Merge tag 'v5.19-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:

   - Test in-place en/decryption with two sglists in testmgr

   - Fix process vs softirq race in cryptd

  Algorithms:

   - Add arm64 acceleration for sm4

   - Add s390 acceleration for chacha20

  Drivers:

   - Add polarfire soc hwrng support in mpsf

   - Add support for TI SoC AM62x in sa2ul

   - Add support for ATSHA204 cryptochip in atmel-sha204a

   - Add support for PRNG in caam

   - Restore support for storage encryption in qat

   - Restore support for storage encryption in hisilicon/sec"

* tag 'v5.19-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (116 commits)
  hwrng: omap3-rom - fix using wrong clk_disable() in omap_rom_rng_runtime_resume()
  crypto: hisilicon/sec - delete the flag CRYPTO_ALG_ALLOCATES_MEMORY
  crypto: qat - add support for 401xx devices
  crypto: qat - re-enable registration of algorithms
  crypto: qat - honor CRYPTO_TFM_REQ_MAY_SLEEP flag
  crypto: qat - add param check for DH
  crypto: qat - add param check for RSA
  crypto: qat - remove dma_free_coherent() for DH
  crypto: qat - remove dma_free_coherent() for RSA
  crypto: qat - fix memory leak in RSA
  crypto: qat - add backlog mechanism
  crypto: qat - refactor submission logic
  crypto: qat - use pre-allocated buffers in datapath
  crypto: qat - set to zero DH parameters before free
  crypto: s390 - add crypto library interface for ChaCha20
  crypto: talitos - Uniform coding style with defined variable
  crypto: octeontx2 - simplify the return expression of otx2_cpt_aead_cbc_aes_sha_setkey()
  crypto: cryptd - Protect per-CPU resource by disabling BH.
  crypto: sun8i-ce - do not fallback if cryptlen is less than sg length
  crypto: sun8i-ce - rework debugging
  ...

83 files changed, 2743 insertions, 898 deletions

diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index a087156a5818..b3f2d55dc551 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -385,6 +385,19 @@ config HW_RANDOM_PIC32
 
 	  If unsure, say Y.
 
+config HW_RANDOM_POLARFIRE_SOC
+	tristate "Microchip PolarFire SoC Random Number Generator support"
+	depends on HW_RANDOM && POLARFIRE_SOC_SYS_CTRL
+	help
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on PolarFire SoC (MPFS).
+
+	  To compile this driver as a module, choose M here. The
+	  module will be called mfps_rng.
+
+	  If unsure, say N.
+
+
 config HW_RANDOM_MESON
 	tristate "Amlogic Meson Random Number Generator support"
 	depends on HW_RANDOM
@@ -527,7 +540,7 @@ config HW_RANDOM_ARM_SMCCC_TRNG
 
 config HW_RANDOM_CN10K
        tristate "Marvell CN10K Random Number Generator support"
-       depends on HW_RANDOM && PCI && ARM64
+       depends on HW_RANDOM && PCI && (ARM64 || (64BIT && COMPILE_TEST))
        default HW_RANDOM
        help
 	 This driver provides support for the True Random Number
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 584d47ba32f7..3e948cf04476 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -46,3 +46,4 @@ obj-$(CONFIG_HW_RANDOM_CCTRNG) += cctrng.o
 obj-$(CONFIG_HW_RANDOM_XIPHERA) += xiphera-trng.o
 obj-$(CONFIG_HW_RANDOM_ARM_SMCCC_TRNG) += arm_smccc_trng.o
 obj-$(CONFIG_HW_RANDOM_CN10K) += cn10k-rng.o
+obj-$(CONFIG_HW_RANDOM_POLARFIRE_SOC) += mpfs-rng.o
diff --git a/drivers/char/hw_random/cn10k-rng.c b/drivers/char/hw_random/cn10k-rng.c
index 35001c63648b..a01e9307737c 100644
--- a/drivers/char/hw_random/cn10k-rng.c
+++ b/drivers/char/hw_random/cn10k-rng.c
@@ -31,26 +31,23 @@ struct cn10k_rng {
 
 #define PLAT_OCTEONTX_RESET_RNG_EBG_HEALTH_STATE     0xc2000b0f
 
-static int reset_rng_health_state(struct cn10k_rng *rng)
+static unsigned long reset_rng_health_state(struct cn10k_rng *rng)
 {
 	struct arm_smccc_res res;
 
 	/* Send SMC service call to reset EBG health state */
 	arm_smccc_smc(PLAT_OCTEONTX_RESET_RNG_EBG_HEALTH_STATE, 0, 0, 0, 0, 0, 0, 0, &res);
-	if (res.a0 != 0UL)
-		return -EIO;
-
-	return 0;
+	return res.a0;
 }
 
 static int check_rng_health(struct cn10k_rng *rng)
 {
 	u64 status;
-	int err;
+	unsigned long err;
 
