diff options
Diffstat (limited to 'drivers/crypto')
190 files changed, 10251 insertions, 3112 deletions
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 4f705674f94f..55e75fbb658e 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -133,98 +133,6 @@ config CRYPTO_PAES_S390 Select this option if you want to use the paes cipher for example to use protected key encrypted devices. -config CRYPTO_SHA1_S390 - tristate "SHA1 digest algorithm" - depends on S390 - select CRYPTO_HASH - help - This is the s390 hardware accelerated implementation of the - SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2). - - It is available as of z990. - -config CRYPTO_SHA256_S390 - tristate "SHA256 digest algorithm" - depends on S390 - select CRYPTO_HASH - help - This is the s390 hardware accelerated implementation of the - SHA256 secure hash standard (DFIPS 180-2). - - It is available as of z9. - -config CRYPTO_SHA512_S390 - tristate "SHA384 and SHA512 digest algorithm" - depends on S390 - select CRYPTO_HASH - help - This is the s390 hardware accelerated implementation of the - SHA512 secure hash standard. - - It is available as of z10. - -config CRYPTO_SHA3_256_S390 - tristate "SHA3_224 and SHA3_256 digest algorithm" - depends on S390 - select CRYPTO_HASH - help - This is the s390 hardware accelerated implementation of the - SHA3_256 secure hash standard. - - It is available as of z14. - -config CRYPTO_SHA3_512_S390 - tristate "SHA3_384 and SHA3_512 digest algorithm" - depends on S390 - select CRYPTO_HASH - help - This is the s390 hardware accelerated implementation of the - SHA3_512 secure hash standard. - - It is available as of z14. - -config CRYPTO_DES_S390 - tristate "DES and Triple DES cipher algorithms" - depends on S390 - select CRYPTO_ALGAPI - select CRYPTO_SKCIPHER - select CRYPTO_LIB_DES - help - This is the s390 hardware accelerated implementation of the - DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3). - - As of z990 the ECB and CBC mode are hardware accelerated. - As of z196 the CTR mode is hardware accelerated. - -config CRYPTO_AES_S390 - tristate "AES cipher algorithms" - depends on S390 - select CRYPTO_ALGAPI - select CRYPTO_SKCIPHER - help - This is the s390 hardware accelerated implementation of the - AES cipher algorithms (FIPS-197). - - As of z9 the ECB and CBC modes are hardware accelerated - for 128 bit keys. - As of z10 the ECB and CBC modes are hardware accelerated - for all AES key sizes. - As of z196 the CTR mode is hardware accelerated for all AES - key sizes and XTS mode is hardware accelerated for 256 and - 512 bit keys. - -config CRYPTO_CHACHA_S390 - tristate "ChaCha20 stream cipher" - depends on S390 - select CRYPTO_ALGAPI - select CRYPTO_SKCIPHER - select CRYPTO_CHACHA20 - help - This is the s390 SIMD implementation of the ChaCha20 stream - cipher (RFC 7539). - - It is available as of z13. - config S390_PRNG tristate "Pseudo random number generator device driver" depends on S390 @@ -238,29 +146,6 @@ config S390_PRNG It is available as of z9. -config CRYPTO_GHASH_S390 - tristate "GHASH hash function" - depends on S390 - select CRYPTO_HASH - help - This is the s390 hardware accelerated implementation of GHASH, - the hash function used in GCM (Galois/Counter mode). - - It is available as of z196. - -config CRYPTO_CRC32_S390 - tristate "CRC-32 algorithms" - depends on S390 - select CRYPTO_HASH - select CRC32 - help - Select this option if you want to use hardware accelerated - implementations of CRC algorithms. With this option, you - can optimize the computation of CRC-32 (IEEE 802.3 Ethernet) - and CRC-32C (Castagnoli). - - It is available with IBM z13 or later. - config CRYPTO_DEV_NIAGARA2 tristate "Niagara2 Stream Processing Unit driver" select CRYPTO_LIB_DES @@ -808,6 +693,16 @@ config CRYPTO_DEV_ZYNQMP_AES accelerator. Select this if you want to use the ZynqMP module for AES algorithms. +config CRYPTO_DEV_ZYNQMP_SHA3 + tristate "Support for Xilinx ZynqMP SHA3 hardware accelerator" + depends on ZYNQMP_FIRMWARE || COMPILE_TEST + select CRYPTO_SHA3 + help + Xilinx ZynqMP has SHA3 engine used for secure hash calculation. + This driver interfaces with SHA3 hardware engine. + Select this if you want to use the ZynqMP module + for SHA3 hash computation. + source "drivers/crypto/chelsio/Kconfig" source "drivers/crypto/virtio/Kconfig" @@ -907,9 +802,7 @@ source "drivers/crypto/amlogic/Kconfig" config CRYPTO_DEV_SA2UL tristate "Support for TI security accelerator" depends on ARCH_K3 || COMPILE_TEST - select ARM64_CRYPTO select CRYPTO_AES - select CRYPTO_AES_ARM64 select CRYPTO_ALGAPI select CRYPTO_AUTHENC select CRYPTO_SHA1 @@ -923,5 +816,6 @@ config CRYPTO_DEV_SA2UL acceleration for cryptographic algorithms on these devices. source "drivers/crypto/keembay/Kconfig" +source "drivers/crypto/aspeed/Kconfig" endif # CRYPTO_HW diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile index 1fe5120eb966..116de173a66c 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_ALLWINNER) += allwinner/ +obj-$(CONFIG_CRYPTO_DEV_ASPEED) += aspeed/ obj-$(CONFIG_CRYPTO_DEV_ATMEL_AES) += atmel-aes.o obj-$(CONFIG_CRYPTO_DEV_ATMEL_SHA) += atmel-sha.o obj-$(CONFIG_CRYPTO_DEV_ATMEL_TDES) += atmel-tdes.o +# __init ordering requires atmel-i2c being before atmel-ecc and atmel-sha204a. obj-$(CONFIG_CRYPTO_DEV_ATMEL_I2C) += atmel-i2c.o obj-$(CONFIG_CRYPTO_DEV_ATMEL_ECC) += atmel-ecc.o obj-$(CONFIG_CRYPTO_DEV_ATMEL_SHA204A) += atmel-sha204a.o @@ -47,7 +49,7 @@ obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/ obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/ obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/ obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/ -obj-$(CONFIG_CRYPTO_DEV_ZYNQMP_AES) += xilinx/ +obj-y += xilinx/ obj-y += hisilicon/ obj-$(CONFIG_CRYPTO_DEV_AMLOGIC_GXL) += amlogic/ obj-y += keembay/ diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c index dec79fa3ebaf..10fe9f73a5fb 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c @@ -20,7 +20,6 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq) unsigned int ivsize = crypto_skcipher_ivsize(tfm); struct sun4i_cipher_req_ctx *ctx = skcipher_request_ctx(areq); u32 mode = ctx->mode; - void *backup_iv = NULL; /* when activating SS, the default FIFO space is SS_RX_DEFAULT(32) */ u32 rx_cnt = SS_RX_DEFAULT; u32 tx_cnt = 0; @@ -48,10 +47,8 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq) } if (areq->iv && ivsize > 0 && mode & SS_DECRYPTION) { - backup_iv = kzalloc(ivsize, GFP_KERNEL); - if (!backup_iv) - return -ENOMEM; - scatterwalk_map_and_copy(backup_iv, areq->src, areq->cryptlen - ivsize, ivsize, 0); + scatterwalk_map_and_copy(ctx->backup_iv, areq->src, + areq->cryptlen - ivsize, ivsize, 0); } if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) { @@ -134,8 +131,8 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq) if (areq->iv) { if (mode & SS_DECRYPTION) { - memcpy(areq->iv, backup_iv, ivsize); - kfree_sensitive(backup_iv); + memcpy(areq->iv, ctx->backup_iv, ivsize); + memzero_explicit(ctx->backup_iv, ivsize); } else { scatterwalk_map_and_copy(areq->iv, areq->dst, areq->cryptlen - ivsize, ivsize, 0); @@ -199,7 +196,6 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) unsigned int ileft = areq->cryptlen; unsigned int oleft = areq->cryptlen; unsigned int todo; - void *backup_iv = NULL; struct sg_mapping_iter mi, mo; unsigned long pi = 0, po = 0; /* progress for in and out */ bool miter_err; @@ -244,10 +240,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) return sun4i_ss_cipher_poll_fallback(areq); if (areq->iv && ivsize > 0 && mode & SS_DECRYPTION) { - backup_iv = kzalloc(ivsize, GFP_KERNEL); - if (!backup_iv) - return -ENOMEM; - scatterwalk_map_and_copy(backup_iv, areq->src, areq->cryptlen - ivsize, ivsize, 0); + scatterwalk_map_and_copy(ctx->backup_iv, areq->src, + areq->cryptlen - ivsize, ivsize, 0); } if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) { @@ -384,8 +378,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) } if (areq->iv) { if (mode & SS_DECRYPTION) { - memcpy(areq->iv, backup_iv, ivsize); - kfree_sensitive(backup_iv); + memcpy(areq->iv, ctx->backup_iv, ivsize); + memzero_explicit(ctx->backup_iv, ivsize); } else { scatterwalk_map_and_copy(areq->iv, areq->dst, areq->cryptlen - ivsize, ivsize, 0); diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c index 44b8fc4b786d..006e40133c28 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c @@ -235,7 +235,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { #endif }; -static int sun4i_ss_dbgfs_read(struct seq_file *seq, void *v) +static int sun4i_ss_debugfs_show(struct seq_file *seq, void *v) { unsigned int i; @@ -266,19 +266,7 @@ static int sun4i_ss_dbgfs_read(struct seq_file *seq, void *v) } return 0; } - -static int sun4i_ss_dbgfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, sun4i_ss_dbgfs_read, inode->i_private); -} - -static const struct file_operations sun4i_ss_debugfs_fops = { - .owner = THIS_MODULE, - .open = sun4i_ss_dbgfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(sun4i_ss_debugfs); /* * Power management strategy: The device is suspended unless a TFM exists for diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h index 0fee6f4e2d90..ba59c7a48825 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h @@ -183,6 +183,7 @@ struct sun4i_tfm_ctx { struct sun4i_cipher_req_ctx { u32 mode; + u8 backup_iv[AES_BLOCK_SIZE]; struct skcipher_request fallback_req; // keep at the end }; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index 54ae8d16e493..74b4e910a38d 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -11,6 +11,7 @@ * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ +#include <linux/bottom_half.h> #include <linux/crypto.h> #include <linux/dma-mapping.h> #include <linux/io.h> @@ -24,26 +25,62 @@ static int sun8i_ce_cipher_need_fallback(struct skcipher_request *areq) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); struct scatterlist *sg; + struct skcipher_alg *alg = crypto_skcipher_alg(tfm); + struct sun8i_ce_alg_template *algt; + unsigned int todo, len; + + algt = container_of(alg, struct sun8i_ce_alg_template, alg.skcipher); + + if (sg_nents_for_len(areq->src, areq->cryptlen) > MAX_SG || + sg_nents_for_len(areq->dst, areq->cryptlen) > MAX_SG) { + algt->stat_fb_maxsg++; + return true; + } - if (sg_nents(areq->src) > MAX_SG || sg_nents(areq->dst) > MAX_SG) + if (areq->cryptlen < crypto_skcipher_ivsize(tfm)) { + algt->stat_fb_leniv++; return true; + } - if (areq->cryptlen < crypto_skcipher_ivsize(tfm)) + if (areq->cryptlen == 0) { + algt->stat_fb_len0++; return true; + } - if (areq->cryptlen == 0 || areq->cryptlen % 16) + if (areq->cryptlen % 16) { + algt->stat_fb_mod16++; return true; + } + len = areq->cryptlen; sg = areq->src; while (sg) { - if (sg->length % 4 || !IS_ALIGNED(sg->offset, sizeof(u32))) + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { + algt->stat_fb_srcali++; + return true; + } + todo = min(len, sg->length); + if (todo % 4) { + algt->stat_fb_srclen++; return true; + } + len -= todo; sg = sg_next(sg); } + + len = areq->cryptlen; sg = areq->dst; while (sg) { - if (sg->length % 4 || !IS_ALIGNED(sg->offset, sizeof(u32))) + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { + algt->stat_fb_dstali++; + return true; + } + todo = min(len, sg->length); + if (todo % 4) { + algt->stat_fb_dstlen++; return true; + } + len -= todo; sg = sg_next(sg); } return false; @@ -93,6 +130,8 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req int nr_sgs = 0; int nr_sgd = 0; int err = 0; + int ns = sg_nents_for_len(areq->src, areq->cryptlen); + int nd = sg_nents_for_len(areq->dst, areq->cryptlen); algt = container_of(alg, struct sun8i_ce_alg_template, alg.skcipher); @@ -151,23 +190,13 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req ivsize = crypto_skcipher_ivsize(tfm); if (areq->iv && crypto_skcipher_ivsize(tfm) > 0) { rctx->ivlen = ivsize; - rctx->bounce_iv = kzalloc(ivsize, GFP_KERNEL | GFP_DMA); - if (!rctx->bounce_iv) { - err = -ENOMEM; - goto theend_key; - } if (rctx->op_dir & CE_DECRYPTION) { - rctx->backup_iv = kzalloc(ivsize, GFP_KERNEL); - if (!rctx->backup_iv) { - err = -ENOMEM; - goto theend_key; - } offset = areq->cryptlen - ivsize; - scatterwalk_map_and_copy(rctx->backup_iv, areq->src, + scatterwalk_map_and_copy(chan->backup_iv, areq->src, offset, ivsize, 0); } - memcpy(rctx->bounce_iv, areq->iv, ivsize); - rctx->addr_iv = dma_map_single(ce->dev, rctx->bounce_iv, rctx->ivlen, + memcpy(chan->bounce_iv, areq->iv, ivsize); + rctx->addr_iv = dma_map_single(ce->dev, chan->bounce_iv, rctx->ivlen, DMA_TO_DEVICE); if (dma_mapping_error(ce->dev, rctx->addr_iv)) { dev_err(ce->dev, "Cannot DMA MAP IV\n"); @@ -178,8 +207,7 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req } if (areq->src == areq->dst) { - nr_sgs = dma_map_sg(ce->dev, areq->src, sg_nents(areq->src), - DMA_BIDIRECTIONAL); + nr_sgs = dma_map_sg(ce->dev, areq->src, ns, DMA_BIDIRECTIONAL); if (nr_sgs <= 0 || nr_sgs > MAX_SG) { dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs); err = -EINVAL; @@ -187,15 +215,13 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req } nr_sgd = nr_sgs; } else { - nr_sgs = dma_map_sg(ce->dev, areq->src, sg_nents(areq->src), - DMA_TO_DEVICE); + nr_sgs = dma_map_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE); if (nr_sgs <= 0 || nr_sgs > MAX_SG) { dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs); err = -EINVAL; goto theend_iv; } - nr_sgd = dma_map_sg(ce->dev, areq->dst, sg_nents(areq->dst), - DMA_FROM_DEVICE); + nr_sgd = dma_map_sg(ce->dev, areq->dst, nd, DMA_FROM_DEVICE); if (nr_sgd <= 0 || nr_sgd > MAX_SG) { dev_err(ce->dev, "Invalid sg number %d\n", nr_sgd); err = -EINVAL; @@ -240,14 +266,11 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req theend_sgs: if (areq->src == areq->dst) { - dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src), - DMA_BIDIRECTIONAL); + dma_unmap_sg(ce->dev, areq->src, ns, DMA_BIDIRECTIONAL); } else { if (nr_sgs > 0) - dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src), - DMA_TO_DEVICE); - dma_unmap_sg(ce->dev, areq->dst, sg_nents(areq->dst), - DMA_FROM_DEVICE); + dma_unmap_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE); + dma_unmap_sg(ce->dev, areq->dst, nd, DMA_FROM_DEVICE); } theend_iv: @@ -256,16 +279,15 @@ theend_iv: dma_unmap_single(ce->dev, rctx->addr_iv, rctx->ivlen, DMA_TO_DEVICE); offset = areq->cryptlen - ivsize; if (rctx->op_dir & CE_DECRYPTION) { - memcpy(areq->iv, rctx->backup_iv, ivsize); - kfree_sensitive(rctx->backup_iv); + memcpy(areq->iv, chan->backup_iv, ivsize); + memzero_explicit(chan->backup_iv, ivsize); } else { scatterwalk_map_and_copy(areq->iv, areq->dst, offset, ivsize, 0); } - kfree(rctx->bounce_iv); + memzero_explicit(chan->bounce_iv, ivsize); } -theend_key: dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE); theend: @@ -283,7 +305,9 @@ static int sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) flow = rctx->flow; err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); + local_bh_disable(); crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); return 0; } @@ -319,13 +343,13 @@ static int sun8i_ce_cipher_unprepare(struct crypto_engine *engine, void *async_r dma_unmap_single(ce->dev, rctx->addr_iv, rctx->ivlen, DMA_TO_DEVICE); offset = areq->cryptlen - ivsize; if (rctx->op_dir & CE_DECRYPTION) { - memcpy(areq->iv, rctx->backup_iv, ivsize); - kfree_sensitive(rctx->backup_iv); + memcpy(areq->iv, chan->backup_iv, ivsize); + memzero_explicit(chan->backup_iv, ivsize); } else { scatterwalk_map_and_copy(areq->iv, areq->dst, offset, ivsize, 0); } - kfree(rctx->bounce_iv); + memzero_explicit(chan->bounce_iv, ivsize); } dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE); @@ -395,10 +419,9 @@ int sun8i_ce_cipher_init(struct crypto_tfm *tfm) sktfm->reqsize = sizeof(struct sun8i_cipher_req_ctx) + crypto_skcipher_reqsize(op->fallback_tfm); - - dev_info(op->ce->dev, "Fallback for %s is %s\n", - crypto_tfm_alg_driver_name(&sktfm->base), - crypto_tfm_alg_driver_name(crypto_skcipher_tfm(op->fallback_tfm))); + memcpy(algt->fbname, + crypto_tfm_alg_driver_name(crypto_skcipher_tfm(op->fallback_tfm)), + CRYPTO_MAX_ALG_NAME); op->enginectx.op.do_one_request = sun8i_ce_cipher_run; op->enginectx.op.prepare_request = sun8i_ce_cipher_prepare; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c index d8623c7e0d1d..9f6594699835 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c @@ -283,7 +283,7 @@ static struct sun8i_ce_alg_template ce_algs[] = { .cra_priority = 400, .cra_blocksize = AES_BLOCK_SIZE, .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | - CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx), .cra_module = THIS_MODULE, @@ -310,7 +310,7 @@ static struct sun8i_ce_alg_template ce_algs[] = { .cra_priority = 400, .cra_blocksize = AES_BLOCK_SIZE, .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | - CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx), .cra_module = THIS_MODULE, @@ -336,7 +336,7 @@ static struct sun8i_ce_alg_template ce_algs[] = { .cra_priority = 400, .cra_blocksize = DES3_EDE_BLOCK_SIZE, .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | - CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx), .cra_module = THIS_MODULE, @@ -363,7 +363,7 @@ static struct sun8i_ce_alg_template ce_algs[] = { .cra_priority = 400, .cra_blocksize = DES3_EDE_BLOCK_SIZE, .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | - CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx), .cra_module = THIS_MODULE, @@ -595,19 +595,47 @@ static int sun8i_ce_debugfs_show(struct seq_file *seq, void *v) continue; switch (ce_algs[i].type) { case CRYPTO_ALG_TYPE_SKCIPHER: - seq_printf(seq, "%s %s %lu %lu\n", + seq_printf(seq, "%s %s reqs=%lu fallback=%lu\n", ce_algs[i].alg.skcipher.base.cra_driver_name, ce_algs[i].alg.skcipher.base.cra_name, ce_algs[i].stat_req, ce_algs[i].stat_fb); + seq_printf(seq, "\tLast fallback is: %s\n", + ce_algs[i].fbname); + seq_printf(seq, "\tFallback due to 0 length: %lu\n", + ce_algs[i].stat_fb_len0); + seq_printf(seq, "\tFallback due to length !mod16: %lu\n", + ce_algs[i].stat_fb_mod16); + seq_printf(seq, "\tFallback due to length < IV: %lu\n", + ce_algs[i].stat_fb_leniv); + seq_printf(seq, "\tFallback due to source alignment: %lu\n", + ce_algs[i].stat_fb_srcali); + seq_printf(seq, "\tFallback due to dest alignment: %lu\n", + ce_algs[i].stat_fb_dstali); + seq_printf(seq, "\tFallback due to source length: %lu\n", + ce_algs[i].stat_fb_srclen); + seq_printf(seq, "\tFallback due to dest length: %lu\n", + ce_algs[i].stat_fb_dstlen); + seq_printf(seq, "\tFallback due to SG numbers: %lu\n", + ce_algs[i].stat_fb_maxsg); break; case CRYPTO_ALG_TYPE_AHASH: - seq_printf(seq, "%s %s %lu %lu\n", + seq_printf(seq, "%s %s reqs=%lu fallback=%lu\n", ce_algs[i].alg.hash.halg.base.cra_driver_name, ce_algs[i].alg.hash.halg.base.cra_name, ce_algs[i].stat_req, ce_algs[i].stat_fb); + seq_printf(seq, "\tLast fallback is: %s\n", + ce_algs[i].fbname); + seq_printf(seq, "\tFallback due to 0 length: %lu\n", + ce_algs[i].stat_fb_len0); + seq_printf(seq, "\tFallback due to length: %lu\n", + ce_algs[i].stat_fb_srclen); + seq_printf(seq, "\tFallback due to alignment: %lu\n", + ce_algs[i].stat_fb_srcali); + seq_printf(seq, "\tFallback due to SG numbers: %lu\n", + ce_algs[i].stat_fb_maxsg); break; case CRYPTO_ALG_TYPE_RNG: - seq_printf(seq, "%s %s %lu %lu\n", + seq_printf(seq, "%s %s reqs=%lu bytes=%lu\n", ce_algs[i].alg.rng.base.cra_driver_name, ce_algs[i].alg.rng.base.cra_name, ce_algs[i].stat_req, ce_algs[i].stat_bytes); @@ -673,6 +701,18 @@ static int sun8i_ce_allocate_chanlist(struct sun8i_ce_dev *ce) err = -ENOMEM; goto error_engine; } + ce->chanlist[i].bounce_iv = devm_kmalloc(ce->dev, AES_BLOCK_SIZE, + GFP_KERNEL | GFP_DMA); + if (!ce->chanlist[i].bounce_iv) { + err = -ENOMEM; + goto error_engine; + } + ce->chanlist[i].backup_iv = devm_kmalloc(ce->dev, AES_BLOCK_SIZE, + GFP_KERNEL); + if (!ce->chanlist[i].backup_iv) { + err = -ENOMEM; + goto error_engine; + } } return 0; error_engine: diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c index 88194718a806..8b5b9b9d04c3 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c @@ -9,6 +9,7 @@ * * You could find the datasheet in Documentation/arm/sunxi.rst */ +#include <linux/bottom_half.h> #include <linux/dma-mapping.h> #include <linux/pm_runtime.h> #include <linux/scatterlist.h> @@ -49,9 +50,9 @@ int sun8i_ce_hash_crainit(struct crypto_tfm *tfm) sizeof(struct sun8i_ce_hash_reqctx) + crypto_ahash_reqsize(op->fallback_tfm)); - dev_info(op->ce->dev, "Fallback for %s is %s\n", - crypto_tfm_alg_driver_name(tfm), - crypto_tfm_alg_driver_name(&op->fallback_tfm->base)); + memcpy(algt->fbname, crypto_tfm_alg_driver_name(&op->fallback_tfm->base), + CRYPTO_MAX_ALG_NAME); + err = pm_runtime_get_sync(op->ce->dev); if (err < 0) goto error_pm; @@ -198,17 +199,32 @@ static int sun8i_ce_hash_digest_fb(struct ahash_request *areq) static bool sun8i_ce_hash_need_fallback(struct ahash_request *areq) { + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct ahash_alg *alg = __crypto_ahash_alg(tfm->base.__crt_alg); + struct sun8i_ce_alg_template *algt; struct scatterlist *sg; - if (areq->nbytes == 0) + algt = container_of(alg, struct sun8i_ce_alg_template, alg.hash); + + if (areq->nbytes == 0) { + algt->stat_fb_len0++; return true; + } /* we need to reserve one SG for padding one */ - if (sg_nents(areq->src) > MAX_SG - 1) + if (sg_nents_for_len(areq->src, areq->nbytes) > MAX_SG - 1) { + algt->stat_fb_maxsg++; return true; + } sg = areq->src; while (sg) { - if (sg->length % 4 || !IS_ALIGNED(sg->offset, sizeof(u32))) + if (sg->length % 4) { + algt->stat_fb_srclen++; return true; + } + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { + algt->stat_fb_srcali++; + return true; + } sg = sg_next(sg); } return false; @@ -228,7 +244,7 @@ int sun8i_ce_hash_digest(struct ahash_request *areq) if (sun8i_ce_hash_need_fallback(areq)) return sun8i_ce_hash_digest_fb(areq); - nr_sgs = sg_nents(areq->src); + nr_sgs = sg_nents_for_len(areq->src, areq->nbytes); if (nr_sgs > MAX_SG - 1) return sun8i_ce_hash_digest_fb(areq); @@ -247,6 +263,64 @@ int sun8i_ce_hash_digest(struct ahash_request *areq) return crypto_transfer_hash_request_to_engine(engine, areq); } +static u64 hash_pad(__le32 *buf, unsigned int bufsize, u64 padi, u64 byte_count, bool le, int bs) +{ + u64 fill, min_fill, j, k; + __be64 *bebits; + __le64 *lebits; + + j = padi; + buf[j++] = cpu_to_le32(0x80); + + if (bs == 64) { + fill = 64 - (byte_count % 64); + min_fill = 2 * sizeof(u32) + sizeof(u32); + } else { + fill = 128 - (byte_count % 128); + min_fill = 4 * sizeof(u32) + sizeof(u32); + } + + if (fill < min_fill) + fill += bs; + + k = j; + j += (fill - min_fill) / sizeof(u32); + if (j * 4 > bufsize) { + pr_err("%s OVERFLOW %llu\n", __func__, j); + return 0; + } + for (; k < j; k++) + buf[k] = 0; + + if (le) { + /* MD5 */ + lebits = (__le64 *)&buf[j]; + *lebits = cpu_to_le64(byte_count << 3); + j += 2; + } else { + if (bs == 64) { + /* sha1 sha224 sha256 */ + bebits = (__be64 *)&buf[j]; + *bebits = cpu_to_be64(byte_count << 3); + j += 2; + } else { + /* sha384 sha512*/ + bebits = (__be64 *)&buf[j]; + *bebits = cpu_to_be64(byte_count >> 61); + j += 2; + bebits = (__be64 *)&buf[j]; + *bebits = cpu_to_be64(byte_count << 3); + j += 2; + } + } + if (j * 4 > bufsize) { + pr_err("%s OVERFLOW %llu\n", __func__, j); + return 0; + } + + return j; +} + int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) { struct ahash_request *areq = container_of(breq, struct ahash_request, base); @@ -265,14 +339,11 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) __le32 *bf; void *buf = NULL; int j, i, todo; - int nbw = 0; - u64 fill, min_fill; - __be64 *bebits; - __le64 *lebits; void *result = NULL; u64 bs; int digestsize; dma_addr_t addr_res, addr_pad; + int ns = sg_nents_for_len(areq->src, areq->nbytes); algt = container_of(alg, struct sun8i_ce_alg_template, alg.hash); ce = algt->ce; @@ -317,7 +388,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) cet->t_sym_ctl = 0; cet->t_asym_ctl = 0; - nr_sgs = dma_map_sg(ce->dev, areq->src, sg_nents(areq->src), DMA_TO_DEVICE); + nr_sgs = dma_map_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE); if (nr_sgs <= 0 || nr_sgs > MAX_SG) { dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs); err = -EINVAL; @@ -347,44 +418,25 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) byte_count = areq->nbytes; j = 0; - bf[j++] = cpu_to_le32(0x80); - - if (bs == 64) { - fill = 64 - (byte_count % 64); - min_fill = 2 * sizeof(u32) + (nbw ? 0 : sizeof(u32)); - } else { - fill = 128 - (byte_count % 128); - min_fill = 4 * sizeof(u32) + (nbw ? 0 : sizeof(u32)); - } - - if (fill < min_fill) - fill += bs; - - j += (fill - min_fill) / sizeof(u32); switch (algt->ce_algo_id) { case CE_ID_HASH_MD5: - lebits = (__le64 *)&bf[j]; - *lebits = cpu_to_le64(byte_count << 3); - j += 2; + j = hash_pad(bf, 2 * bs, j, byte_count, true, bs); break; case CE_ID_HASH_SHA1: case CE_ID_HASH_SHA224: case CE_ID_HASH_SHA256: - bebits = (__be64 *)&bf[j]; - *bebits = cpu_to_be64(byte_count << 3); - j += 2; + j = hash_pad(bf, 2 * bs, j, byte_count, false, bs); break; case CE_ID_HASH_SHA384: case CE_ID_HASH_SHA512: - bebits = (__be64 *)&bf[j]; - *bebits = cpu_to_be64(byte_count >> 61); - j += 2; - bebits = (__be64 *)&bf[j]; - *bebits = cpu_to_be64(byte_count << 3); - j += 2; + j = hash_pad(bf, 2 * bs, j, byte_count, false, bs); break; } + if (!j) { + err = -EINVAL; + goto theend; + } addr_pad = dma_map_single(ce->dev, buf, j * 4, DMA_TO_DEVICE); cet->t_src[i].addr = cpu_to_le32(addr_pad); @@ -405,8 +457,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(areq->base.tfm)); dma_unmap_single(ce->dev, addr_pad, j * 4, DMA_TO_DEVICE); - dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src), - DMA_TO_DEVICE); + dma_unmap_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE); dma_unmap_single(ce->dev, addr_res, digestsize, DMA_FROM_DEVICE); @@ -414,6 +465,8 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) theend: kfree(buf); kfree(result); + local_bh_disable(); crypto_finalize_hash_request(engine, breq, err); + local_bh_enable(); return 0; } diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c index b3a9bbfb8831..b3cc43ea6c8a 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c @@ -108,11 +108,9 @@ int sun8i_ce_prng_generate(struct crypto_rng *tfm, const u8 *src, goto err_dst; } - err = pm_runtime_get_sync(ce->dev); - if (err < 0) { - pm_runtime_put_noidle(ce->dev); + err = pm_runtime_resume_and_get(ce->dev); + if (err < 0) goto err_pm; - } mutex_lock(&ce->rnglock); chan = &ce->chanlist[flow]; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c index 19cd2e52f89d..c4b0a8b58842 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c @@ -54,11 +54,9 @@ static int sun8i_ce_trng_read(struct hwrng *rng, void *data, size_t max, bool wa goto err_dst; } - err = pm_runtime_get_sync(ce->dev); - if (err < 0) { - pm_runtime_put_noidle(ce->dev); + err = pm_runtime_resume_and_get(ce->dev); + if (err < 0) goto err_pm; - } mutex_lock(&ce->rnglock); chan = &ce->chanlist[flow]; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h index 624a5926f21f..8177aaba4434 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h @@ -186,6 +186,8 @@ struct ce_task { * @status: set to 1 by interrupt if task is done * @t_phy: Physical address of task * @tl: pointer to the current ce_task for this flow + * @backup_iv: buffer which contain the next IV to store + * @bounce_iv: buffer which contain the IV * @stat_req: number of request done by this flow */ struct sun8i_ce_flow { @@ -195,6 +197,8 @@ struct sun8i_ce_flow { dma_addr_t t_phy; int timeout; struct ce_task *tl; + void *backup_iv; + void *bounce_iv; #ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG unsigned long stat_req; #endif @@ -241,8 +245,6 @@ struct sun8i_ce_dev { * struct sun8i_cipher_req_ctx - context for a skcipher request * @op_dir: direction (encrypt vs decrypt) for this request * @flow: the flow to use for this request - * @backup_iv: buffer which contain the next IV to store - * @bounce_iv: buffer which contain the IV * @ivlen: size of bounce_iv * @nr_sgs: The number of source SG (as given by dma_map_sg()) * @nr_sgd: The number of destination SG (as given by dma_map_sg()) @@ -253,8 +255,6 @@ struct sun8i_ce_dev { struct sun8i_cipher_req_ctx { u32 op_dir; int flow; - void *backup_iv; - void *bounce_iv; unsigned int ivlen; int nr_sgs; int nr_sgd; @@ -333,11 +333,18 @@ struct sun8i_ce_alg_template { struct ahash_alg hash; struct rng_alg rng; } alg; -#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG unsigned long stat_req; unsigned long stat_fb; unsigned long stat_bytes; -#endif + unsigned long stat_fb_maxsg; + unsigned long stat_fb_leniv; + unsigned long stat_fb_len0; + unsigned long stat_fb_mod16; + unsigned long stat_fb_srcali; + unsigned long stat_fb_srclen; + unsigned long stat_fb_dstali; + unsigned long stat_fb_dstlen; + char fbname[CRYPTO_MAX_ALG_NAME]; }; int sun8i_ce_enqueue(struct crypto_async_request *areq, u32 type); diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c index 9ef1c85c4aaa..910d6751644c 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c @@ -11,6 +11,7 @@ * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ +#include <linux/bottom_half.h> #include <linux/crypto.h> #include <linux/dma-mapping.h> #include <linux/io.h> @@ -21,34 +22,53 @@ static bool sun8i_ss_need_fallback(struct skcipher_request *areq) { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); + struct skcipher_alg *alg = crypto_skcipher_alg(tfm); + struct sun8i_ss_alg_template *algt = container_of(alg, struct sun8i_ss_alg_template, alg.skcipher); struct scatterlist *in_sg = areq->src; struct scatterlist *out_sg = areq->dst; struct scatterlist *sg; + unsigned int todo, len; - if (areq->cryptlen == 0 || areq->cryptlen % 16) + if (areq->cryptlen == 0 || areq->cryptlen % 16) { + algt->stat_fb_len++; return true; + } - if (sg_nents(areq->src) > 8 || sg_nents(areq->dst) > 8) + if (sg_nents_for_len(areq->src, areq->cryptlen) > 8 || + sg_nents_for_len(areq->dst, areq->cryptlen) > 8) { + algt->stat_fb_sgnum++; return true; + } + len = areq->cryptlen; sg = areq->src; while (sg) { - if ((sg->length % 16) != 0) - return true; - if ((sg_dma_len(sg) % 16) != 0) + todo = min(len, sg->length); + if ((todo % 16) != 0) { + algt->stat_fb_sglen++; return true; - if (!IS_ALIGNED(sg->offset, 16)) + } + if (!IS_ALIGNED(sg->offset, 16)) { + algt->stat_fb_align++; return true; + } + len -= todo; sg = sg_next(sg); } + len = areq->cryptlen; sg = areq->dst; while (sg) { - if ((sg->length % 16) != 0) - return true; - if ((sg_dma_len(sg) % 16) != 0) + todo = min(len, sg->length); + if ((todo % 16) != 0) { + algt->stat_fb_sglen++; return true; - if (!IS_ALIGNED(sg->offset, 16)) + } + if (!IS_ALIGNED(sg->offset, 16)) { + algt->stat_fb_align++; return true; + } + len -= todo; sg = sg_next(sg); } @@ -92,6 +112,69 @@ static int sun8i_ss_cipher_fallback(struct skcipher_request *areq) return err; } +static int sun8i_ss_setup_ivs(struct skcipher_request *areq) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); + struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); + struct sun8i_ss_dev *ss = op->ss; + struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq); + struct scatterlist *sg = areq->src; + unsigned int todo, offset; + unsigned int len = areq->cryptlen; + unsigned int ivsize = crypto_skcipher_ivsize(tfm); + struct sun8i_ss_flow *sf = &ss->flows[rctx->flow]; + int i = 0; + u32 a; + int err; + + rctx->ivlen = ivsize; + if (rctx->op_dir & SS_DECRYPTION) { + offset = areq->cryptlen - ivsize; + scatterwalk_map_and_copy(sf->biv, areq->src, offset, + ivsize, 0); + } + + /* we need to copy all IVs from source in case DMA is bi-directionnal */ + while (sg && len) { + if (sg_dma_len(sg) == 0) { + sg = sg_next(sg); + continue; + } + if (i == 0) + memcpy(sf->iv[0], areq->iv, ivsize); + a = dma_map_single(ss->dev, sf->iv[i], ivsize, DMA_TO_DEVICE); + if (dma_mapping_error(ss->dev, a)) { + memzero_explicit(sf->iv[i], ivsize); + dev_err(ss->dev, "Cannot DMA MAP IV\n"); + err = -EFAULT; + goto dma_iv_error; + } + rctx->p_iv[i] = a; + /* we need to setup all others IVs only in the decrypt way */ + if (rctx->op_dir & SS_ENCRYPTION) + return 0; + todo = min(len, sg_dma_len(sg)); + len -= todo; + i++; + if (i < MAX_SG) { + offset = sg->length - ivsize; + scatterwalk_map_and_copy(sf->iv[i], sg, offset, ivsize, 0); + } + rctx->niv = i; + sg = sg_next(sg); + } + + return 0; +dma_iv_error: + i--; + while (i >= 0) { + dma_unmap_single(ss->dev, rctx->p_iv[i], ivsize, DMA_TO_DEVICE); + memzero_explicit(sf->iv[i], ivsize); + i--; + } + return err; +} + static int sun8i_ss_cipher(struct skcipher_request *areq) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); @@ -100,12 +183,14 @@ static int sun8i_ss_cipher(struct skcipher_request *areq) struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(areq); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); struct sun8i_ss_alg_template *algt; + struct sun8i_ss_flow *sf = &ss->flows[rctx->flow]; struct scatterlist *sg; unsigned int todo, len, offset, ivsize; - void *backup_iv = NULL; int nr_sgs = 0; int nr_sgd = 0; int err = 0; + int nsgs = sg_nents_for_len(areq->src, areq->cryptlen); + int nsgd = sg_nents_for_len(areq->dst, areq->cryptlen); int i; algt = container_of(alg, struct sun8i_ss_alg_template, alg.skcipher); @@ -133,34 +218,12 @@ static int sun8i_ss_cipher(struct skcipher_request *areq) ivsize = crypto_skcipher_ivsize(tfm); if (areq->iv && crypto_skcipher_ivsize(tfm) > 0) { - rctx->ivlen = ivsize; - rctx->biv = kzalloc(ivsize, GFP_KERNEL | GFP_DMA); - if (!rctx->biv) { - err = -ENOMEM; + err = sun8i_ss_setup_ivs(areq); + if (err) goto theend_key; - } - if (rctx->op_dir & SS_DECRYPTION) { - backup_iv = kzalloc(ivsize, GFP_KERNEL); - if (!backup_iv) { - err = -ENOMEM; - goto theend_key; - } - offset = areq->cryptlen - ivsize; - scatterwalk_map_and_copy(backup_iv, areq->src, offset, - ivsize, 0); - } - memcpy(rctx->biv, areq->iv, ivsize); - rctx->p_iv = dma_map_single(ss->dev, rctx->biv, rctx->ivlen, - DMA_TO_DEVICE); - if (dma_mapping_error(ss->dev, rctx->p_iv)) { - dev_err(ss->dev, "Cannot DMA MAP IV\n"); - err = -ENOMEM; - goto theend_iv; - } } if (areq->src == areq->dst) { - nr_sgs = dma_map_sg(ss->dev, areq->src, sg_nents(areq->src), - DMA_BIDIRECTIONAL); + nr_sgs = dma_map_sg(ss->dev, areq->src, nsgs, DMA_BIDIRECTIONAL); if (nr_sgs <= 0 || nr_sgs > 8) { dev_err(ss->dev, "Invalid sg number %d\n", nr_sgs); err = -EINVAL; @@ -168,15 +231,13 @@ static int sun8i_ss_cipher(struct skcipher_request *areq) } nr_sgd = nr_sgs; } else { - nr_sgs = dma_map_sg(ss->dev, areq->src, sg_nents(areq->src), - DMA_TO_DEVICE); + nr_sgs = dma_map_sg(ss->dev, areq->src, nsgs, DMA_TO_DEVICE); if (nr_sgs <= 0 || nr_sgs > 8) { dev_err(ss->dev, "Invalid sg number %d\n", nr_sgs); err = -EINVAL; goto theend_iv; } - nr_sgd = dma_map_sg(ss->dev, areq->dst, sg_nents(areq->dst), - DMA_FROM_DEVICE); + nr_sgd = dma_map_sg(ss->dev, areq->dst, nsgd, DMA_FROM_DEVICE); if (nr_sgd <= 0 || nr_sgd > 8) { dev_err(ss->dev, "Invalid sg number %d\n", nr_sgd); err = -EINVAL; @@ -232,31 +293,26 @@ sgd_next: theend_sgs: if (areq->src == areq->dst) { - dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), - DMA_BIDIRECTIONAL); + dma_unmap_sg(ss->dev, areq->src, nsgs, DMA_BIDIRECTIONAL); } else { - dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), - DMA_TO_DEVICE); - dma_unmap_sg(ss->dev, areq->dst, sg_nents(areq->dst), - DMA_FROM_DEVICE); + dma_unmap_sg(ss->dev, areq->src, nsgs, DMA_TO_DEVICE); + dma_unmap_sg(ss->dev, areq->dst, nsgd, DMA_FROM_DEVICE); } theend_iv: - if (rctx->p_iv) - dma_unmap_single(ss->dev, rctx->p_iv, rctx->ivlen, - DMA_TO_DEVICE); - if (areq->iv && ivsize > 0) { - if (rctx->biv) { - offset = areq->cryptlen - ivsize; - if (rctx->op_dir & SS_DECRYPTION) { - memcpy(areq->iv, backup_iv, ivsize); - kfree_sensitive(backup_iv); - } else { - scatterwalk_map_and_copy(areq->iv, areq->dst, offset, - ivsize, 0); - } - kfree(rctx->biv); + for (i = 0; i < rctx->niv; i++) { + dma_unmap_single(ss->dev, rctx->p_iv[i], ivsize, DMA_TO_DEVICE); + memzero_explicit(sf->iv[i], ivsize); + } + + offset = areq->cryptlen - ivsize; + if (rctx->op_dir & SS_DECRYPTION) { + memcpy(areq->iv, sf->biv, ivsize); + memzero_explicit(sf->biv, ivsize); + } else { + scatterwalk_map_and_copy(areq->iv, areq->dst, offset, + ivsize, 0); } } @@ -274,7 +330,9 @@ static int sun8i_ss_handle_cipher_request(struct crypto_engine *engine, void *ar struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); err = sun8i_ss_cipher(breq); + local_bh_disable(); crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); return 0; } @@ -346,9 +404,9 @@ int sun8i_ss_cipher_init(struct crypto_tfm *tfm) crypto_skcipher_reqsize(op->fallback_tfm); - dev_info(op->ss->dev, "Fallback for %s is %s\n", - crypto_tfm_alg_driver_name(&sktfm->base), - crypto_tfm_alg_driver_name(crypto_skcipher_tfm(op->fallback_tfm))); + memcpy(algt->fbname, + crypto_tfm_alg_driver_name(crypto_skcipher_tfm(op->fallback_tfm)), + CRYPTO_MAX_ALG_NAME); op->enginectx.op.do_one_request = sun8i_ss_handle_cipher_request; op->enginectx.op.prepare_request = NULL; diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c index 80e89066dbd1..ac2329e2b0e5 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c @@ -30,6 +30,8 @@ static const struct ss_variant ss_a80_variant = { .alg_cipher = { SS_ALG_AES, SS_ALG_DES, SS_ALG_3DES, }, + .alg_hash = { SS_ID_NOTSUPP, SS_ID_NOTSUPP, SS_ID_NOTSUPP, SS_ID_NOTSUPP, + }, .op_mode = { SS_OP_ECB, SS_OP_CBC, }, .ss_clks = { @@ -64,6 +66,7 @@ int sun8i_ss_run_task(struct sun8i_ss_dev *ss, struct sun8i_cipher_req_ctx *rctx const char *name) { int flow = rctx->flow; + unsigned int ivlen = rctx->ivlen; u32 v = SS_START; int i; @@ -102,15 +105,14 @@ int sun8i_ss_run_task(struct sun8i_ss_dev *ss, struct sun8i_cipher_req_ctx *rctx mutex_lock(&ss->mlock); writel(rctx->p_key, ss->base + SS_KEY_ADR_REG); - if (i == 0) { - if (rctx->p_iv) - writel(rctx->p_iv, ss->base + SS_IV_ADR_REG); - } else { - if (rctx->biv) { - if (rctx->op_dir == SS_ENCRYPTION) - writel(rctx->t_dst[i - 1].addr + rctx->t_dst[i - 1].len * 4 - rctx->ivlen, ss->base + SS_IV_ADR_REG); + if (ivlen) { + if (rctx->op_dir == SS_ENCRYPTION) { + if (i == 0) + writel(rctx->p_iv[0], ss->base + SS_IV_ADR_REG); else - writel(rctx->t_src[i - 1].addr + rctx->t_src[i - 1].len * 4 - rctx->ivlen, ss->base + SS_IV_ADR_REG); + writel(rctx->t_dst[i - 1].addr + rctx->t_dst[i - 1].len * 4 - ivlen, ss->base + SS_IV_ADR_REG); + } else { + writel(rctx->p_iv[i], ss->base + SS_IV_ADR_REG); } } @@ -407,6 +409,37 @@ static struct sun8i_ss_alg_template ss_algs[] = { } } }, +{ .type = CRYPTO_ALG_TYPE_AHASH, + .ss_algo_id = SS_ID_HASH_SHA1, + .alg.hash = { + .init = sun8i_ss_hash_init, + .update = sun8i_ss_hash_update, + .final = sun8i_ss_hash_final, + .finup = sun8i_ss_hash_finup, + .digest = sun8i_ss_hash_digest, + .export = sun8i_ss_hash_export, + .import = sun8i_ss_hash_import, + .setkey = sun8i_ss_hmac_setkey, + .halg = { + .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct sha1_state), + .base = { + .cra_name = "hmac(sha1)", + .cra_driver_name = "hmac-sha1-sun8i-ss", + .cra_priority = 300, + .cra_alignmask = 3, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sun8i_ss_hash_tfm_ctx), + .cra_module = THIS_MODULE, + .cra_init = sun8i_ss_hash_crainit, + .cra_exit = sun8i_ss_hash_craexit, + } + } + } +}, #endif }; @@ -428,6 +461,17 @@ static int sun8i_ss_debugfs_show(struct seq_file *seq, void *v) ss_algs[i].alg.skcipher.base.cra_driver_name, ss_algs[i].alg.skcipher.base.cra_name, ss_algs[i].stat_req, ss_algs[i].stat_fb); + + seq_printf(seq, "\tLast fallback is: %s\n", + ss_algs[i].fbname); + seq_printf(seq, "\tFallback due to length: %lu\n", + ss_algs[i].stat_fb_len); + seq_printf(seq, "\tFallback due to SG length: %lu\n", + ss_algs[i].stat_fb_sglen); + seq_printf(seq, "\tFallback due to alignment: %lu\n", + ss_algs[i].stat_fb_align); + seq_printf(seq, "\tFallback due to SG numbers: %lu\n", + ss_algs[i].stat_fb_sgnum); break; case CRYPTO_ALG_TYPE_RNG: seq_printf(seq, "%s %s reqs=%lu tsize=%lu\n", @@ -440,6 +484,16 @@ static int sun8i_ss_debugfs_show(struct seq_file *seq, void *v) ss_algs[i].alg.hash.halg.base.cra_driver_name, ss_algs[i].alg.hash.halg.base.cra_name, ss_algs[i].stat_req, ss_algs[i].stat_fb); + seq_printf(seq, "\tLast fallback is: %s\n", + ss_algs[i].fbname); + seq_printf(seq, "\tFallback due to length: %lu\n", + ss_algs[i].stat_fb_len); + seq_printf(seq, "\tFallback due to SG length: %lu\n", + ss_algs[i].stat_fb_sglen); + seq_printf(seq, "\tFallback due to alignment: %lu\n", + ss_algs[i].stat_fb_align); + seq_printf(seq, "\tFallback due to SG numbers: %lu\n", + ss_algs[i].stat_fb_sgnum); break; } } @@ -462,7 +516,7 @@ static void sun8i_ss_free_flows(struct sun8i_ss_dev *ss, int i) */ static int allocate_flows(struct sun8i_ss_dev *ss) { - int i, err; + int i, j, err; ss->flows = devm_kcalloc(ss->dev, MAXFLOW, sizeof(struct sun8i_ss_flow), GFP_KERNEL); @@ -472,6 +526,36 @@ static int allocate_flows(struct sun8i_ss_dev *ss) for (i = 0; i < MAXFLOW; i++) { init_completion(&ss->flows[i].complete); + ss->flows[i].biv = devm_kmalloc(ss->dev, AES_BLOCK_SIZE, + GFP_KERNEL | GFP_DMA); + if (!ss->flows[i].biv) { + err = -ENOMEM; + goto error_engine; + } + + for (j = 0; j < MAX_SG; j++) { + ss->flows[i].iv[j] = devm_kmalloc(ss->dev, AES_BLOCK_SIZE, + GFP_KERNEL | GFP_DMA); + if (!ss->flows[i].iv[j]) { + err = -ENOMEM; + goto error_engine; + } + } + + /* the padding could be up to two block. */ + ss->flows[i].pad = devm_kmalloc(ss->dev, MAX_PAD_SIZE, + GFP_KERNEL | GFP_DMA); + if (!ss->flows[i].pad) { + err = -ENOMEM; + goto error_engine; + } + ss->flows[i].result = devm_kmalloc(ss->dev, SHA256_DIGEST_SIZE, + GFP_KERNEL | GFP_DMA); + if (!ss->flows[i].result) { + err = -ENOMEM; + goto error_engine; + } + ss->flows[i].engine = crypto_engine_alloc_init(ss->dev, true); if (!ss->flows[i].engine) { dev_err(ss->dev, "Cannot allocate engine\n"); diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c index 3c073eb3db03..36a82b22953c 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c @@ -9,15 +9,104 @@ * * You could find the datasheet in Documentation/arm/sunxi.rst */ +#include <linux/bottom_half.h> #include <linux/dma-mapping.h> #include <linux/pm_runtime.h> #include <linux/scatterlist.h> #include <crypto/internal/hash.h> +#include <crypto/hmac.h> +#include <crypto/scatterwalk.h> #include <crypto/sha1.h> #include <crypto/sha2.h> #include <crypto/md5.h> #include "sun8i-ss.h" +static int sun8i_ss_hashkey(struct sun8i_ss_hash_tfm_ctx *tfmctx, const u8 *key, + unsigned int keylen) +{ + struct crypto_shash *xtfm; + struct shash_desc *sdesc; + size_t len; + int ret = 0; + + xtfm = crypto_alloc_shash("sha1", 0, CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(xtfm)) + return PTR_ERR(xtfm); + + len = sizeof(*sdesc) + crypto_shash_descsize(xtfm); + sdesc = kmalloc(len, GFP_KERNEL); + if (!sdesc) { + ret = -ENOMEM; + goto err_hashkey_sdesc; + } + sdesc->tfm = xtfm; + + ret = crypto_shash_init(sdesc); + if (ret) { + dev_err(tfmctx->ss->dev, "shash init error ret=%d\n", ret); + goto err_hashkey; + } + ret = crypto_shash_finup(sdesc, key, keylen, tfmctx->key); + if (ret) + dev_err(tfmctx->ss->dev, "shash finup error\n"); +err_hashkey: + kfree(sdesc); +err_hashkey_sdesc: + crypto_free_shash(xtfm); + return ret; +} + +int sun8i_ss_hmac_setkey(struct crypto_ahash *ahash, const u8 *key, + unsigned int keylen) +{ + struct sun8i_ss_hash_tfm_ctx *tfmctx = crypto_ahash_ctx(ahash); + struct ahash_alg *alg = __crypto_ahash_alg(ahash->base.__crt_alg); + struct sun8i_ss_alg_template *algt; + int digestsize, i; + int bs = crypto_ahash_blocksize(ahash); + int ret; + + algt = container_of(alg, struct sun8i_ss_alg_template, alg.hash); + digestsize = algt->alg.hash.halg.digestsize; + + if (keylen > bs) { + ret = sun8i_ss_hashkey(tfmctx, key, keylen); + if (ret) + return ret; + tfmctx->keylen = digestsize; + } else { + tfmctx->keylen = keylen; + memcpy(tfmctx->key, key, keylen); + } + + tfmctx->ipad = kzalloc(bs, GFP_KERNEL | GFP_DMA); + if (!tfmctx->ipad) + return -ENOMEM; + tfmctx->opad = kzalloc(bs, GFP_KERNEL | GFP_DMA); + if (!tfmctx->opad) { + ret = -ENOMEM; + goto err_opad; + } + + memset(tfmctx->key + tfmctx->keylen, 0, bs - tfmctx->keylen); + memcpy(tfmctx->ipad, tfmctx->key, tfmctx->keylen); + memcpy(tfmctx->opad, tfmctx->key, tfmctx->keylen); + for (i = 0; i < bs; i++) { + tfmctx->ipad[i] ^= HMAC_IPAD_VALUE; + tfmctx->opad[i] ^= HMAC_OPAD_VALUE; + } + + ret = crypto_ahash_setkey(tfmctx->fallback_tfm, key, keylen); + if (!ret) + return 0; + + memzero_explicit(tfmctx->key, keylen); + kfree_sensitive(tfmctx->opad); +err_opad: + kfree_sensitive(tfmctx->ipad); + return ret; +} + int sun8i_ss_hash_crainit(struct crypto_tfm *tfm) { struct sun8i_ss_hash_tfm_ctx *op = crypto_tfm_ctx(tfm); @@ -49,9 +138,8 @@ int sun8i_ss_hash_crainit(struct crypto_tfm *tfm) sizeof(struct sun8i_ss_hash_reqctx) + crypto_ahash_reqsize(op->fallback_tfm)); - dev_info(op->ss->dev, "Fallback for %s is %s\n", - crypto_tfm_alg_driver_name(tfm), - crypto_tfm_alg_driver_name(&op->fallback_tfm->base)); + memcpy(algt->fbname, crypto_tfm_alg_driver_name(&op->fallback_tfm->base), CRYPTO_MAX_ALG_NAME); + err = pm_runtime_get_sync(op->ss->dev); if (err < 0) goto error_pm; @@ -66,6 +154,9 @@ void sun8i_ss_hash_craexit(struct crypto_tfm *tfm) { struct sun8i_ss_hash_tfm_ctx *tfmctx = crypto_tfm_ctx(tfm); + kfree_sensitive(tfmctx->ipad); + kfree_sensitive(tfmctx->opad); + crypto_free_ahash(tfmctx->fallback_tfm); pm_runtime_put_sync_suspend(tfmctx->ss->dev); } @@ -257,23 +348,48 @@ static int sun8i_ss_run_hash_task(struct sun8i_ss_dev *ss, static bool sun8i_ss_hash_need_fallback(struct ahash_request *areq) { + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct ahash_alg *alg = __crypto_ahash_alg(tfm->base.__crt_alg); + struct sun8i_ss_alg_template *algt; struct scatterlist *sg; - if (areq->nbytes == 0) + algt = container_of(alg, struct sun8i_ss_alg_template, alg.hash); + + if (areq->nbytes == 0) { + algt->stat_fb_len++; return true; + } + + if (areq->nbytes >= MAX_PAD_SIZE - 64) { + algt->stat_fb_len++; + return true; + } + /* we need to reserve one SG for the padding one */ - if (sg_nents(areq->src) > MAX_SG - 1) + if (sg_nents(areq->src) > MAX_SG - 1) { + algt->stat_fb_sgnum++; return true; + } + sg = areq->src; while (sg) { /* SS can operate hash only on full block size * since SS support only MD5,sha1,sha224 and sha256, blocksize * is always 64 - * TODO: handle request if last SG is not len%64 - * but this will need to copy data on a new SG of size=64 */ - if (sg->length % 64 || !IS_ALIGNED(sg->offset, sizeof(u32))) + /* Only the last block could be bounced to the pad buffer */ + if (sg->length % 64 && sg_next(sg)) { + algt->stat_fb_sglen++; + return true; + } + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { + algt->stat_fb_align++; return true; + } + if (sg->length % 4) { + algt->stat_fb_sglen++; + return true; + } sg = sg_next(sg); } return false; @@ -287,21 +403,11 @@ int sun8i_ss_hash_digest(struct ahash_request *areq) struct sun8i_ss_alg_template *algt; struct sun8i_ss_dev *ss; struct crypto_engine *engine; - struct scatterlist *sg; - int nr_sgs, e, i; + int e; if (sun8i_ss_hash_need_fallback(areq)) return sun8i_ss_hash_digest_fb(areq); - nr_sgs = sg_nents(areq->src); - if (nr_sgs > MAX_SG - 1) - return sun8i_ss_hash_digest_fb(areq); - - for_each_sg(areq->src, sg, nr_sgs, i) { - if (sg->length % 4 || !IS_ALIGNED(sg->offset, sizeof(u32))) - return sun8i_ss_hash_digest_fb(areq); - } - algt = container_of(alg, struct sun8i_ss_alg_template, alg.hash); ss = algt->ss; @@ -312,6 +418,64 @@ int sun8i_ss_hash_digest(struct ahash_request *areq) return crypto_transfer_hash_request_to_engine(engine, areq); } +static u64 hash_pad(__le32 *buf, unsigned int bufsize, u64 padi, u64 byte_count, bool le, int bs) +{ + u64 fill, min_fill, j, k; + __be64 *bebits; + __le64 *lebits; + + j = padi; + buf[j++] = cpu_to_le32(0x80); + + if (bs == 64) { + fill = 64 - (byte_count % 64); + min_fill = 2 * sizeof(u32) + sizeof(u32); + } else { + fill = 128 - (byte_count % 128); + min_fill = 4 * sizeof(u32) + sizeof(u32); + } + + if (fill < min_fill) + fill += bs; + + k = j; + j += (fill - min_fill) / sizeof(u32); + if (j * 4 > bufsize) { + pr_err("%s OVERFLOW %llu\n", __func__, j); + return 0; + } + for (; k < j; k++) + buf[k] = 0; + + if (le) { + /* MD5 */ + lebits = (__le64 *)&buf[j]; + *lebits = cpu_to_le64(byte_count << 3); + j += 2; + } else { + if (bs == 64) { + /* sha1 sha224 sha256 */ + bebits = (__be64 *)&buf[j]; + *bebits = cpu_to_be64(byte_count << 3); + j += 2; + } else { + /* sha384 sha512*/ + bebits = (__be64 *)&buf[j]; + *bebits = cpu_to_be64(byte_count >> 61); + j += 2; + bebits = (__be64 *)&buf[j]; + *bebits = cpu_to_be64(byte_count << 3); + j += 2; + } + } + if (j * 4 > bufsize) { + pr_err("%s OVERFLOW %llu\n", __func__, j); + return 0; + } + + return j; +} + /* sun8i_ss_hash_run - run an ahash request * Send the data of the request to the SS along with an extra SG with padding */ @@ -319,20 +483,26 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq) { struct ahash_request *areq = container_of(breq, struct ahash_request, base); struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct sun8i_ss_hash_tfm_ctx *tfmctx = crypto_ahash_ctx(tfm); struct ahash_alg *alg = __crypto_ahash_alg(tfm->base.__crt_alg); struct sun8i_ss_hash_reqctx *rctx = ahash_request_ctx(areq); struct sun8i_ss_alg_template *algt; struct sun8i_ss_dev *ss; struct scatterlist *sg; + int bs = crypto_ahash_blocksize(tfm); int nr_sgs, err, digestsize; unsigned int len; - u64 fill, min_fill, byte_count; + u64 byte_count; void *pad, *result; - int j, i, todo; - __be64 *bebits; - __le64 *lebits; - dma_addr_t addr_res, addr_pad; + int j, i, k, todo; + dma_addr_t addr_res, addr_pad, addr_xpad; __le32 *bf; + /* HMAC step: + * 0: normal hashing + * 1: IPAD + * 2: OPAD + */ + int hmac = 0; algt = container_of(alg, struct sun8i_ss_alg_template, alg.hash); ss = algt->ss; @@ -341,18 +511,10 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq) if (digestsize == SHA224_DIGEST_SIZE) digestsize = SHA256_DIGEST_SIZE; - /* the padding could be up to two block. */ - pad = kzalloc(algt->alg.hash.halg.base.cra_blocksize * 2, GFP_KERNEL | GFP_DMA); - if (!pad) - return -ENOMEM; + result = ss->flows[rctx->flow].result; + pad = ss->flows[rctx->flow].pad; bf = (__le32 *)pad; - result = kzalloc(digestsize, GFP_KERNEL | GFP_DMA); - if (!result) { - kfree(pad); - return -ENOMEM; - } - for (i = 0; i < MAX_SG; i++) { rctx->t_dst[i].addr = 0; rctx->t_dst[i].len = 0; @@ -375,17 +537,33 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq) if (dma_mapping_error(ss->dev, addr_res)) { dev_err(ss->dev, "DMA map dest\n"); err = -EINVAL; - goto theend; + goto err_dma_result; } + j = 0; len = areq->nbytes; - for_each_sg(areq->src, sg, nr_sgs, i) { - rctx->t_src[i].addr = sg_dma_address(sg); + sg = areq->src; + i = 0; + while (len > 0 && sg) { + if (sg_dma_len(sg) == 0) { + sg = sg_next(sg); + continue; + } todo = min(len, sg_dma_len(sg)); - rctx->t_src[i].len = todo / 4; - len -= todo; - rctx->t_dst[i].addr = addr_res; - rctx->t_dst[i].len = digestsize / 4; + /* only the last SG could be with a size not modulo64 */ + if (todo % 64 == 0) { + rctx->t_src[i].addr = sg_dma_address(sg); + rctx->t_src[i].len = todo / 4; + rctx->t_dst[i].addr = addr_res; + rctx->t_dst[i].len = digestsize / 4; + len -= todo; + } else { + scatterwalk_map_and_copy(bf, sg, 0, todo, 0); + j += todo / 4; + len -= todo; + } + sg = sg_next(sg); + i++; } if (len > 0) { dev_err(ss->dev, "remaining len %d\n", len); @@ -393,55 +571,139 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq) goto theend; } + if (j > 0) + i--; + +retry: byte_count = areq->nbytes; - j = 0; - bf[j++] = cpu_to_le32(0x80); + if (tfmctx->keylen && hmac == 0) { + hmac = 1; + /* shift all SG one slot up, to free slot 0 for IPAD */ + for (k = 6; k >= 0; k--) { + rctx->t_src[k + 1].addr = rctx->t_src[k].addr; + rctx->t_src[k + 1].len = rctx->t_src[k].len; + rctx->t_dst[k + 1].addr = rctx->t_dst[k].addr; + rctx->t_dst[k + 1].len = rctx->t_dst[k].len; + } + addr_xpad = dma_map_single(ss->dev, tfmctx->ipad, bs, DMA_TO_DEVICE); + err = dma_mapping_error(ss->dev, addr_xpad); + if (err) { + dev_err(ss->dev, "Fail to create DMA mapping of ipad\n"); + goto err_dma_xpad; + } + rctx->t_src[0].addr = addr_xpad; + rctx->t_src[0].len = bs / 4; + rctx->t_dst[0].addr = addr_res; + rctx->t_dst[0].len = digestsize / 4; + i++; + byte_count = areq->nbytes + bs; + } + if (tfmctx->keylen && hmac == 2) { + for (i = 0; i < MAX_SG; i++) { + rctx->t_src[i].addr = 0; + rctx->t_src[i].len = 0; + rctx->t_dst[i].addr = 0; + rctx->t_dst[i].len = 0; + } - fill = 64 - (byte_count % 64); - min_fill = 3 * sizeof(u32); + addr_res = dma_map_single(ss->dev, result, digestsize, DMA_FROM_DEVICE); + if (dma_mapping_error(ss->dev, addr_res)) { + dev_err(ss->dev, "Fail to create DMA mapping of result\n"); + err = -EINVAL; + goto err_dma_result; + } + addr_xpad = dma_map_single(ss->dev, tfmctx->opad, bs, DMA_TO_DEVICE); + err = dma_mapping_error(ss->dev, addr_xpad); + if (err) { + dev_err(ss->dev, "Fail to create DMA mapping of opad\n"); + goto err_dma_xpad; + } + rctx->t_src[0].addr = addr_xpad; + rctx->t_src[0].len = bs / 4; - if (fill < min_fill) - fill += 64; + memcpy(bf, result, digestsize); + j = digestsize / 4; + i = 1; + byte_count = digestsize + bs; - j += (fill - min_fill) / sizeof(u32); + rctx->t_dst[0].addr = addr_res; + rctx->t_dst[0].len = digestsize / 4; + } switch (algt->ss_algo_id) { case SS_ID_HASH_MD5: - lebits = (__le64 *)&bf[j]; - *lebits = cpu_to_le64(byte_count << 3); - j += 2; + j = hash_pad(bf, 4096, j, byte_count, true, bs); break; case SS_ID_HASH_SHA1: case SS_ID_HASH_SHA224: case SS_ID_HASH_SHA256: - bebits = (__be64 *)&bf[j]; - *bebits = cpu_to_be64(byte_count << 3); - j += 2; + j = hash_pad(bf, 4096, j, byte_count, false, bs); break; } + if (!j) { + err = -EINVAL; + goto theend; + } addr_pad = dma_map_single(ss->dev, pad, j * 4, DMA_TO_DEVICE); - rctx->t_src[i].addr = addr_pad; - rctx->t_src[i].len = j; - rctx->t_dst[i].addr = addr_res; - rctx->t_dst[i].len = digestsize / 4; if (dma_mapping_error(ss->dev, addr_pad)) { dev_err(ss->dev, "DMA error on padding SG\n"); err = -EINVAL; - goto theend; + goto err_dma_pad; } + rctx->t_src[i].addr = addr_pad; + rctx->t_src[i].len = j; + rctx->t_dst[i].addr = addr_res; + rctx->t_dst[i].len = digestsize / 4; err = sun8i_ss_run_hash_task(ss, rctx, crypto_tfm_alg_name(areq->base.tfm)); + /* + * mini helper for checking dma map/unmap + * flow start for hmac = 0 (and HMAC = 1) + * HMAC = 0 + * MAP src + * MAP res + * + * retry: + * if hmac then hmac = 1 + * MAP xpad (ipad) + * if hmac == 2 + * MAP res + * MAP xpad (opad) + * MAP pad + * ACTION! + * UNMAP pad + * if hmac + * UNMAP xpad + * UNMAP res + * if hmac < 2 + * UNMAP SRC + * + * if hmac = 1 then hmac = 2 goto retry + */ + dma_unmap_single(ss->dev, addr_pad, j * 4, DMA_TO_DEVICE); - dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), - DMA_TO_DEVICE); + +err_dma_pad: + if (hmac > 0) + dma_unmap_single(ss->dev, addr_xpad, bs, DMA_TO_DEVICE); +err_dma_xpad: dma_unmap_single(ss->dev, addr_res, digestsize, DMA_FROM_DEVICE); +err_dma_result: + if (hmac < 2) + dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), + DMA_TO_DEVICE); + if (hmac == 1 && !err) { + hmac = 2; + goto retry; + } - memcpy(areq->result, result, algt->alg.hash.halg.digestsize); + if (!err) + memcpy(areq->result, result, algt->alg.hash.halg.digestsize); theend: - kfree(pad); - kfree(result); + local_bh_disable(); crypto_finalize_hash_request(engine, breq, err); + local_bh_enable(); return 0; } diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c index 246a6782674c..dd677e9ed06f 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c @@ -112,11 +112,9 @@ int sun8i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, goto err_iv; } - err = pm_runtime_get_sync(ss->dev); - if (err < 0) { - pm_runtime_put_noidle(ss->dev); + err = pm_runtime_resume_and_get(ss->dev); + if (err < 0) goto err_pm; - } err = 0; mutex_lock(&ss->mlock); diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h index 28188685b910..df6f08f6092f 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h @@ -82,6 +82,8 @@ #define PRNG_DATA_SIZE (160 / 8) #define PRNG_SEED_SIZE DIV_ROUND_UP(175, 8) +#define MAX_PAD_SIZE 4096 + /* * struct ss_clock - Describe clocks used by sun8i-ss * @name: Name of clock needed by this variant @@ -121,11 +123,19 @@ struct sginfo { * @complete: completion for the current task on this flow * @status: set to 1 by interrupt if task is done * @stat_req: number of request done by this flow + * @iv: list of IV to use for each step + * @biv: buffer which contain the backuped IV + * @pad: padding buffer for hash operations + * @result: buffer for storing the result of hash operations */ struct sun8i_ss_flow { struct crypto_engine *engine; struct completion complete; int status; + u8 *iv[MAX_SG]; + u8 *biv; + void *pad; + void *result; #ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG unsigned long stat_req; #endif @@ -164,28 +174,28 @@ struct sun8i_ss_dev { * @t_src: list of mapped SGs with their size * @t_dst: list of mapped SGs with their size * @p_key: DMA address of the key - * @p_iv: DMA address of the IV + * @p_iv: DMA address of the IVs + * @niv: Number of IVs DMA mapped * @method: current algorithm for this request * @op_mode: op_mode for this request * @op_dir: direction (encrypt vs decrypt) for this request * @flow: the flow to use for this request - * @ivlen: size of biv + * @ivlen: size of IVs * @keylen: keylen for this request - * @biv: buffer which contain the IV * @fallback_req: request struct for invoking the fallback skcipher TFM */ struct sun8i_cipher_req_ctx { struct sginfo t_src[MAX_SG]; struct sginfo t_dst[MAX_SG]; u32 p_key; - u32 p_iv; + u32 p_iv[MAX_SG]; + int niv; u32 method; u32 op_mode; u32 op_dir; int flow; unsigned int ivlen; unsigned int keylen; - void *biv; struct skcipher_request fallback_req; // keep at the end }; @@ -229,6 +239,10 @@ struct sun8i_ss_hash_tfm_ctx { struct crypto_engine_ctx enginectx; struct crypto_ahash *fallback_tfm; struct sun8i_ss_dev *ss; + u8 *ipad; + u8 *opad; + u8 key[SHA256_BLOCK_SIZE]; + int keylen; }; /* @@ -269,11 +283,14 @@ struct sun8i_ss_alg_template { struct rng_alg rng; struct ahash_alg hash; } alg; -#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG unsigned long stat_req; unsigned long stat_fb; unsigned long stat_bytes; -#endif + unsigned long stat_fb_len; + unsigned long stat_fb_sglen; + unsigned long stat_fb_align; + unsigned long stat_fb_sgnum; + char fbname[CRYPTO_MAX_ALG_NAME]; }; int sun8i_ss_enqueue(struct crypto_async_request *areq, u32 type); @@ -306,3 +323,5 @@ int sun8i_ss_hash_update(struct ahash_request *areq); int sun8i_ss_hash_finup(struct ahash_request *areq); int sun8i_ss_hash_digest(struct ahash_request *areq); int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq); +int sun8i_ss_hmac_setkey(struct crypto_ahash *ahash, const u8 *key, + unsigned int keylen); diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c index 8278d98074e9..280f4b0e7133 100644 --- a/drivers/crypto/amcc/crypto4xx_core.c +++ b/drivers/crypto/amcc/crypto4xx_core.c @@ -1378,6 +1378,7 @@ static int crypto4xx_probe(struct platform_device *ofdev) struct resource res; struct device *dev = &ofdev->dev; struct crypto4xx_core_device *core_dev; + struct device_node *np; u32 pvr; bool is_revb = true; @@ -1385,29 +1386,36 @@ static int crypto4xx_probe(struct platform_device *ofdev) if (rc) return -ENODEV; - if (of_find_compatible_node(NULL, NULL, "amcc,ppc460ex-crypto")) { + np = of_find_compatible_node(NULL, NULL, "amcc,ppc460ex-crypto"); + if (np) { mtdcri(SDR0, PPC460EX_SDR0_SRST, mfdcri(SDR0, PPC460EX_SDR0_SRST) | PPC460EX_CE_RESET); mtdcri(SDR0, PPC460EX_SDR0_SRST, mfdcri(SDR0, PPC460EX_SDR0_SRST) & ~PPC460EX_CE_RESET); - } else if (of_find_compatible_node(NULL, NULL, - "amcc,ppc405ex-crypto")) { - mtdcri(SDR0, PPC405EX_SDR0_SRST, - mfdcri(SDR0, PPC405EX_SDR0_SRST) | PPC405EX_CE_RESET); - mtdcri(SDR0, PPC405EX_SDR0_SRST, - mfdcri(SDR0, PPC405EX_SDR0_SRST) & ~PPC405EX_CE_RESET); - is_revb = false; - } else if (of_find_compatible_node(NULL, NULL, - "amcc,ppc460sx-crypto")) { - mtdcri(SDR0, PPC460SX_SDR0_SRST, - mfdcri(SDR0, PPC460SX_SDR0_SRST) | PPC460SX_CE_RESET); - mtdcri(SDR0, PPC460SX_SDR0_SRST, - mfdcri(SDR0, PPC460SX_SDR0_SRST) & ~PPC460SX_CE_RESET); } else { - printk(KERN_ERR "Crypto Function Not supported!\n"); - return -EINVAL; + np = of_find_compatible_node(NULL, NULL, "amcc,ppc405ex-crypto"); + if (np) { + mtdcri(SDR0, PPC405EX_SDR0_SRST, + mfdcri(SDR0, PPC405EX_SDR0_SRST) | PPC405EX_CE_RESET); + mtdcri(SDR0, PPC405EX_SDR0_SRST, + mfdcri(SDR0, PPC405EX_SDR0_SRST) & ~PPC405EX_CE_RESET); + is_revb = false; + } else { + np = of_find_compatible_node(NULL, NULL, "amcc,ppc460sx-crypto"); + if (np) { + mtdcri(SDR0, PPC460SX_SDR0_SRST, + mfdcri(SDR0, PPC460SX_SDR0_SRST) | PPC460SX_CE_RESET); + mtdcri(SDR0, PPC460SX_SDR0_SRST, + mfdcri(SDR0, PPC460SX_SDR0_SRST) & ~PPC460SX_CE_RESET); + } else { + printk(KERN_ERR "Crypto Function Not supported!\n"); + return -EINVAL; + } + } } + of_node_put(np); + core_dev = kzalloc(sizeof(struct crypto4xx_core_device), GFP_KERNEL); if (!core_dev) return -ENOMEM; diff --git a/drivers/crypto/amlogic/amlogic-gxl-cipher.c b/drivers/crypto/amlogic/amlogic-gxl-cipher.c index c6865cbd334b..af017a087ebf 100644 --- a/drivers/crypto/amlogic/amlogic-gxl-cipher.c +++ b/drivers/crypto/amlogic/amlogic-gxl-cipher.c @@ -177,7 +177,7 @@ static int meson_cipher(struct skcipher_request *areq) if (areq->src == areq->dst) { nr_sgs = dma_map_sg(mc->dev, areq->src, sg_nents(areq->src), DMA_BIDIRECTIONAL); - if (nr_sgs < 0) { + if (!nr_sgs) { dev_err(mc->dev, "Invalid SG count %d\n", nr_sgs); err = -EINVAL; goto theend; @@ -186,14 +186,14 @@ static int meson_cipher(struct skcipher_request *areq) } else { nr_sgs = dma_map_sg(mc->dev, areq->src, sg_nents(areq->src), DMA_TO_DEVICE); - if (nr_sgs < 0 || nr_sgs > MAXDESC - 3) { + if (!nr_sgs || nr_sgs > MAXDESC - 3) { dev_err(mc->dev, "Invalid SG count %d\n", nr_sgs); err = -EINVAL; goto theend; } nr_sgd = dma_map_sg(mc->dev, areq->dst, sg_nents(areq->dst), DMA_FROM_DEVICE); - if (nr_sgd < 0 || nr_sgd > MAXDESC - 3) { + if (!nr_sgd || nr_sgd > MAXDESC - 3) { dev_err(mc->dev, "Invalid SG count %d\n", nr_sgd); err = -EINVAL; goto theend; @@ -265,7 +265,9 @@ static int meson_handle_cipher_request(struct crypto_engine *engine, struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); err = meson_cipher(breq); + local_bh_disable(); crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); return 0; } diff --git a/drivers/crypto/aspeed/Kconfig b/drivers/crypto/aspeed/Kconfig new file mode 100644 index 000000000000..ae2710ae8d8f --- /dev/null +++ b/drivers/crypto/aspeed/Kconfig @@ -0,0 +1,48 @@ +config CRYPTO_DEV_ASPEED + tristate "Support for Aspeed cryptographic engine driver" + depends on ARCH_ASPEED || COMPILE_TEST + select CRYPTO_ENGINE + help + Hash and Crypto Engine (HACE) is designed to accelerate the + throughput of hash data digest, encryption and decryption. + + Select y here to have support for the cryptographic driver + available on Aspeed SoC. + +config CRYPTO_DEV_ASPEED_DEBUG + bool "Enable Aspeed crypto debug messages" + depends on CRYPTO_DEV_ASPEED + help + Print Aspeed crypto debugging messages if you use this + option to ask for those messages. + Avoid enabling this option for production build to + minimize driver timing. + +config CRYPTO_DEV_ASPEED_HACE_HASH + bool "Enable Aspeed Hash & Crypto Engine (HACE) hash" + depends on CRYPTO_DEV_ASPEED + select CRYPTO_SHA1 + select CRYPTO_SHA256 + select CRYPTO_SHA512 + select CRYPTO_HMAC + help + Select here to enable Aspeed Hash & Crypto Engine (HACE) + hash driver. + Supports multiple message digest standards, including + SHA-1, SHA-224, SHA-256, SHA-384, SHA-512, and so on. + +config CRYPTO_DEV_ASPEED_HACE_CRYPTO + bool "Enable Aspeed Hash & Crypto Engine (HACE) crypto" + depends on CRYPTO_DEV_ASPEED + select CRYPTO_AES + select CRYPTO_DES + select CRYPTO_ECB + select CRYPTO_CBC + select CRYPTO_CFB + select CRYPTO_OFB + select CRYPTO_CTR + help + Select here to enable Aspeed Hash & Crypto Engine (HACE) + crypto driver. + Supports AES/DES symmetric-key encryption and decryption + with ECB/CBC/CFB/OFB/CTR options. diff --git a/drivers/crypto/aspeed/Makefile b/drivers/crypto/aspeed/Makefile new file mode 100644 index 000000000000..a0ed40ddaad1 --- /dev/null +++ b/drivers/crypto/aspeed/Makefile @@ -0,0 +1,7 @@ +hace-hash-$(CONFIG_CRYPTO_DEV_ASPEED_HACE_HASH) := aspeed-hace-hash.o +hace-crypto-$(CONFIG_CRYPTO_DEV_ASPEED_HACE_CRYPTO) := aspeed-hace-crypto.o + +obj-$(CONFIG_CRYPTO_DEV_ASPEED) += aspeed_crypto.o +aspeed_crypto-objs := aspeed-hace.o \ + $(hace-hash-y) \ + $(hace-crypto-y) diff --git a/drivers/crypto/aspeed/aspeed-hace-crypto.c b/drivers/crypto/aspeed/aspeed-hace-crypto.c new file mode 100644 index 000000000000..ef73b0028b4d --- /dev/null +++ b/drivers/crypto/aspeed/aspeed-hace-crypto.c @@ -0,0 +1,1133 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2021 Aspeed Technology Inc. + */ + +#include "aspeed-hace.h" + +#ifdef CONFIG_CRYPTO_DEV_ASPEED_HACE_CRYPTO_DEBUG +#define CIPHER_DBG(h, fmt, ...) \ + dev_info((h)->dev, "%s() " fmt, __func__, ##__VA_ARGS__) +#else +#define CIPHER_DBG(h, fmt, ...) \ + dev_dbg((h)->dev, "%s() " fmt, __func__, ##__VA_ARGS__) +#endif + +static int aspeed_crypto_do_fallback(struct skcipher_request *areq) +{ + struct aspeed_cipher_reqctx *rctx = skcipher_request_ctx(areq); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + int err; + + skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); + skcipher_request_set_callback(&rctx->fallback_req, areq->base.flags, + areq->base.complete, areq->base.data); + skcipher_request_set_crypt(&rctx->fallback_req, areq->src, areq->dst, + areq->cryptlen, areq->iv); + + if (rctx->enc_cmd & HACE_CMD_ENCRYPT) + err = crypto_skcipher_encrypt(&rctx->fallback_req); + else + err = crypto_skcipher_decrypt(&rctx->fallback_req); + + return err; +} + +static bool aspeed_crypto_need_fallback(struct skcipher_request *areq) +{ + struct aspeed_cipher_reqctx *rctx = skcipher_request_ctx(areq); + + if (areq->cryptlen == 0) + return true; + + if ((rctx->enc_cmd & HACE_CMD_DES_SELECT) && + !IS_ALIGNED(areq->cryptlen, DES_BLOCK_SIZE)) + return true; + + if ((!