diff options
author | Toshi Kani <toshi.kani@hpe.com> | 2016-02-11 14:24:17 -0700 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2016-02-17 09:10:23 +0100 |
commit | a82eee7424525e34e98d821dd059ce14560a1e35 (patch) | |
tree | cfbee28f966b7fcf625c70d0fc0b62a16012307a | |
parent | ee9737c924706aaa72c2ead93e3ad5644681dc1c (diff) | |
download | op-kernel-dev-a82eee7424525e34e98d821dd059ce14560a1e35.zip op-kernel-dev-a82eee7424525e34e98d821dd059ce14560a1e35.tar.gz |
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>
-rw-r--r-- | arch/x86/lib/copy_user_64.S | 36 |
1 files changed, 32 insertions, 4 deletions
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index a644aad..27f89c7 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -237,13 +237,14 @@ ENDPROC(copy_user_enhanced_fast_string) * 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. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC - /* If size is less than 8 bytes, go to byte copy */ + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb .L_1b_cache_copy_entry + jb .L_4b_nocache_copy_entry /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION @@ -282,7 +283,7 @@ ENTRY(__copy_user_nocache) movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz .L_1b_cache_copy_entry /* jump if count is 0 */ + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ /* Perform 8-byte nocache loop-copy */ .L_8b_nocache_copy_loop: @@ -294,11 +295,33 @@ ENTRY(__copy_user_nocache) jnz .L_8b_nocache_copy_loop /* If no byte left, we're done */ -.L_1b_cache_copy_entry: +.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 + 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 */ +.L_1b_cache_copy_entry: movl %edx,%ecx .L_1b_cache_copy_loop: 40: movb (%rsi),%al @@ -323,6 +346,9 @@ ENTRY(__copy_user_nocache) .L_fixup_8b_copy: lea (%rdx,%rcx,8),%rdx jmp .L_fixup_handle_tail +.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: @@ -348,6 +374,8 @@ ENTRY(__copy_user_nocache) _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) _ASM_EXTABLE(20b,.L_fixup_8b_copy) _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _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) |