 	/* Skip checking health */
 	if (!rng->reg_base)
-		return 0;
+		return -ENODEV;
 
 	status = readq(rng->reg_base + RNM_PF_EBG_HEALTH);
 	if (status & BIT_ULL(20)) {
@@ -58,7 +55,9 @@ static int check_rng_health(struct cn10k_rng *rng)
 		if (err) {
 			dev_err(&rng->pdev->dev, "HWRNG: Health test failed (status=%llx)\n",
 					status);
-			dev_err(&rng->pdev->dev, "HWRNG: error during reset\n");
+			dev_err(&rng->pdev->dev, "HWRNG: error during reset (error=%lx)\n",
+					err);
+			return -EIO;
 		}
 	}
 	return 0;
@@ -90,6 +89,7 @@ static int cn10k_rng_read(struct hwrng *hwrng, void *data,
 {
 	struct cn10k_rng *rng = (struct cn10k_rng *)hwrng->priv;
 	unsigned int size;
+	u8 *pos = data;
 	int err = 0;
 	u64 value;
 
@@ -102,17 +102,20 @@ static int cn10k_rng_read(struct hwrng *hwrng, void *data,
 	while (size >= 8) {
 		cn10k_read_trng(rng, &value);
 
-		*((u64 *)data) = (u64)value;
+		*((u64 *)pos) = value;
 		size -= 8;
-		data += 8;
+		pos += 8;
 	}
 
-	while (size > 0) {
+	if (size > 0) {
 		cn10k_read_trng(rng, &value);
 
-		*((u8 *)data) = (u8)value;
-		size--;
-		data++;
+		while (size > 0) {
+			*pos = (u8)value;
+			value >>= 8;
+			size--;
+			pos++;
+		}
 	}
 
 	return max - size;
diff --git a/drivers/char/hw_random/mpfs-rng.c b/drivers/char/hw_random/mpfs-rng.c
new file mode 100644
index 000000000000..5813da617a48
--- /dev/null
+++ b/drivers/char/hw_random/mpfs-rng.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microchip PolarFire SoC (MPFS) hardware random driver
+ *
+ * Copyright (c) 2020-2022 Microchip Corporation. All rights reserved.
+ *
+ * Author: Conor Dooley <conor.dooley@microchip.com>
+ */
+
+#include <linux/module.h>
+#include <linux/hw_random.h>
+#include <linux/platform_device.h>
+#include <soc/microchip/mpfs.h>
+
+#define CMD_OPCODE	0x21
+#define CMD_DATA_SIZE	0U
+#define CMD_DATA	NULL
+#define MBOX_OFFSET	0U
+#define RESP_OFFSET	0U
+#define RNG_RESP_BYTES	32U
+
+struct mpfs_rng {
+	struct mpfs_sys_controller *sys_controller;
+	struct hwrng rng;
+};
+
+static int mpfs_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct mpfs_rng *rng_priv = container_of(rng, struct mpfs_rng, rng);
+	u32 response_msg[RNG_RESP_BYTES / sizeof(u32)];
+	unsigned int count = 0, copy_size_bytes;
+	int ret;
+
+	struct mpfs_mss_response response = {
+		.resp_status = 0U,
+		.resp_msg = (u32 *)response_msg,
+		.resp_size = RNG_RESP_BYTES
+	};
+	struct mpfs_mss_msg msg = {
+		.cmd_opcode = CMD_OPCODE,
+		.cmd_data_size = CMD_DATA_SIZE,
+		.response = &response,
+		.cmd_data = CMD_DATA,
+		.mbox_offset = MBOX_OFFSET,
+		.resp_offset = RESP_OFFSET
+	};
+
+	while (count < max) {
+		ret = mpfs_blocking_transaction(rng_priv->sys_controller, &msg);
+		if (ret)
+			return ret;
+
+		copy_size_bytes = max - count > RNG_RESP_BYTES ? RNG_RESP_BYTES : max - count;
+		memcpy(buf + count, response_msg, copy_size_bytes);
+
+		count += copy_size_bytes;
+		if (!wait)
+			break;
+	}
+
+	return count;
+}
+
+static int mpfs_rng_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mpfs_rng *rng_priv;
+	int ret;
+
+	rng_priv = devm_kzalloc(dev, sizeof(*rng_priv), GFP_KERNEL);
+	if (!rng_priv)
+		return -ENOMEM;
+
+	rng_priv->sys_controller =  mpfs_sys_controller_get(&pdev->dev);
+	if (IS_ERR(rng_priv->sys_controller))
+		return dev_err_probe(dev, PTR_ERR(rng_priv->sys_controller),
+				     "Failed to register system controller hwrng sub device\n");
+
+	rng_priv->rng.read = mpfs_rng_read;
+	rng_priv->rng.name = pdev->name;
+	rng_priv->rng.quality = 1024;
+
+	platform_set_drvdata(pdev, rng_priv);
+
+	ret = devm_hwrng_register(&pdev->dev, &rng_priv->rng);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to register MPFS hwrng\n");
+
+	dev_info(&pdev->dev, "Registered MPFS hwrng\n");
+
+	return 0;
+}
+
+static struct platform_driver mpfs_rng_driver = {
+	.driver = {
+		.name = "mpfs-rng",
+	},
+	.probe = mpfs_rng_probe,
+};
+module_platform_driver(mpfs_rng_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Conor Dooley <conor.dooley@microchip.com>");
+MODULE_DESCRIPTION("PolarFire SoC (MPFS) hardware random driver");
diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c
index e0d77fa048fb..f06e4f95114f 100644
--- a/drivers/char/hw_random/omap3-rom-rng.c
+++ b/drivers/char/hw_random/omap3-rom-rng.c
@@ -92,7 +92,7 @@ static int __maybe_unused omap_rom_rng_runtime_resume(struct device *dev)
 