(rctx->enc_cmd & HACE_CMD_DES_SELECT)) && + !IS_ALIGNED(areq->cryptlen, AES_BLOCK_SIZE)) + return true; + + return false; +} + +static int aspeed_hace_crypto_handle_queue(struct aspeed_hace_dev *hace_dev, + struct skcipher_request *req) +{ + if (hace_dev->version == AST2500_VERSION && + aspeed_crypto_need_fallback(req)) { + CIPHER_DBG(hace_dev, "SW fallback\n"); + return aspeed_crypto_do_fallback(req); + } + + return crypto_transfer_skcipher_request_to_engine( + hace_dev->crypt_engine_crypto, req); +} + +static int aspeed_crypto_do_request(struct crypto_engine *engine, void *areq) +{ + struct skcipher_request *req = skcipher_request_cast(areq); + struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req); + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); + struct aspeed_hace_dev *hace_dev = ctx->hace_dev; + struct aspeed_engine_crypto *crypto_engine; + int rc; + + crypto_engine = &hace_dev->crypto_engine; + crypto_engine->req = req; + crypto_engine->flags |= CRYPTO_FLAGS_BUSY; + + rc = ctx->start(hace_dev); + + if (rc != -EINPROGRESS) + return -EIO; + + return 0; +} + +static int aspeed_sk_complete(struct aspeed_hace_dev *hace_dev, int err) +{ + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_cipher_reqctx *rctx; + struct skcipher_request *req; + + CIPHER_DBG(hace_dev, "\n"); + + req = crypto_engine->req; + rctx = skcipher_request_ctx(req); + + if (rctx->enc_cmd & HACE_CMD_IV_REQUIRE) { + if (rctx->enc_cmd & HACE_CMD_DES_SELECT) + memcpy(req->iv, crypto_engine->cipher_ctx + + DES_KEY_SIZE, DES_KEY_SIZE); + else + memcpy(req->iv, crypto_engine->cipher_ctx, + AES_BLOCK_SIZE); + } + + crypto_engine->flags &= ~CRYPTO_FLAGS_BUSY; + + crypto_finalize_skcipher_request(hace_dev->crypt_engine_crypto, req, + err); + + return err; +} + +static int aspeed_sk_transfer_sg(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct device *dev = hace_dev->dev; + struct aspeed_cipher_reqctx *rctx; + struct skcipher_request *req; + + CIPHER_DBG(hace_dev, "\n"); + + req = crypto_engine->req; + rctx = skcipher_request_ctx(req); + + if (req->src == req->dst) { + dma_unmap_sg(dev, req->src, rctx->src_nents, DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(dev, req->src, rctx->src_nents, DMA_TO_DEVICE); + dma_unmap_sg(dev, req->dst, rctx->dst_nents, DMA_FROM_DEVICE); + } + + return aspeed_sk_complete(hace_dev, 0); +} + +static int aspeed_sk_transfer(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_cipher_reqctx *rctx; + struct skcipher_request *req; + struct scatterlist *out_sg; + int nbytes = 0; + int rc = 0; + + req = crypto_engine->req; + rctx = skcipher_request_ctx(req); + out_sg = req->dst; + + /* Copy output buffer to dst scatter-gather lists */ + nbytes = sg_copy_from_buffer(out_sg, rctx->dst_nents, + crypto_engine->cipher_addr, req->cryptlen); + if (!nbytes) { + dev_warn(hace_dev->dev, "invalid sg copy, %s:0x%x, %s:0x%x\n", + "nbytes", nbytes, "cryptlen", req->cryptlen); + rc = -EINVAL; + } + + CIPHER_DBG(hace_dev, "%s:%d, %s:%d, %s:%d, %s:%p\n", + "nbytes", nbytes, "req->cryptlen", req->cryptlen, + "nb_out_sg", rctx->dst_nents, + "cipher addr", crypto_engine->cipher_addr); + + return aspeed_sk_complete(hace_dev, rc); +} + +static int aspeed_sk_start(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_cipher_reqctx *rctx; + struct skcipher_request *req; + struct scatterlist *in_sg; + int nbytes; + + req = crypto_engine->req; + rctx = skcipher_request_ctx(req); + in_sg = req->src; + + nbytes = sg_copy_to_buffer(in_sg, rctx->src_nents, + crypto_engine->cipher_addr, req->cryptlen); + + CIPHER_DBG(hace_dev, "%s:%d, %s:%d, %s:%d, %s:%p\n", + "nbytes", nbytes, "req->cryptlen", req->cryptlen, + "nb_in_sg", rctx->src_nents, + "cipher addr", crypto_engine->cipher_addr); + + if (!nbytes) { + dev_warn(hace_dev->dev, "invalid sg copy, %s:0x%x, %s:0x%x\n", + "nbytes", nbytes, "cryptlen", req->cryptlen); + return -EINVAL; + } + + crypto_engine->resume = aspeed_sk_transfer; + + /* Trigger engines */ + ast_hace_write(hace_dev, crypto_engine->cipher_dma_addr, + ASPEED_HACE_SRC); + ast_hace_write(hace_dev, crypto_engine->cipher_dma_addr, + ASPEED_HACE_DEST); + ast_hace_write(hace_dev, req->cryptlen, ASPEED_HACE_DATA_LEN); + ast_hace_write(hace_dev, rctx->enc_cmd, ASPEED_HACE_CMD); + + return -EINPROGRESS; +} + +static int aspeed_sk_start_sg(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_sg_list *src_list, *dst_list; + dma_addr_t src_dma_addr, dst_dma_addr; + struct aspeed_cipher_reqctx *rctx; + struct skcipher_request *req; + struct scatterlist *s; + int src_sg_len; + int dst_sg_len; + int total, i; + int rc; + + CIPHER_DBG(hace_dev, "\n"); + + req = crypto_engine->req; + rctx = skcipher_request_ctx(req); + + rctx->enc_cmd |= HACE_CMD_DES_SG_CTRL | HACE_CMD_SRC_SG_CTRL | + HACE_CMD_AES_KEY_HW_EXP | HACE_CMD_MBUS_REQ_SYNC_EN; + + /* BIDIRECTIONAL */ + if (req->dst == req->src) { + src_sg_len = dma_map_sg(hace_dev->dev, req->src, + rctx->src_nents, DMA_BIDIRECTIONAL); + dst_sg_len = src_sg_len; + if (!src_sg_len) { + dev_warn(hace_dev->dev, "dma_map_sg() src error\n"); + return -EINVAL; + } + + } else { + src_sg_len = dma_map_sg(hace_dev->dev, req->src, + rctx->src_nents, DMA_TO_DEVICE); + if (!src_sg_len) { + dev_warn(hace_dev->dev, "dma_map_sg() src error\n"); + return -EINVAL; + } + + dst_sg_len = dma_map_sg(hace_dev->dev, req->dst, + rctx->dst_nents, DMA_FROM_DEVICE); + if (!dst_sg_len) { + dev_warn(hace_dev->dev, "dma_map_sg() dst error\n"); + rc = -EINVAL; + goto free_req_src; + } + } + + src_list = (struct aspeed_sg_list *)crypto_engine->cipher_addr; + src_dma_addr = crypto_engine->cipher_dma_addr; + total = req->cryptlen; + + for_each_sg(req->src, s, src_sg_len, i) { + u32 phy_addr = sg_dma_address(s); + u32 len = sg_dma_len(s); + + if (total > len) + total -= len; + else { + /* last sg list */ + len = total; + len |= BIT(31); + total = 0; + } + + src_list[i].phy_addr = cpu_to_le32(phy_addr); + src_list[i].len = cpu_to_le32(len); + } + + if (total != 0) { + rc = -EINVAL; + goto free_req; + } + + if (req->dst == req->src) { + dst_list = src_list; + dst_dma_addr = src_dma_addr; + + } else { + dst_list = (struct aspeed_sg_list *)crypto_engine->dst_sg_addr; + dst_dma_addr = crypto_engine->dst_sg_dma_addr; + total = req->cryptlen; + + for_each_sg(req->dst, s, dst_sg_len, i) { + u32 phy_addr = sg_dma_address(s); + u32 len = sg_dma_len(s); + + if (total > len) + total -= len; + else { + /* last sg list */ + len = total; + len |= BIT(31); + total = 0; + } + + dst_list[i].phy_addr = cpu_to_le32(phy_addr); + dst_list[i].len = cpu_to_le32(len); + + } + + dst_list[dst_sg_len].phy_addr = 0; + dst_list[dst_sg_len].len = 0; + } + + if (total != 0) { + rc = -EINVAL; + goto free_req; + } + + crypto_engine->resume = aspeed_sk_transfer_sg; + + /* Memory barrier to ensure all data setup before engine starts */ + mb(); + + /* Trigger engines */ + ast_hace_write(hace_dev, src_dma_addr, ASPEED_HACE_SRC); + ast_hace_write(hace_dev, dst_dma_addr, ASPEED_HACE_DEST); + ast_hace_write(hace_dev, req->cryptlen, ASPEED_HACE_DATA_LEN); + ast_hace_write(hace_dev, rctx->enc_cmd, ASPEED_HACE_CMD); + + return -EINPROGRESS; + +free_req: + if (req->dst == req->src) { + dma_unmap_sg(hace_dev->dev, req->src, rctx->src_nents, + DMA_BIDIRECTIONAL); + + } else { + dma_unmap_sg(hace_dev->dev, req->dst, rctx->dst_nents, + DMA_TO_DEVICE); + dma_unmap_sg(hace_dev->dev, req->src, rctx->src_nents, + DMA_TO_DEVICE); + } + + return rc; + +free_req_src: + dma_unmap_sg(hace_dev->dev, req->src, rctx->src_nents, DMA_TO_DEVICE); + + return rc; +} + +static int aspeed_hace_skcipher_trigger(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_cipher_reqctx *rctx; + struct crypto_skcipher *cipher; + struct aspeed_cipher_ctx *ctx; + struct skcipher_request *req; + + CIPHER_DBG(hace_dev, "\n"); + + req = crypto_engine->req; + rctx = skcipher_request_ctx(req); + cipher = crypto_skcipher_reqtfm(req); + ctx = crypto_skcipher_ctx(cipher); + + /* enable interrupt */ + rctx->enc_cmd |= HACE_CMD_ISR_EN; + + rctx->dst_nents = sg_nents(req->dst); + rctx->src_nents = sg_nents(req->src); + + ast_hace_write(hace_dev, crypto_engine->cipher_ctx_dma, + ASPEED_HACE_CONTEXT); + + if (rctx->enc_cmd & HACE_CMD_IV_REQUIRE) { + if (rctx->enc_cmd & HACE_CMD_DES_SELECT) + memcpy(crypto_engine->cipher_ctx + DES_BLOCK_SIZE, + req->iv, DES_BLOCK_SIZE); + else + memcpy(crypto_engine->cipher_ctx, req->iv, + AES_BLOCK_SIZE); + } + + if (hace_dev->version == AST2600_VERSION) { + memcpy(crypto_engine->cipher_ctx + 16, ctx->key, ctx->key_len); + + return aspeed_sk_start_sg(hace_dev); + } + + memcpy(crypto_engine->cipher_ctx + 16, ctx->key, AES_MAX_KEYLENGTH); + + return aspeed_sk_start(hace_dev); +} + +static int aspeed_des_crypt(struct skcipher_request *req, u32 cmd) +{ + struct aspeed_cipher_reqctx *rctx = skcipher_request_ctx(req); + struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req); + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); + struct aspeed_hace_dev *hace_dev = ctx->hace_dev; + u32 crypto_alg = cmd & HACE_CMD_OP_MODE_MASK; + + CIPHER_DBG(hace_dev, "\n"); + + if (crypto_alg == HACE_CMD_CBC || crypto_alg == HACE_CMD_ECB) { + if (!IS_ALIGNED(req->cryptlen, DES_BLOCK_SIZE)) + return -EINVAL; + } + + rctx->enc_cmd = cmd | HACE_CMD_DES_SELECT | HACE_CMD_RI_WO_DATA_ENABLE | + HACE_CMD_DES | HACE_CMD_CONTEXT_LOAD_ENABLE | + HACE_CMD_CONTEXT_SAVE_ENABLE; + + return aspeed_hace_crypto_handle_queue(hace_dev, req); +} + +static int aspeed_des_setkey(struct crypto_skcipher *cipher, const u8 *key, + unsigned int keylen) +{ + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); + struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher); + struct aspeed_hace_dev *hace_dev = ctx->hace_dev; + int rc; + + CIPHER_DBG(hace_dev, "keylen: %d bits\n", keylen); + + if (keylen != DES_KEY_SIZE && keylen != DES3_EDE_KEY_SIZE) { + dev_warn(hace_dev->dev, "invalid keylen: %d bits\n", keylen); + return -EINVAL; + } + + if (keylen == DES_KEY_SIZE) { + rc = crypto_des_verify_key(tfm, key); + if (rc) + return rc; + + } else if (keylen == DES3_EDE_KEY_SIZE) { + rc = crypto_des3_ede_verify_key(tfm, key); + if (rc) + return rc; + } + + memcpy(ctx->key, key, keylen); + ctx->key_len = keylen; + + crypto_skcipher_clear_flags(ctx->fallback_tfm, CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(ctx->fallback_tfm, cipher->base.crt_flags & + CRYPTO_TFM_REQ_MASK); + + return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); +} + +static int aspeed_tdes_ctr_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CTR | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_ctr_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CTR | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_ofb_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_OFB | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_ofb_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_OFB | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_cfb_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CFB | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_cfb_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CFB | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_cbc_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CBC | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_cbc_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CBC | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_ecb_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_ECB | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_tdes_ecb_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_ECB | + HACE_CMD_TRIPLE_DES); +} + +static int aspeed_des_ctr_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CTR | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_ctr_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CTR | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_ofb_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_OFB | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_ofb_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_OFB | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_cfb_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CFB | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_cfb_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CFB | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_cbc_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CBC | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_cbc_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CBC | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_ecb_decrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_ECB | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_des_ecb_encrypt(struct skcipher_request *req) +{ + return aspeed_des_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_ECB | + HACE_CMD_SINGLE_DES); +} + +static int aspeed_aes_crypt(struct skcipher_request *req, u32 cmd) +{ + struct aspeed_cipher_reqctx *rctx = skcipher_request_ctx(req); + struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req); + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); + struct aspeed_hace_dev *hace_dev = ctx->hace_dev; + u32 crypto_alg = cmd & HACE_CMD_OP_MODE_MASK; + + if (crypto_alg == HACE_CMD_CBC || crypto_alg == HACE_CMD_ECB) { + if (!IS_ALIGNED(req->cryptlen, AES_BLOCK_SIZE)) + return -EINVAL; + } + + CIPHER_DBG(hace_dev, "%s\n", + (cmd & HACE_CMD_ENCRYPT) ? "encrypt" : "decrypt"); + + cmd |= HACE_CMD_AES_SELECT | HACE_CMD_RI_WO_DATA_ENABLE | + HACE_CMD_CONTEXT_LOAD_ENABLE | HACE_CMD_CONTEXT_SAVE_ENABLE; + + switch (ctx->key_len) { + case AES_KEYSIZE_128: + cmd |= HACE_CMD_AES128; + break; + case AES_KEYSIZE_192: + cmd |= HACE_CMD_AES192; + break; + case AES_KEYSIZE_256: + cmd |= HACE_CMD_AES256; + break; + default: + return -EINVAL; + } + + rctx->enc_cmd = cmd; + + return aspeed_hace_crypto_handle_queue(hace_dev, req); +} + +static int aspeed_aes_setkey(struct crypto_skcipher *cipher, const u8 *key, + unsigned int keylen) +{ + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); + struct aspeed_hace_dev *hace_dev = ctx->hace_dev; + struct crypto_aes_ctx gen_aes_key; + + CIPHER_DBG(hace_dev, "keylen: %d bits\n", (keylen * 8)); + + if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 && + keylen != AES_KEYSIZE_256) + return -EINVAL; + + if (ctx->hace_dev->version == AST2500_VERSION) { + aes_expandkey(&gen_aes_key, key, keylen); + memcpy(ctx->key, gen_aes_key.key_enc, AES_MAX_KEYLENGTH); + + } else { + memcpy(ctx->key, key, keylen); + } + + ctx->key_len = keylen; + + crypto_skcipher_clear_flags(ctx->fallback_tfm, CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(ctx->fallback_tfm, cipher->base.crt_flags & + CRYPTO_TFM_REQ_MASK); + + return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); +} + +static int aspeed_aes_ctr_decrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CTR); +} + +static int aspeed_aes_ctr_encrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CTR); +} + +static int aspeed_aes_ofb_decrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_OFB); +} + +static int aspeed_aes_ofb_encrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_OFB); +} + +static int aspeed_aes_cfb_decrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CFB); +} + +static int aspeed_aes_cfb_encrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CFB); +} + +static int aspeed_aes_cbc_decrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_CBC); +} + +static int aspeed_aes_cbc_encrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_CBC); +} + +static int aspeed_aes_ecb_decrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_DECRYPT | HACE_CMD_ECB); +} + +static int aspeed_aes_ecb_encrypt(struct skcipher_request *req) +{ + return aspeed_aes_crypt(req, HACE_CMD_ENCRYPT | HACE_CMD_ECB); +} + +static int aspeed_crypto_cra_init(struct crypto_skcipher *tfm) +{ + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_alg *alg = crypto_skcipher_alg(tfm); + const char *name = crypto_tfm_alg_name(&tfm->base); + struct aspeed_hace_alg *crypto_alg; + + + crypto_alg = container_of(alg, struct aspeed_hace_alg, alg.skcipher); + ctx->hace_dev = crypto_alg->hace_dev; + ctx->start = aspeed_hace_skcipher_trigger; + + CIPHER_DBG(ctx->hace_dev, "%s\n", name); + + ctx->fallback_tfm = crypto_alloc_skcipher(name, 0, CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ctx->fallback_tfm)) { + dev_err(ctx->hace_dev->dev, "ERROR: Cannot allocate fallback for %s %ld\n", + name, PTR_ERR(ctx->fallback_tfm)); + return PTR_ERR(ctx->fallback_tfm); + } + + crypto_skcipher_set_reqsize(tfm, sizeof(struct aspeed_cipher_reqctx) + + crypto_skcipher_reqsize(ctx->fallback_tfm)); + + ctx->enginectx.op.do_one_request = aspeed_crypto_do_request; + ctx->enginectx.op.prepare_request = NULL; + ctx->enginectx.op.unprepare_request = NULL; + + return 0; +} + +static void aspeed_crypto_cra_exit(struct crypto_skcipher *tfm) +{ + struct aspeed_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct aspeed_hace_dev *hace_dev = ctx->hace_dev; + + CIPHER_DBG(hace_dev, "%s\n", crypto_tfm_alg_name(&tfm->base)); + crypto_free_skcipher(ctx->fallback_tfm); +} + +static struct aspeed_hace_alg aspeed_crypto_algs[] = { + { + .alg.skcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aspeed_aes_setkey, + .encrypt = aspeed_aes_ecb_encrypt, + .decrypt = aspeed_aes_ecb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ecb(aes)", + .cra_driver_name = "aspeed-ecb-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = AES_BLOCK_SIZE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aspeed_aes_setkey, + .encrypt = aspeed_aes_cbc_encrypt, + .decrypt = aspeed_aes_cbc_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "cbc(aes)", + .cra_driver_name = "aspeed-cbc-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = AES_BLOCK_SIZE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aspeed_aes_setkey, + .encrypt = aspeed_aes_cfb_encrypt, + .decrypt = aspeed_aes_cfb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "cfb(aes)", + .cra_driver_name = "aspeed-cfb-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = AES_BLOCK_SIZE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aspeed_aes_setkey, + .encrypt = aspeed_aes_ofb_encrypt, + .decrypt = aspeed_aes_ofb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ofb(aes)", + .cra_driver_name = "aspeed-ofb-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_des_ecb_encrypt, + .decrypt = aspeed_des_ecb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ecb(des)", + .cra_driver_name = "aspeed-ecb-des", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_des_cbc_encrypt, + .decrypt = aspeed_des_cbc_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "cbc(des)", + .cra_driver_name = "aspeed-cbc-des", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_des_cfb_encrypt, + .decrypt = aspeed_des_cfb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "cfb(des)", + .cra_driver_name = "aspeed-cfb-des", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_des_ofb_encrypt, + .decrypt = aspeed_des_ofb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ofb(des)", + .cra_driver_name = "aspeed-ofb-des", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_tdes_ecb_encrypt, + .decrypt = aspeed_tdes_ecb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ecb(des3_ede)", + .cra_driver_name = "aspeed-ecb-tdes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_tdes_cbc_encrypt, + .decrypt = aspeed_tdes_cbc_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "cbc(des3_ede)", + .cra_driver_name = "aspeed-cbc-tdes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_tdes_cfb_encrypt, + .decrypt = aspeed_tdes_cfb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "cfb(des3_ede)", + .cra_driver_name = "aspeed-cfb-tdes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_tdes_ofb_encrypt, + .decrypt = aspeed_tdes_ofb_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ofb(des3_ede)", + .cra_driver_name = "aspeed-ofb-tdes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = DES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, +}; + +static struct aspeed_hace_alg aspeed_crypto_algs_g6[] = { + { + .alg.skcipher = { + .ivsize = AES_BLOCK_SIZE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aspeed_aes_setkey, + .encrypt = aspeed_aes_ctr_encrypt, + .decrypt = aspeed_aes_ctr_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ctr(aes)", + .cra_driver_name = "aspeed-ctr-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES_KEY_SIZE, + .max_keysize = DES_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_des_ctr_encrypt, + .decrypt = aspeed_des_ctr_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ctr(des)", + .cra_driver_name = "aspeed-ctr-des", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + { + .alg.skcipher = { + .ivsize = DES_BLOCK_SIZE, + .min_keysize = DES3_EDE_KEY_SIZE, + .max_keysize = DES3_EDE_KEY_SIZE, + .setkey = aspeed_des_setkey, + .encrypt = aspeed_tdes_ctr_encrypt, + .decrypt = aspeed_tdes_ctr_decrypt, + .init = aspeed_crypto_cra_init, + .exit = aspeed_crypto_cra_exit, + .base = { + .cra_name = "ctr(des3_ede)", + .cra_driver_name = "aspeed-ctr-tdes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aspeed_cipher_ctx), + .cra_alignmask = 0x0f, + .cra_module = THIS_MODULE, + } + } + }, + +}; + +void aspeed_unregister_hace_crypto_algs(struct aspeed_hace_dev *hace_dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(aspeed_crypto_algs); i++) + crypto_unregister_skcipher(&aspeed_crypto_algs[i].alg.skcipher); + + if (hace_dev->version != AST2600_VERSION) + return; + + for (i = 0; i < ARRAY_SIZE(aspeed_crypto_algs_g6); i++) + crypto_unregister_skcipher(&aspeed_crypto_algs_g6[i].alg.skcipher); +} + +void aspeed_register_hace_crypto_algs(struct aspeed_hace_dev *hace_dev) +{ + int rc, i; + + CIPHER_DBG(hace_dev, "\n"); + + for (i = 0; i < ARRAY_SIZE(aspeed_crypto_algs); i++) { + aspeed_crypto_algs[i].hace_dev = hace_dev; + rc = crypto_register_skcipher(&aspeed_crypto_algs[i].alg.skcipher); + if (rc) { + CIPHER_DBG(hace_dev, "Failed to register %s\n", + aspeed_crypto_algs[i].alg.skcipher.base.cra_name); + } + } + + if (hace_dev->version != AST2600_VERSION) + return; + + for (i = 0; i < ARRAY_SIZE(aspeed_crypto_algs_g6); i++) { + aspeed_crypto_algs_g6[i].hace_dev = hace_dev; + rc = crypto_register_skcipher(&aspeed_crypto_algs_g6[i].alg.skcipher); + if (rc) { + CIPHER_DBG(hace_dev, "Failed to register %s\n", + aspeed_crypto_algs_g6[i].alg.skcipher.base.cra_name); + } + } +} diff --git a/drivers/crypto/aspeed/aspeed-hace-hash.c b/drivers/crypto/aspeed/aspeed-hace-hash.c new file mode 100644 index 000000000000..935135229ebd --- /dev/null +++ b/drivers/crypto/aspeed/aspeed-hace-hash.c @@ -0,0 +1,1391 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2021 Aspeed Technology Inc. + */ + +#include "aspeed-hace.h" + +#ifdef CONFIG_CRYPTO_DEV_ASPEED_DEBUG +#define AHASH_DBG(h, fmt, ...) \ + dev_info((h)->dev, "%s() " fmt, __func__, ##__VA_ARGS__) +#else +#define AHASH_DBG(h, fmt, ...) \ + dev_dbg((h)->dev, "%s() " fmt, __func__, ##__VA_ARGS__) +#endif + +/* Initialization Vectors for SHA-family */ +static const __be32 sha1_iv[8] = { + cpu_to_be32(SHA1_H0), cpu_to_be32(SHA1_H1), + cpu_to_be32(SHA1_H2), cpu_to_be32(SHA1_H3), + cpu_to_be32(SHA1_H4), 0, 0, 0 +}; + +static const __be32 sha224_iv[8] = { + cpu_to_be32(SHA224_H0), cpu_to_be32(SHA224_H1), + cpu_to_be32(SHA224_H2), cpu_to_be32(SHA224_H3), + cpu_to_be32(SHA224_H4), cpu_to_be32(SHA224_H5), + cpu_to_be32(SHA224_H6), cpu_to_be32(SHA224_H7), +}; + +static const __be32 sha256_iv[8] = { + cpu_to_be32(SHA256_H0), cpu_to_be32(SHA256_H1), + cpu_to_be32(SHA256_H2), cpu_to_be32(SHA256_H3), + cpu_to_be32(SHA256_H4), cpu_to_be32(SHA256_H5), + cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7), +}; + +static const __be64 sha384_iv[8] = { + cpu_to_be64(SHA384_H0), cpu_to_be64(SHA384_H1), + cpu_to_be64(SHA384_H2), cpu_to_be64(SHA384_H3), + cpu_to_be64(SHA384_H4), cpu_to_be64(SHA384_H5), + cpu_to_be64(SHA384_H6), cpu_to_be64(SHA384_H7) +}; + +static const __be64 sha512_iv[8] = { + cpu_to_be64(SHA512_H0), cpu_to_be64(SHA512_H1), + cpu_to_be64(SHA512_H2), cpu_to_be64(SHA512_H3), + cpu_to_be64(SHA512_H4), cpu_to_be64(SHA512_H5), + cpu_to_be64(SHA512_H6), cpu_to_be64(SHA512_H7) +}; + +static const __be32 sha512_224_iv[16] = { + cpu_to_be32(0xC8373D8CUL), cpu_to_be32(0xA24D5419UL), + cpu_to_be32(0x6699E173UL), cpu_to_be32(0xD6D4DC89UL), + cpu_to_be32(0xAEB7FA1DUL), cpu_to_be32(0x829CFF32UL), + cpu_to_be32(0x14D59D67UL), cpu_to_be32(0xCF9F2F58UL), + cpu_to_be32(0x692B6D0FUL), cpu_to_be32(0xA84DD47BUL), + cpu_to_be32(0x736FE377UL), cpu_to_be32(0x4289C404UL), + cpu_to_be32(0xA8859D3FUL), cpu_to_be32(0xC8361D6AUL), + cpu_to_be32(0xADE61211UL), cpu_to_be32(0xA192D691UL) +}; + +static const __be32 sha512_256_iv[16] = { + cpu_to_be32(0x94213122UL), cpu_to_be32(0x2CF72BFCUL), + cpu_to_be32(0xA35F559FUL), cpu_to_be32(0xC2644CC8UL), + cpu_to_be32(0x6BB89323UL), cpu_to_be32(0x51B1536FUL), + cpu_to_be32(0x19773896UL), cpu_to_be32(0xBDEA4059UL), + cpu_to_be32(0xE23E2896UL), cpu_to_be32(0xE3FF8EA8UL), + cpu_to_be32(0x251E5EBEUL), cpu_to_be32(0x92398653UL), + cpu_to_be32(0xFC99012BUL), cpu_to_be32(0xAAB8852CUL), + cpu_to_be32(0xDC2DB70EUL), cpu_to_be32(0xA22CC581UL) +}; + +/* The purpose of this padding is to ensure that the padded message is a + * multiple of 512 bits (SHA1/SHA224/SHA256) or 1024 bits (SHA384/SHA512). + * The bit "1" is appended at the end of the message followed by + * "padlen-1" zero bits. Then a 64 bits block (SHA1/SHA224/SHA256) or + * 128 bits block (SHA384/SHA512) equals to the message length in bits + * is appended. + * + * For SHA1/SHA224/SHA256, padlen is calculated as followed: + * - if message length < 56 bytes then padlen = 56 - message length + * - else padlen = 64 + 56 - message length + * + * For SHA384/SHA512, padlen is calculated as followed: + * - if message length < 112 bytes then padlen = 112 - message length + * - else padlen = 128 + 112 - message length + */ +static void aspeed_ahash_fill_padding(struct aspeed_hace_dev *hace_dev, + struct aspeed_sham_reqctx *rctx) +{ + unsigned int index, padlen; + __be64 bits[2]; + + AHASH_DBG(hace_dev, "rctx flags:0x%x\n", (u32)rctx->flags); + + switch (rctx->flags & SHA_FLAGS_MASK) { + case SHA_FLAGS_SHA1: + case SHA_FLAGS_SHA224: + case SHA_FLAGS_SHA256: + bits[0] = cpu_to_be64(rctx->digcnt[0] << 3); + index = rctx->bufcnt & 0x3f; + padlen = (index < 56) ? (56 - index) : ((64 + 56) - index); + *(rctx->buffer + rctx->bufcnt) = 0x80; + memset(rctx->buffer + rctx->bufcnt + 1, 0, padlen - 1); + memcpy(rctx->buffer + rctx->bufcnt + padlen, bits, 8); + rctx->bufcnt += padlen + 8; + break; + default: + bits[1] = cpu_to_be64(rctx->digcnt[0] << 3); + bits[0] = cpu_to_be64(rctx->digcnt[1] << 3 | + rctx->digcnt[0] >> 61); + index = rctx->bufcnt & 0x7f; + padlen = (index < 112) ? (112 - index) : ((128 + 112) - index); + *(rctx->buffer + rctx->bufcnt) = 0x80; + memset(rctx->buffer + rctx->bufcnt + 1, 0, padlen - 1); + memcpy(rctx->buffer + rctx->bufcnt + padlen, bits, 16); + rctx->bufcnt += padlen + 16; + break; + } +} + +/* + * Prepare DMA buffer before hardware engine + * processing. + */ +static int aspeed_ahash_dma_prepare(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + int length, remain; + + length = rctx->total + rctx->bufcnt; + remain = length % rctx->block_size; + + AHASH_DBG(hace_dev, "length:0x%x, remain:0x%x\n", length, remain); + + if (rctx->bufcnt) + memcpy(hash_engine->ahash_src_addr, rctx->buffer, rctx->bufcnt); + + if (rctx->total + rctx->bufcnt < ASPEED_CRYPTO_SRC_DMA_BUF_LEN) { + scatterwalk_map_and_copy(hash_engine->ahash_src_addr + + rctx->bufcnt, rctx->src_sg, + rctx->offset, rctx->total - remain, 0); + rctx->offset += rctx->total - remain; + + } else { + dev_warn(hace_dev->dev, "Hash data length is too large\n"); + return -EINVAL; + } + + scatterwalk_map_and_copy(rctx->buffer, rctx->src_sg, + rctx->offset, remain, 0); + + rctx->bufcnt = remain; + rctx->digest_dma_addr = dma_map_single(hace_dev->dev, rctx->digest, + SHA512_DIGEST_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(hace_dev->dev, rctx->digest_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx digest error\n"); + return -ENOMEM; + } + + hash_engine->src_length = length - remain; + hash_engine->src_dma = hash_engine->ahash_src_dma_addr; + hash_engine->digest_dma = rctx->digest_dma_addr; + + return 0; +} + +/* + * Prepare DMA buffer as SG list buffer before + * hardware engine processing. + */ +static int aspeed_ahash_dma_prepare_sg(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct aspeed_sg_list *src_list; + struct scatterlist *s; + int length, remain, sg_len, i; + int rc = 0; + + remain = (rctx->total + rctx->bufcnt) % rctx->block_size; + length = rctx->total + rctx->bufcnt - remain; + + AHASH_DBG(hace_dev, "%s:0x%x, %s:%zu, %s:0x%x, %s:0x%x\n", + "rctx total", rctx->total, "bufcnt", rctx->bufcnt, + "length", length, "remain", remain); + + sg_len = dma_map_sg(hace_dev->dev, rctx->src_sg, rctx->src_nents, + DMA_TO_DEVICE); + if (!sg_len) { + dev_warn(hace_dev->dev, "dma_map_sg() src error\n"); + rc = -ENOMEM; + goto end; + } + + src_list = (struct aspeed_sg_list *)hash_engine->ahash_src_addr; + rctx->digest_dma_addr = dma_map_single(hace_dev->dev, rctx->digest, + SHA512_DIGEST_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(hace_dev->dev, rctx->digest_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx digest error\n"); + rc = -ENOMEM; + goto free_src_sg; + } + + if (rctx->bufcnt != 0) { + u32 phy_addr; + u32 len; + + rctx->buffer_dma_addr = dma_map_single(hace_dev->dev, + rctx->buffer, + rctx->block_size * 2, + DMA_TO_DEVICE); + if (dma_mapping_error(hace_dev->dev, rctx->buffer_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx buffer error\n"); + rc = -ENOMEM; + goto free_rctx_digest; + } + + phy_addr = rctx->buffer_dma_addr; + len = rctx->bufcnt; + length -= len; + + /* Last sg list */ + if (length == 0) + len |= HASH_SG_LAST_LIST; + + src_list[0].phy_addr = cpu_to_le32(phy_addr); + src_list[0].len = cpu_to_le32(len); + src_list++; + } + + if (length != 0) { + for_each_sg(rctx->src_sg, s, sg_len, i) { + u32 phy_addr = sg_dma_address(s); + u32 len = sg_dma_len(s); + + if (length > len) + length -= len; + else { + /* Last sg list */ + len = length; + len |= HASH_SG_LAST_LIST; + length = 0; + } + + src_list[i].phy_addr = cpu_to_le32(phy_addr); + src_list[i].len = cpu_to_le32(len); + } + } + + if (length != 0) { + rc = -EINVAL; + goto free_rctx_buffer; + } + + rctx->offset = rctx->total - remain; + hash_engine->src_length = rctx->total + rctx->bufcnt - remain; + hash_engine->src_dma = hash_engine->ahash_src_dma_addr; + hash_engine->digest_dma = rctx->digest_dma_addr; + + return 0; + +free_rctx_buffer: + if (rctx->bufcnt != 0) + dma_unmap_single(hace_dev->dev, rctx->buffer_dma_addr, + rctx->block_size * 2, DMA_TO_DEVICE); +free_rctx_digest: + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); +free_src_sg: + dma_unmap_sg(hace_dev->dev, rctx->src_sg, rctx->src_nents, + DMA_TO_DEVICE); +end: + return rc; +} + +static int aspeed_ahash_complete(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + + AHASH_DBG(hace_dev, "\n"); + + hash_engine->flags &= ~CRYPTO_FLAGS_BUSY; + + crypto_finalize_hash_request(hace_dev->crypt_engine_hash, req, 0); + + return 0; +} + +/* + * Copy digest to the corresponding request result. + * This function will be called at final() stage. + */ +static int aspeed_ahash_transfer(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + + AHASH_DBG(hace_dev, "\n"); + + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); + + dma_unmap_single(hace_dev->dev, rctx->buffer_dma_addr, + rctx->block_size * 2, DMA_TO_DEVICE); + + memcpy(req->result, rctx->digest, rctx->digsize); + + return aspeed_ahash_complete(hace_dev); +} + +/* + * Trigger hardware engines to do the math. + */ +static int aspeed_hace_ahash_trigger(struct aspeed_hace_dev *hace_dev, + aspeed_hace_fn_t resume) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + + AHASH_DBG(hace_dev, "src_dma:%pad, digest_dma:%pad, length:%zu\n", + &hash_engine->src_dma, &hash_engine->digest_dma, + hash_engine->src_length); + + rctx->cmd |= HASH_CMD_INT_ENABLE; + hash_engine->resume = resume; + + ast_hace_write(hace_dev, hash_engine->src_dma, ASPEED_HACE_HASH_SRC); + ast_hace_write(hace_dev, hash_engine->digest_dma, + ASPEED_HACE_HASH_DIGEST_BUFF); + ast_hace_write(hace_dev, hash_engine->digest_dma, + ASPEED_HACE_HASH_KEY_BUFF); + ast_hace_write(hace_dev, hash_engine->src_length, + ASPEED_HACE_HASH_DATA_LEN); + + /* Memory barrier to ensure all data setup before engine starts */ + mb(); + + ast_hace_write(hace_dev, rctx->cmd, ASPEED_HACE_HASH_CMD); + + return -EINPROGRESS; +} + +/* + * HMAC resume aims to do the second pass produces + * the final HMAC code derived from the inner hash + * result and the outer key. + */ +static int aspeed_ahash_hmac_resume(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_sha_hmac_ctx *bctx = tctx->base; + int rc = 0; + + AHASH_DBG(hace_dev, "\n"); + + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); + + dma_unmap_single(hace_dev->dev, rctx->buffer_dma_addr, + rctx->block_size * 2, DMA_TO_DEVICE); + + /* o key pad + hash sum 1 */ + memcpy(rctx->buffer, bctx->opad, rctx->block_size); + memcpy(rctx->buffer + rctx->block_size, rctx->digest, rctx->digsize); + + rctx->bufcnt = rctx->block_size + rctx->digsize; + rctx->digcnt[0] = rctx->block_size + rctx->digsize; + + aspeed_ahash_fill_padding(hace_dev, rctx); + memcpy(rctx->digest, rctx->sha_iv, rctx->ivsize); + + rctx->digest_dma_addr = dma_map_single(hace_dev->dev, rctx->digest, + SHA512_DIGEST_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(hace_dev->dev, rctx->digest_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx digest error\n"); + rc = -ENOMEM; + goto end; + } + + rctx->buffer_dma_addr = dma_map_single(hace_dev->dev, rctx->buffer, + rctx->block_size * 2, + DMA_TO_DEVICE); + if (dma_mapping_error(hace_dev->dev, rctx->buffer_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx buffer error\n"); + rc = -ENOMEM; + goto free_rctx_digest; + } + + hash_engine->src_dma = rctx->buffer_dma_addr; + hash_engine->src_length = rctx->bufcnt; + hash_engine->digest_dma = rctx->digest_dma_addr; + + return aspeed_hace_ahash_trigger(hace_dev, aspeed_ahash_transfer); + +free_rctx_digest: + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); +end: + return rc; +} + +static int aspeed_ahash_req_final(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + int rc = 0; + + AHASH_DBG(hace_dev, "\n"); + + aspeed_ahash_fill_padding(hace_dev, rctx); + + rctx->digest_dma_addr = dma_map_single(hace_dev->dev, + rctx->digest, + SHA512_DIGEST_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(hace_dev->dev, rctx->digest_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx digest error\n"); + rc = -ENOMEM; + goto end; + } + + rctx->buffer_dma_addr = dma_map_single(hace_dev->dev, + rctx->buffer, + rctx->block_size * 2, + DMA_TO_DEVICE); + if (dma_mapping_error(hace_dev->dev, rctx->buffer_dma_addr)) { + dev_warn(hace_dev->dev, "dma_map() rctx buffer error\n"); + rc = -ENOMEM; + goto free_rctx_digest; + } + + hash_engine->src_dma = rctx->buffer_dma_addr; + hash_engine->src_length = rctx->bufcnt; + hash_engine->digest_dma = rctx->digest_dma_addr; + + if (rctx->flags & SHA_FLAGS_HMAC) + return aspeed_hace_ahash_trigger(hace_dev, + aspeed_ahash_hmac_resume); + + return aspeed_hace_ahash_trigger(hace_dev, aspeed_ahash_transfer); + +free_rctx_digest: + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); +end: + return rc; +} + +static int aspeed_ahash_update_resume_sg(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + + AHASH_DBG(hace_dev, "\n"); + + dma_unmap_sg(hace_dev->dev, rctx->src_sg, rctx->src_nents, + DMA_TO_DEVICE); + + if (rctx->bufcnt != 0) + dma_unmap_single(hace_dev->dev, rctx->buffer_dma_addr, + rctx->block_size * 2, + DMA_TO_DEVICE); + + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); + + scatterwalk_map_and_copy(rctx->buffer, rctx->src_sg, rctx->offset, + rctx->total - rctx->offset, 0); + + rctx->bufcnt = rctx->total - rctx->offset; + rctx->cmd &= ~HASH_CMD_HASH_SRC_SG_CTRL; + + if (rctx->flags & SHA_FLAGS_FINUP) + return aspeed_ahash_req_final(hace_dev); + + return aspeed_ahash_complete(hace_dev); +} + +static int aspeed_ahash_update_resume(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + + AHASH_DBG(hace_dev, "\n"); + + dma_unmap_single(hace_dev->dev, rctx->digest_dma_addr, + SHA512_DIGEST_SIZE, DMA_BIDIRECTIONAL); + + if (rctx->flags & SHA_FLAGS_FINUP) + return aspeed_ahash_req_final(hace_dev); + + return aspeed_ahash_complete(hace_dev); +} + +static int aspeed_ahash_req_update(struct aspeed_hace_dev *hace_dev) +{ + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + struct ahash_request *req = hash_engine->req; + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + aspeed_hace_fn_t resume; + int ret; + + AHASH_DBG(hace_dev, "\n"); + + if (hace_dev->version == AST2600_VERSION) { + rctx->cmd |= HASH_CMD_HASH_SRC_SG_CTRL; + resume = aspeed_ahash_update_resume_sg; + + } else { + resume = aspeed_ahash_update_resume; + } + + ret = hash_engine->dma_prepare(hace_dev); + if (ret) + return ret; + + return aspeed_hace_ahash_trigger(hace_dev, resume); +} + +static int aspeed_hace_hash_handle_queue(struct aspeed_hace_dev *hace_dev, + struct ahash_request *req) +{ + return crypto_transfer_hash_request_to_engine( + hace_dev->crypt_engine_hash, req); +} + +static int aspeed_ahash_do_request(struct crypto_engine *engine, void *areq) +{ + struct ahash_request *req = ahash_request_cast(areq); + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + struct aspeed_engine_hash *hash_engine; + int ret = 0; + + hash_engine = &hace_dev->hash_engine; + hash_engine->flags |= CRYPTO_FLAGS_BUSY; + + if (rctx->op == SHA_OP_UPDATE) + ret = aspeed_ahash_req_update(hace_dev); + else if (rctx->op == SHA_OP_FINAL) + ret = aspeed_ahash_req_final(hace_dev); + + if (ret != -EINPROGRESS) + return ret; + + return 0; +} + +static int aspeed_ahash_prepare_request(struct crypto_engine *engine, + void *areq) +{ + struct ahash_request *req = ahash_request_cast(areq); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + struct aspeed_engine_hash *hash_engine; + + hash_engine = &hace_dev->hash_engine; + hash_engine->req = req; + + if (hace_dev->version == AST2600_VERSION) + hash_engine->dma_prepare = aspeed_ahash_dma_prepare_sg; + else + hash_engine->dma_prepare = aspeed_ahash_dma_prepare; + + return 0; +} + +static int aspeed_sham_update(struct ahash_request *req) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + + AHASH_DBG(hace_dev, "req->nbytes: %d\n", req->nbytes); + + rctx->total = req->nbytes; + rctx->src_sg = req->src; + rctx->offset = 0; + rctx->src_nents = sg_nents(req->src); + rctx->op = SHA_OP_UPDATE; + + rctx->digcnt[0] += rctx->total; + if (rctx->digcnt[0] < rctx->total) + rctx->digcnt[1]++; + + if (rctx->bufcnt + rctx->total < rctx->block_size) { + scatterwalk_map_and_copy(rctx->buffer + rctx->bufcnt, + rctx->src_sg, rctx->offset, + rctx->total, 0); + rctx->bufcnt += rctx->total; + + return 0; + } + + return aspeed_hace_hash_handle_queue(hace_dev, req); +} + +static int aspeed_sham_shash_digest(struct crypto_shash *tfm, u32 flags, + const u8 *data, unsigned int len, u8 *out) +{ + SHASH_DESC_ON_STACK(shash, tfm); + + shash->tfm = tfm; + + return crypto_shash_digest(shash, data, len, out); +} + +static int aspeed_sham_final(struct ahash_request *req) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + + AHASH_DBG(hace_dev, "req->nbytes:%d, rctx->total:%d\n", + req->nbytes, rctx->total); + rctx->op = SHA_OP_FINAL; + + return aspeed_hace_hash_handle_queue(hace_dev, req); +} + +static int aspeed_sham_finup(struct ahash_request *req) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + int rc1, rc2; + + AHASH_DBG(hace_dev, "req->nbytes: %d\n", req->nbytes); + + rctx->flags |= SHA_FLAGS_FINUP; + + rc1 = aspeed_sham_update(req); + if (rc1 == -EINPROGRESS || rc1 == -EBUSY) + return rc1; + + /* + * final() has to be always called to cleanup resources + * even if update() failed, except EINPROGRESS + */ + rc2 = aspeed_sham_final(req); + + return rc1 ? : rc2; +} + +static int aspeed_sham_init(struct ahash_request *req) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + struct aspeed_sha_hmac_ctx *bctx = tctx->base; + + AHASH_DBG(hace_dev, "%s: digest size:%d\n", + crypto_tfm_alg_name(&tfm->base), + crypto_ahash_digestsize(tfm)); + + rctx->cmd = HASH_CMD_ACC_MODE; + rctx->flags = 0; + + switch (crypto_ahash_digestsize(tfm)) { + case SHA1_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA1 | HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA1; + rctx->digsize = SHA1_DIGEST_SIZE; + rctx->block_size = SHA1_BLOCK_SIZE; + rctx->sha_iv = sha1_iv; + rctx->ivsize = 32; + memcpy(rctx->digest, sha1_iv, rctx->ivsize); + break; + case SHA224_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA224 | HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA224; + rctx->digsize = SHA224_DIGEST_SIZE; + rctx->block_size = SHA224_BLOCK_SIZE; + rctx->sha_iv = sha224_iv; + rctx->ivsize = 32; + memcpy(rctx->digest, sha224_iv, rctx->ivsize); + break; + case SHA256_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA256 | HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA256; + rctx->digsize = SHA256_DIGEST_SIZE; + rctx->block_size = SHA256_BLOCK_SIZE; + rctx->sha_iv = sha256_iv; + rctx->ivsize = 32; + memcpy(rctx->digest, sha256_iv, rctx->ivsize); + break; + case SHA384_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA512_SER | HASH_CMD_SHA384 | + HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA384; + rctx->digsize = SHA384_DIGEST_SIZE; + rctx->block_size = SHA384_BLOCK_SIZE; + rctx->sha_iv = (const __be32 *)sha384_iv; + rctx->ivsize = 64; + memcpy(rctx->digest, sha384_iv, rctx->ivsize); + break; + case SHA512_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA512_SER | HASH_CMD_SHA512 | + HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA512; + rctx->digsize = SHA512_DIGEST_SIZE; + rctx->block_size = SHA512_BLOCK_SIZE; + rctx->sha_iv = (const __be32 *)sha512_iv; + rctx->ivsize = 64; + memcpy(rctx->digest, sha512_iv, rctx->ivsize); + break; + default: + dev_warn(tctx->hace_dev->dev, "digest size %d not support\n", + crypto_ahash_digestsize(tfm)); + return -EINVAL; + } + + rctx->bufcnt = 0; + rctx->total = 0; + rctx->digcnt[0] = 0; + rctx->digcnt[1] = 0; + + /* HMAC init */ + if (tctx->flags & SHA_FLAGS_HMAC) { + rctx->digcnt[0] = rctx->block_size; + rctx->bufcnt = rctx->block_size; + memcpy(rctx->buffer, bctx->ipad, rctx->block_size); + rctx->flags |= SHA_FLAGS_HMAC; + } + + return 0; +} + +static int aspeed_sha512s_init(struct ahash_request *req) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + struct aspeed_sha_hmac_ctx *bctx = tctx->base; + + AHASH_DBG(hace_dev, "digest size: %d\n", crypto_ahash_digestsize(tfm)); + + rctx->cmd = HASH_CMD_ACC_MODE; + rctx->flags = 0; + + switch (crypto_ahash_digestsize(tfm)) { + case SHA224_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA512_SER | HASH_CMD_SHA512_224 | + HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA512_224; + rctx->digsize = SHA224_DIGEST_SIZE; + rctx->block_size = SHA512_BLOCK_SIZE; + rctx->sha_iv = sha512_224_iv; + rctx->ivsize = 64; + memcpy(rctx->digest, sha512_224_iv, rctx->ivsize); + break; + case SHA256_DIGEST_SIZE: + rctx->cmd |= HASH_CMD_SHA512_SER | HASH_CMD_SHA512_256 | + HASH_CMD_SHA_SWAP; + rctx->flags |= SHA_FLAGS_SHA512_256; + rctx->digsize = SHA256_DIGEST_SIZE; + rctx->block_size = SHA512_BLOCK_SIZE; + rctx->sha_iv = sha512_256_iv; + rctx->ivsize = 64; + memcpy(rctx->digest, sha512_256_iv, rctx->ivsize); + break; + default: + dev_warn(tctx->hace_dev->dev, "digest size %d not support\n", + crypto_ahash_digestsize(tfm)); + return -EINVAL; + } + + rctx->bufcnt = 0; + rctx->total = 0; + rctx->digcnt[0] = 0; + rctx->digcnt[1] = 0; + + /* HMAC init */ + if (tctx->flags & SHA_FLAGS_HMAC) { + rctx->digcnt[0] = rctx->block_size; + rctx->bufcnt = rctx->block_size; + memcpy(rctx->buffer, bctx->ipad, rctx->block_size); + rctx->flags |= SHA_FLAGS_HMAC; + } + + return 0; +} + +static int aspeed_sham_digest(struct ahash_request *req) +{ + return aspeed_sham_init(req) ? : aspeed_sham_finup(req); +} + +static int aspeed_sham_setkey(struct crypto_ahash *tfm, const u8 *key, + unsigned int keylen) +{ + struct aspeed_sham_ctx *tctx = crypto_ahash_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + struct aspeed_sha_hmac_ctx *bctx = tctx->base; + int ds = crypto_shash_digestsize(bctx->shash); + int bs = crypto_shash_blocksize(bctx->shash); + int err = 0; + int i; + + AHASH_DBG(hace_dev, "%s: keylen:%d\n", crypto_tfm_alg_name(&tfm->base), + keylen); + + if (keylen > bs) { + err = aspeed_sham_shash_digest(bctx->shash, + crypto_shash_get_flags(bctx->shash), + key, keylen, bctx->ipad); + if (err) + return err; + keylen = ds; + + } else { + memcpy(bctx->ipad, key, keylen); + } + + memset(bctx->ipad + keylen, 0, bs - keylen); + memcpy(bctx->opad, bctx->ipad, bs); + + for (i = 0; i < bs; i++) { + bctx->ipad[i] ^= HMAC_IPAD_VALUE; + bctx->opad[i] ^= HMAC_OPAD_VALUE; + } + + return err; +} + +static int aspeed_sham_cra_init(struct crypto_tfm *tfm) +{ + struct ahash_alg *alg = __crypto_ahash_alg(tfm->__crt_alg); + struct aspeed_sham_ctx *tctx = crypto_tfm_ctx(tfm); + struct aspeed_hace_alg *ast_alg; + + ast_alg = container_of(alg, struct aspeed_hace_alg, alg.ahash); + tctx->hace_dev = ast_alg->hace_dev; + tctx->flags = 0; + + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), + sizeof(struct aspeed_sham_reqctx)); + + if (ast_alg->alg_base) { + /* hmac related */ + struct aspeed_sha_hmac_ctx *bctx = tctx->base; + + tctx->flags |= SHA_FLAGS_HMAC; + bctx->shash = crypto_alloc_shash(ast_alg->alg_base, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(bctx->shash)) { + dev_warn(ast_alg->hace_dev->dev, + "base driver '%s' could not be loaded.\n", + ast_alg->alg_base); + return PTR_ERR(bctx->shash); + } + } + + tctx->enginectx.op.do_one_request = aspeed_ahash_do_request; + tctx->enginectx.op.prepare_request = aspeed_ahash_prepare_request; + tctx->enginectx.op.unprepare_request = NULL; + + return 0; +} + +static void aspeed_sham_cra_exit(struct crypto_tfm *tfm) +{ + struct aspeed_sham_ctx *tctx = crypto_tfm_ctx(tfm); + struct aspeed_hace_dev *hace_dev = tctx->hace_dev; + + AHASH_DBG(hace_dev, "%s\n", crypto_tfm_alg_name(tfm)); + + if (tctx->flags & SHA_FLAGS_HMAC) { + struct aspeed_sha_hmac_ctx *bctx = tctx->base; + + crypto_free_shash(bctx->shash); + } +} + +static int aspeed_sham_export(struct ahash_request *req, void *out) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + + memcpy(out, rctx, sizeof(*rctx)); + + return 0; +} + +static int aspeed_sham_import(struct ahash_request *req, const void *in) +{ + struct aspeed_sham_reqctx *rctx = ahash_request_ctx(req); + + memcpy(rctx, in, sizeof(*rctx)); + + return 0; +} + +static struct aspeed_hace_alg aspeed_ahash_algs[] = { + { + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha1", + .cra_driver_name = "aspeed-sha1", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA256_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha256", + .cra_driver_name = "aspeed-sha256", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA224_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha224", + .cra_driver_name = "aspeed-sha224", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha1", + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha1)", + .cra_driver_name = "aspeed-hmac-sha1", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha224", + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA224_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha224)", + .cra_driver_name = "aspeed-hmac-sha224", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha256", + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA256_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha256)", + .cra_driver_name = "aspeed-hmac-sha256", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, +}; + +static struct aspeed_hace_alg aspeed_ahash_algs_g6[] = { + { + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA384_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha384", + .cra_driver_name = "aspeed-sha384", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA512_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha512", + .cra_driver_name = "aspeed-sha512", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg.ahash = { + .init = aspeed_sha512s_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA224_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha512_224", + .cra_driver_name = "aspeed-sha512_224", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg.ahash = { + .init = aspeed_sha512s_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA256_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "sha512_256", + .cra_driver_name = "aspeed-sha512_256", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha384", + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA384_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha384)", + .cra_driver_name = "aspeed-hmac-sha384", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha512", + .alg.ahash = { + .init = aspeed_sham_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA512_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha512)", + .cra_driver_name = "aspeed-hmac-sha512", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha512_224", + .alg.ahash = { + .init = aspeed_sha512s_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA224_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha512_224)", + .cra_driver_name = "aspeed-hmac-sha512_224", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, + { + .alg_base = "sha512_256", + .alg.ahash = { + .init = aspeed_sha512s_init, + .update = aspeed_sham_update, + .final = aspeed_sham_final, + .finup = aspeed_sham_finup, + .digest = aspeed_sham_digest, + .setkey = aspeed_sham_setkey, + .export = aspeed_sham_export, + .import = aspeed_sham_import, + .halg = { + .digestsize = SHA256_DIGEST_SIZE, + .statesize = sizeof(struct aspeed_sham_reqctx), + .base = { + .cra_name = "hmac(sha512_256)", + .cra_driver_name = "aspeed-hmac-sha512_256", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | + CRYPTO_ALG_ASYNC | + CRYPTO_ALG_KERN_DRIVER_ONLY, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aspeed_sham_ctx) + + sizeof(struct aspeed_sha_hmac_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = aspeed_sham_cra_init, + .cra_exit = aspeed_sham_cra_exit, + } + } + }, + }, +}; + +void aspeed_unregister_hace_hash_algs(struct aspeed_hace_dev *hace_dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(aspeed_ahash_algs); i++) + crypto_unregister_ahash(&aspeed_ahash_algs[i].alg.ahash); + + if (hace_dev->version != AST2600_VERSION) + return; + + for (i = 0; i < ARRAY_SIZE(aspeed_ahash_algs_g6); i++) + crypto_unregister_ahash(&aspeed_ahash_algs_g6[i].alg.ahash); +} + +void aspeed_register_hace_hash_algs(struct aspeed_hace_dev *hace_dev) +{ + int rc, i; + + AHASH_DBG(hace_dev, "\n"); + + for (i = 0; i < ARRAY_SIZE(aspeed_ahash_algs); i++) { + aspeed_ahash_algs[i].hace_dev = hace_dev; + rc = crypto_register_ahash(&aspeed_ahash_algs[i].alg.ahash); + if (rc) { + AHASH_DBG(hace_dev, "Failed to register %s\n", + aspeed_ahash_algs[i].alg.ahash.halg.base.cra_name); + } + } + + if (hace_dev->version != AST2600_VERSION) + return; + + for (i = 0; i < ARRAY_SIZE(aspeed_ahash_algs_g6); i++) { + aspeed_ahash_algs_g6[i].hace_dev = hace_dev; + rc = crypto_register_ahash(&aspeed_ahash_algs_g6[i].alg.ahash); + if (rc) { + AHASH_DBG(hace_dev, "Failed to register %s\n", + aspeed_ahash_algs_g6[i].alg.ahash.halg.base.cra_name); + } + } +} diff --git a/drivers/crypto/aspeed/aspeed-hace.c b/drivers/crypto/aspeed/aspeed-hace.c new file mode 100644 index 000000000000..656cb92c8bb6 --- /dev/null +++ b/drivers/crypto/aspeed/aspeed-hace.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2021 Aspeed Technology Inc. + */ + +#include <linux/clk.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of.h> +#include <linux/platform_device.h> + +#include "aspeed-hace.h" + +#ifdef CONFIG_CRYPTO_DEV_ASPEED_DEBUG +#define HACE_DBG(d, fmt, ...) \ + dev_info((d)->dev, "%s() " fmt, __func__, ##__VA_ARGS__) +#else +#define HACE_DBG(d, fmt, ...) \ + dev_dbg((d)->dev, "%s() " fmt, __func__, ##__VA_ARGS__) +#endif + +/* HACE interrupt service routine */ +static irqreturn_t aspeed_hace_irq(int irq, void *dev) +{ + struct aspeed_hace_dev *hace_dev = (struct aspeed_hace_dev *)dev; + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + u32 sts; + + sts = ast_hace_read(hace_dev, ASPEED_HACE_STS); + ast_hace_write(hace_dev, sts, ASPEED_HACE_STS); + + HACE_DBG(hace_dev, "irq status: 0x%x\n", sts); + + if (sts & HACE_HASH_ISR) { + if (hash_engine->flags & CRYPTO_FLAGS_BUSY) + tasklet_schedule(&hash_engine->done_task); + else + dev_warn(hace_dev->dev, "HASH no active requests.\n"); + } + + if (sts & HACE_CRYPTO_ISR) { + if (crypto_engine->flags & CRYPTO_FLAGS_BUSY) + tasklet_schedule(&crypto_engine->done_task); + else + dev_warn(hace_dev->dev, "CRYPTO no active requests.\n"); + } + + return IRQ_HANDLED; +} + +static void aspeed_hace_crypto_done_task(unsigned long data) +{ + struct aspeed_hace_dev *hace_dev = (struct aspeed_hace_dev *)data; + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + + crypto_engine->resume(hace_dev); +} + +static void aspeed_hace_hash_done_task(unsigned long data) +{ + struct aspeed_hace_dev *hace_dev = (struct aspeed_hace_dev *)data; + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + + hash_engine->resume(hace_dev); +} + +static void aspeed_hace_register(struct aspeed_hace_dev *hace_dev) +{ +#ifdef CONFIG_CRYPTO_DEV_ASPEED_HACE_HASH + aspeed_register_hace_hash_algs(hace_dev); +#endif +#ifdef CONFIG_CRYPTO_DEV_ASPEED_HACE_CRYPTO + aspeed_register_hace_crypto_algs(hace_dev); +#endif +} + +static void aspeed_hace_unregister(struct aspeed_hace_dev *hace_dev) +{ +#ifdef CONFIG_CRYPTO_DEV_ASPEED_HACE_HASH + aspeed_unregister_hace_hash_algs(hace_dev); +#endif +#ifdef CONFIG_CRYPTO_DEV_ASPEED_HACE_CRYPTO + aspeed_unregister_hace_crypto_algs(hace_dev); +#endif +} + +static const struct of_device_id aspeed_hace_of_matches[] = { + { .compatible = "aspeed,ast2500-hace", .data = (void *)5, }, + { .compatible = "aspeed,ast2600-hace", .data = (void *)6, }, + {}, +}; + +static int aspeed_hace_probe(struct platform_device *pdev) +{ + struct aspeed_engine_crypto *crypto_engine; + const struct of_device_id *hace_dev_id; + struct aspeed_engine_hash *hash_engine; + struct aspeed_hace_dev *hace_dev; + struct resource *res; + int rc; + + hace_dev = devm_kzalloc(&pdev->dev, sizeof(struct aspeed_hace_dev), + GFP_KERNEL); + if (!hace_dev) + return -ENOMEM; + + hace_dev_id = of_match_device(aspeed_hace_of_matches, &pdev->dev); + if (!hace_dev_id) { + dev_err(&pdev->dev, "Failed to match hace dev id\n"); + return -EINVAL; + } + + hace_dev->dev = &pdev->dev; + hace_dev->version = (unsigned long)hace_dev_id->data; + hash_engine = &hace_dev->hash_engine; + crypto_engine = &hace_dev->crypto_engine; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + platform_set_drvdata(pdev, hace_dev); + + hace_dev->regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(hace_dev->regs)) + return PTR_ERR(hace_dev->regs); + + /* Get irq number and register it */ + hace_dev->irq = platform_get_irq(pdev, 0); + if (hace_dev->irq < 0) + return -ENXIO; + + rc = devm_request_irq(&pdev->dev, hace_dev->irq, aspeed_hace_irq, 0, + dev_name(&pdev->dev), hace_dev); + if (rc) { + dev_err(&pdev->dev, "Failed to request interrupt\n"); + return rc; + } + + /* Get clk and enable it */ + hace_dev->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(hace_dev->clk)) { + dev_err(&pdev->dev, "Failed to get clk\n"); + return -ENODEV; + } + + rc = clk_prepare_enable(hace_dev->clk); + if (rc) { + dev_err(&pdev->dev, "Failed to enable clock 0x%x\n", rc); + return rc; + } + + /* Initialize crypto hardware engine structure for hash */ + hace_dev->crypt_engine_hash = crypto_engine_alloc_init(hace_dev->dev, + true); + if (!hace_dev->crypt_engine_hash) { + rc = -ENOMEM; + goto clk_exit; + } + + rc = crypto_engine_start(hace_dev->crypt_engine_hash); + if (rc) + goto err_engine_hash_start; + + tasklet_init(&hash_engine->done_task, aspeed_hace_hash_done_task, + (unsigned long)hace_dev); + + /* Initialize crypto hardware engine structure for crypto */ + hace_dev->crypt_engine_crypto = crypto_engine_alloc_init(hace_dev->dev, + true); + if (!hace_dev->crypt_engine_crypto) { + rc = -ENOMEM; + goto err_engine_hash_start; + } + + rc = crypto_engine_start(hace_dev->crypt_engine_crypto); + if (rc) + goto err_engine_crypto_start; + + tasklet_init(&crypto_engine->done_task, aspeed_hace_crypto_done_task, + (unsigned long)hace_dev); + + /* Allocate DMA buffer for hash engine input used */ + hash_engine->ahash_src_addr = + dmam_alloc_coherent(&pdev->dev, + ASPEED_HASH_SRC_DMA_BUF_LEN, + &hash_engine->ahash_src_dma_addr, + GFP_KERNEL); + if (!hash_engine->ahash_src_addr) { + dev_err(&pdev->dev, "Failed to allocate dma buffer\n"); + rc = -ENOMEM; + goto err_engine_crypto_start; + } + + /* Allocate DMA buffer for crypto engine context used */ + crypto_engine->cipher_ctx = + dmam_alloc_coherent(&pdev->dev, + PAGE_SIZE, + &crypto_engine->cipher_ctx_dma, + GFP_KERNEL); + if (!crypto_engine->cipher_ctx) { + dev_err(&pdev->dev, "Failed to allocate cipher ctx dma\n"); + rc = -ENOMEM; + goto err_engine_crypto_start; + } + + /* Allocate DMA buffer for crypto engine input used */ + crypto_engine->cipher_addr = + dmam_alloc_coherent(&pdev->dev, + ASPEED_CRYPTO_SRC_DMA_BUF_LEN, + &crypto_engine->cipher_dma_addr, + GFP_KERNEL); + if (!crypto_engine->cipher_addr) { + dev_err(&pdev->dev, "Failed to allocate cipher addr dma\n"); + rc = -ENOMEM; + goto err_engine_crypto_start; + } + + /* Allocate DMA buffer for crypto engine output used */ + if (hace_dev->version == AST2600_VERSION) { + crypto_engine->dst_sg_addr = + dmam_alloc_coherent(&pdev->dev, + ASPEED_CRYPTO_DST_DMA_BUF_LEN, + &crypto_engine->dst_sg_dma_addr, + GFP_KERNEL); + if (!crypto_engine->dst_sg_addr) { + dev_err(&pdev->dev, "Failed to allocate dst_sg dma\n"); + rc = -ENOMEM; + goto err_engine_crypto_start; + } + } + + aspeed_hace_register(hace_dev); + + dev_info(&pdev->dev, "Aspeed Crypto Accelerator successfully registered\n"); + + return 0; + +err_engine_crypto_start: + crypto_engine_exit(hace_dev->crypt_engine_crypto); +err_engine_hash_start: + crypto_engine_exit(hace_dev->crypt_engine_hash); +clk_exit: + clk_disable_unprepare(hace_dev->clk); + + return rc; +} + +static int aspeed_hace_remove(struct platform_device *pdev) +{ + struct aspeed_hace_dev *hace_dev = platform_get_drvdata(pdev); + struct aspeed_engine_crypto *crypto_engine = &hace_dev->crypto_engine; + struct aspeed_engine_hash *hash_engine = &hace_dev->hash_engine; + + aspeed_hace_unregister(hace_dev); + + crypto_engine_exit(hace_dev->crypt_engine_hash); + crypto_engine_exit(hace_dev->crypt_engine_crypto); + + tasklet_kill(&hash_engine->done_task); + tasklet_kill(&crypto_engine->done_task); + + clk_disable_unprepare(hace_dev->clk); + + return 0; +} + +MODULE_DEVICE_TABLE(of, aspeed_hace_of_matches); + +static struct platform_driver aspeed_hace_driver = { + .probe = aspeed_hace_probe, + .remove = aspeed_hace_remove, + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = aspeed_hace_of_matches, + }, +}; + +module_platform_driver(aspeed_hace_driver); + +MODULE_AUTHOR("Neal Liu <neal_liu@aspeedtech.com>"); +MODULE_DESCRIPTION("Aspeed HACE driver Crypto Accelerator"); +MODULE_LICENSE("GPL"); diff --git a/drivers/crypto/aspeed/aspeed-hace.h b/drivers/crypto/aspeed/aspeed-hace.h new file mode 100644 index 000000000000..f2cde23b56ae --- /dev/null +++ b/drivers/crypto/aspeed/aspeed-hace.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef __ASPEED_HACE_H__ +#define __ASPEED_HACE_H__ + +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/fips.h> +#include <linux/dma-mapping.h> +#include <crypto/aes.h> +#include <crypto/des.h> +#include <crypto/scatterwalk.h> +#include <crypto/internal/aead.h> +#include <crypto/internal/akcipher.h> +#include <crypto/internal/des.h> +#include <crypto/internal/hash.h> +#include <crypto/internal/kpp.h> +#include <crypto/internal/skcipher.h> +#include <crypto/algapi.h> +#include <crypto/engine.h> +#include <crypto/hmac.h> +#include <crypto/sha1.h> +#include <crypto/sha2.h> + +/***************************** + * * + * HACE register definitions * + * * + * ***************************/ +#define ASPEED_HACE_SRC 0x00 /* Crypto Data Source Base Address Register */ +#define ASPEED_HACE_DEST 0x04 /* Crypto Data Destination Base Address Register */ +#define ASPEED_HACE_CONTEXT 0x08 /* Crypto Context Buffer Base Address Register */ +#define ASPEED_HACE_DATA_LEN 0x0C /* Crypto Data Length Register */ +#define ASPEED_HACE_CMD 0x10 /* Crypto Engine Command Register */ + +/* G5 */ +#define ASPEED_HACE_TAG 0x18 /* HACE Tag Register */ +/* G6 */ +#define ASPEED_HACE_GCM_ADD_LEN 0x14 /* Crypto AES-GCM Additional Data Length Register */ +#define ASPEED_HACE_GCM_TAG_BASE_ADDR 0x18 /* Crypto AES-GCM Tag Write Buff Base Address Reg */ + +#define ASPEED_HACE_STS 0x1C /* HACE Status Register */ + +#define ASPEED_HACE_HASH_SRC 0x20 /* Hash Data Source Base Address Register */ +#define ASPEED_HACE_HASH_DIGEST_BUFF 0x24 /* Hash Digest Write Buffer Base Address Register */ +#define ASPEED_HACE_HASH_KEY_BUFF 0x28 /* Hash HMAC Key Buffer Base Address Register */ +#define ASPEED_HACE_HASH_DATA_LEN 0x2C /* Hash Data Length Register */ +#define ASPEED_HACE_HASH_CMD 0x30 /* Hash Engine Command Register */ + +/* crypto cmd */ +#define HACE_CMD_SINGLE_DES 0 +#define HACE_CMD_TRIPLE_DES BIT(17) +#define HACE_CMD_AES_SELECT 0 +#define HACE_CMD_DES_SELECT BIT(16) +#define HACE_CMD_ISR_EN BIT(12) +#define HACE_CMD_CONTEXT_SAVE_ENABLE (0) +#define HACE_CMD_CONTEXT_SAVE_DISABLE BIT(9) +#define HACE_CMD_AES (0) +#define HACE_CMD_DES (0) +#define HACE_CMD_RC4 BIT(8) +#define HACE_CMD_DECRYPT (0) +#define HACE_CMD_ENCRYPT BIT(7) + +#define HACE_CMD_ECB (0x0 << 4) +#define HACE_CMD_CBC (0x1 << 4) +#define HACE_CMD_CFB (0x2 << 4) +#define HACE_CMD_OFB (0x3 << 4) +#define HACE_CMD_CTR (0x4 << 4) +#define HACE_CMD_OP_MODE_MASK (0x7 << 4) + +#define HACE_CMD_AES128 (0x0 << 2) +#define HACE_CMD_AES192 (0x1 << 2) +#define HACE_CMD_AES256 (0x2 << 2) +#define HACE_CMD_OP_CASCADE (0x3) +#define HACE_CMD_OP_INDEPENDENT (0x1) + +/* G5 */ +#define HACE_CMD_RI_WO_DATA_ENABLE (0) +#define HACE_CMD_RI_WO_DATA_DISABLE BIT(11) +#define HACE_CMD_CONTEXT_LOAD_ENABLE (0) +#define HACE_CMD_CONTEXT_LOAD_DISABLE BIT(10) +/* G6 */ +#define HACE_CMD_AES_KEY_FROM_OTP BIT(24) +#define HACE_CMD_GHASH_TAG_XOR_EN BIT(23) +#define HACE_CMD_GHASH_PAD_LEN_INV BIT(22) +#define HACE_CMD_GCM_TAG_ADDR_SEL BIT(21) +#define HACE_CMD_MBUS_REQ_SYNC_EN BIT(20) +#define HACE_CMD_DES_SG_CTRL BIT(19) +#define HACE_CMD_SRC_SG_CTRL BIT(18) +#define HACE_CMD_CTR_IV_AES_96 (0x1 << 14) +#define HACE_CMD_CTR_IV_DES_32 (0x1 << 14) +#define HACE_CMD_CTR_IV_AES_64 (0x2 << 14) +#define HACE_CMD_CTR_IV_AES_32 (0x3 << 14) +#define HACE_CMD_AES_KEY_HW_EXP BIT(13) +#define HACE_CMD_GCM (0x5 << 4) + +/* interrupt status reg */ +#define HACE_CRYPTO_ISR BIT(12) +#define HACE_HASH_ISR BIT(9) +#define HACE_HASH_BUSY BIT(0) + +/* hash cmd reg */ +#define HASH_CMD_MBUS_REQ_SYNC_EN BIT(20) +#define HASH_CMD_HASH_SRC_SG_CTRL BIT(18) +#define HASH_CMD_SHA512_224 (0x3 << 10) +#define HASH_CMD_SHA512_256 (0x2 << 10) +#define HASH_CMD_SHA384 (0x1 << 10) +#define HASH_CMD_SHA512 (0) +#define HASH_CMD_INT_ENABLE BIT(9) +#define HASH_CMD_HMAC (0x1 << 7) +#define HASH_CMD_ACC_MODE (0x2 << 7) +#define HASH_CMD_HMAC_KEY (0x3 << 7) +#define HASH_CMD_SHA1 (0x2 << 4) +#define HASH_CMD_SHA224 (0x4 << 4) +#define HASH_CMD_SHA256 (0x5 << 4) +#define HASH_CMD_SHA512_SER (0x6 << 4) +#define HASH_CMD_SHA_SWAP (0x2 << 2) + +#define HASH_SG_LAST_LIST BIT(31) + +#define CRYPTO_FLAGS_BUSY BIT(1) + +#define SHA_OP_UPDATE 1 +#define SHA_OP_FINAL 2 + +#define SHA_FLAGS_SHA1 BIT(0) +#define SHA_FLAGS_SHA224 BIT(1) +#define SHA_FLAGS_SHA256 BIT(2) +#define SHA_FLAGS_SHA384 BIT(3) +#define SHA_FLAGS_SHA512 BIT(4) +#define SHA_FLAGS_SHA512_224 BIT(5) +#define SHA_FLAGS_SHA512_256 BIT(6) +#define SHA_FLAGS_HMAC BIT(8) +#define SHA_FLAGS_FINUP BIT(9) +#define SHA_FLAGS_MASK (0xff) + +#define ASPEED_CRYPTO_SRC_DMA_BUF_LEN 0xa000 +#define ASPEED_CRYPTO_DST_DMA_BUF_LEN 0xa000 +#define ASPEED_CRYPTO_GCM_TAG_OFFSET 0x9ff0 +#define ASPEED_HASH_SRC_DMA_BUF_LEN 0xa000 +#define ASPEED_HASH_QUEUE_LENGTH 50 + +#define HACE_CMD_IV_REQUIRE (HACE_CMD_CBC | HACE_CMD_CFB | \ + HACE_CMD_OFB | HACE_CMD_CTR) + +struct aspeed_hace_dev; + +typedef int (*aspeed_hace_fn_t)(struct aspeed_hace_dev *); + +struct aspeed_sg_list { + __le32 len; + __le32 phy_addr; +}; + +struct aspeed_engine_hash { + struct tasklet_struct done_task; + unsigned long flags; + struct ahash_request *req; + + /* input buffer */ + void *ahash_src_addr; + dma_addr_t ahash_src_dma_addr; + + dma_addr_t src_dma; + dma_addr_t digest_dma; + + size_t src_length; + + /* callback func */ + aspeed_hace_fn_t resume; + aspeed_hace_fn_t dma_prepare; +}; + +struct aspeed_sha_hmac_ctx { + struct crypto_shash *shash; + u8 ipad[SHA512_BLOCK_SIZE]; + u8 opad[SHA512_BLOCK_SIZE]; +}; + +struct aspeed_sham_ctx { + struct crypto_engine_ctx enginectx; + + struct aspeed_hace_dev *hace_dev; + unsigned long flags; /* hmac flag */ + + struct aspeed_sha_hmac_ctx base[0]; +}; + +struct aspeed_sham_reqctx { + unsigned long flags; /* final update flag should no use*/ + unsigned long op; /* final or update */ + u32 cmd; /* trigger cmd */ + + /* walk state */ + struct scatterlist *src_sg; + int src_nents; + unsigned int offset; /* offset in current sg */ + unsigned int total; /* per update length */ + + size_t digsize; + size_t block_size; + size_t ivsize; + const __be32 *sha_iv; + + /* remain data buffer */ + u8 buffer[SHA512_BLOCK_SIZE * 2]; + dma_addr_t buffer_dma_addr; + size_t bufcnt; /* buffer counter */ + + /* output buffer */ + u8 digest[SHA512_DIGEST_SIZE] __aligned(64); + dma_addr_t digest_dma_addr; + u64 digcnt[2]; +}; + +struct aspeed_engine_crypto { + struct tasklet_struct done_task; + unsigned long flags; + struct skcipher_request *req; + + /* context buffer */ + void *cipher_ctx; + dma_addr_t cipher_ctx_dma; + + /* input buffer, could be single/scatter-gather lists */ + void *cipher_addr; + dma_addr_t cipher_dma_addr; + + /* output buffer, only used in scatter-gather lists */ + void *dst_sg_addr; + dma_addr_t dst_sg_dma_addr; + + /* callback func */ + aspeed_hace_fn_t resume; +}; + +struct aspeed_cipher_ctx { + struct crypto_engine_ctx enginectx; + + struct aspeed_hace_dev *hace_dev; + int key_len; + u8 key[AES_MAX_KEYLENGTH]; + + /* callback func */ + aspeed_hace_fn_t start; + + struct crypto_skcipher *fallback_tfm; +}; + +struct aspeed_cipher_reqctx { + int enc_cmd; + int src_nents; + int dst_nents; + + struct skcipher_request fallback_req; /* keep at the end */ +}; + +struct aspeed_hace_dev { + void __iomem *regs; + struct device *dev; + int irq; + struct clk *clk; + unsigned long version; + + struct crypto_engine *crypt_engine_hash; + struct crypto_engine *crypt_engine_crypto; + + struct aspeed_engine_hash hash_engine; + struct aspeed_engine_crypto crypto_engine; +}; + +struct aspeed_hace_alg { + struct aspeed_hace_dev *hace_dev; + + const char *alg_base; + + union { + struct skcipher_alg skcipher; + struct ahash_alg ahash; + } alg; +}; + +enum aspeed_version { + AST2500_VERSION = 5, + AST2600_VERSION +}; + +#define ast_hace_write(hace, val, offset) \ + writel((val), (hace)->regs + (offset)) +#define ast_hace_read(hace, offset) \ + readl((hace)->regs + (offset)) + +void aspeed_register_hace_hash_algs(struct aspeed_hace_dev *hace_dev); +void aspeed_unregister_hace_hash_algs(struct aspeed_hace_dev *hace_dev); +void aspeed_register_hace_crypto_algs(struct aspeed_hace_dev *hace_dev); +void aspeed_unregister_hace_crypto_algs(struct aspeed_hace_dev *hace_dev); + +#endif diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index fe0558403191..886bf258544c 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -2509,6 +2509,7 @@ static void atmel_aes_get_cap(struct atmel_aes_dev *dd) /* keep only major version number */ switch (dd->hw_version & 0xff0) { + case 0x700: case 0x500: dd->caps.has_dualbuff = 1; dd->caps.has_cfb64 = 1; @@ -2668,8 +2669,7 @@ static int atmel_aes_remove(struct platform_device *pdev) struct atmel_aes_dev *aes_dd; aes_dd = platform_get_drvdata(pdev); - if (!aes_dd) - return -ENODEV; + spin_lock(&atmel_aes.lock); list_del(&aes_dd->list); spin_unlock(&atmel_aes.lock); diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c index 333fbefbbccb..82bf15d49561 100644 --- a/drivers/crypto/atmel-ecc.c +++ b/drivers/crypto/atmel-ecc.c @@ -343,14 +343,22 @@ static int atmel_ecc_probe(struct i2c_client *client, return ret; } -static int atmel_ecc_remove(struct i2c_client *client) +static void atmel_ecc_remove(struct i2c_client *client) { struct atmel_i2c_client_priv *i2c_priv = i2c_get_clientdata(client); /* Return EBUSY if i2c client already allocated. */ if (atomic_read(&i2c_priv->tfm_count)) { - dev_err(&client->dev, "Device is busy\n"); - return -EBUSY; + /* + * After we return here, the memory backing the device is freed. + * That happens no matter what the return value of this function + * is because in the Linux device model there is no error + * handling for unbinding a driver. + * If there is still some action pending, it probably involves + * accessing the freed memory. + */ + dev_emerg(&client->dev, "Device is busy, expect memory corruption.\n"); + return; } crypto_unregister_kpp(&atmel_ecdh_nist_p256); @@ -358,8 +366,6 @@ static int atmel_ecc_remove(struct i2c_client *client) spin_lock(&driver_data.i2c_list_lock); list_del(&i2c_priv->i2c_client_list_node); spin_unlock(&driver_data.i2c_list_lock); - - return 0; } #ifdef CONFIG_OF @@ -398,7 +404,7 @@ static int __init atmel_ecc_init(void) static void __exit atmel_ecc_exit(void) { - flush_scheduled_work(); + atmel_i2c_flush_queue(); i2c_del_driver(&atmel_ecc_driver); } diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c index 6fd3e969211d..81ce09bedda8 100644 --- a/drivers/crypto/atmel-i2c.c +++ b/drivers/crypto/atmel-i2c.c @@ -263,6 +263,8 @@ static void atmel_i2c_work_handler(struct work_struct *work) work_data->cbk(work_data, work_data->areq, status); } +static struct workqueue_struct *atmel_wq; + void atmel_i2c_enqueue(struct atmel_i2c_work_data *work_data, void (*cbk)(struct atmel_i2c_work_data *work_data, void *areq, int status), @@ -272,10 +274,16 @@ void atmel_i2c_enqueue(struct atmel_i2c_work_data *work_data, work_data->areq = areq; INIT_WORK(&work_data->work, atmel_i2c_work_handler); - schedule_work(&work_data->work); + queue_work(atmel_wq, &work_data->work); } EXPORT_SYMBOL(atmel_i2c_enqueue); +void atmel_i2c_flush_queue(void) +{ + flush_workqueue(atmel_wq); +} +EXPORT_SYMBOL(atmel_i2c_flush_queue); + static inline size_t atmel_i2c_wake_token_sz(u32 bus_clk_rate) { u32 no_of_bits = DIV_ROUND_UP(TWLO_USEC * bus_clk_rate, USEC_PER_SEC); @@ -364,14 +372,24 @@ int atmel_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) i2c_set_clientdata(client, i2c_priv); - ret = device_sanity_check(client); - if (ret) - return ret; - - return 0; + return device_sanity_check(client); } EXPORT_SYMBOL(atmel_i2c_probe); +static int __init atmel_i2c_init(void) +{ + atmel_wq = alloc_workqueue("atmel_wq", 0, 0); + return atmel_wq ? 0 : -ENOMEM; +} + +static void __exit atmel_i2c_exit(void) +{ + destroy_workqueue(atmel_wq); +} + +module_init(atmel_i2c_init); +module_exit(atmel_i2c_exit); + MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>"); MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h index 63b97b104f16..48929efe2a5b 100644 --- a/drivers/crypto/atmel-i2c.h +++ b/drivers/crypto/atmel-i2c.h @@ -173,6 +173,7 @@ void atmel_i2c_enqueue(struct atmel_i2c_work_data *work_data, void (*cbk)(struct atmel_i2c_work_data *work_data, void *areq, int status), void *areq); +void atmel_i2c_flush_queue(void); int atmel_i2c_send_receive(struct i2c_client *client, struct atmel_i2c_cmd *cmd); diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 1b13f601fd95..ca4b01926d1b 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -2508,6 +2508,7 @@ static void atmel_sha_get_cap(struct atmel_sha_dev *dd) /* keep only major version number */ switch (dd->hw_version & 0xff0) { + case 0x700: case 0x510: dd->caps.has_dma = 1; dd->caps.has_dualbuff = 1; @@ -2665,11 +2666,8 @@ err_tasklet_kill: static int atmel_sha_remove(struct platform_device *pdev) { - struct atmel_sha_dev *sha_dd; + struct atmel_sha_dev *sha_dd = platform_get_drvdata(pdev); - sha_dd = platform_get_drvdata(pdev); - if (!sha_dd) - return -ENODEV; spin_lock(&atmel_sha.lock); list_del(&sha_dd->list); spin_unlock(&atmel_sha.lock); diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c index c96c14e7dab1..a84b657598c6 100644 --- a/drivers/crypto/atmel-sha204a.c +++ b/drivers/crypto/atmel-sha204a.c @@ -116,28 +116,27 @@ static int atmel_sha204a_probe(struct i2c_client *client, return ret; } -static int atmel_sha204a_remove(struct i2c_client *client) +static void atmel_sha204a_remove(struct i2c_client *client) { struct atmel_i2c_client_priv *i2c_priv = i2c_get_clientdata(client); if (atomic_read(&i2c_priv->tfm_count)) { - dev_err(&client->dev, "Device is busy\n"); - return -EBUSY; + dev_emerg(&client->dev, "Device is busy, will remove it anyhow\n"); + return; } - if (i2c_priv->hwrng.priv) - kfree((void *)i2c_priv->hwrng.priv); - - return 0; + kfree((void *)i2c_priv->hwrng.priv); } static const struct of_device_id atmel_sha204a_dt_ids[] = { + { .compatible = "atmel,atsha204", }, { .compatible = "atmel,atsha204a", }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, atmel_sha204a_dt_ids); static const struct i2c_device_id atmel_sha204a_id[] = { + { "atsha204", 0 }, { "atsha204a", 0 }, { /* sentinel */ } }; @@ -159,7 +158,7 @@ static int __init atmel_sha204a_init(void) static void __exit atmel_sha204a_exit(void) { - flush_scheduled_work(); + atmel_i2c_flush_queue(); i2c_del_driver(&atmel_sha204a_driver); } diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index e30786ec9f2d..8b7bc1076e0d 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -1130,6 +1130,7 @@ static void atmel_tdes_get_cap(struct atmel_tdes_dev *dd) /* keep only major version number */ switch (dd->hw_version & 0xf00) { + case 0x800: case 0x700: dd->caps.has_dma = 1; dd->caps.has_cfb_3keys = 1; @@ -1262,11 +1263,8 @@ err_tasklet_kill: static int atmel_tdes_remove(struct platform_device *pdev) { - struct atmel_tdes_dev *tdes_dd; + struct atmel_tdes_dev *tdes_dd = platform_get_drvdata(pdev); - tdes_dd = platform_get_drvdata(pdev); - if (!tdes_dd) - return -ENODEV; spin_lock(&atmel_tdes.lock); list_del(&tdes_dd->list); spin_unlock(&atmel_tdes.lock); diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c index 9ad188cffd0d..51c66afbe677 100644 --- a/drivers/crypto/axis/artpec6_crypto.c +++ b/drivers/crypto/axis/artpec6_crypto.c @@ -1712,7 +1712,7 @@ static int artpec6_crypto_prepare_crypto(struct skcipher_request *areq) cipher_len = regk_crypto_key_256; break; default: - pr_err("%s: Invalid key length %d!\n", + pr_err("%s: Invalid key length %zu!\n", MODULE_NAME, ctx->key_length); return -EINVAL; } @@ -2091,7 +2091,7 @@ static void artpec6_crypto_task(unsigned long data) return; } - spin_lock_bh(&ac->queue_lock); + spin_lock(&ac->queue_lock); list_for_each_entry_safe(req, n, &ac->pending, list) { struct artpec6_crypto_dma_descriptors *dma = req->dma; @@ -2128,7 +2128,7 @@ static void artpec6_crypto_task(unsigned long data) artpec6_crypto_process_queue(ac, &complete_in_progress); - spin_unlock_bh(&ac->queue_lock); + spin_unlock(&ac->queue_lock); /* Perform the completion callbacks without holding the queue lock * to allow new request submissions from the callbacks. diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c index 053315e260c2..c8c799428fe0 100644 --- a/drivers/crypto/bcm/cipher.c +++ b/drivers/crypto/bcm/cipher.c @@ -1928,7 +1928,7 @@ static int ahash_enqueue(struct ahash_request *req) /* SPU2 hardware does not compute hash of zero length data */ if ((rctx->is_final == 1) && (rctx->total_todo == 0) && (iproc_priv.spu.spu_type == SPU_TYPE_SPU2)) { - alg_name = crypto_tfm_alg_name(crypto_ahash_tfm(tfm)); + alg_name = crypto_ahash_alg_name(tfm); flow_log("Doing %sfinal %s zero-len hash request in software\n", rctx->is_final ? "" : "non-", alg_name); err = do_shash((unsigned char *)alg_name, req->result, @@ -2029,7 +2029,7 @@ static int ahash_init(struct ahash_request *req) * supported by the hardware, we need to handle it in software * by calling synchronous hash functions. */ - alg_name = crypto_tfm_alg_name(crypto_ahash_tfm(tfm)); + alg_name = crypto_ahash_alg_name(tfm); hash = crypto_alloc_shash(alg_name, 0, 0); if (IS_ERR(hash)) { ret = PTR_ERR(hash); diff --git a/drivers/crypto/bcm/cipher.h b/drivers/crypto/bcm/cipher.h index 71281a3bdbdc..d6d87332140a 100644 --- a/drivers/crypto/bcm/cipher.h +++ b/drivers/crypto/bcm/cipher.h @@ -231,7 +231,7 @@ struct iproc_ctx_s { /* * shash descriptor - needed to perform incremental hashing in - * in software, when hw doesn't support it. + * software, when hw doesn't support it. */ struct shash_desc *shash; diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig index 84ea7cba5ee5..ec6a9e6ad4d2 100644 --- a/drivers/crypto/caam/Kconfig +++ b/drivers/crypto/caam/Kconfig @@ -151,6 +151,17 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API Selecting this will register the SEC4 hardware rng to the hw_random API for supplying the kernel entropy pool. +config CRYPTO_DEV_FSL_CAAM_PRNG_API + bool "Register Pseudo random number generation implementation with Crypto API" + default y + select CRYPTO_RNG + help + Selecting this will register the SEC hardware prng to + the Crypto API. + +config CRYPTO_DEV_FSL_CAAM_BLOB_GEN + bool + endif # CRYPTO_DEV_FSL_CAAM_JR endif # CRYPTO_DEV_FSL_CAAM diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile index 3570286eb9ce..acf1b197eb84 100644 --- a/drivers/crypto/caam/Makefile +++ b/drivers/crypto/caam/Makefile @@ -20,7 +20,9 @@ caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI) += caamalg_qi.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o +caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_PRNG_API) += caamprng.o caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_PKC_API) += caampkc.o pkc_desc.o +caam_jr-$(CONFIG_CRYPTO_DEV_FSL_CAAM_BLOB_GEN) += blob_gen.o caam-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI) += qi.o ifneq ($(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI),) diff --git a/drivers/crypto/caam/blob_gen.c b/drivers/crypto/caam/blob_gen.c new file mode 100644 index 000000000000..6345c7269eb0 --- /dev/null +++ b/drivers/crypto/caam/blob_gen.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 Pengutronix, Steffen Trumtrar <kernel@pengutronix.de> + * Copyright (C) 2021 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de> + */ + +#define pr_fmt(fmt) "caam blob_gen: " fmt + +#include <linux/device.h> +#include <soc/fsl/caam-blob.h> + +#include "compat.h" +#include "desc_constr.h" +#include "desc.h" +#include "error.h" +#include "intern.h" +#include "jr.h" +#include "regs.h" + +#define CAAM_BLOB_DESC_BYTES_MAX \ + /* Command to initialize & stating length of descriptor */ \ + (CAAM_CMD_SZ + \ + /* Command to append the key-modifier + key-modifier data */ \ + CAAM_CMD_SZ + CAAM_BLOB_KEYMOD_LENGTH + \ + /* Command to include input key + pointer to the input key */ \ + CAAM_CMD_SZ + CAAM_PTR_SZ_MAX + \ + /* Command to include output key + pointer to the output key */ \ + CAAM_CMD_SZ + CAAM_PTR_SZ_MAX + \ + /* Command describing the operation to perform */ \ + CAAM_CMD_SZ) + +struct caam_blob_priv { + struct device jrdev; +}; + +struct caam_blob_job_result { + int err; + struct completion completion; +}; + +static void caam_blob_job_done(struct device *dev, u32 *desc, u32 err, void *context) +{ + struct caam_blob_job_result *res = context; + int ecode = 0; + + dev_dbg(dev, "%s %d: err 0x%x\n", __func__, __LINE__, err); + + if (err) + ecode = caam_jr_strstatus(dev, err); + + res->err = ecode; + + /* + * Upon completion, desc points to a buffer containing a CAAM job + * descriptor which encapsulates data into an externally-storable + * blob. + */ + complete(&res->completion); +} + +int caam_process_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info, bool encap) +{ + struct caam_blob_job_result testres; + struct device *jrdev = &priv->jrdev; + dma_addr_t dma_in, dma_out; + int op = OP_PCLID_BLOB; + size_t output_len; + u32 *desc; + int ret; + + if (info->key_mod_len > CAAM_BLOB_KEYMOD_LENGTH) + return -EINVAL; + + if (encap) { + op |= OP_TYPE_ENCAP_PROTOCOL; + output_len = info->input_len + CAAM_BLOB_OVERHEAD; + } else { + op |= OP_TYPE_DECAP_PROTOCOL; + output_len = info->input_len - CAAM_BLOB_OVERHEAD; + } + + desc = kzalloc(CAAM_BLOB_DESC_BYTES_MAX, GFP_KERNEL | GFP_DMA); + if (!desc) + return -ENOMEM; + + dma_in = dma_map_single(jrdev, info->input, info->input_len, + DMA_TO_DEVICE); + if (dma_mapping_error(jrdev, dma_in)) { + dev_err(jrdev, "unable to map input DMA buffer\n"); + ret = -ENOMEM; + goto out_free; + } + + dma_out = dma_map_single(jrdev, info->output, output_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(jrdev, dma_out)) { + dev_err(jrdev, "unable to map output DMA buffer\n"); + ret = -ENOMEM; + goto out_unmap_in; + } + + /* + * A data blob is encrypted using a blob key (BK); a random number. + * The BK is used as an AES-CCM key. The initial block (B0) and the + * initial counter (Ctr0) are generated automatically and stored in + * Class 1 Context DWords 0+1+2+3. The random BK is stored in the + * Class 1 Key Register. Operation Mode is set to AES-CCM. + */ + + init_job_desc(desc, 0); + append_key_as_imm(desc, info->key_mod, info->key_mod_len, + info->key_mod_len, CLASS_2 | KEY_DEST_CLASS_REG); + append_seq_in_ptr_intlen(desc, dma_in, info->input_len, 0); + append_seq_out_ptr_intlen(desc, dma_out, output_len, 0); + append_operation(desc, op); + + print_hex_dump_debug("data@"__stringify(__LINE__)": ", + DUMP_PREFIX_ADDRESS, 16, 1, info->input, + info->input_len, false); + print_hex_dump_debug("jobdesc@"__stringify(__LINE__)": ", + DUMP_PREFIX_ADDRESS, 16, 1, desc, + desc_bytes(desc), false); + + testres.err = 0; + init_completion(&testres.completion); + + ret = caam_jr_enqueue(jrdev, desc, caam_blob_job_done, &testres); + if (ret == -EINPROGRESS) { + wait_for_completion(&testres.completion); + ret = testres.err; + print_hex_dump_debug("output@"__stringify(__LINE__)": ", + DUMP_PREFIX_ADDRESS, 16, 1, info->output, + output_len, false); + } + + if (ret == 0) + info->output_len = output_len; + + dma_unmap_single(jrdev, dma_out, output_len, DMA_FROM_DEVICE); +out_unmap_in: + dma_unmap_single(jrdev, dma_in, info->input_len, DMA_TO_DEVICE); +out_free: + kfree(desc); + + return ret; +} +EXPORT_SYMBOL(caam_process_blob); + +struct caam_blob_priv *caam_blob_gen_init(void) +{ + struct caam_drv_private *ctrlpriv; + struct device *jrdev; + + /* + * caam_blob_gen_init() may expectedly fail with -ENODEV, e.g. when + * CAAM driver didn't probe or when SoC lacks BLOB support. An + * error would be harsh in this case, so we stick to info level. + */ + + jrdev = caam_jr_alloc(); + if (IS_ERR(jrdev)) { + pr_info("job ring requested, but none currently available\n"); + return ERR_PTR(-ENODEV); + } + + ctrlpriv = dev_get_drvdata(jrdev->parent); + if (!ctrlpriv->blob_present) { + dev_info(jrdev, "no hardware blob generation support\n"); + caam_jr_free(jrdev); + return ERR_PTR(-ENODEV); + } + + return container_of(jrdev, struct caam_blob_priv, jrdev); +} +EXPORT_SYMBOL(caam_blob_gen_init); + +void caam_blob_gen_exit(struct caam_blob_priv *priv) +{ + caam_jr_free(&priv->jrdev); +} +EXPORT_SYMBOL(caam_blob_gen_exit); diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 6753f0e6e55d..4482cb145d05 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -29,7 +29,7 @@ SHA512_DIGEST_SIZE * 2) /* - * This is a a cache of buffers, from which the users of CAAM QI driver + * This is a cache of buffers, from which the users of CAAM QI driver * can allocate short buffers. It's speedier than doing kmalloc on the hotpath. * NOTE: A more elegant solution would be to have some headroom in the frames * being processed. This can be added by the dpaa2-eth driver. This would @@ -5083,8 +5083,9 @@ static int __cold dpaa2_dpseci_setup(struct fsl_mc_device *ls_dev) ppriv->net_dev.dev = *dev; INIT_LIST_HEAD(&ppriv->net_dev.napi_list); - netif_napi_add(&ppriv->net_dev, &ppriv->napi, dpaa2_dpseci_poll, - DPAA2_CAAM_NAPI_WEIGHT); + netif_napi_add_tx_weight(&ppriv->net_dev, &ppriv->napi, + dpaa2_dpseci_poll, + DPAA2_CAAM_NAPI_WEIGHT); } return 0; diff --git a/drivers/crypto/caam/caamhash_desc.c b/drivers/crypto/caam/caamhash_desc.c index 78383d77da99..619564509936 100644 --- a/drivers/crypto/caam/caamhash_desc.c +++ b/drivers/crypto/caam/caamhash_desc.c @@ -22,7 +22,7 @@ * @ctx_len: size of Context Register * @import_ctx: true if previous Context Register needs to be restored * must be true for ahash update and final - * must be false for for ahash first and digest + * must be false for ahash first and digest * @era: SEC Era */ void cnstr_shdsc_ahash(u32 * const desc, struct alginfo *adata, u32 state, diff --git a/drivers/crypto/caam/caamprng.c b/drivers/crypto/caam/caamprng.c new file mode 100644 index 000000000000..4839e66300a2 --- /dev/null +++ b/drivers/crypto/caam/caamprng.