crypto: x86/sha256-avx2 - Fix RBP usage

Using RBP as a temporary register breaks frame pointer convention and
breaks stack traces when unwinding from an interrupt in the crypto code.

There's no need to use RBP as a temporary register for the TBL value,
because it always stores the same value: the address of the K256 table.
Instead just reference the address of K256 directly.

Reported-by: Eric Biggers <ebiggers@google.com>
Reported-by: Peter Zijlstra <peterz@infradead.org>
Tested-by: Eric Biggers <ebiggers@google.com>
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 7 insertions, 15 deletions

diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 89c8f09787d2..1420db15dcdd 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -98,8 +98,6 @@ d	= %r8d
 e       = %edx  # clobbers NUM_BLKS
 y3      = %esi  # clobbers INP
 
-
-TBL     = %rbp
 SRND    = CTX   # SRND is same register as CTX
 
 a = %eax
@@ -531,7 +529,6 @@ STACK_SIZE	= _RSP      + _RSP_SIZE
 ENTRY(sha256_transform_rorx)
 .align 32
         pushq   %rbx
-        pushq   %rbp
         pushq   %r12
         pushq   %r13
         pushq   %r14
@@ -568,8 +565,6 @@ ENTRY(sha256_transform_rorx)
         mov     CTX, _CTX(%rsp)
 
 loop0:
-        lea     K256(%rip), TBL
-
         ## Load first 16 dwords from two blocks
         VMOVDQ  0*32(INP),XTMP0
         VMOVDQ  1*32(INP),XTMP1
@@ -597,19 +592,19 @@ last_block_enter:
 
 .align 16
 loop1:
-        vpaddd  0*32(TBL, SRND), X0, XFER
+        vpaddd  K256+0*32(SRND), X0, XFER
         vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
         FOUR_ROUNDS_AND_SCHED   _XFER + 0*32
 
-        vpaddd  1*32(TBL, SRND), X0, XFER
+        vpaddd  K256+1*32(SRND), X0, XFER
         vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
         FOUR_ROUNDS_AND_SCHED   _XFER + 1*32
 
-        vpaddd  2*32(TBL, SRND), X0, XFER
+        vpaddd  K256+2*32(SRND), X0, XFER
         vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
         FOUR_ROUNDS_AND_SCHED   _XFER + 2*32
 
-        vpaddd  3*32(TBL, SRND), X0, XFER
+        vpaddd  K256+3*32(SRND), X0, XFER
         vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
         FOUR_ROUNDS_AND_SCHED   _XFER + 3*32
 
@@ -619,10 +614,11 @@ loop1:
 
 loop2:
         ## Do last 16 rounds with no scheduling
-        vpaddd  0*32(TBL, SRND), X0, XFER
+        vpaddd  K256+0*32(SRND), X0, XFER
         vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
         DO_4ROUNDS      _XFER + 0*32
-        vpaddd  1*32(TBL, SRND), X1, XFER
+
+        vpaddd  K256+1*32(SRND), X1, XFER
         vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
         DO_4ROUNDS      _XFER + 1*32
         add     $2*32, SRND
@@ -676,9 +672,6 @@ loop3:
         ja      done_hash
 
 do_last_block:
-        #### do last block
-        lea     K256(%rip), TBL
-
         VMOVDQ  0*16(INP),XWORD0
         VMOVDQ  1*16(INP),XWORD1
         VMOVDQ  2*16(INP),XWORD2
@@ -718,7 +711,6 @@ done_hash:
         popq    %r14
         popq    %r13
         popq    %r12
-        popq    %rbp
         popq    %rbx
         ret
 ENDPROC(sha256_transform_rorx)