kernel normally only writes from/to page sized chunks
* even if user space passed a longer buffer.
* And more would be dangerous because both Intel and AMD have
* errata with rep movsq > 4GB. If someone feels the need to fix
* this please consider this.
*
* Input:
* rdi destination
* rsi source
* rdx count
*
* Output:
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_string)
ASM_STAC
cmpl $8,%edx
jb 2f /* less than 8 bytes, go to byte copy loop */
ALIGN_DESTINATION
movl %edx,%ecx
shrl $3,%ecx
andl $7,%edx
1: rep
movsq
2: movl %edx,%ecx
3: rep
movsb
xorl %eax,%eax
ASM_CLAC
ret
.section .fixup,"ax"
11: leal (%rdx,%rcx,8),%ecx
12: movl %ecx,%edx /* ecx is zerorest also */
jmp copy_user_handle_tail
.previous
_ASM_EXTABLE(1b,11b)
_ASM_EXTABLE(3b,12b)
ENDPROC(copy_user_generic_string)
EXPORT_SYMBOL(copy_user_generic_string)
/*
* Some CPUs are adding enhanced REP MOVSB/STOSB instructions.
* It's recommended to use enhanced REP MOVSB/STOSB if it's enabled.
*
* Input:
* rdi destination
* rsi source
* rdx count
*
* Output:
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_enhanced_fast_string)
ASM_STAC
x86/uaccess: Optimize copy_user_enhanced_fast_string() for short strings According to the Intel datasheet, the REP MOVSB instruction exposes a pretty heavy setup cost (50 ticks), which hurts short string copy operations. This change tries to avoid this cost by calling the explicit loop available in the unrolled code for strings shorter than 64 bytes. The 64 bytes cutoff value is arbitrary from the code logic point of view - it has been selected based on measurements, as the largest value that still ensures a measurable gain. Micro benchmarks of the __copy_from_user() function with lengths in the [0-63] range show this performance gain (shorter the string, larger the gain): - in the [55%-4%] range on Intel Xeon(R) CPU E5-2690 v4 - in the [72%-9%] range on Intel Core i7-4810MQ Other tested CPUs - namely Intel Atom S1260 and AMD Opteron 8216 - show no difference, because they do not expose the ERMS feature bit. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/4533a1d101fd460f80e21329a34928fad521c1d4.1498744345.git.pabeni@redhat.com [ Clarified the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-29 21:55:58 +08:00
cmpl $64,%edx
jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */
movl %edx,%ecx
1: rep
movsb
xorl %eax,%eax
ASM_CLAC
ret
.section .fixup,"ax"
12: movl %ecx,%edx /* ecx is zerorest also */
jmp copy_user_handle_tail
.previous
_ASM_EXTABLE(1b,12b)
ENDPROC(copy_user_enhanced_fast_string)
EXPORT_SYMBOL(copy_user_enhanced_fast_string)
/*
* copy_user_nocache - Uncached memory copy with exception handling
* This will force destination out of cache for more performance.
*
* Note: Cached memory copy is used when destination or size is not
* naturally aligned. That is:
* - Require 8-byte alignment when size is 8 bytes or larger.
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
* - Require 4-byte alignment when size is 4 bytes.
*/
ENTRY(__copy_user_nocache)
ASM_STAC
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
/* If size is less than 8 bytes, go to 4-byte copy */
cmpl $8,%edx
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
jb .L_4b_nocache_copy_entry
/* If destination is not 8-byte aligned, "cache" copy to align it */
ALIGN_DESTINATION
/* Set 4x8-byte copy count and remainder */
movl %edx,%ecx
andl $63,%edx
shrl $6,%ecx
jz .L_8b_nocache_copy_entry /* jump if count is 0 */
/* Perform 4x8-byte nocache loop-copy */
.L_4x8b_nocache_copy_loop:
1: movq (%rsi),%r8
2: movq 1*8(%rsi),%r9
3: movq 2*8(%rsi),%r10
4: movq 3*8(%rsi),%r11
5: movnti %r8,(%rdi)
6: movnti %r9,1*8(%rdi)
7: movnti %r10,2*8(%rdi)
8: movnti %r11,3*8(%rdi)
9: movq 4*8(%rsi),%r8
10: movq 5*8(%rsi),%r9
11: movq 6*8(%rsi),%r10
12: movq 7*8(%rsi),%r11
13: movnti %r8,4*8(%rdi)
14: movnti %r9,5*8(%rdi)
15: movnti %r10,6*8(%rdi)
16: movnti %r11,7*8(%rdi)
leaq 64(%rsi),%rsi
leaq 64(%rdi),%rdi
decl %ecx
jnz .L_4x8b_nocache_copy_loop
/* Set 8-byte copy count and remainder */
.L_8b_nocache_copy_entry:
movl %edx,%ecx
andl $7,%edx
shrl $3,%ecx
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
jz .L_4b_nocache_copy_entry /* jump if count is 0 */
/* Perform 8-byte nocache loop-copy */
.L_8b_nocache_copy_loop:
20: movq (%rsi),%r8
21: movnti %r8,(%rdi)
leaq 8(%rsi),%rsi
leaq 8(%rdi),%rdi
decl %ecx
jnz .L_8b_nocache_copy_loop
/* If no byte left, we're done */
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
.L_4b_nocache_copy_entry:
andl %edx,%edx
jz .L_finish_copy
/* If destination is not 4-byte aligned, go to byte copy: */
movl %edi,%ecx
andl $3,%ecx
jnz .L_1b_cache_copy_entry
/* Set 4-byte copy count (1 or 0) and remainder */
movl %edx,%ecx
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
andl $3,%edx
shrl $2,%ecx
jz .L_1b_cache_copy_entry /* jump if count is 0 */
/* Perform 4-byte nocache copy: */
30: movl (%rsi),%r8d
31: movnti %r8d,(%rdi)
leaq 4(%rsi),%rsi
leaq 4(%rdi),%rdi
/* If no bytes left, we're done: */
andl %edx,%edx
jz .L_finish_copy
/* Perform byte "cache" loop-copy for the remainder */
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
.L_1b_cache_copy_entry:
movl %edx,%ecx
.L_1b_cache_copy_loop:
40: movb (%rsi),%al
41: movb %al,(%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz .L_1b_cache_copy_loop
/* Finished copying; fence the prior stores */
.L_finish_copy:
xorl %eax,%eax
ASM_CLAC
sfence
ret
.section .fixup,"ax"
.L_fixup_4x8b_copy:
shll $6,%ecx
addl %ecx,%edx
jmp .L_fixup_handle_tail
.L_fixup_8b_copy:
lea (%rdx,%rcx,8),%rdx
jmp .L_fixup_handle_tail
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
.L_fixup_4b_copy:
lea (%rdx,%rcx,4),%rdx
jmp .L_fixup_handle_tail
.L_fixup_1b_copy:
movl %ecx,%edx
.L_fixup_handle_tail:
sfence
jmp copy_user_handle_tail
.previous
_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
_ASM_EXTABLE(20b,.L_fixup_8b_copy)
_ASM_EXTABLE(21b,.L_fixup_8b_copy)
x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com> Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: <stable@vger.kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 05:24:17 +08:00
_ASM_EXTABLE(30b,.L_fixup_4b_copy)
_ASM_EXTABLE(31b,.L_fixup_4b_copy)
_ASM_EXTABLE(40b,.L_fixup_1b_copy)
_ASM_EXTABLE(41b,.L_fixup_1b_copy)
ENDPROC(__copy_user_nocache)
EXPORT_SYMBOL(__copy_user_nocache)