whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit b4df50de6ab66e41b3b8d8acf3ce45c632084163
parent 3f16503b7d2274ac8cbab11163047ac0b4c66cfe
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Wed, 29 Aug 2018 13:38:39 -0700

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

Diffstat:
March/arm64/crypto/ghash-ce-glue.c | 29+++++++++++++++++++++++------
March/arm64/crypto/sm4-ce-glue.c | 2+-
March/x86/crypto/aesni-intel_asm.S | 66+++++++++++++++++++++++++++++++++---------------------------------
Mdrivers/crypto/caam/caamalg_qi.c | 6++----
Mdrivers/crypto/caam/caampkc.c | 20++++++++++----------
Mdrivers/crypto/caam/jr.c | 3++-
Mdrivers/crypto/cavium/nitrox/nitrox_dev.h | 3++-
Mdrivers/crypto/cavium/nitrox/nitrox_lib.c | 1+
Mdrivers/crypto/cavium/nitrox/nitrox_reqmgr.c | 57++++++++++++++++++++++++++++++++-------------------------
Mdrivers/crypto/chelsio/chtls/chtls.h | 5+++++
Mdrivers/crypto/chelsio/chtls/chtls_main.c | 7+++++--
Mdrivers/crypto/vmx/aes_cbc.c | 30++++++++++++++----------------
Mdrivers/crypto/vmx/aes_xts.c | 21++++++++++++++-------
13 files changed, 144 insertions(+), 106 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c @@ -417,7 +417,7 @@ static int gcm_encrypt(struct aead_request *req) __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - while (walk.nbytes >= AES_BLOCK_SIZE) { + while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; u8 *src = walk.src.virt.addr; @@ -437,11 +437,18 @@ static int gcm_encrypt(struct aead_request *req) NULL); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); + walk.nbytes % (2 * AES_BLOCK_SIZE)); } - if (walk.nbytes) + if (walk.nbytes) { __aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv, nrounds); + if (walk.nbytes > AES_BLOCK_SIZE) { + crypto_inc(iv, AES_BLOCK_SIZE); + __aes_arm64_encrypt(ctx->aes_key.key_enc, + ks + AES_BLOCK_SIZE, iv, + nrounds); + } + } } /* handle the tail */ @@ -545,7 +552,7 @@ static int gcm_decrypt(struct aead_request *req) __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - while (walk.nbytes >= AES_BLOCK_SIZE) { + while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; u8 *src = walk.src.virt.addr; @@ -564,11 +571,21 @@ static int gcm_decrypt(struct aead_request *req) } while (--blocks > 0); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); + walk.nbytes % (2 * AES_BLOCK_SIZE)); } - if (walk.nbytes) + if (walk.nbytes) { + if (walk.nbytes > AES_BLOCK_SIZE) { + u8 *iv2 = iv + AES_BLOCK_SIZE; + + memcpy(iv2, iv, AES_BLOCK_SIZE); + crypto_inc(iv2, AES_BLOCK_SIZE); + + __aes_arm64_encrypt(ctx->aes_key.key_enc, iv2, + iv2, nrounds); + } __aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv, nrounds); + } } /* handle the tail */ diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c @@ -69,5 +69,5 @@ static void __exit sm4_ce_mod_fini(void) crypto_unregister_alg(&sm4_ce_alg); } -module_cpu_feature_match(SM3, sm4_ce_mod_init); +module_cpu_feature_match(SM4, sm4_ce_mod_init); module_exit(sm4_ce_mod_fini); diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S @@ -223,34 +223,34 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff 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. @@ -271,7 +271,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff 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 @@ -997,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation 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 @@ 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 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst 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 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst 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 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst 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 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst 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 diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c @@ -679,10 +679,8 @@ static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher, int ret = 0; if (keylen != 2 * AES_MIN_KEY_SIZE && keylen != 2 * AES_MAX_KEY_SIZE) { - crypto_ablkcipher_set_flags(ablkcipher, - CRYPTO_TFM_RES_BAD_KEY_LEN); dev_err(jrdev, "key size mismatch\n"); - return -EINVAL; + goto badkey; } ctx->cdata.keylen = keylen; @@ -715,7 +713,7 @@ static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher, return ret; badkey: crypto_ablkcipher_set_flags(ablkcipher, CRYPTO_TFM_RES_BAD_KEY_LEN); - return 0; + return -EINVAL; } /* diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c @@ -71,8 +71,8 @@ static void rsa_priv_f2_unmap(struct device *dev, struct rsa_edesc *edesc, dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); + dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_BIDIRECTIONAL); } static