Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto fixes from Herbert Xu:

 - Check for the right CPU feature bit in sm4-ce on arm64.

 - Fix scatterwalk WARN_ON in aes-gcm-ce on arm64.

 - Fix unaligned fault in aesni on x86.

 - Fix potential NULL pointer dereference on exit in chtls.

 - Fix DMA mapping direction for RSA in caam.

 - Fix error path return value for xts setkey in caam.

 - Fix address endianness when DMA unmapping in caam.

 - Fix sleep-in-atomic in vmx.

 - Fix command corruption when queue is full in cavium/nitrox.

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
  crypto: cavium/nitrox - fix for command corruption in queue full case with backlog submissions.
  crypto: vmx - Fix sleep-in-atomic bugs
  crypto: arm64/aes-gcm-ce - fix scatterwalk API violation
  crypto: aesni - Use unaligned loads from gcm_context_data
  crypto: chtls - fix null dereference chtls_free_uld()
  crypto: arm64/sm4-ce - check for the right CPU feature bit
  crypto: caam - fix DMA mapping direction for RSA forms 2 & 3
  crypto: caam/qi - fix error path in xts setkey
  crypto: caam/jr - fix descriptor DMA unmapping

diff --combined arch/x86/crypto/aesni-intel_asm.S
index 9bd1395,d27a506..cb2deb6
--- 1/arch/x86/crypto/aesni-intel_asm.S
--- 2/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@@ -223,34 -223,34 +223,34 @@@ ALL_F:      .octa 0xfffffffffffffffffff
        pcmpeqd TWOONE(%rip), \TMP2
        pand    POLY(%rip), \TMP2
        pxor    \TMP2, \TMP3
-       movdqa  \TMP3, HashKey(%arg2)
+       movdqu  \TMP3, HashKey(%arg2)
  
        movdqa     \TMP3, \TMP5
        pshufd     $78, \TMP3, \TMP1
        pxor       \TMP3, \TMP1
-       movdqa     \TMP1, HashKey_k(%arg2)
+       movdqu     \TMP1, HashKey_k(%arg2)
  
        GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
  # TMP5 = HashKey^2<<1 (mod poly)
-       movdqa     \TMP5, HashKey_2(%arg2)
+       movdqu     \TMP5, HashKey_2(%arg2)
  # HashKey_2 = HashKey^2<<1 (mod poly)
        pshufd     $78, \TMP5, \TMP1
        pxor       \TMP5, \TMP1
-       movdqa     \TMP1, HashKey_2_k(%arg2)
+       movdqu     \TMP1, HashKey_2_k(%arg2)
  
        GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
  # TMP5 = HashKey^3<<1 (mod poly)
-       movdqa     \TMP5, HashKey_3(%arg2)
+       movdqu     \TMP5, HashKey_3(%arg2)
        pshufd     $78, \TMP5, \TMP1
        pxor       \TMP5, \TMP1
-       movdqa     \TMP1, HashKey_3_k(%arg2)
+       movdqu     \TMP1, HashKey_3_k(%arg2)
  
        GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
  # TMP5 = HashKey^3<<1 (mod poly)
-       movdqa     \TMP5, HashKey_4(%arg2)
+       movdqu     \TMP5, HashKey_4(%arg2)
        pshufd     $78, \TMP5, \TMP1
        pxor       \TMP5, \TMP1
-       movdqa     \TMP1, HashKey_4_k(%arg2)
+       movdqu     \TMP1, HashKey_4_k(%arg2)
  .endm
  
  # GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding.
@@@ -258,7 -258,7 +258,7 @@@
  .macro GCM_INIT Iv SUBKEY AAD AADLEN
        mov \AADLEN, %r11
        mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
 -      xor %r11, %r11
 +      xor %r11d, %r11d
        mov %r11, InLen(%arg2) # ctx_data.in_length = 0
        mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
        mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
@@@ -271,7 -271,7 +271,7 @@@
        movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
  
        PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
-       movdqa HashKey(%arg2), %xmm13
+       movdqu HashKey(%arg2), %xmm13
  
        CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
        %xmm4, %xmm5, %xmm6
@@@ -286,7 -286,7 +286,7 @@@
        movdqu HashKey(%arg2), %xmm13
        add %arg5, InLen(%arg2)
  
 -      xor %r11, %r11 # initialise the data pointer offset as zero
 +      xor %r11d, %r11d # initialise the data pointer offset as zero
        PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
  
        sub %r11, %arg5         # sub partial block data used
@@@ -702,7 -702,7 +702,7 @@@ _no_extra_mask_1_\@
  
        # GHASH computation for the last <16 Byte block
        GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
 -      xor     %rax,%rax
 +      xor     %eax, %eax
  
        mov     %rax, PBlockLen(%arg2)
        jmp     _dec_done_\@
@@@ -737,7 -737,7 +737,7 @@@ _no_extra_mask_2_\@
  