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Driver to expose SEC4 PRNG via crypto RNG API + * + * Copyright 2022 NXP + * + */ + +#include <linux/completion.h> +#include <crypto/internal/rng.h> +#include "compat.h" +#include "regs.h" +#include "intern.h" +#include "desc_constr.h" +#include "jr.h" +#include "error.h" + +/* + * Length of used descriptors, see caam_init_desc() + */ +#define CAAM_PRNG_MAX_DESC_LEN (CAAM_CMD_SZ + \ + CAAM_CMD_SZ + \ + CAAM_CMD_SZ + CAAM_PTR_SZ_MAX) + +/* prng per-device context */ +struct caam_prng_ctx { + int err; + struct completion done; +}; + +struct caam_prng_alg { + struct rng_alg rng; + bool registered; +}; + +static void caam_prng_done(struct device *jrdev, u32 *desc, u32 err, + void *context) +{ + struct caam_prng_ctx *jctx = context; + + jctx->err = err ? caam_jr_strstatus(jrdev, err) : 0; + + complete(&jctx->done); +} + +static u32 *caam_init_reseed_desc(u32 *desc) +{ + init_job_desc(desc, 0); /* + 1 cmd_sz */ + /* Generate random bytes: + 1 cmd_sz */ + append_operation(desc, OP_TYPE_CLASS1_ALG | OP_ALG_ALGSEL_RNG | + OP_ALG_AS_FINALIZE); + + print_hex_dump_debug("prng reseed desc@: ", DUMP_PREFIX_ADDRESS, + 16, 4, desc, desc_bytes(desc), 1); + + return desc; +} + +static u32 *caam_init_prng_desc(u32 *desc, dma_addr_t dst_dma, u32 len) +{ + init_job_desc(desc, 0); /* + 1 cmd_sz */ + /* Generate random bytes: + 1 cmd_sz */ + append_operation(desc, OP_ALG_ALGSEL_RNG | OP_TYPE_CLASS1_ALG); + /* Store bytes: + 1 cmd_sz + caam_ptr_sz */ + append_fifo_store(desc, dst_dma, + len, FIFOST_TYPE_RNGSTORE); + + print_hex_dump_debug("prng job desc@: ", DUMP_PREFIX_ADDRESS, + 16, 4, desc, desc_bytes(desc), 1); + + return desc; +} + +static int caam_prng_generate(struct crypto_rng *tfm, + const u8 *src, unsigned int slen, + u8 *dst, unsigned int dlen) +{ + struct caam_prng_ctx ctx; + struct device *jrdev; + dma_addr_t dst_dma; + u32 *desc; + u8 *buf; + int ret; + + buf = kzalloc(dlen, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + jrdev = caam_jr_alloc(); + ret = PTR_ERR_OR_ZERO(jrdev); + if (ret) { + pr_err("Job Ring Device allocation failed\n"); + kfree(buf); + return ret; + } + + desc = kzalloc(CAAM_PRNG_MAX_DESC_LEN, GFP_KERNEL | GFP_DMA); + if (!desc) { + ret = -ENOMEM; + goto out1; + } + + dst_dma = dma_map_single(jrdev, buf, dlen, DMA_FROM_DEVICE); + if (dma_mapping_error(jrdev, dst_dma)) { + dev_err(jrdev, "Failed to map destination buffer memory\n"); + ret = -ENOMEM; + goto out; + } + + init_completion(&ctx.done); + ret = caam_jr_enqueue(jrdev, + caam_init_prng_desc(desc, dst_dma, dlen), + caam_prng_done, &ctx); + + if (ret == -EINPROGRESS) { + wait_for_completion(&ctx.done); + ret = ctx.err; + } + + dma_unmap_single(jrdev, dst_dma, dlen, DMA_FROM_DEVICE); + + if (!ret) + memcpy(dst, buf, dlen); +out: + kfree(desc); +out1: + caam_jr_free(jrdev); + kfree(buf); + return ret; +} + +static void caam_prng_exit(struct crypto_tfm *tfm) {} + +static int caam_prng_init(struct crypto_tfm *tfm) +{ + return 0; +} + +static int caam_prng_seed(struct crypto_rng *tfm, + const u8 *seed, unsigned int slen) +{ + struct caam_prng_ctx ctx; + struct device *jrdev; + u32 *desc; + int ret; + + if (slen) { + pr_err("Seed length should be zero\n"); + return -EINVAL; + } + + jrdev = caam_jr_alloc(); + ret = PTR_ERR_OR_ZERO(jrdev); + if (ret) { + pr_err("Job Ring Device allocation failed\n"); + return ret; + } + + desc = kzalloc(CAAM_PRNG_MAX_DESC_LEN, GFP_KERNEL | GFP_DMA); + if (!desc) { + caam_jr_free(jrdev); + return -ENOMEM; + } + + init_completion(&ctx.done); + ret = caam_jr_enqueue(jrdev, + caam_init_reseed_desc(desc), + caam_prng_done, &ctx); + + if (ret == -EINPROGRESS) { + wait_for_completion(&ctx.done); + ret = ctx.err; + } + + kfree(desc); + caam_jr_free(jrdev); + return ret; +} + +static struct caam_prng_alg caam_prng_alg = { + .rng = { + .generate = caam_prng_generate, + .seed = caam_prng_seed, + .seedsize = 0, + .base = { + .cra_name = "stdrng", + .cra_driver_name = "prng-caam", + .cra_priority = 500, + .cra_ctxsize = sizeof(struct caam_prng_ctx), + .cra_module = THIS_MODULE, + .cra_init = caam_prng_init, + .cra_exit = caam_prng_exit, + }, + } +}; + +void caam_prng_unregister(void *data) +{ + if (caam_prng_alg.registered) + crypto_unregister_rng(&caam_prng_alg.rng); +} + +int caam_prng_register(struct device *ctrldev) +{ + struct caam_drv_private *priv = dev_get_drvdata(ctrldev); + u32 rng_inst; + int ret = 0; + + /* Check for available RNG blocks before registration */ + if (priv->era < 10) + rng_inst = (rd_reg32(&priv->jr[0]->perfmon.cha_num_ls) & + CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT; + else + rng_inst = rd_reg32(&priv->jr[0]->vreg.rng) & CHA_VER_NUM_MASK; + + if (!rng_inst) { + dev_dbg(ctrldev, "RNG block is not available... skipping registering algorithm\n"); + return ret; + } + + ret = crypto_register_rng(&caam_prng_alg.rng); + if (ret) { + dev_err(ctrldev, + "couldn't register rng crypto alg: %d\n", + ret); + return ret; + } + + caam_prng_alg.registered = true; + + dev_info(ctrldev, + "rng crypto API alg registered %s\n", caam_prng_alg.rng.base.cra_driver_name); + + return 0; +} diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index ca0361b2dbb0..32253a064d0f 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -609,6 +609,13 @@ static bool check_version(struct fsl_mc_version *mc_version, u32 major, } #endif +static bool needs_entropy_delay_adjustment(void) +{ + if (of_machine_is_compatible("fsl,imx6sx")) + return true; + return false; +} + /* Probe routine for CAAM top (controller) level */ static int caam_probe(struct platform_device *pdev) { @@ -820,12 +827,25 @@ static int caam_probe(struct platform_device *pdev) return -ENOMEM; } - if (ctrlpriv->era < 10) + comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ls); + ctrlpriv->blob_present = !!(comp_params & CTPR_LS_BLOB); + + /* + * Some SoCs like the LS1028A (non-E) indicate CTPR_LS_BLOB support, + * but fail when actually using it due to missing AES support, so + * check both here. + */ + if (ctrlpriv->era < 10) { rng_vid = (rd_reg32(&ctrl->perfmon.cha_id_ls) & CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT; - else + ctrlpriv->blob_present = ctrlpriv->blob_present && + (rd_reg32(&ctrl->perfmon.cha_num_ls) & CHA_ID_LS_AES_MASK); + } else { rng_vid = (rd_reg32(&ctrl->vreg.rng) & CHA_VER_VID_MASK) >> CHA_VER_VID_SHIFT; + ctrlpriv->blob_present = ctrlpriv->blob_present && + (rd_reg32(&ctrl->vreg.aesa) & CHA_VER_MISC_AES_NUM_MASK); + } /* * If SEC has RNG version >= 4 and RNG state handle has not been @@ -855,6 +875,8 @@ static int caam_probe(struct platform_device *pdev) * Also, if a handle was instantiated, do not change * the TRNG parameters. */ + if (needs_entropy_delay_adjustment()) + ent_delay = 12000; if (!(ctrlpriv->rng4_sh_init || inst_handles)) { dev_info(dev, "Entropy delay = %u\n", @@ -871,6 +893,15 @@ static int caam_probe(struct platform_device *pdev) */ ret = instantiate_rng(dev, inst_handles, gen_sk); + /* + * Entropy delay is determined via TRNG characterization. + * TRNG characterization is run across different voltages + * and temperatures. + * If worst case value for ent_dly is identified, + * the loop can be skipped for that platform. + */ + if (needs_entropy_delay_adjustment()) + break; if (ret == -EAGAIN) /* * if here, the loop will rerun, diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h index 7d45b21bd55a..572cf66c887a 100644 --- a/drivers/crypto/caam/intern.h +++ b/drivers/crypto/caam/intern.h @@ -92,6 +92,7 @@ struct caam_drv_private { */ u8 total_jobrs; /* Total Job Rings in device */ u8 qi_present; /* Nonzero if QI present in device */ + u8 blob_present; /* Nonzero if BLOB support present in device */ u8 mc_en; /* Nonzero if MC f/w is active */ int secvio_irq; /* Security violation interrupt number */ int virt_en; /* Virtualization enabled in CAAM */ @@ -185,6 +186,21 @@ static inline void caam_rng_exit(struct device *dev) {} #endif /* CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API */ +#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_PRNG_API + +int caam_prng_register(struct device *dev); +void caam_prng_unregister(void *data); + +#else + +static inline int caam_prng_register(struct device *dev) +{ + return 0; +} + +static inline void caam_prng_unregister(void *data) {} +#endif /* CONFIG_CRYPTO_DEV_FSL_CAAM_PRNG_API */ + #ifdef CONFIG_CAAM_QI int caam_qi_algapi_init(struct device *dev); diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index 7f2b1101f567..724fdec18bf9 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -39,6 +39,7 @@ static void register_algs(struct caam_drv_private_jr *jrpriv, caam_algapi_hash_init(dev); caam_pkc_init(dev); jrpriv->hwrng = !caam_rng_init(dev); + caam_prng_register(dev); caam_qi_algapi_init(dev); algs_unlock: @@ -53,7 +54,7 @@ static void unregister_algs(void) goto algs_unlock; caam_qi_algapi_exit(); - + caam_prng_unregister(NULL); caam_pkc_exit(); caam_algapi_hash_exit(); caam_algapi_exit(); diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h index 8ccc22075043..4b1bcf53f7ac 100644 --- a/drivers/crypto/caam/pdb.h +++ b/drivers/crypto/caam/pdb.h @@ -144,7 +144,7 @@ struct ipsec_encap_pdb { }; u32 spi; u32 ip_hdr_len; - u32 ip_hdr[0]; + u32 ip_hdr[]; }; /** diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c index 8163f5df8ebf..c36f27376d7e 100644 --- a/drivers/crypto/caam/qi.c +++ b/drivers/crypto/caam/qi.c @@ -75,7 +75,7 @@ bool caam_congested __read_mostly; EXPORT_SYMBOL(caam_congested); /* - * This is a a cache of buffers, from which the users of CAAM QI driver + * This is a cache of buffers, from which the users of CAAM QI driver * can allocate short (CAAM_QI_MEMCACHE_SIZE) buffers. It's faster than * doing malloc on the hotpath. * NOTE: A more elegant solution would be to have some headroom in the frames @@ -749,8 +749,8 @@ int caam_qi_init(struct platform_device *caam_pdev) net_dev->dev = *qidev; INIT_LIST_HEAD(&net_dev->napi_list); - netif_napi_add(net_dev, irqtask, caam_qi_poll, - CAAM_NAPI_WEIGHT); + netif_napi_add_tx_weight(net_dev, irqtask, caam_qi_poll, + CAAM_NAPI_WEIGHT); napi_enable(irqtask); } diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h index 3738625c0250..66d6dad841bb 100644 --- a/drivers/crypto/caam/regs.h +++ b/drivers/crypto/caam/regs.h @@ -320,7 +320,8 @@ struct version_regs { #define CHA_VER_VID_MASK (0xffull << CHA_VER_VID_SHIFT) /* CHA Miscellaneous Information - AESA_MISC specific */ -#define CHA_VER_MISC_AES_GCM BIT(1 + CHA_VER_MISC_SHIFT) +#define CHA_VER_MISC_AES_NUM_MASK GENMASK(7, 0) +#define CHA_VER_MISC_AES_GCM BIT(1 + CHA_VER_MISC_SHIFT) /* CHA Miscellaneous Information - PKHA_MISC specific */ #define CHA_VER_MISC_PKHA_NO_CRYPT BIT(7 + CHA_VER_MISC_SHIFT) @@ -414,6 +415,7 @@ struct caam_perfmon { #define CTPR_MS_PG_SZ_MASK 0x10 #define CTPR_MS_PG_SZ_SHIFT 4 u32 comp_parms_ms; /* CTPR - Compile Parameters Register */ +#define CTPR_LS_BLOB BIT(1) u32 comp_parms_ls; /* CTPR - Compile Parameters Register */ u64 rsvd1[2]; diff --git a/drivers/crypto/cavium/cpt/cpt_hw_types.h b/drivers/crypto/cavium/cpt/cpt_hw_types.h index 96bc963bb804..ae4791a8ec4a 100644 --- a/drivers/crypto/cavium/cpt/cpt_hw_types.h +++ b/drivers/crypto/cavium/cpt/cpt_hw_types.h @@ -265,7 +265,7 @@ union cptx_pf_exe_bist_status { * big-endian format in memory. * iqb_ldwb:1 [7:7](R/W) Instruction load don't write back. * 0 = The hardware issues NCB transient load (LDT) towards the cache, - * which if the line hits and is is dirty will cause the line to be + * which if the line hits and it is dirty will cause the line to be * written back before being replaced. * 1 = The hardware issues NCB LDWB read-and-invalidate command towards * the cache when fetching the last word of instructions; as a result the @@ -396,7 +396,7 @@ union cptx_vqx_misc_ena_w1s { * Word0 * reserved_20_63:44 [63:20] Reserved. * dbell_cnt:20 [19:0](R/W/H) Number of instruction queue 64-bit words to add - * to the CPT instruction doorbell count. Readback value is the the + * to the CPT instruction doorbell count. Readback value is the * current number of pending doorbell requests. If counter overflows * CPT()_VQ()_MISC_INT[DBELL_DOVF] is set. To reset the count back to * zero, write one to clear CPT()_VQ()_MISC_INT_ENA_W1C[DBELL_DOVF], diff --git a/drivers/crypto/cavium/cpt/cptpf_main.c b/drivers/crypto/cavium/cpt/cptpf_main.c index 8c32d0eb8fcf..6872ac344001 100644 --- a/drivers/crypto/cavium/cpt/cptpf_main.c +++ b/drivers/crypto/cavium/cpt/cptpf_main.c @@ -253,6 +253,7 @@ static int cpt_ucode_load_fw(struct cpt_device *cpt, const u8 *fw, bool is_ae) const struct firmware *fw_entry; struct device *dev = &cpt->pdev->dev; struct ucode_header *ucode; + unsigned int code_length; struct microcode *mcode; int j, ret = 0; @@ -263,11 +264,12 @@ static int cpt_ucode_load_fw(struct cpt_device *cpt, const u8 *fw, bool is_ae) ucode = (struct ucode_header *)fw_entry->data; mcode = &cpt->mcode[cpt->next_mc_idx]; memcpy(mcode->version, (u8 *)fw_entry->data, CPT_UCODE_VERSION_SZ); - mcode->code_size = ntohl(ucode->code_length) * 2; - if (!mcode->code_size) { + code_length = ntohl(ucode->code_length); + if (code_length == 0 || code_length >= INT_MAX / 2) { ret = -EINVAL; goto fw_release; } + mcode->code_size = code_length * 2; mcode->is_ae = is_ae; mcode->core_mask = 0ULL; diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c index 6c61817996a3..432a61aca0c5 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_main.c +++ b/drivers/crypto/cavium/nitrox/nitrox_main.c @@ -269,15 +269,17 @@ static void nitrox_remove_from_devlist(struct nitrox_device *ndev) struct nitrox_device *nitrox_get_first_device(void) { - struct nitrox_device *ndev; + struct nitrox_device *ndev = NULL, *iter; mutex_lock(&devlist_lock); - list_for_each_entry(ndev, &ndevlist, list) { - if (nitrox_ready(ndev)) + list_for_each_entry(iter, &ndevlist, list) { + if (nitrox_ready(iter)) { + ndev = iter; break; + } } mutex_unlock(&devlist_lock); - if (&ndev->list == &ndevlist) + if (!ndev) return NULL; refcount_inc(&ndev->refcnt); diff --git a/drivers/crypto/cavium/nitrox/nitrox_mbx.c b/drivers/crypto/cavium/nitrox/nitrox_mbx.c index 2e9c0d214363..9e7308e39b30 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_mbx.c +++ b/drivers/crypto/cavium/nitrox/nitrox_mbx.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/bitmap.h> #include <linux/workqueue.h> #include "nitrox_csr.h" @@ -120,6 +121,7 @@ static void pf2vf_resp_handler(struct work_struct *work) void nitrox_pf2vf_mbox_handler(struct nitrox_device *ndev) { + DECLARE_BITMAP(csr, BITS_PER_TYPE(u64)); struct nitrox_vfdev *vfdev; struct pf2vf_work *pfwork; u64 value, reg_addr; @@ -129,7 +131,8 @@ void nitrox_pf2vf_mbox_handler(struct nitrox_device *ndev) /* loop for VF(0..63) */ reg_addr = NPS_PKT_MBOX_INT_LO; value = nitrox_read_csr(ndev, reg_addr); - for_each_set_bit(i, (const unsigned long *)&value, BITS_PER_LONG) { + bitmap_from_u64(csr, value); + for_each_set_bit(i, csr, BITS_PER_TYPE(csr)) { /* get the vfno from ring */ vfno = RING_TO_VFNO(i, ndev->iov.max_vf_queues); vfdev = ndev->iov.vfdev + vfno; @@ -151,7 +154,8 @@ void nitrox_pf2vf_mbox_handler(struct nitrox_device *ndev) /* loop for VF(64..127) */ reg_addr = NPS_PKT_MBOX_INT_HI; value = nitrox_read_csr(ndev, reg_addr); - for_each_set_bit(i, (const unsigned long *)&value, BITS_PER_LONG) { + bitmap_from_u64(csr, value); + for_each_set_bit(i, csr, BITS_PER_TYPE(csr)) { /* get the vfno from ring */ vfno = RING_TO_VFNO(i + 64, ndev->iov.max_vf_queues); vfdev = ndev->iov.vfdev + vfno; diff --git a/drivers/crypto/cavium/nitrox/nitrox_req.h b/drivers/crypto/cavium/nitrox/nitrox_req.h index ed174883c8e3..6bf088bcdd11 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_req.h +++ b/drivers/crypto/cavium/nitrox/nitrox_req.h @@ -440,7 +440,7 @@ struct aqmq_command_s { /** * struct ctx_hdr - Book keeping data about the crypto context * @pool: Pool used to allocate crypto context - * @dma: Base DMA address of the cypto context + * @dma: Base DMA address of the crypto context * @ctx_dma: Actual usable crypto context for NITROX */ struct ctx_hdr { diff --git a/drivers/crypto/cavium/zip/zip_crypto.c b/drivers/crypto/cavium/zip/zip_crypto.c index 7df71fcebe8f..1046a746d36f 100644 --- a/drivers/crypto/cavium/zip/zip_crypto.c +++ b/drivers/crypto/cavium/zip/zip_crypto.c @@ -198,22 +198,16 @@ static int zip_decompress(const u8 *src, unsigned int slen, /* Legacy Compress framework start */ int zip_alloc_comp_ctx_deflate(struct crypto_tfm *tfm) { - int ret; struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm); - ret = zip_ctx_init(zip_ctx, 0); - - return ret; + return zip_ctx_init(zip_ctx, 0); } int zip_alloc_comp_ctx_lzs(struct crypto_tfm *tfm) { - int ret; struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm); - ret = zip_ctx_init(zip_ctx, 1); - - return ret; + return zip_ctx_init(zip_ctx, 1); } void zip_free_comp_ctx(struct crypto_tfm *tfm) @@ -227,24 +221,18 @@ int zip_comp_compress(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen) { - int ret; struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm); - ret = zip_compress(src, slen, dst, dlen, zip_ctx); - - return ret; + return zip_compress(src, slen, dst, dlen, zip_ctx); } int zip_comp_decompress(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen) { - int ret; struct zip_kernel_ctx *zip_ctx = crypto_tfm_ctx(tfm); - ret = zip_decompress(src, slen, dst, dlen, zip_ctx); - - return ret; + return zip_decompress(src, slen, dst, dlen, zip_ctx); } /* Legacy compress framework end */ /* SCOMP framework start */ @@ -298,22 +286,16 @@ int zip_scomp_compress(struct crypto_scomp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen, void *ctx) { - int ret; struct zip_kernel_ctx *zip_ctx = ctx; - ret = zip_compress(src, slen, dst, dlen, zip_ctx); - - return ret; + return zip_compress(src, slen, dst, dlen, zip_ctx); } int zip_scomp_decompress(struct crypto_scomp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen, void *ctx) { - int ret; struct zip_kernel_ctx *zip_ctx = ctx; - ret = zip_decompress(src, slen, dst, dlen, zip_ctx); - - return ret; + return zip_decompress(src, slen, dst, dlen, zip_ctx); } /* SCOMP framework end */ diff --git a/drivers/crypto/cavium/zip/zip_main.c b/drivers/crypto/cavium/zip/zip_main.c index 812b4ac9afd6..dc5b7bf7e1fd 100644 --- a/drivers/crypto/cavium/zip/zip_main.c +++ b/drivers/crypto/cavium/zip/zip_main.c @@ -55,6 +55,11 @@ static const struct pci_device_id zip_id_table[] = { { 0, } }; +static void zip_debugfs_init(void); +static void zip_debugfs_exit(void); +static int zip_register_compression_device(void); +static void zip_unregister_compression_device(void); + void zip_reg_write(u64 val, u64 __iomem *addr) { writeq(val, addr); @@ -235,6 +240,15 @@ static int zip_init_hw(struct zip_device *zip) return 0; } +static void zip_reset(struct zip_device *zip) +{ + union zip_cmd_ctl cmd_ctl; + + cmd_ctl.u_reg64 = 0x0ull; + cmd_ctl.s.reset = 1; /* Forces ZIP cores to do reset */ + zip_reg_write(cmd_ctl.u_reg64, (zip->reg_base + ZIP_CMD_CTL)); +} + static int zip_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct device *dev = &pdev->dev; @@ -282,8 +296,21 @@ static int zip_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_release_regions; + /* Register with the Kernel Crypto Interface */ + err = zip_register_compression_device(); + if (err < 0) { + zip_err("ZIP: Kernel Crypto Registration failed\n"); + goto err_register; + } + + /* comp-decomp statistics are handled with debugfs interface */ + zip_debugfs_init(); + return 0; +err_register: + zip_reset(zip); + err_release_regions: if (zip->reg_base) iounmap(zip->reg_base); @@ -305,16 +332,17 @@ err_free_device: static void zip_remove(struct pci_dev *pdev) { struct zip_device *zip = pci_get_drvdata(pdev); - union zip_cmd_ctl cmd_ctl; int q = 0; if (!zip) return; + zip_debugfs_exit(); + + zip_unregister_compression_device(); + if (zip->reg_base) { - cmd_ctl.u_reg64 = 0x0ull; - cmd_ctl.s.reset = 1; /* Forces ZIP cores to do reset */ - zip_reg_write(cmd_ctl.u_reg64, (zip->reg_base + ZIP_CMD_CTL)); + zip_reset(zip); iounmap(zip->reg_base); } @@ -585,7 +613,7 @@ DEFINE_SHOW_ATTRIBUTE(zip_regs); /* Root directory for thunderx_zip debugfs entry */ static struct dentry *zip_debugfs_root; -static void __init zip_debugfs_init(void) +static void zip_debugfs_init(void) { if (!debugfs_initialized()) return; @@ -604,7 +632,7 @@ static void __init zip_debugfs_init(void) } -static void __exit zip_debugfs_exit(void) +static void zip_debugfs_exit(void) { debugfs_remove_recursive(zip_debugfs_root); } @@ -615,48 +643,7 @@ static void __exit zip_debugfs_exit(void) { } #endif /* debugfs - end */ -static int __init zip_init_module(void) -{ - int ret; - - zip_msg("%s\n", DRV_NAME); - - ret = pci_register_driver(&zip_driver); - if (ret < 0) { - zip_err("ZIP: pci_register_driver() failed\n"); - return ret; - } - - /* Register with the Kernel Crypto Interface */ - ret = zip_register_compression_device(); - if (ret < 0) { - zip_err("ZIP: Kernel Crypto Registration failed\n"); - goto err_pci_unregister; - } - - /* comp-decomp statistics are handled with debugfs interface */ - zip_debugfs_init(); - - return ret; - -err_pci_unregister: - pci_unregister_driver(&zip_driver); - return ret; -} - -static void __exit zip_cleanup_module(void) -{ - zip_debugfs_exit(); - - /* Unregister from the kernel crypto interface */ - zip_unregister_compression_device(); - - /* Unregister this driver for pci zip devices */ - pci_unregister_driver(&zip_driver); -} - -module_init(zip_init_module); -module_exit(zip_cleanup_module); +module_pci_driver(zip_driver); MODULE_AUTHOR("Cavium Inc"); MODULE_DESCRIPTION("Cavium Inc ThunderX ZIP Driver"); diff --git a/drivers/crypto/ccp/ccp-crypto-aes.c b/drivers/crypto/ccp/ccp-crypto-aes.c index e6dcd8cedd53..bed331953ff9 100644 --- a/drivers/crypto/ccp/ccp-crypto-aes.c +++ b/drivers/crypto/ccp/ccp-crypto-aes.c @@ -69,7 +69,6 @@ static int ccp_aes_crypt(struct skcipher_request *req, bool encrypt) struct ccp_aes_req_ctx *rctx = skcipher_request_ctx(req); struct scatterlist *iv_sg = NULL; unsigned int iv_len = 0; - int ret; if (!ctx->u.aes.key_len) return -EINVAL; @@ -104,9 +103,7 @@ static int ccp_aes_crypt(struct skcipher_request *req, bool encrypt) rctx->cmd.u.aes.src_len = req->cryptlen; rctx->cmd.u.aes.dst = req->dst; - ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd); - - return ret; + return ccp_crypto_enqueue_request(&req->base, &rctx->cmd); } static int ccp_aes_encrypt(struct skcipher_request *req) diff --git a/drivers/crypto/ccp/ccp-crypto-des3.c b/drivers/crypto/ccp/ccp-crypto-des3.c index ec97daf0fcb7..278636ed251a 100644 --- a/drivers/crypto/ccp/ccp-crypto-des3.c +++ b/drivers/crypto/ccp/ccp-crypto-des3.c @@ -64,7 +64,6 @@ static int ccp_des3_crypt(struct skcipher_request *req, bool encrypt) struct ccp_des3_req_ctx *rctx = skcipher_request_ctx(req); struct scatterlist *iv_sg = NULL; unsigned int iv_len = 0; - int ret; if (!ctx->u.des3.key_len) return -EINVAL; @@ -100,9 +99,7 @@ static int ccp_des3_crypt(struct skcipher_request *req, bool encrypt) rctx->cmd.u.des3.src_len = req->cryptlen; rctx->cmd.u.des3.dst = req->dst; - ret = ccp_crypto_enqueue_request(&req->base, &rctx->cmd); - - return ret; + return ccp_crypto_enqueue_request(&req->base, &rctx->cmd); } static int ccp_des3_encrypt(struct skcipher_request *req) diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h index a5d9123a22ea..83350e2d9821 100644 --- a/drivers/crypto/ccp/ccp-dev.h +++ b/drivers/crypto/ccp/ccp-dev.h @@ -366,7 +366,7 @@ struct ccp_device { /* Master lists that all cmds are queued on. Because there can be * more than one CCP command queue that can process a cmd a separate - * backlog list is neeeded so that the backlog completion call + * backlog list is needed so that the backlog completion call * completes before the cmd is available for execution. */ spinlock_t cmd_lock ____cacheline_aligned; diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index d718db224be4..9f753cb4f5f1 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -632,6 +632,24 @@ static int ccp_terminate_all(struct dma_chan *dma_chan) return 0; } +static void ccp_dma_release(struct ccp_device *ccp) +{ + struct ccp_dma_chan *chan; + struct dma_chan *dma_chan; + unsigned int i; + + for (i = 0; i < ccp->cmd_q_count; i++) { + chan = ccp->ccp_dma_chan + i; + dma_chan = &chan->dma_chan; + + if (dma_chan->client_count) + dma_release_channel(dma_chan); + + tasklet_kill(&chan->cleanup_tasklet); + list_del_rcu(&dma_chan->device_node); + } +} + int ccp_dmaengine_register(struct ccp_device *ccp) { struct ccp_dma_chan *chan; @@ -736,6 +754,7 @@ int ccp_dmaengine_register(struct ccp_device *ccp) return 0; err_reg: + ccp_dma_release(ccp); kmem_cache_destroy(ccp->dma_desc_cache); err_cache: @@ -751,6 +770,7 @@ void ccp_dmaengine_unregister(struct ccp_device *ccp) if (!dmaengine) return; + ccp_dma_release(ccp); dma_async_device_unregister(dma_dev); kmem_cache_destroy(ccp->dma_desc_cache); diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index ae7b44599914..c9c741ac8442 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -70,17 +70,23 @@ static unsigned int psp_get_capability(struct psp_device *psp) */ if (val == 0xffffffff) { dev_notice(psp->dev, "psp: unable to access the device: you might be running a broken BIOS.\n"); - return 0; + return -ENODEV; } + psp->capability = val; + + /* Detect if TSME and SME are both enabled */ + if (psp->capability & PSP_CAPABILITY_PSP_SECURITY_REPORTING && + psp->capability & (PSP_SECURITY_TSME_STATUS << PSP_CAPABILITY_PSP_SECURITY_OFFSET) && + cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) + dev_notice(psp->dev, "psp: Both TSME and SME are active, SME is unnecessary when TSME is active.\n"); - return val; + return 0; } -static int psp_check_sev_support(struct psp_device *psp, - unsigned int capability) +static int psp_check_sev_support(struct psp_device *psp) { /* Check if device supports SEV feature */ - if (!(capability & 1)) { + if (!(psp->capability & PSP_CAPABILITY_SEV)) { dev_dbg(psp->dev, "psp does not support SEV\n"); return -ENODEV; } @@ -88,11 +94,10 @@ static int psp_check_sev_support(struct psp_device *psp, return 0; } -static int psp_check_tee_support(struct psp_device *psp, - unsigned int capability) +static int psp_check_tee_support(struct psp_device *psp) { /* Check if device supports TEE feature */ - if (!(capability & 2)) { + if (!(psp->capability & PSP_CAPABILITY_TEE)) { dev_dbg(psp->dev, "psp does not support TEE\n"); return -ENODEV; } @@ -100,30 +105,17 @@ static int psp_check_tee_support(struct psp_device *psp, return 0; } -static int psp_check_support(struct psp_device *psp, - unsigned int capability) -{ - int sev_support = psp_check_sev_support(psp, capability); - int tee_support = psp_check_tee_support(psp, capability); - - /* Return error if device neither supports SEV nor TEE */ - if (sev_support && tee_support) - return -ENODEV; - - return 0; -} - -static int psp_init(struct psp_device *psp, unsigned int capability) +static int psp_init(struct psp_device *psp) { int ret; - if (!psp_check_sev_support(psp, capability)) { + if (!psp_check_sev_support(psp)) { ret = sev_dev_init(psp); if (ret) return ret; } - if (!psp_check_tee_support(psp, capability)) { + if (!psp_check_tee_support(psp)) { ret = tee_dev_init(psp); if (ret) return ret; @@ -136,7 +128,6 @@ int psp_dev_init(struct sp_device *sp) { struct device *dev = sp->dev; struct psp_device *psp; - unsigned int capability; int ret; ret = -ENOMEM; @@ -155,11 +146,7 @@ int psp_dev_init(struct sp_device *sp) psp->io_regs = sp->io_map; - capability = psp_get_capability(psp); - if (!capability) - goto e_disable; - - ret = psp_check_support(psp, capability); + ret = psp_get_capability(psp); if (ret) goto e_disable; @@ -174,7 +161,7 @@ int psp_dev_init(struct sp_device *sp) goto e_err; } - ret = psp_init(psp, capability); + ret = psp_init(psp); if (ret) goto e_irq; diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h index ef38e4135d81..d528eb04c3ef 100644 --- a/drivers/crypto/ccp/psp-dev.h +++ b/drivers/crypto/ccp/psp-dev.h @@ -45,6 +45,8 @@ struct psp_device { void *sev_data; void *tee_data; + + unsigned int capability; }; void psp_set_sev_irq_handler(struct psp_device *psp, psp_irq_handler_t handler, @@ -57,4 +59,24 @@ void psp_clear_tee_irq_handler(struct psp_device *psp); struct psp_device *psp_get_master_device(void); +#define PSP_CAPABILITY_SEV BIT(0) +#define PSP_CAPABILITY_TEE BIT(1) +#define PSP_CAPABILITY_PSP_SECURITY_REPORTING BIT(7) + +#define PSP_CAPABILITY_PSP_SECURITY_OFFSET 8 +/* + * The PSP doesn't directly store these bits in the capability register + * but instead copies them from the results of query command. + * + * The offsets from the query command are below, and shifted when used. + */ +#define PSP_SECURITY_FUSED_PART BIT(0) +#define PSP_SECURITY_DEBUG_LOCK_ON BIT(2) +#define PSP_SECURITY_TSME_STATUS BIT(5) +#define PSP_SECURITY_ANTI_ROLLBACK_STATUS BIT(7) +#define PSP_SECURITY_RPMC_PRODUCTION_ENABLED BIT(8) +#define PSP_SECURITY_RPMC_SPIROM_AVAILABLE BIT(9) +#define PSP_SECURITY_HSP_TPM_AVAILABLE BIT(10) +#define PSP_SECURITY_ROM_ARMOR_ENFORCED BIT(11) + #endif /* __PSP_DEV_H */ diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 8fd774a10edc..06fc7156c04f 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -23,6 +23,7 @@ #include <linux/gfp.h> #include <linux/cpufeature.h> #include <linux/fs.h> +#include <linux/fs_struct.h> #include <asm/smp.h> @@ -170,6 +171,31 @@ static void *sev_fw_alloc(unsigned long len) return page_address(page); } +static struct file *open_file_as_root(const char *filename, int flags, umode_t mode) +{ + struct file *fp; + struct path root; + struct cred *cred; + const struct cred *old_cred; + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + + cred = prepare_creds(); + if (!cred) + return ERR_PTR(-ENOMEM); + cred->fsuid = GLOBAL_ROOT_UID; + old_cred = override_creds(cred); + + fp = file_open_root(&root, filename, flags, mode); + path_put(&root); + + revert_creds(old_cred); + + return fp; +} + static int sev_read_init_ex_file(void) { struct sev_device *sev = psp_master->sev_data; @@ -181,22 +207,28 @@ static int sev_read_init_ex_file(void) if (!sev_init_ex_buffer) return -EOPNOTSUPP; - fp = filp_open(init_ex_path, O_RDONLY, 0); + fp = open_file_as_root(init_ex_path, O_RDONLY, 0); if (IS_ERR(fp)) { int ret = PTR_ERR(fp); - dev_err(sev->dev, - "SEV: could not open %s for read, error %d\n", - init_ex_path, ret); + if (ret == -ENOENT) { + dev_info(sev->dev, + "SEV: %s does not exist and will be created later.\n", + init_ex_path); + ret = 0; + } else { + dev_err(sev->dev, + "SEV: could not open %s for read, error %d\n", + init_ex_path, ret); + } return ret; } nread = kernel_read(fp, sev_init_ex_buffer, NV_LENGTH, NULL); if (nread != NV_LENGTH) { - dev_err(sev->dev, - "SEV: failed to read %u bytes to non volatile memory area, ret %ld\n", + dev_info(sev->dev, + "SEV: could not read %u bytes to non volatile memory area, ret %ld\n", NV_LENGTH, nread); - return -EIO; } dev_dbg(sev->dev, "SEV: read %ld bytes from NV file\n", nread); @@ -205,7 +237,7 @@ static int sev_read_init_ex_file(void) return 0; } -static void sev_write_init_ex_file(void) +static int sev_write_init_ex_file(void) { struct sev_device *sev = psp_master->sev_data; struct file *fp; @@ -215,14 +247,16 @@ static void sev_write_init_ex_file(void) lockdep_assert_held(&sev_cmd_mutex); if (!sev_init_ex_buffer) - return; + return 0; - fp = filp_open(init_ex_path, O_CREAT | O_WRONLY, 0600); + fp = open_file_as_root(init_ex_path, O_CREAT | O_WRONLY, 0600); if (IS_ERR(fp)) { + int ret = PTR_ERR(fp); + dev_err(sev->dev, - "SEV: could not open file for write, error %ld\n", - PTR_ERR(fp)); - return; + "SEV: could not open file for write, error %d\n", + ret); + return ret; } nwrite = kernel_write(fp, sev_init_ex_buffer, NV_LENGTH, &offset); @@ -233,18 +267,20 @@ static void sev_write_init_ex_file(void) dev_err(sev->dev, "SEV: failed to write %u bytes to non volatile memory area, ret %ld\n", NV_LENGTH, nwrite); - return; + return -EIO; } dev_dbg(sev->dev, "SEV: write successful to NV file\n"); + + return 0; } -static void sev_write_init_ex_file_if_required(int cmd_id) +static int sev_write_init_ex_file_if_required(int cmd_id) { lockdep_assert_held(&sev_cmd_mutex); if (!sev_init_ex_buffer) - return; + return 0; /* * Only a few platform commands modify the SPI/NV area, but none of the @@ -259,10 +295,10 @@ static void sev_write_init_ex_file_if_required(int cmd_id) case SEV_CMD_PEK_GEN: break; default: - return; + return 0; } - sev_write_init_ex_file(); + return sev_write_init_ex_file(); } static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) @@ -335,7 +371,7 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) cmd, reg & PSP_CMDRESP_ERR_MASK); ret = -EIO; } else { - sev_write_init_ex_file_if_required(cmd); + ret = sev_write_init_ex_file_if_required(cmd); } print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, @@ -384,17 +420,12 @@ static int __sev_init_locked(int *error) static int __sev_init_ex_locked(int *error) { struct sev_data_init_ex data; - int ret; memset(&data, 0, sizeof(data)); data.length = sizeof(data); data.nv_address = __psp_pa(sev_init_ex_buffer); data.nv_len = NV_LENGTH; - ret = sev_read_init_ex_file(); - if (ret) - return ret; - if (sev_es_tmr) { /* * Do not include the encryption mask on the physical @@ -413,7 +444,7 @@ static int __sev_platform_init_locked(int *error) { struct psp_device *psp = psp_master; struct sev_device *sev; - int rc, psp_ret; + int rc = 0, psp_ret = -1; int (*init_function)(int *error); if (!psp || !psp->sev_data) @@ -424,8 +455,15 @@ static int __sev_platform_init_locked(int *error) if (sev->state == SEV_STATE_INIT) return 0; - init_function = sev_init_ex_buffer ? __sev_init_ex_locked : - __sev_init_locked; + if (sev_init_ex_buffer) { + init_function = __sev_init_ex_locked; + rc = sev_read_init_ex_file(); + if (rc) + return rc; + } else { + init_function = __sev_init_locked; + } + rc = init_function(&psp_ret); if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) { /* @@ -435,7 +473,7 @@ static int __sev_platform_init_locked(int *error) * initialization function should succeed by replacing the state * with a reset state. */ - dev_dbg(sev->dev, "SEV: retrying INIT command"); + dev_err(sev->dev, "SEV: retrying INIT command because of SECURE_DATA_INVALID error. Retrying once to reset PSP SEV state."); rc = init_function(&psp_ret); } if (error) @@ -477,7 +515,7 @@ static int __sev_platform_shutdown_locked(int *error) struct sev_device *sev = psp_master->sev_data; int ret; - if (sev->state == SEV_STATE_UNINIT) + if (!sev || sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); @@ -551,6 +589,8 @@ static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) struct sev_user_data_status data; int ret; + memset(&data, 0, sizeof(data)); + ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, &argp->error); if (ret) return ret; @@ -604,7 +644,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) if (input.length > SEV_FW_BLOB_MAX_SIZE) return -EFAULT; - blob = kmalloc(input.length, GFP_KERNEL); + blob = kzalloc(input.length, GFP_KERNEL); if (!blob) return -ENOMEM; @@ -716,6 +756,11 @@ static int sev_update_firmware(struct device *dev) struct page *p; u64 data_size; + if (!sev_version_greater_or_equal(0, 15)) { + dev_dbg(dev, "DOWNLOAD_FIRMWARE not supported\n"); + return -1; + } + if (sev_get_firmware(dev, &firmware) == -ENOENT) { dev_dbg(dev, "No SEV firmware file present\n"); return -1; @@ -748,6 +793,14 @@ static int sev_update_firmware(struct device *dev) data->len = firmware->size; ret = sev_do_cmd(SEV_CMD_DOWNLOAD_FIRMWARE, data, &error); + + /* + * A quirk for fixing the committed TCB version, when upgrading from + * earlier firmware version than 1.50. + */ + if (!ret && !sev_version_greater_or_equal(1, 50)) + ret = sev_do_cmd(SEV_CMD_DOWNLOAD_FIRMWARE, data, &error); + if (ret) dev_dbg(dev, "Failed to update SEV firmware: %#x\n", error); else @@ -828,7 +881,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) input_address = (void __user *)input.address; if (input.address && input.length) { - id_blob = kmalloc(input.length, GFP_KERNEL); + id_blob = kzalloc(input.length, GFP_KERNEL); if (!id_blob) return -ENOMEM; @@ -947,14 +1000,14 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) if (input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE) return -EFAULT; - pdh_blob = kmalloc(input.pdh_cert_len, GFP_KERNEL); + pdh_blob = kzalloc(input.pdh_cert_len, GFP_KERNEL); if (!pdh_blob) return -ENOMEM; data.pdh_cert_address = __psp_pa(pdh_blob); data.pdh_cert_len = input.pdh_cert_len; - cert_blob = kmalloc(input.cert_chain_len, GFP_KERNEL); + cert_blob = kzalloc(input.cert_chain_len, GFP_KERNEL); if (!cert_blob) { ret = -ENOMEM; goto e_free_pdh; @@ -1257,8 +1310,7 @@ void sev_pci_init(void) if (sev_get_api_version()) goto err; - if (sev_version_greater_or_equal(0, 15) && - sev_update_firmware(sev->dev) == 0) + if (sev_update_firmware(sev->dev) == 0) sev_get_api_version(); /* If an init_ex_path is provided rely on INIT_EX for PSP initialization diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c index 88c672ad27e4..792d6da7f0c0 100644 --- a/drivers/crypto/ccp/sp-pci.c +++ b/drivers/crypto/ccp/sp-pci.c @@ -32,6 +32,67 @@ struct sp_pci { }; static struct sp_device *sp_dev_master; +#define attribute_show(name, def) \ +static ssize_t name##_show(struct device *d, struct device_attribute *attr, \ + char *buf) \ +{ \ + struct sp_device *sp = dev_get_drvdata(d); \ + struct psp_device *psp = sp->psp_data; \ + int bit = PSP_SECURITY_##def << PSP_CAPABILITY_PSP_SECURITY_OFFSET; \ + return sysfs_emit(buf, "%d\n", (psp->capability & bit) > 0); \ +} + +attribute_show(fused_part, FUSED_PART) +static DEVICE_ATTR_RO(fused_part); +attribute_show(debug_lock_on, DEBUG_LOCK_ON) +static DEVICE_ATTR_RO(debug_lock_on); +attribute_show(tsme_status, TSME_STATUS) +static DEVICE_ATTR_RO(tsme_status); +attribute_show(anti_rollback_status, ANTI_ROLLBACK_STATUS) +static DEVICE_ATTR_RO(anti_rollback_status); +attribute_show(rpmc_production_enabled, RPMC_PRODUCTION_ENABLED) +static DEVICE_ATTR_RO(rpmc_production_enabled); +attribute_show(rpmc_spirom_available, RPMC_SPIROM_AVAILABLE) +static DEVICE_ATTR_RO(rpmc_spirom_available); +attribute_show(hsp_tpm_available, HSP_TPM_AVAILABLE) +static DEVICE_ATTR_RO(hsp_tpm_available); +attribute_show(rom_armor_enforced, ROM_ARMOR_ENFORCED) +static DEVICE_ATTR_RO(rom_armor_enforced); + +static struct attribute *psp_attrs[] = { + &dev_attr_fused_part.attr, + &dev_attr_debug_lock_on.attr, + &dev_attr_tsme_status.attr, + &dev_attr_anti_rollback_status.attr, + &dev_attr_rpmc_production_enabled.attr, + &dev_attr_rpmc_spirom_available.attr, + &dev_attr_hsp_tpm_available.attr, + &dev_attr_rom_armor_enforced.attr, + NULL +}; + +static umode_t psp_security_is_visible(struct kobject *kobj, struct attribute *attr, int idx) +{ + struct device *dev = kobj_to_dev(kobj); + struct sp_device *sp = dev_get_drvdata(dev); + struct psp_device *psp = sp->psp_data; + + if (psp && (psp->capability & PSP_CAPABILITY_PSP_SECURITY_REPORTING)) + return 0444; + + return 0; +} + +static struct attribute_group psp_attr_group = { + .attrs = psp_attrs, + .is_visible = psp_security_is_visible, +}; + +static const struct attribute_group *psp_groups[] = { + &psp_attr_group, + NULL, +}; + static int sp_get_msix_irqs(struct sp_device *sp) { struct sp_pci *sp_pci = sp->dev_specific; @@ -368,6 +429,12 @@ static const struct sp_dev_vdata dev_vdata[] = { .psp_vdata = &pspv2, #endif }, + { /* 6 */ + .bar = 2, +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + .psp_vdata = &pspv3, +#endif + }, }; static const struct pci_device_id sp_pci_table[] = { { PCI_VDEVICE(AMD, 0x1537), (kernel_ulong_t)&dev_vdata[0] }, @@ -377,6 +444,7 @@ static const struct pci_device_id sp_pci_table[] = { { PCI_VDEVICE(AMD, 0x15DF), (kernel_ulong_t)&dev_vdata[4] }, { PCI_VDEVICE(AMD, 0x1649), (kernel_ulong_t)&dev_vdata[4] }, { PCI_VDEVICE(AMD, 0x14CA), (kernel_ulong_t)&dev_vdata[5] }, + { PCI_VDEVICE(AMD, 0x15C7), (kernel_ulong_t)&dev_vdata[6] }, /* Last entry must be zero */ { 0, } }; @@ -391,6 +459,7 @@ static struct pci_driver sp_pci_driver = { .remove = sp_pci_remove, .shutdown = sp_pci_shutdown, .driver.pm = &sp_pci_pm_ops, + .dev_groups = psp_groups, }; int sp_pci_init(void) diff --git a/drivers/crypto/ccp/sp-platform.c b/drivers/crypto/ccp/sp-platform.c index 9dba52fbee99..7d79a8744f9a 100644 --- a/drivers/crypto/ccp/sp-platform.c +++ b/drivers/crypto/ccp/sp-platform.c @@ -85,17 +85,9 @@ static int sp_get_irqs(struct sp_device *sp) struct sp_platform *sp_platform = sp->dev_specific; struct device *dev = sp->dev; struct platform_device *pdev = to_platform_device(dev); - unsigned int i, count; int ret; - for (i = 0, count = 0; i < pdev->num_resources; i++) { - struct resource *res = &pdev->resource[i]; - - if (resource_type(res) == IORESOURCE_IRQ) - count++; - } - - sp_platform->irq_count = count; + sp_platform->irq_count = platform_irq_count(pdev); ret = platform_get_irq(pdev, 0); if (ret < 0) { @@ -104,7 +96,7 @@ static int sp_get_irqs(struct sp_device *sp) } sp->psp_irq = ret; - if (count == 1) { + if (sp_platform->irq_count == 1) { sp->ccp_irq = ret; } else { ret = platform_get_irq(pdev, 1); diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c index a5e041d9d2cf..9efd88f871d1 100644 --- a/drivers/crypto/ccree/cc_buffer_mgr.c +++ b/drivers/crypto/ccree/cc_buffer_mgr.c @@ -258,6 +258,13 @@ static int cc_map_sg(struct device *dev, struct scatterlist *sg, { int ret = 0; + if (!nbytes) { + *mapped_nents = 0; + *lbytes = 0; + *nents = 0; + return 0; + } + *nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes); if (*nents > max_sg_nents) { *nents = 0; @@ -267,7 +274,7 @@ static int cc_map_sg(struct device *dev, struct scatterlist *sg, } ret = dma_map_sg(dev, sg, *nents, direction); - if (dma_mapping_error(dev, ret)) { + if (!ret) { *nents = 0; dev_err(dev, "dma_map_sg() sg buffer failed %d\n", ret); return -ENOMEM; @@ -349,12 +356,14 @@ void cc_unmap_cipher_request(struct device *dev, void *ctx, req_ctx->mlli_params.mlli_dma_addr); } - dma_unmap_sg(dev, src, req_ctx->in_nents, DMA_BIDIRECTIONAL); - dev_dbg(dev, "Unmapped req->src=%pK\n", sg_virt(src)); - if (src != dst) { - dma_unmap_sg(dev, dst, req_ctx->out_nents, DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, src, req_ctx->in_nents, DMA_TO_DEVICE); + dma_unmap_sg(dev, dst, req_ctx->out_nents, DMA_FROM_DEVICE); dev_dbg(dev, "Unmapped req->dst=%pK\n", sg_virt(dst)); + dev_dbg(dev, "Unmapped req->src=%pK\n", sg_virt(src)); + } else { + dma_unmap_sg(dev, src, req_ctx->in_nents, DMA_BIDIRECTIONAL); + dev_dbg(dev, "Unmapped req->src=%pK\n", sg_virt(src)); } } @@ -370,6 +379,7 @@ int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx, u32 dummy = 0; int rc = 0; u32 mapped_nents = 0; + int src_direction = (src != dst ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL); req_ctx->dma_buf_type = CC_DMA_BUF_DLLI; mlli_params->curr_pool = NULL; @@ -392,7 +402,7 @@ int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx, } /* Map the src SGL */ - rc = cc_map_sg(dev, src, nbytes, DMA_BIDIRECTIONAL, &req_ctx->in_nents, + rc = cc_map_sg(dev, src, nbytes, src_direction, &req_ctx->in_nents, LLI_MAX_NUM_OF_DATA_ENTRIES, &dummy, &mapped_nents); if (rc) goto cipher_exit; @@ -409,7 +419,7 @@ int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx, } } else { /* Map the dst sg */ - rc = cc_map_sg(dev, dst, nbytes, DMA_BIDIRECTIONAL, + rc = cc_map_sg(dev, dst, nbytes, DMA_FROM_DEVICE, &req_ctx->out_nents, LLI_MAX_NUM_OF_DATA_ENTRIES, &dummy, &mapped_nents); if (rc) @@ -449,6 +459,7 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req) struct aead_req_ctx *areq_ctx = aead_request_ctx(req); unsigned int hw_iv_size = areq_ctx->hw_iv_size; struct cc_drvdata *drvdata = dev_get_drvdata(dev); + int src_direction = (req->src != req->dst ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL); if (areq_ctx->mac_buf_dma_addr) { dma_unmap_single(dev, areq_ctx->mac_buf_dma_addr, @@ -507,13 +518,11 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req) sg_virt(req->src), areq_ctx->src.nents, areq_ctx->assoc.nents, areq_ctx->assoclen, req->cryptlen); - dma_unmap_sg(dev, req->src, areq_ctx->src.mapped_nents, - DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, req->src, areq_ctx->src.mapped_nents, src_direction); if (req->src != req->dst) { dev_dbg(dev, "Unmapping dst sgl: req->dst=%pK\n", sg_virt(req->dst)); - dma_unmap_sg(dev, req->dst, areq_ctx->dst.mapped_nents, - DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, req->dst, areq_ctx->dst.mapped_nents, DMA_FROM_DEVICE); } if (drvdata->coherent && areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT && @@ -836,7 +845,7 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata, else size_for_map -= authsize; - rc = cc_map_sg(dev, req->dst, size_for_map, DMA_BIDIRECTIONAL, + rc = cc_map_sg(dev, req->dst, size_for_map, DMA_FROM_DEVICE, &areq_ctx->dst.mapped_nents, LLI_MAX_NUM_OF_DATA_ENTRIES, &dst_last_bytes, &dst_mapped_nents); @@ -1049,7 +1058,8 @@ int cc_map_aead_request(struct cc_drvdata *drvdata, struct aead_request *req) size_to_map += authsize; } - rc = cc_map_sg(dev, req->src, size_to_map, DMA_BIDIRECTIONAL, + rc = cc_map_sg(dev, req->src, size_to_map, + (req->src != req->dst ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL), &areq_ctx->src.mapped_nents, (LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES + LLI_MAX_NUM_OF_DATA_ENTRIES), diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c index 78833491f534..309da6334a0a 100644 --- a/drivers/crypto/ccree/cc_cipher.c +++ b/drivers/crypto/ccree/cc_cipher.c @@ -257,8 +257,8 @@ static void cc_cipher_exit(struct crypto_tfm *tfm) &ctx_p->user.key_dma_addr); /* Free key buffer in context */ - kfree_sensitive(ctx_p->user.key); dev_dbg(dev, "Free key buffer in context. key=@%p\n", ctx_p->user.key); + kfree_sensitive(ctx_p->user.key); } struct tdes_keys { diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c index 790fa9058a36..cadead18b59e 100644 --- a/drivers/crypto/ccree/cc_driver.c +++ b/drivers/crypto/ccree/cc_driver.c @@ -372,17 +372,10 @@ static int init_cc_resources(struct platform_device *plat_dev) dev->dma_mask = &dev->coherent_dma_mask; dma_mask = DMA_BIT_MASK(DMA_BIT_MASK_LEN); - while (dma_mask > 0x7fffffffUL) { - if (dma_supported(dev, dma_mask)) { - rc = dma_set_coherent_mask(dev, dma_mask); - if (!rc) - break; - } - dma_mask >>= 1; - } - + rc = dma_set_coherent_mask(dev, dma_mask); if (rc) { - dev_err(dev, "Failed in dma_set_mask, mask=%llx\n", dma_mask); + dev_err(dev, "Failed in dma_set_coherent_mask, mask=%llx\n", + dma_mask); return rc; } @@ -529,24 +522,26 @@ static int init_cc_resources(struct platform_device *plat_dev) goto post_req_mgr_err; } - /* Allocate crypto algs */ - rc = cc_cipher_alloc(new_drvdata); + /* hash must be allocated first due to use of send_request_init() + * and dependency of AEAD on it + */ + rc = cc_hash_alloc(new_drvdata); if (rc) { - dev_err(dev, "cc_cipher_alloc failed\n"); + dev_err(dev, "cc_hash_alloc failed\n"); goto post_buf_mgr_err; } - /* hash must be allocated before aead since hash exports APIs */ - rc = cc_hash_alloc(new_drvdata); + /* Allocate crypto algs */ + rc = cc_cipher_alloc(new_drvdata); if (rc) { - dev_err(dev, "cc_hash_alloc failed\n"); - goto post_cipher_err; + dev_err(dev, "cc_cipher_alloc failed\n"); + goto post_hash_err; } rc = cc_aead_alloc(new_drvdata); if (rc) { dev_err(dev, "cc_aead_alloc failed\n"); - goto post_hash_err; + goto post_cipher_err; } /* If we got here and FIPS mode is enabled @@ -558,10 +553,10 @@ static int init_cc_resources(struct platform_device *plat_dev) pm_runtime_put(dev); return 0; -post_hash_err: - cc_hash_free(new_drvdata); post_cipher_err: cc_cipher_free(new_drvdata); +post_hash_err: + cc_hash_free(new_drvdata); post_buf_mgr_err: cc_buffer_mgr_fini(new_drvdata); post_req_mgr_err: @@ -593,8 +588,8 @@ static void cleanup_cc_resources(struct platform_device *plat_dev) (struct cc_drvdata *)platform_get_drvdata(plat_dev); cc_aead_free(drvdata); - cc_hash_free(drvdata); cc_cipher_free(drvdata); + cc_hash_free(drvdata); cc_buffer_mgr_fini(drvdata); cc_req_mgr_fini(drvdata); cc_fips_fini(drvdata); diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c index d5421b0c6831..6124fbbbed94 100644 --- a/drivers/crypto/ccree/cc_pm.c +++ b/drivers/crypto/ccree/cc_pm.c @@ -41,6 +41,7 @@ static int cc_pm_resume(struct device *dev) /* wait for Cryptocell reset completion */ if (!cc_wait_for_reset_completion(drvdata)) { dev_err(dev, "Cryptocell reset not completed"); + clk_disable_unprepare(drvdata->clk); return -EBUSY; } @@ -48,6 +49,7 @@ static int cc_pm_resume(struct device *dev) rc = init_cc_regs(drvdata); if (rc) { dev_err(dev, "init_cc_regs (%x)\n", rc); + clk_disable_unprepare(drvdata->clk); return rc; } /* check if tee fips error occurred during power down */ diff --git a/drivers/crypto/gemini/sl3516-ce-cipher.c b/drivers/crypto/gemini/sl3516-ce-cipher.c index c1c2b1d86663..14d0d83d388d 100644 --- a/drivers/crypto/gemini/sl3516-ce-cipher.c +++ b/drivers/crypto/gemini/sl3516-ce-cipher.c @@ -23,8 +23,8 @@ static bool sl3516_ce_need_fallback(struct skcipher_request *areq) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); struct sl3516_ce_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); struct sl3516_ce_dev *ce = op->ce; - struct scatterlist *in_sg = areq->src; - struct scatterlist *out_sg = areq->dst; + struct scatterlist *in_sg; + struct scatterlist *out_sg; struct scatterlist *sg; if (areq->cryptlen == 0 || areq->cryptlen % 16) { @@ -264,7 +264,9 @@ static int sl3516_ce_handle_cipher_request(struct crypto_engine *engine, void *a struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); err = sl3516_ce_cipher(breq); + local_bh_disable(); crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); return 0; } diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index e572f9982d4e..27e1fa912063 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -26,6 +26,7 @@ config CRYPTO_DEV_HISI_SEC2 select CRYPTO_SHA1 select CRYPTO_SHA256 select CRYPTO_SHA512 + select CRYPTO_SM4 depends on PCI && PCI_MSI depends on UACCE || UACCE=n depends on ARM64 || (COMPILE_TEST && 64BIT) diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h index e0b4a1982ee9..9f0b94c8e03d 100644 --- a/drivers/crypto/hisilicon/hpre/hpre.h +++ b/drivers/crypto/hisilicon/hpre/hpre.h @@ -4,7 +4,7 @@ #define __HISI_HPRE_H #include <linux/list.h> -#include "../qm.h" +#include <linux/hisi_acc_qm.h> #define HPRE_SQE_SIZE sizeof(struct hpre_sqe) #define HPRE_PF_DEF_Q_NUM 64 @@ -22,7 +22,8 @@ enum { HPRE_CLUSTER0, HPRE_CLUSTER1, HPRE_CLUSTER2, - HPRE_CLUSTER3 + HPRE_CLUSTER3, + HPRE_CLUSTERS_NUM_MAX }; enum hpre_ctrl_dbgfs_file { @@ -42,9 +43,6 @@ enum hpre_dfx_dbgfs_file { HPRE_DFX_FILE_NUM }; -#define HPRE_CLUSTERS_NUM_V2 (HPRE_CLUSTER3 + 1) -#define HPRE_CLUSTERS_NUM_V3 1 -#define HPRE_CLUSTERS_NUM_MAX HPRE_CLUSTERS_NUM_V2 #define HPRE_DEBUGFS_FILE_NUM (HPRE_DEBUG_FILE_NUM + HPRE_CLUSTERS_NUM_MAX - 1) struct hpre_debugfs_file { @@ -105,5 +103,5 @@ struct hpre_sqe { struct hisi_qp *hpre_create_qp(u8 type); int hpre_algs_register(struct hisi_qm *qm); void hpre_algs_unregister(struct hisi_qm *qm); - +bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg); #endif diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c index 97d54c1465c2..ef02dadd6217 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_crypto.c +++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c @@ -51,6 +51,12 @@ struct hpre_ctx; #define HPRE_ECC_HW256_KSZ_B 32 #define HPRE_ECC_HW384_KSZ_B 48 +/* capability register mask of driver */ +#define HPRE_DRV_RSA_MASK_CAP BIT(0) +#define HPRE_DRV_DH_MASK_CAP BIT(1) +#define HPRE_DRV_ECDH_MASK_CAP BIT(2) +#define HPRE_DRV_X25519_MASK_CAP BIT(5) + typedef void (*hpre_cb)(struct hpre_ctx *ctx, void *sqe); struct hpre_rsa_ctx { @@ -147,7 +153,7 @@ static int hpre_alloc_req_id(struct hpre_ctx *ctx) int id; spin_lock_irqsave(&ctx->req_lock, flags); - id = idr_alloc(&ctx->req_idr, NULL, 0, QM_Q_DEPTH, GFP_ATOMIC); + id = idr_alloc(&ctx->req_idr, NULL, 0, ctx->qp->sq_depth, GFP_ATOMIC); spin_unlock_irqrestore(&ctx->req_lock, flags); return id; @@ -252,7 +258,7 @@ static int hpre_prepare_dma_buf(struct hpre_asym_request *hpre_req, if (unlikely(shift < 0)) return -EINVAL; - ptr = dma_alloc_coherent(dev, ctx->key_sz, tmp, GFP_KERNEL); + ptr = dma_alloc_coherent(dev, ctx->key_sz, tmp, GFP_ATOMIC); if (unlikely(!ptr)) return -ENOMEM; @@ -488,7 +494,7 @@ static int hpre_ctx_init(struct hpre_ctx *ctx, u8 type) qp->qp_ctx = ctx; qp->req_cb = hpre_alg_cb; - ret = hpre_ctx_set(ctx, qp, QM_Q_DEPTH); + ret = hpre_ctx_set(ctx, qp, qp->sq_depth); if (ret) hpre_stop_qp_and_put(qp); @@ -2002,55 +2008,53 @@ static struct kpp_alg dh = { }, }; -static struct kpp_alg ecdh_nist_p192 = { - .set_secret = hpre_ecdh_set_secret, - .generate_public_key = hpre_ecdh_compute_value, - .compute_shared_secret = hpre_ecdh_compute_value, - .max_size = hpre_ecdh_max_size, - .init = hpre_ecdh_nist_p192_init_tfm, - .exit = hpre_ecdh_exit_tfm, - .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, - .base = { - .cra_ctxsize = sizeof(struct hpre_ctx), - .cra_priority = HPRE_CRYPTO_ALG_PRI, - .cra_name = "ecdh-nist-p192", - .cra_driver_name = "hpre-ecdh-nist-p192", - .cra_module = THIS_MODULE, - }, -}; - -static struct kpp_alg ecdh_nist_p256 = { - .set_secret = hpre_ecdh_set_secret, - .generate_public_key = hpre_ecdh_compute_value, - .compute_shared_secret = hpre_ecdh_compute_value, - .max_size = hpre_ecdh_max_size, - .init = hpre_ecdh_nist_p256_init_tfm, - .exit = hpre_ecdh_exit_tfm, - .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, - .base = { - .cra_ctxsize = sizeof(struct hpre_ctx), - .cra_priority = HPRE_CRYPTO_ALG_PRI, - .cra_name = "ecdh-nist-p256", - .cra_driver_name = "hpre-ecdh-nist-p256", - .cra_module = THIS_MODULE, - }, -}; - -static struct kpp_alg ecdh_nist_p384 = { - .set_secret = hpre_ecdh_set_secret, - .generate_public_key = hpre_ecdh_compute_value, - .compute_shared_secret = hpre_ecdh_compute_value, - .max_size = hpre_ecdh_max_size, - .init = hpre_ecdh_nist_p384_init_tfm, - .exit = hpre_ecdh_exit_tfm, - .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, - .base = { - .cra_ctxsize = sizeof(struct hpre_ctx), - .cra_priority = HPRE_CRYPTO_ALG_PRI, - .cra_name = "ecdh-nist-p384", - .cra_driver_name = "hpre-ecdh-nist-p384", - .cra_module = THIS_MODULE, - }, +static struct kpp_alg ecdh_curves[] = { + { + .set_secret = hpre_ecdh_set_secret, + .generate_public_key = hpre_ecdh_compute_value, + .compute_shared_secret = hpre_ecdh_compute_value, + .max_size = hpre_ecdh_max_size, + .init = hpre_ecdh_nist_p192_init_tfm, + .exit = hpre_ecdh_exit_tfm, + .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, + .base = { + .cra_ctxsize = sizeof(struct hpre_ctx), + .cra_priority = HPRE_CRYPTO_ALG_PRI, + .cra_name = "ecdh-nist-p192", + .cra_driver_name = "hpre-ecdh-nist-p192", + .cra_module = THIS_MODULE, + }, + }, { + .set_secret = hpre_ecdh_set_secret, + .generate_public_key = hpre_ecdh_compute_value, + .compute_shared_secret = hpre_ecdh_compute_value, + .max_size = hpre_ecdh_max_size, + .init = hpre_ecdh_nist_p256_init_tfm, + .exit = hpre_ecdh_exit_tfm, + .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, + .base = { + .cra_ctxsize = sizeof(struct hpre_ctx), + .cra_priority = HPRE_CRYPTO_ALG_PRI, + .cra_name = "ecdh-nist-p256", + .cra_driver_name = "hpre-ecdh-nist-p256", + .cra_module = THIS_MODULE, + }, + }, { + .set_secret = hpre_ecdh_set_secret, + .generate_public_key = hpre_ecdh_compute_value, + .compute_shared_secret = hpre_ecdh_compute_value, + .max_size = hpre_ecdh_max_size, + .init = hpre_ecdh_nist_p384_init_tfm, + .exit = hpre_ecdh_exit_tfm, + .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, + .base = { + .cra_ctxsize = sizeof(struct hpre_ctx), + .cra_priority = HPRE_CRYPTO_ALG_PRI, + .cra_name = "ecdh-nist-p384", + .cra_driver_name = "hpre-ecdh-nist-p384", + .cra_module = THIS_MODULE, + }, + } }; static struct kpp_alg curve25519_alg = { @@ -2070,78 +2074,144 @@ static struct kpp_alg curve25519_alg = { }, }; - -static int hpre_register_ecdh(void) +static int hpre_register_rsa(struct hisi_qm *qm) { int ret; - ret = crypto_register_kpp(&ecdh_nist_p192); - if (ret) - return ret; + if (!hpre_check_alg_support(qm, HPRE_DRV_RSA_MASK_CAP)) + return 0; - ret = crypto_register_kpp(&ecdh_nist_p256); + rsa.base.cra_flags = 0; + ret = crypto_register_akcipher(&rsa); if (ret) - goto unregister_ecdh_p192; + dev_err(&qm->pdev->dev, "failed to register rsa (%d)!\n", ret); - ret = crypto_register_kpp(&ecdh_nist_p384); + return ret; +} + +static void hpre_unregister_rsa(struct hisi_qm *qm) +{ + if (!hpre_check_alg_support(qm, HPRE_DRV_RSA_MASK_CAP)) + return; + + crypto_unregister_akcipher(&rsa); +} + +static int hpre_register_dh(struct hisi_qm *qm) +{ + int ret; + + if (!hpre_check_alg_support(qm, HPRE_DRV_DH_MASK_CAP)) + return 0; + + ret = crypto_register_kpp(&dh); if (ret) - goto unregister_ecdh_p256; + dev_err(&qm->pdev->dev, "failed to register dh (%d)!\n", ret); + + return ret; +} + +static void hpre_unregister_dh(struct hisi_qm *qm) +{ + if (!hpre_check_alg_support(qm, HPRE_DRV_DH_MASK_CAP)) + return; + + crypto_unregister_kpp(&dh); +} + +static int hpre_register_ecdh(struct hisi_qm *qm) +{ + int ret, i; + + if (!hpre_check_alg_support(qm, HPRE_DRV_ECDH_MASK_CAP)) + return 0; + + for (i = 0; i < ARRAY_SIZE(ecdh_curves); i++) { + ret = crypto_register_kpp(&ecdh_curves[i]); + if (ret) { + dev_err(&qm->pdev->dev, "failed to register %s (%d)!\n", + ecdh_curves[i].base.cra_name, ret); + goto unreg_kpp; + } + } return 0; -unregister_ecdh_p256: - crypto_unregister_kpp(&ecdh_nist_p256); -unregister_ecdh_p192: - crypto_unregister_kpp(&ecdh_nist_p192); +unreg_kpp: + for (--i; i >= 0; --i) + crypto_unregister_kpp(&ecdh_curves[i]); + return ret; } -static void hpre_unregister_ecdh(void) +static void hpre_unregister_ecdh(struct hisi_qm *qm) { - crypto_unregister_kpp(&ecdh_nist_p384); - crypto_unregister_kpp(&ecdh_nist_p256); - crypto_unregister_kpp(&ecdh_nist_p192); + int i; + + if (!hpre_check_alg_support(qm, HPRE_DRV_ECDH_MASK_CAP)) + return; + + for (i = ARRAY_SIZE(ecdh_curves) - 1; i >= 0; --i) + crypto_unregister_kpp(&ecdh_curves[i]); +} + +static int hpre_register_x25519(struct hisi_qm *qm) +{ + int ret; + + if (!hpre_check_alg_support(qm, HPRE_DRV_X25519_MASK_CAP)) + return 0; + + ret = crypto_register_kpp(&curve25519_alg); + if (ret) + dev_err(&qm->pdev->dev, "failed to register x25519 (%d)!\n", ret); + + return ret; +} + +static void hpre_unregister_x25519(struct hisi_qm *qm) +{ + if (!hpre_check_alg_support(qm, HPRE_DRV_X25519_MASK_CAP)) + return; + + crypto_unregister_kpp(&curve25519_alg); } int hpre_algs_register(struct hisi_qm *qm) { int ret; - rsa.base.cra_flags = 0; - ret = crypto_register_akcipher(&rsa); + ret = hpre_register_rsa(qm); if (ret) return ret; - ret = crypto_register_kpp(&dh); + ret = hpre_register_dh(qm); if (ret) goto unreg_rsa; - if (qm->ver >= QM_HW_V3) { - ret = hpre_register_ecdh(); - if (ret) - goto unreg_dh; - ret = crypto_register_kpp(&curve25519_alg); - if (ret) - goto unreg_ecdh; - } - return 0; + ret = hpre_register_ecdh(qm); + if (ret) + goto unreg_dh; + + ret = hpre_register_x25519(qm); + if (ret) + goto unreg_ecdh; + + return ret; unreg_ecdh: - hpre_unregister_ecdh(); + hpre_unregister_ecdh(qm); unreg_dh: - crypto_unregister_kpp(&dh); + hpre_unregister_dh(qm); unreg_rsa: - crypto_unregister_akcipher(&rsa); + hpre_unregister_rsa(qm); return ret; } void hpre_algs_unregister(struct hisi_qm *qm) { - if (qm->ver >= QM_HW_V3) { - crypto_unregister_kpp(&curve25519_alg); - hpre_unregister_ecdh(); - } - - crypto_unregister_kpp(&dh); - crypto_unregister_akcipher(&rsa); + hpre_unregister_x25519(qm); + hpre_unregister_ecdh(qm); + hpre_unregister_dh(qm); + hpre_unregister_rsa(qm); } diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index ebfab3e14499..471e5ca720f5 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -36,6 +36,12 @@ #define HPRE_DATA_WUSER_CFG 0x301040 #define HPRE_INT_MASK 0x301400 #define HPRE_INT_STATUS 0x301800 +#define HPRE_HAC_INT_MSK 0x301400 +#define HPRE_HAC_RAS_CE_ENB 0x301410 +#define HPRE_HAC_RAS_NFE_ENB 0x301414 +#define HPRE_HAC_RAS_FE_ENB 0x301418 +#define HPRE_HAC_INT_SET 0x301500 +#define HPRE_RNG_TIMEOUT_NUM 0x301A34 #define HPRE_CORE_INT_ENABLE 0 #define HPRE_CORE_INT_DISABLE GENMASK(21, 0) #define HPRE_RDCHN_INI_ST 0x301a00 @@ -47,9 +53,7 @@ #define HPRE_CORE_IS_SCHD_OFFSET 0x90 #define HPRE_RAS_CE_ENB 0x301410 -#define HPRE_HAC_RAS_CE_ENABLE (BIT(0) | BIT(22) | BIT(23)) #define HPRE_RAS_NFE_ENB 0x301414 -#define HPRE_HAC_RAS_NFE_ENABLE 0x3ffffe #define HPRE_RAS_FE_ENB 0x301418 #define HPRE_OOO_SHUTDOWN_SEL 0x301a3c #define HPRE_HAC_RAS_FE_ENABLE 0 @@ -68,14 +72,11 @@ #define HPRE_REG_RD_INTVRL_US 10 #define HPRE_REG_RD_TMOUT_US 1000 #define HPRE_DBGFS_VAL_MAX_LEN 20 -#define HPRE_PCI_DEVICE_ID 0xa258 -#define HPRE_PCI_VF_DEVICE_ID 0xa259 +#define PCI_DEVICE_ID_HUAWEI_HPRE_PF 0xa258 #define HPRE_QM_USR_CFG_MASK GENMASK(31, 1) #define HPRE_QM_AXI_CFG_MASK GENMASK(15, 0) #define HPRE_QM_VFG_AX_MASK GENMASK(7, 0) #define HPRE_BD_USR_MASK GENMASK(1, 0) -#define HPRE_CLUSTER_CORE_MASK_V2 GENMASK(3, 0) -#define HPRE_CLUSTER_CORE_MASK_V3 GENMASK(7, 0) #define HPRE_PREFETCH_CFG 0x301130 #define HPRE_SVA_PREFTCH_DFX 0x30115C #define HPRE_PREFETCH_ENABLE (~(BIT(0) | BIT(30))) @@ -108,11 +109,22 @@ #define HPRE_SQE_MASK_OFFSET 8 #define HPRE_SQE_MASK_LEN 24 +#define HPRE_DFX_BASE 0x301000 +#define HPRE_DFX_COMMON1 0x301400 +#define HPRE_DFX_COMMON2 0x301A00 +#define HPRE_DFX_CORE 0x302000 +#define HPRE_DFX_BASE_LEN 0x55 +#define HPRE_DFX_COMMON1_LEN 0x41 +#define HPRE_DFX_COMMON2_LEN 0xE +#define HPRE_DFX_CORE_LEN 0x43 + +#define HPRE_DEV_ALG_MAX_LEN 256 + static const char hpre_name[] = "hisi_hpre"; static struct dentry *hpre_debugfs_root; static const struct pci_device_id hpre_dev_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_DEVICE_ID) }, - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_VF_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_HPRE_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_HPRE_VF) }, { 0, } }; @@ -123,6 +135,38 @@ struct hpre_hw_error { const char *msg; }; +struct hpre_dev_alg { + u32 alg_msk; + const char *alg; +}; + +static const struct hpre_dev_alg hpre_dev_algs[] = { + { + .alg_msk = BIT(0), + .alg = "rsa\n" + }, { + .alg_msk = BIT(1), + .alg = "dh\n" + }, { + .alg_msk = BIT(2), + .alg = "ecdh\n" + }, { + .alg_msk = BIT(3), + .alg = "ecdsa\n" + }, { + .alg_msk = BIT(4), + .alg = "sm2\n" + }, { + .alg_msk = BIT(5), + .alg = "x25519\n" + }, { + .alg_msk = BIT(6), + .alg = "x448\n" + }, { + /* sentinel */ + } +}; + static struct hisi_qm_list hpre_devices = { .register_to_crypto = hpre_algs_register, .unregister_from_crypto = hpre_algs_unregister, @@ -133,6 +177,62 @@ static const char * const hpre_debug_file_name[] = { [HPRE_CLUSTER_CTRL] = "cluster_ctrl", }; +enum hpre_cap_type { + HPRE_QM_NFE_MASK_CAP, + HPRE_QM_RESET_MASK_CAP, + HPRE_QM_OOO_SHUTDOWN_MASK_CAP, + HPRE_QM_CE_MASK_CAP, + HPRE_NFE_MASK_CAP, + HPRE_RESET_MASK_CAP, + HPRE_OOO_SHUTDOWN_MASK_CAP, + HPRE_CE_MASK_CAP, + HPRE_CLUSTER_NUM_CAP, + HPRE_CORE_TYPE_NUM_CAP, + HPRE_CORE_NUM_CAP, + HPRE_CLUSTER_CORE_NUM_CAP, + HPRE_CORE_ENABLE_BITMAP_CAP, + HPRE_DRV_ALG_BITMAP_CAP, + HPRE_DEV_ALG_BITMAP_CAP, + HPRE_CORE1_ALG_BITMAP_CAP, + HPRE_CORE2_ALG_BITMAP_CAP, + HPRE_CORE3_ALG_BITMAP_CAP, + HPRE_CORE4_ALG_BITMAP_CAP, + HPRE_CORE5_ALG_BITMAP_CAP, + HPRE_CORE6_ALG_BITMAP_CAP, + HPRE_CORE7_ALG_BITMAP_CAP, + HPRE_CORE8_ALG_BITMAP_CAP, + HPRE_CORE9_ALG_BITMAP_CAP, + HPRE_CORE10_ALG_BITMAP_CAP +}; + +static const struct hisi_qm_cap_info hpre_basic_info[] = { + {HPRE_QM_NFE_MASK_CAP, 0x3124, 0, GENMASK(31, 0), 0x0, 0x1C37, 0x7C37}, + {HPRE_QM_RESET_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0xC37, 0x6C37}, + {HPRE_QM_OOO_SHUTDOWN_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0x4, 0x6C37}, + {HPRE_QM_CE_MASK_CAP, 0x312C, 0, GENMASK(31, 0), 0x0, 0x8, 0x8}, + {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xFFFFFE}, + {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFFFE}, + {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFFFE}, + {HPRE_CE_MASK_CAP, 0x3138, 0, GENMASK(31, 0), 0x0, 0x1, 0x1}, + {HPRE_CLUSTER_NUM_CAP, 0x313c, 20, GENMASK(3, 0), 0x0, 0x4, 0x1}, + {HPRE_CORE_TYPE_NUM_CAP, 0x313c, 16, GENMASK(3, 0), 0x0, 0x2, 0x2}, + {HPRE_CORE_NUM_CAP, 0x313c, 8, GENMASK(7, 0), 0x0, 0x8, 0xA}, + {HPRE_CLUSTER_CORE_NUM_CAP, 0x313c, 0, GENMASK(7, 0), 0x0, 0x2, 0xA}, + {HPRE_CORE_ENABLE_BITMAP_CAP, 0x3140, 0, GENMASK(31, 0), 0x0, 0xF, 0x3FF}, + {HPRE_DRV_ALG_BITMAP_CAP, 0x3144, 0, GENMASK(31, 0), 0x0, 0x03, 0x27}, + {HPRE_DEV_ALG_BITMAP_CAP, 0x3148, 0, GENMASK(31, 0), 0x0, 0x03, 0x7F}, + {HPRE_CORE1_ALG_BITMAP_CAP, 0x314c, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE2_ALG_BITMAP_CAP, 0x3150, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE3_ALG_BITMAP_CAP, 0x3154, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE4_ALG_BITMAP_CAP, 0x3158, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE5_ALG_BITMAP_CAP, 0x315c, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE6_ALG_BITMAP_CAP, 0x3160, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE7_ALG_BITMAP_CAP, 0x3164, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE8_ALG_BITMAP_CAP, 0x3168, 0, GENMASK(31, 0), 0x0, 0x7F, 0x7F}, + {HPRE_CORE9_ALG_BITMAP_CAP, 0x316c, 0, GENMASK(31, 0), 0x0, 0x10, 0x10}, + {HPRE_CORE10_ALG_BITMAP_CAP, 0x3170, 0, GENMASK(31, 0), 0x0, 0x10, 0x10} +}; + static const struct hpre_hw_error hpre_hw_errors[] = { { .int_msk = BIT(0), @@ -193,28 +293,32 @@ static const u64 hpre_cluster_offsets[] = { }; static const struct debugfs_reg32 hpre_cluster_dfx_regs[] = { - {"CORES_EN_STATUS ", HPRE_CORE_EN_OFFSET}, - {"CORES_INI_CFG ", HPRE_CORE_INI_CFG_OFFSET}, - {"CORES_INI_STATUS ", HPRE_CORE_INI_STATUS_OFFSET}, - {"CORES_HTBT_WARN ", HPRE_CORE_HTBT_WARN_OFFSET}, - {"CORES_IS_SCHD ", HPRE_CORE_IS_SCHD_OFFSET}, + {"CORES_EN_STATUS ", HPRE_CORE_EN_OFFSET}, + {"CORES_INI_CFG ", HPRE_CORE_INI_CFG_OFFSET}, + {"CORES_INI_STATUS ", HPRE_CORE_INI_STATUS_OFFSET}, + {"CORES_HTBT_WARN ", HPRE_CORE_HTBT_WARN_OFFSET}, + {"CORES_IS_SCHD ", HPRE_CORE_IS_SCHD_OFFSET}, }; static const struct debugfs_reg32 hpre_com_dfx_regs[] = { - {"READ_CLR_EN ", HPRE_CTRL_CNT_CLR_CE}, - {"AXQOS ", HPRE_VFG_AXQOS}, - {"AWUSR_CFG ", HPRE_AWUSR_FP_CFG}, - {"QM_ARUSR_MCFG1 ", QM_ARUSER_M_CFG_1}, - {"QM_AWUSR_MCFG1 ", QM_AWUSER_M_CFG_1}, - {"BD_ENDIAN ", HPRE_BD_ENDIAN}, - {"ECC_CHECK_CTRL ", HPRE_ECC_BYPASS}, - {"RAS_INT_WIDTH ", HPRE_RAS_WIDTH_CFG}, - {"POISON_BYPASS ", HPRE_POISON_BYPASS}, - {"BD_ARUSER ", HPRE_BD_ARUSR_CFG}, - {"BD_AWUSER ", HPRE_BD_AWUSR_CFG}, - {"DATA_ARUSER ", HPRE_DATA_RUSER_CFG}, - {"DATA_AWUSER ", HPRE_DATA_WUSER_CFG}, - {"INT_STATUS ", HPRE_INT_STATUS}, + {"READ_CLR_EN ", HPRE_CTRL_CNT_CLR_CE}, + {"AXQOS ", HPRE_VFG_AXQOS}, + {"AWUSR_CFG ", HPRE_AWUSR_FP_CFG}, + {"BD_ENDIAN ", HPRE_BD_ENDIAN}, + {"ECC_CHECK_CTRL ", HPRE_ECC_BYPASS}, + {"RAS_INT_WIDTH ", HPRE_RAS_WIDTH_CFG}, + {"POISON_BYPASS ", HPRE_POISON_BYPASS}, + {"BD_ARUSER ", HPRE_BD_ARUSR_CFG}, + {"BD_AWUSER ", HPRE_BD_AWUSR_CFG}, + {"DATA_ARUSER ", HPRE_DATA_RUSER_CFG}, + {"DATA_AWUSER ", HPRE_DATA_WUSER_CFG}, + {"INT_STATUS ", HPRE_INT_STATUS}, + {"INT_MASK ", HPRE_HAC_INT_MSK}, + {"RAS_CE_ENB ", HPRE_HAC_RAS_CE_ENB}, + {"RAS_NFE_ENB ", HPRE_HAC_RAS_NFE_ENB}, + {"RAS_FE_ENB ", HPRE_HAC_RAS_FE_ENB}, + {"INT_SET ", HPRE_HAC_INT_SET}, + {"RNG_TIMEOUT_NUM ", HPRE_RNG_TIMEOUT_NUM}, }; static const char *hpre_dfx_files[HPRE_DFX_FILE_NUM] = { @@ -227,6 +331,93 @@ static const char *hpre_dfx_files[HPRE_DFX_FILE_NUM] = { "invalid_req_cnt" }; +/* define the HPRE's dfx regs region and region length */ +static struct dfx_diff_registers hpre_diff_regs[] = { + { + .reg_offset = HPRE_DFX_BASE, + .reg_len = HPRE_DFX_BASE_LEN, + }, { + .reg_offset = HPRE_DFX_COMMON1, + .reg_len = HPRE_DFX_COMMON1_LEN, + }, { + .reg_offset = HPRE_DFX_COMMON2, + .reg_len = HPRE_DFX_COMMON2_LEN, + }, { + .reg_offset = HPRE_DFX_CORE, + .reg_len = HPRE_DFX_CORE_LEN, + }, +}; + +bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg) +{ + u32 cap_val; + + cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DRV_ALG_BITMAP_CAP, qm->cap_ver); + if (alg & cap_val) + return true; + + return false; +} + +static int hpre_set_qm_algs(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + char *algs, *ptr; + u32 alg_msk; + int i; + + if (!qm->use_sva) + return 0; + + algs = devm_kzalloc(dev, HPRE_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); + if (!algs) + return -ENOMEM; + + alg_msk = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DEV_ALG_BITMAP_CAP, qm->cap_ver); + + for (i = 0; i < ARRAY_SIZE(hpre_dev_algs); i++) + if (alg_msk & hpre_dev_algs[i].alg_msk) + strcat(algs, hpre_dev_algs[i].alg); + + ptr = strrchr(algs, '\n'); + if (ptr) + *ptr = '\0'; + + qm->uacce->algs = algs; + + return 0; +} + +static int hpre_diff_regs_show(struct seq_file *s, void *unused) +{ + struct hisi_qm *qm = s->private; + + hisi_qm_acc_diff_regs_dump(qm, s, qm->debug.acc_diff_regs, + ARRAY_SIZE(hpre_diff_regs)); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(hpre_diff_regs); + +static int hpre_com_regs_show(struct seq_file *s, void *unused) +{ + hisi_qm_regs_dump(s, s->private); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(hpre_com_regs); + +static int hpre_cluster_regs_show(struct seq_file *s, void *unused) +{ + hisi_qm_regs_dump(s, s->private); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(hpre_cluster_regs); + static const struct kernel_param_ops hpre_uacce_mode_ops = { .set = uacce_mode_set, .get = param_get_int, @@ -242,7 +433,7 @@ MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); static int pf_q_num_set(const char *val, const struct kernel_param *kp) { - return q_num_set(val, kp, HPRE_PCI_DEVICE_ID); + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_HPRE_PF); } static const struct kernel_param_ops hpre_pf_q_num_ops = { @@ -265,14 +456,12 @@ MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); static inline int hpre_cluster_num(struct hisi_qm *qm) { - return (qm->ver >= QM_HW_V3) ? HPRE_CLUSTERS_NUM_V3 : - HPRE_CLUSTERS_NUM_V2; + return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CLUSTER_NUM_CAP, qm->cap_ver); } static inline int hpre_cluster_core_mask(struct hisi_qm *qm) { - return (qm->ver >= QM_HW_V3) ? - HPRE_CLUSTER_CORE_MASK_V3 : HPRE_CLUSTER_CORE_MASK_V2; + return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CORE_ENABLE_BITMAP_CAP, qm->cap_ver); } struct hisi_qp *hpre_create_qp(u8 type) @@ -392,7 +581,7 @@ static void hpre_open_sva_prefetch(struct hisi_qm *qm) u32 val; int ret; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; /* Enable prefetch */ @@ -413,7 +602,7 @@ static void hpre_close_sva_prefetch(struct hisi_qm *qm) u32 val; int ret; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; val = readl_relaxed(qm->io_base + HPRE_PREFETCH_CFG); @@ -565,7 +754,8 @@ static void hpre_master_ooo_ctrl(struct hisi_qm *qm, bool enable) val1 = readl(qm->io_base + HPRE_AM_OOO_SHUTDOWN_ENB); if (enable) { val1 |= HPRE_AM_OOO_SHUTDOWN_ENABLE; - val2 = HPRE_HAC_RAS_NFE_ENABLE; + val2 = hisi_qm_get_hw_info(qm, hpre_basic_info, + HPRE_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); } else { val1 &= ~HPRE_AM_OOO_SHUTDOWN_ENABLE; val2 = 0x0; @@ -579,21 +769,30 @@ static void hpre_master_ooo_ctrl(struct hisi_qm *qm, bool enable) static void hpre_hw_error_disable(struct hisi_qm *qm) { - /* disable hpre hw error interrupts */ - writel(HPRE_CORE_INT_DISABLE, qm->io_base + HPRE_INT_MASK); + u32 ce, nfe; + ce = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CE_MASK_CAP, qm->cap_ver); + nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_NFE_MASK_CAP, qm->cap_ver); + + /* disable hpre hw error interrupts */ + writel(ce | nfe | HPRE_HAC_RAS_FE_ENABLE, qm->io_base + HPRE_INT_MASK); /* disable HPRE block master OOO when nfe occurs on Kunpeng930 */ hpre_master_ooo_ctrl(qm, false); } static void hpre_hw_error_enable(struct hisi_qm *qm) { + u32 ce, nfe; + + ce = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CE_MASK_CAP, qm->cap_ver); + nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_NFE_MASK_CAP, qm->cap_ver); + /* clear HPRE hw error source if having */ - writel(HPRE_CORE_INT_DISABLE, qm->io_base + HPRE_HAC_SOURCE_INT); + writel(ce | nfe | HPRE_HAC_RAS_FE_ENABLE, qm->io_base + HPRE_HAC_SOURCE_INT); /* configure error type */ - writel(HPRE_HAC_RAS_CE_ENABLE, qm->io_base + HPRE_RAS_CE_ENB); - writel(HPRE_HAC_RAS_NFE_ENABLE, qm->io_base + HPRE_RAS_NFE_ENB); + writel(ce, qm->io_base + HPRE_RAS_CE_ENB); + writel(nfe, qm->io_base + HPRE_RAS_NFE_ENB); writel(HPRE_HAC_RAS_FE_ENABLE, qm->io_base + HPRE_RAS_FE_ENB); /* enable HPRE block master OOO when nfe occurs on Kunpeng930 */ @@ -643,7 +842,7 @@ static u32 hpre_cluster_inqry_read(struct hpre_debugfs_file *file) return readl(qm->io_base + offset + HPRE_CLSTR_ADDR_INQRY_RSLT); } -static int hpre_cluster_inqry_write(struct hpre_debugfs_file *file, u32 val) +static void hpre_cluster_inqry_write(struct hpre_debugfs_file *file, u32 val) { struct hisi_qm *qm = hpre_file_to_qm(file); int cluster_index = file->index - HPRE_CLUSTER_CTRL; @@ -651,8 +850,6 @@ static int hpre_cluster_inqry_write(struct hpre_debugfs_file *file, u32 val) HPRE_CLSTR_ADDR_INTRVL; writel(val, qm->io_base + offset + HPRE_CLUSTER_INQURY); - - return 0; } static ssize_t hpre_ctrl_debug_read(struct file *filp, char __user *buf, @@ -727,9 +924,7 @@ static ssize_t hpre_ctrl_debug_write(struct file *filp, const char __user *buf, goto err_input; break; case HPRE_CLUSTER_CTRL: - ret = hpre_cluster_inqry_write(file, val); - if (ret) - goto err_input; + hpre_cluster_inqry_write(file, val); break; default: ret = -EINVAL; @@ -780,24 +975,6 @@ static int hpre_debugfs_atomic64_set(void *data, u64 val) DEFINE_DEBUGFS_ATTRIBUTE(hpre_atomic64_ops, hpre_debugfs_atomic64_get, hpre_debugfs_atomic64_set, "%llu\n"); -static int hpre_com_regs_show(struct seq_file *s, void *unused) -{ - hisi_qm_regs_dump(s, s->private); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(hpre_com_regs); - -static int hpre_cluster_regs_show(struct seq_file *s, void *unused) -{ - hisi_qm_regs_dump(s, s->private); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(hpre_cluster_regs); - static int hpre_create_debugfs_file(struct hisi_qm *qm, struct dentry *dir, enum hpre_ctrl_dbgfs_file type, int indx) { @@ -896,6 +1073,7 @@ static int hpre_ctrl_debug_init(struct hisi_qm *qm) static void hpre_dfx_debug_init(struct hisi_qm *qm) { + struct dfx_diff_registers *hpre_regs = qm->debug.acc_diff_regs; struct hpre *hpre = container_of(qm, struct hpre, qm); struct hpre_dfx *dfx = hpre->debug.dfx; struct dentry *parent; @@ -907,6 +1085,10 @@ static void hpre_dfx_debug_init(struct hisi_qm *qm) debugfs_create_file(hpre_dfx_files[i], 0644, parent, &dfx[i], &hpre_atomic64_ops); } + + if (qm->fun_type == QM_HW_PF && hpre_regs) + debugfs_create_file("diff_regs", 0444, parent, + qm, &hpre_diff_regs_fops); } static int hpre_debugfs_init(struct hisi_qm *qm) @@ -919,9 +1101,16 @@ static int hpre_debugfs_init(struct hisi_qm *qm) qm->debug.sqe_mask_offset = HPRE_SQE_MASK_OFFSET; qm->debug.sqe_mask_len = HPRE_SQE_MASK_LEN; + ret = hisi_qm_diff_regs_init(qm, hpre_diff_regs, + ARRAY_SIZE(hpre_diff_regs)); + if (ret) { + dev_warn(dev, "Failed to init HPRE diff regs!\n"); + goto debugfs_remove; + } + hisi_qm_debug_init(qm); - if (qm->pdev->device == HPRE_PCI_DEVICE_ID) { + if (qm->pdev->device == PCI_DEVICE_ID_HUAWEI_HPRE_PF) { ret = hpre_ctrl_debug_init(qm); if (ret) goto failed_to_create; @@ -932,33 +1121,35 @@ static int hpre_debugfs_init(struct hisi_qm *qm) return 0; failed_to_create: + hisi_qm_diff_regs_uninit(qm, ARRAY_SIZE(hpre_diff_regs)); +debugfs_remove: debugfs_remove_recursive(qm->debug.debug_root); return ret; } static void hpre_debugfs_exit(struct hisi_qm *qm) { + hisi_qm_diff_regs_uninit(qm, ARRAY_SIZE(hpre_diff_regs)); + debugfs_remove_recursive(qm->debug.debug_root); } static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + int ret; + if (pdev->revision == QM_HW_V1) { pci_warn(pdev, "HPRE version 1 is not supported!\n"); return -EINVAL; } - if (pdev->revision >= QM_HW_V3) - qm->algs = "rsa\ndh\necdh\nx25519\nx448\necdsa\nsm2"; - else - qm->algs = "rsa\ndh"; qm->mode = uacce_mode; qm->pdev = pdev; qm->ver = pdev->revision; qm->sqe_size = HPRE_SQE_SIZE; qm->dev_name = hpre_name; - qm->fun_type = (pdev->device == HPRE_PCI_DEVICE_ID) ? + qm->fun_type = (pdev->device == PCI_DEVICE_ID_HUAWEI_HPRE_PF) ? QM_HW_PF : QM_HW_VF; if (qm->fun_type == QM_HW_PF) { qm->qp_base = HPRE_PF_DEF_Q_BASE; @@ -967,7 +1158,95 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qm_list = &hpre_devices; } - return hisi_qm_init(qm); + ret = hisi_qm_init(qm); + if (ret) { + pci_err(pdev, "Failed to init hpre qm configures!\n"); + return ret; + } + + ret = hpre_set_qm_algs(qm); + if (ret) { + pci_err(pdev, "Failed to set hpre algs!