 	r = ddata->rom_rng_call(0, 0, RNG_GEN_PRNG_HW_INIT);
 	if (r != 0) {
-		clk_disable(ddata->clk);
+		clk_disable_unprepare(ddata->clk);
 		dev_err(dev, "HW init failed: %d\n", r);
 
 		return -EIO;
diff --git a/drivers/char/hw_random/optee-rng.c b/drivers/char/hw_random/optee-rng.c
index a948c0727b2b..96b5d546d136 100644
--- a/drivers/char/hw_random/optee-rng.c
+++ b/drivers/char/hw_random/optee-rng.c
@@ -115,7 +115,7 @@ static size_t get_optee_rng_data(struct optee_rng_private *pvt_data,
 static int optee_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
 {
 	struct optee_rng_private *pvt_data = to_optee_rng_private(rng);
-	size_t read = 0, rng_size = 0;
+	size_t read = 0, rng_size;
 	int timeout = 1;
 	u8 *data = buf;
 
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 7b2d138bc83e..ee99c02c84e8 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -216,9 +216,9 @@ config CRYPTO_AES_S390
 config CRYPTO_CHACHA_S390
 	tristate "ChaCha20 stream cipher"
 	depends on S390
-	select CRYPTO_ALGAPI
 	select CRYPTO_SKCIPHER
-	select CRYPTO_CHACHA20
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
 	help
 	  This is the s390 SIMD implementation of the ChaCha20 stream
 	  cipher (RFC 7539).
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 0a4fff23d272..f81703a86b98 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_CRYPTO_DEV_ALLWINNER) += allwinner/
 obj-$(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
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.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 35e3cadccac2..74b4e910a38d 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -25,26 +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;
@@ -94,6 +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);
 
@@ -152,23 +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");
@@ -179,8 +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;
@@ -188,15 +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;
@@ -241,14 +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:
@@ -257,16 +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:
@@ -322,13 +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);
@@ -398,10 +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 859b7522faaa..8b5b9b9d04c3 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -50,9 +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;
@@ -199,17 +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;
@@ -229,7 +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);
 
@@ -248,6 +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);
@@ -266,14 +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;
@@ -318,7 +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;
@@ -348,44 +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);
@@ -406,8 +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);
 
 
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.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 554e400d41ca..5bb950182026 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
@@ -22,34 +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);
 	}
 
@@ -93,6 +112,68 @@ 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);
+	}
+	return err;
+}
+
 static int sun8i_ss_cipher(struct skcipher_request *areq)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
@@ -101,12 +182,14 @@ 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);
@@ -134,34 +217,12 @@ 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;
@@ -169,15 +230,13 @@ 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;
@@ -233,31 +292,26 @@ 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);
 		}
 	}
 
@@ -349,9 +403,9 @@ 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 319fe3279a71..98593a0cff69 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
@@ -66,6 +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;
 
@@ -104,15 +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);
 			}
 		}
 
@@ -409,6 +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
 };
 
