crypto: x86/sha256-mb - fix panic due to unaligned access

struct sha256_ctx_mgr allocated in sha256_mb_mod_init() via kzalloc()
and later passed in sha256_mb_flusher_mgr_flush_avx2() function where
instructions vmovdqa used to access the struct. vmovdqa requires
16-bytes aligned argument, but nothing guarantees that struct
sha256_ctx_mgr will have that alignment. Unaligned vmovdqa will
generate GP fault.

Fix this by replacing vmovdqa with vmovdqu which doesn't have alignment
requirements.

Fixes: a377c6b1876e ("crypto: sha256-mb - submit/flush routines for AVX2")
Reported-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: <stable@vger.kernel.org>
Acked-by: Tim Chen
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index 8fe6338bcc845713338531694e3ed54fdf483662..16c4ccb1f154883017062c90d7ca0fc22dc67e29 100644 (file)
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -155,8 +155,8 @@ LABEL skip_ %I
 .endr
 
        # Find min length
-       vmovdqa _lens+0*16(state), %xmm0
-       vmovdqa _lens+1*16(state), %xmm1
+       vmovdqu _lens+0*16(state), %xmm0
+       vmovdqu _lens+1*16(state), %xmm1
 
        vpminud %xmm1, %xmm0, %xmm2             # xmm2 has {D,C,B,A}
        vpalignr $8, %xmm2, %xmm3, %xmm3        # xmm3 has {x,x,D,C}
@@ -176,8 +176,8 @@ LABEL skip_ %I
        vpsubd  %xmm2, %xmm0, %xmm0
        vpsubd  %xmm2, %xmm1, %xmm1
 
-       vmovdqa %xmm0, _lens+0*16(state)
-       vmovdqa %xmm1, _lens+1*16(state)
+       vmovdqu %xmm0, _lens+0*16(state)
+       vmovdqu %xmm1, _lens+1*16(state)
 
        # "state" and "args" are the same address, arg1
        # len is arg2
@@ -234,8 +234,8 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2)
        jc      .return_null
 
        # Find min length
-       vmovdqa _lens(state), %xmm0
-       vmovdqa _lens+1*16(state), %xmm1
+       vmovdqu _lens(state), %xmm0
+       vmovdqu _lens+1*16(state), %xmm1
 
        vpminud %xmm1, %xmm0, %xmm2             # xmm2 has {D,C,B,A}
        vpalignr $8, %xmm2, %xmm3, %xmm3        # xmm3 has {x,x,D,C}