\n"); + hisi_qm_uninit(qm); + } + + return ret; +} + +static int hpre_show_last_regs_init(struct hisi_qm *qm) +{ + int cluster_dfx_regs_num = ARRAY_SIZE(hpre_cluster_dfx_regs); + int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs); + u8 clusters_num = hpre_cluster_num(qm); + struct qm_debug *debug = &qm->debug; + void __iomem *io_base; + int i, j, idx; + + debug->last_words = kcalloc(cluster_dfx_regs_num * clusters_num + + com_dfx_regs_num, sizeof(unsigned int), GFP_KERNEL); + if (!debug->last_words) + return -ENOMEM; + + for (i = 0; i < com_dfx_regs_num; i++) + debug->last_words[i] = readl_relaxed(qm->io_base + + hpre_com_dfx_regs[i].offset); + + for (i = 0; i < clusters_num; i++) { + io_base = qm->io_base + hpre_cluster_offsets[i]; + for (j = 0; j < cluster_dfx_regs_num; j++) { + idx = com_dfx_regs_num + i * cluster_dfx_regs_num + j; + debug->last_words[idx] = readl_relaxed( + io_base + hpre_cluster_dfx_regs[j].offset); + } + } + + return 0; +} + +static void hpre_show_last_regs_uninit(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + + if (qm->fun_type == QM_HW_VF || !debug->last_words) + return; + + kfree(debug->last_words); + debug->last_words = NULL; +} + +static void hpre_show_last_dfx_regs(struct hisi_qm *qm) +{ + int cluster_dfx_regs_num = ARRAY_SIZE(hpre_cluster_dfx_regs); + int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs); + u8 clusters_num = hpre_cluster_num(qm); + struct qm_debug *debug = &qm->debug; + struct pci_dev *pdev = qm->pdev; + void __iomem *io_base; + int i, j, idx; + u32 val; + + if (qm->fun_type == QM_HW_VF || !debug->last_words) + return; + + /* dumps last word of the debugging registers during controller reset */ + for (i = 0; i < com_dfx_regs_num; i++) { + val = readl_relaxed(qm->io_base + hpre_com_dfx_regs[i].offset); + if (debug->last_words[i] != val) + pci_info(pdev, "Common_core:%s \t= 0x%08x => 0x%08x\n", + hpre_com_dfx_regs[i].name, debug->last_words[i], val); + } + + for (i = 0; i < clusters_num; i++) { + io_base = qm->io_base + hpre_cluster_offsets[i]; + for (j = 0; j < cluster_dfx_regs_num; j++) { + val = readl_relaxed(io_base + + hpre_cluster_dfx_regs[j].offset); + idx = com_dfx_regs_num + i * cluster_dfx_regs_num + j; + if (debug->last_words[idx] != val) + pci_info(pdev, "cluster-%d:%s \t= 0x%08x => 0x%08x\n", + i, hpre_cluster_dfx_regs[j].name, debug->last_words[idx], val); + } + } } static void hpre_log_hw_error(struct hisi_qm *qm, u32 err_sts) @@ -990,7 +1269,11 @@ static u32 hpre_get_hw_err_status(struct hisi_qm *qm) static void hpre_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts) { + u32 nfe; + writel(err_sts, qm->io_base + HPRE_HAC_SOURCE_INT); + nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_NFE_MASK_CAP, qm->cap_ver); + writel(nfe, qm->io_base + HPRE_RAS_NFE_ENB); } static void hpre_open_axi_master_ooo(struct hisi_qm *qm) @@ -1008,14 +1291,20 @@ static void hpre_err_info_init(struct hisi_qm *qm) { struct hisi_qm_err_info *err_info = &qm->err_info; - err_info->ce = QM_BASE_CE; - err_info->fe = 0; - err_info->ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | - HPRE_OOO_ECC_2BIT_ERR; - err_info->dev_ce_mask = HPRE_HAC_RAS_CE_ENABLE; + err_info->fe = HPRE_HAC_RAS_FE_ENABLE; + err_info->ce = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_QM_CE_MASK_CAP, qm->cap_ver); + err_info->nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_QM_NFE_MASK_CAP, qm->cap_ver); + err_info->ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | HPRE_OOO_ECC_2BIT_ERR; + err_info->dev_shutdown_mask = hisi_qm_get_hw_info(qm, hpre_basic_info, + HPRE_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); + err_info->qm_shutdown_mask = hisi_qm_get_hw_info(qm, hpre_basic_info, + HPRE_QM_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); + err_info->qm_reset_mask = hisi_qm_get_hw_info(qm, hpre_basic_info, + HPRE_QM_RESET_MASK_CAP, qm->cap_ver); + err_info->dev_reset_mask = hisi_qm_get_hw_info(qm, hpre_basic_info, + HPRE_RESET_MASK_CAP, qm->cap_ver); err_info->msi_wr_port = HPRE_WR_MSI_PORT; err_info->acpi_rst = "HRST"; - err_info->nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; } static const struct hisi_qm_err_ini hpre_err_ini = { @@ -1028,6 +1317,7 @@ static const struct hisi_qm_err_ini hpre_err_ini = { .open_axi_master_ooo = hpre_open_axi_master_ooo, .open_sva_prefetch = hpre_open_sva_prefetch, .close_sva_prefetch = hpre_close_sva_prefetch, + .show_last_dfx_regs = hpre_show_last_dfx_regs, .err_info_init = hpre_err_info_init, }; @@ -1045,8 +1335,11 @@ static int hpre_pf_probe_init(struct hpre *hpre) qm->err_ini = &hpre_err_ini; qm->err_ini->err_info_init(qm); hisi_qm_dev_err_init(qm); + ret = hpre_show_last_regs_init(qm); + if (ret) + pci_err(qm->pdev, "Failed to init last word regs!\n"); - return 0; + return ret; } static int hpre_probe_init(struct hpre *hpre) @@ -1132,6 +1425,7 @@ err_with_qm_start: hisi_qm_stop(qm, QM_NORMAL); err_with_err_init: + hpre_show_last_regs_uninit(qm); hisi_qm_dev_err_uninit(qm); err_with_qm_init: @@ -1162,6 +1456,7 @@ static void hpre_remove(struct pci_dev *pdev) if (qm->fun_type == QM_HW_PF) { hpre_cnt_regs_clear(qm); qm->debug.curr_qm_qp_num = 0; + hpre_show_last_regs_uninit(qm); hisi_qm_dev_err_uninit(qm); } @@ -1191,6 +1486,12 @@ static struct pci_driver hpre_pci_driver = { .driver.pm = &hpre_pm_ops, }; +struct pci_driver *hisi_hpre_get_pf_driver(void) +{ + return &hpre_pci_driver; +} +EXPORT_SYMBOL_GPL(hisi_hpre_get_pf_driver); + static void hpre_register_debugfs(void) { if (!debugfs_initialized()) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index c5b84a5ea350..8b387de69d22 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -15,44 +15,24 @@ #include <linux/uacce.h> #include <linux/uaccess.h> #include <uapi/misc/uacce/hisi_qm.h> -#include "qm.h" +#include <linux/hisi_acc_qm.h> /* eq/aeq irq enable */ #define QM_VF_AEQ_INT_SOURCE 0x0 #define QM_VF_AEQ_INT_MASK 0x4 #define QM_VF_EQ_INT_SOURCE 0x8 #define QM_VF_EQ_INT_MASK 0xc -#define QM_IRQ_NUM_V1 1 -#define QM_IRQ_NUM_PF_V2 4 -#define QM_IRQ_NUM_VF_V2 2 -#define QM_IRQ_NUM_VF_V3 3 -#define QM_EQ_EVENT_IRQ_VECTOR 0 -#define QM_AEQ_EVENT_IRQ_VECTOR 1 -#define QM_CMD_EVENT_IRQ_VECTOR 2 -#define QM_ABNORMAL_EVENT_IRQ_VECTOR 3 +#define QM_IRQ_VECTOR_MASK GENMASK(15, 0) +#define QM_IRQ_TYPE_MASK GENMASK(15, 0) +#define QM_IRQ_TYPE_SHIFT 16 +#define QM_ABN_IRQ_TYPE_MASK GENMASK(7, 0) /* mailbox */ -#define QM_MB_CMD_SQC 0x0 -#define QM_MB_CMD_CQC 0x1 -#define QM_MB_CMD_EQC 0x2 -#define QM_MB_CMD_AEQC 0x3 -#define QM_MB_CMD_SQC_BT 0x4 -#define QM_MB_CMD_CQC_BT 0x5 -#define QM_MB_CMD_SQC_VFT_V2 0x6 -#define QM_MB_CMD_STOP_QP 0x8 -#define QM_MB_CMD_SRC 0xc -#define QM_MB_CMD_DST 0xd - -#define QM_MB_CMD_SEND_BASE 0x300 -#define QM_MB_EVENT_SHIFT 8 -#define QM_MB_BUSY_SHIFT 13 -#define QM_MB_OP_SHIFT 14 -#define QM_MB_CMD_DATA_ADDR_L 0x304 -#define QM_MB_CMD_DATA_ADDR_H 0x308 #define QM_MB_PING_ALL_VFS 0xffff #define QM_MB_CMD_DATA_SHIFT 32 #define QM_MB_CMD_DATA_MASK GENMASK(31, 0) +#define QM_MB_STATUS_MASK GENMASK(12, 9) /* sqc shift */ #define QM_SQ_HOP_NUM_SHIFT 0 @@ -94,6 +74,9 @@ #define QM_EQ_OVERFLOW 1 #define QM_CQE_ERROR 2 +#define QM_XQ_DEPTH_SHIFT 16 +#define QM_XQ_DEPTH_MASK GENMASK(15, 0) + #define QM_DOORBELL_CMD_SQ 0 #define QM_DOORBELL_CMD_CQ 1 #define QM_DOORBELL_CMD_EQ 2 @@ -103,19 +86,8 @@ #define QM_DB_CMD_SHIFT_V1 16 #define QM_DB_INDEX_SHIFT_V1 32 #define QM_DB_PRIORITY_SHIFT_V1 48 -#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 -#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 -#define QM_QUE_ISO_CFG_V 0x0030 #define QM_PAGE_SIZE 0x0034 -#define QM_QUE_ISO_EN 0x100154 -#define QM_CAPBILITY 0x100158 -#define QM_QP_NUN_MASK GENMASK(10, 0) #define QM_QP_DB_INTERVAL 0x10000 -#define QM_QP_MAX_NUM_SHIFT 11 -#define QM_DB_CMD_SHIFT_V2 12 -#define QM_DB_RAND_SHIFT_V2 16 -#define QM_DB_INDEX_SHIFT_V2 32 -#define QM_DB_PRIORITY_SHIFT_V2 48 #define QM_MEM_START_INIT 0x100040 #define QM_MEM_INIT_DONE 0x100044 @@ -150,7 +122,6 @@ #define QM_DFX_CNT_CLR_CE 0x100118 #define QM_ABNORMAL_INT_SOURCE 0x100000 -#define QM_ABNORMAL_INT_SOURCE_CLR GENMASK(14, 0) #define QM_ABNORMAL_INT_MASK 0x100004 #define QM_ABNORMAL_INT_MASK_VALUE 0x7fff #define QM_ABNORMAL_INT_STATUS 0x100008 @@ -168,8 +139,10 @@ #define QM_RAS_NFE_ENABLE 0x1000f4 #define QM_RAS_CE_THRESHOLD 0x1000f8 #define QM_RAS_CE_TIMES_PER_IRQ 1 -#define QM_RAS_MSI_INT_SEL 0x1040f4 #define QM_OOO_SHUTDOWN_SEL 0x1040f8 +#define QM_ECC_MBIT BIT(2) +#define QM_DB_TIMEOUT BIT(10) +#define QM_OF_FIFO_OF BIT(11) #define QM_RESET_WAIT_TIMEOUT 400 #define QM_PEH_VENDOR_ID 0x1000d8 @@ -229,6 +202,8 @@ #define MAX_WAIT_COUNTS 1000 #define QM_CACHE_WB_START 0x204 #define QM_CACHE_WB_DONE 0x208 +#define QM_FUNC_CAPS_REG 0x3100 +#define QM_CAPBILITY_VERSION GENMASK(7, 0) #define PCI_BAR_2 2 #define PCI_BAR_4 4 @@ -245,7 +220,6 @@ #define WAIT_PERIOD 20 #define REMOVE_WAIT_DELAY 10 #define QM_SQE_ADDR_MASK GENMASK(7, 0) -#define QM_EQ_DEPTH (1024 * 2) #define QM_DRIVER_REMOVING 0 #define QM_RST_SCHED 1 @@ -277,7 +251,15 @@ #define QM_QOS_MAX_CIR_U 6 #define QM_QOS_MAX_CIR_S 11 #define QM_QOS_VAL_MAX_LEN 32 - +#define QM_DFX_BASE 0x0100000 +#define QM_DFX_STATE1 0x0104000 +#define QM_DFX_STATE2 0x01040C8 +#define QM_DFX_COMMON 0x0000 +#define QM_DFX_BASE_LEN 0x5A +#define QM_DFX_STATE1_LEN 0x2E +#define QM_DFX_STATE2_LEN 0x11 +#define QM_DFX_COMMON_LEN 0xC3 +#define QM_DFX_REGS_LEN 4UL #define QM_AUTOSUSPEND_DELAY 3000 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \ @@ -286,8 +268,8 @@ ((buf_sz) << QM_CQ_BUF_SIZE_SHIFT) | \ ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) -#define QM_MK_CQC_DW3_V2(cqe_sz) \ - ((QM_Q_DEPTH - 1) | ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) +#define QM_MK_CQC_DW3_V2(cqe_sz, cq_depth) \ + ((((u32)cq_depth) - 1) | ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) #define QM_MK_SQC_W13(priority, orders, alg_type) \ (((priority) << QM_SQ_PRIORITY_SHIFT) | \ @@ -300,8 +282,8 @@ ((buf_sz) << QM_SQ_BUF_SIZE_SHIFT) | \ ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT)) -#define QM_MK_SQC_DW3_V2(sqe_sz) \ - ((QM_Q_DEPTH - 1) | ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT)) +#define QM_MK_SQC_DW3_V2(sqe_sz, sq_depth) \ + ((((u32)sq_depth) - 1) | ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT)) #define INIT_QC_COMMON(qc, base, pasid) do { \ (qc)->head = 0; \ @@ -345,6 +327,48 @@ enum qm_mb_cmd { QM_VF_GET_QOS, }; +enum qm_basic_type { + QM_TOTAL_QP_NUM_CAP = 0x0, + QM_FUNC_MAX_QP_CAP, + QM_XEQ_DEPTH_CAP, + QM_QP_DEPTH_CAP, + QM_EQ_IRQ_TYPE_CAP, + QM_AEQ_IRQ_TYPE_CAP, + QM_ABN_IRQ_TYPE_CAP, + QM_PF2VF_IRQ_TYPE_CAP, + QM_PF_IRQ_NUM_CAP, + QM_VF_IRQ_NUM_CAP, +}; + +static const struct hisi_qm_cap_info qm_cap_info_comm[] = { + {QM_SUPPORT_DB_ISOLATION, 0x30, 0, BIT(0), 0x0, 0x0, 0x0}, + {QM_SUPPORT_FUNC_QOS, 0x3100, 0, BIT(8), 0x0, 0x0, 0x1}, + {QM_SUPPORT_STOP_QP, 0x3100, 0, BIT(9), 0x0, 0x0, 0x1}, + {QM_SUPPORT_MB_COMMAND, 0x3100, 0, BIT(11), 0x0, 0x0, 0x1}, + {QM_SUPPORT_SVA_PREFETCH, 0x3100, 0, BIT(14), 0x0, 0x0, 0x1}, +}; + +static const struct hisi_qm_cap_info qm_cap_info_pf[] = { + {QM_SUPPORT_RPM, 0x3100, 0, BIT(13), 0x0, 0x0, 0x1}, +}; + +static const struct hisi_qm_cap_info qm_cap_info_vf[] = { + {QM_SUPPORT_RPM, 0x3100, 0, BIT(12), 0x0, 0x0, 0x0}, +}; + +static const struct hisi_qm_cap_info qm_basic_info[] = { + {QM_TOTAL_QP_NUM_CAP, 0x100158, 0, GENMASK(10, 0), 0x1000, 0x400, 0x400}, + {QM_FUNC_MAX_QP_CAP, 0x100158, 11, GENMASK(10, 0), 0x1000, 0x400, 0x400}, + {QM_XEQ_DEPTH_CAP, 0x3104, 0, GENMASK(15, 0), 0x800, 0x4000800, 0x4000800}, + {QM_QP_DEPTH_CAP, 0x3108, 0, GENMASK(31, 0), 0x4000400, 0x4000400, 0x4000400}, + {QM_EQ_IRQ_TYPE_CAP, 0x310c, 0, GENMASK(31, 0), 0x10000, 0x10000, 0x10000}, + {QM_AEQ_IRQ_TYPE_CAP, 0x3110, 0, GENMASK(31, 0), 0x0, 0x10001, 0x10001}, + {QM_ABN_IRQ_TYPE_CAP, 0x3114, 0, GENMASK(31, 0), 0x0, 0x10003, 0x10003}, + {QM_PF2VF_IRQ_TYPE_CAP, 0x3118, 0, GENMASK(31, 0), 0x0, 0x0, 0x10002}, + {QM_PF_IRQ_NUM_CAP, 0x311c, 16, GENMASK(15, 0), 0x1, 0x4, 0x4}, + {QM_VF_IRQ_NUM_CAP, 0x311c, 0, GENMASK(15, 0), 0x1, 0x2, 0x3}, +}; + struct qm_cqe { __le32 rsvd0; __le16 cmd_id; @@ -437,15 +461,11 @@ struct hisi_qm_hw_ops { int (*get_vft)(struct hisi_qm *qm, u32 *base, u32 *number); void (*qm_db)(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority); - u32 (*get_irq_num)(struct hisi_qm *qm); int (*debug_init)(struct hisi_qm *qm); - void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe); + void (*hw_error_init)(struct hisi_qm *qm); void (*hw_error_uninit)(struct hisi_qm *qm); enum acc_err_result (*hw_error_handle)(struct hisi_qm *qm); - int (*stop_qp)(struct hisi_qp *qp); int (*set_msi)(struct hisi_qm *qm, bool set); - int (*ping_all_vfs)(struct hisi_qm *qm, u64 cmd); - int (*ping_pf)(struct hisi_qm *qm, u64 cmd); }; struct qm_dfx_item { @@ -491,6 +511,23 @@ static const struct hisi_qm_hw_error qm_hw_error[] = { { /* sentinel */ } }; +/* define the QM's dfx regs region and region length */ +static struct dfx_diff_registers qm_diff_regs[] = { + { + .reg_offset = QM_DFX_BASE, + .reg_len = QM_DFX_BASE_LEN, + }, { + .reg_offset = QM_DFX_STATE1, + .reg_len = QM_DFX_STATE1_LEN, + }, { + .reg_offset = QM_DFX_STATE2, + .reg_len = QM_DFX_STATE2_LEN, + }, { + .reg_offset = QM_DFX_COMMON, + .reg_len = QM_DFX_COMMON_LEN, + }, +}; + static const char * const qm_db_timeout[] = { "sq", "cq", "eq", "aeq", }; @@ -532,6 +569,8 @@ static struct qm_typical_qos_table shaper_cbs_s[] = { {50100, 100000, 19} }; +static void qm_irqs_unregister(struct hisi_qm *qm); + static bool qm_avail_state(struct hisi_qm *qm, enum qm_state new) { enum qm_state curr = atomic_read(&qm->status.flags); @@ -622,22 +661,17 @@ static u32 qm_get_dev_err_status(struct hisi_qm *qm) } /* Check if the error causes the master ooo block */ -static int qm_check_dev_error(struct hisi_qm *qm) +static bool qm_check_dev_error(struct hisi_qm *qm) { u32 val, dev_val; if (qm->fun_type == QM_HW_VF) - return 0; - - val = qm_get_hw_error_status(qm); - dev_val = qm_get_dev_err_status(qm); + return false; - if (qm->ver < QM_HW_V3) - return (val & QM_ECC_MBIT) || - (dev_val & qm->err_info.ecc_2bits_mask); + val = qm_get_hw_error_status(qm) & qm->err_info.qm_shutdown_mask; + dev_val = qm_get_dev_err_status(qm) & qm->err_info.dev_shutdown_mask; - return (val & readl(qm->io_base + QM_OOO_SHUTDOWN_SEL)) || - (dev_val & (~qm->err_info.dev_ce_mask)); + return val || dev_val; } static int qm_wait_reset_finish(struct hisi_qm *qm) @@ -693,7 +727,7 @@ static void qm_mb_pre_init(struct qm_mailbox *mailbox, u8 cmd, } /* return 0 mailbox ready, -ETIMEDOUT hardware timeout */ -static int qm_wait_mb_ready(struct hisi_qm *qm) +int hisi_qm_wait_mb_ready(struct hisi_qm *qm) { u32 val; @@ -701,6 +735,7 @@ static int qm_wait_mb_ready(struct hisi_qm *qm) val, !((val >> QM_MB_BUSY_SHIFT) & 0x1), POLL_PERIOD, POLL_TIMEOUT); } +EXPORT_SYMBOL_GPL(hisi_qm_wait_mb_ready); /* 128 bit should be written to hardware at one time to trigger a mailbox */ static void qm_mb_write(struct hisi_qm *qm, const void *src) @@ -710,13 +745,13 @@ static void qm_mb_write(struct hisi_qm *qm, const void *src) if (!IS_ENABLED(CONFIG_ARM64)) { memcpy_toio(fun_base, src, 16); - wmb(); + dma_wmb(); return; } asm volatile("ldp %0, %1, %3\n" "stp %0, %1, %2\n" - "dsb sy\n" + "dmb oshst\n" : "=&r" (tmp0), "=&r" (tmp1), "+Q" (*((char __iomem *)fun_base)) @@ -726,15 +761,27 @@ static void qm_mb_write(struct hisi_qm *qm, const void *src) static int qm_mb_nolock(struct hisi_qm *qm, struct qm_mailbox *mailbox) { - if (unlikely(qm_wait_mb_ready(qm))) { + int ret; + u32 val; + + if (unlikely(hisi_qm_wait_mb_ready(qm))) { dev_err(&qm->pdev->dev, "QM mailbox is busy to start!\n"); + ret = -EBUSY; goto mb_busy; } qm_mb_write(qm, mailbox); - if (unlikely(qm_wait_mb_ready(qm))) { + if (unlikely(hisi_qm_wait_mb_ready(qm))) { dev_err(&qm->pdev->dev, "QM mailbox operation timeout!\n"); + ret = -ETIMEDOUT; + goto mb_busy; + } + + val = readl(qm->io_base + QM_MB_CMD_SEND_BASE); + if (val & QM_MB_STATUS_MASK) { + dev_err(&qm->pdev->dev, "QM mailbox operation failed!\n"); + ret = -EIO; goto mb_busy; } @@ -742,11 +789,11 @@ static int qm_mb_nolock(struct hisi_qm *qm, struct qm_mailbox *mailbox) mb_busy: atomic64_inc(&qm->debug.dfx.mb_err_cnt); - return -EBUSY; + return ret; } -static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, - bool op) +int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op) { struct qm_mailbox mailbox; int ret; @@ -762,6 +809,7 @@ static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, return ret; } +EXPORT_SYMBOL_GPL(hisi_qm_mb); static void qm_db_v1(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) { @@ -825,25 +873,52 @@ static int qm_dev_mem_reset(struct hisi_qm *qm) POLL_TIMEOUT); } -static u32 qm_get_irq_num_v1(struct hisi_qm *qm) +/** + * hisi_qm_get_hw_info() - Get device information. + * @qm: The qm which want to get information. + * @info_table: Array for storing device information. + * @index: Index in info_table. + * @is_read: Whether read from reg, 0: not support read from reg. + * + * This function returns device information the caller needs. + */ +u32 hisi_qm_get_hw_info(struct hisi_qm *qm, + const struct hisi_qm_cap_info *info_table, + u32 index, bool is_read) { - return QM_IRQ_NUM_V1; + u32 val; + + switch (qm->ver) { + case QM_HW_V1: + return info_table[index].v1_val; + case QM_HW_V2: + return info_table[index].v2_val; + default: + if (!is_read) + return info_table[index].v3_val; + + val = readl(qm->io_base + info_table[index].offset); + return (val >> info_table[index].shift) & info_table[index].mask; + } } +EXPORT_SYMBOL_GPL(hisi_qm_get_hw_info); -static u32 qm_get_irq_num_v2(struct hisi_qm *qm) +static void qm_get_xqc_depth(struct hisi_qm *qm, u16 *low_bits, + u16 *high_bits, enum qm_basic_type type) { - if (qm->fun_type == QM_HW_PF) - return QM_IRQ_NUM_PF_V2; - else - return QM_IRQ_NUM_VF_V2; + u32 depth; + + depth = hisi_qm_get_hw_info(qm, qm_basic_info, type, qm->cap_ver); + *high_bits = depth & QM_XQ_DEPTH_MASK; + *low_bits = (depth >> QM_XQ_DEPTH_SHIFT) & QM_XQ_DEPTH_MASK; } -static u32 qm_get_irq_num_v3(struct hisi_qm *qm) +static u32 qm_get_irq_num(struct hisi_qm *qm) { if (qm->fun_type == QM_HW_PF) - return QM_IRQ_NUM_PF_V2; + return hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF_IRQ_NUM_CAP, qm->cap_ver); - return QM_IRQ_NUM_VF_V3; + return hisi_qm_get_hw_info(qm, qm_basic_info, QM_VF_IRQ_NUM_CAP, qm->cap_ver); } static int qm_pm_get_sync(struct hisi_qm *qm) @@ -851,7 +926,7 @@ static int qm_pm_get_sync(struct hisi_qm *qm) struct device *dev = &qm->pdev->dev; int ret; - if (qm->fun_type == QM_HW_VF || qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_RPM, &qm->caps)) return 0; ret = pm_runtime_resume_and_get(dev); @@ -867,23 +942,16 @@ static void qm_pm_put_sync(struct hisi_qm *qm) { struct device *dev = &qm->pdev->dev; - if (qm->fun_type == QM_HW_VF || qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_RPM, &qm->caps)) return; pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); } -static struct hisi_qp *qm_to_hisi_qp(struct hisi_qm *qm, struct qm_eqe *eqe) -{ - u16 cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK; - - return &qm->qp_array[cqn]; -} - static void qm_cq_head_update(struct hisi_qp *qp) { - if (qp->qp_status.cq_head == QM_Q_DEPTH - 1) { + if (qp->qp_status.cq_head == qp->cq_depth - 1) { qp->qp_status.cqc_phase = !qp->qp_status.cqc_phase; qp->qp_status.cq_head = 0; } else { @@ -891,49 +959,40 @@ static void qm_cq_head_update(struct hisi_qp *qp) } } -static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm) +static void qm_poll_req_cb(struct hisi_qp *qp) { - if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP)) - return; - - if (qp->event_cb) { - qp->event_cb(qp); - return; - } - - if (qp->req_cb) { - struct qm_cqe *cqe = qp->cqe + qp->qp_status.cq_head; - - while (QM_CQE_PHASE(cqe) == qp->qp_status.cqc_phase) { - dma_rmb(); - qp->req_cb(qp, qp->sqe + qm->sqe_size * - le16_to_cpu(cqe->sq_head)); - qm_cq_head_update(qp); - cqe = qp->cqe + qp->qp_status.cq_head; - qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, - qp->qp_status.cq_head, 0); - atomic_dec(&qp->qp_status.used); - } + struct qm_cqe *cqe = qp->cqe + qp->qp_status.cq_head; + struct hisi_qm *qm = qp->qm; - /* set c_flag */ + while (QM_CQE_PHASE(cqe) == qp->qp_status.cqc_phase) { + dma_rmb(); + qp->req_cb(qp, qp->sqe + qm->sqe_size * + le16_to_cpu(cqe->sq_head)); + qm_cq_head_update(qp); + cqe = qp->cqe + qp->qp_status.cq_head; qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, - qp->qp_status.cq_head, 1); + qp->qp_status.cq_head, 0); + atomic_dec(&qp->qp_status.used); } + + /* set c_flag */ + qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 1); } -static void qm_work_process(struct work_struct *work) +static int qm_get_complete_eqe_num(struct hisi_qm_poll_data *poll_data) { - struct hisi_qm *qm = container_of(work, struct hisi_qm, work); + struct hisi_qm *qm = poll_data->qm; struct qm_eqe *eqe = qm->eqe + qm->status.eq_head; - struct hisi_qp *qp; + u16 eq_depth = qm->eq_depth; int eqe_num = 0; + u16 cqn; while (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) { + cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK; + poll_data->qp_finish_id[eqe_num] = cqn; eqe_num++; - qp = qm_to_hisi_qp(qm, eqe); - qm_poll_qp(qp, qm); - if (qm->status.eq_head == QM_EQ_DEPTH - 1) { + if (qm->status.eq_head == eq_depth - 1) { qm->status.eqc_phase = !qm->status.eqc_phase; eqe = qm->eqe; qm->status.eq_head = 0; @@ -942,37 +1001,70 @@ static void qm_work_process(struct work_struct *work) qm->status.eq_head++; } - if (eqe_num == QM_EQ_DEPTH / 2 - 1) { - eqe_num = 0; - qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); - } + if (eqe_num == (eq_depth >> 1) - 1) + break; } qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); + + return eqe_num; +} + +static void qm_work_process(struct work_struct *work) +{ + struct hisi_qm_poll_data *poll_data = + container_of(work, struct hisi_qm_poll_data, work); + struct hisi_qm *qm = poll_data->qm; + struct hisi_qp *qp; + int eqe_num, i; + + /* Get qp id of completed tasks and re-enable the interrupt. */ + eqe_num = qm_get_complete_eqe_num(poll_data); + for (i = eqe_num - 1; i >= 0; i--) { + qp = &qm->qp_array[poll_data->qp_finish_id[i]]; + if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP)) + continue; + + if (qp->event_cb) { + qp->event_cb(qp); + continue; + } + + if (likely(qp->req_cb)) + qm_poll_req_cb(qp); + } } -static irqreturn_t do_qm_irq(int irq, void *data) +static bool do_qm_irq(struct hisi_qm *qm) { - struct hisi_qm *qm = (struct hisi_qm *)data; + struct qm_eqe *eqe = qm->eqe + qm->status.eq_head; + struct hisi_qm_poll_data *poll_data; + u16 cqn; - /* the workqueue created by device driver of QM */ - if (qm->wq) - queue_work(qm->wq, &qm->work); - else - schedule_work(&qm->work); + if (!readl(qm->io_base + QM_VF_EQ_INT_SOURCE)) + return false; - return IRQ_HANDLED; + if (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) { + cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK; + poll_data = &qm->poll_data[cqn]; + queue_work(qm->wq, &poll_data->work); + + return true; + } + + return false; } static irqreturn_t qm_irq(int irq, void *data) { struct hisi_qm *qm = data; + bool ret; - if (readl(qm->io_base + QM_VF_EQ_INT_SOURCE)) - return do_qm_irq(irq, data); + ret = do_qm_irq(qm); + if (ret) + return IRQ_HANDLED; atomic64_inc(&qm->debug.dfx.err_irq_cnt); - dev_err(&qm->pdev->dev, "invalid int source\n"); qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); return IRQ_NONE; @@ -1004,7 +1096,7 @@ static void qm_set_qp_disable(struct hisi_qp *qp, int offset) *addr = 1; /* make sure setup is completed */ - mb(); + smp_wmb(); } static void qm_disable_qp(struct hisi_qm *qm, u32 qp_id) @@ -1049,6 +1141,7 @@ static irqreturn_t qm_aeq_thread(int irq, void *data) { struct hisi_qm *qm = data; struct qm_aeqe *aeqe = qm->aeqe + qm->status.aeq_head; + u16 aeq_depth = qm->aeq_depth; u32 type, qp_id; while (QM_AEQE_PHASE(aeqe) == qm->status.aeqc_phase) { @@ -1073,7 +1166,7 @@ static irqreturn_t qm_aeq_thread(int irq, void *data) break; } - if (qm->status.aeq_head == QM_Q_DEPTH - 1) { + if (qm->status.aeq_head == aeq_depth - 1) { qm->status.aeqc_phase = !qm->status.aeqc_phase; aeqe = qm->aeqe; qm->status.aeq_head = 0; @@ -1099,24 +1192,6 @@ static irqreturn_t qm_aeq_irq(int irq, void *data) return IRQ_WAKE_THREAD; } -static void qm_irq_unregister(struct hisi_qm *qm) -{ - struct pci_dev *pdev = qm->pdev; - - free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm); - - if (qm->ver > QM_HW_V1) { - free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm); - - if (qm->fun_type == QM_HW_PF) - free_irq(pci_irq_vector(pdev, - QM_ABNORMAL_EVENT_IRQ_VECTOR), qm); - } - - if (qm->ver > QM_HW_V2) - free_irq(pci_irq_vector(pdev, QM_CMD_EVENT_IRQ_VECTOR), qm); -} - static void qm_init_qp_status(struct hisi_qp *qp) { struct hisi_qp_status *qp_status = &qp->qp_status; @@ -1132,7 +1207,7 @@ static void qm_init_prefetch(struct hisi_qm *qm) struct device *dev = &qm->pdev->dev; u32 page_type = 0x0; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; switch (PAGE_SIZE) { @@ -1251,7 +1326,7 @@ static void qm_vft_data_cfg(struct hisi_qm *qm, enum vft_type type, u32 base, } break; case SHAPER_VFT: - if (qm->ver >= QM_HW_V3) { + if (factor) { tmp = factor->cir_b | (factor->cir_u << QM_SHAPER_FACTOR_CIR_U_SHIFT) | (factor->cir_s << QM_SHAPER_FACTOR_CIR_S_SHIFT) | @@ -1269,10 +1344,13 @@ static void qm_vft_data_cfg(struct hisi_qm *qm, enum vft_type type, u32 base, static int qm_set_vft_common(struct hisi_qm *qm, enum vft_type type, u32 fun_num, u32 base, u32 number) { - struct qm_shaper_factor *factor = &qm->factor[fun_num]; + struct qm_shaper_factor *factor = NULL; unsigned int val; int ret; + if (type == SHAPER_VFT && test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) + factor = &qm->factor[fun_num]; + ret = readl_relaxed_poll_timeout(qm->io_base + QM_VFT_CFG_RDY, val, val & BIT(0), POLL_PERIOD, POLL_TIMEOUT); @@ -1330,7 +1408,7 @@ static int qm_set_sqc_cqc_vft(struct hisi_qm *qm, u32 fun_num, u32 base, } /* init default shaper qos val */ - if (qm->ver >= QM_HW_V3) { + if (test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) { ret = qm_shaper_init_vft(qm, fun_num); if (ret) goto back_sqc_cqc; @@ -1338,11 +1416,9 @@ static int qm_set_sqc_cqc_vft(struct hisi_qm *qm, u32 fun_num, u32 base, return 0; back_sqc_cqc: - for (i = SQC_VFT; i <= CQC_VFT; i++) { - ret = qm_set_vft_common(qm, i, fun_num, 0, 0); - if (ret) - return ret; - } + for (i = SQC_VFT; i <= CQC_VFT; i++) + qm_set_vft_common(qm, i, fun_num, 0, 0); + return ret; } @@ -1351,7 +1427,7 @@ static int qm_get_vft_v2(struct hisi_qm *qm, u32 *base, u32 *number) u64 sqc_vft; int ret; - ret = qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1); + ret = hisi_qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1); if (ret) return ret; @@ -1647,6 +1723,156 @@ static int qm_regs_show(struct seq_file *s, void *unused) DEFINE_SHOW_ATTRIBUTE(qm_regs); +static struct dfx_diff_registers *dfx_regs_init(struct hisi_qm *qm, + const struct dfx_diff_registers *cregs, int reg_len) +{ + struct dfx_diff_registers *diff_regs; + u32 j, base_offset; + int i; + + diff_regs = kcalloc(reg_len, sizeof(*diff_regs), GFP_KERNEL); + if (!diff_regs) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < reg_len; i++) { + if (!cregs[i].reg_len) + continue; + + diff_regs[i].reg_offset = cregs[i].reg_offset; + diff_regs[i].reg_len = cregs[i].reg_len; + diff_regs[i].regs = kcalloc(QM_DFX_REGS_LEN, cregs[i].reg_len, + GFP_KERNEL); + if (!diff_regs[i].regs) + goto alloc_error; + + for (j = 0; j < diff_regs[i].reg_len; j++) { + base_offset = diff_regs[i].reg_offset + + j * QM_DFX_REGS_LEN; + diff_regs[i].regs[j] = readl(qm->io_base + base_offset); + } + } + + return diff_regs; + +alloc_error: + while (i > 0) { + i--; + kfree(diff_regs[i].regs); + } + kfree(diff_regs); + return ERR_PTR(-ENOMEM); +} + +static void dfx_regs_uninit(struct hisi_qm *qm, + struct dfx_diff_registers *dregs, int reg_len) +{ + int i; + + /* Setting the pointer is NULL to prevent double free */ + for (i = 0; i < reg_len; i++) { + kfree(dregs[i].regs); + dregs[i].regs = NULL; + } + kfree(dregs); + dregs = NULL; +} + +/** + * hisi_qm_diff_regs_init() - Allocate memory for registers. + * @qm: device qm handle. + * @dregs: diff registers handle. + * @reg_len: diff registers region length. + */ +int hisi_qm_diff_regs_init(struct hisi_qm *qm, + struct dfx_diff_registers *dregs, int reg_len) +{ + if (!qm || !dregs || reg_len <= 0) + return -EINVAL; + + if (qm->fun_type != QM_HW_PF) + return 0; + + qm->debug.qm_diff_regs = dfx_regs_init(qm, qm_diff_regs, + ARRAY_SIZE(qm_diff_regs)); + if (IS_ERR(qm->debug.qm_diff_regs)) + return PTR_ERR(qm->debug.qm_diff_regs); + + qm->debug.acc_diff_regs = dfx_regs_init(qm, dregs, reg_len); + if (IS_ERR(qm->debug.acc_diff_regs)) { + dfx_regs_uninit(qm, qm->debug.qm_diff_regs, + ARRAY_SIZE(qm_diff_regs)); + return PTR_ERR(qm->debug.acc_diff_regs); + } + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_diff_regs_init); + +/** + * hisi_qm_diff_regs_uninit() - Free memory for registers. + * @qm: device qm handle. + * @reg_len: diff registers region length. + */ +void hisi_qm_diff_regs_uninit(struct hisi_qm *qm, int reg_len) +{ + if (!qm || reg_len <= 0 || qm->fun_type != QM_HW_PF) + return; + + dfx_regs_uninit(qm, qm->debug.acc_diff_regs, reg_len); + dfx_regs_uninit(qm, qm->debug.qm_diff_regs, ARRAY_SIZE(qm_diff_regs)); +} +EXPORT_SYMBOL_GPL(hisi_qm_diff_regs_uninit); + +/** + * hisi_qm_acc_diff_regs_dump() - Dump registers's value. + * @qm: device qm handle. + * @s: Debugfs file handle. + * @dregs: diff registers handle. + * @regs_len: diff registers region length. + */ +void hisi_qm_acc_diff_regs_dump(struct hisi_qm *qm, struct seq_file *s, + struct dfx_diff_registers *dregs, int regs_len) +{ + u32 j, val, base_offset; + int i, ret; + + if (!qm || !s || !dregs || regs_len <= 0) + return; + + ret = hisi_qm_get_dfx_access(qm); + if (ret) + return; + + down_read(&qm->qps_lock); + for (i = 0; i < regs_len; i++) { + if (!dregs[i].reg_len) + continue; + + for (j = 0; j < dregs[i].reg_len; j++) { + base_offset = dregs[i].reg_offset + j * QM_DFX_REGS_LEN; + val = readl(qm->io_base + base_offset); + if (val != dregs[i].regs[j]) + seq_printf(s, "0x%08x = 0x%08x ---> 0x%08x\n", + base_offset, dregs[i].regs[j], val); + } + } + up_read(&qm->qps_lock); + + hisi_qm_put_dfx_access(qm); +} +EXPORT_SYMBOL_GPL(hisi_qm_acc_diff_regs_dump); + +static int qm_diff_regs_show(struct seq_file *s, void *unused) +{ + struct hisi_qm *qm = s->private; + + hisi_qm_acc_diff_regs_dump(qm, s, qm->debug.qm_diff_regs, + ARRAY_SIZE(qm_diff_regs)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(qm_diff_regs); + static ssize_t qm_cmd_read(struct file *filp, char __user *buffer, size_t count, loff_t *pos) { @@ -1688,49 +1914,29 @@ static void qm_ctx_free(struct hisi_qm *qm, size_t ctx_size, kfree(ctx_addr); } -static int dump_show(struct hisi_qm *qm, void *info, +static void dump_show(struct hisi_qm *qm, void *info, unsigned int info_size, char *info_name) { struct device *dev = &qm->pdev->dev; - u8 *info_buf, *info_curr = info; + u8 *info_curr = info; u32 i; #define BYTE_PER_DW 4 - info_buf = kzalloc(info_size, GFP_KERNEL); - if (!info_buf) - return -ENOMEM; - - for (i = 0; i < info_size; i++, info_curr++) { - if (i % BYTE_PER_DW == 0) - info_buf[i + 3UL] = *info_curr; - else if (i % BYTE_PER_DW == 1) - info_buf[i + 1UL] = *info_curr; - else if (i % BYTE_PER_DW == 2) - info_buf[i - 1] = *info_curr; - else if (i % BYTE_PER_DW == 3) - info_buf[i - 3] = *info_curr; - } - dev_info(dev, "%s DUMP\n", info_name); - for (i = 0; i < info_size; i += BYTE_PER_DW) { + for (i = 0; i < info_size; i += BYTE_PER_DW, info_curr += BYTE_PER_DW) { pr_info("DW%u: %02X%02X %02X%02X\n", i / BYTE_PER_DW, - info_buf[i], info_buf[i + 1UL], - info_buf[i + 2UL], info_buf[i + 3UL]); + *(info_curr + 3), *(info_curr + 2), *(info_curr + 1), *(info_curr)); } - - kfree(info_buf); - - return 0; } static int qm_dump_sqc_raw(struct hisi_qm *qm, dma_addr_t dma_addr, u16 qp_id) { - return qm_mb(qm, QM_MB_CMD_SQC, dma_addr, qp_id, 1); + return hisi_qm_mb(qm, QM_MB_CMD_SQC, dma_addr, qp_id, 1); } static int qm_dump_cqc_raw(struct hisi_qm *qm, dma_addr_t dma_addr, u16 qp_id) { - return qm_mb(qm, QM_MB_CMD_CQC, dma_addr, qp_id, 1); + return hisi_qm_mb(qm, QM_MB_CMD_CQC, dma_addr, qp_id, 1); } static int qm_sqc_dump(struct hisi_qm *qm, const char *s) @@ -1760,23 +1966,18 @@ static int qm_sqc_dump(struct hisi_qm *qm, const char *s) if (qm->sqc) { sqc_curr = qm->sqc + qp_id; - ret = dump_show(qm, sqc_curr, sizeof(*sqc), - "SOFT SQC"); - if (ret) - dev_info(dev, "Show soft sqc failed!\n"); + dump_show(qm, sqc_curr, sizeof(*sqc), "SOFT SQC"); } up_read(&qm->qps_lock); - goto err_free_ctx; + goto free_ctx; } - ret = dump_show(qm, sqc, sizeof(*sqc), "SQC"); - if (ret) - dev_info(dev, "Show hw sqc failed!\n"); + dump_show(qm, sqc, sizeof(*sqc), "SQC"); -err_free_ctx: +free_ctx: qm_ctx_free(qm, sizeof(*sqc), sqc, &sqc_dma); - return ret; + return 0; } static int qm_cqc_dump(struct hisi_qm *qm, const char *s) @@ -1806,23 +2007,18 @@ static int qm_cqc_dump(struct hisi_qm *qm, const char *s) if (qm->cqc) { cqc_curr = qm->cqc + qp_id; - ret = dump_show(qm, cqc_curr, sizeof(*cqc), - "SOFT CQC"); - if (ret) - dev_info(dev, "Show soft cqc failed!\n"); + dump_show(qm, cqc_curr, sizeof(*cqc), "SOFT CQC"); } up_read(&qm->qps_lock); - goto err_free_ctx; + goto free_ctx; } - ret = dump_show(qm, cqc, sizeof(*cqc), "CQC"); - if (ret) - dev_info(dev, "Show hw cqc failed!\n"); + dump_show(qm, cqc, sizeof(*cqc), "CQC"); -err_free_ctx: +free_ctx: qm_ctx_free(qm, sizeof(*cqc), cqc, &cqc_dma); - return ret; + return 0; } static int qm_eqc_aeqc_dump(struct hisi_qm *qm, char *s, size_t size, @@ -1842,13 +2038,11 @@ static int qm_eqc_aeqc_dump(struct hisi_qm *qm, char *s, size_t size, if (IS_ERR(xeqc)) return PTR_ERR(xeqc); - ret = qm_mb(qm, cmd, xeqc_dma, 0, 1); + ret = hisi_qm_mb(qm, cmd, xeqc_dma, 0, 1); if (ret) goto err_free_ctx; - ret = dump_show(qm, xeqc, size, name); - if (ret) - dev_info(dev, "Show hw %s failed!\n", name); + dump_show(qm, xeqc, size, name); err_free_ctx: qm_ctx_free(qm, size, xeqc, &xeqc_dma); @@ -1856,7 +2050,7 @@ err_free_ctx: } static int q_dump_param_parse(struct hisi_qm *qm, char *s, - u32 *e_id, u32 *q_id) + u32 *e_id, u32 *q_id, u16 q_depth) { struct device *dev = &qm->pdev->dev; unsigned int qp_num = qm->qp_num; @@ -1882,8 +2076,8 @@ static int q_dump_param_parse(struct hisi_qm *qm, char *s, } ret = kstrtou32(presult, 0, e_id); - if (ret || *e_id >= QM_Q_DEPTH) { - dev_err(dev, "Please input sqe num (0-%d)", QM_Q_DEPTH - 1); + if (ret || *e_id >= q_depth) { + dev_err(dev, "Please input sqe num (0-%u)", q_depth - 1); return -EINVAL; } @@ -1897,54 +2091,49 @@ static int q_dump_param_parse(struct hisi_qm *qm, char *s, static int qm_sq_dump(struct hisi_qm *qm, char *s) { - struct device *dev = &qm->pdev->dev; + u16 sq_depth = qm->qp_array->cq_depth; void *sqe, *sqe_curr; struct hisi_qp *qp; u32 qp_id, sqe_id; int ret; - ret = q_dump_param_parse(qm, s, &sqe_id, &qp_id); + ret = q_dump_param_parse(qm, s, &sqe_id, &qp_id, sq_depth); if (ret) return ret; - sqe = kzalloc(qm->sqe_size * QM_Q_DEPTH, GFP_KERNEL); + sqe = kzalloc(qm->sqe_size * sq_depth, GFP_KERNEL); if (!sqe) return -ENOMEM; qp = &qm->qp_array[qp_id]; - memcpy(sqe, qp->sqe, qm->sqe_size * QM_Q_DEPTH); + memcpy(sqe, qp->sqe, qm->sqe_size * sq_depth); sqe_curr = sqe + (u32)(sqe_id * qm->sqe_size); memset(sqe_curr + qm->debug.sqe_mask_offset, QM_SQE_ADDR_MASK, qm->debug.sqe_mask_len); - ret = dump_show(qm, sqe_curr, qm->sqe_size, "SQE"); - if (ret) - dev_info(dev, "Show sqe failed!\n"); + dump_show(qm, sqe_curr, qm->sqe_size, "SQE"); kfree(sqe); - return ret; + return 0; } static int qm_cq_dump(struct hisi_qm *qm, char *s) { - struct device *dev = &qm->pdev->dev; struct qm_cqe *cqe_curr; struct hisi_qp *qp; u32 qp_id, cqe_id; int ret; - ret = q_dump_param_parse(qm, s, &cqe_id, &qp_id); + ret = q_dump_param_parse(qm, s, &cqe_id, &qp_id, qm->qp_array->cq_depth); if (ret) return ret; qp = &qm->qp_array[qp_id]; cqe_curr = qp->cqe + cqe_id; - ret = dump_show(qm, cqe_curr, sizeof(struct qm_cqe), "CQE"); - if (ret) - dev_info(dev, "Show cqe failed!\n"); + dump_show(qm, cqe_curr, sizeof(struct qm_cqe), "CQE"); - return ret; + return 0; } static int qm_eq_aeq_dump(struct hisi_qm *qm, const char *s, @@ -1962,11 +2151,11 @@ static int qm_eq_aeq_dump(struct hisi_qm *qm, const char *s, if (ret) return -EINVAL; - if (!strcmp(name, "EQE") && xeqe_id >= QM_EQ_DEPTH) { - dev_err(dev, "Please input eqe num (0-%d)", QM_EQ_DEPTH - 1); + if (!strcmp(name, "EQE") && xeqe_id >= qm->eq_depth) { + dev_err(dev, "Please input eqe num (0-%u)", qm->eq_depth - 1); return -EINVAL; - } else if (!strcmp(name, "AEQE") && xeqe_id >= QM_Q_DEPTH) { - dev_err(dev, "Please input aeqe num (0-%d)", QM_Q_DEPTH - 1); + } else if (!strcmp(name, "AEQE") && xeqe_id >= qm->aeq_depth) { + dev_err(dev, "Please input aeqe num (0-%u)", qm->eq_depth - 1); return -EINVAL; } @@ -1981,9 +2170,7 @@ static int qm_eq_aeq_dump(struct hisi_qm *qm, const char *s, goto err_unlock; } - ret = dump_show(qm, xeqe, size, name); - if (ret) - dev_info(dev, "Show %s failed!\n", name); + dump_show(qm, xeqe, size, name); err_unlock: up_read(&qm->qps_lock); @@ -2076,8 +2263,10 @@ static ssize_t qm_cmd_write(struct file *filp, const char __user *buffer, return ret; /* Judge if the instance is being reset. */ - if (unlikely(atomic_read(&qm->status.flags) == QM_STOP)) - return 0; + if (unlikely(atomic_read(&qm->status.flags) == QM_STOP)) { + ret = 0; + goto put_dfx_access; + } if (count > QM_DBG_WRITE_LEN) { ret = -ENOSPC; @@ -2131,58 +2320,65 @@ static void qm_create_debugfs_file(struct hisi_qm *qm, struct dentry *dir, file->debug = &qm->debug; } -static void qm_hw_error_init_v1(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe) +static void qm_hw_error_init_v1(struct hisi_qm *qm) { writel(QM_ABNORMAL_INT_MASK_VALUE, qm->io_base + QM_ABNORMAL_INT_MASK); } -static void qm_hw_error_cfg(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe) +static void qm_hw_error_cfg(struct hisi_qm *qm) { - qm->error_mask = ce | nfe | fe; + struct hisi_qm_err_info *err_info = &qm->err_info; + + qm->error_mask = err_info->nfe | err_info->ce | err_info->fe; /* clear QM hw residual error source */ - writel(QM_ABNORMAL_INT_SOURCE_CLR, - qm->io_base + QM_ABNORMAL_INT_SOURCE); + writel(qm->error_mask, qm->io_base + QM_ABNORMAL_INT_SOURCE); /* configure error type */ - writel(ce, qm->io_base + QM_RAS_CE_ENABLE); + writel(err_info->ce, qm->io_base + QM_RAS_CE_ENABLE); writel(QM_RAS_CE_TIMES_PER_IRQ, qm->io_base + QM_RAS_CE_THRESHOLD); - writel(nfe, qm->io_base + QM_RAS_NFE_ENABLE); - writel(fe, qm->io_base + QM_RAS_FE_ENABLE); + writel(err_info->nfe, qm->io_base + QM_RAS_NFE_ENABLE); + writel(err_info->fe, qm->io_base + QM_RAS_FE_ENABLE); } -static void qm_hw_error_init_v2(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe) +static void qm_hw_error_init_v2(struct hisi_qm *qm) { - u32 irq_enable = ce | nfe | fe; - u32 irq_unmask = ~irq_enable; + u32 irq_unmask; - qm_hw_error_cfg(qm, ce, nfe, fe); + qm_hw_error_cfg(qm); + irq_unmask = ~qm->error_mask; irq_unmask &= readl(qm->io_base + QM_ABNORMAL_INT_MASK); writel(irq_unmask, qm->io_base + QM_ABNORMAL_INT_MASK); } static void qm_hw_error_uninit_v2(struct hisi_qm *qm) { - writel(QM_ABNORMAL_INT_MASK_VALUE, qm->io_base + QM_ABNORMAL_INT_MASK); + u32 irq_mask = qm->error_mask; + + irq_mask |= readl(qm->io_base + QM_ABNORMAL_INT_MASK); + writel(irq_mask, qm->io_base + QM_ABNORMAL_INT_MASK); } -static void qm_hw_error_init_v3(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe) +static void qm_hw_error_init_v3(struct hisi_qm *qm) { - u32 irq_enable = ce | nfe | fe; - u32 irq_unmask = ~irq_enable; + u32 irq_unmask; - qm_hw_error_cfg(qm, ce, nfe, fe); + qm_hw_error_cfg(qm); /* enable close master ooo when hardware error happened */ - writel(nfe & (~QM_DB_RANDOM_INVALID), qm->io_base + QM_OOO_SHUTDOWN_SEL); + writel(qm->err_info.qm_shutdown_mask, qm->io_base + QM_OOO_SHUTDOWN_SEL); + irq_unmask = ~qm->error_mask; irq_unmask &= readl(qm->io_base + QM_ABNORMAL_INT_MASK); writel(irq_unmask, qm->io_base + QM_ABNORMAL_INT_MASK); } static void qm_hw_error_uninit_v3(struct hisi_qm *qm) { - writel(QM_ABNORMAL_INT_MASK_VALUE, qm->io_base + QM_ABNORMAL_INT_MASK); + u32 irq_mask = qm->error_mask; + + irq_mask |= readl(qm->io_base + QM_ABNORMAL_INT_MASK); + writel(irq_mask, qm->io_base + QM_ABNORMAL_INT_MASK); /* disable close master ooo when hardware error happened */ writel(0x0, qm->io_base + QM_OOO_SHUTDOWN_SEL); @@ -2227,7 +2423,7 @@ static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status) static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm) { - u32 error_status, tmp, val; + u32 error_status, tmp; /* read err sts */ tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); @@ -2238,17 +2434,11 @@ static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm) qm->err_status.is_qm_ecc_mbit = true; qm_log_hw_error(qm, error_status); - val = error_status | QM_DB_RANDOM_INVALID | QM_BASE_CE; - /* ce error does not need to be reset */ - if (val == (QM_DB_RANDOM_INVALID | QM_BASE_CE)) { - writel(error_status, qm->io_base + - QM_ABNORMAL_INT_SOURCE); - writel(qm->err_info.nfe, - qm->io_base + QM_RAS_NFE_ENABLE); - return ACC_ERR_RECOVERED; - } + if (error_status & qm->err_info.qm_reset_mask) + return ACC_ERR_NEED_RESET; - return ACC_ERR_NEED_RESET; + writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE); + writel(qm->err_info.nfe, qm->io_base + QM_RAS_NFE_ENABLE); } return ACC_ERR_RECOVERED; @@ -2324,7 +2514,7 @@ static int qm_wait_vf_prepare_finish(struct hisi_qm *qm) u64 val; u32 i; - if (!qm->vfs_num || qm->ver < QM_HW_V3) + if (!qm->vfs_num || !test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) return 0; while (true) { @@ -2495,7 +2685,7 @@ unlock: static int qm_stop_qp(struct hisi_qp *qp) { - return qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0); + return hisi_qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0); } static int qm_set_msi(struct hisi_qm *qm, bool set) @@ -2587,7 +2777,6 @@ static int qm_set_msi_v3(struct hisi_qm *qm, bool set) static const struct hisi_qm_hw_ops qm_hw_ops_v1 = { .qm_db = qm_db_v1, - .get_irq_num = qm_get_irq_num_v1, .hw_error_init = qm_hw_error_init_v1, .set_msi = qm_set_msi, }; @@ -2595,7 +2784,6 @@ static const struct hisi_qm_hw_ops qm_hw_ops_v1 = { static const struct hisi_qm_hw_ops qm_hw_ops_v2 = { .get_vft = qm_get_vft_v2, .qm_db = qm_db_v2, - .get_irq_num = qm_get_irq_num_v2, .hw_error_init = qm_hw_error_init_v2, .hw_error_uninit = qm_hw_error_uninit_v2, .hw_error_handle = qm_hw_error_handle_v2, @@ -2605,14 +2793,10 @@ static const struct hisi_qm_hw_ops qm_hw_ops_v2 = { static const struct hisi_qm_hw_ops qm_hw_ops_v3 = { .get_vft = qm_get_vft_v2, .qm_db = qm_db_v2, - .get_irq_num = qm_get_irq_num_v3, .hw_error_init = qm_hw_error_init_v3, .hw_error_uninit = qm_hw_error_uninit_v3, .hw_error_handle = qm_hw_error_handle_v2, - .stop_qp = qm_stop_qp, .set_msi = qm_set_msi_v3, - .ping_all_vfs = qm_ping_all_vfs, - .ping_pf = qm_ping_pf, }; static void *qm_get_avail_sqe(struct hisi_qp *qp) @@ -2620,7 +2804,7 @@ static void *qm_get_avail_sqe(struct hisi_qp *qp) struct hisi_qp_status *qp_status = &qp->qp_status; u16 sq_tail = qp_status->sq_tail; - if (unlikely(atomic_read(&qp->qp_status.used) == QM_Q_DEPTH - 1)) + if (unlikely(atomic_read(&qp->qp_status.used) == qp->sq_depth - 1)) return NULL; return qp->sqe + sq_tail * qp->qm->sqe_size; @@ -2661,7 +2845,7 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type) qp = &qm->qp_array[qp_id]; hisi_qm_unset_hw_reset(qp); - memset(qp->cqe, 0, sizeof(struct qm_cqe) * QM_Q_DEPTH); + memset(qp->cqe, 0, sizeof(struct qm_cqe) * qp->cq_depth); qp->event_cb = NULL; qp->req_cb = NULL; @@ -2682,7 +2866,7 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type) * return created qp, -EBUSY if all qps in qm allocated, -ENOMEM if allocating * qp memory fails. */ -struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type) +static struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type) { struct hisi_qp *qp; int ret; @@ -2700,7 +2884,6 @@ struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type) return qp; } -EXPORT_SYMBOL_GPL(hisi_qm_create_qp); /** * hisi_qm_release_qp() - Release a qp back to its qm. @@ -2708,7 +2891,7 @@ EXPORT_SYMBOL_GPL(hisi_qm_create_qp); * * This function releases the resource of a qp. */ -void hisi_qm_release_qp(struct hisi_qp *qp) +static void hisi_qm_release_qp(struct hisi_qp *qp) { struct hisi_qm *qm = qp->qm; @@ -2726,7 +2909,6 @@ void hisi_qm_release_qp(struct hisi_qp *qp) qm_pm_put_sync(qm); } -EXPORT_SYMBOL_GPL(hisi_qm_release_qp); static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) { @@ -2744,9 +2926,9 @@ static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) INIT_QC_COMMON(sqc, qp->sqe_dma, pasid); if (ver == QM_HW_V1) { sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V1(0, 0, 0, qm->sqe_size)); - sqc->w8 = cpu_to_le16(QM_Q_DEPTH - 1); + sqc->w8 = cpu_to_le16(qp->sq_depth - 1); } else { - sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V2(qm->sqe_size)); + sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V2(qm->sqe_size, qp->sq_depth)); sqc->w8 = 0; /* rand_qc */ } sqc->cq_num = cpu_to_le16(qp_id); @@ -2763,7 +2945,7 @@ static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0); dma_unmap_single(dev, sqc_dma, sizeof(struct qm_sqc), DMA_TO_DEVICE); kfree(sqc); @@ -2787,9 +2969,9 @@ static int qm_cq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) if (ver == QM_HW_V1) { cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V1(0, 0, 0, QM_QC_CQE_SIZE)); - cqc->w8 = cpu_to_le16(QM_Q_DEPTH - 1); + cqc->w8 = cpu_to_le16(qp->cq_depth - 1); } else { - cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V2(QM_QC_CQE_SIZE)); + cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V2(QM_QC_CQE_SIZE, qp->cq_depth)); cqc->w8 = 0; /* rand_qc */ } cqc->dw6 = cpu_to_le32(1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT); @@ -2804,7 +2986,7 @@ static int qm_cq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0); dma_unmap_single(dev, cqc_dma, sizeof(struct qm_cqc), DMA_TO_DEVICE); kfree(cqc); @@ -2876,13 +3058,14 @@ static void qp_stop_fail_cb(struct hisi_qp *qp) { int qp_used = atomic_read(&qp->qp_status.used); u16 cur_tail = qp->qp_status.sq_tail; - u16 cur_head = (cur_tail + QM_Q_DEPTH - qp_used) % QM_Q_DEPTH; + u16 sq_depth = qp->sq_depth; + u16 cur_head = (cur_tail + sq_depth - qp_used) % sq_depth; struct hisi_qm *qm = qp->qm; u16 pos; int i; for (i = 0; i < qp_used; i++) { - pos = (i + cur_head) % QM_Q_DEPTH; + pos = (i + cur_head) % sq_depth; qp->req_cb(qp, qp->sqe + (u32)(qm->sqe_size * pos)); atomic_dec(&qp->qp_status.used); } @@ -2911,8 +3094,8 @@ static int qm_drain_qp(struct hisi_qp *qp) return 0; /* Kunpeng930 supports drain qp by device */ - if (qm->ops->stop_qp) { - ret = qm->ops->stop_qp(qp); + if (test_bit(QM_SUPPORT_STOP_QP, &qm->caps)) { + ret = qm_stop_qp(qp); if (ret) dev_err(dev, "Failed to stop qp(%u)!\n", qp->qp_id); return ret; @@ -2983,11 +3166,8 @@ static int qm_stop_qp_nolock(struct hisi_qp *qp) if (ret) dev_err(dev, "Failed to drain out data for stopping!\n"); - if (qp->qm->wq) - flush_workqueue(qp->qm->wq); - else - flush_work(&qp->qm->work); + flush_workqueue(qp->qm->wq); if (unlikely(qp->is_resetting && atomic_read(&qp->qp_status.used))) qp_stop_fail_cb(qp); @@ -3033,7 +3213,7 @@ int hisi_qp_send(struct hisi_qp *qp, const void *msg) { struct hisi_qp_status *qp_status = &qp->qp_status; u16 sq_tail = qp_status->sq_tail; - u16 sq_tail_next = (sq_tail + 1) % QM_Q_DEPTH; + u16 sq_tail_next = (sq_tail + 1) % qp->sq_depth; void *sqe = qm_get_avail_sqe(qp); if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP || @@ -3075,9 +3255,17 @@ static void qm_qp_event_notifier(struct hisi_qp *qp) wake_up_interruptible(&qp->uacce_q->wait); } + /* This function returns free number of qp in qm. */ static int hisi_qm_get_available_instances(struct uacce_device *uacce) { - return hisi_qm_get_free_qp_num(uacce->priv); + struct hisi_qm *qm = uacce->priv; + int ret; + + down_read(&qm->qps_lock); + ret = qm->qp_num - qm->qp_in_used; + up_read(&qm->qps_lock); + + return ret; } static void hisi_qm_set_hw_reset(struct hisi_qm *qm, int offset) @@ -3114,7 +3302,6 @@ static void hisi_qm_uacce_put_queue(struct uacce_queue *q) { struct hisi_qp *qp = q->priv; - hisi_qm_cache_wb(qp->qm); hisi_qm_release_qp(qp); } @@ -3138,7 +3325,7 @@ static int hisi_qm_uacce_mmap(struct uacce_queue *q, if (qm->ver == QM_HW_V1) { if (sz > PAGE_SIZE * QM_DOORBELL_PAGE_NR) return -EINVAL; - } else if (qm->ver == QM_HW_V2 || !qm->use_db_isolation) { + } else if (!test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) { if (sz > PAGE_SIZE * (QM_DOORBELL_PAGE_NR + QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE)) return -EINVAL; @@ -3215,6 +3402,7 @@ static long hisi_qm_uacce_ioctl(struct uacce_queue *q, unsigned int cmd, unsigned long arg) { struct hisi_qp *qp = q->priv; + struct hisi_qp_info qp_info; struct hisi_qp_ctx qp_ctx; if (cmd == UACCE_CMD_QM_SET_QP_CTX) { @@ -3231,11 +3419,25 @@ static long hisi_qm_uacce_ioctl(struct uacce_queue *q, unsigned int cmd, if (copy_to_user((void __user *)arg, &qp_ctx, sizeof(struct hisi_qp_ctx))) return -EFAULT; - } else { - return -EINVAL; + + return 0; + } else if (cmd == UACCE_CMD_QM_SET_QP_INFO) { + if (copy_from_user(&qp_info, (void __user *)arg, + sizeof(struct hisi_qp_info))) + return -EFAULT; + + qp_info.sqe_size = qp->qm->sqe_size; + qp_info.sq_depth = qp->sq_depth; + qp_info.cq_depth = qp->cq_depth; + + if (copy_to_user((void __user *)arg, &qp_info, + sizeof(struct hisi_qp_info))) + return -EFAULT; + + return 0; } - return 0; + return -EINVAL; } static const struct uacce_ops uacce_qm_ops = { @@ -3255,6 +3457,7 @@ static int qm_alloc_uacce(struct hisi_qm *qm) struct uacce_device *uacce; unsigned long mmio_page_nr; unsigned long dus_page_nr; + u16 sq_depth, cq_depth; struct uacce_interface interface = { .flags = UACCE_DEV_SVA, .ops = &uacce_qm_ops, @@ -3281,7 +3484,6 @@ static int qm_alloc_uacce(struct hisi_qm *qm) uacce->is_vf = pdev->is_virtfn; uacce->priv = qm; - uacce->algs = qm->algs; if (qm->ver == QM_HW_V1) uacce->api_ver = HISI_QM_API_VER_BASE; @@ -3292,15 +3494,17 @@ static int qm_alloc_uacce(struct hisi_qm *qm) if (qm->ver == QM_HW_V1) mmio_page_nr = QM_DOORBELL_PAGE_NR; - else if (qm->ver == QM_HW_V2 || !qm->use_db_isolation) + else if (!test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) mmio_page_nr = QM_DOORBELL_PAGE_NR + QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE; else mmio_page_nr = qm->db_interval / PAGE_SIZE; + qm_get_xqc_depth(qm, &sq_depth, &cq_depth, QM_QP_DEPTH_CAP); + /* Add one more page for device or qp status */ - dus_page_nr = (PAGE_SIZE - 1 + qm->sqe_size * QM_Q_DEPTH + - sizeof(struct qm_cqe) * QM_Q_DEPTH + PAGE_SIZE) >> + dus_page_nr = (PAGE_SIZE - 1 + qm->sqe_size * sq_depth + + sizeof(struct qm_cqe) * cq_depth + PAGE_SIZE) >> PAGE_SHIFT; uacce->qf_pg_num[UACCE_QFRT_MMIO] = mmio_page_nr; @@ -3389,24 +3593,6 @@ void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list) } EXPORT_SYMBOL_GPL(hisi_qm_wait_task_finish); -/** - * hisi_qm_get_free_qp_num() - Get free number of qp in qm. - * @qm: The qm which want to get free qp. - * - * This function return free number of qp in qm. - */ -int hisi_qm_get_free_qp_num(struct hisi_qm *qm) -{ - int ret; - - down_read(&qm->qps_lock); - ret = qm->qp_num - qm->qp_in_used; - up_read(&qm->qps_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(hisi_qm_get_free_qp_num); - static void hisi_qp_memory_uninit(struct hisi_qm *qm, int num) { struct device *dev = &qm->pdev->dev; @@ -3416,32 +3602,47 @@ static void hisi_qp_memory_uninit(struct hisi_qm *qm, int num) for (i = num - 1; i >= 0; i--) { qdma = &qm->qp_array[i].qdma; dma_free_coherent(dev, qdma->size, qdma->va, qdma->dma); + kfree(qm->poll_data[i].qp_finish_id); } + kfree(qm->poll_data); kfree(qm->qp_array); } -static int hisi_qp_memory_init(struct hisi_qm *qm, size_t dma_size, int id) +static int hisi_qp_memory_init(struct hisi_qm *qm, size_t dma_size, int id, + u16 sq_depth, u16 cq_depth) { struct device *dev = &qm->pdev->dev; - size_t off = qm->sqe_size * QM_Q_DEPTH; + size_t off = qm->sqe_size * sq_depth; struct hisi_qp *qp; + int ret = -ENOMEM; + + qm->poll_data[id].qp_finish_id = kcalloc(qm->qp_num, sizeof(u16), + GFP_KERNEL); + if (!qm->poll_data[id].qp_finish_id) + return -ENOMEM; qp = &qm->qp_array[id]; qp->qdma.va = dma_alloc_coherent(dev, dma_size, &qp->qdma.dma, GFP_KERNEL); if (!qp->qdma.va) - return -ENOMEM; + goto err_free_qp_finish_id; qp->sqe = qp->qdma.va; qp->sqe_dma = qp->qdma.dma; qp->cqe = qp->qdma.va + off; qp->cqe_dma = qp->qdma.dma + off; qp->qdma.size = dma_size; + qp->sq_depth = sq_depth; + qp->cq_depth = cq_depth; qp->qm = qm; qp->qp_id = id; return 0; + +err_free_qp_finish_id: + kfree(qm->poll_data[id].qp_finish_id); + return ret; } static void hisi_qm_pre_init(struct hisi_qm *qm) @@ -3460,7 +3661,7 @@ static void hisi_qm_pre_init(struct hisi_qm *qm) init_rwsem(&qm->qps_lock); qm->qp_in_used = 0; qm->misc_ctl = false; - if (qm->fun_type == QM_HW_PF && qm->ver > QM_HW_V2) { + if (test_bit(QM_SUPPORT_RPM, &qm->caps)) { if (!acpi_device_power_manageable(ACPI_COMPANION(&pdev->dev))) dev_info(&pdev->dev, "_PS0 and _PR0 are not defined"); } @@ -3470,7 +3671,7 @@ static void qm_cmd_uninit(struct hisi_qm *qm) { u32 val; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) return; val = readl(qm->io_base + QM_IFC_INT_MASK); @@ -3482,7 +3683,7 @@ static void qm_cmd_init(struct hisi_qm *qm) { u32 val; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) return; /* Clear communication interrupt source */ @@ -3498,7 +3699,7 @@ static void qm_put_pci_res(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; - if (qm->use_db_isolation) + if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) iounmap(qm->db_io_base); iounmap(qm->io_base); @@ -3514,6 +3715,45 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) pci_disable_device(pdev); } +static void hisi_qm_set_state(struct hisi_qm *qm, u8 state) +{ + if (qm->ver > QM_HW_V2 && qm->fun_type == QM_HW_VF) + writel(state, qm->io_base + QM_VF_STATE); +} + +static void qm_last_regs_uninit(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + + if (qm->fun_type == QM_HW_VF || !debug->qm_last_words) + return; + + kfree(debug->qm_last_words); + debug->qm_last_words = NULL; +} + +static void hisi_qm_unint_work(struct hisi_qm *qm) +{ + destroy_workqueue(qm->wq); +} + +static void hisi_qm_memory_uninit(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + + hisi_qp_memory_uninit(qm, qm->qp_num); + if (qm->qdma.va) { + hisi_qm_cache_wb(qm); + dma_free_coherent(dev, qm->qdma.size, + qm->qdma.va, qm->qdma.dma); + } + + idr_destroy(&qm->qp_idr); + + if (test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) + kfree(qm->factor); +} + /** * hisi_qm_uninit() - Uninitialize qm. * @qm: The qm needed uninit. @@ -3522,11 +3762,10 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) */ void hisi_qm_uninit(struct hisi_qm *qm) { - struct pci_dev *pdev = qm->pdev; - struct device *dev = &pdev->dev; + qm_last_regs_uninit(qm); qm_cmd_uninit(qm); - kfree(qm->factor); + hisi_qm_unint_work(qm); down_write(&qm->qps_lock); if (!qm_avail_state(qm, QM_CLOSE)) { @@ -3534,17 +3773,11 @@ void hisi_qm_uninit(struct hisi_qm *qm) return; } - hisi_qp_memory_uninit(qm, qm->qp_num); - idr_destroy(&qm->qp_idr); - - if (qm->qdma.va) { - hisi_qm_cache_wb(qm); - dma_free_coherent(dev, qm->qdma.size, - qm->qdma.va, qm->qdma.dma); - } + hisi_qm_memory_uninit(qm); + hisi_qm_set_state(qm, QM_NOT_READY); up_write(&qm->qps_lock); - qm_irq_unregister(qm); + qm_irqs_unregister(qm); hisi_qm_pci_uninit(qm); if (qm->use_sva) { uacce_remove(qm->uacce); @@ -3565,7 +3798,7 @@ EXPORT_SYMBOL_GPL(hisi_qm_uninit); * * qm hw v1 does not support this interface. */ -int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number) +static int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number) { if (!base || !number) return -EINVAL; @@ -3577,7 +3810,6 @@ int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number) return qm->ops->get_vft(qm, base, number); } -EXPORT_SYMBOL_GPL(hisi_qm_get_vft); /** * hisi_qm_set_vft() - Set vft to a qm. @@ -3646,7 +3878,7 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm) eqc->base_h = cpu_to_le32(upper_32_bits(qm->eqe_dma)); if (qm->ver == QM_HW_V1) eqc->dw3 = cpu_to_le32(QM_EQE_AEQE_SIZE); - eqc->dw6 = cpu_to_le32((QM_EQ_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT)); + eqc->dw6 = cpu_to_le32(((u32)qm->eq_depth - 1) | (1 << QM_EQC_PHASE_SHIFT)); eqc_dma = dma_map_single(dev, eqc, sizeof(struct qm_eqc), DMA_TO_DEVICE); @@ -3655,7 +3887,7 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0); dma_unmap_single(dev, eqc_dma, sizeof(struct qm_eqc), DMA_TO_DEVICE); kfree(eqc); @@ -3675,7 +3907,7 @@ static int qm_aeq_ctx_cfg(struct hisi_qm *qm) aeqc->base_l = cpu_to_le32(lower_32_bits(qm->aeqe_dma)); aeqc->base_h = cpu_to_le32(upper_32_bits(qm->aeqe_dma)); - aeqc->dw6 = cpu_to_le32((QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT)); + aeqc->dw6 = cpu_to_le32(((u32)qm->aeq_depth - 1) | (1 << QM_EQC_PHASE_SHIFT)); aeqc_dma = dma_map_single(dev, aeqc, sizeof(struct qm_aeqc), DMA_TO_DEVICE); @@ -3684,7 +3916,7 @@ static int qm_aeq_ctx_cfg(struct hisi_qm *qm) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0); dma_unmap_single(dev, aeqc_dma, sizeof(struct qm_aeqc), DMA_TO_DEVICE); kfree(aeqc); @@ -3723,11 +3955,11 @@ static int __hisi_qm_start(struct hisi_qm *qm) if (ret) return ret; - ret = qm_mb(qm, QM_MB_CMD_SQC_BT, qm->sqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_SQC_BT, qm->sqc_dma, 0, 0); if (ret) return ret; - ret = qm_mb(qm, QM_MB_CMD_CQC_BT, qm->cqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_CQC_BT, qm->cqc_dma, 0, 0); if (ret) return ret; @@ -3767,6 +3999,7 @@ int hisi_qm_start(struct hisi_qm *qm) if (!ret) atomic_set(&qm->status.flags, QM_START); + hisi_qm_set_state(qm, QM_READY); err_unlock: up_write(&qm->qps_lock); return ret; @@ -3840,7 +4073,7 @@ static void qm_clear_queues(struct hisi_qm *qm) for (i = 0; i < qm->qp_num; i++) { qp = &qm->qp_array[i]; - if (qp->is_resetting) + if (qp->is_in_kernel && qp->is_resetting) memset(qp->qdma.va, 0, qp->qdma.size); } @@ -3940,14 +4173,12 @@ DEFINE_DEBUGFS_ATTRIBUTE(qm_atomic64_ops, qm_debugfs_atomic64_get, static void qm_hw_error_init(struct hisi_qm *qm) { - struct hisi_qm_err_info *err_info = &qm->err_info; - if (!qm->ops->hw_error_init) { dev_err(&qm->pdev->dev, "QM doesn't support hw error handling!\n"); return; } - qm->ops->hw_error_init(qm, err_info->ce, err_info->nfe, err_info->fe); + qm->ops->hw_error_init(qm); } static void qm_hw_error_uninit(struct hisi_qm *qm) @@ -4295,18 +4526,16 @@ static void qm_vf_get_qos(struct hisi_qm *qm, u32 fun_num) static int qm_vf_read_qos(struct hisi_qm *qm) { int cnt = 0; - int ret; + int ret = -EINVAL; /* reset mailbox qos val */ qm->mb_qos = 0; /* vf ping pf to get function qos */ - if (qm->ops->ping_pf) { - ret = qm->ops->ping_pf(qm, QM_VF_GET_QOS); - if (ret) { - pci_err(qm->pdev, "failed to send cmd to PF to get qos!\n"); - return ret; - } + ret = qm_ping_pf(qm, QM_VF_GET_QOS); + if (ret) { + pci_err(qm->pdev, "failed to send cmd to PF to get qos!\n"); + return ret; } while (true) { @@ -4478,14 +4707,14 @@ static const struct file_operations qm_algqos_fops = { * hisi_qm_set_algqos_init() - Initialize function qos debugfs files. * @qm: The qm for which we want to add debugfs files. * - * Create function qos debugfs files. + * Create function qos debugfs files, VF ping PF to get function qos. */ static void hisi_qm_set_algqos_init(struct hisi_qm *qm) { if (qm->fun_type == QM_HW_PF) debugfs_create_file("alg_qos", 0644, qm->debug.debug_root, qm, &qm_algqos_fops); - else + else if (test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) debugfs_create_file("alg_qos", 0444, qm->debug.debug_root, qm, &qm_algqos_fops); } @@ -4498,6 +4727,7 @@ static void hisi_qm_set_algqos_init(struct hisi_qm *qm) */ void hisi_qm_debug_init(struct hisi_qm *qm) { + struct dfx_diff_registers *qm_regs = qm->debug.qm_diff_regs; struct qm_dfx *dfx = &qm->debug.dfx; struct dentry *qm_d; void *data; @@ -4513,6 +4743,10 @@ void hisi_qm_debug_init(struct hisi_qm *qm) qm_create_debugfs_file(qm, qm->debug.qm_d, i); } + if (qm_regs) + debugfs_create_file("diff_regs", 0444, qm->debug.qm_d, + qm, &qm_diff_regs_fops); + debugfs_create_file("regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops); debugfs_create_file("cmd", 0600, qm->debug.qm_d, qm, &qm_cmd_fops); @@ -4528,7 +4762,7 @@ void hisi_qm_debug_init(struct hisi_qm *qm) &qm_atomic64_ops); } - if (qm->ver >= QM_HW_V3) + if (test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) hisi_qm_set_algqos_init(qm); } EXPORT_SYMBOL_GPL(hisi_qm_debug_init); @@ -4567,6 +4801,14 @@ void hisi_qm_debug_regs_clear(struct hisi_qm *qm) } EXPORT_SYMBOL_GPL(hisi_qm_debug_regs_clear); +static void hisi_qm_init_vf_qos(struct hisi_qm *qm, int total_func) +{ + int i; + + for (i = 1; i <= total_func; i++) + qm->factor[i].func_qos = QM_QOS_MAX_VAL; +} + /** * hisi_qm_sriov_enable() - enable virtual functions * @pdev: the PCIe device @@ -4593,7 +4835,17 @@ int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs) goto err_put_sync; } - num_vfs = min_t(int, max_vfs, total_vfs); + if (max_vfs > total_vfs) { + pci_err(pdev, "%d VFs is more than total VFs %d!\n", max_vfs, total_vfs); + ret = -ERANGE; + goto err_put_sync; + } + + num_vfs = max_vfs; + + if (test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) + hisi_qm_init_vf_qos(qm, num_vfs); + ret = qm_vf_q_assign(qm, num_vfs); if (ret) { pci_err(pdev, "Can't assign queues for VF!\n"); @@ -4629,7 +4881,6 @@ EXPORT_SYMBOL_GPL(hisi_qm_sriov_enable); int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen) { struct hisi_qm *qm = pci_get_drvdata(pdev); - int total_vfs = pci_sriov_get_totalvfs(qm->pdev); int ret; if (pci_vfs_assigned(pdev)) { @@ -4644,8 +4895,7 @@ int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen) } pci_disable_sriov(pdev); - /* clear vf function shaper configure array */ - memset(qm->factor + 1, 0, sizeof(struct qm_shaper_factor) * total_vfs); + ret = qm_clear_vft_config(qm); if (ret) return ret; @@ -4690,17 +4940,11 @@ static enum acc_err_result qm_dev_err_handle(struct hisi_qm *qm) if (qm->err_ini->log_dev_hw_err) qm->err_ini->log_dev_hw_err(qm, err_sts); - /* ce error does not need to be reset */ - if ((err_sts | qm->err_info.dev_ce_mask) == - qm->err_info.dev_ce_mask) { - if (qm->err_ini->clear_dev_hw_err_status) - qm->err_ini->clear_dev_hw_err_status(qm, - err_sts); - - return ACC_ERR_RECOVERED; - } + if (err_sts & qm->err_info.dev_reset_mask) + return ACC_ERR_NEED_RESET; - return ACC_ERR_NEED_RESET; + if (qm->err_ini->clear_dev_hw_err_status) + qm->err_ini->clear_dev_hw_err_status(qm, err_sts); } return ACC_ERR_RECOVERED; @@ -4869,8 +5113,8 @@ static int qm_try_stop_vfs(struct hisi_qm *qm, u64 cmd, return 0; /* Kunpeng930 supports to notify VFs to stop before PF reset */ - if (qm->ops->ping_all_vfs) { - ret = qm->ops->ping_all_vfs(qm, cmd); + if (test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) { + ret = qm_ping_all_vfs(qm, cmd); if (ret) pci_err(pdev, "failed to send cmd to all VFs before PF reset!\n"); } else { @@ -5061,8 +5305,8 @@ static int qm_try_start_vfs(struct hisi_qm *qm, enum qm_mb_cmd cmd) } /* Kunpeng930 supports to notify VFs to start after PF reset. */ - if (qm->ops->ping_all_vfs) { - ret = qm->ops->ping_all_vfs(qm, cmd); + if (test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) { + ret = qm_ping_all_vfs(qm, cmd); if (ret) pci_warn(pdev, "failed to send cmd to all VFs after PF reset!\n"); } else { @@ -5195,6 +5439,24 @@ static int qm_controller_reset_done(struct hisi_qm *qm) return 0; } +static void qm_show_last_dfx_regs(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + struct pci_dev *pdev = qm->pdev; + u32 val; + int i; + + if (qm->fun_type == QM_HW_VF || !debug->qm_last_words) + return; + + for (i = 0; i < ARRAY_SIZE(qm_dfx_regs); i++) { + val = readl_relaxed(qm->io_base + qm_dfx_regs[i].offset); + if (debug->qm_last_words[i] != val) + pci_info(pdev, "%s \t= 0x%08x => 0x%08x\n", + qm_dfx_regs[i].name, debug->qm_last_words[i], val); + } +} + static int qm_controller_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -5210,6 +5472,10 @@ static int qm_controller_reset(struct hisi_qm *qm) return ret; } + qm_show_last_dfx_regs(qm); + if (qm->err_ini->show_last_dfx_regs) + qm->err_ini->show_last_dfx_regs(qm); + ret = qm_soft_reset(qm); if (ret) { pci_err(pdev, "Controller reset failed (%d)\n", ret); @@ -5243,8 +5509,6 @@ pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev) if (pdev->is_virtfn) return PCI_ERS_RESULT_RECOVERED; - pci_aer_clear_nonfatal_status(pdev); - /* reset pcie device controller */ ret = qm_controller_reset(qm); if (ret) { @@ -5376,51 +5640,6 @@ static irqreturn_t qm_abnormal_irq(int irq, void *data) return IRQ_HANDLED; } -static int qm_irq_register(struct hisi_qm *qm) -{ - struct pci_dev *pdev = qm->pdev; - int ret; - - ret = request_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), - qm_irq, 0, qm->dev_name, qm); - if (ret) - return ret; - - if (qm->ver > QM_HW_V1) { - ret = request_threaded_irq(pci_irq_vector(pdev, - QM_AEQ_EVENT_IRQ_VECTOR), - qm_aeq_irq, qm_aeq_thread, - 0, qm->dev_name, qm); - if (ret) - goto err_aeq_irq; - - if (qm->fun_type == QM_HW_PF) { - ret = request_irq(pci_irq_vector(pdev, - QM_ABNORMAL_EVENT_IRQ_VECTOR), - qm_abnormal_irq, 0, qm->dev_name, qm); - if (ret) - goto err_abonormal_irq; - } - } - - if (qm->ver > QM_HW_V2) { - ret = request_irq(pci_irq_vector(pdev, QM_CMD_EVENT_IRQ_VECTOR), - qm_mb_cmd_irq, 0, qm->dev_name, qm); - if (ret) - goto err_mb_cmd_irq; - } - - return 0; - -err_mb_cmd_irq: - if (qm->fun_type == QM_HW_PF) - free_irq(pci_irq_vector(pdev, QM_ABNORMAL_EVENT_IRQ_VECTOR), qm); -err_abonormal_irq: - free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm); -err_aeq_irq: - free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm); - return ret; -} /** * hisi_qm_dev_shutdown() - Shutdown device. @@ -5488,7 +5707,7 @@ err_prepare: hisi_qm_set_hw_reset(qm, QM_RESET_STOP_RX_OFFSET); out: pci_save_state(pdev); - ret = qm->ops->ping_pf(qm, cmd); + ret = qm_ping_pf(qm, cmd); if (ret) dev_warn(&pdev->dev, "PF responds timeout in reset prepare!\n"); } @@ -5506,7 +5725,7 @@ static void qm_pf_reset_vf_done(struct hisi_qm *qm) cmd = QM_VF_START_FAIL; } - ret = qm->ops->ping_pf(qm, cmd); + ret = qm_ping_pf(qm, cmd); if (ret) dev_warn(&pdev->dev, "PF responds timeout in reset done!\n"); @@ -5701,21 +5920,193 @@ void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list) } EXPORT_SYMBOL_GPL(hisi_qm_alg_unregister); +static void qm_unregister_abnormal_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + + if (qm->fun_type == QM_HW_VF) + return; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK)) + return; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + free_irq(pci_irq_vector(pdev, irq_vector), qm); +} + +static int qm_register_abnormal_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + int ret; + + if (qm->fun_type == QM_HW_VF) + return 0; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK)) + return 0; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + ret = request_irq(pci_irq_vector(pdev, irq_vector), qm_abnormal_irq, 0, qm->dev_name, qm); + if (ret) + dev_err(&qm->pdev->dev, "failed to request abnormal irq, ret = %d", ret); + + return ret; +} + +static void qm_unregister_mb_cmd_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) + return; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + free_irq(pci_irq_vector(pdev, irq_vector), qm); +} + +static int qm_register_mb_cmd_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + int ret; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) + return 0; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + ret = request_irq(pci_irq_vector(pdev, irq_vector), qm_mb_cmd_irq, 0, qm->dev_name, qm); + if (ret) + dev_err(&pdev->dev, "failed to request function communication irq, ret = %d", ret); + + return ret; +} + +static void qm_unregister_aeq_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) + return; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + free_irq(pci_irq_vector(pdev, irq_vector), qm); +} + +static int qm_register_aeq_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + int ret; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) + return 0; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + ret = request_threaded_irq(pci_irq_vector(pdev, irq_vector), qm_aeq_irq, + qm_aeq_thread, 0, qm->dev_name, qm); + if (ret) + dev_err(&pdev->dev, "failed to request eq irq, ret = %d", ret); + + return ret; +} + +static void qm_unregister_eq_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) + return; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + free_irq(pci_irq_vector(pdev, irq_vector), qm); +} + +static int qm_register_eq_irq(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 irq_vector, val; + int ret; + + val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver); + if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) + return 0; + + irq_vector = val & QM_IRQ_VECTOR_MASK; + ret = request_irq(pci_irq_vector(pdev, irq_vector), qm_irq, 0, qm->dev_name, qm); + if (ret) + dev_err(&pdev->dev, "failed to request eq irq, ret = %d", ret); + + return ret; +} + +static void qm_irqs_unregister(struct hisi_qm *qm) +{ + qm_unregister_mb_cmd_irq(qm); + qm_unregister_abnormal_irq(qm); + qm_unregister_aeq_irq(qm); + qm_unregister_eq_irq(qm); +} + +static int qm_irqs_register(struct hisi_qm *qm) +{ + int ret; + + ret = qm_register_eq_irq(qm); + if (ret) + return ret; + + ret = qm_register_aeq_irq(qm); + if (ret) + goto free_eq_irq; + + ret = qm_register_abnormal_irq(qm); + if (ret) + goto free_aeq_irq; + + ret = qm_register_mb_cmd_irq(qm); + if (ret) + goto free_abnormal_irq; + + return 0; + +free_abnormal_irq: + qm_unregister_abnormal_irq(qm); +free_aeq_irq: + qm_unregister_aeq_irq(qm); +free_eq_irq: + qm_unregister_eq_irq(qm); + return ret; +} + static int qm_get_qp_num(struct hisi_qm *qm) { - if (qm->ver == QM_HW_V1) - qm->ctrl_qp_num = QM_QNUM_V1; - else if (qm->ver == QM_HW_V2) - qm->ctrl_qp_num = QM_QNUM_V2; - else - qm->ctrl_qp_num = readl(qm->io_base + QM_CAPBILITY) & - QM_QP_NUN_MASK; + bool is_db_isolation; - if (qm->use_db_isolation) - qm->max_qp_num = (readl(qm->io_base + QM_CAPBILITY) >> - QM_QP_MAX_NUM_SHIFT) & QM_QP_NUN_MASK; - else - qm->max_qp_num = qm->ctrl_qp_num; + /* VF's qp_num assigned by PF in v2, and VF can get qp_num by vft. */ + if (qm->fun_type == QM_HW_VF) { + if (qm->ver != QM_HW_V1) + /* v2 starts to support get vft by mailbox */ + return hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num); + + return 0; + } + + is_db_isolation = test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps); + qm->ctrl_qp_num = hisi_qm_get_hw_info(qm, qm_basic_info, QM_TOTAL_QP_NUM_CAP, true); + qm->max_qp_num = hisi_qm_get_hw_info(qm, qm_basic_info, + QM_FUNC_MAX_QP_CAP, is_db_isolation); /* check if qp number is valid */ if (qm->qp_num > qm->max_qp_num) { @@ -5727,6 +6118,39 @@ static int qm_get_qp_num(struct hisi_qm *qm) return 0; } +static void qm_get_hw_caps(struct hisi_qm *qm) +{ + const struct hisi_qm_cap_info *cap_info = qm->fun_type == QM_HW_PF ? + qm_cap_info_pf : qm_cap_info_vf; + u32 size = qm->fun_type == QM_HW_PF ? ARRAY_SIZE(qm_cap_info_pf) : + ARRAY_SIZE(qm_cap_info_vf); + u32 val, i; + + /* Doorbell isolate register is a independent register. */ + val = hisi_qm_get_hw_info(qm, qm_cap_info_comm, QM_SUPPORT_DB_ISOLATION, true); + if (val) + set_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps); + + if (qm->ver >= QM_HW_V3) { + val = readl(qm->io_base + QM_FUNC_CAPS_REG); + qm->cap_ver = val & QM_CAPBILITY_VERSION; + } + + /* Get PF/VF common capbility */ + for (i = 1; i < ARRAY_SIZE(qm_cap_info_comm); i++) { + val = hisi_qm_get_hw_info(qm, qm_cap_info_comm, i, qm->cap_ver); + if (val) + set_bit(qm_cap_info_comm[i].type, &qm->caps); + } + + /* Get PF/VF different capbility */ + for (i = 0; i < size; i++) { + val = hisi_qm_get_hw_info(qm, cap_info, i, qm->cap_ver); + if (val) + set_bit(cap_info[i].type, &qm->caps); + } +} + static int qm_get_pci_res(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -5746,16 +6170,8 @@ static int qm_get_pci_res(struct hisi_qm *qm) goto err_request_mem_regions; } - if (qm->ver > QM_HW_V2) { - if (qm->fun_type == QM_HW_PF) - qm->use_db_isolation = readl(qm->io_base + - QM_QUE_ISO_EN) & BIT(0); - else - qm->use_db_isolation = readl(qm->io_base + - QM_QUE_ISO_CFG_V) & BIT(0); - } - - if (qm->use_db_isolation) { + qm_get_hw_caps(qm); + if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) { qm->db_interval = QM_QP_DB_INTERVAL; qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4); qm->db_io_base = ioremap(qm->db_phys_base, @@ -5770,16 +6186,14 @@ static int qm_get_pci_res(struct hisi_qm *qm) qm->db_interval = 0; } - if (qm->fun_type == QM_HW_PF) { - ret = qm_get_qp_num(qm); - if (ret) - goto err_db_ioremap; - } + ret = qm_get_qp_num(qm); + if (ret) + goto err_db_ioremap; return 0; err_db_ioremap: - if (qm->use_db_isolation) + if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) iounmap(qm->db_io_base); err_ioremap: iounmap(qm->io_base); @@ -5810,11 +6224,7 @@ static int hisi_qm_pci_init(struct hisi_qm *qm) goto err_get_pci_res; pci_set_master(pdev); - if (!qm->ops->get_irq_num) { - ret = -EOPNOTSUPP; - goto err_get_pci_res; - } - num_vec = qm->ops->get_irq_num(qm); + num_vec = qm_get_irq_num(qm); ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI); if (ret < 0) { dev_err(dev, "Failed to enable MSI vectors!\n"); @@ -5830,19 +6240,34 @@ err_disable_pcidev: return ret; } -static void hisi_qm_init_work(struct hisi_qm *qm) +static int hisi_qm_init_work(struct hisi_qm *qm) { - INIT_WORK(&qm->work, qm_work_process); + int i; + + for (i = 0; i < qm->qp_num; i++) + INIT_WORK(&qm->poll_data[i].work, qm_work_process); + if (qm->fun_type == QM_HW_PF) INIT_WORK(&qm->rst_work, hisi_qm_controller_reset); if (qm->ver > QM_HW_V2) INIT_WORK(&qm->cmd_process, qm_cmd_process); + + qm->wq = alloc_workqueue("%s", WQ_HIGHPRI | WQ_MEM_RECLAIM | + WQ_UNBOUND, num_online_cpus(), + pci_name(qm->pdev)); + if (!qm->wq) { + pci_err(qm->pdev, "failed to alloc workqueue!