        # GHASH computation for the last <16 Byte block
        GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
 -      xor     %rax,%rax
 +      xor     %eax, %eax
  
        mov     %rax, PBlockLen(%arg2)
        jmp     _encode_done_\@
@@@ -997,7 -997,7 +997,7 @@@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM
        pshufd    $78, \XMM5, \TMP6
        pxor      \XMM5, \TMP6
        paddd     ONE(%rip), \XMM0              # INCR CNT
-       movdqa    HashKey_4(%arg2), \TMP5
+       movdqu    HashKey_4(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
        movdqa    \XMM0, \XMM1
        paddd     ONE(%rip), \XMM0              # INCR CNT
@@@ -1016,7 -1016,7 +1016,7 @@@
        pxor      (%arg1), \XMM2
        pxor      (%arg1), \XMM3
        pxor      (%arg1), \XMM4
-       movdqa    HashKey_4_k(%arg2), \TMP5
+       movdqu    HashKey_4_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
        movaps 0x10(%arg1), \TMP1
        AESENC    \TMP1, \XMM1              # Round 1
@@@ -1031,7 -1031,7 +1031,7 @@@
        movdqa    \XMM6, \TMP1
        pshufd    $78, \XMM6, \TMP2
        pxor      \XMM6, \TMP2
-       movdqa    HashKey_3(%arg2), \TMP5
+       movdqu    HashKey_3(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
        movaps 0x30(%arg1), \TMP3
        AESENC    \TMP3, \XMM1              # Round 3
@@@ -1044,7 -1044,7 +1044,7 @@@
        AESENC    \TMP3, \XMM2
        AESENC    \TMP3, \XMM3
        AESENC    \TMP3, \XMM4
-       movdqa    HashKey_3_k(%arg2), \TMP5
+       movdqu    HashKey_3_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
        movaps 0x50(%arg1), \TMP3
        AESENC    \TMP3, \XMM1              # Round 5
@@@ -1058,7 -1058,7 +1058,7 @@@
        movdqa    \XMM7, \TMP1
        pshufd    $78, \XMM7, \TMP2
        pxor      \XMM7, \TMP2
-       movdqa    HashKey_2(%arg2), \TMP5
+       movdqu    HashKey_2(%arg2), \TMP5
  
          # Multiply TMP5 * HashKey using karatsuba
  
@@@ -1074,7 -1074,7 +1074,7 @@@
        AESENC    \TMP3, \XMM2
        AESENC    \TMP3, \XMM3
        AESENC    \TMP3, \XMM4
-       movdqa    HashKey_2_k(%arg2), \TMP5
+       movdqu    HashKey_2_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
        movaps 0x80(%arg1), \TMP3
        AESENC    \TMP3, \XMM1             # Round 8
@@@ -1092,7 -1092,7 +1092,7 @@@
        movdqa    \XMM8, \TMP1
        pshufd    $78, \XMM8, \TMP2
        pxor      \XMM8, \TMP2
-       movdqa    HashKey(%arg2), \TMP5
+       movdqu    HashKey(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
        movaps 0x90(%arg1), \TMP3
        AESENC    \TMP3, \XMM1            # Round 9
@@@ -1121,7 -1121,7 +1121,7 @@@ aes_loop_par_enc_done\@
        AESENCLAST \TMP3, \XMM2
        AESENCLAST \TMP3, \XMM3
        AESENCLAST \TMP3, \XMM4
-       movdqa    HashKey_k(%arg2), \TMP5
+       movdqu    HashKey_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
        movdqu    (%arg4,%r11,1), \TMP3
        pxor      \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
@@@ -1205,7 -1205,7 +1205,7 @@@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM
        pshufd    $78, \XMM5, \TMP6
        pxor      \XMM5, \TMP6
        paddd     ONE(%rip), \XMM0              # INCR CNT
-       movdqa    HashKey_4(%arg2), \TMP5
+       movdqu    HashKey_4(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
        movdqa    \XMM0, \XMM1
        paddd     ONE(%rip), \XMM0              # INCR CNT
@@@ -1224,7 -1224,7 +1224,7 @@@
        pxor      (%arg1), \XMM2
        pxor      (%arg1), \XMM3
        pxor      (%arg1), \XMM4
-       movdqa    HashKey_4_k(%arg2), \TMP5
+       movdqu    HashKey_4_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
        movaps 0x10(%arg1), \TMP1
        AESENC    \TMP1, \XMM1              # Round 1
@@@ -1239,7 -1239,7 +1239,7 @@@
        movdqa    \XMM6, \TMP1
        pshufd    $78, \XMM6, \TMP2
        pxor      \XMM6, \TMP2
-       movdqa    HashKey_3(%arg2), \TMP5
+       movdqu    HashKey_3(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
        movaps 0x30(%arg1), \TMP3
        AESENC    \TMP3, \XMM1              # Round 3
@@@ -1252,7 -1252,7 +1252,7 @@@
        AESENC    \TMP3, \XMM2
        AESENC    \TMP3, \XMM3
        AESENC    \TMP3, \XMM4
-       movdqa    HashKey_3_k(%arg2), \TMP5
+       movdqu    HashKey_3_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
        movaps 0x50(%arg1), \TMP3
        AESENC    \TMP3, \XMM1              # Round 5
@@@ -1266,7 -1266,7 +1266,7 @@@
        movdqa    \XMM7, \TMP1
        pshufd    $78, \XMM7, \TMP2
        pxor      \XMM7, \TMP2
-       movdqa    HashKey_2(%arg2), \TMP5
+       movdqu    HashKey_2(%arg2), \TMP5
  