void rsa_priv_f3_unmap(struct device *dev, struct rsa_edesc *edesc, @@ -90,8 +90,8 @@ static void rsa_priv_f3_unmap(struct device *dev, struct rsa_edesc *edesc, dma_unmap_single(dev, pdb->dp_dma, p_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->dq_dma, q_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->c_dma, p_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); + dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_BIDIRECTIONAL); } /* RSA Job Completion handler */ @@ -417,13 +417,13 @@ static int set_rsa_priv_f2_pdb(struct akcipher_request *req, goto unmap_p; } - pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_TO_DEVICE); + pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp1_dma)) { dev_err(dev, "Unable to map RSA tmp1 memory\n"); goto unmap_q; } - pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_TO_DEVICE); + pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp2_dma)) { dev_err(dev, "Unable to map RSA tmp2 memory\n"); goto unmap_tmp1; @@ -451,7 +451,7 @@ static int set_rsa_priv_f2_pdb(struct akcipher_request *req, return 0; unmap_tmp1: - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); unmap_q: dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); unmap_p: @@ -504,13 +504,13 @@ static int set_rsa_priv_f3_pdb(struct akcipher_request *req, goto unmap_dq; } - pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_TO_DEVICE); + pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp1_dma)) { dev_err(dev, "Unable to map RSA tmp1 memory\n"); goto unmap_qinv; } - pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_TO_DEVICE); + pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp2_dma)) { dev_err(dev, "Unable to map RSA tmp2 memory\n"); goto unmap_tmp1; @@ -538,7 +538,7 @@ static int set_rsa_priv_f3_pdb(struct akcipher_request *req, return 0; unmap_tmp1: - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); unmap_qinv: dma_unmap_single(dev, pdb->c_dma, p_sz, DMA_TO_DEVICE); unmap_dq: diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c @@ -190,7 +190,8 @@ static void caam_jr_dequeue(unsigned long devarg) BUG_ON(CIRC_CNT(head, tail + i, JOBR_DEPTH) <= 0); /* Unmap just-run descriptor so we can post-process */ - dma_unmap_single(dev, jrp->outring[hw_idx].desc, + dma_unmap_single(dev, + caam_dma_to_cpu(jrp->outring[hw_idx].desc), jrp->entinfo[sw_idx].desc_size, DMA_TO_DEVICE); diff --git a/drivers/crypto/cavium/nitrox/nitrox_dev.h b/drivers/crypto/cavium/nitrox/nitrox_dev.h @@ -35,6 +35,7 @@ struct nitrox_cmdq { /* requests in backlog queues */ atomic_t backlog_count; + int write_idx; /* command size 32B/64B */ u8 instr_size; u8 qno; @@ -87,7 +88,7 @@ struct nitrox_bh { struct bh_data *slc; }; -/* NITROX-5 driver state */ +/* NITROX-V driver state */ #define NITROX_UCODE_LOADED 0 #define NITROX_READY 1 diff --git a/drivers/crypto/cavium/nitrox/nitrox_lib.c b/drivers/crypto/cavium/nitrox/nitrox_lib.c @@ -36,6 +36,7 @@ static int cmdq_common_init(struct nitrox_cmdq *cmdq) cmdq->head = PTR_ALIGN(cmdq->head_unaligned, PKT_IN_ALIGN); cmdq->dma = PTR_ALIGN(cmdq->dma_unaligned, PKT_IN_ALIGN); cmdq->qsize = (qsize + PKT_IN_ALIGN); + cmdq->write_idx = 0; spin_lock_init(&cmdq->response_lock); spin_lock_init(&cmdq->cmdq_lock); diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c @@ -42,6 +42,16 @@ * Invalid flag options in AES-CCM IV. */ +static inline int incr_index(int index, int count, int max) +{ + if ((index + count) >= max) + index = index + count - max; + else + index += count; + + return index; +} + /** * dma_free_sglist - unmap and free the sg lists. * @ndev: N5 device @@ -426,30 +436,29 @@ static void post_se_instr(struct nitrox_softreq *sr, struct nitrox_cmdq *cmdq) { struct nitrox_device *ndev = sr->ndev; - union nps_pkt_in_instr_baoff_dbell pkt_in_baoff_dbell; - u64 offset; + int idx; u8 *ent; spin_lock_bh(&cmdq->cmdq_lock); - /* get the next write offset */ - offset = NPS_PKT_IN_INSTR_BAOFF_DBELLX(cmdq->qno); - pkt_in_baoff_dbell.value = nitrox_read_csr(ndev, offset); + idx = cmdq->write_idx; /* copy the instruction */ - ent = cmdq->head + pkt_in_baoff_dbell.s.aoff; + ent = cmdq->head + (idx * cmdq->instr_size); memcpy(ent, &sr->instr, cmdq->instr_size); - /* flush the command queue updates */ - dma_wmb(); - sr->tstamp = jiffies; atomic_set(&sr->status, REQ_POSTED); response_list_add(sr, cmdq); + sr->tstamp = jiffies; + /* flush the command queue updates */ + dma_wmb(); /* Ring doorbell with count 1 */ writeq(1, cmdq->dbell_csr_addr); /* orders the doorbell rings */ mmiowb(); + cmdq->write_idx = incr_index(idx, 1, ndev->qlen); + spin_unlock_bh(&cmdq->cmdq_lock); } @@ -459,6 +468,9 @@ static int post_backlog_cmds(struct nitrox_cmdq *cmdq) struct nitrox_softreq *sr, *tmp; int ret = 0; + if (!atomic_read(&cmdq->backlog_count)) + return 0; + spin_lock_bh(&cmdq->backlog_lock); list_for_each_entry_safe(sr, tmp, &cmdq->backlog_head, backlog) { @@ -466,7 +478,7 @@ static int post_backlog_cmds(struct nitrox_cmdq *cmdq) /* submit until space available */ if (unlikely(cmdq_full(cmdq, ndev->qlen))) { - ret = -EBUSY; + ret = -ENOSPC; break; } /* delete from backlog list */ @@ -491,23 +503,20 @@ static int nitrox_enqueue_request(struct nitrox_softreq *sr) { struct nitrox_cmdq *cmdq = sr->cmdq; struct nitrox_device *ndev = sr->ndev; - int ret = -EBUSY; + + /* try to post backlog requests */ + post_backlog_cmds(cmdq); if (unlikely(cmdq_full(cmdq, ndev->qlen))) { if (!(sr->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) - return -EAGAIN; - + return -ENOSPC; + /* add to backlog list */ backlog_list_add(sr, cmdq); - } else { - ret = post_backlog_cmds(cmdq); - if (ret) { - backlog_list_add(sr, cmdq); - return ret; - } - post_se_instr(sr, cmdq); - ret = -EINPROGRESS; + return -EBUSY; } - return ret; + post_se_instr(sr, cmdq); + + return -EINPROGRESS; } /** @@ -624,11 +633,9 @@ int nitrox_process_se_request(struct nitrox_device *ndev, */ sr->instr.fdata[0] = *((u64 *)&req->gph); sr->instr.fdata[1] = 0; - /* flush the soft_req changes before posting the cmd */ - wmb(); ret = nitrox_enqueue_request(sr); - if (ret == -EAGAIN) + if (ret == -ENOSPC) goto send_fail; return ret; diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h @@ -96,6 +96,10 @@ enum csk_flags { CSK_CONN_INLINE, /* Connection on HW */ }; +enum chtls_cdev_state { + CHTLS_CDEV_STATE_UP = 1 +}; + struct listen_ctx { struct sock *lsk; struct chtls_dev *cdev; @@ -146,6 +150,7 @@ struct chtls_dev { unsigned int send_page_order; int max_host_sndbuf; struct key_map kmap; + unsigned int cdev_state; }; struct chtls_hws { diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -160,6 +160,7 @@ static void chtls_register_dev(struct chtls_dev *cdev) tlsdev->hash = chtls_create_hash; tlsdev->unhash = chtls_destroy_hash; tls_register_device(&cdev->tlsdev); + cdev->cdev_state = CHTLS_CDEV_STATE_UP; } static void chtls_unregister_dev(struct chtls_dev *cdev) @@ -281,8 +282,10 @@ static void chtls_free_all_uld(void) struct chtls_dev *cdev, *tmp; mutex_lock(&cdev_mutex); - list_for_each_entry_safe(cdev, tmp, &cdev_list, list) - chtls_free_uld(cdev); + list_for_each_entry_safe(cdev, tmp, &cdev_list, list) { + if (cdev->cdev_state == CHTLS_CDEV_STATE_UP) + chtls_free_uld(cdev); + } mutex_unlock(&cdev_mutex); } diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c @@ -107,24 +107,23 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc, ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); } else { - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - blkcipher_walk_init(&walk, dst, src, nbytes); ret = blkcipher_walk_virt(desc, &walk); while ((nbytes = walk.nbytes)) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->enc_key, walk.iv, 1); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, &walk, nbytes); } - - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); } return ret; @@ -147,24 +146,23 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc, ret = crypto_skcipher_decrypt(req); skcipher_request_zero(req); } else { - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - blkcipher_walk_init(&walk, dst, src, nbytes); ret = blkcipher_walk_virt(desc, &walk); while ((nbytes = walk.nbytes)) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->dec_key, walk.iv, 0); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, &walk, nbytes); } - - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); } return ret; diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c @@ -116,32 +116,39 @@ static int p8_aes_xts_crypt(struct blkcipher_desc *desc, ret = enc? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req); skcipher_request_zero(req); } else { + blkcipher_walk_init(&walk, dst, src, nbytes); + + ret = blkcipher_walk_virt(desc, &walk); + preempt_disable(); pagefault_disable(); enable_kernel_vsx(); - blkcipher_walk_init(&walk, dst, src, nbytes); - - ret = blkcipher_walk_virt(desc, &walk); iv = walk.iv; memset(tweak, 0, AES_BLOCK_SIZE); aes_p8_encrypt(iv, tweak, &ctx->tweak_key); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + while ((nbytes = walk.nbytes)) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); if (enc) aes_p8_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->enc_key, NULL, tweak); else aes_p8_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->dec_key, NULL, tweak); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, &walk, nbytes); } - - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); } return ret; }