\n"); + return -ENOMEM; + } + + return 0; } static int hisi_qp_alloc_memory(struct hisi_qm *qm) { struct device *dev = &qm->pdev->dev; + u16 sq_depth, cq_depth; size_t qp_dma_size; int i, ret; @@ -5850,12 +6275,20 @@ static int hisi_qp_alloc_memory(struct hisi_qm *qm) if (!qm->qp_array) return -ENOMEM; + qm->poll_data = kcalloc(qm->qp_num, sizeof(struct hisi_qm_poll_data), GFP_KERNEL); + if (!qm->poll_data) { + kfree(qm->qp_array); + return -ENOMEM; + } + + qm_get_xqc_depth(qm, &sq_depth, &cq_depth, QM_QP_DEPTH_CAP); + /* one more page for device or qp statuses */ - qp_dma_size = qm->sqe_size * QM_Q_DEPTH + - sizeof(struct qm_cqe) * QM_Q_DEPTH; + qp_dma_size = qm->sqe_size * sq_depth + sizeof(struct qm_cqe) * cq_depth; qp_dma_size = PAGE_ALIGN(qp_dma_size) + PAGE_SIZE; for (i = 0; i < qm->qp_num; i++) { - ret = hisi_qp_memory_init(qm, qp_dma_size, i); + qm->poll_data[i].qm = qm; + ret = hisi_qp_memory_init(qm, qp_dma_size, i, sq_depth, cq_depth); if (ret) goto err_init_qp_mem; @@ -5872,15 +6305,18 @@ err_init_qp_mem: static int hisi_qm_memory_init(struct hisi_qm *qm) { struct device *dev = &qm->pdev->dev; - int ret, total_func, i; + int ret, total_func; size_t off = 0; - total_func = pci_sriov_get_totalvfs(qm->pdev) + 1; - qm->factor = kcalloc(total_func, sizeof(struct qm_shaper_factor), GFP_KERNEL); - if (!qm->factor) - return -ENOMEM; - for (i = 0; i < total_func; i++) - qm->factor[i].func_qos = QM_QOS_MAX_VAL; + if (test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) { + total_func = pci_sriov_get_totalvfs(qm->pdev) + 1; + qm->factor = kcalloc(total_func, sizeof(struct qm_shaper_factor), GFP_KERNEL); + if (!qm->factor) + return -ENOMEM; + + /* Only the PF value needs to be initialized */ + qm->factor[0].func_qos = QM_QOS_MAX_VAL; + } #define QM_INIT_BUF(qm, type, num) do { \ (qm)->type = ((qm)->qdma.va + (off)); \ @@ -5889,20 +6325,21 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) } while (0) idr_init(&qm->qp_idr); - qm->qdma.size = QMC_ALIGN(sizeof(struct qm_eqe) * QM_EQ_DEPTH) + - QMC_ALIGN(sizeof(struct qm_aeqe) * QM_Q_DEPTH) + + qm_get_xqc_depth(qm, &qm->eq_depth, &qm->aeq_depth, QM_XEQ_DEPTH_CAP); + qm->qdma.size = QMC_ALIGN(sizeof(struct qm_eqe) * qm->eq_depth) + + QMC_ALIGN(sizeof(struct qm_aeqe) * qm->aeq_depth) + QMC_ALIGN(sizeof(struct qm_sqc) * qm->qp_num) + QMC_ALIGN(sizeof(struct qm_cqc) * qm->qp_num); qm->qdma.va = dma_alloc_coherent(dev, qm->qdma.size, &qm->qdma.dma, GFP_ATOMIC); dev_dbg(dev, "allocate qm dma buf size=%zx)\n", qm->qdma.size); if (!qm->qdma.va) { - ret = -ENOMEM; - goto err_alloc_qdma; + ret = -ENOMEM; + goto err_destroy_idr; } - QM_INIT_BUF(qm, eqe, QM_EQ_DEPTH); - QM_INIT_BUF(qm, aeqe, QM_Q_DEPTH); + QM_INIT_BUF(qm, eqe, qm->eq_depth); + QM_INIT_BUF(qm, aeqe, qm->aeq_depth); QM_INIT_BUF(qm, sqc, qm->qp_num); QM_INIT_BUF(qm, cqc, qm->qp_num); @@ -5914,12 +6351,34 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) err_alloc_qp_array: dma_free_coherent(dev, qm->qdma.size, qm->qdma.va, qm->qdma.dma); -err_alloc_qdma: - kfree(qm->factor); +err_destroy_idr: + idr_destroy(&qm->qp_idr); + if (test_bit(QM_SUPPORT_FUNC_QOS, &qm->caps)) + kfree(qm->factor); return ret; } +static void qm_last_regs_init(struct hisi_qm *qm) +{ + int dfx_regs_num = ARRAY_SIZE(qm_dfx_regs); + struct qm_debug *debug = &qm->debug; + int i; + + if (qm->fun_type == QM_HW_VF) + return; + + debug->qm_last_words = kcalloc(dfx_regs_num, sizeof(unsigned int), + GFP_KERNEL); + if (!debug->qm_last_words) + return; + + for (i = 0; i < dfx_regs_num; i++) { + debug->qm_last_words[i] = readl_relaxed(qm->io_base + + qm_dfx_regs[i].offset); + } +} + /** * hisi_qm_init() - Initialize configures about qm. * @qm: The qm needing init. @@ -5938,17 +6397,10 @@ int hisi_qm_init(struct hisi_qm *qm) if (ret) return ret; - ret = qm_irq_register(qm); + ret = qm_irqs_register(qm); if (ret) goto err_pci_init; - if (qm->fun_type == QM_HW_VF && qm->ver != QM_HW_V1) { - /* v2 starts to support get vft by mailbox */ - ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num); - if (ret) - goto err_irq_register; - } - if (qm->fun_type == QM_HW_PF) { qm_disable_clock_gate(qm); ret = qm_dev_mem_reset(qm); @@ -5968,19 +6420,26 @@ int hisi_qm_init(struct hisi_qm *qm) if (ret) goto err_alloc_uacce; - hisi_qm_init_work(qm); + ret = hisi_qm_init_work(qm); + if (ret) + goto err_free_qm_memory; + qm_cmd_init(qm); atomic_set(&qm->status.flags, QM_INIT); + qm_last_regs_init(qm); + return 0; +err_free_qm_memory: + hisi_qm_memory_uninit(qm); err_alloc_uacce: if (qm->use_sva) { uacce_remove(qm->uacce); qm->uacce = NULL; } err_irq_register: - qm_irq_unregister(qm); + qm_irqs_unregister(qm); err_pci_init: hisi_qm_pci_uninit(qm); return ret; @@ -6031,7 +6490,7 @@ void hisi_qm_pm_init(struct hisi_qm *qm) { struct device *dev = &qm->pdev->dev; - if (qm->fun_type == QM_HW_VF || qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_RPM, &qm->caps)) return; pm_runtime_set_autosuspend_delay(dev, QM_AUTOSUSPEND_DELAY); @@ -6050,7 +6509,7 @@ void hisi_qm_pm_uninit(struct hisi_qm *qm) { struct device *dev = &qm->pdev->dev; - if (qm->fun_type == QM_HW_VF || qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_RPM, &qm->caps)) return; pm_runtime_get_noresume(dev); diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h deleted file mode 100644 index 3068093229a5..000000000000 --- a/drivers/crypto/hisilicon/qm.h +++ /dev/null @@ -1,441 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2019 HiSilicon Limited. */ -#ifndef HISI_ACC_QM_H -#define HISI_ACC_QM_H - -#include <linux/bitfield.h> -#include <linux/debugfs.h> -#include <linux/iopoll.h> -#include <linux/module.h> -#include <linux/pci.h> - -#define QM_QNUM_V1 4096 -#define QM_QNUM_V2 1024 -#define QM_MAX_VFS_NUM_V2 63 - -/* qm user domain */ -#define QM_ARUSER_M_CFG_1 0x100088 -#define AXUSER_SNOOP_ENABLE BIT(30) -#define AXUSER_CMD_TYPE GENMASK(14, 12) -#define AXUSER_CMD_SMMU_NORMAL 1 -#define AXUSER_NS BIT(6) -#define AXUSER_NO BIT(5) -#define AXUSER_FP BIT(4) -#define AXUSER_SSV BIT(0) -#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ - FIELD_PREP(AXUSER_CMD_TYPE, \ - AXUSER_CMD_SMMU_NORMAL) | \ - AXUSER_NS | AXUSER_NO | AXUSER_FP) -#define QM_ARUSER_M_CFG_ENABLE 0x100090 -#define ARUSER_M_CFG_ENABLE 0xfffffffe -#define QM_AWUSER_M_CFG_1 0x100098 -#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 -#define AWUSER_M_CFG_ENABLE 0xfffffffe -#define QM_WUSER_M_CFG_ENABLE 0x1000a8 -#define WUSER_M_CFG_ENABLE 0xffffffff - -/* qm cache */ -#define QM_CACHE_CTL 0x100050 -#define SQC_CACHE_ENABLE BIT(0) -#define CQC_CACHE_ENABLE BIT(1) -#define SQC_CACHE_WB_ENABLE BIT(4) -#define SQC_CACHE_WB_THRD GENMASK(10, 5) -#define CQC_CACHE_WB_ENABLE BIT(11) -#define CQC_CACHE_WB_THRD GENMASK(17, 12) -#define QM_AXI_M_CFG 0x1000ac -#define AXI_M_CFG 0xffff -#define QM_AXI_M_CFG_ENABLE 0x1000b0 -#define AM_CFG_SINGLE_PORT_MAX_TRANS 0x300014 -#define AXI_M_CFG_ENABLE 0xffffffff -#define QM_PEH_AXUSER_CFG 0x1000cc -#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 -#define PEH_AXUSER_CFG 0x401001 -#define PEH_AXUSER_CFG_ENABLE 0xffffffff - -#define QM_AXI_RRESP BIT(0) -#define QM_AXI_BRESP BIT(1) -#define QM_ECC_MBIT BIT(2) -#define QM_ECC_1BIT BIT(3) -#define QM_ACC_GET_TASK_TIMEOUT BIT(4) -#define QM_ACC_DO_TASK_TIMEOUT BIT(5) -#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) -#define QM_SQ_CQ_VF_INVALID BIT(7) -#define QM_CQ_VF_INVALID BIT(8) -#define QM_SQ_VF_INVALID BIT(9) -#define QM_DB_TIMEOUT BIT(10) -#define QM_OF_FIFO_OF BIT(11) -#define QM_DB_RANDOM_INVALID BIT(12) -#define QM_MAILBOX_TIMEOUT BIT(13) -#define QM_FLR_TIMEOUT BIT(14) - -#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ - QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ - QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ - QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) -#define QM_BASE_CE QM_ECC_1BIT - -#define QM_Q_DEPTH 1024 -#define QM_MIN_QNUM 2 -#define HISI_ACC_SGL_SGE_NR_MAX 255 -#define QM_SHAPER_CFG 0x100164 -#define QM_SHAPER_ENABLE BIT(30) -#define QM_SHAPER_TYPE1_OFFSET 10 - -/* page number for queue file region */ -#define QM_DOORBELL_PAGE_NR 1 - -/* uacce mode of the driver */ -#define UACCE_MODE_NOUACCE 0 /* don't use uacce */ -#define UACCE_MODE_SVA 1 /* use uacce sva mode */ -#define UACCE_MODE_DESC "0(default) means only register to crypto, 1 means both register to crypto and uacce" - -enum qm_stop_reason { - QM_NORMAL, - QM_SOFT_RESET, - QM_FLR, -}; - -enum qm_state { - QM_INIT = 0, - QM_START, - QM_CLOSE, - QM_STOP, -}; - -enum qp_state { - QP_INIT = 1, - QP_START, - QP_STOP, - QP_CLOSE, -}; - -enum qm_hw_ver { - QM_HW_UNKNOWN = -1, - QM_HW_V1 = 0x20, - QM_HW_V2 = 0x21, - QM_HW_V3 = 0x30, -}; - -enum qm_fun_type { - QM_HW_PF, - QM_HW_VF, -}; - -enum qm_debug_file { - CURRENT_QM, - CURRENT_Q, - CLEAR_ENABLE, - DEBUG_FILE_NUM, -}; - -struct qm_dfx { - atomic64_t err_irq_cnt; - atomic64_t aeq_irq_cnt; - atomic64_t abnormal_irq_cnt; - atomic64_t create_qp_err_cnt; - atomic64_t mb_err_cnt; -}; - -struct debugfs_file { - enum qm_debug_file index; - struct mutex lock; - struct qm_debug *debug; -}; - -struct qm_debug { - u32 curr_qm_qp_num; - u32 sqe_mask_offset; - u32 sqe_mask_len; - struct qm_dfx dfx; - struct dentry *debug_root; - struct dentry *qm_d; - struct debugfs_file files[DEBUG_FILE_NUM]; -}; - -struct qm_shaper_factor { - u32 func_qos; - u64 cir_b; - u64 cir_u; - u64 cir_s; - u64 cbs_s; -}; - -struct qm_dma { - void *va; - dma_addr_t dma; - size_t size; -}; - -struct hisi_qm_status { - u32 eq_head; - bool eqc_phase; - u32 aeq_head; - bool aeqc_phase; - atomic_t flags; - int stop_reason; -}; - -struct hisi_qm; - -struct hisi_qm_err_info { - char *acpi_rst; - u32 msi_wr_port; - u32 ecc_2bits_mask; - u32 dev_ce_mask; - u32 ce; - u32 nfe; - u32 fe; -}; - -struct hisi_qm_err_status { - u32 is_qm_ecc_mbit; - u32 is_dev_ecc_mbit; -}; - -struct hisi_qm_err_ini { - int (*hw_init)(struct hisi_qm *qm); - void (*hw_err_enable)(struct hisi_qm *qm); - void (*hw_err_disable)(struct hisi_qm *qm); - u32 (*get_dev_hw_err_status)(struct hisi_qm *qm); - void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts); - void (*open_axi_master_ooo)(struct hisi_qm *qm); - void (*close_axi_master_ooo)(struct hisi_qm *qm); - void (*open_sva_prefetch)(struct hisi_qm *qm); - void (*close_sva_prefetch)(struct hisi_qm *qm); - void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); - void (*err_info_init)(struct hisi_qm *qm); -}; - -struct hisi_qm_list { - struct mutex lock; - struct list_head list; - int (*register_to_crypto)(struct hisi_qm *qm); - void (*unregister_from_crypto)(struct hisi_qm *qm); -}; - -struct hisi_qm { - enum qm_hw_ver ver; - enum qm_fun_type fun_type; - const char *dev_name; - struct pci_dev *pdev; - void __iomem *io_base; - void __iomem *db_io_base; - u32 sqe_size; - u32 qp_base; - u32 qp_num; - u32 qp_in_used; - u32 ctrl_qp_num; - u32 max_qp_num; - u32 vfs_num; - u32 db_interval; - struct list_head list; - struct hisi_qm_list *qm_list; - - struct qm_dma qdma; - struct qm_sqc *sqc; - struct qm_cqc *cqc; - struct qm_eqe *eqe; - struct qm_aeqe *aeqe; - dma_addr_t sqc_dma; - dma_addr_t cqc_dma; - dma_addr_t eqe_dma; - dma_addr_t aeqe_dma; - - struct hisi_qm_status status; - const struct hisi_qm_err_ini *err_ini; - struct hisi_qm_err_info err_info; - struct hisi_qm_err_status err_status; - unsigned long misc_ctl; /* driver removing and reset sched */ - - struct rw_semaphore qps_lock; - struct idr qp_idr; - struct hisi_qp *qp_array; - - struct mutex mailbox_lock; - - const struct hisi_qm_hw_ops *ops; - - struct qm_debug debug; - - u32 error_mask; - - struct workqueue_struct *wq; - struct work_struct work; - struct work_struct rst_work; - struct work_struct cmd_process; - - const char *algs; - bool use_sva; - bool is_frozen; - - /* doorbell isolation enable */ - bool use_db_isolation; - resource_size_t phys_base; - resource_size_t db_phys_base; - struct uacce_device *uacce; - int mode; - struct qm_shaper_factor *factor; - u32 mb_qos; - u32 type_rate; -}; - -struct hisi_qp_status { - atomic_t used; - u16 sq_tail; - u16 cq_head; - bool cqc_phase; - atomic_t flags; -}; - -struct hisi_qp_ops { - int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); -}; - -struct hisi_qp { - u32 qp_id; - u8 alg_type; - u8 req_type; - - struct qm_dma qdma; - void *sqe; - struct qm_cqe *cqe; - dma_addr_t sqe_dma; - dma_addr_t cqe_dma; - - struct hisi_qp_status qp_status; - struct hisi_qp_ops *hw_ops; - void *qp_ctx; - void (*req_cb)(struct hisi_qp *qp, void *data); - void (*event_cb)(struct hisi_qp *qp); - - struct hisi_qm *qm; - bool is_resetting; - bool is_in_kernel; - u16 pasid; - struct uacce_queue *uacce_q; -}; - -static inline int q_num_set(const char *val, const struct kernel_param *kp, - unsigned int device) -{ - struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, - device, NULL); - u32 n, q_num; - int ret; - - if (!val) - return -EINVAL; - - if (!pdev) { - q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); - pr_info("No device found currently, suppose queue number is %u\n", - q_num); - } else { - if (pdev->revision == QM_HW_V1) - q_num = QM_QNUM_V1; - else - q_num = QM_QNUM_V2; - } - - ret = kstrtou32(val, 10, &n); - if (ret || n < QM_MIN_QNUM || n > q_num) - return -EINVAL; - - return param_set_int(val, kp); -} - -static inline int vfs_num_set(const char *val, const struct kernel_param *kp) -{ - u32 n; - int ret; - - if (!val) - return -EINVAL; - - ret = kstrtou32(val, 10, &n); - if (ret < 0) - return ret; - - if (n > QM_MAX_VFS_NUM_V2) - return -EINVAL; - - return param_set_int(val, kp); -} - -static inline int mode_set(const char *val, const struct kernel_param *kp) -{ - u32 n; - int ret; - - if (!val) - return -EINVAL; - - ret = kstrtou32(val, 10, &n); - if (ret != 0 || (n != UACCE_MODE_SVA && - n != UACCE_MODE_NOUACCE)) - return -EINVAL; - - return param_set_int(val, kp); -} - -static inline int uacce_mode_set(const char *val, const struct kernel_param *kp) -{ - return mode_set(val, kp); -} - -static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list) -{ - INIT_LIST_HEAD(&qm_list->list); - mutex_init(&qm_list->lock); -} - -int hisi_qm_init(struct hisi_qm *qm); -void hisi_qm_uninit(struct hisi_qm *qm); -int hisi_qm_start(struct hisi_qm *qm); -int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); -struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); -int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); -int hisi_qm_stop_qp(struct hisi_qp *qp); -void hisi_qm_release_qp(struct hisi_qp *qp); -int hisi_qp_send(struct hisi_qp *qp, const void *msg); -int hisi_qm_get_free_qp_num(struct hisi_qm *qm); -int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); -void hisi_qm_debug_init(struct hisi_qm *qm); -enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); -void hisi_qm_debug_regs_clear(struct hisi_qm *qm); -int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); -int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); -int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); -void hisi_qm_dev_err_init(struct hisi_qm *qm); -void hisi_qm_dev_err_uninit(struct hisi_qm *qm); -pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, - pci_channel_state_t state); -pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); -void hisi_qm_reset_prepare(struct pci_dev *pdev); -void hisi_qm_reset_done(struct pci_dev *pdev); - -struct hisi_acc_sgl_pool; -struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, - struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, - u32 index, dma_addr_t *hw_sgl_dma); -void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, - struct hisi_acc_hw_sgl *hw_sgl); -struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, - u32 count, u32 sge_nr); -void hisi_acc_free_sgl_pool(struct device *dev, - struct hisi_acc_sgl_pool *pool); -int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, - u8 alg_type, int node, struct hisi_qp **qps); -void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); -void hisi_qm_dev_shutdown(struct pci_dev *pdev); -void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); -int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list); -void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list); -int hisi_qm_resume(struct device *dev); -int hisi_qm_suspend(struct device *dev); -void hisi_qm_pm_uninit(struct hisi_qm *qm); -void hisi_qm_pm_init(struct hisi_qm *qm); -int hisi_qm_get_dfx_access(struct hisi_qm *qm); -void hisi_qm_put_dfx_access(struct hisi_qm *qm); -void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); -#endif diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c index 0a3c8f019b02..490e1542305e 100644 --- a/drivers/crypto/hisilicon/sec/sec_algs.c +++ b/drivers/crypto/hisilicon/sec/sec_algs.c @@ -449,7 +449,7 @@ static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp, */ } - mutex_lock(&ctx->queue->queuelock); + spin_lock_bh(&ctx->queue->queuelock); /* Put the IV in place for chained cases */ switch (ctx->cipher_alg) { case SEC_C_AES_CBC_128: @@ -509,7 +509,7 @@ static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp, list_del(&backlog_req->backlog_head); } } - mutex_unlock(&ctx->queue->queuelock); + spin_unlock_bh(&ctx->queue->queuelock); mutex_lock(&sec_req->lock); list_del(&sec_req_el->head); @@ -798,7 +798,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, */ /* Grab a big lock for a long time to avoid concurrency issues */ - mutex_lock(&queue->queuelock); + spin_lock_bh(&queue->queuelock); /* * Can go on to queue if we have space in either: @@ -814,15 +814,15 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, ret = -EBUSY; if ((skreq->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) { list_add_tail(&sec_req->backlog_head, &ctx->backlog); - mutex_unlock(&queue->queuelock); + spin_unlock_bh(&queue->queuelock); goto out; } - mutex_unlock(&queue->queuelock); + spin_unlock_bh(&queue->queuelock); goto err_free_elements; } ret = sec_send_request(sec_req, queue); - mutex_unlock(&queue->queuelock); + spin_unlock_bh(&queue->queuelock); if (ret) goto err_free_elements; @@ -881,7 +881,7 @@ static int sec_alg_skcipher_init(struct crypto_skcipher *tfm) if (IS_ERR(ctx->queue)) return PTR_ERR(ctx->queue); - mutex_init(&ctx->queue->queuelock); + spin_lock_init(&ctx->queue->queuelock); ctx->queue->havesoftqueue = false; return 0; diff --git a/drivers/crypto/hisilicon/sec/sec_drv.c b/drivers/crypto/hisilicon/sec/sec_drv.c index c8de1b51c843..e75851326c1e 100644 --- a/drivers/crypto/hisilicon/sec/sec_drv.c +++ b/drivers/crypto/hisilicon/sec/sec_drv.c @@ -892,7 +892,7 @@ bool sec_queue_can_enqueue(struct sec_queue *queue, int num) static void sec_queue_hw_init(struct sec_queue *queue) { sec_queue_ar_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC); - sec_queue_aw_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC); + sec_queue_aw_alloc(queue, SEC_QUEUE_AW_FROCE_NOALLOC); sec_queue_ar_pkgattr(queue, 1); sec_queue_aw_pkgattr(queue, 1); diff --git a/drivers/crypto/hisilicon/sec/sec_drv.h b/drivers/crypto/hisilicon/sec/sec_drv.h index 179a8250d691..e2a50bf2234b 100644 --- a/drivers/crypto/hisilicon/sec/sec_drv.h +++ b/drivers/crypto/hisilicon/sec/sec_drv.h @@ -347,7 +347,7 @@ struct sec_queue { DECLARE_BITMAP(unprocessed, SEC_QUEUE_LEN); DECLARE_KFIFO_PTR(softqueue, typeof(struct sec_request_el *)); bool havesoftqueue; - struct mutex queuelock; + spinlock_t queuelock; void *shadow[SEC_QUEUE_LEN]; }; diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index d97cf02b1df7..3e57fc04b377 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -4,7 +4,7 @@ #ifndef __HISI_SEC_V2_H #define __HISI_SEC_V2_H -#include "../qm.h" +#include <linux/hisi_acc_qm.h> #include "sec_crypto.h" /* Algorithm resource per hardware SEC queue */ @@ -17,6 +17,7 @@ struct sec_alg_res { dma_addr_t a_ivin_dma; u8 *out_mac; dma_addr_t out_mac_dma; + u16 depth; }; /* Cipher request of SEC private */ @@ -115,11 +116,11 @@ struct sec_cipher_ctx { /* SEC queue context which defines queue's relatives */ struct sec_qp_ctx { struct hisi_qp *qp; - struct sec_req *req_list[QM_Q_DEPTH]; + struct sec_req **req_list; struct idr req_idr; - struct sec_alg_res res[QM_Q_DEPTH]; + struct sec_alg_res *res; struct sec_ctx *ctx; - struct mutex req_lock; + spinlock_t req_lock; struct list_head backlog; struct hisi_acc_sgl_pool *c_in_pool; struct hisi_acc_sgl_pool *c_out_pool; @@ -143,10 +144,10 @@ struct sec_ctx { /* Threshold for fake busy, trigger to return -EBUSY to user */ u32 fake_req_limit; - /* Currrent cyclic index to select a queue for encipher */ + /* Current cyclic index to select a queue for encipher */ atomic_t enc_qcyclic; - /* Currrent cyclic index to select a queue for decipher */ + /* Current cyclic index to select a queue for decipher */ atomic_t dec_qcyclic; enum sec_alg_type alg_type; @@ -191,8 +192,37 @@ struct sec_dev { bool iommu_used; }; +enum sec_cap_type { + SEC_QM_NFE_MASK_CAP = 0x0, + SEC_QM_RESET_MASK_CAP, + SEC_QM_OOO_SHUTDOWN_MASK_CAP, + SEC_QM_CE_MASK_CAP, + SEC_NFE_MASK_CAP, + SEC_RESET_MASK_CAP, + SEC_OOO_SHUTDOWN_MASK_CAP, + SEC_CE_MASK_CAP, + SEC_CLUSTER_NUM_CAP, + SEC_CORE_TYPE_NUM_CAP, + SEC_CORE_NUM_CAP, + SEC_CORES_PER_CLUSTER_NUM_CAP, + SEC_CORE_ENABLE_BITMAP, + SEC_DRV_ALG_BITMAP_LOW, + SEC_DRV_ALG_BITMAP_HIGH, + SEC_DEV_ALG_BITMAP_LOW, + SEC_DEV_ALG_BITMAP_HIGH, + SEC_CORE1_ALG_BITMAP_LOW, + SEC_CORE1_ALG_BITMAP_HIGH, + SEC_CORE2_ALG_BITMAP_LOW, + SEC_CORE2_ALG_BITMAP_HIGH, + SEC_CORE3_ALG_BITMAP_LOW, + SEC_CORE3_ALG_BITMAP_HIGH, + SEC_CORE4_ALG_BITMAP_LOW, + SEC_CORE4_ALG_BITMAP_HIGH, +}; + void sec_destroy_qps(struct hisi_qp **qps, int qp_num); struct hisi_qp **sec_create_qps(void); int sec_register_to_crypto(struct hisi_qm *qm); void sec_unregister_from_crypto(struct hisi_qm *qm); +u64 sec_get_alg_bitmap(struct hisi_qm *qm, u32 high, u32 low); #endif diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 6a45bd23b363..84ae8ddd1a13 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -42,6 +42,8 @@ #define SEC_DE_OFFSET_V3 9 #define SEC_SCENE_OFFSET_V3 5 #define SEC_CKEY_OFFSET_V3 13 +#define SEC_CTR_CNT_OFFSET 25 +#define SEC_CTR_CNT_ROLLOVER 2 #define SEC_SRC_SGL_OFFSET_V3 11 #define SEC_DST_SGL_OFFSET_V3 14 #define SEC_CALG_OFFSET_V3 4 @@ -57,13 +59,14 @@ #define SEC_ICV_MASK 0x000E #define SEC_SQE_LEN_RATE_MASK 0x3 -#define SEC_TOTAL_IV_SZ (SEC_IV_SIZE * QM_Q_DEPTH) +#define SEC_TOTAL_IV_SZ(depth) (SEC_IV_SIZE * (depth)) #define SEC_SGL_SGE_NR 128 #define SEC_CIPHER_AUTH 0xfe #define SEC_AUTH_CIPHER 0x1 #define SEC_MAX_MAC_LEN 64 #define SEC_MAX_AAD_LEN 65535 -#define SEC_TOTAL_MAC_SZ (SEC_MAX_MAC_LEN * QM_Q_DEPTH) +#define SEC_MAX_CCM_AAD_LEN 65279 +#define SEC_TOTAL_MAC_SZ(depth) (SEC_MAX_MAC_LEN * (depth)) #define SEC_PBUF_SZ 512 #define SEC_PBUF_IV_OFFSET SEC_PBUF_SZ @@ -71,11 +74,11 @@ #define SEC_PBUF_PKG (SEC_PBUF_SZ + SEC_IV_SIZE + \ SEC_MAX_MAC_LEN * 2) #define SEC_PBUF_NUM (PAGE_SIZE / SEC_PBUF_PKG) -#define SEC_PBUF_PAGE_NUM (QM_Q_DEPTH / SEC_PBUF_NUM) -#define SEC_PBUF_LEFT_SZ (SEC_PBUF_PKG * (QM_Q_DEPTH - \ - SEC_PBUF_PAGE_NUM * SEC_PBUF_NUM)) -#define SEC_TOTAL_PBUF_SZ (PAGE_SIZE * SEC_PBUF_PAGE_NUM + \ - SEC_PBUF_LEFT_SZ) +#define SEC_PBUF_PAGE_NUM(depth) ((depth) / SEC_PBUF_NUM) +#define SEC_PBUF_LEFT_SZ(depth) (SEC_PBUF_PKG * ((depth) - \ + SEC_PBUF_PAGE_NUM(depth) * SEC_PBUF_NUM)) +#define SEC_TOTAL_PBUF_SZ(depth) (PAGE_SIZE * SEC_PBUF_PAGE_NUM(depth) + \ + SEC_PBUF_LEFT_SZ(depth)) #define SEC_SQE_LEN_RATE 4 #define SEC_SQE_CFLAG 2 @@ -101,6 +104,16 @@ #define IV_CTR_INIT 0x1 #define IV_BYTE_OFFSET 0x8 +struct sec_skcipher { + u64 alg_msk; + struct skcipher_alg alg; +}; + +struct sec_aead { + u64 alg_msk; + struct aead_alg alg; +}; + /* Get an en/de-cipher queue cyclically to balance load over queues of TFM */ static inline int sec_alloc_queue_id(struct sec_ctx *ctx, struct sec_req *req) { @@ -124,11 +137,9 @@ static int sec_alloc_req_id(struct sec_req *req, struct sec_qp_ctx *qp_ctx) { int req_id; - mutex_lock(&qp_ctx->req_lock); - - req_id = idr_alloc_cyclic(&qp_ctx->req_idr, NULL, - 0, QM_Q_DEPTH, GFP_ATOMIC); - mutex_unlock(&qp_ctx->req_lock); + spin_lock_bh(&qp_ctx->req_lock); + req_id = idr_alloc_cyclic(&qp_ctx->req_idr, NULL, 0, qp_ctx->qp->sq_depth, GFP_ATOMIC); + spin_unlock_bh(&qp_ctx->req_lock); if (unlikely(req_id < 0)) { dev_err(req->ctx->dev, "alloc req id fail!\n"); return req_id; @@ -145,7 +156,7 @@ static void sec_free_req_id(struct sec_req *req) struct sec_qp_ctx *qp_ctx = req->qp_ctx; int req_id = req->req_id; - if (unlikely(req_id < 0 || req_id >= QM_Q_DEPTH)) { + if (unlikely(req_id < 0 || req_id >= qp_ctx->qp->sq_depth)) { dev_err(req->ctx->dev, "free request id invalid!\n"); return; } @@ -153,9 +164,9 @@ static void sec_free_req_id(struct sec_req *req) qp_ctx->req_list[req_id] = NULL; req->qp_ctx = NULL; - mutex_lock(&qp_ctx->req_lock); + spin_lock_bh(&qp_ctx->req_lock); idr_remove(&qp_ctx->req_idr, req_id); - mutex_unlock(&qp_ctx->req_lock); + spin_unlock_bh(&qp_ctx->req_lock); } static u8 pre_parse_finished_bd(struct bd_status *status, void *resp) @@ -237,7 +248,7 @@ static void sec_req_cb(struct hisi_qp *qp, void *resp) if (unlikely(type != type_supported)) { atomic64_inc(&dfx->err_bd_cnt); - pr_err("err bd type [%d]\n", type); + pr_err("err bd type [%u]\n", type); return; } @@ -270,7 +281,7 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req) !(req->flag & CRYPTO_TFM_REQ_MAY_BACKLOG)) return -EBUSY; - mutex_lock(&qp_ctx->req_lock); + spin_lock_bh(&qp_ctx->req_lock); ret = hisi_qp_send(qp_ctx->qp, &req->sec_sqe); if (ctx->fake_req_limit <= @@ -278,10 +289,10 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req) list_add_tail(&req->backlog_head, &qp_ctx->backlog); atomic64_inc(&ctx->sec->debug.dfx.send_cnt); atomic64_inc(&ctx->sec->debug.dfx.send_busy_cnt); - mutex_unlock(&qp_ctx->req_lock); + spin_unlock_bh(&qp_ctx->req_lock); return -EBUSY; } - mutex_unlock(&qp_ctx->req_lock); + spin_unlock_bh(&qp_ctx->req_lock); if (unlikely(ret == -EBUSY)) return -ENOBUFS; @@ -297,14 +308,15 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req) /* Get DMA memory resources */ static int sec_alloc_civ_resource(struct device *dev, struct sec_alg_res *res) { + u16 q_depth = res->depth; int i; - res->c_ivin = dma_alloc_coherent(dev, SEC_TOTAL_IV_SZ, + res->c_ivin = dma_alloc_coherent(dev, SEC_TOTAL_IV_SZ(q_depth), &res->c_ivin_dma, GFP_KERNEL); if (!res->c_ivin) return -ENOMEM; - for (i = 1; i < QM_Q_DEPTH; i++) { + for (i = 1; i < q_depth; i++) { res[i].c_ivin_dma = res->c_ivin_dma + i * SEC_IV_SIZE; res[i].c_ivin = res->c_ivin + i * SEC_IV_SIZE; } @@ -315,20 +327,21 @@ static int sec_alloc_civ_resource(struct device *dev, struct sec_alg_res *res) static void sec_free_civ_resource(struct device *dev, struct sec_alg_res *res) { if (res->c_ivin) - dma_free_coherent(dev, SEC_TOTAL_IV_SZ, + dma_free_coherent(dev, SEC_TOTAL_IV_SZ(res->depth), res->c_ivin, res->c_ivin_dma); } static int sec_alloc_aiv_resource(struct device *dev, struct sec_alg_res *res) { + u16 q_depth = res->depth; int i; - res->a_ivin = dma_alloc_coherent(dev, SEC_TOTAL_IV_SZ, + res->a_ivin = dma_alloc_coherent(dev, SEC_TOTAL_IV_SZ(q_depth), &res->a_ivin_dma, GFP_KERNEL); if (!res->a_ivin) return -ENOMEM; - for (i = 1; i < QM_Q_DEPTH; i++) { + for (i = 1; i < q_depth; i++) { res[i].a_ivin_dma = res->a_ivin_dma + i * SEC_IV_SIZE; res[i].a_ivin = res->a_ivin + i * SEC_IV_SIZE; } @@ -339,20 +352,21 @@ static int sec_alloc_aiv_resource(struct device *dev, struct sec_alg_res *res) static void sec_free_aiv_resource(struct device *dev, struct sec_alg_res *res) { if (res->a_ivin) - dma_free_coherent(dev, SEC_TOTAL_IV_SZ, + dma_free_coherent(dev, SEC_TOTAL_IV_SZ(res->depth), res->a_ivin, res->a_ivin_dma); } static int sec_alloc_mac_resource(struct device *dev, struct sec_alg_res *res) { + u16 q_depth = res->depth; int i; - res->out_mac = dma_alloc_coherent(dev, SEC_TOTAL_MAC_SZ << 1, + res->out_mac = dma_alloc_coherent(dev, SEC_TOTAL_MAC_SZ(q_depth) << 1, &res->out_mac_dma, GFP_KERNEL); if (!res->out_mac) return -ENOMEM; - for (i = 1; i < QM_Q_DEPTH; i++) { + for (i = 1; i < q_depth; i++) { res[i].out_mac_dma = res->out_mac_dma + i * (SEC_MAX_MAC_LEN << 1); res[i].out_mac = res->out_mac + i * (SEC_MAX_MAC_LEN << 1); @@ -364,14 +378,14 @@ static int sec_alloc_mac_resource(struct device *dev, struct sec_alg_res *res) static void sec_free_mac_resource(struct device *dev, struct sec_alg_res *res) { if (res->out_mac) - dma_free_coherent(dev, SEC_TOTAL_MAC_SZ << 1, + dma_free_coherent(dev, SEC_TOTAL_MAC_SZ(res->depth) << 1, res->out_mac, res->out_mac_dma); } static void sec_free_pbuf_resource(struct device *dev, struct sec_alg_res *res) { if (res->pbuf) - dma_free_coherent(dev, SEC_TOTAL_PBUF_SZ, + dma_free_coherent(dev, SEC_TOTAL_PBUF_SZ(res->depth), res->pbuf, res->pbuf_dma); } @@ -381,10 +395,12 @@ static void sec_free_pbuf_resource(struct device *dev, struct sec_alg_res *res) */ static int sec_alloc_pbuf_resource(struct device *dev, struct sec_alg_res *res) { + u16 q_depth = res->depth; + int size = SEC_PBUF_PAGE_NUM(q_depth); int pbuf_page_offset; int i, j, k; - res->pbuf = dma_alloc_coherent(dev, SEC_TOTAL_PBUF_SZ, + res->pbuf = dma_alloc_coherent(dev, SEC_TOTAL_PBUF_SZ(q_depth), &res->pbuf_dma, GFP_KERNEL); if (!res->pbuf) return -ENOMEM; @@ -397,11 +413,11 @@ static int sec_alloc_pbuf_resource(struct device *dev, struct sec_alg_res *res) * So we need SEC_PBUF_PAGE_NUM numbers of PAGE * for the SEC_TOTAL_PBUF_SZ */ - for (i = 0; i <= SEC_PBUF_PAGE_NUM; i++) { + for (i = 0; i <= size; i++) { pbuf_page_offset = PAGE_SIZE * i; for (j = 0; j < SEC_PBUF_NUM; j++) { k = i * SEC_PBUF_NUM + j; - if (k == QM_Q_DEPTH) + if (k == q_depth) break; res[k].pbuf = res->pbuf + j * SEC_PBUF_PKG + pbuf_page_offset; @@ -467,36 +483,29 @@ static void sec_alg_resource_free(struct sec_ctx *ctx, sec_free_mac_resource(dev, qp_ctx->res); } -static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx, - int qp_ctx_id, int alg_type) +static int sec_alloc_qp_ctx_resource(struct hisi_qm *qm, struct sec_ctx *ctx, + struct sec_qp_ctx *qp_ctx) { + u16 q_depth = qp_ctx->qp->sq_depth; struct device *dev = ctx->dev; - struct sec_qp_ctx *qp_ctx; - struct hisi_qp *qp; int ret = -ENOMEM; - qp_ctx = &ctx->qp_ctx[qp_ctx_id]; - qp = ctx->qps[qp_ctx_id]; - qp->req_type = 0; - qp->qp_ctx = qp_ctx; - qp_ctx->qp = qp; - qp_ctx->ctx = ctx; + qp_ctx->req_list = kcalloc(q_depth, sizeof(struct sec_req *), GFP_KERNEL); + if (!qp_ctx->req_list) + return ret; - qp->req_cb = sec_req_cb; + qp_ctx->res = kcalloc(q_depth, sizeof(struct sec_alg_res), GFP_KERNEL); + if (!qp_ctx->res) + goto err_free_req_list; + qp_ctx->res->depth = q_depth; - mutex_init(&qp_ctx->req_lock); - idr_init(&qp_ctx->req_idr); - INIT_LIST_HEAD(&qp_ctx->backlog); - - qp_ctx->c_in_pool = hisi_acc_create_sgl_pool(dev, QM_Q_DEPTH, - SEC_SGL_SGE_NR); + qp_ctx->c_in_pool = hisi_acc_create_sgl_pool(dev, q_depth, SEC_SGL_SGE_NR); if (IS_ERR(qp_ctx->c_in_pool)) { dev_err(dev, "fail to create sgl pool for input!\n"); - goto err_destroy_idr; + goto err_free_res; } - qp_ctx->c_out_pool = hisi_acc_create_sgl_pool(dev, QM_Q_DEPTH, - SEC_SGL_SGE_NR); + qp_ctx->c_out_pool = hisi_acc_create_sgl_pool(dev, q_depth, SEC_SGL_SGE_NR); if (IS_ERR(qp_ctx->c_out_pool)) { dev_err(dev, "fail to create sgl pool for output!\n"); goto err_free_c_in_pool; @@ -506,34 +515,72 @@ static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx, if (ret) goto err_free_c_out_pool; - ret = hisi_qm_start_qp(qp, 0); - if (ret < 0) - goto err_queue_free; - return 0; -err_queue_free: - sec_alg_resource_free(ctx, qp_ctx); err_free_c_out_pool: hisi_acc_free_sgl_pool(dev, qp_ctx->c_out_pool); err_free_c_in_pool: hisi_acc_free_sgl_pool(dev, qp_ctx->c_in_pool); -err_destroy_idr: - idr_destroy(&qp_ctx->req_idr); +err_free_res: + kfree(qp_ctx->res); +err_free_req_list: + kfree(qp_ctx->req_list); return ret; } -static void sec_release_qp_ctx(struct sec_ctx *ctx, - struct sec_qp_ctx *qp_ctx) +static void sec_free_qp_ctx_resource(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) { struct device *dev = ctx->dev; - hisi_qm_stop_qp(qp_ctx->qp); sec_alg_resource_free(ctx, qp_ctx); - hisi_acc_free_sgl_pool(dev, qp_ctx->c_out_pool); hisi_acc_free_sgl_pool(dev, qp_ctx->c_in_pool); + kfree(qp_ctx->res); + kfree(qp_ctx->req_list); +} + +static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx, + int qp_ctx_id, int alg_type) +{ + struct sec_qp_ctx *qp_ctx; + struct hisi_qp *qp; + int ret; + + qp_ctx = &ctx->qp_ctx[qp_ctx_id]; + qp = ctx->qps[qp_ctx_id]; + qp->req_type = 0; + qp->qp_ctx = qp_ctx; + qp_ctx->qp = qp; + qp_ctx->ctx = ctx; + qp->req_cb = sec_req_cb; + + spin_lock_init(&qp_ctx->req_lock); + idr_init(&qp_ctx->req_idr); + INIT_LIST_HEAD(&qp_ctx->backlog); + + ret = sec_alloc_qp_ctx_resource(qm, ctx, qp_ctx); + if (ret) + goto err_destroy_idr; + + ret = hisi_qm_start_qp(qp, 0); + if (ret < 0) + goto err_resource_free; + + return 0; + +err_resource_free: + sec_free_qp_ctx_resource(ctx, qp_ctx); +err_destroy_idr: + idr_destroy(&qp_ctx->req_idr); + return ret; +} + +static void sec_release_qp_ctx(struct sec_ctx *ctx, + struct sec_qp_ctx *qp_ctx) +{ + hisi_qm_stop_qp(qp_ctx->qp); + sec_free_qp_ctx_resource(ctx, qp_ctx); idr_destroy(&qp_ctx->req_idr); } @@ -556,7 +603,7 @@ static int sec_ctx_base_init(struct sec_ctx *ctx) ctx->pbuf_supported = ctx->sec->iommu_used; /* Half of queue depth is taken as fake requests limit in the queue. */ - ctx->fake_req_limit = QM_Q_DEPTH >> 1; + ctx->fake_req_limit = ctx->qps[0]->sq_depth >> 1; ctx->qp_ctx = kcalloc(sec->ctx_q_num, sizeof(struct sec_qp_ctx), GFP_KERNEL); if (!ctx->qp_ctx) { @@ -617,7 +664,7 @@ static int sec_auth_init(struct sec_ctx *ctx) { struct sec_auth_ctx *a_ctx = &ctx->a_ctx; - a_ctx->a_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE, + a_ctx->a_key = dma_alloc_coherent(ctx->dev, SEC_MAX_AKEY_SIZE, &a_ctx->a_key_dma, GFP_KERNEL); if (!a_ctx->a_key) return -ENOMEM; @@ -629,8 +676,8 @@ static void sec_auth_uninit(struct sec_ctx *ctx) { struct sec_auth_ctx *a_ctx = &ctx->a_ctx; - memzero_explicit(a_ctx->a_key, SEC_MAX_KEY_SIZE); - dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE, + memzero_explicit(a_ctx->a_key, SEC_MAX_AKEY_SIZE); + dma_free_coherent(ctx->dev, SEC_MAX_AKEY_SIZE, a_ctx->a_key, a_ctx->a_key_dma); } @@ -641,13 +688,15 @@ static int sec_skcipher_fbtfm_init(struct crypto_skcipher *tfm) struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; c_ctx->fallback = false; + + /* Currently, only XTS mode need fallback tfm when using 192bit key */ if (likely(strncmp(alg, "xts", SEC_XTS_NAME_SZ))) return 0; c_ctx->fbtfm = crypto_alloc_sync_skcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK); if (IS_ERR(c_ctx->fbtfm)) { - pr_err("failed to alloc fallback tfm!\n"); + pr_err("failed to alloc xts mode fallback tfm!\n"); return PTR_ERR(c_ctx->fbtfm); } @@ -808,7 +857,7 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, } memcpy(c_ctx->c_key, key, keylen); - if (c_ctx->fallback) { + if (c_ctx->fallback && c_ctx->fbtfm) { ret = crypto_sync_skcipher_setkey(c_ctx->fbtfm, key, keylen); if (ret) { dev_err(dev, "failed to set fallback skcipher key!\n"); @@ -1300,6 +1349,10 @@ static int sec_skcipher_bd_fill_v3(struct sec_ctx *ctx, struct sec_req *req) cipher = SEC_CIPHER_DEC; sec_sqe3->c_icv_key |= cpu_to_le16(cipher); + /* Set the CTR counter mode is 128bit rollover */ + sec_sqe3->auth_mac_key = cpu_to_le32((u32)SEC_CTR_CNT_ROLLOVER << + SEC_CTR_CNT_OFFSET); + if (req->use_pbuf) { bd_param |= SEC_PBUF << SEC_SRC_SGL_OFFSET_V3; bd_param |= SEC_PBUF << SEC_DST_SGL_OFFSET_V3; @@ -1373,7 +1426,7 @@ static struct sec_req *sec_back_req_clear(struct sec_ctx *ctx, { struct sec_req *backlog_req = NULL; - mutex_lock(&qp_ctx->req_lock); + spin_lock_bh(&qp_ctx->req_lock); if (ctx->fake_req_limit >= atomic_read(&qp_ctx->qp->qp_status.used) && !list_empty(&qp_ctx->backlog)) { @@ -1381,7 +1434,7 @@ static struct sec_req *sec_back_req_clear(struct sec_ctx *ctx, typeof(*backlog_req), backlog_head); list_del(&backlog_req->backlog_head); } - mutex_unlock(&qp_ctx->req_lock); + spin_unlock_bh(&qp_ctx->req_lock); return backlog_req; } @@ -1614,7 +1667,7 @@ static void sec_auth_bd_fill_ex_v3(struct sec_auth_ctx *ctx, int dir, sqe3->auth_mac_key |= cpu_to_le32((u32)SEC_AUTH_TYPE1); sqe3->huk_iv_seq &= SEC_CIPHER_AUTH_V3; } else { - sqe3->auth_mac_key |= cpu_to_le32((u32)SEC_AUTH_TYPE1); + sqe3->auth_mac_key |= cpu_to_le32((u32)SEC_AUTH_TYPE2); sqe3->huk_iv_seq |= SEC_AUTH_CIPHER_V3; } sqe3->a_len_key = cpu_to_le32(c_req->c_len + aq->assoclen); @@ -1670,7 +1723,6 @@ static void sec_aead_callback(struct sec_ctx *c, struct sec_req *req, int err) aead_req->out_mac, authsize, a_req->cryptlen + a_req->assoclen); - if (unlikely(sz != authsize)) { dev_err(c->dev, "copy out mac err!\n"); err = -EINVAL; @@ -1957,7 +2009,6 @@ static int sec_aead_sha512_ctx_init(struct crypto_aead *tfm) return sec_aead_ctx_init(tfm, "sha512"); } - static int sec_skcipher_cryptlen_ckeck(struct sec_ctx *ctx, struct sec_req *sreq) { @@ -2032,13 +2083,12 @@ static int sec_skcipher_soft_crypto(struct sec_ctx *ctx, struct skcipher_request *sreq, bool encrypt) { struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; + SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, c_ctx->fbtfm); struct device *dev = ctx->dev; int ret; - SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, c_ctx->fbtfm); - if (!c_ctx->fbtfm) { - dev_err(dev, "failed to check fallback tfm\n"); + dev_err_ratelimited(dev, "the soft tfm isn't supported in the current system.\n"); return -EINVAL; } @@ -2105,7 +2155,6 @@ static int sec_skcipher_decrypt(struct skcipher_request *sk_req) .cra_driver_name = "hisi_sec_"sec_cra_name,\ .cra_priority = SEC_PRIORITY,\ .cra_flags = CRYPTO_ALG_ASYNC |\ - CRYPTO_ALG_ALLOCATES_MEMORY |\ CRYPTO_ALG_NEED_FALLBACK,\ .cra_blocksize = blk_size,\ .cra_ctxsize = sizeof(struct sec_ctx),\ @@ -2119,67 +2168,80 @@ static int sec_skcipher_decrypt(struct skcipher_request *sk_req) .min_keysize = sec_min_key_size,\ .max_keysize = sec_max_key_size,\ .ivsize = iv_size,\ -}, +} #define SEC_SKCIPHER_ALG(name, key_func, min_key_size, \ max_key_size, blk_size, iv_size) \ SEC_SKCIPHER_GEN_ALG(name, key_func, min_key_size, max_key_size, \ sec_skcipher_ctx_init, sec_skcipher_ctx_exit, blk_size, iv_size) -static struct skcipher_alg sec_skciphers[] = { - SEC_SKCIPHER_ALG("ecb(aes)", sec_setkey_aes_ecb, - AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE, - AES_BLOCK_SIZE, 0) - - SEC_SKCIPHER_ALG("cbc(aes)", sec_setkey_aes_cbc, - AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE, - AES_BLOCK_SIZE, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("xts(aes)", sec_setkey_aes_xts, - SEC_XTS_MIN_KEY_SIZE, SEC_XTS_MAX_KEY_SIZE, - AES_BLOCK_SIZE, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("ecb(des3_ede)", sec_setkey_3des_ecb, - SEC_DES3_3KEY_SIZE, SEC_DES3_3KEY_SIZE, - DES3_EDE_BLOCK_SIZE, 0) - - SEC_SKCIPHER_ALG("cbc(des3_ede)", sec_setkey_3des_cbc, - SEC_DES3_3KEY_SIZE, SEC_DES3_3KEY_SIZE, - DES3_EDE_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("xts(sm4)", sec_setkey_sm4_xts, - SEC_XTS_MIN_KEY_SIZE, SEC_XTS_MIN_KEY_SIZE, - AES_BLOCK_SIZE, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("cbc(sm4)", sec_setkey_sm4_cbc, - AES_MIN_KEY_SIZE, AES_MIN_KEY_SIZE, - AES_BLOCK_SIZE, AES_BLOCK_SIZE) -}; - -static struct skcipher_alg sec_skciphers_v3[] = { - SEC_SKCIPHER_ALG("ofb(aes)", sec_setkey_aes_ofb, - AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE, - SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("cfb(aes)", sec_setkey_aes_cfb, - AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE, - SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("ctr(aes)", sec_setkey_aes_ctr, - AES_MIN_KEY_SIZE, AES_MAX_KEY_SIZE, - SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("ofb(sm4)", sec_setkey_sm4_ofb, - AES_MIN_KEY_SIZE, AES_MIN_KEY_SIZE, - SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("cfb(sm4)", sec_setkey_sm4_cfb, - AES_MIN_KEY_SIZE, AES_MIN_KEY_SIZE, - SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE) - - SEC_SKCIPHER_ALG("ctr(sm4)", sec_setkey_sm4_ctr, - AES_MIN_KEY_SIZE, AES_MIN_KEY_SIZE, - SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE) +static struct sec_skcipher sec_skciphers[] = { + { + .alg_msk = BIT(0), + .alg = SEC_SKCIPHER_ALG("ecb(aes)", sec_setkey_aes_ecb, AES_MIN_KEY_SIZE, + AES_MAX_KEY_SIZE, AES_BLOCK_SIZE, 0), + }, + { + .alg_msk = BIT(1), + .alg = SEC_SKCIPHER_ALG("cbc(aes)", sec_setkey_aes_cbc, AES_MIN_KEY_SIZE, + AES_MAX_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(2), + .alg = SEC_SKCIPHER_ALG("ctr(aes)", sec_setkey_aes_ctr, AES_MIN_KEY_SIZE, + AES_MAX_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(3), + .alg = SEC_SKCIPHER_ALG("xts(aes)", sec_setkey_aes_xts, SEC_XTS_MIN_KEY_SIZE, + SEC_XTS_MAX_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(4), + .alg = SEC_SKCIPHER_ALG("ofb(aes)", sec_setkey_aes_ofb, AES_MIN_KEY_SIZE, + AES_MAX_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(5), + .alg = SEC_SKCIPHER_ALG("cfb(aes)", sec_setkey_aes_cfb, AES_MIN_KEY_SIZE, + AES_MAX_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(12), + .alg = SEC_SKCIPHER_ALG("cbc(sm4)", sec_setkey_sm4_cbc, AES_MIN_KEY_SIZE, + AES_MIN_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(13), + .alg = SEC_SKCIPHER_ALG("ctr(sm4)", sec_setkey_sm4_ctr, AES_MIN_KEY_SIZE, + AES_MIN_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(14), + .alg = SEC_SKCIPHER_ALG("xts(sm4)", sec_setkey_sm4_xts, SEC_XTS_MIN_KEY_SIZE, + SEC_XTS_MIN_KEY_SIZE, AES_BLOCK_SIZE, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(15), + .alg = SEC_SKCIPHER_ALG("ofb(sm4)", sec_setkey_sm4_ofb, AES_MIN_KEY_SIZE, + AES_MIN_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(16), + .alg = SEC_SKCIPHER_ALG("cfb(sm4)", sec_setkey_sm4_cfb, AES_MIN_KEY_SIZE, + AES_MIN_KEY_SIZE, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(23), + .alg = SEC_SKCIPHER_ALG("ecb(des3_ede)", sec_setkey_3des_ecb, SEC_DES3_3KEY_SIZE, + SEC_DES3_3KEY_SIZE, DES3_EDE_BLOCK_SIZE, 0), + }, + { + .alg_msk = BIT(24), + .alg = SEC_SKCIPHER_ALG("cbc(des3_ede)", sec_setkey_3des_cbc, SEC_DES3_3KEY_SIZE, + SEC_DES3_3KEY_SIZE, DES3_EDE_BLOCK_SIZE, + DES3_EDE_BLOCK_SIZE), + }, }; static int aead_iv_demension_check(struct aead_request *aead_req) @@ -2219,6 +2281,10 @@ static int sec_aead_spec_check(struct sec_ctx *ctx, struct sec_req *sreq) } if (c_mode == SEC_CMODE_CCM) { + if (unlikely(req->assoclen > SEC_MAX_CCM_AAD_LEN)) { + dev_err_ratelimited(dev, "CCM input aad parameter is too long!\n"); + return -EINVAL; + } ret = aead_iv_demension_check(req); if (ret) { dev_err(dev, "aead input iv param error!\n"); @@ -2256,7 +2322,6 @@ static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq) if (ctx->sec->qm.ver == QM_HW_V2) { if (unlikely(!req->cryptlen || (!sreq->c_req.encrypt && req->cryptlen <= authsize))) { - dev_err(dev, "Kunpeng920 not support 0 length!\n"); ctx->a_ctx.fallback = true; return -EINVAL; } @@ -2284,9 +2349,10 @@ static int sec_aead_soft_crypto(struct sec_ctx *ctx, struct aead_request *aead_req, bool encrypt) { - struct aead_request *subreq = aead_request_ctx(aead_req); struct sec_auth_ctx *a_ctx = &ctx->a_ctx; struct device *dev = ctx->dev; + struct aead_request *subreq; + int ret; /* Kunpeng920 aead mode not support input 0 size */ if (!a_ctx->fallback_aead_tfm) { @@ -2294,6 +2360,10 @@ static int sec_aead_soft_crypto(struct sec_ctx *ctx, return -EINVAL; } + subreq = aead_request_alloc(a_ctx->fallback_aead_tfm, GFP_KERNEL); + if (!subreq) + return -ENOMEM; + aead_request_set_tfm(subreq, a_ctx->fallback_aead_tfm); aead_request_set_callback(subreq, aead_req->base.flags, aead_req->base.complete, aead_req->base.data); @@ -2301,8 +2371,13 @@ static int sec_aead_soft_crypto(struct sec_ctx *ctx, aead_req->cryptlen, aead_req->iv); aead_request_set_ad(subreq, aead_req->assoclen); - return encrypt ? crypto_aead_encrypt(subreq) : - crypto_aead_decrypt(subreq); + if (encrypt) + ret = crypto_aead_encrypt(subreq); + else + ret = crypto_aead_decrypt(subreq); + aead_request_free(subreq); + + return ret; } static int sec_aead_crypto(struct aead_request *a_req, bool encrypt) @@ -2345,7 +2420,6 @@ static int sec_aead_decrypt(struct aead_request *a_req) .cra_driver_name = "hisi_sec_"sec_cra_name,\ .cra_priority = SEC_PRIORITY,\ .cra_flags = CRYPTO_ALG_ASYNC |\ - CRYPTO_ALG_ALLOCATES_MEMORY |\ CRYPTO_ALG_NEED_FALLBACK,\ .cra_blocksize = blk_size,\ .cra_ctxsize = sizeof(struct sec_ctx),\ @@ -2361,90 +2435,135 @@ static int sec_aead_decrypt(struct aead_request *a_req) .maxauthsize = max_authsize,\ } -static struct aead_alg sec_aeads[] = { - SEC_AEAD_ALG("authenc(hmac(sha1),cbc(aes))", - sec_setkey_aes_cbc_sha1, sec_aead_sha1_ctx_init, - sec_aead_ctx_exit, AES_BLOCK_SIZE, - AES_BLOCK_SIZE, SHA1_DIGEST_SIZE), +static struct sec_aead sec_aeads[] = { + { + .alg_msk = BIT(6), + .alg = SEC_AEAD_ALG("ccm(aes)", sec_setkey_aes_ccm, sec_aead_xcm_ctx_init, + sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE, + AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(7), + .alg = SEC_AEAD_ALG("gcm(aes)", sec_setkey_aes_gcm, sec_aead_xcm_ctx_init, + sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, SEC_AIV_SIZE, + AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(17), + .alg = SEC_AEAD_ALG("ccm(sm4)", sec_setkey_sm4_ccm, sec_aead_xcm_ctx_init, + sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, AES_BLOCK_SIZE, + AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(18), + .alg = SEC_AEAD_ALG("gcm(sm4)", sec_setkey_sm4_gcm, sec_aead_xcm_ctx_init, + sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, SEC_AIV_SIZE, + AES_BLOCK_SIZE), + }, + { + .alg_msk = BIT(43), + .alg = SEC_AEAD_ALG("authenc(hmac(sha1),cbc(aes))", sec_setkey_aes_cbc_sha1, + sec_aead_sha1_ctx_init, sec_aead_ctx_exit, AES_BLOCK_SIZE, + AES_BLOCK_SIZE, SHA1_DIGEST_SIZE), + }, + { + .alg_msk = BIT(44), + .alg = SEC_AEAD_ALG("authenc(hmac(sha256),cbc(aes))", sec_setkey_aes_cbc_sha256, + sec_aead_sha256_ctx_init, sec_aead_ctx_exit, AES_BLOCK_SIZE, + AES_BLOCK_SIZE, SHA256_DIGEST_SIZE), + }, + { + .alg_msk = BIT(45), + .alg = SEC_AEAD_ALG("authenc(hmac(sha512),cbc(aes))", sec_setkey_aes_cbc_sha512, + sec_aead_sha512_ctx_init, sec_aead_ctx_exit, AES_BLOCK_SIZE, + AES_BLOCK_SIZE, SHA512_DIGEST_SIZE), + }, +}; - SEC_AEAD_ALG("authenc(hmac(sha256),cbc(aes))", - sec_setkey_aes_cbc_sha256, sec_aead_sha256_ctx_init, - sec_aead_ctx_exit, AES_BLOCK_SIZE, - AES_BLOCK_SIZE, SHA256_DIGEST_SIZE), +static void sec_unregister_skcipher(u64 alg_mask, int end) +{ + int i; - SEC_AEAD_ALG("authenc(hmac(sha512),cbc(aes))", - sec_setkey_aes_cbc_sha512, sec_aead_sha512_ctx_init, - sec_aead_ctx_exit, AES_BLOCK_SIZE, - AES_BLOCK_SIZE, SHA512_DIGEST_SIZE), + for (i = 0; i < end; i++) + if (sec_skciphers[i].alg_msk & alg_mask) + crypto_unregister_skcipher(&sec_skciphers[i].alg); +} - SEC_AEAD_ALG("ccm(aes)", sec_setkey_aes_ccm, sec_aead_xcm_ctx_init, - sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, - AES_BLOCK_SIZE, AES_BLOCK_SIZE), +static int sec_register_skcipher(u64 alg_mask) +{ + int i, ret, count; - SEC_AEAD_ALG("gcm(aes)", sec_setkey_aes_gcm, sec_aead_xcm_ctx_init, - sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, - SEC_AIV_SIZE, AES_BLOCK_SIZE) -}; + count = ARRAY_SIZE(sec_skciphers); -static struct aead_alg sec_aeads_v3[] = { - SEC_AEAD_ALG("ccm(sm4)", sec_setkey_sm4_ccm, sec_aead_xcm_ctx_init, - sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, - AES_BLOCK_SIZE, AES_BLOCK_SIZE), + for (i = 0; i < count; i++) { + if (!(sec_skciphers[i].alg_msk & alg_mask)) + continue; - SEC_AEAD_ALG("gcm(sm4)", sec_setkey_sm4_gcm, sec_aead_xcm_ctx_init, - sec_aead_xcm_ctx_exit, SEC_MIN_BLOCK_SZ, - SEC_AIV_SIZE, AES_BLOCK_SIZE) -}; + ret = crypto_register_skcipher(&sec_skciphers[i].alg); + if (ret) + goto err; + } + + return 0; + +err: + sec_unregister_skcipher(alg_mask, i); + + return ret; +} + +static void sec_unregister_aead(u64 alg_mask, int end) +{ + int i; + + for (i = 0; i < end; i++) + if (sec_aeads[i].alg_msk & alg_mask) + crypto_unregister_aead(&sec_aeads[i].alg); +} + +static int sec_register_aead(u64 alg_mask) +{ + int i, ret, count; + + count = ARRAY_SIZE(sec_aeads); + + for (i = 0; i < count; i++) { + if (!(sec_aeads[i].alg_msk & alg_mask)) + continue; + + ret = crypto_register_aead(&sec_aeads[i].alg); + if (ret) + goto err; + } + + return 0; + +err: + sec_unregister_aead(alg_mask, i); + + return ret; +} int sec_register_to_crypto(struct hisi_qm *qm) { + u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW); int ret; - /* To avoid repeat register */ - ret = crypto_register_skciphers(sec_skciphers, - ARRAY_SIZE(sec_skciphers)); + ret = sec_register_skcipher(alg_mask); if (ret) return ret; - if (qm->ver > QM_HW_V2) { - ret = crypto_register_skciphers(sec_skciphers_v3, - ARRAY_SIZE(sec_skciphers_v3)); - if (ret) - goto reg_skcipher_fail; - } - - ret = crypto_register_aeads(sec_aeads, ARRAY_SIZE(sec_aeads)); + ret = sec_register_aead(alg_mask); if (ret) - goto reg_aead_fail; - if (qm->ver > QM_HW_V2) { - ret = crypto_register_aeads(sec_aeads_v3, ARRAY_SIZE(sec_aeads_v3)); - if (ret) - goto reg_aead_v3_fail; - } - return ret; + sec_unregister_skcipher(alg_mask, ARRAY_SIZE(sec_skciphers)); -reg_aead_v3_fail: - crypto_unregister_aeads(sec_aeads, ARRAY_SIZE(sec_aeads)); -reg_aead_fail: - if (qm->ver > QM_HW_V2) - crypto_unregister_skciphers(sec_skciphers_v3, - ARRAY_SIZE(sec_skciphers_v3)); -reg_skcipher_fail: - crypto_unregister_skciphers(sec_skciphers, - ARRAY_SIZE(sec_skciphers)); return ret; } void sec_unregister_from_crypto(struct hisi_qm *qm) { - if (qm->ver > QM_HW_V2) - crypto_unregister_aeads(sec_aeads_v3, - ARRAY_SIZE(sec_aeads_v3)); - crypto_unregister_aeads(sec_aeads, ARRAY_SIZE(sec_aeads)); + u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW); - if (qm->ver > QM_HW_V2) - crypto_unregister_skciphers(sec_skciphers_v3, - ARRAY_SIZE(sec_skciphers_v3)); - crypto_unregister_skciphers(sec_skciphers, - ARRAY_SIZE(sec_skciphers)); + sec_unregister_aead(alg_mask, ARRAY_SIZE(sec_aeads)); + sec_unregister_skcipher(alg_mask, ARRAY_SIZE(sec_skciphers)); } diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h index 9f71c358a6d3..d033f63b583f 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.h +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h @@ -7,6 +7,7 @@ #define SEC_AIV_SIZE 12 #define SEC_IV_SIZE 24 #define SEC_MAX_KEY_SIZE 64 +#define SEC_MAX_AKEY_SIZE 128 #define SEC_COMM_SCENE 0 #define SEC_MIN_BLOCK_SZ 1 @@ -354,8 +355,10 @@ struct sec_sqe3 { * akey_len: 9~14 bits * a_alg: 15~20 bits * key_sel: 21~24 bits - * updata_key: 25 bits - * reserved: 26~31 bits + * ctr_count_mode/sm4_xts: 25~26 bits + * sva_prefetch: 27 bits + * key_wrap_num: 28~30 bits + * update_key: 31 bits */ __le32 auth_mac_key; __le32 salt; diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 26d3ab1d308b..3705412bac5f 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -20,15 +20,13 @@ #define SEC_VF_NUM 63 #define SEC_QUEUE_NUM_V1 4096 -#define SEC_PF_PCI_DEVICE_ID 0xa255 -#define SEC_VF_PCI_DEVICE_ID 0xa256 +#define PCI_DEVICE_ID_HUAWEI_SEC_PF 0xa255 #define SEC_BD_ERR_CHK_EN0 0xEFFFFFFF #define SEC_BD_ERR_CHK_EN1 0x7ffff7fd #define SEC_BD_ERR_CHK_EN3 0xffffbfff #define SEC_SQE_SIZE 128 -#define SEC_SQ_SIZE (SEC_SQE_SIZE * QM_Q_DEPTH) #define SEC_PF_DEF_Q_NUM 256 #define SEC_PF_DEF_Q_BASE 0 #define SEC_CTX_Q_NUM_DEF 2 @@ -43,16 +41,11 @@ #define SEC_ECC_NUM 16 #define SEC_ECC_MASH 0xFF #define SEC_CORE_INT_DISABLE 0x0 -#define SEC_CORE_INT_ENABLE 0x7c1ff -#define SEC_CORE_INT_CLEAR 0x7c1ff -#define SEC_SAA_ENABLE 0x17f #define SEC_RAS_CE_REG 0x301050 #define SEC_RAS_FE_REG 0x301054 #define SEC_RAS_NFE_REG 0x301058 -#define SEC_RAS_CE_ENB_MSK 0x88 #define SEC_RAS_FE_ENB_MSK 0x0 -#define SEC_RAS_NFE_ENB_MSK 0x7c177 #define SEC_OOO_SHUTDOWN_SEL 0x301014 #define SEC_RAS_DISABLE 0x0 #define SEC_MEM_START_INIT_REG 0x301100 @@ -90,6 +83,10 @@ SEC_USER1_WB_DATA_SSV) #define SEC_USER1_SMMU_SVA (SEC_USER1_SMMU_NORMAL | SEC_USER1_SVA_SET) #define SEC_USER1_SMMU_MASK (~SEC_USER1_SVA_SET) +#define SEC_INTERFACE_USER_CTRL0_REG_V3 0x302220 +#define SEC_INTERFACE_USER_CTRL1_REG_V3 0x302224 +#define SEC_USER1_SMMU_NORMAL_V3 (BIT(23) | BIT(17) | BIT(11) | BIT(5)) +#define SEC_USER1_SMMU_MASK_V3 0xFF79E79E #define SEC_CORE_INT_STATUS_M_ECC BIT(2) #define SEC_PREFETCH_CFG 0x301130 @@ -107,6 +104,25 @@ #define SEC_SQE_MASK_LEN 48 #define SEC_SHAPER_TYPE_RATE 400 +#define SEC_DFX_BASE 0x301000 +#define SEC_DFX_CORE 0x302100 +#define SEC_DFX_COMMON1 0x301600 +#define SEC_DFX_COMMON2 0x301C00 +#define SEC_DFX_BASE_LEN 0x9D +#define SEC_DFX_CORE_LEN 0x32B +#define SEC_DFX_COMMON1_LEN 0x45 +#define SEC_DFX_COMMON2_LEN 0xBA + +#define SEC_ALG_BITMAP_SHIFT 32 + +#define SEC_CIPHER_BITMAP (GENMASK_ULL(5, 0) | GENMASK_ULL(16, 12) | \ + GENMASK(24, 21)) +#define SEC_DIGEST_BITMAP (GENMASK_ULL(11, 8) | GENMASK_ULL(20, 19) | \ + GENMASK_ULL(42, 25)) +#define SEC_AEAD_BITMAP (GENMASK_ULL(7, 6) | GENMASK_ULL(18, 17) | \ + GENMASK_ULL(45, 43)) +#define SEC_DEV_ALG_MAX_LEN 256 + struct sec_hw_error { u32 int_msk; const char *msg; @@ -117,6 +133,11 @@ struct sec_dfx_item { u32 offset; }; +struct sec_dev_alg { + u64 alg_msk; + const char *algs; +}; + static const char sec_name[] = "hisi_sec2"; static struct dentry *sec_debugfs_root; @@ -125,6 +146,46 @@ static struct hisi_qm_list sec_devices = { .unregister_from_crypto = sec_unregister_from_crypto, }; +static const struct hisi_qm_cap_info sec_basic_info[] = { + {SEC_QM_NFE_MASK_CAP, 0x3124, 0, GENMASK(31, 0), 0x0, 0x1C77, 0x7C77}, + {SEC_QM_RESET_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0xC77, 0x6C77}, + {SEC_QM_OOO_SHUTDOWN_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0x4, 0x6C77}, + {SEC_QM_CE_MASK_CAP, 0x312C, 0, GENMASK(31, 0), 0x0, 0x8, 0x8}, + {SEC_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x177, 0x60177}, + {SEC_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x177, 0x177}, + {SEC_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x4, 0x177}, + {SEC_CE_MASK_CAP, 0x3138, 0, GENMASK(31, 0), 0x0, 0x88, 0xC088}, + {SEC_CLUSTER_NUM_CAP, 0x313c, 20, GENMASK(3, 0), 0x1, 0x1, 0x1}, + {SEC_CORE_TYPE_NUM_CAP, 0x313c, 16, GENMASK(3, 0), 0x1, 0x1, 0x1}, + {SEC_CORE_NUM_CAP, 0x313c, 8, GENMASK(7, 0), 0x4, 0x4, 0x4}, + {SEC_CORES_PER_CLUSTER_NUM_CAP, 0x313c, 0, GENMASK(7, 0), 0x4, 0x4, 0x4}, + {SEC_CORE_ENABLE_BITMAP, 0x3140, 32, GENMASK(31, 0), 0x17F, 0x17F, 0xF}, + {SEC_DRV_ALG_BITMAP_LOW, 0x3144, 0, GENMASK(31, 0), 0x18050CB, 0x18050CB, 0x187F0FF}, + {SEC_DRV_ALG_BITMAP_HIGH, 0x3148, 0, GENMASK(31, 0), 0x395C, 0x395C, 0x395C}, + {SEC_DEV_ALG_BITMAP_LOW, 0x314c, 0, GENMASK(31, 0), 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF}, + {SEC_DEV_ALG_BITMAP_HIGH, 0x3150, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, + {SEC_CORE1_ALG_BITMAP_LOW, 0x3154, 0, GENMASK(31, 0), 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF}, + {SEC_CORE1_ALG_BITMAP_HIGH, 0x3158, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, + {SEC_CORE2_ALG_BITMAP_LOW, 0x315c, 0, GENMASK(31, 0), 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF}, + {SEC_CORE2_ALG_BITMAP_HIGH, 0x3160, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, + {SEC_CORE3_ALG_BITMAP_LOW, 0x3164, 0, GENMASK(31, 0), 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF}, + {SEC_CORE3_ALG_BITMAP_HIGH, 0x3168, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, + {SEC_CORE4_ALG_BITMAP_LOW, 0x316c, 0, GENMASK(31, 0), 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF}, + {SEC_CORE4_ALG_BITMAP_HIGH, 0x3170, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, +}; + +static const struct sec_dev_alg sec_dev_algs[] = { { + .alg_msk = SEC_CIPHER_BITMAP, + .algs = "cipher\n", + }, { + .alg_msk = SEC_DIGEST_BITMAP, + .algs = "digest\n", + }, { + .alg_msk = SEC_AEAD_BITMAP, + .algs = "aead\n", + }, +}; + static const struct sec_hw_error sec_hw_errors[] = { { .int_msk = BIT(0), @@ -223,9 +284,37 @@ static const struct debugfs_reg32 sec_dfx_regs[] = { {"SEC_BD_SAA8 ", 0x301C40}, }; +/* define the SEC's dfx regs region and region length */ +static struct dfx_diff_registers sec_diff_regs[] = { + { + .reg_offset = SEC_DFX_BASE, + .reg_len = SEC_DFX_BASE_LEN, + }, { + .reg_offset = SEC_DFX_COMMON1, + .reg_len = SEC_DFX_COMMON1_LEN, + }, { + .reg_offset = SEC_DFX_COMMON2, + .reg_len = SEC_DFX_COMMON2_LEN, + }, { + .reg_offset = SEC_DFX_CORE, + .reg_len = SEC_DFX_CORE_LEN, + }, +}; + +static int sec_diff_regs_show(struct seq_file *s, void *unused) +{ + struct hisi_qm *qm = s->private; + + hisi_qm_acc_diff_regs_dump(qm, s, qm->debug.acc_diff_regs, + ARRAY_SIZE(sec_diff_regs)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(sec_diff_regs); + static int sec_pf_q_num_set(const char *val, const struct kernel_param *kp) { - return q_num_set(val, kp, SEC_PF_PCI_DEVICE_ID); + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_SEC_PF); } static const struct kernel_param_ops sec_pf_q_num_ops = { @@ -299,6 +388,16 @@ struct hisi_qp **sec_create_qps(void) return NULL; } +u64 sec_get_alg_bitmap(struct hisi_qm *qm, u32 high, u32 low) +{ + u32 cap_val_h, cap_val_l; + + cap_val_h = hisi_qm_get_hw_info(qm, sec_basic_info, high, qm->cap_ver); + cap_val_l = hisi_qm_get_hw_info(qm, sec_basic_info, low, qm->cap_ver); + + return ((u64)cap_val_h << SEC_ALG_BITMAP_SHIFT) | (u64)cap_val_l; +} + static const struct kernel_param_ops sec_uacce_mode_ops = { .set = uacce_mode_set, .get = param_get_int, @@ -313,8 +412,8 @@ module_param_cb(uacce_mode, &sec_uacce_mode_ops, &uacce_mode, 0444); MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); static const struct pci_device_id sec_dev_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_PF_PCI_DEVICE_ID) }, - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_VF_PCI_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_SEC_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_SEC_VF) }, { 0, } }; MODULE_DEVICE_TABLE(pci, sec_dev_ids); @@ -335,12 +434,47 @@ static void sec_set_endian(struct hisi_qm *qm) writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG); } +static void sec_engine_sva_config(struct hisi_qm *qm) +{ + u32 reg; + + if (qm->ver > QM_HW_V2) { + reg = readl_relaxed(qm->io_base + + SEC_INTERFACE_USER_CTRL0_REG_V3); + reg |= SEC_USER0_SMMU_NORMAL; + writel_relaxed(reg, qm->io_base + + SEC_INTERFACE_USER_CTRL0_REG_V3); + + reg = readl_relaxed(qm->io_base + + SEC_INTERFACE_USER_CTRL1_REG_V3); + reg &= SEC_USER1_SMMU_MASK_V3; + reg |= SEC_USER1_SMMU_NORMAL_V3; + writel_relaxed(reg, qm->io_base + + SEC_INTERFACE_USER_CTRL1_REG_V3); + } else { + reg = readl_relaxed(qm->io_base + + SEC_INTERFACE_USER_CTRL0_REG); + reg |= SEC_USER0_SMMU_NORMAL; + writel_relaxed(reg, qm->io_base + + SEC_INTERFACE_USER_CTRL0_REG); + reg = readl_relaxed(qm->io_base + + SEC_INTERFACE_USER_CTRL1_REG); + reg &= SEC_USER1_SMMU_MASK; + if (qm->use_sva) + reg |= SEC_USER1_SMMU_SVA; + else + reg |= SEC_USER1_SMMU_NORMAL; + writel_relaxed(reg, qm->io_base + + SEC_INTERFACE_USER_CTRL1_REG); + } +} + static void sec_open_sva_prefetch(struct hisi_qm *qm) { u32 val; int ret; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; /* Enable prefetch */ @@ -360,7 +494,7 @@ static void sec_close_sva_prefetch(struct hisi_qm *qm) u32 val; int ret; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; val = readl_relaxed(qm->io_base + SEC_PREFETCH_CFG); @@ -426,31 +560,25 @@ static int sec_engine_init(struct hisi_qm *qm) reg |= (0x1 << SEC_TRNG_EN_SHIFT); writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG); - reg = readl_relaxed(qm->io_base + SEC_INTERFACE_USER_CTRL0_REG); - reg |= SEC_USER0_SMMU_NORMAL; - writel_relaxed(reg, qm->io_base + SEC_INTERFACE_USER_CTRL0_REG); - - reg = readl_relaxed(qm->io_base + SEC_INTERFACE_USER_CTRL1_REG); - reg &= SEC_USER1_SMMU_MASK; - if (qm->use_sva && qm->ver == QM_HW_V2) - reg |= SEC_USER1_SMMU_SVA; - else - reg |= SEC_USER1_SMMU_NORMAL; - writel_relaxed(reg, qm->io_base + SEC_INTERFACE_USER_CTRL1_REG); + sec_engine_sva_config(qm); writel(SEC_SINGLE_PORT_MAX_TRANS, qm->io_base + AM_CFG_SINGLE_PORT_MAX_TRANS); - writel(SEC_SAA_ENABLE, qm->io_base + SEC_SAA_EN_REG); + reg = hisi_qm_get_hw_info(qm, sec_basic_info, SEC_CORE_ENABLE_BITMAP, qm->cap_ver); + writel(reg, qm->io_base + SEC_SAA_EN_REG); - /* Enable sm4 extra mode, as ctr/ecb */ - writel_relaxed(SEC_BD_ERR_CHK_EN0, - qm->io_base + SEC_BD_ERR_CHK_EN_REG0); - /* Enable sm4 xts mode multiple iv */ - writel_relaxed(SEC_BD_ERR_CHK_EN1, - qm->io_base + SEC_BD_ERR_CHK_EN_REG1); - writel_relaxed(SEC_BD_ERR_CHK_EN3, - qm->io_base + SEC_BD_ERR_CHK_EN_REG3); + if (qm->ver < QM_HW_V3) { + /* HW V2 enable sm4 extra mode, as ctr/ecb */ + writel_relaxed(SEC_BD_ERR_CHK_EN0, + qm->io_base + SEC_BD_ERR_CHK_EN_REG0); + + /* HW V2 enable sm4 xts mode multiple iv */ + writel_relaxed(SEC_BD_ERR_CHK_EN1, + qm->io_base + SEC_BD_ERR_CHK_EN_REG1); + writel_relaxed(SEC_BD_ERR_CHK_EN3, + qm->io_base + SEC_BD_ERR_CHK_EN_REG3); + } /* config endian */ sec_set_endian(qm); @@ -508,7 +636,8 @@ static void sec_master_ooo_ctrl(struct hisi_qm *qm, bool enable) val1 = readl(qm->io_base + SEC_CONTROL_REG); if (enable) { val1 |= SEC_AXI_SHUTDOWN_ENABLE; - val2 = SEC_RAS_NFE_ENB_MSK; + val2 = hisi_qm_get_hw_info(qm, sec_basic_info, + SEC_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); } else { val1 &= SEC_AXI_SHUTDOWN_DISABLE; val2 = 0x0; @@ -522,25 +651,30 @@ static void sec_master_ooo_ctrl(struct hisi_qm *qm, bool enable) static void sec_hw_error_enable(struct hisi_qm *qm) { + u32 ce, nfe; + if (qm->ver == QM_HW_V1) { writel(SEC_CORE_INT_DISABLE, qm->io_base + SEC_CORE_INT_MASK); pci_info(qm->pdev, "V1 not support hw error handle\n"); return; } + ce = hisi_qm_get_hw_info(qm, sec_basic_info, SEC_CE_MASK_CAP, qm->cap_ver); + nfe = hisi_qm_get_hw_info(qm, sec_basic_info, SEC_NFE_MASK_CAP, qm->cap_ver); + /* clear SEC hw error source if having */ - writel(SEC_CORE_INT_CLEAR, qm->io_base + SEC_CORE_INT_SOURCE); + writel(ce | nfe | SEC_RAS_FE_ENB_MSK, qm->io_base + SEC_CORE_INT_SOURCE); /* enable RAS int */ - writel(SEC_RAS_CE_ENB_MSK, qm->io_base + SEC_RAS_CE_REG); + writel(ce, qm->io_base + SEC_RAS_CE_REG); writel(SEC_RAS_FE_ENB_MSK, qm->io_base + SEC_RAS_FE_REG); - writel(SEC_RAS_NFE_ENB_MSK, qm->io_base + SEC_RAS_NFE_REG); + writel(nfe, qm->io_base + SEC_RAS_NFE_REG); /* enable SEC block master OOO when nfe occurs on Kunpeng930 */ sec_master_ooo_ctrl(qm, true); /* enable SEC hw error interrupts */ - writel(SEC_CORE_INT_ENABLE, qm->io_base + SEC_CORE_INT_MASK); + writel(ce | nfe | SEC_RAS_FE_ENB_MSK, qm->io_base + SEC_CORE_INT_MASK); } static void sec_hw_error_disable(struct hisi_qm *qm) @@ -699,6 +833,7 @@ DEFINE_SHOW_ATTRIBUTE(sec_regs); static int sec_core_debug_init(struct hisi_qm *qm) { + struct dfx_diff_registers *sec_regs = qm->debug.acc_diff_regs; struct sec_dev *sec = container_of(qm, struct sec_dev, qm); struct device *dev = &qm->pdev->dev; struct sec_dfx *dfx = &sec->debug.dfx; @@ -717,8 +852,11 @@ static int sec_core_debug_init(struct hisi_qm *qm) regset->base = qm->io_base; regset->dev = dev; - if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) + if (qm->pdev->device == PCI_DEVICE_ID_HUAWEI_SEC_PF) debugfs_create_file("regs", 0444, tmp_d, regset, &sec_regs_fops); + if (qm->fun_type == QM_HW_PF && sec_regs) + debugfs_create_file("diff_regs", 0444, tmp_d, + qm, &sec_diff_regs_fops); for (i = 0; i < ARRAY_SIZE(sec_dfx_labels); i++) { atomic64_t *data = (atomic64_t *)((uintptr_t)dfx + @@ -735,7 +873,7 @@ static int sec_debug_init(struct hisi_qm *qm) struct sec_dev *sec = container_of(qm, struct sec_dev, qm); int i; - if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) { + if (qm->pdev->device == PCI_DEVICE_ID_HUAWEI_SEC_PF) { for (i = SEC_CLEAR_ENABLE; i < SEC_DEBUG_FILE_NUM; i++) { spin_lock_init(&sec->debug.files[i].lock); sec->debug.files[i].index = i; @@ -760,6 +898,14 @@ static int sec_debugfs_init(struct hisi_qm *qm) sec_debugfs_root); qm->debug.sqe_mask_offset = SEC_SQE_MASK_OFFSET; qm->debug.sqe_mask_len = SEC_SQE_MASK_LEN; + + ret = hisi_qm_diff_regs_init(qm, sec_diff_regs, + ARRAY_SIZE(sec_diff_regs)); + if (ret) { + dev_warn(dev, "Failed to init SEC diff regs!\n"); + goto debugfs_remove; + } + hisi_qm_debug_init(qm); ret = sec_debug_init(qm); @@ -769,15 +915,66 @@ static int sec_debugfs_init(struct hisi_qm *qm) return 0; failed_to_create: + hisi_qm_diff_regs_uninit(qm, ARRAY_SIZE(sec_diff_regs)); +debugfs_remove: debugfs_remove_recursive(sec_debugfs_root); return ret; } static void sec_debugfs_exit(struct hisi_qm *qm) { + hisi_qm_diff_regs_uninit(qm, ARRAY_SIZE(sec_diff_regs)); + debugfs_remove_recursive(qm->debug.debug_root); } +static int sec_show_last_regs_init(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + int i; + + debug->last_words = kcalloc(ARRAY_SIZE(sec_dfx_regs), + sizeof(unsigned int), GFP_KERNEL); + if (!debug->last_words) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(sec_dfx_regs); i++) + debug->last_words[i] = readl_relaxed(qm->io_base + + sec_dfx_regs[i].offset); + + return 0; +} + +static void sec_show_last_regs_uninit(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + + if (qm->fun_type == QM_HW_VF || !debug->last_words) + return; + + kfree(debug->last_words); + debug->last_words = NULL; +} + +static void sec_show_last_dfx_regs(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + struct pci_dev *pdev = qm->pdev; + u32 val; + int i; + + if (qm->fun_type == QM_HW_VF || !debug->last_words) + return; + + /* dumps last word of the debugging registers during controller reset */ + for (i = 0; i < ARRAY_SIZE(sec_dfx_regs); i++) { + val = readl_relaxed(qm->io_base + sec_dfx_regs[i].offset); + if (val != debug->last_words[i]) + pci_info(pdev, "%s \t= 0x%08x => 0x%08x\n", + sec_dfx_regs[i].name, debug->last_words[i], val); + } +} + static void sec_log_hw_error(struct hisi_qm *qm, u32 err_sts) { const struct sec_hw_error *errs = sec_hw_errors; @@ -808,7 +1005,11 @@ static u32 sec_get_hw_err_status(struct hisi_qm *qm) static void sec_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts) { + u32 nfe; + writel(err_sts, qm->io_base + SEC_CORE_INT_SOURCE); + nfe = hisi_qm_get_hw_info(qm, sec_basic_info, SEC_NFE_MASK_CAP, qm->cap_ver); + writel(nfe, qm->io_base + SEC_RAS_NFE_REG); } static void sec_open_axi_master_ooo(struct hisi_qm *qm) @@ -824,14 +1025,20 @@ static void sec_err_info_init(struct hisi_qm *qm) { struct hisi_qm_err_info *err_info = &qm->err_info; - err_info->ce = QM_BASE_CE; - err_info->fe = 0; + err_info->fe = SEC_RAS_FE_ENB_MSK; + err_info->ce = hisi_qm_get_hw_info(qm, sec_basic_info, SEC_QM_CE_MASK_CAP, qm->cap_ver); + err_info->nfe = hisi_qm_get_hw_info(qm, sec_basic_info, SEC_QM_NFE_MASK_CAP, qm->cap_ver); err_info->ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC; - err_info->dev_ce_mask = SEC_RAS_CE_ENB_MSK; + err_info->qm_shutdown_mask = hisi_qm_get_hw_info(qm, sec_basic_info, + SEC_QM_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); + err_info->dev_shutdown_mask = hisi_qm_get_hw_info(qm, sec_basic_info, + SEC_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); + err_info->qm_reset_mask = hisi_qm_get_hw_info(qm, sec_basic_info, + SEC_QM_RESET_MASK_CAP, qm->cap_ver); + err_info->dev_reset_mask = hisi_qm_get_hw_info(qm, sec_basic_info, + SEC_RESET_MASK_CAP, qm->cap_ver); err_info->msi_wr_port = BIT(0); err_info->acpi_rst = "SRST"; - err_info->nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT | - QM_ACC_WB_NOT_READY_TIMEOUT; } static const struct hisi_qm_err_ini sec_err_ini = { @@ -844,6 +1051,7 @@ static const struct hisi_qm_err_ini sec_err_ini = { .open_axi_master_ooo = sec_open_axi_master_ooo, .open_sva_prefetch = sec_open_sva_prefetch, .close_sva_prefetch = sec_close_sva_prefetch, + .show_last_dfx_regs = sec_show_last_dfx_regs, .err_info_init = sec_err_info_init, }; @@ -862,6 +1070,38 @@ static int sec_pf_probe_init(struct sec_dev *sec) sec_open_sva_prefetch(qm); hisi_qm_dev_err_init(qm); sec_debug_regs_clear(qm); + ret = sec_show_last_regs_init(qm); + if (ret) + pci_err(qm->pdev, "Failed to init last word regs!\n"); + + return ret; +} + +static int sec_set_qm_algs(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + char *algs, *ptr; + u64 alg_mask; + int i; + + if (!qm->use_sva) + return 0; + + algs = devm_kzalloc(dev, SEC_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); + if (!algs) + return -ENOMEM; + + alg_mask = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH, SEC_DEV_ALG_BITMAP_LOW); + + for (i = 0; i < ARRAY_SIZE(sec_dev_algs); i++) + if (alg_mask & sec_dev_algs[i].alg_msk) + strcat(algs, sec_dev_algs[i].algs); + + ptr = strrchr(algs, '\n'); + if (ptr) + *ptr = '\0'; + + qm->uacce->algs = algs; return 0; } @@ -872,12 +1112,11 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->pdev = pdev; qm->ver = pdev->revision; - qm->algs = "cipher\ndigest\naead"; qm->mode = uacce_mode; qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; - qm->fun_type = (pdev->device == SEC_PF_PCI_DEVICE_ID) ? + qm->fun_type = (pdev->device == PCI_DEVICE_ID_HUAWEI_SEC_PF) ? QM_HW_PF : QM_HW_VF; if (qm->fun_type == QM_HW_PF) { qm->qp_base = SEC_PF_DEF_Q_BASE; @@ -895,23 +1134,17 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = SEC_QUEUE_NUM_V1 - SEC_PF_DEF_Q_NUM; } - /* - * WQ_HIGHPRI: SEC request must be low delayed, - * so need a high priority workqueue. - * WQ_UNBOUND: SEC task is likely with long - * running CPU intensive workloads. - */ - qm->wq = alloc_workqueue("%s", WQ_HIGHPRI | WQ_MEM_RECLAIM | - WQ_UNBOUND, num_online_cpus(), - pci_name(qm->pdev)); - if (!qm->wq) { - pci_err(qm->pdev, "fail to alloc workqueue\n"); - return -ENOMEM; + ret = hisi_qm_init(qm); + if (ret) { + pci_err(qm->pdev, "Failed to init sec qm configures!\n"); + return ret; } - ret = hisi_qm_init(qm); - if (ret) - destroy_workqueue(qm->wq); + ret = sec_set_qm_algs(qm); + if (ret) { + pci_err(qm->pdev, "Failed to set sec algs!\n"); + hisi_qm_uninit(qm); + } return ret; } @@ -944,8 +1177,6 @@ static int sec_probe_init(struct sec_dev *sec) static void sec_probe_uninit(struct hisi_qm *qm) { hisi_qm_dev_err_uninit(qm); - - destroy_workqueue(qm->wq); } static void sec_iommu_used_check(struct sec_dev *sec) @@ -1037,6 +1268,7 @@ err_qm_stop: sec_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); err_probe_uninit: + sec_show_last_regs_uninit(qm); sec_probe_uninit(qm); err_qm_uninit: sec_qm_uninit(qm); @@ -1061,6 +1293,7 @@ static void sec_remove(struct pci_dev *pdev) if (qm->fun_type == QM_HW_PF) sec_debug_regs_clear(qm); + sec_show_last_regs_uninit(qm); sec_probe_uninit(qm); @@ -1089,6 +1322,12 @@ static struct pci_driver sec_pci_driver = { .driver.pm = &sec_pm_ops, }; +struct pci_driver *hisi_sec_get_pf_driver(void) +{ + return &sec_pci_driver; +} +EXPORT_SYMBOL_GPL(hisi_sec_get_pf_driver); + static void sec_register_debugfs(void) { if (!debugfs_initialized()) diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 057273769f26..2b6f2281cfd6 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 HiSilicon Limited. */ +#include <linux/align.h> #include <linux/dma-mapping.h> +#include <linux/hisi_acc_qm.h> #include <linux/module.h> #include <linux/slab.h> -#include "qm.h" #define HISI_ACC_SGL_SGE_NR_MIN 1 #define HISI_ACC_SGL_NR_MAX 256 @@ -64,8 +65,9 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, if (!dev || !count || !sge_nr || sge_nr > HISI_ACC_SGL_SGE_NR_MAX) return ERR_PTR(-EINVAL); - sgl_size = sizeof(struct acc_hw_sge) * sge_nr + - sizeof(struct hisi_acc_hw_sgl); + sgl_size = ALIGN(sizeof(struct acc_hw_sge) * sge_nr + + sizeof(struct hisi_acc_hw_sgl), + HISI_ACC_SGL_ALIGN_SIZE); /* * the pool may allocate a block of memory of size PAGE_SIZE * 2^(MAX_ORDER - 1), diff --git a/drivers/crypto/hisilicon/trng/trng.c b/drivers/crypto/hisilicon/trng/trng.c index 829f2caf0f67..97e500db0a82 100644 --- a/drivers/crypto/hisilicon/trng/trng.c +++ b/drivers/crypto/hisilicon/trng/trng.c @@ -185,7 +185,7 @@ static int hisi_trng_read(struct hwrng *rng, void *buf, size_t max, bool wait) struct hisi_trng *trng; int currsize = 0; u32 val = 0; - u32 ret; + int ret; trng = container_of(rng, struct hisi_trng, rng); diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h index 517fdbdff3ea..f2e6da3240ae 100644 --- a/drivers/crypto/hisilicon/zip/zip.h +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -7,7 +7,7 @@ #define pr_fmt(fmt) "hisi_zip: " fmt #include <linux/list.h> -#include "../qm.h" +#include <linux/hisi_acc_qm.h> enum hisi_zip_error_type { /* negative compression */ @@ -81,7 +81,8 @@ struct hisi_zip_sqe { u32 rsvd1[4]; }; -int zip_create_qps(struct hisi_qp **qps, int ctx_num, int node); +int zip_create_qps(struct hisi_qp **qps, int qp_num, int node); int hisi_zip_register_to_crypto(struct hisi_qm *qm); void hisi_zip_unregister_from_crypto(struct hisi_qm *qm); +bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg); #endif diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c index 9520a4113c81..6608971d10cd 100644 --- a/drivers/crypto/hisilicon/zip/zip_crypto.c +++ b/drivers/crypto/hisilicon/zip/zip_crypto.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 HiSilicon Limited. */ #include <crypto/internal/acompress.h> #include <linux/bitfield.h> +#include <linux/bitmap.h> #include <linux/dma-mapping.h> #include <linux/scatterlist.h> #include "zip.h" @@ -38,6 +39,9 @@ #define HZIP_ALG_PRIORITY 300 #define HZIP_SGL_SGE_NR 10 +#define HZIP_ALG_ZLIB GENMASK(1, 0) +#define HZIP_ALG_GZIP GENMASK(3, 2) + static const u8 zlib_head[HZIP_ZLIB_HEAD_SIZE] = {0x78, 0x9c}; static const u8 gzip_head[HZIP_GZIP_HEAD_SIZE] = { 0x1f, 0x8b, 0x08, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x03 @@ -122,19 +126,19 @@ static int sgl_sge_nr_set(const char *val, const struct kernel_param *kp) if (ret || n == 0 || n > HISI_ACC_SGL_SGE_NR_MAX) return -EINVAL; - return param_set_int(val, kp); + return param_set_ushort(val, kp); } static const struct kernel_param_ops sgl_sge_nr_ops = { .set = sgl_sge_nr_set, - .get = param_get_int, + .get = param_get_ushort, }; static u16 sgl_sge_nr = HZIP_SGL_SGE_NR; module_param_cb(sgl_sge_nr, &sgl_sge_nr_ops, &sgl_sge_nr, 0444); MODULE_PARM_DESC(sgl_sge_nr, "Number of sge in sgl(1-255)"); -static u16 get_extra_field_size(const u8 *start) +static u32 get_extra_field_size(const u8 *start) { return *((u16 *)start) + GZIP_HEAD_FEXTRA_XLEN; } @@ -166,7 +170,7 @@ static u32 __get_gzip_head_size(const u8 *src) return size; } -static size_t __maybe_unused get_gzip_head_size(struct scatterlist *sgl) +static u32 __maybe_unused get_gzip_head_size(struct scatterlist *sgl) { char buf[HZIP_GZIP_HEAD_BUF]; @@ -182,7 +186,7 @@ static int add_comp_head(struct scatterlist *dst, u8 req_type) int ret; ret = sg_copy_from_buffer(dst, sg_nents(dst), head, head_size); - if (ret != head_size) { + if (unlikely(ret != head_size)) { pr_err("the head size of buffer is wrong (%d)!\n", ret); return -ENOMEM; } @@ -192,11 +196,11 @@ static int add_comp_head(struct scatterlist *dst, u8 req_type) static int get_comp_head_size(struct acomp_req *acomp_req, u8 req_type) { - if (!acomp_req->src || !acomp_req->slen) + if (unlikely(!acomp_req->src || !acomp_req->slen)) return -EINVAL; - if (req_type == HZIP_ALG_TYPE_GZIP && - acomp_req->slen < GZIP_HEAD_FEXTRA_SHIFT) + if (unlikely(req_type == HZIP_ALG_TYPE_GZIP && + acomp_req->slen < GZIP_HEAD_FEXTRA_SHIFT)) return -EINVAL; switch (req_type) { @@ -229,6 +233,8 @@ static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req, } set_bit(req_id, req_q->req_bitmap); + write_unlock(&req_q->req_lock); + req_cache = q + req_id; req_cache->req_id = req_id; req_cache->req = req; @@ -241,8 +247,6 @@ static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req, req_cache->dskip = 0; } - write_unlock(&req_q->req_lock); - return req_cache; } @@ -253,7 +257,6 @@ static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx, write_lock(&req_q->req_lock); clear_bit(req->req_id, req_q->req_bitmap); - memset(req, 0, sizeof(struct hisi_zip_req)); write_unlock(&req_q->req_lock); } @@ -338,7 +341,7 @@ static int hisi_zip_do_work(struct hisi_zip_req *req, struct hisi_zip_sqe zip_sqe; int ret; - if (!a_req->src || !a_req->slen || !a_req->dst || !a_req->dlen) + if (unlikely(!a_req->src || !a_req->slen || !a_req->dst || !a_req->dlen)) return -EINVAL; req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->src, pool, @@ -364,7 +367,7 @@ static int hisi_zip_do_work(struct hisi_zip_req *req, /* send command to start a task */ atomic64_inc(&dfx->send_cnt); ret = hisi_qp_send(qp, &zip_sqe); - if (ret < 0) { + if (unlikely(ret < 0)) { atomic64_inc(&dfx->send_busy_cnt); ret = -EAGAIN; dev_dbg_ratelimited(dev, "failed to send request!\n"); @@ -416,7 +419,7 @@ static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data) atomic64_inc(&dfx->recv_cnt); status = ops->get_status(sqe); - if (status != 0 && status != HZIP_NC_ERR) { + if (unlikely(status != 0 && status != HZIP_NC_ERR)) { dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n", (qp->alg_type == 0) ? "" : "de", qp->qp_id, status, sqe->produced); @@ -449,7 +452,7 @@ static int hisi_zip_acompress(struct acomp_req *acomp_req) /* let's output compression head now */ head_size = add_comp_head(acomp_req->dst, qp_ctx->qp->req_type); - if (head_size < 0) { + if (unlikely(head_size < 0)) { dev_err_ratelimited(dev, "failed to add comp head (%d)!\n", head_size); return head_size; @@ -460,7 +463,7 @@ static int hisi_zip_acompress(struct acomp_req *acomp_req) return PTR_ERR(req); ret = hisi_zip_do_work(req, qp_ctx); - if (ret != -EINPROGRESS) { + if (unlikely(ret != -EINPROGRESS)) { dev_info_ratelimited(dev, "failed to do compress (%d)!\n", ret); hisi_zip_remove_req(qp_ctx, req); } @@ -477,7 +480,7 @@ static int hisi_zip_adecompress(struct acomp_req *acomp_req) int head_size, ret; head_size = get_comp_head_size(acomp_req, qp_ctx->qp->req_type); - if (head_size < 0) { + if (unlikely(head_size < 0)) { dev_err_ratelimited(dev, "failed to get comp head size (%d)!\n", head_size); return head_size; @@ -488,7 +491,7 @@ static int hisi_zip_adecompress(struct acomp_req *acomp_req) return PTR_ERR(req); ret = hisi_zip_do_work(req, qp_ctx); - if (ret != -EINPROGRESS) { + if (unlikely(ret != -EINPROGRESS)) { dev_info_ratelimited(dev, "failed to do decompress (%d)!\n", ret); hisi_zip_remove_req(qp_ctx, req); @@ -497,7 +500,7 @@ static int hisi_zip_adecompress(struct acomp_req *acomp_req) return ret; } -static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx, +static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *qp_ctx, int alg_type, int req_type) { struct device *dev = &qp->qm->pdev->dev; @@ -505,7 +508,7 @@ static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx, qp->req_type = req_type; qp->alg_type = alg_type; - qp->qp_ctx = ctx; + qp->qp_ctx = qp_ctx; ret = hisi_qm_start_qp(qp, 0); if (ret < 0) { @@ -513,15 +516,15 @@ static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx, return ret; } - ctx->qp = qp; + qp_ctx->qp = qp; return 0; } -static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx) +static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *qp_ctx) { - hisi_qm_stop_qp(ctx->qp); - hisi_qm_release_qp(ctx->qp); + hisi_qm_stop_qp(qp_ctx->qp); + hisi_qm_free_qps(&qp_ctx->qp, 1); } static const struct hisi_zip_sqe_ops hisi_zip_ops_v1 = { @@ -593,27 +596,27 @@ static void hisi_zip_ctx_exit(struct hisi_zip_ctx *hisi_zip_ctx) { int i; - for (i = 1; i >= 0; i--) + for (i = 0; i < HZIP_CTX_Q_NUM; i++) hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]); } static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx) { + u16 q_depth = ctx->qp_ctx[0].qp->sq_depth; struct hisi_zip_req_q *req_q; int i, ret; for (i = 0; i < HZIP_CTX_Q_NUM; i++) { req_q = &ctx->qp_ctx[i].req_q; - req_q->size = QM_Q_DEPTH; + req_q->size = q_depth; - req_q->req_bitmap = kcalloc(BITS_TO_LONGS(req_q->size), - sizeof(long), GFP_KERNEL); + req_q->req_bitmap = bitmap_zalloc(req_q->size, GFP_KERNEL); if (!req_q->req_bitmap) { ret = -ENOMEM; if (i == 0) return ret; - goto err_free_loop0; + goto err_free_comp_q; } rwlock_init(&req_q->req_lock); @@ -622,20 +625,20 @@ static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx) if (!req_q->q) { ret = -ENOMEM; if (i == 0) - goto err_free_bitmap; + goto err_free_comp_bitmap; else - goto err_free_loop1; + goto err_free_decomp_bitmap; } } return 0; -err_free_loop1: - kfree(ctx->qp_ctx[HZIP_QPC_DECOMP].req_q.req_bitmap); -err_free_loop0: +err_free_decomp_bitmap: + bitmap_free(ctx->qp_ctx[HZIP_QPC_DECOMP].req_q.req_bitmap); +err_free_comp_q: kfree(ctx->qp_ctx[HZIP_QPC_COMP].req_q.q); -err_free_bitmap: - kfree(ctx->qp_ctx[HZIP_QPC_COMP].req_q.req_bitmap); +err_free_comp_bitmap: + bitmap_free(ctx->qp_ctx[HZIP_QPC_COMP].req_q.req_bitmap); return ret; } @@ -645,12 +648,13 @@ static void hisi_zip_release_req_q(struct hisi_zip_ctx *ctx) for (i = 0; i < HZIP_CTX_Q_NUM; i++) { kfree(ctx->qp_ctx[i].req_q.q); - kfree(ctx->qp_ctx[i].req_q.req_bitmap); + bitmap_free(ctx->qp_ctx[i].req_q.req_bitmap); } } static int hisi_zip_create_sgl_pool(struct hisi_zip_ctx *ctx) { + u16 q_depth = ctx->qp_ctx[0].qp->sq_depth; struct hisi_zip_qp_ctx *tmp; struct device *dev; int i; @@ -658,7 +662,7 @@ static int hisi_zip_create_sgl_pool(struct hisi_zip_ctx *ctx) for (i = 0; i < HZIP_CTX_Q_NUM; i++) { tmp = &ctx->qp_ctx[i]; dev = &tmp->qp->qm->pdev->dev; - tmp->sgl_pool = hisi_acc_create_sgl_pool(dev, QM_Q_DEPTH << 1, + tmp->sgl_pool = hisi_acc_create_sgl_pool(dev, q_depth << 1, sgl_sge_nr); if (IS_ERR(tmp->sgl_pool)) { if (i == 1) @@ -755,6 +759,28 @@ static struct acomp_alg hisi_zip_acomp_zlib = { } }; +static int hisi_zip_register_zlib(struct hisi_qm *qm) +{ + int ret; + + if (!hisi_zip_alg_support(qm, HZIP_ALG_ZLIB)) + return 0; + + ret = crypto_register_acomp(&hisi_zip_acomp_zlib); + if (ret) + dev_err(&qm->pdev->dev, "failed to register to zlib (%d)!\n", ret); + + return ret; +} + +static void hisi_zip_unregister_zlib(struct hisi_qm *qm) +{ + if (!hisi_zip_alg_support(qm, HZIP_ALG_ZLIB)) + return; + + crypto_unregister_acomp(&hisi_zip_acomp_zlib); +} + static struct acomp_alg hisi_zip_acomp_gzip = { .init = hisi_zip_acomp_init, .exit = hisi_zip_acomp_exit, @@ -769,27 +795,45 @@ static struct acomp_alg hisi_zip_acomp_gzip = { } }; -int hisi_zip_register_to_crypto(struct hisi_qm *qm) +static int hisi_zip_register_gzip(struct hisi_qm *qm) { int ret; - ret = crypto_register_acomp(&hisi_zip_acomp_zlib); - if (ret) { - pr_err("failed to register to zlib (%d)!