          # Multiply TMP5 * HashKey using karatsuba
  
@@@ -1282,7 -1282,7 +1282,7 @@@
        AESENC    \TMP3, \XMM2
        AESENC    \TMP3, \XMM3
        AESENC    \TMP3, \XMM4
-       movdqa    HashKey_2_k(%arg2), \TMP5
+       movdqu    HashKey_2_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
        movaps 0x80(%arg1), \TMP3
        AESENC    \TMP3, \XMM1             # Round 8
@@@ -1300,7 -1300,7 +1300,7 @@@
        movdqa    \XMM8, \TMP1
        pshufd    $78, \XMM8, \TMP2
        pxor      \XMM8, \TMP2
-       movdqa    HashKey(%arg2), \TMP5
+       movdqu    HashKey(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
        movaps 0x90(%arg1), \TMP3
        AESENC    \TMP3, \XMM1            # Round 9
@@@ -1329,7 -1329,7 +1329,7 @@@ aes_loop_par_dec_done\@
        AESENCLAST \TMP3, \XMM2
        AESENCLAST \TMP3, \XMM3
        AESENCLAST \TMP3, \XMM4
-       movdqa    HashKey_k(%arg2), \TMP5
+       movdqu    HashKey_k(%arg2), \TMP5
        PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
        movdqu    (%arg4,%r11,1), \TMP3
        pxor      \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
@@@ -1405,10 -1405,10 +1405,10 @@@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDs
        movdqa    \XMM1, \TMP6
        pshufd    $78, \XMM1, \TMP2
        pxor      \XMM1, \TMP2
-       movdqa    HashKey_4(%arg2), \TMP5
+       movdqu    HashKey_4(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP6       # TMP6 = a1*b1
        PCLMULQDQ 0x00, \TMP5, \XMM1       # XMM1 = a0*b0
-       movdqa    HashKey_4_k(%arg2), \TMP4
+       movdqu    HashKey_4_k(%arg2), \TMP4
        PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
        movdqa    \XMM1, \XMMDst
        movdqa    \TMP2, \XMM1              # result in TMP6, XMMDst, XMM1
@@@ -1418,10 -1418,10 +1418,10 @@@
        movdqa    \XMM2, \TMP1
        pshufd    $78, \XMM2, \TMP2
        pxor      \XMM2, \TMP2
-       movdqa    HashKey_3(%arg2), \TMP5
+       movdqu    HashKey_3(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
        PCLMULQDQ 0x00, \TMP5, \XMM2       # XMM2 = a0*b0
-       movdqa    HashKey_3_k(%arg2), \TMP4
+       movdqu    HashKey_3_k(%arg2), \TMP4
        PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
        pxor      \TMP1, \TMP6
        pxor      \XMM2, \XMMDst
@@@ -1433,10 -1433,10 +1433,10 @@@
        movdqa    \XMM3, \TMP1
        pshufd    $78, \XMM3, \TMP2
        pxor      \XMM3, \TMP2
-       movdqa    HashKey_2(%arg2), \TMP5
+       movdqu    HashKey_2(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
        PCLMULQDQ 0x00, \TMP5, \XMM3       # XMM3 = a0*b0
-       movdqa    HashKey_2_k(%arg2), \TMP4
+       movdqu    HashKey_2_k(%arg2), \TMP4
        PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
        pxor      \TMP1, \TMP6
        pxor      \XMM3, \XMMDst
@@@ -1446,10 -1446,10 +1446,10 @@@
        movdqa    \XMM4, \TMP1
        pshufd    $78, \XMM4, \TMP2
        pxor      \XMM4, \TMP2
-       movdqa    HashKey(%arg2), \TMP5
+       movdqu    HashKey(%arg2), \TMP5
        PCLMULQDQ 0x11, \TMP5, \TMP1        # TMP1 = a1*b1
        PCLMULQDQ 0x00, \TMP5, \XMM4       # XMM4 = a0*b0
-       movdqa    HashKey_k(%arg2), \TMP4
+       movdqu    HashKey_k(%arg2), \TMP4
        PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
        pxor      \TMP1, \TMP6
        pxor      \XMM4, \XMMDst