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

Pull crypto update from Herbert Xu:
 "API:
   - Restrict crypto_cipher to internal API users only.

  Algorithms:
   - Add x86 aesni acceleration for cts.
   - Improve x86 aesni acceleration for xts.
   - Remove x86 acceleration of some uncommon algorithms.
   - Remove RIPE-MD, Tiger and Salsa20.
   - Remove tnepres.
   - Add ARM acceleration for BLAKE2s and BLAKE2b.

  Drivers:
   - Add Keem Bay OCS HCU driver.
   - Add Marvell OcteonTX2 CPT PF driver.
   - Remove PicoXcell driver.
   - Remove mediatek driver"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (154 commits)
  hwrng: timeriomem - Use device-managed registration API
  crypto: hisilicon/qm - fix printing format issue
  crypto: hisilicon/qm - do not reset hardware when CE happens
  crypto: hisilicon/qm - update irqflag
  crypto: hisilicon/qm - fix the value of 'QM_SQC_VFT_BASE_MASK_V2'
  crypto: hisilicon/qm - fix request missing error
  crypto: hisilicon/qm - removing driver after reset
  crypto: octeontx2 - fix -Wpointer-bool-conversion warning
  crypto: hisilicon/hpre - enable Elliptic curve cryptography
  crypto: hisilicon - PASID fixed on Kunpeng 930
  crypto: hisilicon/qm - fix use of 'dma_map_single'
  crypto: hisilicon/hpre - tiny fix
  crypto: hisilicon/hpre - adapt the number of clusters
  crypto: cpt - remove casting dma_alloc_coherent
  crypto: keembay-ocs-aes - Fix 'q' assignment during CCM B0 generation
  crypto: xor - Fix typo of optimization
  hwrng: optee - Use device-managed registration API
  crypto: arm64/crc-t10dif - move NEON yield to C code
  crypto: arm64/aes-ce-mac - simplify NEON yield
  crypto: arm64/aes-neonbs - remove NEON yield calls
  ...

1 files changed, 0 insertions, 104 deletions

diff --git a/arch/x86/crypto/glue_helper-asm-avx.S b/arch/x86/crypto/glue_helper-asm-avx.S
index d08fc575ef7f..3da385271227 100644
--- a/arch/x86/crypto/glue_helper-asm-avx.S
+++ b/arch/x86/crypto/glue_helper-asm-avx.S
@@ -34,107 +34,3 @@
 	vpxor (5*16)(src), x6, x6; \
 	vpxor (6*16)(src), x7, x7; \
 	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
-
-#define inc_le128(x, minus_one, tmp) \
-	vpcmpeqq minus_one, x, tmp; \
-	vpsubq minus_one, x, x; \
-	vpslldq $8, tmp, tmp; \
-	vpsubq tmp, x, x;
-
-#define load_ctr_8way(iv, bswap, x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2) \
-	vpcmpeqd t0, t0, t0; \
-	vpsrldq $8, t0, t0; /* low: -1, high: 0 */ \
-	vmovdqa bswap, t1; \
-	\
-	/* load IV and byteswap */ \
-	vmovdqu (iv), x7; \
-	vpshufb t1, x7, x0; \
-	\
-	/* construct IVs */ \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x1; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x2; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x3; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x4; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x5; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x6; \
-	inc_le128(x7, t0, t2); \
-	vmovdqa x7, t2; \
-	vpshufb t1, x7, x7; \
-	inc_le128(t2, t0, t1); \
-	vmovdqu t2, (iv);
-
-#define store_ctr_8way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \
-	vpxor (0*16)(src), x0, x0; \
-	vpxor (1*16)(src), x1, x1; \
-	vpxor (2*16)(src), x2, x2; \
-	vpxor (3*16)(src), x3, x3; \
-	vpxor (4*16)(src), x4, x4; \
-	vpxor (5*16)(src), x5, x5; \
-	vpxor (6*16)(src), x6, x6; \
-	vpxor (7*16)(src), x7, x7; \
-	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
-
-#define gf128mul_x_ble(iv, mask, tmp) \
-	vpsrad $31, iv, tmp; \
-	vpaddq iv, iv, iv; \
-	vpshufd $0x13, tmp, tmp; \
-	vpand mask, tmp, tmp; \
-	vpxor tmp, iv, iv;
-
-#define load_xts_8way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, t0, \
-		      t1, xts_gf128mul_and_shl1_mask) \
-	vmovdqa xts_gf128mul_and_shl1_mask, t0; \
-	\
-	/* load IV */ \
-	vmovdqu (iv), tiv; \
-	vpxor (0*16)(src), tiv, x0; \
-	vmovdqu tiv, (0*16)(dst); \
-	\
-	/* construct and store IVs, also xor with source */ \
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (1*16)(src), tiv, x1; \
-	vmovdqu tiv, (1*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (2*16)(src), tiv, x2; \
-	vmovdqu tiv, (2*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (3*16)(src), tiv, x3; \
-	vmovdqu tiv, (3*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (4*16)(src), tiv, x4; \
-	vmovdqu tiv, (4*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (5*16)(src), tiv, x5; \
-	vmovdqu tiv, (5*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (6*16)(src), tiv, x6; \
-	vmovdqu tiv, (6*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (7*16)(src), tiv, x7; \
-	vmovdqu tiv, (7*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vmovdqu tiv, (iv);
-
-#define store_xts_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \
-	vpxor (0*16)(dst), x0, x0; \
-	vpxor (1*16)(dst), x1, x1; \
-	vpxor (2*16)(dst), x2, x2; \
-	vpxor (3*16)(dst), x3, x3; \
-	vpxor (4*16)(dst), x4, x4; \
-	vpxor (5*16)(dst), x5, x5; \
-	vpxor (6*16)(dst), x6, x6; \
-	vpxor (7*16)(dst), x7, x7; \
-	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);