\n", ret); - return ret; - } + if (!hisi_zip_alg_support(qm, HZIP_ALG_GZIP)) + return 0; ret = crypto_register_acomp(&hisi_zip_acomp_gzip); - if (ret) { - pr_err("failed to register to gzip (%d)!\n", ret); - crypto_unregister_acomp(&hisi_zip_acomp_zlib); - } + if (ret) + dev_err(&qm->pdev->dev, "failed to register to gzip (%d)!\n", ret); return ret; } -void hisi_zip_unregister_from_crypto(struct hisi_qm *qm) +static void hisi_zip_unregister_gzip(struct hisi_qm *qm) { + if (!hisi_zip_alg_support(qm, HZIP_ALG_GZIP)) + return; + crypto_unregister_acomp(&hisi_zip_acomp_gzip); - crypto_unregister_acomp(&hisi_zip_acomp_zlib); +} + +int hisi_zip_register_to_crypto(struct hisi_qm *qm) +{ + int ret = 0; + + ret = hisi_zip_register_zlib(qm); + if (ret) + return ret; + + ret = hisi_zip_register_gzip(qm); + if (ret) + hisi_zip_unregister_zlib(qm); + + return ret; +} + +void hisi_zip_unregister_from_crypto(struct hisi_qm *qm) +{ + hisi_zip_unregister_zlib(qm); + hisi_zip_unregister_gzip(qm); } diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 678f8b58ec42..c863435e8c75 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -15,24 +15,11 @@ #include <linux/uacce.h> #include "zip.h" -#define PCI_DEVICE_ID_ZIP_PF 0xa250 -#define PCI_DEVICE_ID_ZIP_VF 0xa251 +#define PCI_DEVICE_ID_HUAWEI_ZIP_PF 0xa250 #define HZIP_QUEUE_NUM_V1 4096 #define HZIP_CLOCK_GATE_CTRL 0x301004 -#define COMP0_ENABLE BIT(0) -#define COMP1_ENABLE BIT(1) -#define DECOMP0_ENABLE BIT(2) -#define DECOMP1_ENABLE BIT(3) -#define DECOMP2_ENABLE BIT(4) -#define DECOMP3_ENABLE BIT(5) -#define DECOMP4_ENABLE BIT(6) -#define DECOMP5_ENABLE BIT(7) -#define HZIP_ALL_COMP_DECOMP_EN (COMP0_ENABLE | COMP1_ENABLE | \ - DECOMP0_ENABLE | DECOMP1_ENABLE | \ - DECOMP2_ENABLE | DECOMP3_ENABLE | \ - DECOMP4_ENABLE | DECOMP5_ENABLE) #define HZIP_DECOMP_CHECK_ENABLE BIT(16) #define HZIP_FSM_MAX_CNT 0x301008 @@ -50,14 +37,18 @@ #define HZIP_QM_IDEL_STATUS 0x3040e4 -#define HZIP_CORE_DEBUG_COMP_0 0x302000 -#define HZIP_CORE_DEBUG_COMP_1 0x303000 -#define HZIP_CORE_DEBUG_DECOMP_0 0x304000 -#define HZIP_CORE_DEBUG_DECOMP_1 0x305000 -#define HZIP_CORE_DEBUG_DECOMP_2 0x306000 -#define HZIP_CORE_DEBUG_DECOMP_3 0x307000 -#define HZIP_CORE_DEBUG_DECOMP_4 0x308000 -#define HZIP_CORE_DEBUG_DECOMP_5 0x309000 +#define HZIP_CORE_DFX_BASE 0x301000 +#define HZIP_CLOCK_GATED_CONTL 0X301004 +#define HZIP_CORE_DFX_COMP_0 0x302000 +#define HZIP_CORE_DFX_COMP_1 0x303000 +#define HZIP_CORE_DFX_DECOMP_0 0x304000 +#define HZIP_CORE_DFX_DECOMP_1 0x305000 +#define HZIP_CORE_DFX_DECOMP_2 0x306000 +#define HZIP_CORE_DFX_DECOMP_3 0x307000 +#define HZIP_CORE_DFX_DECOMP_4 0x308000 +#define HZIP_CORE_DFX_DECOMP_5 0x309000 +#define HZIP_CORE_REGS_BASE_LEN 0xB0 +#define HZIP_CORE_REGS_DFX_LEN 0x28 #define HZIP_CORE_INT_SOURCE 0x3010A0 #define HZIP_CORE_INT_MASK_REG 0x3010A4 @@ -66,20 +57,14 @@ #define HZIP_CORE_INT_STATUS_M_ECC BIT(1) #define HZIP_CORE_SRAM_ECC_ERR_INFO 0x301148 #define HZIP_CORE_INT_RAS_CE_ENB 0x301160 -#define HZIP_CORE_INT_RAS_CE_ENABLE 0x1 #define HZIP_CORE_INT_RAS_NFE_ENB 0x301164 #define HZIP_CORE_INT_RAS_FE_ENB 0x301168 +#define HZIP_CORE_INT_RAS_FE_ENB_MASK 0x0 #define HZIP_OOO_SHUTDOWN_SEL 0x30120C -#define HZIP_CORE_INT_RAS_NFE_ENABLE 0x1FFE #define HZIP_SRAM_ECC_ERR_NUM_SHIFT 16 #define HZIP_SRAM_ECC_ERR_ADDR_SHIFT 24 #define HZIP_CORE_INT_MASK_ALL GENMASK(12, 0) -#define HZIP_COMP_CORE_NUM 2 -#define HZIP_DECOMP_CORE_NUM 6 -#define HZIP_CORE_NUM (HZIP_COMP_CORE_NUM + \ - HZIP_DECOMP_CORE_NUM) #define HZIP_SQE_SIZE 128 -#define HZIP_SQ_SIZE (HZIP_SQE_SIZE * QM_Q_DEPTH) #define HZIP_PF_DEF_Q_NUM 64 #define HZIP_PF_DEF_Q_BASE 0 @@ -89,6 +74,12 @@ #define HZIP_AXI_SHUTDOWN_ENABLE BIT(14) #define HZIP_WR_PORT BIT(11) +#define HZIP_DEV_ALG_MAX_LEN 256 +#define HZIP_ALG_ZLIB_BIT GENMASK(1, 0) +#define HZIP_ALG_GZIP_BIT GENMASK(3, 2) +#define HZIP_ALG_DEFLATE_BIT GENMASK(5, 4) +#define HZIP_ALG_LZ77_BIT GENMASK(7, 6) + #define HZIP_BUF_SIZE 22 #define HZIP_SQE_MASK_OFFSET 64 #define HZIP_SQE_MASK_LEN 48 @@ -129,6 +120,26 @@ struct zip_dfx_item { u32 offset; }; +struct zip_dev_alg { + u32 alg_msk; + const char *algs; +}; + +static const struct zip_dev_alg zip_dev_algs[] = { { + .alg_msk = HZIP_ALG_ZLIB_BIT, + .algs = "zlib\n", + }, { + .alg_msk = HZIP_ALG_GZIP_BIT, + .algs = "gzip\n", + }, { + .alg_msk = HZIP_ALG_DEFLATE_BIT, + .algs = "deflate\n", + }, { + .alg_msk = HZIP_ALG_LZ77_BIT, + .algs = "lz77_zstd\n", + }, +}; + static struct hisi_qm_list zip_devices = { .register_to_crypto = hisi_zip_register_to_crypto, .unregister_from_crypto = hisi_zip_unregister_from_crypto, @@ -184,6 +195,58 @@ struct hisi_zip_ctrl { struct ctrl_debug_file files[HZIP_DEBUG_FILE_NUM]; }; +enum zip_cap_type { + ZIP_QM_NFE_MASK_CAP = 0x0, + ZIP_QM_RESET_MASK_CAP, + ZIP_QM_OOO_SHUTDOWN_MASK_CAP, + ZIP_QM_CE_MASK_CAP, + ZIP_NFE_MASK_CAP, + ZIP_RESET_MASK_CAP, + ZIP_OOO_SHUTDOWN_MASK_CAP, + ZIP_CE_MASK_CAP, + ZIP_CLUSTER_NUM_CAP, + ZIP_CORE_TYPE_NUM_CAP, + ZIP_CORE_NUM_CAP, + ZIP_CLUSTER_COMP_NUM_CAP, + ZIP_CLUSTER_DECOMP_NUM_CAP, + ZIP_DECOMP_ENABLE_BITMAP, + ZIP_COMP_ENABLE_BITMAP, + ZIP_DRV_ALG_BITMAP, + ZIP_DEV_ALG_BITMAP, + ZIP_CORE1_ALG_BITMAP, + ZIP_CORE2_ALG_BITMAP, + ZIP_CORE3_ALG_BITMAP, + ZIP_CORE4_ALG_BITMAP, + ZIP_CORE5_ALG_BITMAP, + ZIP_CAP_MAX +}; + +static struct hisi_qm_cap_info zip_basic_cap_info[] = { + {ZIP_QM_NFE_MASK_CAP, 0x3124, 0, GENMASK(31, 0), 0x0, 0x1C57, 0x7C77}, + {ZIP_QM_RESET_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0xC57, 0x6C77}, + {ZIP_QM_OOO_SHUTDOWN_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0x4, 0x6C77}, + {ZIP_QM_CE_MASK_CAP, 0x312C, 0, GENMASK(31, 0), 0x0, 0x8, 0x8}, + {ZIP_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x7FE, 0x1FFE}, + {ZIP_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x7FE, 0x7FE}, + {ZIP_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x2, 0x7FE}, + {ZIP_CE_MASK_CAP, 0x3138, 0, GENMASK(31, 0), 0x0, 0x1, 0x1}, + {ZIP_CLUSTER_NUM_CAP, 0x313C, 28, GENMASK(3, 0), 0x1, 0x1, 0x1}, + {ZIP_CORE_TYPE_NUM_CAP, 0x313C, 24, GENMASK(3, 0), 0x2, 0x2, 0x2}, + {ZIP_CORE_NUM_CAP, 0x313C, 16, GENMASK(7, 0), 0x8, 0x8, 0x5}, + {ZIP_CLUSTER_COMP_NUM_CAP, 0x313C, 8, GENMASK(7, 0), 0x2, 0x2, 0x2}, + {ZIP_CLUSTER_DECOMP_NUM_CAP, 0x313C, 0, GENMASK(7, 0), 0x6, 0x6, 0x3}, + {ZIP_DECOMP_ENABLE_BITMAP, 0x3140, 16, GENMASK(15, 0), 0xFC, 0xFC, 0x1C}, + {ZIP_COMP_ENABLE_BITMAP, 0x3140, 0, GENMASK(15, 0), 0x3, 0x3, 0x3}, + {ZIP_DRV_ALG_BITMAP, 0x3144, 0, GENMASK(31, 0), 0xF, 0xF, 0xF}, + {ZIP_DEV_ALG_BITMAP, 0x3148, 0, GENMASK(31, 0), 0xF, 0xF, 0xFF}, + {ZIP_CORE1_ALG_BITMAP, 0x314C, 0, GENMASK(31, 0), 0x5, 0x5, 0xD5}, + {ZIP_CORE2_ALG_BITMAP, 0x3150, 0, GENMASK(31, 0), 0x5, 0x5, 0xD5}, + {ZIP_CORE3_ALG_BITMAP, 0x3154, 0, GENMASK(31, 0), 0xA, 0xA, 0x2A}, + {ZIP_CORE4_ALG_BITMAP, 0x3158, 0, GENMASK(31, 0), 0xA, 0xA, 0x2A}, + {ZIP_CORE5_ALG_BITMAP, 0x315C, 0, GENMASK(31, 0), 0xA, 0xA, 0x2A}, + {ZIP_CAP_MAX, 0x317c, 0, GENMASK(0, 0), 0x0, 0x0, 0x0} +}; + enum { HZIP_COMP_CORE0, HZIP_COMP_CORE1, @@ -231,6 +294,64 @@ static const struct debugfs_reg32 hzip_dfx_regs[] = { {"HZIP_DECOMP_LZ77_CURR_ST ", 0x9cull}, }; +static const struct debugfs_reg32 hzip_com_dfx_regs[] = { + {"HZIP_CLOCK_GATE_CTRL ", 0x301004}, + {"HZIP_CORE_INT_RAS_CE_ENB ", 0x301160}, + {"HZIP_CORE_INT_RAS_NFE_ENB ", 0x301164}, + {"HZIP_CORE_INT_RAS_FE_ENB ", 0x301168}, + {"HZIP_UNCOM_ERR_RAS_CTRL ", 0x30116C}, +}; + +static const struct debugfs_reg32 hzip_dump_dfx_regs[] = { + {"HZIP_GET_BD_NUM ", 0x00ull}, + {"HZIP_GET_RIGHT_BD ", 0x04ull}, + {"HZIP_GET_ERROR_BD ", 0x08ull}, + {"HZIP_DONE_BD_NUM ", 0x0cull}, + {"HZIP_MAX_DELAY ", 0x20ull}, +}; + +/* define the ZIP's dfx regs region and region length */ +static struct dfx_diff_registers hzip_diff_regs[] = { + { + .reg_offset = HZIP_CORE_DFX_BASE, + .reg_len = HZIP_CORE_REGS_BASE_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_COMP_0, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_COMP_1, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_DECOMP_0, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_DECOMP_1, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_DECOMP_2, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_DECOMP_3, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_DECOMP_4, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, { + .reg_offset = HZIP_CORE_DFX_DECOMP_5, + .reg_len = HZIP_CORE_REGS_DFX_LEN, + }, +}; + +static int hzip_diff_regs_show(struct seq_file *s, void *unused) +{ + struct hisi_qm *qm = s->private; + + hisi_qm_acc_diff_regs_dump(qm, s, qm->debug.acc_diff_regs, + ARRAY_SIZE(hzip_diff_regs)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(hzip_diff_regs); static const struct kernel_param_ops zip_uacce_mode_ops = { .set = uacce_mode_set, .get = param_get_int, @@ -246,7 +367,7 @@ MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); static int pf_q_num_set(const char *val, const struct kernel_param *kp) { - return q_num_set(val, kp, PCI_DEVICE_ID_ZIP_PF); + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_ZIP_PF); } static const struct kernel_param_ops pf_q_num_ops = { @@ -268,8 +389,8 @@ module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444); MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); static const struct pci_device_id hisi_zip_dev_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_PF) }, - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_VF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_ZIP_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_ZIP_VF) }, { 0, } }; MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids); @@ -282,12 +403,52 @@ int zip_create_qps(struct hisi_qp **qps, int qp_num, int node) return hisi_qm_alloc_qps_node(&zip_devices, qp_num, 0, node, qps); } +bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg) +{ + u32 cap_val; + + cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DRV_ALG_BITMAP, qm->cap_ver); + if ((alg & cap_val) == alg) + return true; + + return false; +} + +static int hisi_zip_set_qm_algs(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + char *algs, *ptr; + u32 alg_mask; + int i; + + if (!qm->use_sva) + return 0; + + algs = devm_kzalloc(dev, HZIP_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); + if (!algs) + return -ENOMEM; + + alg_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DEV_ALG_BITMAP, qm->cap_ver); + + for (i = 0; i < ARRAY_SIZE(zip_dev_algs); i++) + if (alg_mask & zip_dev_algs[i].alg_msk) + strcat(algs, zip_dev_algs[i].algs); + + ptr = strrchr(algs, '\n'); + if (ptr) + *ptr = '\0'; + + qm->uacce->algs = algs; + + return 0; +} + static void hisi_zip_open_sva_prefetch(struct hisi_qm *qm) { u32 val; int ret; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; /* Enable prefetch */ @@ -307,7 +468,7 @@ static void hisi_zip_close_sva_prefetch(struct hisi_qm *qm) u32 val; int ret; - if (qm->ver < QM_HW_V3) + if (!test_bit(QM_SUPPORT_SVA_PREFETCH, &qm->caps)) return; val = readl_relaxed(qm->io_base + HZIP_PREFETCH_CFG); @@ -340,6 +501,7 @@ static void hisi_zip_enable_clock_gate(struct hisi_qm *qm) static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm) { void __iomem *base = qm->io_base; + u32 dcomp_bm, comp_bm; /* qm user domain */ writel(AXUSER_BASE, base + QM_ARUSER_M_CFG_1); @@ -377,8 +539,11 @@ static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm) } /* let's open all compression/decompression cores */ - writel(HZIP_DECOMP_CHECK_ENABLE | HZIP_ALL_COMP_DECOMP_EN, - base + HZIP_CLOCK_GATE_CTRL); + dcomp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_DECOMP_ENABLE_BITMAP, qm->cap_ver); + comp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_COMP_ENABLE_BITMAP, qm->cap_ver); + writel(HZIP_DECOMP_CHECK_ENABLE | dcomp_bm | comp_bm, base + HZIP_CLOCK_GATE_CTRL); /* enable sqc,cqc writeback */ writel(SQC_CACHE_ENABLE | CQC_CACHE_ENABLE | SQC_CACHE_WB_ENABLE | @@ -397,7 +562,8 @@ static void hisi_zip_master_ooo_ctrl(struct hisi_qm *qm, bool enable) val1 = readl(qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL); if (enable) { val1 |= HZIP_AXI_SHUTDOWN_ENABLE; - val2 = HZIP_CORE_INT_RAS_NFE_ENABLE; + val2 = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); } else { val1 &= ~HZIP_AXI_SHUTDOWN_ENABLE; val2 = 0x0; @@ -411,6 +577,8 @@ static void hisi_zip_master_ooo_ctrl(struct hisi_qm *qm, bool enable) static void hisi_zip_hw_error_enable(struct hisi_qm *qm) { + u32 nfe, ce; + if (qm->ver == QM_HW_V1) { writel(HZIP_CORE_INT_MASK_ALL, qm->io_base + HZIP_CORE_INT_MASK_REG); @@ -418,17 +586,17 @@ static void hisi_zip_hw_error_enable(struct hisi_qm *qm) return; } + nfe = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_NFE_MASK_CAP, qm->cap_ver); + ce = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CE_MASK_CAP, qm->cap_ver); + /* clear ZIP hw error source if having */ - writel(HZIP_CORE_INT_MASK_ALL, qm->io_base + HZIP_CORE_INT_SOURCE); + writel(ce | nfe | HZIP_CORE_INT_RAS_FE_ENB_MASK, qm->io_base + HZIP_CORE_INT_SOURCE); /* configure error type */ - writel(HZIP_CORE_INT_RAS_CE_ENABLE, - qm->io_base + HZIP_CORE_INT_RAS_CE_ENB); - writel(0x0, qm->io_base + HZIP_CORE_INT_RAS_FE_ENB); - writel(HZIP_CORE_INT_RAS_NFE_ENABLE, - qm->io_base + HZIP_CORE_INT_RAS_NFE_ENB); + writel(ce, qm->io_base + HZIP_CORE_INT_RAS_CE_ENB); + writel(HZIP_CORE_INT_RAS_FE_ENB_MASK, qm->io_base + HZIP_CORE_INT_RAS_FE_ENB); + writel(nfe, qm->io_base + HZIP_CORE_INT_RAS_NFE_ENB); - /* enable ZIP block master OOO when nfe occurs on Kunpeng930 */ hisi_zip_master_ooo_ctrl(qm, true); /* enable ZIP hw error interrupts */ @@ -437,10 +605,13 @@ static void hisi_zip_hw_error_enable(struct hisi_qm *qm) static void hisi_zip_hw_error_disable(struct hisi_qm *qm) { + u32 nfe, ce; + /* disable ZIP hw error interrupts */ - writel(HZIP_CORE_INT_MASK_ALL, qm->io_base + HZIP_CORE_INT_MASK_REG); + nfe = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_NFE_MASK_CAP, qm->cap_ver); + ce = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CE_MASK_CAP, qm->cap_ver); + writel(ce | nfe | HZIP_CORE_INT_RAS_FE_ENB_MASK, qm->io_base + HZIP_CORE_INT_MASK_REG); - /* disable ZIP block master OOO when nfe occurs on Kunpeng930 */ hisi_zip_master_ooo_ctrl(qm, false); } @@ -525,8 +696,9 @@ static ssize_t hisi_zip_ctrl_debug_write(struct file *filp, return len; tbuf[len] = '\0'; - if (kstrtoul(tbuf, 0, &val)) - return -EFAULT; + ret = kstrtoul(tbuf, 0, &val); + if (ret) + return ret; ret = hisi_qm_get_dfx_access(qm); if (ret) @@ -590,18 +762,23 @@ DEFINE_SHOW_ATTRIBUTE(hisi_zip_regs); static int hisi_zip_core_debug_init(struct hisi_qm *qm) { + u32 zip_core_num, zip_comp_core_num; struct device *dev = &qm->pdev->dev; struct debugfs_regset32 *regset; struct dentry *tmp_d; char buf[HZIP_BUF_SIZE]; int i; - for (i = 0; i < HZIP_CORE_NUM; i++) { - if (i < HZIP_COMP_CORE_NUM) + zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); + zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP, + qm->cap_ver); + + for (i = 0; i < zip_core_num; i++) { + if (i < zip_comp_core_num) scnprintf(buf, sizeof(buf), "comp_core%d", i); else scnprintf(buf, sizeof(buf), "decomp_core%d", - i - HZIP_COMP_CORE_NUM); + i - zip_comp_core_num); regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL); if (!regset) @@ -614,7 +791,7 @@ static int hisi_zip_core_debug_init(struct hisi_qm *qm) tmp_d = debugfs_create_dir(buf, qm->debug.debug_root); debugfs_create_file("regs", 0444, tmp_d, regset, - &hisi_zip_regs_fops); + &hisi_zip_regs_fops); } return 0; @@ -622,6 +799,7 @@ static int hisi_zip_core_debug_init(struct hisi_qm *qm) static void hisi_zip_dfx_debug_init(struct hisi_qm *qm) { + struct dfx_diff_registers *hzip_regs = qm->debug.acc_diff_regs; struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm); struct hisi_zip_dfx *dfx = &zip->dfx; struct dentry *tmp_dir; @@ -635,6 +813,10 @@ static void hisi_zip_dfx_debug_init(struct hisi_qm *qm) 0644, tmp_dir, data, &zip_atomic64_ops); } + + if (qm->fun_type == QM_HW_PF && hzip_regs) + debugfs_create_file("diff_regs", 0444, tmp_dir, + qm, &hzip_diff_regs_fops); } static int hisi_zip_ctrl_debug_init(struct hisi_qm *qm) @@ -667,6 +849,13 @@ static int hisi_zip_debugfs_init(struct hisi_qm *qm) qm->debug.sqe_mask_offset = HZIP_SQE_MASK_OFFSET; qm->debug.sqe_mask_len = HZIP_SQE_MASK_LEN; qm->debug.debug_root = dev_d; + ret = hisi_qm_diff_regs_init(qm, hzip_diff_regs, + ARRAY_SIZE(hzip_diff_regs)); + if (ret) { + dev_warn(dev, "Failed to init ZIP diff regs!\n"); + goto debugfs_remove; + } + hisi_qm_debug_init(qm); if (qm->fun_type == QM_HW_PF) { @@ -680,6 +869,8 @@ static int hisi_zip_debugfs_init(struct hisi_qm *qm) return 0; failed_to_create: + hisi_qm_diff_regs_uninit(qm, ARRAY_SIZE(hzip_diff_regs)); +debugfs_remove: debugfs_remove_recursive(hzip_debugfs_root); return ret; } @@ -704,6 +895,8 @@ static void hisi_zip_debug_regs_clear(struct hisi_qm *qm) static void hisi_zip_debugfs_exit(struct hisi_qm *qm) { + hisi_qm_diff_regs_uninit(qm, ARRAY_SIZE(hzip_diff_regs)); + debugfs_remove_recursive(qm->debug.debug_root); if (qm->fun_type == QM_HW_PF) { @@ -712,6 +905,95 @@ static void hisi_zip_debugfs_exit(struct hisi_qm *qm) } } +static int hisi_zip_show_last_regs_init(struct hisi_qm *qm) +{ + int core_dfx_regs_num = ARRAY_SIZE(hzip_dump_dfx_regs); + int com_dfx_regs_num = ARRAY_SIZE(hzip_com_dfx_regs); + struct qm_debug *debug = &qm->debug; + void __iomem *io_base; + u32 zip_core_num; + int i, j, idx; + + zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); + + debug->last_words = kcalloc(core_dfx_regs_num * zip_core_num + com_dfx_regs_num, + sizeof(unsigned int), GFP_KERNEL); + if (!debug->last_words) + return -ENOMEM; + + for (i = 0; i < com_dfx_regs_num; i++) { + io_base = qm->io_base + hzip_com_dfx_regs[i].offset; + debug->last_words[i] = readl_relaxed(io_base); + } + + for (i = 0; i < zip_core_num; i++) { + io_base = qm->io_base + core_offsets[i]; + for (j = 0; j < core_dfx_regs_num; j++) { + idx = com_dfx_regs_num + i * core_dfx_regs_num + j; + debug->last_words[idx] = readl_relaxed( + io_base + hzip_dump_dfx_regs[j].offset); + } + } + + return 0; +} + +static void hisi_zip_show_last_regs_uninit(struct hisi_qm *qm) +{ + struct qm_debug *debug = &qm->debug; + + if (qm->fun_type == QM_HW_VF || !debug->last_words) + return; + + kfree(debug->last_words); + debug->last_words = NULL; +} + +static void hisi_zip_show_last_dfx_regs(struct hisi_qm *qm) +{ + int core_dfx_regs_num = ARRAY_SIZE(hzip_dump_dfx_regs); + int com_dfx_regs_num = ARRAY_SIZE(hzip_com_dfx_regs); + u32 zip_core_num, zip_comp_core_num; + struct qm_debug *debug = &qm->debug; + char buf[HZIP_BUF_SIZE]; + void __iomem *base; + int i, j, idx; + u32 val; + + if (qm->fun_type == QM_HW_VF || !debug->last_words) + return; + + for (i = 0; i < com_dfx_regs_num; i++) { + val = readl_relaxed(qm->io_base + hzip_com_dfx_regs[i].offset); + if (debug->last_words[i] != val) + pci_info(qm->pdev, "com_dfx: %s \t= 0x%08x => 0x%08x\n", + hzip_com_dfx_regs[i].name, debug->last_words[i], val); + } + + zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); + zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP, + qm->cap_ver); + for (i = 0; i < zip_core_num; i++) { + if (i < zip_comp_core_num) + scnprintf(buf, sizeof(buf), "Comp_core-%d", i); + else + scnprintf(buf, sizeof(buf), "Decomp_core-%d", + i - zip_comp_core_num); + base = qm->io_base + core_offsets[i]; + + pci_info(qm->pdev, "==>%s:\n", buf); + /* dump last word for dfx regs during control resetting */ + for (j = 0; j < core_dfx_regs_num; j++) { + idx = com_dfx_regs_num + i * core_dfx_regs_num + j; + val = readl_relaxed(base + hzip_dump_dfx_regs[j].offset); + if (debug->last_words[idx] != val) + pci_info(qm->pdev, "%s \t= 0x%08x => 0x%08x\n", + hzip_dump_dfx_regs[j].name, + debug->last_words[idx], val); + } + } +} + static void hisi_zip_log_hw_error(struct hisi_qm *qm, u32 err_sts) { const struct hisi_zip_hw_error *err = zip_hw_error; @@ -742,7 +1024,11 @@ static u32 hisi_zip_get_hw_err_status(struct hisi_qm *qm) static void hisi_zip_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts) { + u32 nfe; + writel(err_sts, qm->io_base + HZIP_CORE_INT_SOURCE); + nfe = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_NFE_MASK_CAP, qm->cap_ver); + writel(nfe, qm->io_base + HZIP_CORE_INT_RAS_NFE_ENB); } static void hisi_zip_open_axi_master_ooo(struct hisi_qm *qm) @@ -776,16 +1062,21 @@ static void hisi_zip_err_info_init(struct hisi_qm *qm) { struct hisi_qm_err_info *err_info = &qm->err_info; - err_info->ce = QM_BASE_CE; - err_info->fe = 0; + err_info->fe = HZIP_CORE_INT_RAS_FE_ENB_MASK; + err_info->ce = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_QM_CE_MASK_CAP, qm->cap_ver); + err_info->nfe = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_QM_NFE_MASK_CAP, qm->cap_ver); err_info->ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; - err_info->dev_ce_mask = HZIP_CORE_INT_RAS_CE_ENABLE; + err_info->qm_shutdown_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_QM_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); + err_info->dev_shutdown_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_OOO_SHUTDOWN_MASK_CAP, qm->cap_ver); + err_info->qm_reset_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_QM_RESET_MASK_CAP, qm->cap_ver); + err_info->dev_reset_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + ZIP_RESET_MASK_CAP, qm->cap_ver); err_info->msi_wr_port = HZIP_WR_PORT; err_info->acpi_rst = "ZRST"; - err_info->nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; - - if (qm->ver >= QM_HW_V3) - err_info->nfe |= QM_ACC_DO_TASK_TIMEOUT; } static const struct hisi_qm_err_ini hisi_zip_err_ini = { @@ -799,6 +1090,7 @@ static const struct hisi_qm_err_ini hisi_zip_err_ini = { .close_axi_master_ooo = hisi_zip_close_axi_master_ooo, .open_sva_prefetch = hisi_zip_open_sva_prefetch, .close_sva_prefetch = hisi_zip_close_sva_prefetch, + .show_last_dfx_regs = hisi_zip_show_last_dfx_regs, .err_info_init = hisi_zip_err_info_init, }; @@ -806,6 +1098,7 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) { struct hisi_qm *qm = &hisi_zip->qm; struct hisi_zip_ctrl *ctrl; + int ret; ctrl = devm_kzalloc(&qm->pdev->dev, sizeof(*ctrl), GFP_KERNEL); if (!ctrl) @@ -816,12 +1109,19 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) qm->err_ini = &hisi_zip_err_ini; qm->err_ini->err_info_init(qm); - hisi_zip_set_user_domain_and_cache(qm); + ret = hisi_zip_set_user_domain_and_cache(qm); + if (ret) + return ret; + hisi_zip_open_sva_prefetch(qm); hisi_qm_dev_err_init(qm); hisi_zip_debug_regs_clear(qm); - return 0; + ret = hisi_zip_show_last_regs_init(qm); + if (ret) + pci_err(qm->pdev, "Failed to init last word regs!\n"); + + return ret; } static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) @@ -830,15 +1130,11 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->pdev = pdev; qm->ver = pdev->revision; - if (pdev->revision >= QM_HW_V3) - qm->algs = "zlib\ngzip\ndeflate\nlz77_zstd"; - else - qm->algs = "zlib\ngzip"; qm->mode = uacce_mode; qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; - qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? + qm->fun_type = (pdev->device == PCI_DEVICE_ID_HUAWEI_ZIP_PF) ? QM_HW_PF : QM_HW_VF; if (qm->fun_type == QM_HW_PF) { qm->qp_base = HZIP_PF_DEF_Q_BASE; @@ -857,17 +1153,17 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM; } - qm->wq = alloc_workqueue("%s", WQ_HIGHPRI | WQ_MEM_RECLAIM | - WQ_UNBOUND, num_online_cpus(), - pci_name(qm->pdev)); - if (!qm->wq) { - pci_err(qm->pdev, "fail to alloc workqueue\n"); - return -ENOMEM; + ret = hisi_qm_init(qm); + if (ret) { + pci_err(qm->pdev, "Failed to init zip qm configures!\n"); + return ret; } - ret = hisi_qm_init(qm); - if (ret) - destroy_workqueue(qm->wq); + ret = hisi_zip_set_qm_algs(qm); + if (ret) { + pci_err(qm->pdev, "Failed to set zip algs!\n"); + hisi_qm_uninit(qm); + } return ret; } @@ -875,7 +1171,6 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) static void hisi_zip_qm_uninit(struct hisi_qm *qm) { hisi_qm_uninit(qm); - destroy_workqueue(qm->wq); } static int hisi_zip_probe_init(struct hisi_zip *hisi_zip) @@ -965,6 +1260,7 @@ err_qm_stop: hisi_qm_stop(qm, QM_NORMAL); err_dev_err_uninit: + hisi_zip_show_last_regs_uninit(qm); hisi_qm_dev_err_uninit(qm); err_qm_uninit: @@ -986,6 +1282,7 @@ static void hisi_zip_remove(struct pci_dev *pdev) hisi_zip_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); + hisi_zip_show_last_regs_uninit(qm); hisi_qm_dev_err_uninit(qm); hisi_zip_qm_uninit(qm); } @@ -1013,6 +1310,12 @@ static struct pci_driver hisi_zip_pci_driver = { .driver.pm = &hisi_zip_pm_ops, }; +struct pci_driver *hisi_zip_get_pf_driver(void) +{ + return &hisi_zip_pci_driver; +} +EXPORT_SYMBOL_GPL(hisi_zip_get_pf_driver); + static void hisi_zip_register_debugfs(void) { if (!debugfs_initialized()) diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index 9ff885d50edf..ad0d8c4a71ac 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -1831,6 +1831,8 @@ static const struct of_device_id safexcel_of_match_table[] = { {}, }; +MODULE_DEVICE_TABLE(of, safexcel_of_match_table); + static struct platform_driver crypto_safexcel = { .probe = safexcel_probe, .remove = safexcel_remove, @@ -1997,3 +1999,12 @@ MODULE_AUTHOR("Igal Liberman <igall@marvell.com>"); MODULE_DESCRIPTION("Support for SafeXcel cryptographic engines: EIP97 & EIP197"); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(CRYPTO_INTERNAL); + +MODULE_FIRMWARE("ifpp.bin"); +MODULE_FIRMWARE("ipue.bin"); +MODULE_FIRMWARE("inside-secure/eip197b/ifpp.bin"); +MODULE_FIRMWARE("inside-secure/eip197b/ipue.bin"); +MODULE_FIRMWARE("inside-secure/eip197d/ifpp.bin"); +MODULE_FIRMWARE("inside-secure/eip197d/ipue.bin"); +MODULE_FIRMWARE("inside-secure/eip197_minifw/ifpp.bin"); +MODULE_FIRMWARE("inside-secure/eip197_minifw/ipue.bin"); diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h index ce1e611a163e..797ff91512e0 100644 --- a/drivers/crypto/inside-secure/safexcel.h +++ b/drivers/crypto/inside-secure/safexcel.h @@ -497,15 +497,15 @@ struct result_data_desc { u32 packet_length:17; u32 error_code:15; - u8 bypass_length:4; - u8 e15:1; - u16 rsvd0; - u8 hash_bytes:1; - u8 hash_length:6; - u8 generic_bytes:1; - u8 checksum:1; - u8 next_header:1; - u8 length:1; + u32 bypass_length:4; + u32 e15:1; + u32 rsvd0:16; + u32 hash_bytes:1; + u32 hash_length:6; + u32 generic_bytes:1; + u32 checksum:1; + u32 next_header:1; + u32 length:1; u16 application_id; u16 rsvd1; diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c index d68ef16650d4..32a37e3850c5 100644 --- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -63,7 +63,6 @@ struct safexcel_cipher_ctx { u32 hash_alg; u32 state_sz; - struct crypto_cipher *hkaes; struct crypto_aead *fback; }; @@ -642,10 +641,16 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin safexcel_complete(priv, ring); if (src == dst) { - dma_unmap_sg(priv->dev, src, sreq->nr_src, DMA_BIDIRECTIONAL); + if (sreq->nr_src > 0) + dma_unmap_sg(priv->dev, src, sreq->nr_src, + DMA_BIDIRECTIONAL); } else { - dma_unmap_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE); - dma_unmap_sg(priv->dev, dst, sreq->nr_dst, DMA_FROM_DEVICE); + if (sreq->nr_src > 0) + dma_unmap_sg(priv->dev, src, sreq->nr_src, + DMA_TO_DEVICE); + if (sreq->nr_dst > 0) + dma_unmap_sg(priv->dev, dst, sreq->nr_dst, + DMA_FROM_DEVICE); } /* @@ -737,23 +742,29 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, max(totlen_src, totlen_dst)); return -EINVAL; } - dma_map_sg(priv->dev, src, sreq->nr_src, DMA_BIDIRECTIONAL); + if (sreq->nr_src > 0) + dma_map_sg(priv->dev, src, sreq->nr_src, + DMA_BIDIRECTIONAL); } else { if (unlikely(totlen_src && (sreq->nr_src <= 0))) { dev_err(priv->dev, "Source buffer not large enough (need %d bytes)!", totlen_src); return -EINVAL; } - dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE); + + if (sreq->nr_src > 0) + dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE); if (unlikely(totlen_dst && (sreq->nr_dst <= 0))) { dev_err(priv->dev, "Dest buffer not large enough (need %d bytes)!", totlen_dst); - dma_unmap_sg(priv->dev, src, sreq->nr_src, - DMA_TO_DEVICE); - return -EINVAL; + ret = -EINVAL; + goto unmap; } - dma_map_sg(priv->dev, dst, sreq->nr_dst, DMA_FROM_DEVICE); + + if (sreq->nr_dst > 0) + dma_map_sg(priv->dev, dst, sreq->nr_dst, + DMA_FROM_DEVICE); } memcpy(ctx->base.ctxr->data, ctx->key, ctx->key_len); @@ -883,12 +894,18 @@ rdesc_rollback: cdesc_rollback: for (i = 0; i < n_cdesc; i++) safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr); - +unmap: if (src == dst) { - dma_unmap_sg(priv->dev, src, sreq->nr_src, DMA_BIDIRECTIONAL); + if (sreq->nr_src > 0) + dma_unmap_sg(priv->dev, src, sreq->nr_src, + DMA_BIDIRECTIONAL); } else { - dma_unmap_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE); - dma_unmap_sg(priv->dev, dst, sreq->nr_dst, DMA_FROM_DEVICE); + if (sreq->nr_src > 0) + dma_unmap_sg(priv->dev, src, sreq->nr_src, + DMA_TO_DEVICE); + if (sreq->nr_dst > 0) + dma_unmap_sg(priv->dev, dst, sreq->nr_dst, + DMA_FROM_DEVICE); } return ret; @@ -2589,15 +2606,8 @@ static int safexcel_aead_gcm_setkey(struct crypto_aead *ctfm, const u8 *key, ctx->key_len = len; /* Compute hash key by encrypting zeroes with cipher key */ - crypto_cipher_clear_flags(ctx->hkaes, CRYPTO_TFM_REQ_MASK); - crypto_cipher_set_flags(ctx->hkaes, crypto_aead_get_flags(ctfm) & - CRYPTO_TFM_REQ_MASK); - ret = crypto_cipher_setkey(ctx->hkaes, key, len); - if (ret) - return ret; - memset(hashkey, 0, AES_BLOCK_SIZE); - crypto_cipher_encrypt_one(ctx->hkaes, (u8 *)hashkey, (u8 *)hashkey); + aes_encrypt(&aes, (u8 *)hashkey, (u8 *)hashkey); if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) { for (i = 0; i < AES_BLOCK_SIZE / sizeof(u32); i++) { @@ -2626,15 +2636,11 @@ static int safexcel_aead_gcm_cra_init(struct crypto_tfm *tfm) ctx->xcm = EIP197_XCM_MODE_GCM; ctx->mode = CONTEXT_CONTROL_CRYPTO_MODE_XCM; /* override default */ - ctx->hkaes = crypto_alloc_cipher("aes", 0, 0); - return PTR_ERR_OR_ZERO(ctx->hkaes); + return 0; } static void safexcel_aead_gcm_cra_exit(struct crypto_tfm *tfm) { - struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm); - - crypto_free_cipher(ctx->hkaes); safexcel_aead_cra_exit(tfm); } diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c index bc60b5802256..103fc551d2af 100644 --- a/drivers/crypto/inside-secure/safexcel_hash.c +++ b/drivers/crypto/inside-secure/safexcel_hash.c @@ -30,7 +30,7 @@ struct safexcel_ahash_ctx { bool fb_init_done; bool fb_do_setkey; - struct crypto_cipher *kaes; + struct crypto_aes_ctx *aes; struct crypto_ahash *fback; struct crypto_shash *shpre; struct shash_desc *shdesc; @@ -383,7 +383,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring, u32 x; x = ipad[i] ^ ipad[i + 4]; - cache[i] ^= swab(x); + cache[i] ^= swab32(x); } } cache_len = AES_BLOCK_SIZE; @@ -821,10 +821,10 @@ static int safexcel_ahash_final(struct ahash_request *areq) u32 *result = (void *)areq->result; /* K3 */ - result[i] = swab(ctx->base.ipad.word[i + 4]); + result[i] = swab32(ctx->base.ipad.word[i + 4]); } areq->result[0] ^= 0x80; // 10- padding - crypto_cipher_encrypt_one(ctx->kaes, areq->result, areq->result); + aes_encrypt(ctx->aes, areq->result, areq->result); return 0; } else if (unlikely(req->hmac && (req->len == req->block_sz) && @@ -2083,37 +2083,26 @@ static int safexcel_xcbcmac_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int len) { struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm)); - struct crypto_aes_ctx aes; u32 key_tmp[3 * AES_BLOCK_SIZE / sizeof(u32)]; int ret, i; - ret = aes_expandkey(&aes, key, len); + ret = aes_expandkey(ctx->aes, key, len); if (ret) return ret; /* precompute the XCBC key material */ - crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK); - crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) & - CRYPTO_TFM_REQ_MASK); - ret = crypto_cipher_setkey(ctx->kaes, key, len); - if (ret) - return ret; - - crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp + 2 * AES_BLOCK_SIZE, - "\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1"); - crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp, - "\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2"); - crypto_cipher_encrypt_one(ctx->kaes, (u8 *)key_tmp + AES_BLOCK_SIZE, - "\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3"); + aes_encrypt(ctx->aes, (u8 *)key_tmp + 2 * AES_BLOCK_SIZE, + "\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1\x1"); + aes_encrypt(ctx->aes, (u8 *)key_tmp, + "\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2\x2"); + aes_encrypt(ctx->aes, (u8 *)key_tmp + AES_BLOCK_SIZE, + "\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3\x3"); for (i = 0; i < 3 * AES_BLOCK_SIZE / sizeof(u32); i++) - ctx->base.ipad.word[i] = swab(key_tmp[i]); - - crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK); - crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) & - CRYPTO_TFM_REQ_MASK); - ret = crypto_cipher_setkey(ctx->kaes, - (u8 *)key_tmp + 2 * AES_BLOCK_SIZE, - AES_MIN_KEY_SIZE); + ctx->base.ipad.word[i] = swab32(key_tmp[i]); + + ret = aes_expandkey(ctx->aes, + (u8 *)key_tmp + 2 * AES_BLOCK_SIZE, + AES_MIN_KEY_SIZE); if (ret) return ret; @@ -2121,7 +2110,6 @@ static int safexcel_xcbcmac_setkey(struct crypto_ahash *tfm, const u8 *key, ctx->key_sz = AES_MIN_KEY_SIZE + 2 * AES_BLOCK_SIZE; ctx->cbcmac = false; - memzero_explicit(&aes, sizeof(aes)); return 0; } @@ -2130,15 +2118,15 @@ static int safexcel_xcbcmac_cra_init(struct crypto_tfm *tfm) struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm); safexcel_ahash_cra_init(tfm); - ctx->kaes = crypto_alloc_cipher("aes", 0, 0); - return PTR_ERR_OR_ZERO(ctx->kaes); + ctx->aes = kmalloc(sizeof(*ctx->aes), GFP_KERNEL); + return PTR_ERR_OR_ZERO(ctx->aes); } static void safexcel_xcbcmac_cra_exit(struct crypto_tfm *tfm) { struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm); - crypto_free_cipher(ctx->kaes); + kfree(ctx->aes); safexcel_ahash_cra_exit(tfm); } @@ -2178,31 +2166,23 @@ static int safexcel_cmac_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int len) { struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm)); - struct crypto_aes_ctx aes; __be64 consts[4]; u64 _const[2]; u8 msb_mask, gfmask; int ret, i; - ret = aes_expandkey(&aes, key, len); + /* precompute the CMAC key material */ + ret = aes_expandkey(ctx->aes, key, len); if (ret) return ret; for (i = 0; i < len / sizeof(u32); i++) - ctx->base.ipad.word[i + 8] = swab(aes.key_enc[i]); - - /* precompute the CMAC key material */ - crypto_cipher_clear_flags(ctx->kaes, CRYPTO_TFM_REQ_MASK); - crypto_cipher_set_flags(ctx->kaes, crypto_ahash_get_flags(tfm) & - CRYPTO_TFM_REQ_MASK); - ret = crypto_cipher_setkey(ctx->kaes, key, len); - if (ret) - return ret; + ctx->base.ipad.word[i + 8] = swab32(ctx->aes->key_enc[i]); /* code below borrowed from crypto/cmac.c */ /* encrypt the zero block */ memset(consts, 0, AES_BLOCK_SIZE); - crypto_cipher_encrypt_one(ctx->kaes, (u8 *)consts, (u8 *)consts); + aes_encrypt(ctx->aes, (u8 *)consts, (u8 *)consts); gfmask = 0x87; _const[0] = be64_to_cpu(consts[1]); @@ -2234,7 +2214,6 @@ static int safexcel_cmac_setkey(struct crypto_ahash *tfm, const u8 *key, } ctx->cbcmac = false; - memzero_explicit(&aes, sizeof(aes)); return 0; } diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 98730aab287c..d39a386b31ac 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -33,7 +33,6 @@ /* Intermittent includes, delete this after v5.14-rc1 */ #include <linux/soc/ixp4xx/cpu.h> -#include <mach/ixp4xx-regs.h> #define MAX_KEYLEN 32 diff --git a/drivers/crypto/keembay/Kconfig b/drivers/crypto/keembay/Kconfig index 7942b48dd55a..1cd62f9c3e3a 100644 --- a/drivers/crypto/keembay/Kconfig +++ b/drivers/crypto/keembay/Kconfig @@ -42,7 +42,7 @@ config CRYPTO_DEV_KEEMBAY_OCS_AES_SM4_CTS config CRYPTO_DEV_KEEMBAY_OCS_ECC tristate "Support for Intel Keem Bay OCS ECC HW acceleration" depends on ARCH_KEEMBAY || COMPILE_TEST - depends on OF || COMPILE_TEST + depends on OF depends on HAS_IOMEM select CRYPTO_ECDH select CRYPTO_ENGINE @@ -64,7 +64,7 @@ config CRYPTO_DEV_KEEMBAY_OCS_HCU select CRYPTO_ENGINE depends on HAS_IOMEM depends on ARCH_KEEMBAY || COMPILE_TEST - depends on OF || COMPILE_TEST + depends on OF help Support for Intel Keem Bay Offload and Crypto Subsystem (OCS) Hash Control Unit (HCU) hardware acceleration for use with Crypto API. diff --git a/drivers/crypto/keembay/keembay-ocs-aes-core.c b/drivers/crypto/keembay/keembay-ocs-aes-core.c index e2a39fdaf623..9953f5590ac4 100644 --- a/drivers/crypto/keembay/keembay-ocs-aes-core.c +++ b/drivers/crypto/keembay/keembay-ocs-aes-core.c @@ -1598,7 +1598,6 @@ static int kmb_ocs_aes_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct ocs_aes_dev *aes_dev; - struct resource *aes_mem; int rc; aes_dev = devm_kzalloc(dev, sizeof(*aes_dev), GFP_KERNEL); @@ -1616,13 +1615,7 @@ static int kmb_ocs_aes_probe(struct platform_device *pdev) } /* Get base register address. */ - aes_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!aes_mem) { - dev_err(dev, "Could not retrieve io mem resource\n"); - return -ENODEV; - } - - aes_dev->base_reg = devm_ioremap_resource(&pdev->dev, aes_mem); + aes_dev->base_reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(aes_dev->base_reg)) return PTR_ERR(aes_dev->base_reg); diff --git a/drivers/crypto/keembay/keembay-ocs-ecc.c b/drivers/crypto/keembay/keembay-ocs-ecc.c index 5d0785d3f1b5..2269df17514c 100644 --- a/drivers/crypto/keembay/keembay-ocs-ecc.c +++ b/drivers/crypto/keembay/keembay-ocs-ecc.c @@ -976,8 +976,6 @@ static int kmb_ocs_ecc_remove(struct platform_device *pdev) struct ocs_ecc_dev *ecc_dev; ecc_dev = platform_get_drvdata(pdev); - if (!ecc_dev) - return -ENODEV; crypto_unregister_kpp(&ocs_ecdh_p384); crypto_unregister_kpp(&ocs_ecdh_p256); diff --git a/drivers/crypto/marvell/Kconfig b/drivers/crypto/marvell/Kconfig index 9125199f1702..a48591af12d0 100644 --- a/drivers/crypto/marvell/Kconfig +++ b/drivers/crypto/marvell/Kconfig @@ -47,6 +47,7 @@ config CRYPTO_DEV_OCTEONTX2_CPT select CRYPTO_SKCIPHER select CRYPTO_HASH select CRYPTO_AEAD + select NET_DEVLINK help This driver allows you to utilize the Marvell Cryptographic Accelerator Unit(CPT) found in OcteonTX2 series of processors. diff --git a/drivers/crypto/marvell/cesa/cipher.c b/drivers/crypto/marvell/cesa/cipher.c index b739d3b873dc..c6f2fa753b7c 100644 --- a/drivers/crypto/marvell/cesa/cipher.c +++ b/drivers/crypto/marvell/cesa/cipher.c @@ -624,7 +624,6 @@ struct skcipher_alg mv_cesa_ecb_des3_ede_alg = { .decrypt = mv_cesa_ecb_des3_ede_decrypt, .min_keysize = DES3_EDE_KEY_SIZE, .max_keysize = DES3_EDE_KEY_SIZE, - .ivsize = DES3_EDE_BLOCK_SIZE, .base = { .cra_name = "ecb(des3_ede)", .cra_driver_name = "mv-ecb-des3-ede", diff --git a/drivers/crypto/marvell/octeontx/otx_cpt_hw_types.h b/drivers/crypto/marvell/octeontx/otx_cpt_hw_types.h index b8bdb9f134f3..205eacac4a34 100644 --- a/drivers/crypto/marvell/octeontx/otx_cpt_hw_types.h +++ b/drivers/crypto/marvell/octeontx/otx_cpt_hw_types.h @@ -403,7 +403,7 @@ union otx_cptx_pf_exe_bist_status { * big-endian format in memory. * iqb_ldwb:1 [7:7](R/W) Instruction load don't write back. * 0 = The hardware issues NCB transient load (LDT) towards the cache, - * which if the line hits and is is dirty will cause the line to be + * which if the line hits and is dirty will cause the line to be * written back before being replaced. * 1 = The hardware issues NCB LDWB read-and-invalidate command towards * the cache when fetching the last word of instructions; as a result the diff --git a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c index 40b482198ebc..df9c2b8747e6 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c @@ -97,7 +97,7 @@ static int dev_supports_eng_type(struct otx_cpt_eng_grps *eng_grps, static void set_ucode_filename(struct otx_cpt_ucode *ucode, const char *filename) { - strlcpy(ucode->filename, filename, OTX_CPT_UCODE_NAME_LENGTH); + strscpy(ucode->filename, filename, OTX_CPT_UCODE_NAME_LENGTH); } static char *get_eng_type_str(int eng_type) @@ -138,7 +138,7 @@ static int get_ucode_type(struct otx_cpt_ucode_hdr *ucode_hdr, int *ucode_type) u32 i, val = 0; u8 nn; - strlcpy(tmp_ver_str, ucode_hdr->ver_str, OTX_CPT_UCODE_VER_STR_SZ); + strscpy(tmp_ver_str, ucode_hdr->ver_str, OTX_CPT_UCODE_VER_STR_SZ); for (i = 0; i < strlen(tmp_ver_str); i++) tmp_ver_str[i] = tolower(tmp_ver_str[i]); @@ -286,6 +286,7 @@ static int process_tar_file(struct device *dev, struct tar_ucode_info_t *tar_info; struct otx_cpt_ucode_hdr *ucode_hdr; int ucode_type, ucode_size; + unsigned int code_length; /* * If size is less than microcode header size then don't report @@ -303,7 +304,13 @@ static int process_tar_file(struct device *dev, if (get_ucode_type(ucode_hdr, &ucode_type)) return 0; - ucode_size = ntohl(ucode_hdr->code_length) * 2; + code_length = ntohl(ucode_hdr->code_length); + if (code_length >= INT_MAX / 2) { + dev_err(dev, "Invalid code_length %u\n", code_length); + return -EINVAL; + } + + ucode_size = code_length * 2; if (!ucode_size || (size < round_up(ucode_size, 16) + sizeof(struct otx_cpt_ucode_hdr) + OTX_CPT_UCODE_SIGN_LEN)) { dev_err(dev, "Ucode %s invalid size\n", filename); @@ -886,6 +893,7 @@ static int ucode_load(struct device *dev, struct otx_cpt_ucode *ucode, { struct otx_cpt_ucode_hdr *ucode_hdr; const struct firmware *fw; + unsigned int code_length; int ret; set_ucode_filename(ucode, ucode_filename); @@ -896,7 +904,13 @@ static int ucode_load(struct device *dev, struct otx_cpt_ucode *ucode, ucode_hdr = (struct otx_cpt_ucode_hdr *) fw->data; memcpy(ucode->ver_str, ucode_hdr->ver_str, OTX_CPT_UCODE_VER_STR_SZ); ucode->ver_num = ucode_hdr->ver_num; - ucode->size = ntohl(ucode_hdr->code_length) * 2; + code_length = ntohl(ucode_hdr->code_length); + if (code_length >= INT_MAX / 2) { + dev_err(dev, "Ucode invalid code_length %u\n", code_length); + ret = -EINVAL; + goto release_fw; + } + ucode->size = code_length * 2; if (!ucode->size || (fw->size < round_up(ucode->size, 16) + sizeof(struct otx_cpt_ucode_hdr) + OTX_CPT_UCODE_SIGN_LEN)) { dev_err(dev, "Ucode %s invalid size\n", ucode_filename); @@ -1328,7 +1342,7 @@ static ssize_t ucode_load_store(struct device *dev, eng_grps = container_of(attr, struct otx_cpt_eng_grps, ucode_load_attr); err_msg = "Invalid engine group format"; - strlcpy(tmp_buf, buf, OTX_CPT_UCODE_NAME_LENGTH); + strscpy(tmp_buf, buf, OTX_CPT_UCODE_NAME_LENGTH); start = tmp_buf; has_se = has_ie = has_ae = false; diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c index ccbef01888d4..01c48ddc4eeb 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c @@ -1639,11 +1639,8 @@ static void swap_func(void *lptr, void *rptr, int size) { struct cpt_device_desc *ldesc = (struct cpt_device_desc *) lptr; struct cpt_device_desc *rdesc = (struct cpt_device_desc *) rptr; - struct cpt_device_desc desc; - desc = *ldesc; - *ldesc = *rdesc; - *rdesc = desc; + swap(*ldesc, *rdesc); } int otx_cpt_crypto_init(struct pci_dev *pdev, struct module *mod, diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c index b681bd2dc6ad..88a41d1ca5f6 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c @@ -204,7 +204,6 @@ static int alloc_command_queues(struct otx_cptvf *cptvf, /* per queue initialization */ for (i = 0; i < cptvf->num_queues; i++) { - c_size = 0; rem_q_size = q_size; first = NULL; last = NULL; @@ -662,7 +661,7 @@ static ssize_t vf_type_show(struct device *dev, msg = "Invalid"; } - return scnprintf(buf, PAGE_SIZE, "%s\n", msg); + return sysfs_emit(buf, "%s\n", msg); } static ssize_t vf_engine_group_show(struct device *dev, @@ -671,7 +670,7 @@ static ssize_t vf_engine_group_show(struct device *dev, { struct otx_cptvf *cptvf = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", cptvf->vfgrp); + return sysfs_emit(buf, "%d\n", cptvf->vfgrp); } static ssize_t vf_engine_group_store(struct device *dev, @@ -707,7 +706,7 @@ static ssize_t vf_coalesc_time_wait_show(struct device *dev, { struct otx_cptvf *cptvf = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", + return sysfs_emit(buf, "%d\n", cptvf_read_vq_done_timewait(cptvf)); } @@ -717,7 +716,7 @@ static ssize_t vf_coalesc_num_wait_show(struct device *dev, { struct otx_cptvf *cptvf = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", + return sysfs_emit(buf, "%d\n", cptvf_read_vq_done_numwait(cptvf)); } diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_mbox.c b/drivers/crypto/marvell/octeontx/otx_cptvf_mbox.c index 5663787c7a62..90fdafb7c468 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_mbox.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_mbox.c @@ -159,12 +159,10 @@ static int cptvf_send_msg_to_pf_timeout(struct otx_cptvf *cptvf, int otx_cptvf_check_pf_ready(struct otx_cptvf *cptvf) { struct otx_cpt_mbox mbx = {}; - int ret; mbx.msg = OTX_CPT_MSG_READY; - ret = cptvf_send_msg_to_pf_timeout(cptvf, &mbx); - return ret; + return cptvf_send_msg_to_pf_timeout(cptvf, &mbx); } /* @@ -174,13 +172,11 @@ int otx_cptvf_check_pf_ready(struct otx_cptvf *cptvf) int otx_cptvf_send_vq_size_msg(struct otx_cptvf *cptvf) { struct otx_cpt_mbox mbx = {}; - int ret; mbx.msg = OTX_CPT_MSG_QLEN; mbx.data = cptvf->qsize; - ret = cptvf_send_msg_to_pf_timeout(cptvf, &mbx); - return ret; + return cptvf_send_msg_to_pf_timeout(cptvf, &mbx); } /* @@ -208,14 +204,12 @@ int otx_cptvf_send_vf_to_grp_msg(struct otx_cptvf *cptvf, int group) int otx_cptvf_send_vf_priority_msg(struct otx_cptvf *cptvf) { struct otx_cpt_mbox mbx = {}; - int ret; mbx.msg = OTX_CPT_MSG_VQ_PRIORITY; /* Convey group of the VF */ mbx.data = cptvf->priority; - ret = cptvf_send_msg_to_pf_timeout(cptvf, &mbx); - return ret; + return cptvf_send_msg_to_pf_timeout(cptvf, &mbx); } /* @@ -224,12 +218,10 @@ int otx_cptvf_send_vf_priority_msg(struct otx_cptvf *cptvf) int otx_cptvf_send_vf_up(struct otx_cptvf *cptvf) { struct otx_cpt_mbox mbx = {}; - int ret; mbx.msg = OTX_CPT_MSG_VF_UP; - ret = cptvf_send_msg_to_pf_timeout(cptvf, &mbx); - return ret; + return cptvf_send_msg_to_pf_timeout(cptvf, &mbx); } /* @@ -238,10 +230,8 @@ int otx_cptvf_send_vf_up(struct otx_cptvf *cptvf) int otx_cptvf_send_vf_down(struct otx_cptvf *cptvf) { struct otx_cpt_mbox mbx = {}; - int ret; mbx.msg = OTX_CPT_MSG_VF_DOWN; - ret = cptvf_send_msg_to_pf_timeout(cptvf, &mbx); - return ret; + return cptvf_send_msg_to_pf_timeout(cptvf, &mbx); } diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index fb56824cb0a6..5012b7e669f0 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -157,5 +157,6 @@ struct otx2_cptlfs_info; int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs); int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs); int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs); +int otx2_cpt_sync_mbox_msg(struct otx2_mbox *mbox); #endif /* __OTX2_CPT_COMMON_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c index bb02e0db3615..7503f6b18ac5 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c @@ -51,11 +51,47 @@ static const struct devlink_param otx2_cpt_dl_params[] = { NULL), }; -static int otx2_cpt_devlink_info_get(struct devlink *devlink, +static int otx2_cpt_dl_info_firmware_version_put(struct devlink_info_req *req, + struct otx2_cpt_eng_grp_info grp[], + const char *ver_name, int eng_type) +{ + struct otx2_cpt_engs_rsvd *eng; + int i; + + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) { + eng = find_engines_by_type(&grp[i], eng_type); + if (eng) + return devlink_info_version_running_put(req, ver_name, + eng->ucode->ver_str); + } + + return 0; +} + +static int otx2_cpt_devlink_info_get(struct devlink *dl, struct devlink_info_req *req, struct netlink_ext_ack *extack) { - return devlink_info_driver_name_put(req, "rvu_cptpf"); + struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl); + struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf; + int err; + + err = devlink_info_driver_name_put(req, "rvu_cptpf"); + if (err) + return err; + + err = otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp, + "fw.ae", OTX2_CPT_AE_TYPES); + if (err) + return err; + + err = otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp, + "fw.se", OTX2_CPT_SE_TYPES); + if (err) + return err; + + return otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp, + "fw.ie", OTX2_CPT_IE_TYPES); } static const struct devlink_ops otx2_cpt_devlink_ops = { diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c index 9074876d38e5..a317319696ef 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c @@ -202,3 +202,17 @@ int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs) } return ret; } + +int otx2_cpt_sync_mbox_msg(struct otx2_mbox *mbox) +{ + int err; + + if (!otx2_mbox_nonempty(mbox, 0)) + return 0; + otx2_mbox_msg_send(mbox, 0); + err = otx2_mbox_wait_for_rsp(mbox, 0); + if (err) + return err; + + return otx2_mbox_check_rsp_msgs(mbox, 0); +} diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h index b691b6c1d5c4..4fcaf61a70e3 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h @@ -26,12 +26,22 @@ */ #define OTX2_CPT_INST_QLEN_MSGS ((OTX2_CPT_SIZE_DIV40 - 1) * 40) +/* + * LDWB is getting incorrectly used when IQB_LDWB = 1 and CPT instruction + * queue has less than 320 free entries. So, increase HW instruction queue + * size by 320 and give 320 entries less for SW/NIX RX as a workaround. + */ +#define OTX2_CPT_INST_QLEN_EXTRA_BYTES (320 * OTX2_CPT_INST_SIZE) +#define OTX2_CPT_EXTRA_SIZE_DIV40 (320/40) + /* CPT instruction queue length in bytes */ -#define OTX2_CPT_INST_QLEN_BYTES (OTX2_CPT_SIZE_DIV40 * 40 * \ - OTX2_CPT_INST_SIZE) +#define OTX2_CPT_INST_QLEN_BYTES \ + ((OTX2_CPT_SIZE_DIV40 * 40 * OTX2_CPT_INST_SIZE) + \ + OTX2_CPT_INST_QLEN_EXTRA_BYTES) /* CPT instruction group queue length in bytes */ -#define OTX2_CPT_INST_GRP_QLEN_BYTES (OTX2_CPT_SIZE_DIV40 * 16) +#define OTX2_CPT_INST_GRP_QLEN_BYTES \ + ((OTX2_CPT_SIZE_DIV40 + OTX2_CPT_EXTRA_SIZE_DIV40) * 16) /* CPT FC length in bytes */ #define OTX2_CPT_Q_FC_LEN 128 @@ -179,7 +189,8 @@ static inline void otx2_cptlf_do_set_iqueue_size(struct otx2_cptlf_info *lf) { union otx2_cptx_lf_q_size lf_q_size = { .u = 0x0 }; - lf_q_size.s.size_div40 = OTX2_CPT_SIZE_DIV40; + lf_q_size.s.size_div40 = OTX2_CPT_SIZE_DIV40 + + OTX2_CPT_EXTRA_SIZE_DIV40; otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, OTX2_CPT_LF_Q_SIZE, lf_q_size.u); } diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h index 05b2d9c650e1..936174b012e8 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h @@ -46,6 +46,7 @@ struct otx2_cptpf_dev { struct workqueue_struct *flr_wq; struct cptpf_flr_work *flr_work; + struct mutex lock; /* serialize mailbox access */ unsigned long cap_flag; u8 pf_id; /* RVU PF number */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c index 1720a5bb7016..a402ccfac557 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c @@ -140,10 +140,13 @@ static void cptpf_flr_wq_handler(struct work_struct *work) vf = flr_work - pf->flr_work; + mutex_lock(&pf->lock); req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), sizeof(struct msg_rsp)); - if (!req) + if (!req) { + mutex_unlock(&pf->lock); return; + } req->sig = OTX2_MBOX_REQ_SIG; req->id = MBOX_MSG_VF_FLR; @@ -151,16 +154,19 @@ static void cptpf_flr_wq_handler(struct work_struct *work) req->pcifunc |= (vf + 1) & RVU_PFVF_FUNC_MASK; otx2_cpt_send_mbox_msg(mbox, pf->pdev); + if (!otx2_cpt_sync_mbox_msg(&pf->afpf_mbox)) { - if (vf >= 64) { - reg = 1; - vf = vf - 64; + if (vf >= 64) { + reg = 1; + vf = vf - 64; + } + /* Clear transaction pending register */ + otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFTRPENDX(reg), BIT_ULL(vf)); + otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf)); } - /* Clear transaction pending register */ - otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0, - RVU_PF_VFTRPENDX(reg), BIT_ULL(vf)); - otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0, - RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf)); + mutex_unlock(&pf->lock); } static irqreturn_t cptpf_vf_flr_intr(int __always_unused irq, void *arg) @@ -468,6 +474,7 @@ static int cptpf_afpf_mbox_init(struct otx2_cptpf_dev *cptpf) goto error; INIT_WORK(&cptpf->afpf_mbox_work, otx2_cptpf_afpf_mbox_handler); + mutex_init(&cptpf->lock); return 0; error: diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c index 186f1c1190c1..dee0aa60b698 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c @@ -18,9 +18,12 @@ static int forward_to_af(struct otx2_cptpf_dev *cptpf, struct mbox_msghdr *msg; int ret; + mutex_lock(&cptpf->lock); msg = otx2_mbox_alloc_msg(&cptpf->afpf_mbox, 0, size); - if (msg == NULL) + if (msg == NULL) { + mutex_unlock(&cptpf->lock); return -ENOMEM; + } memcpy((uint8_t *)msg + sizeof(struct mbox_msghdr), (uint8_t *)req + sizeof(struct mbox_msghdr), size); @@ -29,15 +32,19 @@ static int forward_to_af(struct otx2_cptpf_dev *cptpf, msg->sig = req->sig; msg->ver = req->ver; - otx2_mbox_msg_send(&cptpf->afpf_mbox, 0); - ret = otx2_mbox_wait_for_rsp(&cptpf->afpf_mbox, 0); + ret = otx2_cpt_sync_mbox_msg(&cptpf->afpf_mbox); + /* Error code -EIO indicate there is a communication failure + * to the AF. Rest of the error codes indicate that AF processed + * VF messages and set the error codes in response messages + * (if any) so simply forward responses to VF. + */ if (ret == -EIO) { - dev_err(&cptpf->pdev->dev, "RVU MBOX timeout.\n"); + dev_warn(&cptpf->pdev->dev, + "AF not responding to VF%d messages\n", vf->vf_id); + mutex_unlock(&cptpf->lock); return ret; - } else if (ret) { - dev_err(&cptpf->pdev->dev, "RVU MBOX error: %d.\n", ret); - return -EFAULT; } + mutex_unlock(&cptpf->lock); return 0; } @@ -204,6 +211,10 @@ void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work) if (err == -ENOMEM || err == -EIO) break; offset = msg->next_msgoff; + /* Write barrier required for VF responses which are handled by + * PF driver and not forwarded to AF. + */ + smp_wmb(); } /* Send mbox responses to VF */ if (mdev->num_msgs) @@ -350,6 +361,8 @@ void otx2_cptpf_afpf_mbox_handler(struct work_struct *work) process_afpf_mbox_msg(cptpf, msg); offset = msg->next_msgoff; + /* Sync VF response ready to be sent */ + smp_wmb(); mdev->msgs_acked++; } otx2_mbox_reset(afpf_mbox, 0); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c index 4c8ebdf671ca..1577986677f6 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c @@ -68,7 +68,7 @@ static int is_2nd_ucode_used(struct otx2_cpt_eng_grp_info *eng_grp) static void set_ucode_filename(struct otx2_cpt_ucode *ucode, const char *filename) { - strlcpy(ucode->filename, filename, OTX2_CPT_NAME_LENGTH); + strscpy(ucode->filename, filename, OTX2_CPT_NAME_LENGTH); } static char *get_eng_type_str(int eng_type) @@ -126,7 +126,7 @@ static int get_ucode_type(struct device *dev, int i, val = 0; u8 nn; - strlcpy(tmp_ver_str, ucode_hdr->ver_str, OTX2_CPT_UCODE_VER_STR_SZ); + strscpy(tmp_ver_str, ucode_hdr->ver_str, OTX2_CPT_UCODE_VER_STR_SZ); for (i = 0; i < strlen(tmp_ver_str); i++) tmp_ver_str[i] = tolower(tmp_ver_str[i]); @@ -476,7 +476,7 @@ release_fw: return ret; } -static struct otx2_cpt_engs_rsvd *find_engines_by_type( +struct otx2_cpt_engs_rsvd *find_engines_by_type( struct otx2_cpt_eng_grp_info *eng_grp, int eng_type) { @@ -1076,6 +1076,39 @@ static void delete_engine_grps(struct pci_dev *pdev, delete_engine_group(&pdev->dev, &eng_grps->grp[i]); } +#define PCI_DEVID_CN10K_RNM 0xA098 +#define RNM_ENTROPY_STATUS 0x8 + +static void rnm_to_cpt_errata_fixup(struct device *dev) +{ + struct pci_dev *pdev; + void __iomem *base; + int timeout = 5000; + + pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RNM, NULL); + if (!pdev) + return; + + base = pci_ioremap_bar(pdev, 0); + if (!base) + goto put_pdev; + + while ((readq(base + RNM_ENTROPY_STATUS) & 0x7F) != 0x40) { + cpu_relax(); + udelay(1); + timeout--; + if (!timeout) { + dev_warn(dev, "RNM is not producing entropy\n"); + break; + } + } + + iounmap(base); + +put_pdev: + pci_dev_put(pdev); +} + int otx2_cpt_get_eng_grp(struct otx2_cpt_eng_grps *eng_grps, int eng_type) { @@ -1111,6 +1144,7 @@ int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf, struct otx2_cpt_engines engs[OTX2_CPT_MAX_ETYPES_PER_GRP] = { {0} }; struct pci_dev *pdev = cptpf->pdev; struct fw_info_t fw_info; + u64 reg_val; int ret = 0; mutex_lock(&eng_grps->lock); @@ -1189,9 +1223,17 @@ int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf, if (is_dev_otx2(pdev)) goto unlock; + + /* + * Ensure RNM_ENTROPY_STATUS[NORMAL_CNT] = 0x40 before writing + * CPT_AF_CTL[RNM_REQ_EN] = 1 as a workaround for HW errata. + */ + rnm_to_cpt_errata_fixup(&pdev->dev); + /* * Configure engine group mask to allow context prefetching - * for the groups. + * for the groups and enable random number request, to enable + * CPT to request random numbers from RNM. */ otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTL, OTX2_CPT_ALL_ENG_GRPS_MASK << 3 | BIT_ULL(16), @@ -1203,6 +1245,18 @@ int otx2_cpt_create_eng_grps(struct otx2_cptpf_dev *cptpf, */ otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_CTX_FLUSH_TIMER, CTX_FLUSH_TIMER_CNT, BLKADDR_CPT0); + + /* + * Set CPT_AF_DIAG[FLT_DIS], as a workaround for HW errata, when + * CPT_AF_DIAG[FLT_DIS] = 0 and a CPT engine access to LLC/DRAM + * encounters a fault/poison, a rare case may result in + * unpredictable data being delivered to a CPT engine. + */ + otx2_cpt_read_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_DIAG, ®_val, + BLKADDR_CPT0); + otx2_cpt_write_af_reg(&cptpf->afpf_mbox, pdev, CPT_AF_DIAG, + reg_val | BIT_ULL(24), BLKADDR_CPT0); + mutex_unlock(&eng_grps->lock); return 0; @@ -1551,7 +1605,10 @@ int otx2_cpt_dl_custom_egrp_create(struct otx2_cptpf_dev *cptpf, if (!strncasecmp(val, "se", 2) && strchr(val, ':')) { if (has_se || ucode_idx) goto err_print; - tmp = strim(strsep(&val, ":")); + tmp = strsep(&val, ":"); + if (!tmp) + goto err_print; + tmp = strim(tmp); if (!val) goto err_print; if (strlen(tmp) != 2) @@ -1563,7 +1620,10 @@ int otx2_cpt_dl_custom_egrp_create(struct otx2_cptpf_dev *cptpf, } else if (!strncasecmp(val, "ae", 2) && strchr(val, ':')) { if (has_ae || ucode_idx) goto err_print; - tmp = strim(strsep(&val, ":")); + tmp = strsep(&val, ":"); + if (!tmp) + goto err_print; + tmp = strim(tmp); if (!val) goto err_print; if (strlen(tmp) != 2) @@ -1575,7 +1635,10 @@ int otx2_cpt_dl_custom_egrp_create(struct otx2_cptpf_dev *cptpf, } else if (!strncasecmp(val, "ie", 2) && strchr(val, ':')) { if (has_ie || ucode_idx) goto err_print; - tmp = strim(strsep(&val, ":")); + tmp = strsep(&val, ":"); + if (!tmp) + goto err_print; + tmp = strim(tmp); if (!val) goto err_print; if (strlen(tmp) != 2) @@ -1753,7 +1816,6 @@ void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf) char engs_info[2 * OTX2_CPT_NAME_LENGTH]; struct otx2_cpt_eng_grp_info *grp; struct otx2_cpt_engs_rsvd *engs; - u32 mask[4]; int i, j; pr_debug("Engine groups global info"); @@ -1785,6 +1847,8 @@ void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf) for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) { engs = &grp->engs[j]; if (engs->type) { + u32 mask[5] = { }; + get_engs_info(grp, engs_info, 2 * OTX2_CPT_NAME_LENGTH, j); pr_debug("Slot%d: %s", j, engs_info); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h index 8f4d4e5f531a..e69320a54b5d 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h @@ -166,4 +166,7 @@ int otx2_cpt_dl_custom_egrp_create(struct otx2_cptpf_dev *cptpf, int otx2_cpt_dl_custom_egrp_delete(struct otx2_cptpf_dev *cptpf, struct devlink_param_gset_ctx *ctx); void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf); +struct otx2_cpt_engs_rsvd *find_engines_by_type( + struct otx2_cpt_eng_grp_info *eng_grp, + int eng_type); #endif /* __OTX2_CPTPF_UCODE_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c index 2748a3327e39..67530e90bbfe 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c @@ -896,7 +896,6 @@ static int otx2_cpt_aead_cbc_aes_sha_setkey(struct crypto_aead *cipher, struct crypto_authenc_key_param *param; int enckeylen = 0, authkeylen = 0; struct rtattr *rta = (void *)key; - int status; if (!RTA_OK(rta, keylen)) return -EINVAL; @@ -938,11 +937,7 @@ static int otx2_cpt_aead_cbc_aes_sha_setkey(struct crypto_aead *cipher, ctx->enc_key_len = enckeylen; ctx->auth_key_len = authkeylen; - status = aead_hmac_init(cipher); - if (status) - return status; - - return 0; + return aead_hmac_init(cipher); } static int otx2_cpt_aead_ecb_null_sha_setkey(struct crypto_aead *cipher, @@ -1634,16 +1629,13 @@ static inline int cpt_register_algs(void) { int i, err = 0; - if (!IS_ENABLED(CONFIG_DM_CRYPT)) { - for (i = 0; i < ARRAY_SIZE(otx2_cpt_skciphers); i++) - otx2_cpt_skciphers[i].base.cra_flags &= - ~CRYPTO_ALG_DEAD; + for (i = 0; i < ARRAY_SIZE(otx2_cpt_skciphers); i++) + otx2_cpt_skciphers[i].base.cra_flags &= ~CRYPTO_ALG_DEAD; - err = crypto_register_skciphers(otx2_cpt_skciphers, - ARRAY_SIZE(otx2_cpt_skciphers)); - if (err) - return err; - } + err = crypto_register_skciphers(otx2_cpt_skciphers, + ARRAY_SIZE(otx2_cpt_skciphers)); + if (err) + return err; for (i = 0; i < ARRAY_SIZE(otx2_cpt_aeads); i++) otx2_cpt_aeads[i].base.cra_flags &= ~CRYPTO_ALG_DEAD; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c index 02cb9e44afd8..75c403f2b1d9 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c @@ -191,7 +191,6 @@ int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf) struct otx2_mbox *mbox = &cptvf->pfvf_mbox; struct pci_dev *pdev = cptvf->pdev; struct mbox_msghdr *req; - int ret; req = (struct mbox_msghdr *) otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), @@ -204,7 +203,5 @@ int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf) req->sig = OTX2_MBOX_REQ_SIG; req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0); - ret = otx2_cpt_send_mbox_msg(mbox, pdev); - - return ret; + return otx2_cpt_send_mbox_msg(mbox, pdev); } diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c index d19e5ffb5104..d6f9e2fe863d 100644 --- a/drivers/crypto/mxs-dcp.c +++ b/drivers/crypto/mxs-dcp.c @@ -331,7 +331,7 @@ static int mxs_dcp_aes_block_crypt(struct crypto_async_request *arq) memset(key + AES_KEYSIZE_128, 0, AES_KEYSIZE_128); } - for_each_sg(req->src, src, sg_nents(src), i) { + for_each_sg(req->src, src, sg_nents(req->src), i) { src_buf = sg_virt(src); len = sg_dma_len(src); tlen += len; diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c index 3b0bf6fea491..31e24df18877 100644 --- a/drivers/crypto/n2_core.c +++ b/drivers/crypto/n2_core.c @@ -1494,7 +1494,7 @@ static void n2_unregister_algs(void) * * So we have to back-translate, going through the 'intr' and 'ino' * property tables of the n2cp MDESC node, matching it with the OF - * 'interrupts' property entries, in order to to figure out which + * 'interrupts' property entries, in order to figure out which * devino goes to which already-translated IRQ. */ static int find_devino_index(struct platform_device *dev, struct spu_mdesc_info *ip, diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c index 3793885f928d..c843f4c6f684 100644 --- a/drivers/crypto/nx/nx-aes-ccm.c +++ b/drivers/crypto/nx/nx-aes-ccm.c @@ -134,7 +134,6 @@ static int generate_b0(u8 *iv, unsigned int assoclen, unsigned int authsize, unsigned int cryptlen, u8 *b0) { unsigned int l, lp, m = authsize; - int rc; memcpy(b0, iv, 16); @@ -148,9 +147,7 @@ static int generate_b0(u8 *iv, unsigned int assoclen, unsigned int authsize, if (assoclen) *b0 |= 64; - rc = set_msg_len(b0 + 16 - l, cryptlen, l); - - return rc; + return set_msg_len(b0 + 16 - l, cryptlen, l); } static int generate_pat(u8 *iv, diff --git a/drivers/crypto/nx/nx-common-powernv.c b/drivers/crypto/nx/nx-common-powernv.c index 32a036ada5d0..f34c75a862f2 100644 --- a/drivers/crypto/nx/nx-common-powernv.c +++ b/drivers/crypto/nx/nx-common-powernv.c @@ -75,7 +75,7 @@ static int (*nx842_powernv_exec)(const unsigned char *in, /** * setup_indirect_dde - Setup an indirect DDE * - * The DDE is setup with the the DDE count, byte count, and address of + * The DDE is setup with the DDE count, byte count, and address of * first direct DDE in the list. */ static void setup_indirect_dde(struct data_descriptor_entry *dde, @@ -827,7 +827,7 @@ static int __init vas_cfg_coproc_info(struct device_node *dn, int chip_id, goto err_out; vas_init_rx_win_attr(&rxattr, coproc->ct); - rxattr.rx_fifo = (void *)rx_fifo; + rxattr.rx_fifo = rx_fifo; rxattr.rx_fifo_size = fifo_size; rxattr.lnotify_lpid = lpid; rxattr.lnotify_pid = pid; diff --git a/drivers/crypto/nx/nx-common-pseries.c b/drivers/crypto/nx/nx-common-pseries.c index 4e304f6081e4..3ea334b7f820 100644 --- a/drivers/crypto/nx/nx-common-pseries.c +++ b/drivers/crypto/nx/nx-common-pseries.c @@ -962,7 +962,7 @@ static struct attribute *nx842_sysfs_entries[] = { NULL, }; -static struct attribute_group nx842_attribute_group = { +static const struct attribute_group nx842_attribute_group = { .name = NULL, /* put in device directory */ .attrs = nx842_sysfs_entries, }; @@ -992,7 +992,7 @@ static struct attribute *nxcop_caps_sysfs_entries[] = { NULL, }; -static struct attribute_group nxcop_caps_attr_group = { +static const struct attribute_group nxcop_caps_attr_group = { .name = "nx_gzip_caps", .attrs = nxcop_caps_sysfs_entries, }; @@ -1208,10 +1208,13 @@ static struct vio_driver nx842_vio_driver = { static int __init nx842_pseries_init(void) { struct nx842_devdata *new_devdata; + struct device_node *np; int ret; - if (!of_find_compatible_node(NULL, NULL, "ibm,compression")) + np = of_find_compatible_node(NULL, NULL, "ibm,compression"); + if (!np) return -ENODEV; + of_node_put(np); RCU_INIT_POINTER(devdata, NULL); new_devdata = kzalloc(sizeof(*new_devdata), GFP_KERNEL); diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c index a196bb8b1701..67a99c760bc4 100644 --- a/drivers/crypto/omap-aes.c +++ b/drivers/crypto/omap-aes.c @@ -1093,7 +1093,7 @@ static struct attribute *omap_aes_attrs[] = { NULL, }; -static struct attribute_group omap_aes_attr_group = { +static const struct attribute_group omap_aes_attr_group = { .attrs = omap_aes_attrs, }; @@ -1261,9 +1261,6 @@ static int omap_aes_remove(struct platform_device *pdev) struct aead_alg *aalg; int i, j; - if (!dd) - return -ENODEV; - spin_lock_bh(&list_lock); list_del(&dd->list); spin_unlock_bh(&list_lock); @@ -1279,7 +1276,6 @@ static int omap_aes_remove(struct platform_device *pdev) aalg = &dd->pdata->aead_algs_info->algs_list[i]; crypto_unregister_aead(aalg); dd->pdata->aead_algs_info->registered--; - } crypto_engine_exit(dd->engine); diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c index 538aff80869f..f783769ea110 100644 --- a/drivers/crypto/omap-des.c +++ b/drivers/crypto/omap-des.c @@ -1091,9 +1091,6 @@ static int omap_des_remove(struct platform_device *pdev) struct omap_des_dev *dd = platform_get_drvdata(pdev); int i, j; - if (!dd) - return -ENODEV; - spin_lock_bh(&list_lock); list_del(&dd->list); spin_unlock_bh(&list_lock); @@ -1106,7 +1103,6 @@ static int omap_des_remove(struct platform_device *pdev) tasklet_kill(&dd->done_task); omap_des_dma_cleanup(dd); pm_runtime_disable(dd->dev); - dd = NULL; return 0; } diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index f6bf53c00b61..655a7f5a406a 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -2045,7 +2045,7 @@ static struct attribute *omap_sham_attrs[] = { NULL, }; -static struct attribute_group omap_sham_attr_group = { +static const struct attribute_group omap_sham_attr_group = { .attrs = omap_sham_attrs, }; @@ -2197,8 +2197,7 @@ static int omap_sham_remove(struct platform_device *pdev) int i, j; dd = platform_get_drvdata(pdev); - if (!dd) - return -ENODEV; + spin_lock_bh(&sham.lock); list_del(&dd->list); spin_unlock_bh(&sham.lock); diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig index 4b90c0f22b03..1220cc86f910 100644 --- a/drivers/crypto/qat/Kconfig +++ b/drivers/crypto/qat/Kconfig @@ -17,7 +17,7 @@ config CRYPTO_DEV_QAT config CRYPTO_DEV_QAT_DH895xCC tristate "Support for Intel(R) DH895xCC" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select CRYPTO_DEV_QAT help Support for Intel(R) DH895xcc with Intel(R) QuickAssist Technology @@ -28,7 +28,7 @@ config CRYPTO_DEV_QAT_DH895xCC config CRYPTO_DEV_QAT_C3XXX tristate "Support for Intel(R) C3XXX" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select CRYPTO_DEV_QAT help Support for Intel(R) C3xxx with Intel(R) QuickAssist Technology @@ -39,7 +39,7 @@ config CRYPTO_DEV_QAT_C3XXX config CRYPTO_DEV_QAT_C62X tristate "Support for Intel(R) C62X" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select CRYPTO_DEV_QAT help Support for Intel(R) C62x with Intel(R) QuickAssist Technology @@ -50,7 +50,7 @@ config CRYPTO_DEV_QAT_C62X config CRYPTO_DEV_QAT_4XXX tristate "Support for Intel(R) QAT_4XXX" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select CRYPTO_DEV_QAT help Support for Intel(R) QuickAssist Technology QAT_4xxx @@ -61,7 +61,7 @@ config CRYPTO_DEV_QAT_4XXX config CRYPTO_DEV_QAT_DH895xCCVF tristate "Support for Intel(R) DH895xCC Virtual Function" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select PCI_IOV select CRYPTO_DEV_QAT @@ -74,7 +74,7 @@ config CRYPTO_DEV_QAT_DH895xCCVF config CRYPTO_DEV_QAT_C3XXXVF tristate "Support for Intel(R) C3XXX Virtual Function" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select PCI_IOV select CRYPTO_DEV_QAT help @@ -86,7 +86,7 @@ config CRYPTO_DEV_QAT_C3XXXVF config CRYPTO_DEV_QAT_C62XVF tristate "Support for Intel(R) C62X Virtual Function" - depends on X86 && PCI + depends on PCI && (!CPU_BIG_ENDIAN || COMPILE_TEST) select PCI_IOV select CRYPTO_DEV_QAT help diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c index 6d10edc40aca..fda5f699ff57 100644 --- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c +++ b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c @@ -6,6 +6,7 @@ #include <adf_common_drv.h> #include <adf_gen4_hw_data.h> #include <adf_gen4_pfvf.h> +#include <adf_gen4_pm.h> #include "adf_4xxx_hw_data.h" #include "icp_qat_hw.h" @@ -52,7 +53,7 @@ static const char *const dev_cfg_services[] = { static int get_service_enabled(struct adf_accel_dev *accel_dev) { char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; - u32 ret; + int ret; ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, ADF_SERVICES_ENABLED, services); @@ -229,7 +230,7 @@ static void adf_enable_error_correction(struct adf_accel_dev *accel_dev) void __iomem *csr = misc_bar->virt_addr; /* Enable all in errsou3 except VFLR notification on host */ - ADF_CSR_WR(csr, ADF_4XXX_ERRMSK3, ADF_4XXX_VFLNOTIFY); + ADF_CSR_WR(csr, ADF_GEN4_ERRMSK3, ADF_GEN4_VFLNOTIFY); } static void adf_enable_ints(struct adf_accel_dev *accel_dev) @@ -256,19 +257,19 @@ static int adf_init_device(struct adf_accel_dev *accel_dev) addr = (&GET_BARS(accel_dev)[ADF_4XXX_PMISC_BAR])->virt_addr; /* Temporarily mask PM interrupt */ - csr = ADF_CSR_RD(addr, ADF_4XXX_ERRMSK2); - csr |= ADF_4XXX_PM_SOU; - ADF_CSR_WR(addr, ADF_4XXX_ERRMSK2, csr); + csr = ADF_CSR_RD(addr, ADF_GEN4_ERRMSK2); + csr |= ADF_GEN4_PM_SOU; + ADF_CSR_WR(addr, ADF_GEN4_ERRMSK2, csr); /* Set DRV_ACTIVE bit to power up the device */ - ADF_CSR_WR(addr, ADF_4XXX_PM_INTERRUPT, ADF_4XXX_PM_DRV_ACTIVE); + ADF_CSR_WR(addr, ADF_GEN4_PM_INTERRUPT, ADF_GEN4_PM_DRV_ACTIVE); /* Poll status register to make sure the device is powered up */ ret = read_poll_timeout(ADF_CSR_RD, status, - status & ADF_4XXX_PM_INIT_STATE, - ADF_4XXX_PM_POLL_DELAY_US, - ADF_4XXX_PM_POLL_TIMEOUT_US, true, addr, - ADF_4XXX_PM_STATUS); + status & ADF_GEN4_PM_INIT_STATE, + ADF_GEN4_PM_POLL_DELAY_US, + ADF_GEN4_PM_POLL_TIMEOUT_US, true, addr, + ADF_GEN4_PM_STATUS); if (ret) dev_err(&GET_DEV(accel_dev), "Failed to power up the device\n"); @@ -354,6 +355,9 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data) hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer; hw_data->disable_iov = adf_disable_sriov; hw_data->ring_pair_reset = adf_gen4_ring_pair_reset; + hw_data->enable_pm = adf_gen4_enable_pm; + hw_data->handle_pm_interrupt = adf_gen4_handle_pm_interrupt; + hw_data->dev_config = adf_crypto_dev_config; adf_gen4_init_hw_csr_ops(&hw_data->csr_ops); adf_gen4_init_pf_pfvf_ops(&hw_data->pfvf_ops); diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.h b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.h index 12e4fb9b40ce..9d49248931f6 100644 --- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.h +++ b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.h @@ -39,20 +39,6 @@ #define ADF_4XXX_NUM_RINGS_PER_BANK 2 #define ADF_4XXX_NUM_BANKS_PER_VF 4 -/* Error source registers */ -#define ADF_4XXX_ERRSOU0 (0x41A200) -#define ADF_4XXX_ERRSOU1 (0x41A204) -#define ADF_4XXX_ERRSOU2 (0x41A208) -#define ADF_4XXX_ERRSOU3 (0x41A20C) - -/* Error source mask registers */ -#define ADF_4XXX_ERRMSK0 (0x41A210) -#define ADF_4XXX_ERRMSK1 (0x41A214) -#define ADF_4XXX_ERRMSK2 (0x41A218) -#define ADF_4XXX_ERRMSK3 (0x41A21C) - -#define ADF_4XXX_VFLNOTIFY BIT(7) - /* Arbiter configuration */ #define ADF_4XXX_ARB_CONFIG (BIT(31) | BIT(6) | BIT(0)) #define ADF_4XXX_ARB_OFFSET (0x0) @@ -63,16 +49,6 @@ #define ADF_4XXX_ADMINMSGLR_OFFSET (0x500578) #define ADF_4XXX_MAILBOX_BASE_OFFSET (0x600970) -/* Power management */ -#define ADF_4XXX_PM_POLL_DELAY_US 20 -#define ADF_4XXX_PM_POLL_TIMEOUT_US USEC_PER_SEC -#define ADF_4XXX_PM_STATUS (0x50A00C) -#define ADF_4XXX_PM_INTERRUPT (0x50A028) -#define ADF_4XXX_PM_DRV_ACTIVE BIT(20) -#define ADF_4XXX_PM_INIT_STATE BIT(21) -/* Power management source in ERRSOU2 and ERRMSK2 */ -#define ADF_4XXX_PM_SOU BIT(18) - /* Firmware Binaries */ #define ADF_4XXX_FW "qat_4xxx.bin" #define ADF_4XXX_MMP "qat_4xxx_mmp.bin" @@ -94,5 +70,6 @@ enum icp_qat_4xxx_slice_mask { void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data); void adf_clean_hw_data_4xxx(struct adf_hw_device_data *hw_data); +int adf_crypto_dev_config(struct adf_accel_dev *accel_dev); #endif diff --git a/drivers/crypto/qat/qat_4xxx/adf_drv.c b/drivers/crypto/qat/qat_4xxx/adf_drv.c index a6c78b9c730b..2f212561acc4 100644 --- a/drivers/crypto/qat/qat_4xxx/adf_drv.c +++ b/drivers/crypto/qat/qat_4xxx/adf_drv.c @@ -14,6 +14,7 @@ static const struct pci_device_id adf_pci_tbl[] = { { PCI_VDEVICE(INTEL, ADF_4XXX_PCI_DEVICE_ID), }, + { PCI_VDEVICE(INTEL, ADF_401XX_PCI_DEVICE_ID), }, { } }; MODULE_DEVICE_TABLE(pci, adf_pci_tbl); @@ -52,7 +53,7 @@ static int adf_cfg_dev_init(struct adf_accel_dev *accel_dev) return 0; } -static int adf_crypto_dev_config(struct adf_accel_dev *accel_dev) +int adf_crypto_dev_config(struct adf_accel_dev *accel_dev) { char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES]; int banks = GET_MAX_BANKS(accel_dev); @@ -288,6 +289,10 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_err_disable_aer; } + ret = adf_sysfs_init(accel_dev); + if (ret) + goto out_err_disable_aer; + ret = adf_crypto_dev_config(accel_dev); if (ret) goto out_err_disable_aer; diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c index b941fe3713ff..50d5afa26a9b 100644 --- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c +++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c @@ -78,19 +78,6 @@ static const u32 *adf_get_arbiter_mapping(void) return thrd_to_arb_map; } -static void adf_enable_ints(struct adf_accel_dev *accel_dev) -{ - void __iomem *addr; - - addr = (&GET_BARS(accel_dev)[ADF_C3XXX_PMISC_BAR])->virt_addr; - - /* Enable bundle and misc interrupts */ - ADF_CSR_WR(addr, ADF_C3XXX_SMIAPF0_MASK_OFFSET, - ADF_C3XXX_SMIA0_MASK); - ADF_CSR_WR(addr, ADF_C3XXX_SMIAPF1_MASK_OFFSET, - ADF_C3XXX_SMIA1_MASK); -} - static void configure_iov_threads(struct adf_accel_dev *accel_dev, bool enable) { adf_gen2_cfg_iov_thds(accel_dev, enable, @@ -133,7 +120,7 @@ void adf_init_hw_data_c3xxx(struct adf_hw_device_data *hw_data) hw_data->init_arb = adf_init_arb; hw_data->exit_arb = adf_exit_arb; hw_data->get_arb_mapping = adf_get_arbiter_mapping; - hw_data->enable_ints = adf_enable_ints; + hw_data->enable_ints = adf_gen2_enable_ints; hw_data->reset_device = adf_reset_flr; hw_data->set_ssm_wdtimer = adf_gen2_set_ssm_wdtimer; hw_data->disable_iov = adf_disable_sriov; diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h index 1b86f828725c..336a06f11dbd 100644 --- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h +++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h @@ -13,10 +13,6 @@ #define ADF_C3XXX_ACCELERATORS_MASK 0x7 #define ADF_C3XXX_ACCELENGINES_MASK 0x3F #define ADF_C3XXX_ETR_MAX_BANKS 16 -#define ADF_C3XXX_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28) -#define ADF_C3XXX_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30) -#define ADF_C3XXX_SMIA0_MASK 0xFFFF -#define ADF_C3XXX_SMIA1_MASK 0x1 #define ADF_C3XXX_SOFTSTRAP_CSR_OFFSET 0x2EC /* AE to function mapping */ diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c index b1eac2f81faa..c00386fe6587 100644 --- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c +++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c @@ -80,19 +80,6 @@ static const u32 *adf_get_arbiter_mapping(void) return thrd_to_arb_map; } -static void adf_enable_ints(struct adf_accel_dev *accel_dev) -{ - void __iomem *addr; - - addr = (&GET_BARS(accel_dev)[ADF_C62X_PMISC_BAR])->virt_addr; - - /* Enable bundle and misc interrupts */ - ADF_CSR_WR(addr, ADF_C62X_SMIAPF0_MASK_OFFSET, - ADF_C62X_SMIA0_MASK); - ADF_CSR_WR(addr, ADF_C62X_SMIAPF1_MASK_OFFSET, - ADF_C62X_SMIA1_MASK); -} - static void configure_iov_threads(struct adf_accel_dev *accel_dev, bool enable) { adf_gen2_cfg_iov_thds(accel_dev, enable, @@ -135,7 +122,7 @@ void