[PATCH v3 2/2] x86/lib/copy_user_64.S: Handle 4-byte nocache copy

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(a)hpe.com&gt; Reported-and-tested-by: Brian Boylston <brian.boylston(a)hpe.com&gt; Signed-off-by: Toshi Kani <toshi.kani(a)hpe.com&gt; Cc: Thomas Gleixner <tglx(a)linutronix.de&gt; Cc: Ingo Molnar <mingo(a)redhat.com&gt; Cc: H. Peter Anvin <hpa(a)zytor.com&gt; Cc: Borislav Petkov <bp(a)suse.de&gt; Cc: Dan Williams <dan.j.williams(a)intel.com&gt; Cc: Ross Zwisler <ross.zwisler(a)linux.intel.com&gt; Cc: Vishal Verma <vishal.l.verma(a)intel.com&gt; --- arch/x86/lib/copy_user_64.S | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 23042ff..9228ce6 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, goto byte copy */ + /* If size is less than 8 bytes, goto 4-byte copy */ cmpl $8,%edx - jb .Lcun_1b_cache_copy_entry + jb .Lcun_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 .Lcun_1b_cache_copy_entry /* jump if count is 0 */ + jz .Lcun_4b_nocache_copy_entry /* jump if count is 0 */ /* Perform 8-byte nocache loop-copy */ .Lcun_8b_nocache_copy_loop: @@ -294,11 +295,33 @@ ENTRY(__copy_user_nocache) jnz .Lcun_8b_nocache_copy_loop /* If no byte left, we're done */ -.Lcun_1b_cache_copy_entry: +.Lcun_4b_nocache_copy_entry: + andl %edx,%edx + jz .Lcun_finish_copy + + /* If destination is not 4-byte aligned, goto byte copy */ + movl %edi,%ecx + andl $3,%ecx + jnz .Lcun_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ + movl %edx,%ecx + andl $3,%edx + shrl $2,%ecx + jz .Lcun_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 byte left, we're done */ andl %edx,%edx jz .Lcun_finish_copy /* Perform byte "cache" loop-copy for the remainder */ +.Lcun_1b_cache_copy_entry: movl %edx,%ecx .Lcun_1b_cache_copy_loop: 40: movb (%rsi),%al @@ -323,6 +346,9 @@ ENTRY(__copy_user_nocache) .Lcun_fixup_8b_copy: lea (%rdx,%rcx,8),%rdx jmp .Lcun_fixup_handle_tail +.Lcun_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .Lcun_fixup_handle_tail .Lcun_fixup_1b_copy: movl %ecx,%edx .Lcun_fixup_handle_tail: @@ -348,6 +374,8 @@ ENTRY(__copy_user_nocache) _ASM_EXTABLE(16b,.Lcun_fixup_4x8b_copy) _ASM_EXTABLE(20b,.Lcun_fixup_8b_copy) _ASM_EXTABLE(21b,.Lcun_fixup_8b_copy) + _ASM_EXTABLE(30b,.Lcun_fixup_4b_copy) + _ASM_EXTABLE(31b,.Lcun_fixup_4b_copy) _ASM_EXTABLE(40b,.Lcun_fixup_1b_copy) _ASM_EXTABLE(41b,.Lcun_fixup_1b_copy) ENDPROC(__copy_user_nocache)