adf_init_hw_data_c62x(struct adf_hw_device_data *hw_data) hw_data->init_arb = adf_init_arb; hw_data->exit_arb = adf_exit_arb; hw_data->get_arb_mapping = adf_get_arbiter_mapping; - hw_data->enable_ints = adf_enable_ints; + hw_data->enable_ints = adf_gen2_enable_ints; hw_data->reset_device = adf_reset_flr; hw_data->set_ssm_wdtimer = adf_gen2_set_ssm_wdtimer; hw_data->disable_iov = adf_disable_sriov; diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h index 68c3436bd3aa..008c0a3a9769 100644 --- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h +++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h @@ -13,10 +13,6 @@ #define ADF_C62X_ACCELERATORS_MASK 0x1F #define ADF_C62X_ACCELENGINES_MASK 0x3FF #define ADF_C62X_ETR_MAX_BANKS 16 -#define ADF_C62X_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28) -#define ADF_C62X_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30) -#define ADF_C62X_SMIA0_MASK 0xFFFF -#define ADF_C62X_SMIA1_MASK 0x1 #define ADF_C62X_SOFTSTRAP_CSR_OFFSET 0x2EC /* AE to function mapping */ diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile index 7e191a42a5c7..80919cfcc29d 100644 --- a/drivers/crypto/qat/qat_common/Makefile +++ b/drivers/crypto/qat/qat_common/Makefile @@ -10,11 +10,14 @@ intel_qat-objs := adf_cfg.o \ adf_transport.o \ adf_admin.o \ adf_hw_arbiter.o \ + adf_sysfs.o \ adf_gen2_hw_data.o \ adf_gen4_hw_data.o \ + adf_gen4_pm.o \ qat_crypto.o \ qat_algs.o \ qat_asym_algs.o \ + qat_algs_send.o \ qat_uclo.o \ qat_hal.o diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h index 2d4cd7c7cf33..0a55a4f34dcf 100644 --- a/drivers/crypto/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h @@ -19,6 +19,8 @@ #define ADF_4XXX_DEVICE_NAME "4xxx" #define ADF_4XXX_PCI_DEVICE_ID 0x4940 #define ADF_4XXXIOV_PCI_DEVICE_ID 0x4941 +#define ADF_401XX_PCI_DEVICE_ID 0x4942 +#define ADF_401XXIOV_PCI_DEVICE_ID 0x4943 #define ADF_DEVICE_FUSECTL_OFFSET 0x40 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C #define ADF_DEVICE_FUSECTL_MASK 0x80000000 @@ -152,9 +154,9 @@ struct adf_pfvf_ops { int (*enable_comms)(struct adf_accel_dev *accel_dev); u32 (*get_pf2vf_offset)(u32 i); u32 (*get_vf2pf_offset)(u32 i); - u32 (*get_vf2pf_sources)(void __iomem *pmisc_addr); void (*enable_vf2pf_interrupts)(void __iomem *pmisc_addr, u32 vf_mask); - void (*disable_vf2pf_interrupts)(void __iomem *pmisc_addr, u32 vf_mask); + void (*disable_all_vf2pf_interrupts)(void __iomem *pmisc_addr); + u32 (*disable_pending_vf2pf_interrupts)(void __iomem *pmisc_addr); int (*send_msg)(struct adf_accel_dev *accel_dev, struct pfvf_message msg, u32 pfvf_offset, struct mutex *csr_lock); struct pfvf_message (*recv_msg)(struct adf_accel_dev *accel_dev, @@ -184,6 +186,8 @@ struct adf_hw_device_data { void (*exit_arb)(struct adf_accel_dev *accel_dev); const u32 *(*get_arb_mapping)(void); int (*init_device)(struct adf_accel_dev *accel_dev); + int (*enable_pm)(struct adf_accel_dev *accel_dev); + bool (*handle_pm_interrupt)(struct adf_accel_dev *accel_dev); void (*disable_iov)(struct adf_accel_dev *accel_dev); void (*configure_iov_threads)(struct adf_accel_dev *accel_dev, bool enable); @@ -195,6 +199,7 @@ struct adf_hw_device_data { char *(*uof_get_name)(struct adf_accel_dev *accel_dev, u32 obj_num); u32 (*uof_get_num_objs)(void); u32 (*uof_get_ae_mask)(struct adf_accel_dev *accel_dev, u32 obj_num); + int (*dev_config)(struct adf_accel_dev *accel_dev); struct adf_pfvf_ops pfvf_ops; struct adf_hw_csr_ops csr_ops; const char *fw_name; diff --git a/drivers/crypto/qat/qat_common/adf_admin.c b/drivers/crypto/qat/qat_common/adf_admin.c index 498eb6f690e3..3b6184c35081 100644 --- a/drivers/crypto/qat/qat_common/adf_admin.c +++ b/drivers/crypto/qat/qat_common/adf_admin.c @@ -251,6 +251,43 @@ int adf_send_admin_init(struct adf_accel_dev *accel_dev) } EXPORT_SYMBOL_GPL(adf_send_admin_init); +/** + * adf_init_admin_pm() - Function sends PM init message to FW + * @accel_dev: Pointer to acceleration device. + * @idle_delay: QAT HW idle time before power gating is initiated. + * 000 - 64us + * 001 - 128us + * 010 - 256us + * 011 - 512us + * 100 - 1ms + * 101 - 2ms + * 110 - 4ms + * 111 - 8ms + * + * Function sends to the FW the admin init message for the PM state + * configuration. + * + * Return: 0 on success, error code otherwise. + */ +int adf_init_admin_pm(struct adf_accel_dev *accel_dev, u32 idle_delay) +{ + struct adf_hw_device_data *hw_data = accel_dev->hw_device; + struct icp_qat_fw_init_admin_resp resp = {0}; + struct icp_qat_fw_init_admin_req req = {0}; + u32 ae_mask = hw_data->admin_ae_mask; + + if (!accel_dev->admin) { + dev_err(&GET_DEV(accel_dev), "adf_admin is not available\n"); + return -EFAULT; + } + + req.cmd_id = ICP_QAT_FW_PM_STATE_CONFIG; + req.idle_filter = idle_delay; + + return adf_send_admin(accel_dev, &req, &resp, ae_mask); +} +EXPORT_SYMBOL_GPL(adf_init_admin_pm); + int adf_init_admin_comms(struct adf_accel_dev *accel_dev) { struct adf_admin_comms *admin; diff --git a/drivers/crypto/qat/qat_common/adf_cfg.c b/drivers/crypto/qat/qat_common/adf_cfg.c index b5b208cbe5a1..1931e5b37f2b 100644 --- a/drivers/crypto/qat/qat_common/adf_cfg.c +++ b/drivers/crypto/qat/qat_common/adf_cfg.c @@ -128,6 +128,24 @@ static void adf_cfg_keyval_add(struct adf_cfg_key_val *new, list_add_tail(&new->list, &sec->param_head); } +static void adf_cfg_keyval_remove(const char *key, struct adf_cfg_section *sec) +{ + struct list_head *head = &sec->param_head; + struct list_head *list_ptr, *tmp; + + list_for_each_prev_safe(list_ptr, tmp, head) { + struct adf_cfg_key_val *ptr = + list_entry(list_ptr, struct adf_cfg_key_val, list); + + if (strncmp(ptr->key, key, sizeof(ptr->key))) + continue; + + list_del(list_ptr); + kfree(ptr); + break; + } +} + static void adf_cfg_keyval_del_all(struct list_head *head) { struct list_head *list_ptr, *tmp; @@ -208,7 +226,8 @@ static int adf_cfg_key_val_get(struct adf_accel_dev *accel_dev, * @type: Type - string, int or address * * Function adds configuration key - value entry in the appropriate section - * in the given acceleration device + * in the given acceleration device. If the key exists already, the value + * is updated. * To be used by QAT device specific drivers. * * Return: 0 on success, error code otherwise. @@ -222,6 +241,8 @@ int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev, struct adf_cfg_key_val *key_val; struct adf_cfg_section *section = adf_cfg_sec_find(accel_dev, section_name); + char temp_val[ADF_CFG_MAX_VAL_LEN_IN_BYTES]; + if (!section) return -EFAULT; @@ -230,13 +251,13 @@ int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev, return -ENOMEM; INIT_LIST_HEAD(&key_val->list); - strlcpy(key_val->key, key, sizeof(key_val->key)); + strscpy(key_val->key, key, sizeof(key_val->key)); if (type == ADF_DEC) { snprintf(key_val->val, ADF_CFG_MAX_VAL_LEN_IN_BYTES, "%ld", (*((long *)val))); } else if (type == ADF_STR) { - strlcpy(key_val->val, (char *)val, sizeof(key_val->val)); + strscpy(key_val->val, (char *)val, sizeof(key_val->val)); } else if (type == ADF_HEX) { snprintf(key_val->val, ADF_CFG_MAX_VAL_LEN_IN_BYTES, "0x%lx", (unsigned long)val); @@ -246,6 +267,24 @@ int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev, return -EINVAL; } key_val->type = type; + + /* Add the key-value pair as below policy: + * 1. if the key doesn't exist, add it; + * 2. if the key already exists with a different value then update it + * to the new value (the key is deleted and the newly created + * key_val containing the new value is added to the database); + * 3. if the key exists with the same value, then return without doing + * anything (the newly created key_val is freed). + */ + if (!adf_cfg_key_val_get(accel_dev, section_name, key, temp_val)) { + if (strncmp(temp_val, key_val->val, sizeof(temp_val))) { + adf_cfg_keyval_remove(key, section); + } else { + kfree(key_val); + return 0; + } + } + down_write(&cfg->lock); adf_cfg_keyval_add(key_val, section); up_write(&cfg->lock); @@ -276,7 +315,7 @@ int adf_cfg_section_add(struct adf_accel_dev *accel_dev, const char *name) if (!sec) return -ENOMEM; - strlcpy(sec->name, name, sizeof(sec->name)); + strscpy(sec->name, name, sizeof(sec->name)); INIT_LIST_HEAD(&sec->param_head); down_write(&cfg->lock); list_add_tail(&sec->list, &cfg->sec_list); diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h index 76f4f96ec5eb..7bb477c3ce25 100644 --- a/drivers/crypto/qat/qat_common/adf_common_drv.h +++ b/drivers/crypto/qat/qat_common/adf_common_drv.h @@ -49,11 +49,6 @@ struct service_hndl { struct list_head list; }; -static inline int get_current_node(void) -{ - return topology_physical_package_id(raw_smp_processor_id()); -} - int adf_service_register(struct service_hndl *service); int adf_service_unregister(struct service_hndl *service); @@ -61,6 +56,7 @@ int adf_dev_init(struct adf_accel_dev *accel_dev); int adf_dev_start(struct adf_accel_dev *accel_dev); void adf_dev_stop(struct adf_accel_dev *accel_dev); void adf_dev_shutdown(struct adf_accel_dev *accel_dev); +int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev); void adf_devmgr_update_class_index(struct adf_hw_device_data *hw_data); void adf_clean_vf_map(bool); @@ -102,6 +98,7 @@ void adf_exit_aer(void); int adf_init_admin_comms(struct adf_accel_dev *accel_dev); void adf_exit_admin_comms(struct adf_accel_dev *accel_dev); int adf_send_admin_init(struct adf_accel_dev *accel_dev); +int adf_init_admin_pm(struct adf_accel_dev *accel_dev, u32 idle_delay); int adf_init_arb(struct adf_accel_dev *accel_dev); void adf_exit_arb(struct adf_accel_dev *accel_dev); void adf_update_ring_arb(struct adf_etr_ring_data *ring); @@ -131,6 +128,8 @@ void adf_vf_isr_resource_free(struct adf_accel_dev *accel_dev); int adf_pfvf_comms_disabled(struct adf_accel_dev *accel_dev); +int adf_sysfs_init(struct adf_accel_dev *accel_dev); + int qat_hal_init(struct adf_accel_dev *accel_dev); void qat_hal_deinit(struct icp_qat_fw_loader_handle *handle); int qat_hal_start(struct icp_qat_fw_loader_handle *handle); @@ -188,13 +187,14 @@ int qat_uclo_map_obj(struct icp_qat_fw_loader_handle *handle, void *addr_ptr, u32 mem_size, char *obj_name); int qat_uclo_set_cfg_ae_mask(struct icp_qat_fw_loader_handle *handle, unsigned int cfg_ae_mask); +int adf_init_misc_wq(void); +void adf_exit_misc_wq(void); +bool adf_misc_wq_queue_work(struct work_struct *work); #if defined(CONFIG_PCI_IOV) int adf_sriov_configure(struct pci_dev *pdev, int numvfs); void adf_disable_sriov(struct adf_accel_dev *accel_dev); -void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, - u32 vf_mask); -void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, - u32 vf_mask); +void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask); +void adf_disable_all_vf2pf_interrupts(struct adf_accel_dev *accel_dev); bool adf_recv_and_handle_pf2vf_msg(struct adf_accel_dev *accel_dev); bool adf_recv_and_handle_vf2pf_msg(struct adf_accel_dev *accel_dev, u32 vf_nr); int adf_pf2vf_handle_pf_restarting(struct adf_accel_dev *accel_dev); @@ -213,14 +213,6 @@ static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev) { } -static inline void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev) -{ -} - -static inline void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev) -{ -} - static inline int adf_init_pf_wq(void) { return 0; @@ -239,10 +231,6 @@ static inline void adf_exit_vf_wq(void) { } -static inline void adf_flush_vf_wq(struct adf_accel_dev *accel_dev) -{ -} - #endif static inline void __iomem *adf_get_pmisc_base(struct adf_accel_dev *accel_dev) diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index 6f64aa693146..82b69e1f725b 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -16,6 +16,9 @@ #include "adf_cfg_common.h" #include "adf_cfg_user.h" +#define ADF_CFG_MAX_SECTION 512 +#define ADF_CFG_MAX_KEY_VAL 256 + #define DEVICE_NAME "qat_adf_ctl" static DEFINE_MUTEX(adf_ctl_lock); @@ -137,10 +140,11 @@ static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev, struct adf_user_cfg_key_val key_val; struct adf_user_cfg_key_val *params_head; struct adf_user_cfg_section section, *section_head; + int i, j; section_head = ctl_data->config_section; - while (section_head) { + for (i = 0; section_head && i < ADF_CFG_MAX_SECTION; i++) { if (copy_from_user(§ion, (void __user *)section_head, sizeof(*section_head))) { dev_err(&GET_DEV(accel_dev), @@ -156,7 +160,7 @@ static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev, params_head = section.params; - while (params_head) { + for (j = 0; params_head && j < ADF_CFG_MAX_KEY_VAL; j++) { if (copy_from_user(&key_val, (void __user *)params_head, sizeof(key_val))) { dev_err(&GET_DEV(accel_dev), @@ -363,7 +367,7 @@ static int adf_ctl_ioctl_get_status(struct file *fp, unsigned int cmd, dev_info.num_logical_accel = hw_data->num_logical_accel; dev_info.banks_per_accel = hw_data->num_banks / hw_data->num_logical_accel; - strlcpy(dev_info.name, hw_data->dev_class->name, sizeof(dev_info.name)); + strscpy(dev_info.name, hw_data->dev_class->name, sizeof(dev_info.name)); dev_info.instance_id = hw_data->instance_id; dev_info.type = hw_data->dev_class->type; dev_info.bus = accel_to_pci_dev(accel_dev)->bus->number; @@ -419,6 +423,9 @@ static int __init adf_register_ctl_device_driver(void) if (adf_chr_drv_create()) goto err_chr_dev; + if (adf_init_misc_wq()) + goto err_misc_wq; + if (adf_init_aer()) goto err_aer; @@ -440,6 +447,8 @@ err_vf_wq: err_pf_wq: adf_exit_aer(); err_aer: + adf_exit_misc_wq(); +err_misc_wq: adf_chr_drv_destroy(); err_chr_dev: mutex_destroy(&adf_ctl_lock); @@ -449,6 +458,7 @@ err_chr_dev: static void __exit adf_unregister_ctl_device_driver(void) { adf_chr_drv_destroy(); + adf_exit_misc_wq(); adf_exit_aer(); adf_exit_vf_wq(); adf_exit_pf_wq(); diff --git a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c index 57035b7dd4b2..d1884547b5a1 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c +++ b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c @@ -98,6 +98,19 @@ void adf_gen2_get_arb_info(struct arb_info *arb_info) } EXPORT_SYMBOL_GPL(adf_gen2_get_arb_info); +void adf_gen2_enable_ints(struct adf_accel_dev *accel_dev) +{ + void __iomem *addr = adf_get_pmisc_base(accel_dev); + u32 val; + + val = accel_dev->pf.vf_info ? 0 : BIT_ULL(GET_MAX_BANKS(accel_dev)) - 1; + + /* Enable bundle and misc interrupts */ + ADF_CSR_WR(addr, ADF_GEN2_SMIAPF0_MASK_OFFSET, val); + ADF_CSR_WR(addr, ADF_GEN2_SMIAPF1_MASK_OFFSET, ADF_GEN2_SMIA1_MASK); +} +EXPORT_SYMBOL_GPL(adf_gen2_enable_ints); + static u64 build_csr_ring_base_addr(dma_addr_t addr, u32 size) { return BUILD_RING_BASE_ADDR(addr, size); diff --git a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h index f2e0451b11c0..e4bc07529be4 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h +++ b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h @@ -145,6 +145,11 @@ do { \ #define ADF_GEN2_CERRSSMSH(i) ((i) * 0x4000 + 0x10) #define ADF_GEN2_ERRSSMSH_EN BIT(3) +/* Interrupts */ +#define ADF_GEN2_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28) +#define ADF_GEN2_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30) +#define ADF_GEN2_SMIA1_MASK 0x1 + u32 adf_gen2_get_num_accels(struct adf_hw_device_data *self); u32 adf_gen2_get_num_aes(struct adf_hw_device_data *self); void adf_gen2_enable_error_correction(struct adf_accel_dev *accel_dev); @@ -153,6 +158,7 @@ void adf_gen2_cfg_iov_thds(struct adf_accel_dev *accel_dev, bool enable, void adf_gen2_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops); void adf_gen2_get_admin_info(struct admin_info *admin_csrs_info); void adf_gen2_get_arb_info(struct arb_info *arb_info); +void adf_gen2_enable_ints(struct adf_accel_dev *accel_dev); u32 adf_gen2_get_accel_cap(struct adf_accel_dev *accel_dev); void adf_gen2_set_ssm_wdtimer(struct adf_accel_dev *accel_dev); diff --git a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c b/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c index 1a9072aac2ca..70ef11963938 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c +++ b/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c @@ -13,8 +13,9 @@ #include "adf_pfvf_utils.h" /* VF2PF interrupts */ +#define ADF_GEN2_VF_MSK 0xFFFF #define ADF_GEN2_ERR_REG_VF2PF(vf_src) (((vf_src) & 0x01FFFE00) >> 9) -#define ADF_GEN2_ERR_MSK_VF2PF(vf_mask) (((vf_mask) & 0xFFFF) << 9) +#define ADF_GEN2_ERR_MSK_VF2PF(vf_mask) (((vf_mask) & ADF_GEN2_VF_MSK) << 9) #define ADF_GEN2_PF_PF2VF_OFFSET(i) (0x3A000 + 0x280 + ((i) * 0x04)) #define ADF_GEN2_VF_PF2VF_OFFSET 0x200 @@ -50,43 +51,60 @@ static u32 adf_gen2_vf_get_pfvf_offset(u32 i) return ADF_GEN2_VF_PF2VF_OFFSET; } -static u32 adf_gen2_get_vf2pf_sources(void __iomem *pmisc_addr) -{ - u32 errsou3, errmsk3, vf_int_mask; - - /* Get the interrupt sources triggered by VFs */ - errsou3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU3); - vf_int_mask = ADF_GEN2_ERR_REG_VF2PF(errsou3); - - /* To avoid adding duplicate entries to work queue, clear - * vf_int_mask_sets bits that are already masked in ERRMSK register. - */ - errmsk3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3); - vf_int_mask &= ~ADF_GEN2_ERR_REG_VF2PF(errmsk3); - - return vf_int_mask; -} - -static void adf_gen2_enable_vf2pf_interrupts(void __iomem *pmisc_addr, - u32 vf_mask) +static void adf_gen2_enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) { /* Enable VF2PF Messaging Ints - VFs 0 through 15 per vf_mask[15:0] */ - if (vf_mask & 0xFFFF) { + if (vf_mask & ADF_GEN2_VF_MSK) { u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3) & ~ADF_GEN2_ERR_MSK_VF2PF(vf_mask); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, val); } } -static void adf_gen2_disable_vf2pf_interrupts(void __iomem *pmisc_addr, - u32 vf_mask) +static void adf_gen2_disable_all_vf2pf_interrupts(void __iomem *pmisc_addr) { /* Disable VF2PF interrupts for VFs 0 through 15 per vf_mask[15:0] */ - if (vf_mask & 0xFFFF) { - u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3) - | ADF_GEN2_ERR_MSK_VF2PF(vf_mask); - ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, val); - } + u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3) + | ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, val); +} + +static u32 adf_gen2_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) +{ + u32 sources, disabled, pending; + u32 errsou3, errmsk3; + + /* Get the interrupt sources triggered by VFs */ + errsou3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU3); + sources = ADF_GEN2_ERR_REG_VF2PF(errsou3); + + if (!sources) + return 0; + + /* Get the already disabled interrupts */ + errmsk3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3); + disabled = ADF_GEN2_ERR_REG_VF2PF(errmsk3); + + pending = sources & ~disabled; + if (!pending) + return 0; + + /* Due to HW limitations, when disabling the interrupts, we can't + * just disable the requested sources, as this would lead to missed + * interrupts if ERRSOU3 changes just before writing to ERRMSK3. + * To work around it, disable all and re-enable only the sources that + * are not in vf_mask and were not already disabled. Re-enabling will + * trigger a new interrupt for the sources that have changed in the + * meantime, if any. + */ + errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + + errmsk3 &= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + + /* Return the sources of the (new) interrupt(s) */ + return pending; } static u32 gen2_csr_get_int_bit(enum gen2_csr_pos offset) @@ -362,9 +380,9 @@ void adf_gen2_init_pf_pfvf_ops(struct adf_pfvf_ops *pfvf_ops) pfvf_ops->enable_comms = adf_enable_pf2vf_comms; pfvf_ops->get_pf2vf_offset = adf_gen2_pf_get_pfvf_offset; pfvf_ops->get_vf2pf_offset = adf_gen2_pf_get_pfvf_offset; - pfvf_ops->get_vf2pf_sources = adf_gen2_get_vf2pf_sources; pfvf_ops->enable_vf2pf_interrupts = adf_gen2_enable_vf2pf_interrupts; - pfvf_ops->disable_vf2pf_interrupts = adf_gen2_disable_vf2pf_interrupts; + pfvf_ops->disable_all_vf2pf_interrupts = adf_gen2_disable_all_vf2pf_interrupts; + pfvf_ops->disable_pending_vf2pf_interrupts = adf_gen2_disable_pending_vf2pf_interrupts; pfvf_ops->send_msg = adf_gen2_pf2vf_send; pfvf_ops->recv_msg = adf_gen2_vf2pf_recv; } diff --git a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h b/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h index f0f71ca44ca3..4fb4b3df5a18 100644 --- a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h +++ b/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h @@ -107,7 +107,7 @@ do { \ * Timeout is in cycles. Clock speed may vary across products but this * value should be a few milli-seconds. */ -#define ADF_SSM_WDT_DEFAULT_VALUE 0x200000 +#define ADF_SSM_WDT_DEFAULT_VALUE 0x7000000ULL #define ADF_SSM_WDT_PKE_DEFAULT_VALUE 0x8000000 #define ADF_SSMWDTL_OFFSET 0x54 #define ADF_SSMWDTH_OFFSET 0x5C @@ -122,6 +122,20 @@ do { \ #define ADF_WQM_CSR_RPRESETSTS_STATUS BIT(0) #define ADF_WQM_CSR_RPRESETSTS(bank) (ADF_WQM_CSR_RPRESETCTL(bank) + 4) +/* Error source registers */ +#define ADF_GEN4_ERRSOU0 (0x41A200) +#define ADF_GEN4_ERRSOU1 (0x41A204) +#define ADF_GEN4_ERRSOU2 (0x41A208) +#define ADF_GEN4_ERRSOU3 (0x41A20C) + +/* Error source mask registers */ +#define ADF_GEN4_ERRMSK0 (0x41A210) +#define ADF_GEN4_ERRMSK1 (0x41A214) +#define ADF_GEN4_ERRMSK2 (0x41A218) +#define ADF_GEN4_ERRMSK3 (0x41A21C) + +#define ADF_GEN4_VFLNOTIFY BIT(7) + void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev); void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops); int adf_gen4_ring_pair_reset(struct adf_accel_dev *accel_dev, u32 bank_number); diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c b/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c index 8efbedf63bc8..8e8efe93f3ee 100644 --- a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c +++ b/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c @@ -9,15 +9,13 @@ #include "adf_pfvf_pf_proto.h" #include "adf_pfvf_utils.h" -#define ADF_4XXX_MAX_NUM_VFS 16 - #define ADF_4XXX_PF2VM_OFFSET(i) (0x40B010 + ((i) * 0x20)) #define ADF_4XXX_VM2PF_OFFSET(i) (0x40B014 + ((i) * 0x20)) /* VF2PF interrupt source registers */ -#define ADF_4XXX_VM2PF_SOU(i) (0x41A180 + ((i) * 4)) -#define ADF_4XXX_VM2PF_MSK(i) (0x41A1C0 + ((i) * 4)) -#define ADF_4XXX_VM2PF_INT_EN_MSK BIT(0) +#define ADF_4XXX_VM2PF_SOU 0x41A180 +#define ADF_4XXX_VM2PF_MSK 0x41A1C0 +#define ADF_GEN4_VF_MSK 0xFFFF #define ADF_PFVF_GEN4_MSGTYPE_SHIFT 2 #define ADF_PFVF_GEN4_MSGTYPE_MASK 0x3F @@ -39,53 +37,48 @@ static u32 adf_gen4_pf_get_vf2pf_offset(u32 i) return ADF_4XXX_VM2PF_OFFSET(i); } -static u32 adf_gen4_get_vf2pf_sources(void __iomem *pmisc_addr) +static void adf_gen4_enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) { - int i; - u32 sou, mask; - int num_csrs = ADF_4XXX_MAX_NUM_VFS; - u32 vf_mask = 0; - - for (i = 0; i < num_csrs; i++) { - sou = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_SOU(i)); - mask = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK(i)); - sou &= ~mask; - vf_mask |= sou << i; - } + u32 val; - return vf_mask; + val = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK) & ~vf_mask; + ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, val); } -static void adf_gen4_enable_vf2pf_interrupts(void __iomem *pmisc_addr, - u32 vf_mask) +static void adf_gen4_disable_all_vf2pf_interrupts(void __iomem *pmisc_addr) { - int num_csrs = ADF_4XXX_MAX_NUM_VFS; - unsigned long mask = vf_mask; - unsigned int val; - int i; - - for_each_set_bit(i, &mask, num_csrs) { - unsigned int offset = ADF_4XXX_VM2PF_MSK(i); - - val = ADF_CSR_RD(pmisc_addr, offset) & ~ADF_4XXX_VM2PF_INT_EN_MSK; - ADF_CSR_WR(pmisc_addr, offset, val); - } + ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, ADF_GEN4_VF_MSK); } -static void adf_gen4_disable_vf2pf_interrupts(void __iomem *pmisc_addr, - u32 vf_mask) +static u32 adf_gen4_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) { - int num_csrs = ADF_4XXX_MAX_NUM_VFS; - unsigned long mask = vf_mask; - unsigned int val; - int i; - - for_each_set_bit(i, &mask, num_csrs) { - unsigned int offset = ADF_4XXX_VM2PF_MSK(i); + u32 sources, disabled, pending; + + /* Get the interrupt sources triggered by VFs */ + sources = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_SOU); + if (!sources) + return 0; + + /* Get the already disabled interrupts */ + disabled = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK); + + pending = sources & ~disabled; + if (!pending) + return 0; + + /* Due to HW limitations, when disabling the interrupts, we can't + * just disable the requested sources, as this would lead to missed + * interrupts if VM2PF_SOU changes just before writing to VM2PF_MSK. + * To work around it, disable all and re-enable only the sources that + * are not in vf_mask and were not already disabled. Re-enabling will + * trigger a new interrupt for the sources that have changed in the + * meantime, if any. + */ + ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, ADF_GEN4_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, disabled | sources); - val = ADF_CSR_RD(pmisc_addr, offset) | ADF_4XXX_VM2PF_INT_EN_MSK; - ADF_CSR_WR(pmisc_addr, offset, val); - } + /* Return the sources of the (new) interrupt(s) */ + return pending; } static int adf_gen4_pfvf_send(struct adf_accel_dev *accel_dev, @@ -120,10 +113,16 @@ static struct pfvf_message adf_gen4_pfvf_recv(struct adf_accel_dev *accel_dev, u32 pfvf_offset, u8 compat_ver) { void __iomem *pmisc_addr = adf_get_pmisc_base(accel_dev); + struct pfvf_message msg = { 0 }; u32 csr_val; /* Read message from the CSR */ csr_val = ADF_CSR_RD(pmisc_addr, pfvf_offset); + if (!(csr_val & ADF_PFVF_INT)) { + dev_info(&GET_DEV(accel_dev), + "Spurious PFVF interrupt, msg 0x%.8x. Ignored\n", csr_val); + return msg; + } /* We can now acknowledge the message reception by clearing the * interrupt bit @@ -139,9 +138,9 @@ void adf_gen4_init_pf_pfvf_ops(struct adf_pfvf_ops *pfvf_ops) pfvf_ops->enable_comms = adf_enable_pf2vf_comms; pfvf_ops->get_pf2vf_offset = adf_gen4_pf_get_pf2vf_offset; pfvf_ops->get_vf2pf_offset = adf_gen4_pf_get_vf2pf_offset; - pfvf_ops->get_vf2pf_sources = adf_gen4_get_vf2pf_sources; pfvf_ops->enable_vf2pf_interrupts = adf_gen4_enable_vf2pf_interrupts; - pfvf_ops->disable_vf2pf_interrupts = adf_gen4_disable_vf2pf_interrupts; + pfvf_ops->disable_all_vf2pf_interrupts = adf_gen4_disable_all_vf2pf_interrupts; + pfvf_ops->disable_pending_vf2pf_interrupts = adf_gen4_disable_pending_vf2pf_interrupts; pfvf_ops->send_msg = adf_gen4_pfvf_send; pfvf_ops->recv_msg = adf_gen4_pfvf_recv; } diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pm.c b/drivers/crypto/qat/qat_common/adf_gen4_pm.c new file mode 100644 index 000000000000..7037c0892a8a --- /dev/null +++ b/drivers/crypto/qat/qat_common/adf_gen4_pm.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) +/* Copyright(c) 2022 Intel Corporation */ +#include <linux/bitfield.h> +#include <linux/iopoll.h> +#include "adf_accel_devices.h" +#include "adf_common_drv.h" +#include "adf_gen4_pm.h" +#include "adf_cfg_strings.h" +#include "icp_qat_fw_init_admin.h" +#include "adf_gen4_hw_data.h" +#include "adf_cfg.h" + +enum qat_pm_host_msg { + PM_NO_CHANGE = 0, + PM_SET_MIN, +}; + +struct adf_gen4_pm_data { + struct work_struct pm_irq_work; + struct adf_accel_dev *accel_dev; + u32 pm_int_sts; +}; + +static int send_host_msg(struct adf_accel_dev *accel_dev) +{ + void __iomem *pmisc = adf_get_pmisc_base(accel_dev); + u32 msg; + + msg = ADF_CSR_RD(pmisc, ADF_GEN4_PM_HOST_MSG); + if (msg & ADF_GEN4_PM_MSG_PENDING) + return -EBUSY; + + /* Send HOST_MSG */ + msg = FIELD_PREP(ADF_GEN4_PM_MSG_PAYLOAD_BIT_MASK, PM_SET_MIN); + msg |= ADF_GEN4_PM_MSG_PENDING; + ADF_CSR_WR(pmisc, ADF_GEN4_PM_HOST_MSG, msg); + + /* Poll status register to make sure the HOST_MSG has been processed */ + return read_poll_timeout(ADF_CSR_RD, msg, + !(msg & ADF_GEN4_PM_MSG_PENDING), + ADF_GEN4_PM_MSG_POLL_DELAY_US, + ADF_GEN4_PM_POLL_TIMEOUT_US, true, pmisc, + ADF_GEN4_PM_HOST_MSG); +} + +static void pm_bh_handler(struct work_struct *work) +{ + struct adf_gen4_pm_data *pm_data = + container_of(work, struct adf_gen4_pm_data, pm_irq_work); + struct adf_accel_dev *accel_dev = pm_data->accel_dev; + void __iomem *pmisc = adf_get_pmisc_base(accel_dev); + u32 pm_int_sts = pm_data->pm_int_sts; + u32 val; + + /* PM Idle interrupt */ + if (pm_int_sts & ADF_GEN4_PM_IDLE_STS) { + /* Issue host message to FW */ + if (send_host_msg(accel_dev)) + dev_warn_ratelimited(&GET_DEV(accel_dev), + "Failed to send host msg to FW\n"); + } + + /* Clear interrupt status */ + ADF_CSR_WR(pmisc, ADF_GEN4_PM_INTERRUPT, pm_int_sts); + + /* Reenable PM interrupt */ + val = ADF_CSR_RD(pmisc, ADF_GEN4_ERRMSK2); + val &= ~ADF_GEN4_PM_SOU; + ADF_CSR_WR(pmisc, ADF_GEN4_ERRMSK2, val); + + kfree(pm_data); +} + +bool adf_gen4_handle_pm_interrupt(struct adf_accel_dev *accel_dev) +{ + void __iomem *pmisc = adf_get_pmisc_base(accel_dev); + struct adf_gen4_pm_data *pm_data = NULL; + u32 errsou2; + u32 errmsk2; + u32 val; + + /* Only handle the interrupt triggered by PM */ + errmsk2 = ADF_CSR_RD(pmisc, ADF_GEN4_ERRMSK2); + if (errmsk2 & ADF_GEN4_PM_SOU) + return false; + + errsou2 = ADF_CSR_RD(pmisc, ADF_GEN4_ERRSOU2); + if (!(errsou2 & ADF_GEN4_PM_SOU)) + return false; + + /* Disable interrupt */ + val = ADF_CSR_RD(pmisc, ADF_GEN4_ERRMSK2); + val |= ADF_GEN4_PM_SOU; + ADF_CSR_WR(pmisc, ADF_GEN4_ERRMSK2, val); + + val = ADF_CSR_RD(pmisc, ADF_GEN4_PM_INTERRUPT); + + pm_data = kzalloc(sizeof(*pm_data), GFP_ATOMIC); + if (!pm_data) + return false; + + pm_data->pm_int_sts = val; + pm_data->accel_dev = accel_dev; + + INIT_WORK(&pm_data->pm_irq_work, pm_bh_handler); + adf_misc_wq_queue_work(&pm_data->pm_irq_work); + + return true; +} +EXPORT_SYMBOL_GPL(adf_gen4_handle_pm_interrupt); + +int adf_gen4_enable_pm(struct adf_accel_dev *accel_dev) +{ + void __iomem *pmisc = adf_get_pmisc_base(accel_dev); + int ret; + u32 val; + + ret = adf_init_admin_pm(accel_dev, ADF_GEN4_PM_DEFAULT_IDLE_FILTER); + if (ret) + return ret; + + /* Enable default PM interrupts: IDLE, THROTTLE */ + val = ADF_CSR_RD(pmisc, ADF_GEN4_PM_INTERRUPT); + val |= ADF_GEN4_PM_INT_EN_DEFAULT; + + /* Clear interrupt status */ + val |= ADF_GEN4_PM_INT_STS_MASK; + ADF_CSR_WR(pmisc, ADF_GEN4_PM_INTERRUPT, val); + + /* Unmask PM Interrupt */ + val = ADF_CSR_RD(pmisc, ADF_GEN4_ERRMSK2); + val &= ~ADF_GEN4_PM_SOU; + ADF_CSR_WR(pmisc, ADF_GEN4_ERRMSK2, val); + + return 0; +} +EXPORT_SYMBOL_GPL(adf_gen4_enable_pm); diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pm.h b/drivers/crypto/qat/qat_common/adf_gen4_pm.h new file mode 100644 index 000000000000..f8f8a9ee29e5 --- /dev/null +++ b/drivers/crypto/qat/qat_common/adf_gen4_pm.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) */ +/* Copyright(c) 2022 Intel Corporation */ +#ifndef ADF_GEN4_PM_H +#define ADF_GEN4_PM_H + +#include "adf_accel_devices.h" + +/* Power management registers */ +#define ADF_GEN4_PM_HOST_MSG (0x50A01C) + +/* Power management */ +#define ADF_GEN4_PM_POLL_DELAY_US 20 +#define ADF_GEN4_PM_POLL_TIMEOUT_US USEC_PER_SEC +#define ADF_GEN4_PM_MSG_POLL_DELAY_US (10 * USEC_PER_MSEC) +#define ADF_GEN4_PM_STATUS (0x50A00C) +#define ADF_GEN4_PM_INTERRUPT (0x50A028) + +/* Power management source in ERRSOU2 and ERRMSK2 */ +#define ADF_GEN4_PM_SOU BIT(18) + +#define ADF_GEN4_PM_IDLE_INT_EN BIT(18) +#define ADF_GEN4_PM_THROTTLE_INT_EN BIT(19) +#define ADF_GEN4_PM_DRV_ACTIVE BIT(20) +#define ADF_GEN4_PM_INIT_STATE BIT(21) +#define ADF_GEN4_PM_INT_EN_DEFAULT (ADF_GEN4_PM_IDLE_INT_EN | \ + ADF_GEN4_PM_THROTTLE_INT_EN) + +#define ADF_GEN4_PM_THR_STS BIT(0) +#define ADF_GEN4_PM_IDLE_STS BIT(1) +#define ADF_GEN4_PM_FW_INT_STS BIT(2) +#define ADF_GEN4_PM_INT_STS_MASK (ADF_GEN4_PM_THR_STS | \ + ADF_GEN4_PM_IDLE_STS | \ + ADF_GEN4_PM_FW_INT_STS) + +#define ADF_GEN4_PM_MSG_PENDING BIT(0) +#define ADF_GEN4_PM_MSG_PAYLOAD_BIT_MASK GENMASK(28, 1) + +#define ADF_GEN4_PM_DEFAULT_IDLE_FILTER (0x0) +#define ADF_GEN4_PM_MAX_IDLE_FILTER (0x7) + +int adf_gen4_enable_pm(struct adf_accel_dev *accel_dev); +bool adf_gen4_handle_pm_interrupt(struct adf_accel_dev *accel_dev); + +#endif diff --git a/drivers/crypto/qat/qat_common/adf_init.c b/drivers/crypto/qat/qat_common/adf_init.c index 2edc63c6b6ca..33a9a46d6949 100644 --- a/drivers/crypto/qat/qat_common/adf_init.c +++ b/drivers/crypto/qat/qat_common/adf_init.c @@ -181,6 +181,12 @@ int adf_dev_start(struct adf_accel_dev *accel_dev) if (hw_data->set_ssm_wdtimer) hw_data->set_ssm_wdtimer(accel_dev); + /* Enable Power Management */ + if (hw_data->enable_pm && hw_data->enable_pm(accel_dev)) { + dev_err(&GET_DEV(accel_dev), "Failed to configure Power Management\n"); + return -EFAULT; + } + list_for_each(list_itr, &service_table) { service = list_entry(list_itr, struct service_hndl, list); if (service->event_hld(accel_dev, ADF_EVENT_START)) { @@ -357,3 +363,29 @@ int adf_dev_restarted_notify(struct adf_accel_dev *accel_dev) } return 0; } + +int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev) +{ + char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; + int ret; + + ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, + ADF_SERVICES_ENABLED, services); + + adf_dev_stop(accel_dev); + adf_dev_shutdown(accel_dev); + + if (!ret) { + ret = adf_cfg_section_add(accel_dev, ADF_GENERAL_SEC); + if (ret) + return ret; + + ret = adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC, + ADF_SERVICES_ENABLED, + services, ADF_STR); + if (ret) + return ret; + } + + return 0; +} diff --git a/drivers/crypto/qat/qat_common/adf_isr.c b/drivers/crypto/qat/qat_common/adf_isr.c index 4ca482aa69f7..ad9e135b8560 100644 --- a/drivers/crypto/qat/qat_common/adf_isr.c +++ b/drivers/crypto/qat/qat_common/adf_isr.c @@ -16,6 +16,7 @@ #include "adf_transport_internal.h" #define ADF_MAX_NUM_VFS 32 +static struct workqueue_struct *adf_misc_wq; static int adf_enable_msix(struct adf_accel_dev *accel_dev) { @@ -65,42 +66,39 @@ void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask) spin_unlock_irqrestore(&accel_dev->pf.vf2pf_ints_lock, flags); } -void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask) +void adf_disable_all_vf2pf_interrupts(struct adf_accel_dev *accel_dev) { void __iomem *pmisc_addr = adf_get_pmisc_base(accel_dev); unsigned long flags; spin_lock_irqsave(&accel_dev->pf.vf2pf_ints_lock, flags); - GET_PFVF_OPS(accel_dev)->disable_vf2pf_interrupts(pmisc_addr, vf_mask); + GET_PFVF_OPS(accel_dev)->disable_all_vf2pf_interrupts(pmisc_addr); spin_unlock_irqrestore(&accel_dev->pf.vf2pf_ints_lock, flags); } -static void adf_disable_vf2pf_interrupts_irq(struct adf_accel_dev *accel_dev, - u32 vf_mask) +static u32 adf_disable_pending_vf2pf_interrupts(struct adf_accel_dev *accel_dev) { void __iomem *pmisc_addr = adf_get_pmisc_base(accel_dev); + u32 pending; spin_lock(&accel_dev->pf.vf2pf_ints_lock); - GET_PFVF_OPS(accel_dev)->disable_vf2pf_interrupts(pmisc_addr, vf_mask); + pending = GET_PFVF_OPS(accel_dev)->disable_pending_vf2pf_interrupts(pmisc_addr); spin_unlock(&accel_dev->pf.vf2pf_ints_lock); + + return pending; } static bool adf_handle_vf2pf_int(struct adf_accel_dev *accel_dev) { - void __iomem *pmisc_addr = adf_get_pmisc_base(accel_dev); bool irq_handled = false; unsigned long vf_mask; - /* Get the interrupt sources triggered by VFs */ - vf_mask = GET_PFVF_OPS(accel_dev)->get_vf2pf_sources(pmisc_addr); - + /* Get the interrupt sources triggered by VFs, except for those already disabled */ + vf_mask = adf_disable_pending_vf2pf_interrupts(accel_dev); if (vf_mask) { struct adf_accel_vf_info *vf_info; int i; - /* Disable VF2PF interrupts for VFs with pending ints */ - adf_disable_vf2pf_interrupts_irq(accel_dev, vf_mask); - /* * Handle VF2PF interrupt unless the VF is malicious and * is attempting to flood the host OS with VF2PF interrupts. @@ -123,6 +121,17 @@ static bool adf_handle_vf2pf_int(struct adf_accel_dev *accel_dev) } #endif /* CONFIG_PCI_IOV */ +static bool adf_handle_pm_int(struct adf_accel_dev *accel_dev) +{ + struct adf_hw_device_data *hw_data = accel_dev->hw_device; + + if (hw_data->handle_pm_interrupt && + hw_data->handle_pm_interrupt(accel_dev)) + return true; + + return false; +} + static irqreturn_t adf_msix_isr_ae(int irq, void *dev_ptr) { struct adf_accel_dev *accel_dev = dev_ptr; @@ -133,6 +142,9 @@ static irqreturn_t adf_msix_isr_ae(int irq, void *dev_ptr) return IRQ_HANDLED; #endif /* CONFIG_PCI_IOV */ + if (adf_handle_pm_int(accel_dev)) + return IRQ_HANDLED; + dev_dbg(&GET_DEV(accel_dev), "qat_dev%d spurious AE interrupt\n", accel_dev->accel_id); @@ -341,3 +353,30 @@ err_out: return ret; } EXPORT_SYMBOL_GPL(adf_isr_resource_alloc); + +/** + * adf_init_misc_wq() - Init misc workqueue + * + * Function init workqueue 'qat_misc_wq' for general purpose. + * + * Return: 0 on success, error code otherwise. + */ +int __init adf_init_misc_wq(void) +{ + adf_misc_wq = alloc_workqueue("qat_misc_wq", WQ_MEM_RECLAIM, 0); + + return !adf_misc_wq ? -ENOMEM : 0; +} + +void adf_exit_misc_wq(void) +{ + if (adf_misc_wq) + destroy_workqueue(adf_misc_wq); + + adf_misc_wq = NULL; +} + +bool adf_misc_wq_queue_work(struct work_struct *work) +{ + return queue_work(adf_misc_wq, work); +} diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_msg.h b/drivers/crypto/qat/qat_common/adf_pfvf_msg.h index 9c37a2661392..204a42438992 100644 --- a/drivers/crypto/qat/qat_common/adf_pfvf_msg.h +++ b/drivers/crypto/qat/qat_common/adf_pfvf_msg.h @@ -8,8 +8,8 @@ /* * PF<->VF Gen2 Messaging format * - * The PF has an array of 32-bit PF2VF registers, one for each VF. The - * PF can access all these registers; each VF can access only the one + * The PF has an array of 32-bit PF2VF registers, one for each VF. The + * PF can access all these registers while each VF can access only the one * register associated with that particular VF. * * The register functionally is split into two parts: diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.c b/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.c index 588352de1ef0..388e58bcbcaf 100644 --- a/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.c +++ b/drivers/crypto/qat/qat_common/adf_pfvf_pf_proto.c @@ -154,7 +154,7 @@ static struct pfvf_message handle_blkmsg_req(struct adf_accel_vf_info *vf_info, if (FIELD_GET(ADF_VF2PF_BLOCK_CRC_REQ_MASK, req.data)) { dev_dbg(&GET_DEV(vf_info->accel_dev), "BlockMsg of type %d for CRC over %d bytes received from VF%d\n", - blk_type, blk_byte, vf_info->vf_nr); + blk_type, blk_byte + 1, vf_info->vf_nr); if (!adf_pf2vf_blkmsg_get_data(vf_info, blk_type, blk_byte, byte_max, &resp_data, @@ -242,7 +242,9 @@ static int adf_handle_vf2pf_msg(struct adf_accel_dev *accel_dev, u8 vf_nr, "VersionRequest received from VF%d (vers %d) to PF (vers %d)\n", vf_nr, vf_compat_ver, ADF_PFVF_COMPAT_THIS_VERSION); - if (vf_compat_ver <= ADF_PFVF_COMPAT_THIS_VERSION) + if (vf_compat_ver == 0) + compat = ADF_PF2VF_VF_INCOMPATIBLE; + else if (vf_compat_ver <= ADF_PFVF_COMPAT_THIS_VERSION) compat = ADF_PF2VF_VF_COMPATIBLE; else compat = ADF_PF2VF_VF_COMPAT_UNKNOWN; diff --git a/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.c b/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.c index 14b222691c9c..1141258db4b6 100644 --- a/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.c +++ b/drivers/crypto/qat/qat_common/adf_pfvf_vf_msg.c @@ -96,7 +96,7 @@ int adf_vf2pf_request_version(struct adf_accel_dev *accel_dev) int adf_vf2pf_get_capabilities(struct adf_accel_dev *accel_dev) { struct adf_hw_device_data *hw_data = accel_dev->hw_device; - struct capabilities_v3 cap_msg = { { 0 }, }; + struct capabilities_v3 cap_msg = { 0 }; unsigned int len = sizeof(cap_msg); if (accel_dev->vf.pf_compat_ver < ADF_PFVF_COMPAT_CAPABILITIES) @@ -141,7 +141,7 @@ int adf_vf2pf_get_capabilities(struct adf_accel_dev *accel_dev) int adf_vf2pf_get_ring_to_svc(struct adf_accel_dev *accel_dev) { - struct ring_to_svc_map_v1 rts_map_msg = { { 0 }, }; + struct ring_to_svc_map_v1 rts_map_msg = { 0 }; unsigned int len = sizeof(rts_map_msg); if (accel_dev->vf.pf_compat_ver < ADF_PFVF_COMPAT_RING_TO_SVC_MAP) diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c index b960bca1f9d2..b2db1d70d71f 100644 --- a/drivers/crypto/qat/qat_common/adf_sriov.c +++ b/drivers/crypto/qat/qat_common/adf_sriov.c @@ -3,7 +3,6 @@ #include <linux/workqueue.h> #include <linux/pci.h> #include <linux/device.h> -#include <linux/iommu.h> #include "adf_common_drv.h" #include "adf_cfg.h" #include "adf_pfvf_pf_msg.h" @@ -74,8 +73,7 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev) hw_data->configure_iov_threads(accel_dev, true); /* Enable VF to PF interrupts for all VFs */ - if (hw_data->pfvf_ops.get_pf2vf_offset) - adf_enable_vf2pf_interrupts(accel_dev, BIT_ULL(totalvfs) - 1); + adf_enable_vf2pf_interrupts(accel_dev, BIT_ULL(totalvfs) - 1); /* * Due to the hardware design, when SR-IOV and the ring arbiter @@ -104,54 +102,24 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev) if (!accel_dev->pf.vf_info) return; - if (hw_data->pfvf_ops.get_pf2vf_offset) - adf_pf2vf_notify_restarting(accel_dev); - + adf_pf2vf_notify_restarting(accel_dev); pci_disable_sriov(accel_to_pci_dev(accel_dev)); /* Disable VF to PF interrupts */ - if (hw_data->pfvf_ops.get_pf2vf_offset) - adf_disable_vf2pf_interrupts(accel_dev, GENMASK(31, 0)); + adf_disable_all_vf2pf_interrupts(accel_dev); /* Clear Valid bits in AE Thread to PCIe Function Mapping */ if (hw_data->configure_iov_threads) hw_data->configure_iov_threads(accel_dev, false); - for (i = 0, vf = accel_dev->pf.vf_info; i < totalvfs; i++, vf++) { + for (i = 0, vf = accel_dev->pf.vf_info; i < totalvfs; i++, vf++) mutex_destroy(&vf->pf2vf_lock); - } kfree(accel_dev->pf.vf_info); accel_dev->pf.vf_info = NULL; } EXPORT_SYMBOL_GPL(adf_disable_sriov); -static int adf_sriov_prepare_restart(struct adf_accel_dev *accel_dev) -{ - char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; - int ret; - - ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, - ADF_SERVICES_ENABLED, services); - - adf_dev_stop(accel_dev); - adf_dev_shutdown(accel_dev); - - if (!ret) { - ret = adf_cfg_section_add(accel_dev, ADF_GENERAL_SEC); - if (ret) - return ret; - - ret = adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC, - ADF_SERVICES_ENABLED, - services, ADF_STR); - if (ret) - return ret; - } - - return 0; -} - /** * adf_sriov_configure() - Enable SRIOV for the device * @pdev: Pointer to PCI device. @@ -176,7 +144,7 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs) return -EFAULT; } - if (!iommu_present(&pci_bus_type)) + if (!device_iommu_mapped(&pdev->dev)) dev_warn(&pdev->dev, "IOMMU should be enabled for SR-IOV to work correctly\n"); if (accel_dev->pf.vf_info) { @@ -191,7 +159,7 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs) return -EBUSY; } - ret = adf_sriov_prepare_restart(accel_dev); + ret = adf_dev_shutdown_cache_cfg(accel_dev); if (ret) return ret; } diff --git a/drivers/crypto/qat/qat_common/adf_sysfs.c b/drivers/crypto/qat/qat_common/adf_sysfs.c new file mode 100644 index 000000000000..e8b078e719c2 --- /dev/null +++ b/drivers/crypto/qat/qat_common/adf_sysfs.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) +/* Copyright(c) 2022 Intel Corporation */ +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include "adf_accel_devices.h" +#include "adf_cfg.h" +#include "adf_common_drv.h" + +static const char * const state_operations[] = { + [DEV_DOWN] = "down", + [DEV_UP] = "up", +}; + +static ssize_t state_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct adf_accel_dev *accel_dev; + char *state; + + accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); + if (!accel_dev) + return -EINVAL; + + state = adf_dev_started(accel_dev) ? "up" : "down"; + return sysfs_emit(buf, "%s\n", state); +} + +static ssize_t state_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct adf_accel_dev *accel_dev; + u32 accel_id; + int ret; + + accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); + if (!accel_dev) + return -EINVAL; + + accel_id = accel_dev->accel_id; + + if (adf_devmgr_in_reset(accel_dev) || adf_dev_in_use(accel_dev)) { + dev_info(dev, "Device qat_dev%d is busy\n", accel_id); + return -EBUSY; + } + + ret = sysfs_match_string(state_operations, buf); + if (ret < 0) + return ret; + + switch (ret) { + case DEV_DOWN: + if (!adf_dev_started(accel_dev)) { + dev_info(dev, "Device qat_dev%d already down\n", + accel_id); + return -EINVAL; + } + + dev_info(dev, "Stopping device qat_dev%d\n", accel_id); + + ret = adf_dev_shutdown_cache_cfg(accel_dev); + if (ret < 0) + return -EINVAL; + + break; + case DEV_UP: + if (adf_dev_started(accel_dev)) { + dev_info(dev, "Device qat_dev%d already up\n", + accel_id); + return -EINVAL; + } + + dev_info(dev, "Starting device qat_dev%d\n", accel_id); + + ret = GET_HW_DATA(accel_dev)->dev_config(accel_dev); + if (!ret) + ret = adf_dev_init(accel_dev); + if (!ret) + ret = adf_dev_start(accel_dev); + + if (ret < 0) { + dev_err(dev, "Failed to start device qat_dev%d\n", + accel_id); + adf_dev_shutdown_cache_cfg(accel_dev); + return ret; + } + break; + default: + return -EINVAL; + } + + return count; +} + +static const char * const services_operations[] = { + ADF_CFG_CY, + ADF_CFG_DC, +}; + +static ssize_t cfg_services_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; + struct adf_accel_dev *accel_dev; + int ret; + + accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); + if (!accel_dev) + return -EINVAL; + + ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, + ADF_SERVICES_ENABLED, services); + if (ret) + return ret; + + return sysfs_emit(buf, "%s\n", services); +} + +static int adf_sysfs_update_dev_config(struct adf_accel_dev *accel_dev, + const char *services) +{ + return adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC, + ADF_SERVICES_ENABLED, services, + ADF_STR); +} + +static ssize_t cfg_services_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct adf_hw_device_data *hw_data; + struct adf_accel_dev *accel_dev; + int ret; + + ret = sysfs_match_string(services_operations, buf); + if (ret < 0) + return ret; + + accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); + if (!accel_dev) + return -EINVAL; + + if (adf_dev_started(accel_dev)) { + dev_info(dev, "Device qat_dev%d must be down to reconfigure the service.\n", + accel_dev->accel_id); + return -EINVAL; + } + + ret = adf_sysfs_update_dev_config(accel_dev, services_operations[ret]); + if (ret < 0) + return ret; + + hw_data = GET_HW_DATA(accel_dev); + + /* Update capabilities mask after change in configuration. + * A call to this function is required as capabilities are, at the + * moment, tied to configuration + */ + hw_data->accel_capabilities_mask = hw_data->get_accel_cap(accel_dev); + if (!hw_data->accel_capabilities_mask) + return -EINVAL; + + return count; +} + +static DEVICE_ATTR_RW(state); +static DEVICE_ATTR_RW(cfg_services); + +static struct attribute *qat_attrs[] = { + &dev_attr_state.attr, + &dev_attr_cfg_services.attr, + NULL, +}; + +static struct attribute_group qat_group = { + .attrs = qat_attrs, + .name = "qat", +}; + +int adf_sysfs_init(struct adf_accel_dev *accel_dev) +{ + int ret; + + ret = devm_device_add_group(&GET_DEV(accel_dev), &qat_group); + if (ret) { + dev_err(&GET_DEV(accel_dev), + "Failed to create qat attribute group: %d\n", ret); + } + + return ret; +} +EXPORT_SYMBOL_GPL(adf_sysfs_init); diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c index 8ba28409fb74..630d0483c4e0 100644 --- a/drivers/crypto/qat/qat_common/adf_transport.c +++ b/drivers/crypto/qat/qat_common/adf_transport.c @@ -8,6 +8,9 @@ #include "adf_cfg.h" #include "adf_common_drv.h" +#define ADF_MAX_RING_THRESHOLD 80 +#define ADF_PERCENT(tot, percent) (((tot) * (percent)) / 100) + static inline u32 adf_modulo(u32 data, u32 shift) { u32 div = data >> shift; @@ -77,6 +80,11 @@ static void adf_disable_ring_irq(struct adf_etr_bank_data *bank, u32 ring) bank->irq_mask); } +bool adf_ring_nearly_full(struct adf_etr_ring_data *ring) +{ + return atomic_read(ring->inflights) > ring->threshold; +} + int adf_send_message(struct adf_etr_ring_data *ring, u32 *msg) { struct adf_hw_csr_ops *csr_ops = GET_CSR_OPS(ring->bank->accel_dev); @@ -217,6 +225,7 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section, struct adf_etr_bank_data *bank; struct adf_etr_ring_data *ring; char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES]; + int max_inflights; u32 ring_num; int ret; @@ -263,6 +272,8 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section, ring->ring_size = adf_verify_ring_size(msg_size, num_msgs); ring->head = 0; ring->tail = 0; + max_inflights = ADF_MAX_INFLIGHTS(ring->ring_size, ring->msg_size); + ring->threshold = ADF_PERCENT(max_inflights, ADF_MAX_RING_THRESHOLD); atomic_set(ring->inflights, 0); ret = adf_init_ring(ring); if (ret) diff --git a/drivers/crypto/qat/qat_common/adf_transport.h b/drivers/crypto/qat/qat_common/adf_transport.h index 2c95f1697c76..e6ef6f9b7691 100644 --- a/drivers/crypto/qat/qat_common/adf_transport.h +++ b/drivers/crypto/qat/qat_common/adf_transport.h @@ -14,6 +14,7 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section, const char *ring_name, adf_callback_fn callback, int poll_mode, struct adf_etr_ring_data **ring_ptr); +bool adf_ring_nearly_full(struct adf_etr_ring_data *ring); int adf_send_message(struct adf_etr_ring_data *ring, u32 *msg); void adf_remove_ring(struct adf_etr_ring_data *ring); #endif diff --git a/drivers/crypto/qat/qat_common/adf_transport_debug.c b/drivers/crypto/qat/qat_common/adf_transport_debug.c index e69e5907f595..08bca1c506c0 100644 --- a/drivers/crypto/qat/qat_common/adf_transport_debug.c +++ b/drivers/crypto/qat/qat_common/adf_transport_debug.c @@ -96,7 +96,7 @@ int adf_ring_debugfs_add(struct adf_etr_ring_data *ring, const char *name) if (!ring_debug) return -ENOMEM; - strlcpy(ring_debug->ring_name, name, sizeof(ring_debug->ring_name)); + strscpy(ring_debug->ring_name, name, sizeof(ring_debug->ring_name)); snprintf(entry_name, sizeof(entry_name), "ring_%02d", ring->ring_number); diff --git a/drivers/crypto/qat/qat_common/adf_transport_internal.h b/drivers/crypto/qat/qat_common/adf_transport_internal.h index 501bcf0f1809..8b2c92ba7ca1 100644 --- a/drivers/crypto/qat/qat_common/adf_transport_internal.h +++ b/drivers/crypto/qat/qat_common/adf_transport_internal.h @@ -22,6 +22,7 @@ struct adf_etr_ring_data { spinlock_t lock; /* protects ring data struct */ u16 head; u16 tail; + u32 threshold; u8 ring_number; u8 ring_size; u8 msg_size; diff --git a/drivers/crypto/qat/qat_common/adf_vf_isr.c b/drivers/crypto/qat/qat_common/adf_vf_isr.c index 86c3bd0c9c2b..8c95fcd8e64b 100644 --- a/drivers/crypto/qat/qat_common/adf_vf_isr.c +++ b/drivers/crypto/qat/qat_common/adf_vf_isr.c @@ -70,6 +70,7 @@ static void adf_dev_stop_async(struct work_struct *work) container_of(work, struct adf_vf_stop_data, work); struct adf_accel_dev *accel_dev = stop_data->accel_dev; + adf_dev_restarting_notify(accel_dev); adf_dev_stop(accel_dev); adf_dev_shutdown(accel_dev); diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h b/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h index afe59a7684ac..56cb827f93ea 100644 --- a/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h +++ b/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h @@ -16,6 +16,7 @@ enum icp_qat_fw_init_admin_cmd_id { ICP_QAT_FW_HEARTBEAT_SYNC = 7, ICP_QAT_FW_HEARTBEAT_GET = 8, ICP_QAT_FW_COMP_CAPABILITY_GET = 9, + ICP_QAT_FW_PM_STATE_CONFIG = 128, }; enum icp_qat_fw_init_admin_resp_status { diff --git a/drivers/crypto/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/qat/qat_common/icp_qat_uclo.h index 4b36869bf460..69482abdb8b9 100644 --- a/drivers/crypto/qat/qat_common/icp_qat_uclo.h +++ b/drivers/crypto/qat/qat_common/icp_qat_uclo.h @@ -86,7 +86,8 @@ ICP_QAT_CSS_FWSK_MODULUS_LEN(handle) + \ ICP_QAT_CSS_FWSK_EXPONENT_LEN(handle) + \ ICP_QAT_CSS_SIGNATURE_LEN(handle)) -#define ICP_QAT_CSS_MAX_IMAGE_LEN 0x40000 +#define ICP_QAT_CSS_RSA4K_MAX_IMAGE_LEN 0x40000 +#define ICP_QAT_CSS_RSA3K_MAX_IMAGE_LEN 0x30000 #define ICP_QAT_CTX_MODE(ae_mode) ((ae_mode) & 0xf) #define ICP_QAT_NN_MODE(ae_mode) (((ae_mode) >> 0x4) & 0xf) diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index f998ed58457c..cad9c58caab1 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -17,7 +17,7 @@ #include <crypto/xts.h> #include <linux/dma-mapping.h> #include "adf_accel_devices.h" -#include "adf_transport.h" +#include "qat_algs_send.h" #include "adf_common_drv.h" #include "qat_crypto.h" #include "icp_qat_hw.h" @@ -46,19 +46,6 @@ static DEFINE_MUTEX(algs_lock); static unsigned int active_devs; -struct qat_alg_buf { - u32 len; - u32 resrvd; - u64 addr; -} __packed; - -struct qat_alg_buf_list { - u64 resrvd; - u32 num_bufs; - u32 num_mapped_bufs; - struct qat_alg_buf bufers[]; -} __packed __aligned(64); - /* Common content descriptor */ struct qat_alg_cd { union { @@ -618,7 +605,7 @@ static int qat_alg_aead_newkey(struct crypto_aead *tfm, const u8 *key, { struct qat_alg_aead_ctx *ctx = crypto_aead_ctx(tfm); struct qat_crypto_instance *inst = NULL; - int node = get_current_node(); + int node = numa_node_id(); struct device *dev; int ret; @@ -686,14 +673,20 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst, dma_addr_t blpout = qat_req->buf.bloutp; size_t sz = qat_req->buf.sz; size_t sz_out = qat_req->buf.sz_out; + int bl_dma_dir; int i; + bl_dma_dir = blp != blpout ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL; + for (i = 0; i < bl->num_bufs; i++) dma_unmap_single(dev, bl->bufers[i].addr, - bl->bufers[i].len, DMA_BIDIRECTIONAL); + bl->bufers[i].len, bl_dma_dir); dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE); - kfree(bl); + + if (!qat_req->buf.sgl_src_valid) + kfree(bl); + if (blp != blpout) { /* If out of place operation dma unmap only data */ int bufless = blout->num_bufs - blout->num_mapped_bufs; @@ -701,17 +694,20 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst, for (i = bufless; i < blout->num_bufs; i++) { dma_unmap_single(dev, blout->bufers[i].addr, blout->bufers[i].len, - DMA_BIDIRECTIONAL); + DMA_FROM_DEVICE); } dma_unmap_single(dev, blpout, sz_out, DMA_TO_DEVICE); - kfree(blout); + + if (!qat_req->buf.sgl_dst_valid) + kfree(blout); } } static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, struct scatterlist *sgl, struct scatterlist *sglout, - struct qat_crypto_request *qat_req) + struct qat_crypto_request *qat_req, + gfp_t flags) { struct device *dev = &GET_DEV(inst->accel_dev); int i, sg_nctr = 0; @@ -721,15 +717,27 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, dma_addr_t blp = DMA_MAPPING_ERROR; dma_addr_t bloutp = DMA_MAPPING_ERROR; struct scatterlist *sg; - size_t sz_out, sz = struct_size(bufl, bufers, n + 1); + size_t sz_out, sz = struct_size(bufl, bufers, n); + int node = dev_to_node(&GET_DEV(inst->accel_dev)); + int bufl_dma_dir; if (unlikely(!n)) return -EINVAL; - bufl = kzalloc_node(sz, GFP_ATOMIC, - dev_to_node(&GET_DEV(inst->accel_dev))); - if (unlikely(!bufl)) - return -ENOMEM; + qat_req->buf.sgl_src_valid = false; + qat_req->buf.sgl_dst_valid = false; + + if (n > QAT_MAX_BUFF_DESC) { + bufl = kzalloc_node(sz, flags, node); + if (unlikely(!bufl)) + return -ENOMEM; + } else { + bufl = &qat_req->buf.sgl_src.sgl_hdr; + memset(bufl, 0, sizeof(struct qat_alg_buf_list)); + qat_req->buf.sgl_src_valid = true; + } + + bufl_dma_dir = sgl != sglout ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL; for_each_sg(sgl, sg, n, i) bufl->bufers[i].addr = DMA_MAPPING_ERROR; @@ -742,7 +750,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, bufl->bufers[y].addr = dma_map_single(dev, sg_virt(sg), sg->length, - DMA_BIDIRECTIONAL); + bufl_dma_dir); bufl->bufers[y].len = sg->length; if (unlikely(dma_mapping_error(dev, bufl->bufers[y].addr))) goto err_in; @@ -760,12 +768,18 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, struct qat_alg_buf *bufers; n = sg_nents(sglout); - sz_out = struct_size(buflout, bufers, n + 1); + sz_out = struct_size(buflout, bufers, n); sg_nctr = 0; - buflout = kzalloc_node(sz_out, GFP_ATOMIC, - dev_to_node(&GET_DEV(inst->accel_dev))); - if (unlikely(!buflout)) - goto err_in; + + if (n > QAT_MAX_BUFF_DESC) { + buflout = kzalloc_node(sz_out, flags, node); + if (unlikely(!buflout)) + goto err_in; + } else { + buflout = &qat_req->buf.sgl_dst.sgl_hdr; + memset(buflout, 0, sizeof(struct qat_alg_buf_list)); + qat_req->buf.sgl_dst_valid = true; + } bufers = buflout->bufers; for_each_sg(sglout, sg, n, i) @@ -779,7 +793,7 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, bufers[y].addr = dma_map_single(dev, sg_virt(sg), sg->length, - DMA_BIDIRECTIONAL); + DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(dev, bufers[y].addr))) goto err_out; bufers[y].len = sg->length; @@ -809,8 +823,10 @@ err_out: if (!dma_mapping_error(dev, buflout->bufers[i].addr)) dma_unmap_single(dev, buflout->bufers[i].addr, buflout->bufers[i].len, - DMA_BIDIRECTIONAL); - kfree(buflout); + DMA_FROM_DEVICE); + + if (!qat_req->buf.sgl_dst_valid) + kfree(buflout); err_in: if (!dma_mapping_error(dev, blp)) @@ -821,9 +837,10 @@ err_in: if (!dma_mapping_error(dev, bufl->bufers[i].addr)) dma_unmap_single(dev, bufl->bufers[i].addr, bufl->bufers[i].len, - DMA_BIDIRECTIONAL); + bufl_dma_dir); - kfree(bufl); + if (!qat_req->buf.sgl_src_valid) + kfree(bufl); dev_err(dev, "Failed to map buf for dma\n"); return -ENOMEM; @@ -925,8 +942,25 @@ void qat_alg_callback(void *resp) struct icp_qat_fw_la_resp *qat_resp = resp; struct qat_crypto_request *qat_req = (void *)(__force long)qat_resp->opaque_data; + struct qat_instance_backlog *backlog = qat_req->alg_req.backlog; qat_req->cb(qat_resp, qat_req); + + qat_alg_send_backlog(backlog); +} + +static int qat_alg_send_sym_message(struct qat_crypto_request *qat_req, + struct qat_crypto_instance *inst, + struct crypto_async_request *base) +{ + struct qat_alg_req *alg_req = &qat_req->alg_req; + + alg_req->fw_req = (u32 *)&qat_req->req; + alg_req->tx_ring = inst->sym_tx; + alg_req->base = base; + alg_req->backlog = &inst->backlog; + + return qat_alg_send_message(alg_req); } static int qat_alg_aead_dec(struct aead_request *areq) @@ -939,14 +973,15 @@ static int qat_alg_aead_dec(struct aead_request *areq) struct icp_qat_fw_la_auth_req_params *auth_param; struct icp_qat_fw_la_bulk_req *msg; int digst_size = crypto_aead_authsize(aead_tfm); - int ret, ctr = 0; + gfp_t f = qat_algs_alloc_flags(&areq->base); + int ret; u32 cipher_len; cipher_len = areq->cryptlen - digst_size; if (cipher_len % AES_BLOCK_SIZE != 0) return -EINVAL; - ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req); + ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req, f); if (unlikely(ret)) return ret; @@ -965,15 +1000,12 @@ static int qat_alg_aead_dec(struct aead_request *areq) auth_param = (void *)((u8 *)cipher_param + sizeof(*cipher_param)); auth_param->auth_off = 0; auth_param->auth_len = areq->assoclen + cipher_param->cipher_length; - do { - ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg); - } while (ret == -EAGAIN && ctr++ < 10); - if (ret == -EAGAIN) { + ret = qat_alg_send_sym_message(qat_req, ctx->inst, &areq->base); + if (ret == -ENOSPC) qat_alg_free_bufl(ctx->inst, qat_req); - return -EBUSY; - } - return -EINPROGRESS; + + return ret; } static int qat_alg_aead_enc(struct aead_request *areq) @@ -984,14 +1016,15 @@ static int qat_alg_aead_enc(struct aead_request *areq) struct qat_crypto_request *qat_req = aead_request_ctx(areq); struct icp_qat_fw_la_cipher_req_params *cipher_param; struct icp_qat_fw_la_auth_req_params *auth_param; + gfp_t f = qat_algs_alloc_flags(&areq->base); struct icp_qat_fw_la_bulk_req *msg; u8 *iv = areq->iv; - int ret, ctr = 0; + int ret; if (areq->cryptlen % AES_BLOCK_SIZE != 0) return -EINVAL; - ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req); + ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req, f); if (unlikely(ret)) return ret; @@ -1013,15 +1046,11 @@ static int qat_alg_aead_enc(struct aead_request *areq) auth_param->auth_off = 0; auth_param->auth_len = areq->assoclen + areq->cryptlen; - do { - ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg); - } while (ret == -EAGAIN && ctr++ < 10); - - if (ret == -EAGAIN) { + ret = qat_alg_send_sym_message(qat_req, ctx->inst, &areq->base); + if (ret == -ENOSPC) qat_alg_free_bufl(ctx->inst, qat_req); - return -EBUSY; - } - return -EINPROGRESS; + + return ret; } static int qat_alg_skcipher_rekey(struct qat_alg_skcipher_ctx *ctx, @@ -1042,7 +1071,7 @@ static int qat_alg_skcipher_newkey(struct qat_alg_skcipher_ctx *ctx, { struct qat_crypto_instance *inst = NULL; struct device *dev; - int node = get_current_node(); + int node = numa_node_id(); int ret; inst = qat_crypto_get_instance_node(node); @@ -1173,13 +1202,14 @@ static int qat_alg_skcipher_encrypt(struct skcipher_request *req) struct qat_alg_skcipher_ctx *ctx = crypto_tfm_ctx(tfm); struct qat_crypto_request *qat_req = skcipher_request_ctx(req); struct icp_qat_fw_la_cipher_req_params *cipher_param; + gfp_t f = qat_algs_alloc_flags(&req->base); struct icp_qat_fw_la_bulk_req *msg; - int ret, ctr = 0; + int ret; if (req->cryptlen == 0) return 0; - ret = qat_alg_sgl_to_bufl(ctx->inst, req->src, req->dst, qat_req); + ret = qat_alg_sgl_to_bufl(ctx->inst, req->src, req->dst, qat_req, f); if (unlikely(ret)) return ret; @@ -1198,15 +1228,11 @@ static int qat_alg_skcipher_encrypt(struct skcipher_request *req) qat_alg_set_req_iv(qat_req); - do { - ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg); - } while (ret == -EAGAIN && ctr++ < 10); - - if (ret == -EAGAIN) { + ret = qat_alg_send_sym_message(qat_req, ctx->inst, &req->base); + if (ret == -ENOSPC) qat_alg_free_bufl(ctx->inst, qat_req); - return -EBUSY; - } - return -EINPROGRESS; + + return ret; } static int qat_alg_skcipher_blk_encrypt(struct skcipher_request *req) @@ -1242,13 +1268,14 @@ static int qat_alg_skcipher_decrypt(struct skcipher_request *req) struct qat_alg_skcipher_ctx *ctx = crypto_tfm_ctx(tfm); struct qat_crypto_request *qat_req = skcipher_request_ctx(req); struct icp_qat_fw_la_cipher_req_params *cipher_param; + gfp_t f = qat_algs_alloc_flags(&req->base); struct icp_qat_fw_la_bulk_req *msg; - int ret, ctr = 0; + int ret; if (req->cryptlen == 0) return 0; - ret = qat_alg_sgl_to_bufl(ctx->inst, req->src, req->dst, qat_req); + ret = qat_alg_sgl_to_bufl(ctx->inst, req->src, req->dst, qat_req, f); if (unlikely(ret)) return ret; @@ -1268,15 +1295,11 @@ static int qat_alg_skcipher_decrypt(struct skcipher_request *req) qat_alg_set_req_iv(qat_req); qat_alg_update_iv(qat_req); - do { - ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg); - } while (ret == -EAGAIN && ctr++ < 10); - - if (ret == -EAGAIN) { + ret = qat_alg_send_sym_message(qat_req, ctx->inst, &req->base); + if (ret == -ENOSPC) qat_alg_free_bufl(ctx->inst, qat_req); - return -EBUSY; - } - return -EINPROGRESS; + + return ret; } static int qat_alg_skcipher_blk_decrypt(struct skcipher_request *req) diff --git a/drivers/crypto/qat/qat_common/qat_algs_send.c b/drivers/crypto/qat/qat_common/qat_algs_send.c new file mode 100644 index 000000000000..ff5b4347f783 --- /dev/null +++ b/drivers/crypto/qat/qat_common/qat_algs_send.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) +/* Copyright(c) 2022 Intel Corporation */ +#include "adf_transport.h" +#include "qat_algs_send.h" +#include "qat_crypto.h" + +#define ADF_MAX_RETRIES 20 + +static int qat_alg_send_message_retry(struct qat_alg_req *req) +{ + int ret = 0, ctr = 0; + + do { + ret = adf_send_message(req->tx_ring, req->fw_req); + } while (ret == -EAGAIN && ctr++ < ADF_MAX_RETRIES); + + if (ret == -EAGAIN) + return -ENOSPC; + + return -EINPROGRESS; +} + +void qat_alg_send_backlog(struct qat_instance_backlog *backlog) +{ + struct qat_alg_req *req, *tmp; + + spin_lock_bh(&backlog->lock); + list_for_each_entry_safe(req, tmp, &backlog->list, list) { + if (adf_send_message(req->tx_ring, req->fw_req)) { + /* The HW ring is full. Do nothing. + * qat_alg_send_backlog() will be invoked again by + * another callback. + */ + break; + } + list_del(&req->list); + req->base->complete(req->base, -EINPROGRESS); + } + spin_unlock_bh(&backlog->lock); +} + +static void qat_alg_backlog_req(struct qat_alg_req *req, + struct qat_instance_backlog *backlog) +{ + INIT_LIST_HEAD(&req->list); + + spin_lock_bh(&backlog->lock); + list_add_tail(&req->list, &backlog->list); + spin_unlock_bh(&backlog->lock); +} + +static int qat_alg_send_message_maybacklog(struct qat_alg_req *req) +{ + struct qat_instance_backlog *backlog = req->backlog; + struct adf_etr_ring_data *tx_ring = req->tx_ring; + u32 *fw_req = req->fw_req; + + /* If any request is already backlogged, then add to backlog list */ + if (!list_empty(&backlog->list)) + goto enqueue; + + /* If ring is nearly full, then add to backlog list */ + if (adf_ring_nearly_full(tx_ring)) + goto enqueue; + + /* If adding request to HW ring fails, then add to backlog list */ + if (adf_send_message(tx_ring, fw_req)) + goto enqueue; + + return -EINPROGRESS; + +enqueue: + qat_alg_backlog_req(req, backlog); + + return -EBUSY; +} + +int qat_alg_send_message(struct qat_alg_req *req) +{ + u32 flags = req->base->flags; + + if (flags & CRYPTO_TFM_REQ_MAY_BACKLOG) + return qat_alg_send_message_maybacklog(req); + else + return qat_alg_send_message_retry(req); +} diff --git a/drivers/crypto/qat/qat_common/qat_algs_send.h b/drivers/crypto/qat/qat_common/qat_algs_send.h new file mode 100644 index 000000000000..5ce9f4f69d8f --- /dev/null +++ b/drivers/crypto/qat/qat_common/qat_algs_send.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) */ +/* Copyright(c) 2022 Intel Corporation */ +#ifndef QAT_ALGS_SEND_H +#define QAT_ALGS_SEND_H + +#include "qat_crypto.h" + +int qat_alg_send_message(struct qat_alg_req *req); +void qat_alg_send_backlog(struct qat_instance_backlog *backlog); + +#endif diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c index b0b78445418b..94a26702aeae 100644 --- a/drivers/crypto/qat/qat_common/qat_asym_algs.c +++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c @@ -12,6 +12,7 @@ #include <crypto/scatterwalk.h> #include "icp_qat_fw_pke.h" #include "adf_accel_devices.h" +#include "qat_algs_send.h" #include "adf_transport.h" #include "adf_common_drv.h" #include "qat_crypto.h" @@ -135,8 +136,23 @@ struct qat_asym_request { } areq; int err; void (*cb)(struct icp_qat_fw_pke_resp *resp); + struct qat_alg_req alg_req; } __aligned(64); +static int qat_alg_send_asym_message(struct qat_asym_request *qat_req, + struct qat_crypto_instance *inst, + struct crypto_async_request *base) +{ + struct qat_alg_req *alg_req = &qat_req->alg_req; + + alg_req->fw_req = (u32 *)&qat_req->req; + alg_req->tx_ring = inst->pke_tx; + alg_req->base = base; + alg_req->backlog = &inst->backlog; + + return qat_alg_send_message(alg_req); +} + static void qat_dh_cb(struct icp_qat_fw_pke_resp *resp) { struct qat_asym_request *req = (void *)(__force long)resp->opaque; @@ -148,26 +164,21 @@ static void qat_dh_cb(struct icp_qat_fw_pke_resp *resp) err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL; if (areq->src) { - if (req->src_align) - dma_free_coherent(dev, req->ctx.dh->p_size, - req->src_align, req->in.dh.in.b); - else - dma_unmap_single(dev, req->in.dh.in.b, - req->ctx.dh->p_size, DMA_TO_DEVICE); + dma_unmap_single(dev, req->in.dh.in.b, req->ctx.dh->p_size, + DMA_TO_DEVICE); + kfree_sensitive(req->src_align); } areq->dst_len = req->ctx.dh->p_size; if (req->dst_align) { scatterwalk_map_and_copy(req->dst_align, areq->dst, 0, areq->dst_len, 1); - - dma_free_coherent(dev, req->ctx.dh->p_size, req->dst_align, - req->out.dh.r); - } else { - dma_unmap_single(dev, req->out.dh.r, req->ctx.dh->p_size, - DMA_FROM_DEVICE); + kfree_sensitive(req->dst_align); } + dma_unmap_single(dev, req->out.dh.r, req->ctx.dh->p_size, + DMA_FROM_DEVICE); + dma_unmap_single(dev, req->phy_in, sizeof(struct qat_dh_input_params), DMA_TO_DEVICE); dma_unmap_single(dev, req->phy_out, @@ -213,8 +224,10 @@ static int qat_dh_compute_value(struct kpp_request *req) struct qat_asym_request *qat_req = PTR_ALIGN(kpp_request_ctx(req), 64); struct icp_qat_fw_pke_request *msg = &qat_req->req; - int ret, ctr = 0; + gfp_t flags = qat_algs_alloc_flags(&req->base); int n_input_params = 0; + u8 *vaddr; + int ret; if (unlikely(!ctx->xa)) return -EINVAL; @@ -223,6 +236,10 @@ static int qat_dh_compute_value(struct kpp_request *req) req->dst_len = ctx->p_size; return -EOVERFLOW; } + + if (req->src_len > ctx->p_size) + return -EINVAL; + memset(msg, '\0', sizeof(*msg)); ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr, ICP_QAT_FW_COMN_REQ_FLAG_SET); @@ -271,27 +288,24 @@ static int qat_dh_compute_value(struct kpp_request *req) */ if (sg_is_last(req->src) && req->src_len == ctx->p_size) { qat_req->src_align = NULL; - qat_req->in.dh.in.b = dma_map_single(dev, - sg_virt(req->src), - req->src_len, - DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, - qat_req->in.dh.in.b))) - return ret; - + vaddr = sg_virt(req->src); } else { int shift = ctx->p_size - req->src_len; - qat_req->src_align = dma_alloc_coherent(dev, - ctx->p_size, - &qat_req->in.dh.in.b, - GFP_KERNEL); + qat_req->src_align = kzalloc(ctx->p_size, flags); if (unlikely(!qat_req->src_align)) return ret; scatterwalk_map_and_copy(qat_req->src_align + shift, req->src, 0, req->src_len, 0); + + vaddr = qat_req->src_align; } + + qat_req->in.dh.in.b = dma_map_single(dev, vaddr, ctx->p_size, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, qat_req->in.dh.in.b))) + goto unmap_src; } /* * dst can be of any size in valid range, but HW expects it to be the @@ -302,32 +316,30 @@ static int qat_dh_compute_value(struct kpp_request *req) */ if (sg_is_last(req->dst) && req->dst_len == ctx->p_size) { qat_req->dst_align = NULL; - qat_req->out.dh.r = dma_map_single(dev, sg_virt(req->dst), - req->dst_len, - DMA_FROM_DEVICE); - - if (unlikely(dma_mapping_error(dev, qat_req->out.dh.r))) - goto unmap_src; - + vaddr = sg_virt(req->dst); } else { - qat_req->dst_align = dma_alloc_coherent(dev, ctx->p_size, - &qat_req->out.dh.r, - GFP_KERNEL); + qat_req->dst_align = kzalloc(ctx->p_size, flags); if (unlikely(!qat_req->dst_align)) goto unmap_src; + + vaddr = qat_req->dst_align; } + qat_req->out.dh.r = dma_map_single(dev, vaddr, ctx->p_size, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, qat_req->out.dh.r))) + goto unmap_dst; qat_req->in.dh.in_tab[n_input_params] = 0; qat_req->out.dh.out_tab[1] = 0; /* Mapping in.in.b or in.in_g2.xa is the same */ - qat_req->phy_in = dma_map_single(dev, &qat_req->in.dh.in.b, - sizeof(qat_req->in.dh.in.b), + qat_req->phy_in = dma_map_single(dev, &qat_req->in.dh, + sizeof(struct qat_dh_input_params), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, qat_req->phy_in))) goto unmap_dst; - qat_req->phy_out = dma_map_single(dev, &qat_req->out.dh.r, - sizeof(qat_req->out.dh.r), + qat_req->phy_out = dma_map_single(dev, &qat_req->out.dh, + sizeof(struct qat_dh_output_params), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, qat_req->phy_out))) goto unmap_in_params; @@ -338,13 +350,13 @@ static int qat_dh_compute_value(struct kpp_request *req) msg->input_param_count = n_input_params; msg->output_param_count = 1; - do { - ret = adf_send_message(ctx->inst->pke_tx, (u32 *)msg); - } while (ret == -EBUSY && ctr++ < 100); + ret = qat_alg_send_asym_message(qat_req, inst, &req->base); + if (ret == -ENOSPC) + goto unmap_all; - if (!ret) - return -EINPROGRESS; + return ret; +unmap_all: if (!dma_mapping_error(dev, qat_req->phy_out)) dma_unmap_single(dev, qat_req->phy_out, sizeof(struct qat_dh_output_params), @@ -355,23 +367,17 @@ unmap_in_params: sizeof(struct qat_dh_input_params), DMA_TO_DEVICE); unmap_dst: - if (qat_req->dst_align) - dma_free_coherent(dev, ctx->p_size, qat_req->dst_align, - qat_req->out.dh.r); - else - if (!dma_mapping_error(dev, qat_req->out.dh.r)) - dma_unmap_single(dev, qat_req->out.dh.r, ctx->p_size, - DMA_FROM_DEVICE); + if (!dma_mapping_error(dev, qat_req->out.dh.r)) + dma_unmap_single(dev, qat_req->out.dh.r, ctx->p_size, + DMA_FROM_DEVICE); + kfree_sensitive(qat_req->dst_align); unmap_src: if (req->src) { - if (qat_req->src_align) - dma_free_coherent(dev, ctx->p_size, qat_req->src_align, - qat_req->in.dh.in.b); - else - if (!dma_mapping_error(dev, qat_req->in.dh.in.b)) - dma_unmap_single(dev, qat_req->in.dh.in.b, - ctx->p_size, - DMA_TO_DEVICE); + if (!dma_mapping_error(dev, qat_req->in.dh.in.b)) + dma_unmap_single(dev, qat_req->in.dh.in.b, + ctx->p_size, + DMA_TO_DEVICE); + kfree_sensitive(qat_req->src_align); } return ret; } @@ -420,14 +426,17 @@ static int qat_dh_set_params(struct qat_dh_ctx *ctx, struct dh *params) static void qat_dh_clear_ctx(struct device *dev, struct qat_dh_ctx *ctx) { if (ctx->g) { + memset(ctx->g, 0, ctx->p_size); dma_free_coherent(dev, ctx->p_size, ctx->g, ctx->dma_g); ctx->g = NULL; } if (ctx->xa) { + memset(ctx->xa, 0, ctx->p_size); dma_free_coherent(dev, ctx->p_size, ctx->xa, ctx->dma_xa); ctx->xa = NULL; } if (ctx->p) { + memset(ctx->p, 0, ctx->p_size); dma_free_coherent(dev, ctx->p_size, ctx->p, ctx->dma_p); ctx->p = NULL; } @@ -480,7 +489,7 @@ static int qat_dh_init_tfm(struct crypto_kpp *tfm) { struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm); struct qat_crypto_instance *inst = - qat_crypto_get_instance_node(get_current_node()); + qat_crypto_get_instance_node(numa_node_id()); if (!inst) return -EINVAL; @@ -510,25 +519,22 @@ static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp) err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL; - if (req->src_align) - dma_free_coherent(dev, req->ctx.rsa->key_sz, req->src_align, - req->in.rsa.enc.m); - else - dma_unmap_single(dev, req->in.rsa.enc.m, req->ctx.rsa->key_sz, - DMA_TO_DEVICE); + kfree_sensitive(req->src_align); + + dma_unmap_single(dev, req->in.rsa.enc.m, req->ctx.rsa->key_sz, + DMA_TO_DEVICE); areq->dst_len = req->ctx.rsa->key_sz; if (req->dst_align) { scatterwalk_map_and_copy(req->dst_align, areq->dst, 0, areq->dst_len, 1); - dma_free_coherent(dev, req->ctx.rsa->key_sz, req->dst_align, - req->out.rsa.enc.c); - } else { - dma_unmap_single(dev, req->out.rsa.enc.c, req->ctx.rsa->key_sz, - DMA_FROM_DEVICE); + kfree_sensitive(req->dst_align); } + dma_unmap_single(dev, req->out.rsa.enc.c, req->ctx.rsa->key_sz, + DMA_FROM_DEVICE); + dma_unmap_single(dev, req->phy_in, sizeof(struct qat_rsa_input_params), DMA_TO_DEVICE); dma_unmap_single(dev, req->phy_out, @@ -542,8 +548,11 @@ void qat_alg_asym_callback(void *_resp) { struct icp_qat_fw_pke_resp *resp = _resp; struct qat_asym_request *areq = (void *)(__force long)resp->opaque; + struct qat_instance_backlog *backlog = areq->alg_req.backlog; areq->cb(resp); + + qat_alg_send_backlog(backlog); } #define PKE_RSA_EP_512 0x1c161b21 @@ -642,7 +651,9 @@ static int qat_rsa_enc(struct akcipher_request *req) struct qat_asym_request *qat_req = PTR_ALIGN(akcipher_request_ctx(req), 64); struct icp_qat_fw_pke_request *msg = &qat_req->req; - int ret, ctr = 0; + gfp_t flags = qat_algs_alloc_flags(&req->base); + u8 *vaddr; + int ret; if (unlikely(!ctx->n || !ctx->e)) return -EINVAL; @@ -651,6 +662,10 @@ static int qat_rsa_enc(struct akcipher_request *req) req->dst_len = ctx->key_sz; return -EOVERFLOW; } + + if (req->src_len > ctx->key_sz) + return -EINVAL; + memset(msg, '\0', sizeof(*msg)); ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr, ICP_QAT_FW_COMN_REQ_FLAG_SET); @@ -679,50 +694,49 @@ static int qat_rsa_enc(struct akcipher_request *req) */ if (sg_is_last(req->src) && req->src_len == ctx->key_sz) { qat_req->src_align = NULL; - qat_req->in.rsa.enc.m = dma_map_single(dev, sg_virt(req->src), - req->src_len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.enc.m))) - return ret; - + vaddr = sg_virt(req->src); } else { int shift = ctx->key_sz - req->src_len; - qat_req->src_align = dma_alloc_coherent(dev, ctx->key_sz, - &qat_req->in.rsa.enc.m, - GFP_KERNEL); + qat_req->src_align = kzalloc(ctx->key_sz, flags); if (unlikely(!qat_req->src_align)) return ret; scatterwalk_map_and_copy(qat_req->src_align + shift, req->src, 0, req->src_len, 0); + vaddr = qat_req->src_align; } - if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) { - qat_req->dst_align = NULL; - qat_req->out.rsa.enc.c = dma_map_single(dev, sg_virt(req->dst), - req->dst_len, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.enc.c))) - goto unmap_src; + qat_req->in.rsa.enc.m = dma_map_single(dev, vaddr, ctx->key_sz, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.enc.m))) + goto unmap_src; + if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) { + qat_req->dst_align = NULL; + vaddr = sg_virt(req->dst); } else { - qat_req->dst_align = dma_alloc_coherent(dev, ctx->key_sz, - &qat_req->out.rsa.enc.c, - GFP_KERNEL); + qat_req->dst_align = kzalloc(ctx->key_sz, flags); if (unlikely(!qat_req->dst_align)) goto unmap_src; - + vaddr = qat_req->dst_align; } + + qat_req->out.rsa.enc.c = dma_map_single(dev, vaddr, ctx->key_sz, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.enc.c))) + goto unmap_dst; + qat_req->in.rsa.in_tab[3] = 0; qat_req->out.rsa.out_tab[1] = 0; - qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.enc.m, - sizeof(qat_req->in.rsa.enc.m), + qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa, + sizeof(struct qat_rsa_input_params), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, qat_req->phy_in))) goto unmap_dst; - qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.enc.c, - sizeof(qat_req->out.rsa.enc.c), + qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa, + sizeof(struct qat_rsa_output_params), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, qat_req->phy_out))) goto unmap_in_params; @@ -732,13 +746,14 @@ static int qat_rsa_enc(struct akcipher_request *req) msg->pke_mid.opaque = (u64)(__force long)qat_req; msg->input_param_count = 3; msg->output_param_count = 1; - do { - ret = adf_send_message(ctx->inst->pke_tx, (u32 *)msg); - } while (ret == -EBUSY && ctr++ < 100); - if (!ret) - return -EINPROGRESS; + ret = qat_alg_send_asym_message(qat_req, inst, &req->base); + if (ret == -ENOSPC) + goto unmap_all; + return ret; + +unmap_all: if (!dma_mapping_error(dev, qat_req->phy_out)) dma_unmap_single(dev, qat_req->phy_out, sizeof(struct qat_rsa_output_params), @@ -749,21 +764,15 @@ unmap_in_params: sizeof(struct qat_rsa_input_params), DMA_TO_DEVICE); unmap_dst: - if (qat_req->dst_align) - dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align, - qat_req->out.rsa.enc.c); - else - if (!dma_mapping_error(dev, qat_req->out.rsa.enc.c)) - dma_unmap_single(dev, qat_req->out.rsa.enc.c, - ctx->key_sz, DMA_FROM_DEVICE); + if (!dma_mapping_error(dev, qat_req->out.rsa.enc.c)) + dma_unmap_single(dev, qat_req->out.rsa.enc.c, + ctx->key_sz, DMA_FROM_DEVICE); + kfree_sensitive(qat_req->dst_align); unmap_src: - if (qat_req->src_align) - dma_free_coherent(dev, ctx->key_sz, qat_req->src_align, - qat_req->in.rsa.enc.m); - else - if (!dma_mapping_error(dev, qat_req->in.rsa.enc.m)) - dma_unmap_single(dev, qat_req->in.rsa.enc.m, - ctx->key_sz, DMA_TO_DEVICE); + if (!dma_mapping_error(dev, qat_req->in.rsa.enc.m)) + dma_unmap_single(dev, qat_req->in.rsa.enc.m, ctx->key_sz, + DMA_TO_DEVICE); + kfree_sensitive(qat_req->src_align); return ret; } @@ -776,7 +785,9 @@ static int qat_rsa_dec(struct akcipher_request *req) struct qat_asym_request *qat_req = PTR_ALIGN(akcipher_request_ctx(req), 64); struct icp_qat_fw_pke_request *msg = &qat_req->req; - int ret, ctr = 0; + gfp_t flags = qat_algs_alloc_flags(&req->base); + u8 *vaddr; + int ret; if (unlikely(!ctx->n || !ctx->d)) return -EINVAL; @@ -785,6 +796,10 @@ static int qat_rsa_dec(struct akcipher_request *req) req->dst_len = ctx->key_sz; return -EOVERFLOW; } + + if (req->src_len > ctx->key_sz) + return -EINVAL; + memset(msg, '\0', sizeof(*msg)); ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr, ICP_QAT_FW_COMN_REQ_FLAG_SET); @@ -823,54 +838,51 @@ static int qat_rsa_dec(struct akcipher_request *req) */ if (sg_is_last(req->src) && req->src_len == ctx->key_sz) { qat_req->src_align = NULL; - qat_req->in.rsa.dec.c = dma_map_single(dev, sg_virt(req->src), - req->dst_len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.dec.c))) - return ret; - + vaddr = sg_virt(req->src); } else { int shift = ctx->key_sz - req->src_len; - qat_req->src_align = dma_alloc_coherent(dev, ctx->key_sz, - &qat_req->in.rsa.dec.c, - GFP_KERNEL); + qat_req->src_align = kzalloc(ctx->key_sz, flags); if (unlikely(!qat_req->src_align)) return ret; scatterwalk_map_and_copy(qat_req->src_align + shift, req->src, 0, req->src_len, 0); + vaddr = qat_req->src_align; } - if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) { - qat_req->dst_align = NULL; - qat_req->out.rsa.dec.m = dma_map_single(dev, sg_virt(req->dst), - req->dst_len, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.dec.m))) - goto unmap_src; + qat_req->in.rsa.dec.c = dma_map_single(dev, vaddr, ctx->key_sz, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.dec.c))) + goto unmap_src; + if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) { + qat_req->dst_align = NULL; + vaddr = sg_virt(req->dst); } else { - qat_req->dst_align = dma_alloc_coherent(dev, ctx->key_sz, - &qat_req->out.rsa.dec.m, - GFP_KERNEL); + qat_req->dst_align = kzalloc(ctx->key_sz, flags); if (unlikely(!qat_req->dst_align)) goto unmap_src; - + vaddr = qat_req->dst_align; } + qat_req->out.rsa.dec.m = dma_map_single(dev, vaddr, ctx->key_sz, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.dec.m))) + goto unmap_dst; if (ctx->crt_mode) qat_req->in.rsa.in_tab[6] = 0; else qat_req->in.rsa.in_tab[3] = 0; qat_req->out.rsa.out_tab[1] = 0; - qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.dec.c, - sizeof(qat_req->in.rsa.dec.c), + qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa, + sizeof(struct qat_rsa_input_params), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, qat_req->phy_in))) goto unmap_dst; - qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.dec.m, - sizeof(qat_req->out.rsa.dec.m), + qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa, + sizeof(struct qat_rsa_output_params), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, qat_req->phy_out))) goto unmap_in_params; @@ -884,13 +896,14 @@ static int qat_rsa_dec(struct akcipher_request *req) msg->input_param_count = 3; msg->output_param_count = 1; - do { - ret = adf_send_message(ctx->inst->pke_tx, (u32 *)msg); - } while (ret == -EBUSY && ctr++ < 100); - if (!ret) - return -EINPROGRESS; + ret = qat_alg_send_asym_message(qat_req, inst, &req->base); + if (ret == -ENOSPC) + goto unmap_all; + + return ret; +unmap_all: if (!dma_mapping_error(dev, qat_req->phy_out)) dma_unmap_single(dev, qat_req->phy_out, sizeof(struct qat_rsa_output_params), @@ -901,21 +914,15 @@ unmap_in_params: sizeof(struct qat_rsa_input_params), DMA_TO_DEVICE); unmap_dst: - if (qat_req->dst_align) - dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align, - qat_req->out.rsa.dec.m); - else - if (!dma_mapping_error(dev, qat_req->out.rsa.dec.m)) - dma_unmap_single(dev, qat_req->out.rsa.dec.m, - ctx->key_sz, DMA_FROM_DEVICE); + if (!dma_mapping_error(dev, qat_req->out.rsa.dec.m)) + dma_unmap_single(dev, qat_req->out.rsa.dec.m, + ctx->key_sz, DMA_FROM_DEVICE); + kfree_sensitive(qat_req->dst_align); unmap_src: - if (qat_req->src_align) - dma_free_coherent(dev, ctx->key_sz, qat_req->src_align, - qat_req->in.rsa.dec.c); - else - if (!dma_mapping_error(dev, qat_req->in.rsa.dec.c)) - dma_unmap_single(dev, qat_req->in.rsa.dec.c, - ctx->key_sz, DMA_TO_DEVICE); + if (!dma_mapping_error(dev, qat_req->in.rsa.dec.c)) + dma_unmap_single(dev, qat_req->in.rsa.dec.c, ctx->key_sz, + DMA_TO_DEVICE); + kfree_sensitive(qat_req->src_align); return ret; } @@ -1218,7 +1225,7 @@ static int qat_rsa_init_tfm(struct crypto_akcipher *tfm) { struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); struct qat_crypto_instance *inst = - qat_crypto_get_instance_node(get_current_node()); + qat_crypto_get_instance_node(numa_node_id()); if (!inst) return -EINVAL; @@ -1233,18 +1240,8 @@ static void qat_rsa_exit_tfm(struct crypto_akcipher *tfm) struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); struct device *dev = &GET_DEV(ctx->inst->accel_dev); - if (ctx->n) - dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n); - if (ctx->e) - dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e); - if (ctx->d) { - memset(ctx->d, '\0', ctx->key_sz); - dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d); - } + qat_rsa_clear_ctx(dev, ctx); qat_crypto_put_instance(ctx->inst); - ctx->n = NULL; - ctx->e = NULL; - ctx->d = NULL; } static struct akcipher_alg rsa = { diff --git a/drivers/crypto/qat/qat_common/qat_crypto.c b/drivers/crypto/qat/qat_common/qat_crypto.c index 7234c4940fae..9341d892533a 100644 --- a/drivers/crypto/qat/qat_common/qat_crypto.c +++ b/drivers/crypto/qat/qat_common/qat_crypto.c @@ -346,6 +346,9 @@ static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev) &inst->pke_rx); if (ret) goto err; + + INIT_LIST_HEAD(&inst->backlog.list); + spin_lock_init(&inst->backlog.lock); } return 0; err: diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/qat/qat_common/qat_crypto.h index b6a4c95ae003..df3c738ce323 100644 --- a/drivers/crypto/qat/qat_common/qat_crypto.h +++ b/drivers/crypto/qat/qat_common/qat_crypto.h @@ -9,6 +9,19 @@ #include "adf_accel_devices.h" #include "icp_qat_fw_la.h" +struct qat_instance_backlog { + struct list_head list; + spinlock_t lock; /* protects backlog list */ +}; + +struct qat_alg_req { + u32 *fw_req; + struct adf_etr_ring_data *tx_ring; + struct crypto_async_request *base; + struct list_head list; + struct qat_instance_backlog *backlog; +}; + struct qat_crypto_instance { struct adf_etr_ring_data *sym_tx; struct adf_etr_ring_data *sym_rx; @@ -19,8 +32,29 @@ struct qat_crypto_instance { unsigned long state; int id; atomic_t refctr; + struct qat_instance_backlog backlog; }; +#define QAT_MAX_BUFF_DESC 4 + +struct qat_alg_buf { + u32 len; + u32 resrvd; + u64 addr; +} __packed; + +struct qat_alg_buf_list { + u64 resrvd; + u32 num_bufs; + u32 num_mapped_bufs; + struct qat_alg_buf bufers[]; +} __packed; + +struct qat_alg_fixed_buf_list { + struct qat_alg_buf_list sgl_hdr; + struct qat_alg_buf descriptors[QAT_MAX_BUFF_DESC]; +} __packed __aligned(64); + struct qat_crypto_request_buffs { struct qat_alg_buf_list *bl; dma_addr_t blp; @@ -28,6 +62,10 @@ struct qat_crypto_request_buffs { dma_addr_t bloutp; size_t sz; size_t sz_out; + bool sgl_src_valid; + bool sgl_dst_valid; + struct qat_alg_fixed_buf_list sgl_src; + struct qat_alg_fixed_buf_list sgl_dst; }; struct qat_crypto_request; @@ -53,6 +91,7 @@ struct qat_crypto_request { u8 iv[AES_BLOCK_SIZE]; }; bool encryption; + struct qat_alg_req alg_req; }; static inline bool adf_hw_dev_has_crypto(struct adf_accel_dev *accel_dev) @@ -70,4 +109,9 @@ static inline bool adf_hw_dev_has_crypto(struct adf_accel_dev *accel_dev) return true; } +static inline gfp_t qat_algs_alloc_flags(struct crypto_async_request *req) +{ + return req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC; +} + #endif diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c index 4bfd8f3566f7..7bba35280dac 100644 --- a/drivers/crypto/qat/qat_common/qat_hal.c +++ b/drivers/crypto/qat/qat_common/qat_hal.c @@ -695,6 +695,7 @@ static int qat_hal_chip_init(struct icp_qat_fw_loader_handle *handle, handle->pci_dev = pci_info->pci_dev; switch (handle->pci_dev->device) { case ADF_4XXX_PCI_DEVICE_ID: + case ADF_401XX_PCI_DEVICE_ID: handle->chip_info->mmp_sram_size = 0; handle->chip_info->nn = false; handle->chip_info->lm2lm3 = true; diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c index 2026cc6be8f0..b7f7869ef8b2 100644 --- a/drivers/crypto/qat/qat_common/qat_uclo.c +++ b/drivers/crypto/qat/qat_common/qat_uclo.c @@ -387,7 +387,9 @@ static int qat_uclo_init_ustore(struct icp_qat_fw_loader_handle *handle, page = image->page; for_each_set_bit(ae, &ae_mask, handle->hal_handle->ae_max_num) { - if (!test_bit(ae, (unsigned long *)&uof_image->ae_assigned)) + unsigned long ae_assigned = uof_image->ae_assigned; + + if (!test_bit(ae, &ae_assigned)) continue; if (!test_bit(ae, &cfg_ae_mask)) @@ -517,7 +519,7 @@ qat_uclo_map_chunk(char *buf, struct icp_qat_uof_filehdr *file_hdr, return NULL; } -static unsigned int +static int qat_uclo_check_image_compat(struct icp_qat_uof_encap_obj *encap_uof_obj, struct icp_qat_uof_image *image) { @@ -664,8 +666,9 @@ static int qat_uclo_map_ae(struct icp_qat_fw_loader_handle *handle, int max_ae) continue; for (i = 0; i < obj_handle->uimage_num; i++) { - if (!test_bit(ae, (unsigned long *) - &obj_handle->ae_uimage[i].img_ptr->ae_assigned)) + unsigned long ae_assigned = obj_handle->ae_uimage[i].img_ptr->ae_assigned; + + if (!test_bit(ae, &ae_assigned)) continue; mflag = 1; if (qat_uclo_init_ae_data(obj_handle, ae, i)) @@ -728,6 +731,7 @@ qat_uclo_get_dev_type(struct icp_qat_fw_loader_handle *handle) case PCI_DEVICE_ID_INTEL_QAT_C3XXX: return ICP_QAT_AC_C3XXX_DEV_TYPE; case ADF_4XXX_PCI_DEVICE_ID: + case ADF_401XX_PCI_DEVICE_ID: return ICP_QAT_AC_4XXX_A_DEV_TYPE; default: pr_err("QAT: unsupported device 0x%x\n", @@ -1363,6 +1367,48 @@ static void qat_uclo_ummap_auth_fw(struct icp_qat_fw_loader_handle *handle, } } +static int qat_uclo_check_image(struct icp_qat_fw_loader_handle *handle, + char *image, unsigned int size, + unsigned int fw_type) +{ + char *fw_type_name = fw_type ? "MMP" : "AE"; + unsigned int css_dword_size = sizeof(u32); + + if (handle->chip_info->fw_auth) { + struct icp_qat_css_hdr *css_hdr = (struct icp_qat_css_hdr *)image; + unsigned int header_len = ICP_QAT_AE_IMG_OFFSET(handle); + + if ((css_hdr->header_len * css_dword_size) != header_len) + goto err; + if ((css_hdr->size * css_dword_size) != size) + goto err; + if (fw_type != css_hdr->fw_type) + goto err; + if (size <= header_len) + goto err; + size -= header_len; + } + + if (fw_type == CSS_AE_FIRMWARE) { + if (size < sizeof(struct icp_qat_simg_ae_mode *) + + ICP_QAT_SIMG_AE_INIT_SEQ_LEN) + goto err; + if (size > ICP_QAT_CSS_RSA4K_MAX_IMAGE_LEN) + goto err; + } else if (fw_type == CSS_MMP_FIRMWARE) { + if (size > ICP_QAT_CSS_RSA3K_MAX_IMAGE_LEN) + goto err; + } else { + pr_err("QAT: Unsupported firmware type\n"); + return -EINVAL; + } + return 0; + +err: + pr_err("QAT: Invalid %s firmware image\n", fw_type_name); + return -EINVAL; +} + static int qat_uclo_map_auth_fw(struct icp_qat_fw_loader_handle *handle, char *image, unsigned int size, struct icp_qat_fw_auth_desc **desc) @@ -1375,7 +1421,7 @@ static int qat_uclo_map_auth_fw(struct icp_qat_fw_loader_handle *handle, struct icp_qat_simg_ae_mode *simg_ae_mode; struct icp_firml_dram_desc img_desc; - if (size > (ICP_QAT_AE_IMG_OFFSET(handle) + ICP_QAT_CSS_MAX_IMAGE_LEN)) { + if (size > (ICP_QAT_AE_IMG_OFFSET(handle) + ICP_QAT_CSS_RSA4K_MAX_IMAGE_LEN)) { pr_err("QAT: error, input image size overflow %d\n", size); return -EINVAL; } @@ -1543,6 +1589,11 @@ int qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle, { struct icp_qat_fw_auth_desc *desc = NULL; int status = 0; + int ret; + + ret = qat_uclo_check_image(handle, addr_ptr, mem_size, CSS_MMP_FIRMWARE); + if (ret) + return ret; if (handle->chip_info->fw_auth) { status = qat_uclo_map_auth_fw(handle, addr_ptr, mem_size, &desc); @@ -2014,8 +2065,15 @@ static int qat_uclo_wr_suof_img(struct icp_qat_fw_loader_handle *handle) struct icp_qat_fw_auth_desc *desc = NULL; struct icp_qat_suof_handle *sobj_handle = handle->sobj_handle; struct icp_qat_suof_img_hdr *simg_hdr = sobj_handle->img_table.simg_hdr; + int ret; for (i = 0; i < sobj_handle->img_table.num_simgs; i++) { + ret = qat_uclo_check_image(handle, simg_hdr[i].simg_buf, + simg_hdr[i].simg_len, + CSS_AE_FIRMWARE); + if (ret) + return ret; + if (qat_uclo_map_auth_fw(handle, (char *)simg_hdr[i].simg_buf, (unsigned int) diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c index 09599fe4d2f3..cb3bdd3618fb 100644 --- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c +++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c @@ -7,6 +7,8 @@ #include "adf_dh895xcc_hw_data.h" #include "icp_qat_hw.h" +#define ADF_DH895XCC_VF_MSK 0xFFFFFFFF + /* Worker thread to service arbiter mappings */ static const u32 thrd_to_arb_map[ADF_DH895XCC_MAX_ACCELENGINES] = { 0x12222AAA, 0x11666666, 0x12222AAA, 0x11666666, @@ -58,17 +60,24 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev) capabilities = ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC | ICP_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC | - ICP_ACCEL_CAPABILITIES_AUTHENTICATION; + ICP_ACCEL_CAPABILITIES_AUTHENTICATION | + ICP_ACCEL_CAPABILITIES_CIPHER | + ICP_ACCEL_CAPABILITIES_COMPRESSION; /* Read accelerator capabilities mask */ pci_read_config_dword(pdev, ADF_DEVICE_LEGFUSE_OFFSET, &legfuses); - if (legfuses & ICP_ACCEL_MASK_CIPHER_SLICE) + /* A set bit in legfuses means the feature is OFF in this SKU */ + if (legfuses & ICP_ACCEL_MASK_CIPHER_SLICE) { capabilities &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC; + capabilities &= ~ICP_ACCEL_CAPABILITIES_CIPHER; + } if (legfuses & ICP_ACCEL_MASK_PKE_SLICE) capabilities &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC; - if (legfuses & ICP_ACCEL_MASK_AUTH_SLICE) + if (legfuses & ICP_ACCEL_MASK_AUTH_SLICE) { capabilities &= ~ICP_ACCEL_CAPABILITIES_AUTHENTICATION; + capabilities &= ~ICP_ACCEL_CAPABILITIES_CIPHER; + } if (legfuses & ICP_ACCEL_MASK_COMPRESS_SLICE) capabilities &= ~ICP_ACCEL_CAPABILITIES_COMPRESSION; @@ -100,43 +109,6 @@ static const u32 *adf_get_arbiter_mapping(void) return thrd_to_arb_map; } -static void adf_enable_ints(struct adf_accel_dev *accel_dev) -{ - void __iomem *addr; - - addr = (&GET_BARS(accel_dev)[ADF_DH895XCC_PMISC_BAR])->virt_addr; - - /* Enable bundle and misc interrupts */ - ADF_CSR_WR(addr, ADF_DH895XCC_SMIAPF0_MASK_OFFSET, - accel_dev->pf.vf_info ? 0 : - BIT_ULL(GET_MAX_BANKS(accel_dev)) - 1); - ADF_CSR_WR(addr, ADF_DH895XCC_SMIAPF1_MASK_OFFSET, - ADF_DH895XCC_SMIA1_MASK); -} - -static u32 get_vf2pf_sources(void __iomem *pmisc_bar) -{ - u32 errsou3, errmsk3, errsou5, errmsk5, vf_int_mask; - - /* Get the interrupt sources triggered by VFs */ - errsou3 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRSOU3); - vf_int_mask = ADF_DH895XCC_ERR_REG_VF2PF_L(errsou3); - - /* To avoid adding duplicate entries to work queue, clear - * vf_int_mask_sets bits that are already masked in ERRMSK register. - */ - errmsk3 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRMSK3); - vf_int_mask &= ~ADF_DH895XCC_ERR_REG_VF2PF_L(errmsk3); - - /* Do the same for ERRSOU5 */ - errsou5 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRSOU5); - errmsk5 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRMSK5); - vf_int_mask |= ADF_DH895XCC_ERR_REG_VF2PF_U(errsou5); - vf_int_mask &= ~ADF_DH895XCC_ERR_REG_VF2PF_U(errmsk5); - - return vf_int_mask; -} - static void enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) { /* Enable VF2PF Messaging Ints - VFs 0 through 15 per vf_mask[15:0] */ @@ -150,27 +122,71 @@ static void enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) if (vf_mask >> 16) { u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK5) & ~ADF_DH895XCC_ERR_MSK_VF2PF_U(vf_mask); - ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, val); } } -static void disable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) +static void disable_all_vf2pf_interrupts(void __iomem *pmisc_addr) { + u32 val; + /* Disable VF2PF interrupts for VFs 0 through 15 per vf_mask[15:0] */ - if (vf_mask & 0xFFFF) { - u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3) - | ADF_DH895XCC_ERR_MSK_VF2PF_L(vf_mask); - ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, val); - } + val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3) + | ADF_DH895XCC_ERR_MSK_VF2PF_L(ADF_DH895XCC_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, val); /* Disable VF2PF interrupts for VFs 16 through 31 per vf_mask[31:16] */ - if (vf_mask >> 16) { - u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK5) - | ADF_DH895XCC_ERR_MSK_VF2PF_U(vf_mask); + val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK5) + | ADF_DH895XCC_ERR_MSK_VF2PF_U(ADF_DH895XCC_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, val); +} - ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, val); - } +static u32 disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) +{ + u32 sources, pending, disabled; + u32 errsou3, errmsk3; + u32 errsou5, errmsk5; + + /* Get the interrupt sources triggered by VFs */ + errsou3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU3); + errsou5 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU5); + sources = ADF_DH895XCC_ERR_REG_VF2PF_L(errsou3) + | ADF_DH895XCC_ERR_REG_VF2PF_U(errsou5); + + if (!sources) + return 0; + + /* Get the already disabled interrupts */ + errmsk3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3); + errmsk5 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK5); + disabled = ADF_DH895XCC_ERR_REG_VF2PF_L(errmsk3) + | ADF_DH895XCC_ERR_REG_VF2PF_U(errmsk5); + + pending = sources & ~disabled; + if (!pending) + return 0; + + /* Due to HW limitations, when disabling the interrupts, we can't + * just disable the requested sources, as this would lead to missed + * interrupts if sources changes just before writing to ERRMSK3 and + * ERRMSK5. + * To work around it, disable all and re-enable only the sources that + * are not in vf_mask and were not already disabled. Re-enabling will + * trigger a new interrupt for the sources that have changed in the + * meantime, if any. + */ + errmsk3 |= ADF_DH895XCC_ERR_MSK_VF2PF_L(ADF_DH895XCC_VF_MSK); + errmsk5 |= ADF_DH895XCC_ERR_MSK_VF2PF_U(ADF_DH895XCC_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); + + errmsk3 &= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled); + errmsk5 &= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); + + /* Return the sources of the (new) interrupt(s) */ + return pending; } static void configure_iov_threads(struct adf_accel_dev *accel_dev, bool enable) @@ -215,14 +231,14 @@ void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data) hw_data->init_arb = adf_init_arb; hw_data->exit_arb = adf_exit_arb; hw_data->get_arb_mapping = adf_get_arbiter_mapping; - hw_data->enable_ints = adf_enable_ints; + hw_data->enable_ints = adf_gen2_enable_ints; hw_data->reset_device = adf_reset_sbr; hw_data->disable_iov = adf_disable_sriov; adf_gen2_init_pf_pfvf_ops(&hw_data->pfvf_ops); - hw_data->pfvf_ops.get_vf2pf_sources = get_vf2pf_sources; hw_data->pfvf_ops.enable_vf2pf_interrupts = enable_vf2pf_interrupts; - hw_data->pfvf_ops.disable_vf2pf_interrupts = disable_vf2pf_interrupts; + hw_data->pfvf_ops.disable_all_vf2pf_interrupts = disable_all_vf2pf_interrupts; + hw_data->pfvf_ops.disable_pending_vf2pf_interrupts = disable_pending_vf2pf_interrupts; adf_gen2_init_hw_csr_ops(&hw_data->csr_ops); } diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h index aa17272a1507..7b674bbe4192 100644 --- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h +++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h @@ -19,10 +19,6 @@ #define ADF_DH895XCC_ACCELERATORS_MASK 0x3F #define ADF_DH895XCC_ACCELENGINES_MASK 0xFFF #define ADF_DH895XCC_ETR_MAX_BANKS 32 -#define ADF_DH895XCC_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28) -#define ADF_DH895XCC_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30) -#define ADF_DH895XCC_SMIA0_MASK 0xFFFFFFFF -#define ADF_DH895XCC_SMIA1_MASK 0x1 /* Masks for VF2PF interrupts */ #define ADF_DH895XCC_ERR_REG_VF2PF_L(vf_src) (((vf_src) & 0x01FFFE00) >> 9) diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c index 97a530171f07..6eb4d2e35629 100644 --- a/drivers/crypto/qce/aead.c +++ b/drivers/crypto/qce/aead.c @@ -450,8 +450,8 @@ qce_aead_async_req_handle(struct crypto_async_request *async_req) if (ret) return ret; dst_nents = dma_map_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst); - if (dst_nents < 0) { - ret = dst_nents; + if (!dst_nents) { + ret = -EIO; goto error_free; } diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c index 59159f5e64e5..37bafd7aeb79 100644 --- a/drivers/crypto/qce/sha.c +++ b/drivers/crypto/qce/sha.c @@ -97,14 +97,16 @@ static int qce_ahash_async_req_handle(struct crypto_async_request *async_req) } ret = dma_map_sg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE); - if (ret < 0) - return ret; + if (!ret) + return -EIO; sg_init_one(&rctx->result_sg, qce->dma.result_buf, QCE_RESULT_BUF_SZ); ret = dma_map_sg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE); - if (ret < 0) + if (!ret) { + ret = -EIO; goto error_unmap_src; + } ret = qce_dma_prep_sgs(&qce->dma, req->src, rctx->src_nents, &rctx->result_sg, 1, qce_ahash_done, async_req); diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c index 3d27cd5210ef..5b493fdc1e74 100644 --- a/drivers/crypto/qce/skcipher.c +++ b/drivers/crypto/qce/skcipher.c @@ -124,15 +124,15 @@ qce_skcipher_async_req_handle(struct crypto_async_request *async_req) rctx->dst_sg = rctx->dst_tbl.sgl; dst_nents = dma_map_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst); - if (dst_nents < 0) { - ret = dst_nents; + if (!dst_nents) { + ret = -EIO; goto error_free; } if (diff_dst) { src_nents = dma_map_sg(qce->dev, req->src, rctx->src_nents, dir_src); - if (src_nents < 0) { - ret = src_nents; + if (!src_nents) { + ret = -EIO; goto error_unmap_dst; } rctx->src_sg = req->src; diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 99ba8d51d102..72dd1a4ebac4 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -8,6 +8,8 @@ #include <linux/clk.h> #include <linux/crypto.h> #include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> @@ -43,16 +45,19 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) { unsigned int currsize = 0; u32 val; + int ret; /* read random data from hardware */ do { - val = readl_relaxed(rng->base + PRNG_STATUS); - if (!(val & PRNG_STATUS_DATA_AVAIL)) - break; + ret = readl_poll_timeout(rng->base + PRNG_STATUS, val, + val & PRNG_STATUS_DATA_AVAIL, + 200, 10000); + if (ret) + return ret; val = readl_relaxed(rng->base + PRNG_DATA_OUT); if (!val) - break; + return -EINVAL; if ((max - currsize) >= WORD_SZ) { memcpy(data, &val, WORD_SZ); @@ -65,7 +70,7 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) } } while (currsize < max); - return currsize; + return 0; } static int qcom_rng_generate(struct crypto_rng *tfm, @@ -87,7 +92,7 @@ static int qcom_rng_generate(struct crypto_rng *tfm, mutex_unlock(&rng->lock); clk_disable_unprepare(rng->clk); - return 0; + return ret; } static int qcom_rng_seed(struct crypto_rng *tfm, const u8 *seed, @@ -197,15 +202,13 @@ static int qcom_rng_remove(struct platform_device *pdev) return 0; } -#if IS_ENABLED(CONFIG_ACPI) -static const struct acpi_device_id qcom_rng_acpi_match[] = { +static const struct acpi_device_id __maybe_unused qcom_rng_acpi_match[] = { { .id = "QCOM8160", .driver_data = 1 }, {} }; MODULE_DEVICE_TABLE(acpi, qcom_rng_acpi_match); -#endif -static const struct of_device_id qcom_rng_of_match[] = { +static const struct of_device_id __maybe_unused qcom_rng_of_match[] = { { .compatible = "qcom,prng", .data = (void *)0}, { .compatible = "qcom,prng-ee", .data = (void *)1}, {} diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index 1cece1a7d3f0..5bbf0d2722e1 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -506,7 +506,6 @@ struct rk_crypto_tmp rk_ecb_des3_ede_alg = { .exit = rk_ablk_exit_tfm, .min_keysize = DES3_EDE_KEY_SIZE, .max_keysize = DES3_EDE_KEY_SIZE, - .ivsize = DES_BLOCK_SIZE, .setkey = rk_tdes_setkey, .encrypt = rk_des3_ede_ecb_encrypt, .decrypt = rk_des3_ede_ecb_decrypt, diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c index 7717e9e5977b..b79e49aa724f 100644 --- a/drivers/crypto/s5p-sss.c +++ b/drivers/crypto/s5p-sss.c @@ -2321,9 +2321,6 @@ static int s5p_aes_remove(struct platform_device *pdev) struct s5p_aes_dev *pdata = platform_get_drvdata(pdev); int i; - if (!pdata) - return -ENODEV; - for (i = 0; i < ARRAY_SIZE(algs); i++) crypto_unregister_skcipher(&algs[i]); diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c index 51b58e57153f..f4bc06c24ad8 100644 --- a/drivers/crypto/sa2ul.c +++ b/drivers/crypto/sa2ul.c @@ -86,7 +86,6 @@ struct sa_match_data { u8 priv; u8 priv_id; u32 supported_algos; - bool skip_engine_control; }; static struct device *sa_k3_dev; @@ -2361,7 +2360,15 @@ static int sa_link_child(struct device *dev, void *data) static struct sa_match_data am654_match_data = { .priv = 1, .priv_id = 1, - .supported_algos = GENMASK(SA_ALG_AUTHENC_SHA256_AES, 0), + .supported_algos = BIT(SA_ALG_CBC_AES) | + BIT(SA_ALG_EBC_AES) | + BIT(SA_ALG_CBC_DES3) | + BIT(SA_ALG_ECB_DES3) | + BIT(SA_ALG_SHA1) | + BIT(SA_ALG_SHA256) | + BIT(SA_ALG_SHA512) | + BIT(SA_ALG_AUTHENC_SHA1_AES) | + BIT(SA_ALG_AUTHENC_SHA256_AES), }; static struct sa_match_data am64_match_data = { @@ -2372,13 +2379,13 @@ static struct sa_match_data am64_match_data = { BIT(SA_ALG_SHA256) | BIT(SA_ALG_SHA512) | BIT(SA_ALG_AUTHENC_SHA256_AES), - .skip_engine_control = true, }; static const struct of_device_id of_match[] = { { .compatible = "ti,j721e-sa2ul", .data = &am654_match_data, }, { .compatible = "ti,am654-sa2ul", .data = &am654_match_data, }, { .compatible = "ti,am64-sa2ul", .data = &am64_match_data, }, + { .compatible = "ti,am62-sa3ul", .data = &am64_match_data, }, {}, }; MODULE_DEVICE_TABLE(of, of_match); @@ -2389,6 +2396,7 @@ static int sa_ul_probe(struct platform_device *pdev) struct device_node *node = dev->of_node; static void __iomem *saul_base; struct sa_crypto_data *dev_data; + u32 status, val; int ret; dev_data = devm_kzalloc(dev, sizeof(*dev_data), GFP_KERNEL); @@ -2425,13 +2433,13 @@ static int sa_ul_probe(struct platform_device *pdev) spin_lock_init(&dev_data->scid_lock); - if (!dev_data->match_data->skip_engine_control) { - u32 val = SA_EEC_ENCSS_EN | SA_EEC_AUTHSS_EN | SA_EEC_CTXCACH_EN | - SA_EEC_CPPI_PORT_IN_EN | SA_EEC_CPPI_PORT_OUT_EN | - SA_EEC_TRNG_EN; - + val = SA_EEC_ENCSS_EN | SA_EEC_AUTHSS_EN | SA_EEC_CTXCACH_EN | + SA_EEC_CPPI_PORT_IN_EN | SA_EEC_CPPI_PORT_OUT_EN | + SA_EEC_TRNG_EN; + status = readl_relaxed(saul_base + SA_ENGINE_STATUS); + /* Only enable engines if all are not already enabled */ + if (val & ~status) writel_relaxed(val, saul_base + SA_ENGINE_ENABLE_CONTROL); - } sa_register_algos(dev_data); diff --git a/drivers/crypto/sa2ul.h b/drivers/crypto/sa2ul.h index ed66d1f111db..92bf97232a29 100644 --- a/drivers/crypto/sa2ul.h +++ b/drivers/crypto/sa2ul.h @@ -16,6 +16,7 @@ #include <crypto/sha1.h> #include <crypto/sha2.h> +#define SA_ENGINE_STATUS 0x0008 #define SA_ENGINE_ENABLE_CONTROL 0x1000 struct sa_tfm_ctx; diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c index 457084b344c1..7ab20fb95166 100644 --- a/drivers/crypto/sahara.c +++ b/drivers/crypto/sahara.c @@ -26,10 +26,10 @@ #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/spinlock.h> #define SHA_BUFFER_LEN PAGE_SIZE #define SAHARA_MAX_SHA_BLOCK_SIZE SHA256_BLOCK_SIZE @@ -196,7 +196,7 @@ struct sahara_dev { void __iomem *regs_base; struct clk *clk_ipg; struct clk *clk_ahb; - struct mutex queue_mutex; + spinlock_t queue_spinlock; struct task_struct *kthread; struct completion dma_completion; @@ -487,13 +487,13 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) ret = dma_map_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); - if (ret != dev->nb_in_sg) { + if (!ret) { dev_err(dev->device, "couldn't map in sg\n"); goto unmap_in; } ret = dma_map_sg(dev->device, dev->out_sg, dev->nb_out_sg, DMA_FROM_DEVICE); - if (ret != dev->nb_out_sg) { + if (!ret) { dev_err(dev->device, "couldn't map out sg\n"); goto unmap_out; } @@ -642,9 +642,9 @@ static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode) rctx->mode = mode; - mutex_lock(&dev->queue_mutex); + spin_lock_bh(&dev->queue_spinlock); err = crypto_enqueue_request(&dev->queue, &req->base); - mutex_unlock(&dev->queue_mutex); + spin_unlock_bh(&dev->queue_spinlock); wake_up_process(dev->kthread); @@ -1043,10 +1043,10 @@ static int sahara_queue_manage(void *data) do { __set_current_state(TASK_INTERRUPTIBLE); - mutex_lock(&dev->queue_mutex); + spin_lock_bh(&dev->queue_spinlock); backlog = crypto_get_backlog(&dev->queue); async_req = crypto_dequeue_request(&dev->queue); - mutex_unlock(&dev->queue_mutex); + spin_unlock_bh(&dev->queue_spinlock); if (backlog) backlog->complete(backlog, -EINPROGRESS); @@ -1092,9 +1092,9 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last) rctx->first = 1; } - mutex_lock(&dev->queue_mutex); + spin_lock_bh(&dev->queue_spinlock); ret = crypto_enqueue_request(&dev->queue, &req->base); - mutex_unlock(&dev->queue_mutex); + spin_unlock_bh(&dev->queue_spinlock); wake_up_process(dev->kthread); @@ -1449,7 +1449,7 @@ static int sahara_probe(struct platform_device *pdev) crypto_init_queue(&dev->queue, SAHARA_QUEUE_LENGTH); - mutex_init(&dev->queue_mutex); + spin_lock_init(&dev->queue_spinlock); dev_ptr = dev; diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index be1bf39a317d..90a920e7f664 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -384,8 +384,10 @@ static int stm32_crc_remove(struct platform_device *pdev) struct stm32_crc *crc = platform_get_drvdata(pdev); int ret = pm_runtime_get_sync(crc->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(crc->dev); return ret; + } spin_lock(&crc_list.lock); list_del(&crc->list); diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 25c9f825b8b5..c9ad6c213090 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1709,7 +1709,7 @@ static void common_nonsnoop_hash_unmap(struct device *dev, struct talitos_desc *desc2 = (struct talitos_desc *) (edesc->buf + edesc->dma_len); - unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE); + unmap_single_talitos_ptr(dev, &desc->ptr[5], DMA_FROM_DEVICE); if (desc->next_desc && desc->ptr[5].ptr != desc2->ptr[5].ptr) unmap_single_talitos_ptr(dev, &desc2->ptr[5], DMA_FROM_DEVICE); @@ -1721,8 +1721,8 @@ static void common_nonsnoop_hash_unmap(struct device *dev, talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL, 0, 0); /* When using hashctx-in, must unmap it. */ - if (from_talitos_ptr_len(&edesc->desc.ptr[1], is_sec1)) - unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1], + if (from_talitos_ptr_len(&desc->ptr[1], is_sec1)) + unmap_single_talitos_ptr(dev, &desc->ptr[1], DMA_TO_DEVICE); else if (desc->next_desc) unmap_single_talitos_ptr(dev, &desc2->ptr[1], @@ -1736,8 +1736,8 @@ static void common_nonsnoop_hash_unmap(struct device *dev, dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); - if (edesc->desc.next_desc) - dma_unmap_single(dev, be32_to_cpu(edesc->desc.next_desc), + if (desc->next_desc) + dma_unmap_single(dev, be32_to_cpu(desc->next_desc), TALITOS_DESC_SIZE, DMA_BIDIRECTIONAL); } diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index 97277b7150cb..5a57c9afd8c8 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1264,7 +1264,7 @@ static int ux500_cryp_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; dev_dbg(dev, "[%s]", __func__); - device_data = devm_kzalloc(dev, sizeof(*device_data), GFP_ATOMIC); + device_data = devm_kzalloc(dev, sizeof(*device_data), GFP_KERNEL); if (!device_data) { ret = -ENOMEM; goto out; diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 51a6e1a42434..f104e8a43036 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -421,7 +421,7 @@ static int hash_get_device_data(struct hash_ctx *ctx, * @keylen: The lengt of the key. * * Note! This function DOES NOT write to the NBLW registry, even though - * specified in the the hw design spec. Either due to incorrect info in the + * specified in the hw design spec. Either due to incorrect info in the * spec or due to a bug in the hw. */ static void hash_hw_write_key(struct hash_device_data *device_data, @@ -877,9 +877,7 @@ static int hash_dma_final(struct ahash_request *req) __func__); goto out; } - } - - if (!req_ctx->updated) { + } else { ret = hash_setconfiguration(device_data, &ctx->config); if (ret) { dev_err(device_data->dev, @@ -1658,7 +1656,7 @@ static int ux500_hash_probe(struct platform_device *pdev) struct hash_device_data *device_data; struct device *dev = &pdev->dev; - device_data = devm_kzalloc(dev, sizeof(*device_data), GFP_ATOMIC); + device_data = devm_kzalloc(dev, sizeof(*device_data), GFP_KERNEL); if (!device_data) { ret = -ENOMEM; goto out; diff --git a/drivers/crypto/virtio/Kconfig b/drivers/crypto/virtio/Kconfig index b894e3a8be4f..5f8915f4a9ff 100644 --- a/drivers/crypto/virtio/Kconfig +++ b/drivers/crypto/virtio/Kconfig @@ -3,8 +3,11 @@ config CRYPTO_DEV_VIRTIO tristate "VirtIO crypto driver" depends on VIRTIO select CRYPTO_AEAD + select CRYPTO_AKCIPHER2 select CRYPTO_SKCIPHER select CRYPTO_ENGINE + select CRYPTO_RSA + select MPILIB help This driver provides support for virtio crypto device. If you choose 'M' here, this module will be called virtio_crypto. diff --git a/drivers/crypto/virtio/Makefile b/drivers/crypto/virtio/Makefile index cbfccccfa135..bfa6cbae342e 100644 --- a/drivers/crypto/virtio/Makefile +++ b/drivers/crypto/virtio/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio_crypto.o virtio_crypto-objs := \ - virtio_crypto_algs.o \ + virtio_crypto_skcipher_algs.o \ + virtio_crypto_akcipher_algs.o \ virtio_crypto_mgr.o \ virtio_crypto_core.o diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c new file mode 100644 index 000000000000..168195672e2e --- /dev/null +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -0,0 +1,594 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + /* Asymmetric algorithms supported by virtio crypto device + * + * Authors: zhenwei pi <pizhenwei@bytedance.com> + * lei he <helei.sig11@bytedance.com> + * + * Copyright 2022 Bytedance CO., LTD. + */ + +#include <linux/mpi.h> +#include <linux/scatterlist.h> +#include <crypto/algapi.h> +#include <crypto/internal/akcipher.h> +#include <crypto/internal/rsa.h> +#include <linux/err.h> +#include <crypto/scatterwalk.h> +#include <linux/atomic.h> + +#include <uapi/linux/virtio_crypto.h> +#include "virtio_crypto_common.h" + +struct virtio_crypto_rsa_ctx { + MPI n; +}; + +struct virtio_crypto_akcipher_ctx { + struct crypto_engine_ctx enginectx; + struct virtio_crypto *vcrypto; + struct crypto_akcipher *tfm; + bool session_valid; + __u64 session_id; + union { + struct virtio_crypto_rsa_ctx rsa_ctx; + }; +}; + +struct virtio_crypto_akcipher_request { + struct virtio_crypto_request base; + struct virtio_crypto_akcipher_ctx *akcipher_ctx; + struct akcipher_request *akcipher_req; + void *src_buf; + void *dst_buf; + uint32_t opcode; +}; + +struct virtio_crypto_akcipher_algo { + uint32_t algonum; + uint32_t service; + unsigned int active_devs; + struct akcipher_alg algo; +}; + +static DEFINE_MUTEX(algs_lock); + +static void virtio_crypto_akcipher_finalize_req( + struct virtio_crypto_akcipher_request *vc_akcipher_req, + struct akcipher_request *req, int err) +{ + kfree(vc_akcipher_req->src_buf); + kfree(vc_akcipher_req->dst_buf); + vc_akcipher_req->src_buf = NULL; + vc_akcipher_req->dst_buf = NULL; + virtcrypto_clear_request(&vc_akcipher_req->base); + + crypto_finalize_akcipher_request(vc_akcipher_req->base.dataq->engine, req, err); +} + +static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request *vc_req, int len) +{ + struct virtio_crypto_akcipher_request *vc_akcipher_req = + container_of(vc_req, struct virtio_crypto_akcipher_request, base); + struct akcipher_request *akcipher_req; + int error; + + switch (vc_req->status) { + case VIRTIO_CRYPTO_OK: + error = 0; + break; + case VIRTIO_CRYPTO_INVSESS: + case VIRTIO_CRYPTO_ERR: + error = -EINVAL; + break; + case VIRTIO_CRYPTO_BADMSG: + error = -EBADMSG; + break; + + case VIRTIO_CRYPTO_KEY_REJECTED: + error = -EKEYREJECTED; + break; + + default: + error = -EIO; + break; + } + + akcipher_req = vc_akcipher_req->akcipher_req; + if (vc_akcipher_req->opcode != VIRTIO_CRYPTO_AKCIPHER_VERIFY) { + /* actuall length maybe less than dst buffer */ + akcipher_req->dst_len = len - sizeof(vc_req->status); + sg_copy_from_buffer(akcipher_req->dst, sg_nents(akcipher_req->dst), + vc_akcipher_req->dst_buf, akcipher_req->dst_len); + } + virtio_crypto_akcipher_finalize_req(vc_akcipher_req, akcipher_req, error); +} + +static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, + struct virtio_crypto_ctrl_header *header, void *para, + const uint8_t *key, unsigned int keylen) +{ + struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; + struct virtio_crypto *vcrypto = ctx->vcrypto; + uint8_t *pkey; + int err; + unsigned int num_out = 0, num_in = 0; + struct virtio_crypto_op_ctrl_req *ctrl; + struct virtio_crypto_session_input *input; + struct virtio_crypto_ctrl_request *vc_ctrl_req; + + pkey = kmemdup(key, keylen, GFP_ATOMIC); + if (!pkey) + return -ENOMEM; + + vc_ctrl_req = kzalloc(sizeof(*vc_ctrl_req), GFP_KERNEL); + if (!vc_ctrl_req) { + err = -ENOMEM; + goto out; + } + + ctrl = &vc_ctrl_req->ctrl; + memcpy(&ctrl->header, header, sizeof(ctrl->header)); + memcpy(&ctrl->u, para, sizeof(ctrl->u)); + input = &vc_ctrl_req->input; + input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); + + sg_init_one(&outhdr_sg, ctrl, sizeof(*ctrl)); + sgs[num_out++] = &outhdr_sg; + + sg_init_one(&key_sg, pkey, keylen); + sgs[num_out++] = &key_sg; + + sg_init_one(&inhdr_sg, input, sizeof(*input)); + sgs[num_out + num_in++] = &inhdr_sg; + + err = virtio_crypto_ctrl_vq_request(vcrypto, sgs, num_out, num_in, vc_ctrl_req); + if (err < 0) + goto out; + + if (le32_to_cpu(input->status) != VIRTIO_CRYPTO_OK) { + pr_err("virtio_crypto: Create session failed status: %u\n", + le32_to_cpu(input->status)); + err = -EINVAL; + goto out; + } + + ctx->session_id = le64_to_cpu(input->session_id); + ctx->session_valid = true; + err = 0; + +out: + kfree(vc_ctrl_req); + kfree_sensitive(pkey); + + return err; +} + +static int virtio_crypto_alg_akcipher_close_session(struct virtio_crypto_akcipher_ctx *ctx) +{ + struct scatterlist outhdr_sg, inhdr_sg, *sgs[2]; + struct virtio_crypto_destroy_session_req *destroy_session; + struct virtio_crypto *vcrypto = ctx->vcrypto; + unsigned int num_out = 0, num_in = 0; + int err; + struct virtio_crypto_op_ctrl_req *ctrl; + struct virtio_crypto_inhdr *ctrl_status; + struct virtio_crypto_ctrl_request *vc_ctrl_req; + + if (!ctx->session_valid) + return 0; + + vc_ctrl_req = kzalloc(sizeof(*vc_ctrl_req), GFP_KERNEL); + if (!vc_ctrl_req) + return -ENOMEM; + + ctrl_status = &vc_ctrl_req->ctrl_status; + ctrl_status->status = VIRTIO_CRYPTO_ERR; + ctrl = &vc_ctrl_req->ctrl; + ctrl->header.opcode = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_DESTROY_SESSION); + ctrl->header.queue_id = 0; + + destroy_session = &ctrl->u.destroy_session; + destroy_session->session_id = cpu_to_le64(ctx->session_id); + + sg_init_one(&outhdr_sg, ctrl, sizeof(*ctrl)); + sgs[num_out++] = &outhdr_sg; + + sg_init_one(&inhdr_sg, &ctrl_status->status, sizeof(ctrl_status->status)); + sgs[num_out + num_in++] = &inhdr_sg; + + err = virtio_crypto_ctrl_vq_request(vcrypto, sgs, num_out, num_in, vc_ctrl_req); + if (err < 0) + goto out; + + if (ctrl_status->status != VIRTIO_CRYPTO_OK) { + pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n", + ctrl_status->status, destroy_session->session_id); + err = -EINVAL; + goto out; + } + + err = 0; + ctx->session_valid = false; + +out: + kfree(vc_ctrl_req); + + return err; +} + +static int __virtio_crypto_akcipher_do_req(struct virtio_crypto_akcipher_request *vc_akcipher_req, + struct akcipher_request *req, struct data_queue *data_vq) +{ + struct virtio_crypto_akcipher_ctx *ctx = vc_akcipher_req->akcipher_ctx; + struct virtio_crypto_request *vc_req = &vc_akcipher_req->base; + struct virtio_crypto *vcrypto = ctx->vcrypto; + struct virtio_crypto_op_data_req *req_data = vc_req->req_data; + struct scatterlist *sgs[4], outhdr_sg, inhdr_sg, srcdata_sg, dstdata_sg; + void *src_buf = NULL, *dst_buf = NULL; + unsigned int num_out = 0, num_in = 0; + int node = dev_to_node(&vcrypto->vdev->dev); + unsigned long flags; + int ret = -ENOMEM; + bool verify = vc_akcipher_req->opcode == VIRTIO_CRYPTO_AKCIPHER_VERIFY; + unsigned int src_len = verify ? req->src_len + req->dst_len : req->src_len; + + /* out header */ + sg_init_one(&outhdr_sg, req_data, sizeof(*req_data)); + sgs[num_out++] = &outhdr_sg; + + /* src data */ + src_buf = kcalloc_node(src_len, 1, GFP_KERNEL, node); + if (!src_buf) + goto err; + + if (verify) { + /* for verify operation, both src and dst data work as OUT direction */ + sg_copy_to_buffer(req->src, sg_nents(req->src), src_buf, src_len); + sg_init_one(&srcdata_sg, src_buf, src_len); + sgs[num_out++] = &srcdata_sg; + } else { + sg_copy_to_buffer(req->src, sg_nents(req->src), src_buf, src_len); + sg_init_one(&srcdata_sg, src_buf, src_len); + sgs[num_out++] = &srcdata_sg; + + /* dst data */ + dst_buf = kcalloc_node(req->dst_len, 1, GFP_KERNEL, node); + if (!dst_buf) + goto err; + + sg_init_one(&dstdata_sg, dst_buf, req->dst_len); + sgs[num_out + num_in++] = &dstdata_sg; + } + + vc_akcipher_req->src_buf = src_buf; + vc_akcipher_req->dst_buf = dst_buf; + + /* in header */ + sg_init_one(&inhdr_sg, &vc_req->status, sizeof(vc_req->status)); + sgs[num_out + num_in++] = &inhdr_sg; + + spin_lock_irqsave(&data_vq->lock, flags); + ret = virtqueue_add_sgs(data_vq->vq, sgs, num_out, num_in, vc_req, GFP_ATOMIC); + virtqueue_kick(data_vq->vq); + spin_unlock_irqrestore(&data_vq->lock, flags); + if (ret) + goto err; + + return 0; + +err: + kfree(src_buf); + kfree(dst_buf); + + return -ENOMEM; +} + +static int virtio_crypto_rsa_do_req(struct crypto_engine *engine, void *vreq) +{ + struct akcipher_request *req = container_of(vreq, struct akcipher_request, base); + struct virtio_crypto_akcipher_request *vc_akcipher_req = akcipher_request_ctx(req); + struct virtio_crypto_request *vc_req = &vc_akcipher_req->base; + struct virtio_crypto_akcipher_ctx *ctx = vc_akcipher_req->akcipher_ctx; + struct virtio_crypto *vcrypto = ctx->vcrypto; + struct data_queue *data_vq = vc_req->dataq; + struct virtio_crypto_op_header *header; + struct virtio_crypto_akcipher_data_req *akcipher_req; + int ret; + + vc_req->sgs = NULL; + vc_req->req_data = kzalloc_node(sizeof(*vc_req->req_data), + GFP_KERNEL, dev_to_node(&vcrypto->vdev->dev)); + if (!vc_req->req_data) + return -ENOMEM; + + /* build request header */ + header = &vc_req->req_data->header; + header->opcode = cpu_to_le32(vc_akcipher_req->opcode); + header->algo = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_RSA); + header->session_id = cpu_to_le64(ctx->session_id); + + /* build request akcipher data */ + akcipher_req = &vc_req->req_data->u.akcipher_req; + akcipher_req->para.src_data_len = cpu_to_le32(req->src_len); + akcipher_req->para.dst_data_len = cpu_to_le32(req->dst_len); + + ret = __virtio_crypto_akcipher_do_req(vc_akcipher_req, req, data_vq); + if (ret < 0) { + kfree_sensitive(vc_req->req_data); + vc_req->req_data = NULL; + return ret; + } + + return 0; +} + +static int virtio_crypto_rsa_req(struct akcipher_request *req, uint32_t opcode) +{ + struct crypto_akcipher *atfm = crypto_akcipher_reqtfm(req); + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(atfm); + struct virtio_crypto_akcipher_request *vc_akcipher_req = akcipher_request_ctx(req); + struct virtio_crypto_request *vc_req = &vc_akcipher_req->base; + struct virtio_crypto *vcrypto = ctx->vcrypto; + /* Use the first data virtqueue as default */ + struct data_queue *data_vq = &vcrypto->data_vq[0]; + + vc_req->dataq = data_vq; + vc_req->alg_cb = virtio_crypto_dataq_akcipher_callback; + vc_akcipher_req->akcipher_ctx = ctx; + vc_akcipher_req->akcipher_req = req; + vc_akcipher_req->opcode = opcode; + + return crypto_transfer_akcipher_request_to_engine(data_vq->engine, req); +} + +static int virtio_crypto_rsa_encrypt(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_ENCRYPT); +} + +static int virtio_crypto_rsa_decrypt(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_DECRYPT); +} + +static int virtio_crypto_rsa_sign(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_SIGN); +} + +static int virtio_crypto_rsa_verify(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_VERIFY); +} + +static int virtio_crypto_rsa_set_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen, + bool private, + int padding_algo, + int hash_algo) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + struct virtio_crypto_rsa_ctx *rsa_ctx = &ctx->rsa_ctx; + struct virtio_crypto *vcrypto; + struct virtio_crypto_ctrl_header header; + struct virtio_crypto_akcipher_session_para para; + struct rsa_key rsa_key = {0}; + int node = virtio_crypto_get_current_node(); + uint32_t keytype; + int ret; + + /* mpi_free will test n, just free it. */ + mpi_free(rsa_ctx->n); + rsa_ctx->n = NULL; + + if (private) { + keytype = VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PRIVATE; + ret = rsa_parse_priv_key(&rsa_key, key, keylen); + } else { + keytype = VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PUBLIC; + ret = rsa_parse_pub_key(&rsa_key, key, keylen); + } + + if (ret) + return ret; + + rsa_ctx->n = mpi_read_raw_data(rsa_key.n, rsa_key.n_sz); + if (!rsa_ctx->n) + return -ENOMEM; + + if (!ctx->vcrypto) { + vcrypto = virtcrypto_get_dev_node(node, VIRTIO_CRYPTO_SERVICE_AKCIPHER, + VIRTIO_CRYPTO_AKCIPHER_RSA); + if (!vcrypto) { + pr_err("virtio_crypto: Could not find a virtio device in the system or unsupported algo\n"); + return -ENODEV; + } + + ctx->vcrypto = vcrypto; + } else { + virtio_crypto_alg_akcipher_close_session(ctx); + } + + /* set ctrl header */ + header.opcode = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_CREATE_SESSION); + header.algo = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_RSA); + header.queue_id = 0; + + /* set RSA para */ + para.algo = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_RSA); + para.keytype = cpu_to_le32(keytype); + para.keylen = cpu_to_le32(keylen); + para.u.rsa.padding_algo = cpu_to_le32(padding_algo); + para.u.rsa.hash_algo = cpu_to_le32(hash_algo); + + return virtio_crypto_alg_akcipher_init_session(ctx, &header, ¶, key, keylen); +} + +static int virtio_crypto_rsa_raw_set_priv_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 1, + VIRTIO_CRYPTO_RSA_RAW_PADDING, + VIRTIO_CRYPTO_RSA_NO_HASH); +} + + +static int virtio_crypto_p1pad_rsa_sha1_set_priv_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 1, + VIRTIO_CRYPTO_RSA_PKCS1_PADDING, + VIRTIO_CRYPTO_RSA_SHA1); +} + +static int virtio_crypto_rsa_raw_set_pub_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 0, + VIRTIO_CRYPTO_RSA_RAW_PADDING, + VIRTIO_CRYPTO_RSA_NO_HASH); +} + +static int virtio_crypto_p1pad_rsa_sha1_set_pub_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 0, + VIRTIO_CRYPTO_RSA_PKCS1_PADDING, + VIRTIO_CRYPTO_RSA_SHA1); +} + +static unsigned int virtio_crypto_rsa_max_size(struct crypto_akcipher *tfm) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + struct virtio_crypto_rsa_ctx *rsa_ctx = &ctx->rsa_ctx; + + return mpi_get_size(rsa_ctx->n); +} + +static int virtio_crypto_rsa_init_tfm(struct crypto_akcipher *tfm) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + + ctx->tfm = tfm; + ctx->enginectx.op.do_one_request = virtio_crypto_rsa_do_req; + ctx->enginectx.op.prepare_request = NULL; + ctx->enginectx.op.unprepare_request = NULL; + + return 0; +} + +static void virtio_crypto_rsa_exit_tfm(struct crypto_akcipher *tfm) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + struct virtio_crypto_rsa_ctx *rsa_ctx = &ctx->rsa_ctx; + + virtio_crypto_alg_akcipher_close_session(ctx); + virtcrypto_dev_put(ctx->vcrypto); + mpi_free(rsa_ctx->n); + rsa_ctx->n = NULL; +} + +static struct virtio_crypto_akcipher_algo virtio_crypto_akcipher_algs[] = { + { + .algonum = VIRTIO_CRYPTO_AKCIPHER_RSA, + .service = VIRTIO_CRYPTO_SERVICE_AKCIPHER, + .algo = { + .encrypt = virtio_crypto_rsa_encrypt, + .decrypt = virtio_crypto_rsa_decrypt, + .set_pub_key = virtio_crypto_rsa_raw_set_pub_key, + .set_priv_key = virtio_crypto_rsa_raw_set_priv_key, + .max_size = virtio_crypto_rsa_max_size, + .init = virtio_crypto_rsa_init_tfm, + .exit = virtio_crypto_rsa_exit_tfm, + .reqsize = sizeof(struct virtio_crypto_akcipher_request), + .base = { + .cra_name = "rsa", + .cra_driver_name = "virtio-crypto-rsa", + .cra_priority = 150, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct virtio_crypto_akcipher_ctx), + }, + }, + }, + { + .algonum = VIRTIO_CRYPTO_AKCIPHER_RSA, + .service = VIRTIO_CRYPTO_SERVICE_AKCIPHER, + .algo = { + .encrypt = virtio_crypto_rsa_encrypt, + .decrypt = virtio_crypto_rsa_decrypt, + .sign = virtio_crypto_rsa_sign, + .verify = virtio_crypto_rsa_verify, + .set_pub_key = virtio_crypto_p1pad_rsa_sha1_set_pub_key, + .set_priv_key = virtio_crypto_p1pad_rsa_sha1_set_priv_key, + .max_size = virtio_crypto_rsa_max_size, + .init = virtio_crypto_rsa_init_tfm, + .exit = virtio_crypto_rsa_exit_tfm, + .reqsize = sizeof(struct virtio_crypto_akcipher_request), + .base = { + .cra_name = "pkcs1pad(rsa,sha1)", + .cra_driver_name = "virtio-pkcs1-rsa-with-sha1", + .cra_priority = 150, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct virtio_crypto_akcipher_ctx), + }, + }, + }, +}; + +int virtio_crypto_akcipher_algs_register(struct virtio_crypto *vcrypto) +{ + int ret = 0; + int i = 0; + + mutex_lock(&algs_lock); + + for (i = 0; i < ARRAY_SIZE(virtio_crypto_akcipher_algs); i++) { + uint32_t service = virtio_crypto_akcipher_algs[i].service; + uint32_t algonum = virtio_crypto_akcipher_algs[i].algonum; + + if (!virtcrypto_algo_is_supported(vcrypto, service, algonum)) + continue; + + if (virtio_crypto_akcipher_algs[i].active_devs == 0) { + ret = crypto_register_akcipher(&virtio_crypto_akcipher_algs[i].algo); + if (ret) + goto unlock; + } + + virtio_crypto_akcipher_algs[i].active_devs++; + dev_info(&vcrypto->vdev->dev, "Registered akcipher algo %s\n", + virtio_crypto_akcipher_algs[i].algo.base.cra_name); + } + +unlock: + mutex_unlock(&algs_lock); + return ret; +} + +void virtio_crypto_akcipher_algs_unregister(struct virtio_crypto *vcrypto) +{ + int i = 0; + + mutex_lock(&algs_lock); + + for (i = 0; i < ARRAY_SIZE(virtio_crypto_akcipher_algs); i++) { + uint32_t service = virtio_crypto_akcipher_algs[i].service; + uint32_t algonum = virtio_crypto_akcipher_algs[i].algonum; + + if (virtio_crypto_akcipher_algs[i].active_devs == 0 || + !virtcrypto_algo_is_supported(vcrypto, service, algonum)) + continue; + + if (virtio_crypto_akcipher_algs[i].active_devs == 1) + crypto_unregister_akcipher(&virtio_crypto_akcipher_algs[i].algo); + + virtio_crypto_akcipher_algs[i].active_devs--; + } + + mutex_unlock(&algs_lock); +} diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h index a24f85c589e7..59a4c0259456 100644 --- a/drivers/crypto/virtio/virtio_crypto_common.h +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -13,6 +13,7 @@ #include <crypto/aead.h> #include <crypto/aes.h> #include <crypto/engine.h> +#include <uapi/linux/virtio_crypto.h> /* Internal representation of a data virtqueue */ @@ -56,6 +57,7 @@ struct virtio_crypto { u32 mac_algo_l; u32 mac_algo_h; u32 aead_algo; + u32 akcipher_algo; /* Maximum length of cipher key */ u32 max_cipher_key_len; @@ -64,11 +66,6 @@ struct virtio_crypto { /* Maximum size of per request */ u64 max_size; - /* Control VQ buffers: protected by the ctrl_lock */ - struct virtio_crypto_op_ctrl_req ctrl; - struct virtio_crypto_session_input input; - struct virtio_crypto_inhdr ctrl_status; - unsigned long status; atomic_t ref_count; struct list_head list; @@ -84,6 +81,18 @@ struct virtio_crypto_sym_session_info { __u64 session_id; }; +/* + * Note: there are padding fields in request, clear them to zero before + * sending to host to avoid to divulge any information. + * Ex, virtio_crypto_ctrl_request::ctrl::u::destroy_session::padding[48] + */ +struct virtio_crypto_ctrl_request { + struct virtio_crypto_op_ctrl_req ctrl; + struct virtio_crypto_session_input input; + struct virtio_crypto_inhdr ctrl_status; + struct completion compl; +}; + struct virtio_crypto_request; typedef void (*virtio_crypto_data_callback) (struct virtio_crypto_request *vc_req, int len); @@ -129,7 +138,12 @@ static inline int virtio_crypto_get_current_node(void) return node; } -int virtio_crypto_algs_register(struct virtio_crypto *vcrypto); -void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto); +int virtio_crypto_skcipher_algs_register(struct virtio_crypto *vcrypto); +void virtio_crypto_skcipher_algs_unregister(struct virtio_crypto *vcrypto); +int virtio_crypto_akcipher_algs_register(struct virtio_crypto *vcrypto); +void virtio_crypto_akcipher_algs_unregister(struct virtio_crypto *vcrypto); +int virtio_crypto_ctrl_vq_request(struct virtio_crypto *vcrypto, struct scatterlist *sgs[], + unsigned int out_sgs, unsigned int in_sgs, + struct virtio_crypto_ctrl_request *vc_ctrl_req); #endif /* _VIRTIO_CRYPTO_COMMON_H */ diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index e2375d992308..1198bd306365 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -22,6 +22,56 @@ virtcrypto_clear_request(struct virtio_crypto_request *vc_req) } } +static void virtio_crypto_ctrlq_callback(struct virtio_crypto_ctrl_request *vc_ctrl_req) +{ + complete(&vc_ctrl_req->compl); +} + +static void virtcrypto_ctrlq_callback(struct virtqueue *vq) +{ + struct virtio_crypto *vcrypto = vq->vdev->priv; + struct virtio_crypto_ctrl_request *vc_ctrl_req; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&vcrypto->ctrl_lock, flags); + do { + virtqueue_disable_cb(vq); + while ((vc_ctrl_req = virtqueue_get_buf(vq, &len)) != NULL) { + spin_unlock_irqrestore(&vcrypto->ctrl_lock, flags); + virtio_crypto_ctrlq_callback(vc_ctrl_req); + spin_lock_irqsave(&vcrypto->ctrl_lock, flags); + } + if (unlikely(virtqueue_is_broken(vq))) + break; + } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&vcrypto->ctrl_lock, flags); +} + +int virtio_crypto_ctrl_vq_request(struct virtio_crypto *vcrypto, struct scatterlist *sgs[], + unsigned int out_sgs, unsigned int in_sgs, + struct virtio_crypto_ctrl_request *vc_ctrl_req) +{ + int err; + unsigned long flags; + + init_completion(&vc_ctrl_req->compl); + + spin_lock_irqsave(&vcrypto->ctrl_lock, flags); + err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, out_sgs, in_sgs, vc_ctrl_req, GFP_ATOMIC); + if (err < 0) { + spin_unlock_irqrestore(&vcrypto->ctrl_lock, flags); + return err; + } + + virtqueue_kick(vcrypto->ctrl_vq); + spin_unlock_irqrestore(&vcrypto->ctrl_lock, flags); + + wait_for_completion(&vc_ctrl_req->compl); + + return 0; +} + static void virtcrypto_dataq_callback(struct virtqueue *vq) { struct virtio_crypto *vcrypto = vq->vdev->priv; @@ -73,7 +123,7 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi) goto err_names; /* Parameters for control virtqueue */ - callbacks[total_vqs - 1] = NULL; + callbacks[total_vqs - 1] = virtcrypto_ctrlq_callback; names[total_vqs - 1] = "controlq"; /* Allocate/initialize parameters for data virtqueues */ @@ -94,7 +144,8 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi) spin_lock_init(&vi->data_vq[i].lock); vi->data_vq[i].vq = vqs[i]; /* Initialize crypto engine */ - vi->data_vq[i].engine = crypto_engine_alloc_init(dev, 1); + vi->data_vq[i].engine = crypto_engine_alloc_init_and_set(dev, true, NULL, true, + virtqueue_get_vring_size(vqs[i])); if (!vi->data_vq[i].engine) { ret = -ENOMEM; goto err_engine; @@ -297,6 +348,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) u32 mac_algo_l = 0; u32 mac_algo_h = 0; u32 aead_algo = 0; + u32 akcipher_algo = 0; u32 crypto_services = 0; if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) @@ -348,6 +400,9 @@ static int virtcrypto_probe(struct virtio_device *vdev) mac_algo_h, &mac_algo_h); virtio_cread_le(vdev, struct virtio_crypto_config, aead_algo, &aead_algo); + if (crypto_services & (1 << VIRTIO_CRYPTO_SERVICE_AKCIPHER)) + virtio_cread_le(vdev, struct virtio_crypto_config, + akcipher_algo, &akcipher_algo); /* Add virtio crypto device to global table */ err = virtcrypto_devmgr_add_dev(vcrypto); @@ -374,7 +429,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) vcrypto->mac_algo_h = mac_algo_h; vcrypto->hash_algo = hash_algo; vcrypto->aead_algo = aead_algo; - + vcrypto->akcipher_algo = akcipher_algo; dev_info(&vdev->dev, "max_queues: %u, max_cipher_key_len: %u, max_auth_key_len: %u, max_size 0x%llx\n", @@ -404,7 +459,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); free_dev: virtcrypto_devmgr_rm_dev(vcrypto); @@ -436,7 +491,7 @@ static void virtcrypto_remove(struct virtio_device *vdev) if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); virtcrypto_clear_crypto_engines(vcrypto); virtcrypto_del_vqs(vcrypto); @@ -456,7 +511,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); @@ -492,7 +547,7 @@ static int virtcrypto_restore(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); return err; } diff --git a/drivers/crypto/virtio/virtio_crypto_mgr.c b/drivers/crypto/virtio/virtio_crypto_mgr.c index 6860f8180c7c..70e778aac0f2 100644 --- a/drivers/crypto/virtio/virtio_crypto_mgr.c +++ b/drivers/crypto/virtio/virtio_crypto_mgr.c @@ -237,8 +237,14 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node, uint32_t service, */ int virtcrypto_dev_start(struct virtio_crypto *vcrypto) { - if (virtio_crypto_algs_register(vcrypto)) { - pr_err("virtio_crypto: Failed to register crypto algs\n"); + if (virtio_crypto_skcipher_algs_register(vcrypto)) { + pr_err("virtio_crypto: Failed to register crypto skcipher algs\n"); + return -EFAULT; + } + + if (virtio_crypto_akcipher_algs_register(vcrypto)) { + pr_err("virtio_crypto: Failed to register crypto akcipher algs\n"); + virtio_crypto_skcipher_algs_unregister(vcrypto); return -EFAULT; } @@ -257,7 +263,8 @@ int virtcrypto_dev_start(struct virtio_crypto *vcrypto) */ void virtcrypto_dev_stop(struct virtio_crypto *vcrypto) { - virtio_crypto_algs_unregister(vcrypto); + virtio_crypto_skcipher_algs_unregister(vcrypto); + virtio_crypto_akcipher_algs_unregister(vcrypto); } /* @@ -312,6 +319,10 @@ bool virtcrypto_algo_is_supported(struct virtio_crypto *vcrypto, case VIRTIO_CRYPTO_SERVICE_AEAD: algo_mask = vcrypto->aead_algo; break; + + case VIRTIO_CRYPTO_SERVICE_AKCIPHER: + algo_mask = vcrypto->akcipher_algo; + break; } if (!(algo_mask & (1u << algo))) diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c index 583c0b535d13..e553ccadbcbc 100644 --- a/drivers/crypto/virtio/virtio_crypto_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c @@ -118,11 +118,14 @@ static int virtio_crypto_alg_skcipher_init_session( int encrypt) { struct scatterlist outhdr, key_sg, inhdr, *sgs[3]; - unsigned int tmp; struct virtio_crypto *vcrypto = ctx->vcrypto; int op = encrypt ? VIRTIO_CRYPTO_OP_ENCRYPT : VIRTIO_CRYPTO_OP_DECRYPT; int err; unsigned int num_out = 0, num_in = 0; + struct virtio_crypto_op_ctrl_req *ctrl; + struct virtio_crypto_session_input *input; + struct virtio_crypto_sym_create_session_req *sym_create_session; + struct virtio_crypto_ctrl_request *vc_ctrl_req; /* * Avoid to do DMA from the stack, switch to using @@ -133,26 +136,29 @@ static int virtio_crypto_alg_skcipher_init_session( if (!cipher_key) return -ENOMEM; - spin_lock(&vcrypto->ctrl_lock); + vc_ctrl_req = kzalloc(sizeof(*vc_ctrl_req), GFP_KERNEL); + if (!vc_ctrl_req) { + err = -ENOMEM; + goto out; + } + /* Pad ctrl header */ - vcrypto->ctrl.header.opcode = - cpu_to_le32(VIRTIO_CRYPTO_CIPHER_CREATE_SESSION); - vcrypto->ctrl.header.algo = cpu_to_le32(alg); + ctrl = &vc_ctrl_req->ctrl; + ctrl->header.opcode = cpu_to_le32(VIRTIO_CRYPTO_CIPHER_CREATE_SESSION); + ctrl->header.algo = cpu_to_le32(alg); /* Set the default dataqueue id to 0 */ - vcrypto->ctrl.header.queue_id = 0; + ctrl->header.queue_id = 0; - vcrypto->input.status = cpu_to_le32(VIRTIO_CRYPTO_ERR); + input = &vc_ctrl_req->input; + input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); /* Pad cipher's parameters */ - vcrypto->ctrl.u.sym_create_session.op_type = - cpu_to_le32(VIRTIO_CRYPTO_SYM_OP_CIPHER); - vcrypto->ctrl.u.sym_create_session.u.cipher.para.algo = - vcrypto->ctrl.header.algo; - vcrypto->ctrl.u.sym_create_session.u.cipher.para.keylen = - cpu_to_le32(keylen); - vcrypto->ctrl.u.sym_create_session.u.cipher.para.op = - cpu_to_le32(op); - - sg_init_one(&outhdr, &vcrypto->ctrl, sizeof(vcrypto->ctrl)); + sym_create_session = &ctrl->u.sym_create_session; + sym_create_session->op_type = cpu_to_le32(VIRTIO_CRYPTO_SYM_OP_CIPHER); + sym_create_session->u.cipher.para.algo = ctrl->header.algo; + sym_create_session->u.cipher.para.keylen = cpu_to_le32(keylen); + sym_create_session->u.cipher.para.op = cpu_to_le32(op); + + sg_init_one(&outhdr, ctrl, sizeof(*ctrl)); sgs[num_out++] = &outhdr; /* Set key */ @@ -160,45 +166,30 @@ static int virtio_crypto_alg_skcipher_init_session( sgs[num_out++] = &key_sg; /* Return status and session id back */ - sg_init_one(&inhdr, &vcrypto->input, sizeof(vcrypto->input)); + sg_init_one(&inhdr, input, sizeof(*input)); sgs[num_out + num_in++] = &inhdr; - err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, num_out, - num_in, vcrypto, GFP_ATOMIC); - if (err < 0) { - spin_unlock(&vcrypto->ctrl_lock); - kfree_sensitive(cipher_key); - return err; - } - virtqueue_kick(vcrypto->ctrl_vq); + err = virtio_crypto_ctrl_vq_request(vcrypto, sgs, num_out, num_in, vc_ctrl_req); + if (err < 0) + goto out; - /* - * Trapping into the hypervisor, so the request should be - * handled immediately. - */ - while (!virtqueue_get_buf(vcrypto->ctrl_vq, &tmp) && - !virtqueue_is_broken(vcrypto->ctrl_vq)) - cpu_relax(); - - if (le32_to_cpu(vcrypto->input.status) != VIRTIO_CRYPTO_OK) { - spin_unlock(&vcrypto->ctrl_lock); + if (le32_to_cpu(input->status) != VIRTIO_CRYPTO_OK) { pr_err("virtio_crypto: Create session failed status: %u\n", - le32_to_cpu(vcrypto->input.status)); - kfree_sensitive(cipher_key); - return -EINVAL; + le32_to_cpu(input->status)); + err = -EINVAL; + goto out; } if (encrypt) - ctx->enc_sess_info.session_id = - le64_to_cpu(vcrypto->input.session_id); + ctx->enc_sess_info.session_id = le64_to_cpu(input->session_id); else - ctx->dec_sess_info.session_id = - le64_to_cpu(vcrypto->input.session_id); - - spin_unlock(&vcrypto->ctrl_lock); + ctx->dec_sess_info.session_id = le64_to_cpu(input->session_id); + err = 0; +out: + kfree(vc_ctrl_req); kfree_sensitive(cipher_key); - return 0; + return err; } static int virtio_crypto_alg_skcipher_close_session( @@ -206,60 +197,55 @@ static int virtio_crypto_alg_skcipher_close_session( int encrypt) { struct scatterlist outhdr, status_sg, *sgs[2]; - unsigned int tmp; struct virtio_crypto_destroy_session_req *destroy_session; struct virtio_crypto *vcrypto = ctx->vcrypto; int err; unsigned int num_out = 0, num_in = 0; + struct virtio_crypto_op_ctrl_req *ctrl; + struct virtio_crypto_inhdr *ctrl_status; + struct virtio_crypto_ctrl_request *vc_ctrl_req; - spin_lock(&vcrypto->ctrl_lock); - vcrypto->ctrl_status.status = VIRTIO_CRYPTO_ERR; + vc_ctrl_req = kzalloc(sizeof(*vc_ctrl_req), GFP_KERNEL); + if (!vc_ctrl_req) + return -ENOMEM; + + ctrl_status = &vc_ctrl_req->ctrl_status; + ctrl_status->status = VIRTIO_CRYPTO_ERR; /* Pad ctrl header */ - vcrypto->ctrl.header.opcode = - cpu_to_le32(VIRTIO_CRYPTO_CIPHER_DESTROY_SESSION); + ctrl = &vc_ctrl_req->ctrl; + ctrl->header.opcode = cpu_to_le32(VIRTIO_CRYPTO_CIPHER_DESTROY_SESSION); /* Set the default virtqueue id to 0 */ - vcrypto->ctrl.header.queue_id = 0; + ctrl->header.queue_id = 0; - destroy_session = &vcrypto->ctrl.u.destroy_session; + destroy_session = &ctrl->u.destroy_session; if (encrypt) - destroy_session->session_id = - cpu_to_le64(ctx->enc_sess_info.session_id); + destroy_session->session_id = cpu_to_le64(ctx->enc_sess_info.session_id); else - destroy_session->session_id = - cpu_to_le64(ctx->dec_sess_info.session_id); + destroy_session->session_id = cpu_to_le64(ctx->dec_sess_info.session_id); - sg_init_one(&outhdr, &vcrypto->ctrl, sizeof(vcrypto->ctrl)); + sg_init_one(&outhdr, ctrl, sizeof(*ctrl)); sgs[num_out++] = &outhdr; /* Return status and session id back */ - sg_init_one(&status_sg, &vcrypto->ctrl_status.status, - sizeof(vcrypto->ctrl_status.status)); + sg_init_one(&status_sg, &ctrl_status->status, sizeof(ctrl_status->status)); sgs[num_out + num_in++] = &status_sg; - err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, num_out, - num_in, vcrypto, GFP_ATOMIC); - if (err < 0) { - spin_unlock(&vcrypto->ctrl_lock); - return err; - } - virtqueue_kick(vcrypto->ctrl_vq); - - while (!virtqueue_get_buf(vcrypto->ctrl_vq, &tmp) && - !virtqueue_is_broken(vcrypto->ctrl_vq)) - cpu_relax(); + err = virtio_crypto_ctrl_vq_request(vcrypto, sgs, num_out, num_in, vc_ctrl_req); + if (err < 0) + goto out; - if (vcrypto->ctrl_status.status != VIRTIO_CRYPTO_OK) { - spin_unlock(&vcrypto->ctrl_lock); + if (ctrl_status->status != VIRTIO_CRYPTO_OK) { pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n", - vcrypto->ctrl_status.status, - destroy_session->session_id); + ctrl_status->status, destroy_session->session_id); return -EINVAL; } - spin_unlock(&vcrypto->ctrl_lock); - return 0; + err = 0; +out: + kfree(vc_ctrl_req); + return err; } static int virtio_crypto_alg_skcipher_init_sessions( @@ -613,7 +599,7 @@ static struct virtio_crypto_algo virtio_crypto_algs[] = { { }, } }; -int virtio_crypto_algs_register(struct virtio_crypto *vcrypto) +int virtio_crypto_skcipher_algs_register(struct virtio_crypto *vcrypto) { int ret = 0; int i = 0; @@ -644,7 +630,7 @@ unlock: return ret; } -void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto) +void virtio_crypto_skcipher_algs_unregister(struct virtio_crypto *vcrypto) { int i = 0; diff --git a/drivers/crypto/vmx/Kconfig b/drivers/crypto/vmx/Kconfig index c85fab7ef0bd..b2c28b87f14b 100644 --- a/drivers/crypto/vmx/Kconfig +++ b/drivers/crypto/vmx/Kconfig @@ -2,7 +2,11 @@ config CRYPTO_DEV_VMX_ENCRYPT tristate "Encryption acceleration support on P8 CPU" depends on CRYPTO_DEV_VMX + select CRYPTO_AES + select CRYPTO_CBC + select CRYPTO_CTR select CRYPTO_GHASH + select CRYPTO_XTS default m help Support for VMX cryptographic acceleration instructions on Power8 CPU. diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile index 709670d2b553..2560cfea1dec 100644 --- a/drivers/crypto/vmx/Makefile +++ b/drivers/crypto/vmx/Makefile @@ -2,21 +2,10 @@ obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -override flavour := linux-ppc64le -else -override flavour := linux-ppc64 -endif - -quiet_cmd_perl = PERL $@ - cmd_perl = $(PERL) $(<) $(flavour) > $(@) +quiet_cmd_perl = PERL $@ + cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@ targets += aesp8-ppc.S ghashp8-ppc.S -$(obj)/aesp8-ppc.S: $(src)/aesp8-ppc.pl FORCE - $(call if_changed,perl) - -$(obj)/ghashp8-ppc.S: $(src)/ghashp8-ppc.pl FORCE +$(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE $(call if_changed,perl) - -clean-files := aesp8-ppc.S ghashp8-ppc.S diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c index 5bc5710a6de0..77eca20bc7ac 100644 --- a/drivers/crypto/vmx/ghash.c +++ b/drivers/crypto/vmx/ghash.c @@ -23,6 +23,7 @@ #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/b128ops.h> +#include "aesp8-ppc.h" void gcm_init_p8(u128 htable[16], const u64 Xi[2]); void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]); diff --git a/drivers/crypto/vmx/ghashp8-ppc.pl b/drivers/crypto/vmx/ghashp8-ppc.pl index 09bba1852eec..041e633c214f 100644 --- a/drivers/crypto/vmx/ghashp8-ppc.pl +++ b/drivers/crypto/vmx/ghashp8-ppc.pl @@ -16,7 +16,7 @@ # details see https://www.openssl.org/~appro/cryptogams/. # ==================================================================== # -# GHASH for for PowerISA v2.07. +# GHASH for PowerISA v2.07. # # July 2014 # diff --git a/drivers/crypto/xilinx/Makefile b/drivers/crypto/xilinx/Makefile index 534e32daf76a..730feff5b5f2 100644 --- a/drivers/crypto/xilinx/Makefile +++ b/drivers/crypto/xilinx/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_CRYPTO_DEV_ZYNQMP_AES) += zynqmp-aes-gcm.o +obj-$(CONFIG_CRYPTO_DEV_ZYNQMP_SHA3) += zynqmp-sha.o diff --git a/drivers/crypto/xilinx/zynqmp-sha.c b/drivers/crypto/xilinx/zynqmp-sha.c new file mode 100644 index 000000000000..43ff170ff1c2 --- /dev/null +++ b/drivers/crypto/xilinx/zynqmp-sha.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Xilinx ZynqMP SHA Driver. + * Copyright (c) 2022 Xilinx Inc. + */ +#include <linux/cacheflush.h> +#include <crypto/hash.h> +#include <crypto/internal/hash.h> +#include <crypto/sha3.h> +#include <linux/crypto.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> +#include <linux/firmware/xlnx-zynqmp.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> + +#define ZYNQMP_DMA_BIT_MASK 32U +#define ZYNQMP_DMA_ALLOC_FIXED_SIZE 0x1000U + +enum zynqmp_sha_op { + ZYNQMP_SHA3_INIT = 1, + ZYNQMP_SHA3_UPDATE = 2, + ZYNQMP_SHA3_FINAL = 4, +}; + +struct zynqmp_sha_drv_ctx { + struct shash_alg sha3_384; + struct device *dev; +}; + +struct zynqmp_sha_tfm_ctx { + struct device *dev; + struct crypto_shash *fbk_tfm; +}; + +struct zynqmp_sha_desc_ctx { + struct shash_desc fbk_req; +}; + +static dma_addr_t update_dma_addr, final_dma_addr; +static char *ubuf, *fbuf; + +static int zynqmp_sha_init_tfm(struct crypto_shash *hash) +{ + const char *fallback_driver_name = crypto_shash_alg_name(hash); + struct zynqmp_sha_tfm_ctx *tfm_ctx = crypto_shash_ctx(hash); + struct shash_alg *alg = crypto_shash_alg(hash); + struct crypto_shash *fallback_tfm; + struct zynqmp_sha_drv_ctx *drv_ctx; + + drv_ctx = container_of(alg, struct zynqmp_sha_drv_ctx, sha3_384); + tfm_ctx->dev = drv_ctx->dev; + + /* Allocate a fallback and abort if it failed. */ + fallback_tfm = crypto_alloc_shash(fallback_driver_name, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(fallback_tfm)) + return PTR_ERR(fallback_tfm); + + tfm_ctx->fbk_tfm = fallback_tfm; + hash->descsize += crypto_shash_descsize(tfm_ctx->fbk_tfm); + + return 0; +} + +static void zynqmp_sha_exit_tfm(struct crypto_shash *hash) +{ + struct zynqmp_sha_tfm_ctx *tfm_ctx = crypto_shash_ctx(hash); + + if (tfm_ctx->fbk_tfm) { + crypto_free_shash(tfm_ctx->fbk_tfm); + tfm_ctx->fbk_tfm = NULL; + } + + memzero_explicit(tfm_ctx, sizeof(struct zynqmp_sha_tfm_ctx)); +} + +static int zynqmp_sha_init(struct shash_desc *desc) +{ + struct zynqmp_sha_desc_ctx *dctx = shash_desc_ctx(desc); + struct zynqmp_sha_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + + dctx->fbk_req.tfm = tctx->fbk_tfm; + return crypto_shash_init(&dctx->fbk_req); +} + +static int zynqmp_sha_update(struct shash_desc *desc, const u8 *data, unsigned int length) +{ + struct zynqmp_sha_desc_ctx *dctx = shash_desc_ctx(desc); + + return crypto_shash_update(&dctx->fbk_req, data, length); +} + +static int zynqmp_sha_final(struct shash_desc *desc, u8 *out) +{ + struct zynqmp_sha_desc_ctx *dctx = shash_desc_ctx(desc); + + return crypto_shash_final(&dctx->fbk_req, out); +} + +static int zynqmp_sha_finup(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) +{ + struct zynqmp_sha_desc_ctx *dctx = shash_desc_ctx(desc); + + return crypto_shash_finup(&dctx->fbk_req, data, length, out); +} + +static int zynqmp_sha_import(struct shash_desc *desc, const void *in) +{ + struct zynqmp_sha_desc_ctx *dctx = shash_desc_ctx(desc); + struct zynqmp_sha_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + + dctx->fbk_req.tfm = tctx->fbk_tfm; + return crypto_shash_import(&dctx->fbk_req, in); +} + +static int zynqmp_sha_export(struct shash_desc *desc, void *out) +{ + struct zynqmp_sha_desc_ctx *dctx = shash_desc_ctx(desc); + + return crypto_shash_export(&dctx->fbk_req, out); +} + +static int zynqmp_sha_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) +{ + unsigned int remaining_len = len; + int update_size; + int ret; + + ret = zynqmp_pm_sha_hash(0, 0, ZYNQMP_SHA3_INIT); + if (ret) + return ret; + + while (remaining_len != 0) { + memzero_explicit(ubuf, ZYNQMP_DMA_ALLOC_FIXED_SIZE); + if (remaining_len >= ZYNQMP_DMA_ALLOC_FIXED_SIZE) { + update_size = ZYNQMP_DMA_ALLOC_FIXED_SIZE; + remaining_len -= ZYNQMP_DMA_ALLOC_FIXED_SIZE; + } else { + update_size = remaining_len; + remaining_len = 0; + } + memcpy(ubuf, data, update_size); + flush_icache_range((unsigned long)ubuf, (unsigned long)ubuf + update_size); + ret = zynqmp_pm_sha_hash(update_dma_addr, update_size, ZYNQMP_SHA3_UPDATE); + if (ret) + return ret; + + data += update_size; + } + + ret = zynqmp_pm_sha_hash(final_dma_addr, SHA3_384_DIGEST_SIZE, ZYNQMP_SHA3_FINAL); + memcpy(out, fbuf, SHA3_384_DIGEST_SIZE); + memzero_explicit(fbuf, SHA3_384_DIGEST_SIZE); + + return ret; +} + +static struct zynqmp_sha_drv_ctx sha3_drv_ctx = { + .sha3_384 = { + .init = zynqmp_sha_init, + .update = zynqmp_sha_update, + .final = zynqmp_sha_final, + .finup = zynqmp_sha_finup, + .digest = zynqmp_sha_digest, + .export = zynqmp_sha_export, + .import = zynqmp_sha_import, + .init_tfm = zynqmp_sha_init_tfm, + .exit_tfm = zynqmp_sha_exit_tfm, + .descsize = sizeof(struct zynqmp_sha_desc_ctx), + .statesize = sizeof(struct sha3_state), + .digestsize = SHA3_384_DIGEST_SIZE, + .base = { + .cra_name = "sha3-384", + .cra_driver_name = "zynqmp-sha3-384", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_ALLOCATES_MEMORY | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA3_384_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct zynqmp_sha_tfm_ctx), + .cra_alignmask = 3, + .cra_module = THIS_MODULE, + } + } +}; + +static int zynqmp_sha_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + int err; + u32 v; + + /* Verify the hardware is present */ + err = zynqmp_pm_get_api_version(&v); + if (err) + return err; + + + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(ZYNQMP_DMA_BIT_MASK)); + if (err < 0) { + dev_err(dev, "No usable DMA configuration\n"); + return err; + } + + err = crypto_register_shash(&sha3_drv_ctx.sha3_384); + if (err < 0) { + dev_err(dev, "Failed to register shash alg.\n"); + return err; + } + + sha3_drv_ctx.dev = dev; + platform_set_drvdata(pdev, &sha3_drv_ctx); + + ubuf = dma_alloc_coherent(dev, ZYNQMP_DMA_ALLOC_FIXED_SIZE, &update_dma_addr, GFP_KERNEL); + if (!ubuf) { + err = -ENOMEM; + goto err_shash; + } + + fbuf = dma_alloc_coherent(dev, SHA3_384_DIGEST_SIZE, &final_dma_addr, GFP_KERNEL); + if (!fbuf) { + err = -ENOMEM; + goto err_mem; + } + + return 0; + +err_mem: + dma_free_coherent(sha3_drv_ctx.dev, ZYNQMP_DMA_ALLOC_FIXED_SIZE, ubuf, update_dma_addr); + +err_shash: + crypto_unregister_shash(&sha3_drv_ctx.sha3_384); + + return err; +} + +static int zynqmp_sha_remove(struct platform_device *pdev) +{ + sha3_drv_ctx.dev = platform_get_drvdata(pdev); + + dma_free_coherent(sha3_drv_ctx.dev, ZYNQMP_DMA_ALLOC_FIXED_SIZE, ubuf, update_dma_addr); + dma_free_coherent(sha3_drv_ctx.dev, SHA3_384_DIGEST_SIZE, fbuf, final_dma_addr); + crypto_unregister_shash(&sha3_drv_ctx.sha3_384); + + return 0; +} + +static struct platform_driver zynqmp_sha_driver = { + .probe = zynqmp_sha_probe, + .remove = zynqmp_sha_remove, + .driver = { + .name = "zynqmp-sha3-384", + }, +}; + +module_platform_driver(zynqmp_sha_driver); +MODULE_DESCRIPTION("ZynqMP SHA3 hardware acceleration support."); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Harsha <harsha.harsha@xilinx.com>"); |