@@ -430,6 +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",
@@ -442,6 +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;
 		}
 	}
@@ -464,7 +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);
@@ -474,6 +526,28 @@ 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)
+			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])
+				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)
+			goto error_engine;
+		ss->flows[i].result = devm_kmalloc(ss->dev, SHA256_DIGEST_SIZE,
+						   GFP_KERNEL | GFP_DMA);
+		if (!ss->flows[i].result)
+			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 1a71ed49d233..ac417a6b39e5 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
@@ -14,11 +14,99 @@
 #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 (!xtfm)
+		return -ENOMEM;
+
+	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);
@@ -50,9 +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;
@@ -67,6 +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);
 }
@@ -258,23 +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;
@@ -288,21 +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;
 
@@ -313,6 +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
  */
@@ -320,20 +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;
@@ -342,18 +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;
@@ -376,17 +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);
@@ -394,55 +571,135 @@ 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);
+		if (dma_mapping_error(ss->dev, addr_xpad)) {
+			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);
+		if (dma_mapping_error(ss->dev, addr_xpad)) {
+			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();
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/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index 333fbefbbccb..59a57279e77b 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -398,7 +398,7 @@ 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-sha204a.c b/drivers/crypto/atmel-sha204a.c
index c96c14e7dab1..e4087bdd2475 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -121,23 +121,24 @@ static int 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 0;
 	}
 
-	if (i2c_priv->hwrng.priv)
-		kfree((void *)i2c_priv->hwrng.priv);
+	kfree((void *)i2c_priv->hwrng.priv);
 
 	return 0;
 }
 
 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 +160,7 @@ 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/caam/Kconfig b/drivers/crypto/caam/Kconfig
index ea9f8b1ae981..ec6a9e6ad4d2 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -151,6 +151,14 @@ 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
 
diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile
index 25f7ae5a4642..acf1b197eb84 100644
--- a/drivers/crypto/caam/Makefile
+++ b/drivers/crypto/caam/Makefile
@@ -20,6 +20,7 @@ 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
 
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 38c4d88a9d03..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)
 {
@@ -868,6 +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",
@@ -884,6 +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 e92210e2ab76..572cf66c887a 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -186,6 +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/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/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 6ab93dfd478a..799b476fc3e8 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;
@@ -181,7 +207,7 @@ 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);
 
@@ -217,7 +243,7 @@ static void sev_write_init_ex_file(void)
 	if (!sev_init_ex_buffer)
 		return;
 
-	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)) {
 		dev_err(sev->dev,
 			"SEV: could not open file for write, error %ld\n",
@@ -435,7 +461,7 @@ 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)
diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index 88c672ad27e4..b5970ae54d0e 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;
@@ -391,6 +452,7 @@ 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/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
index 11e0278c8631..6140e4927322 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.c
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -356,12 +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));
 	}
 }
 
@@ -377,6 +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;
@@ -399,7 +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;
@@ -416,7 +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)
@@ -456,6 +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,
@@ -514,13 +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 &&
@@ -843,7 +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);
@@ -1056,7 +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_driver.c b/drivers/crypto/ccree/cc_driver.c
index 790fa9058a36..7d1bee86d581 100644
--- a/drivers/crypto/ccree/cc_driver.c
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -529,24 +529,26 @@ 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 +560,10 @@ 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 +595,8 @@ 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/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_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index 36ab30e9e654..9d529df0eab9 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
@@ -107,6 +113,15 @@
 #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
+
 static const char hpre_name[] = "hisi_hpre";
 static struct dentry *hpre_debugfs_root;
 static const struct pci_device_id hpre_dev_ids[] = {
@@ -192,28 +207,32 @@ 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] = {
@@ -226,6 +245,53 @@ 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,
+	},
+};
+
+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,
@@ -779,24 +845,6 @@ 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)
 {
@@ -895,6 +943,7 @@ 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;
@@ -906,6 +955,10 @@ 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)
@@ -918,6 +971,13 @@ 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 == PCI_DEVICE_ID_HUAWEI_HPRE_PF) {
@@ -931,12 +991,16 @@ 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);
 }
 
@@ -969,6 +1033,82 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 	return hisi_qm_init(qm);
 }
 
+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)
 {
 	const struct hpre_hw_error *err = hpre_hw_errors;
@@ -1027,6 +1167,7 @@ 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,
 };
 
@@ -1044,8 +1185,11 @@ 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)
@@ -1131,6 +1275,7 @@ 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:
@@ -1161,6 +1306,7 @@ 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);
 	}
 
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 009132333d2b..b4ca2eb034d7 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -253,7 +253,15 @@
 #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) \
@@ -467,6 +475,23 @@ 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",
 };
@@ -687,13 +712,13 @@ 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))
@@ -982,7 +1007,7 @@ 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)
@@ -1625,6 +1650,156 @@ 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)
 {
@@ -2660,7 +2835,7 @@ 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;
@@ -2678,7 +2853,6 @@ 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.
@@ -2686,7 +2860,7 @@ 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;
 
@@ -2704,7 +2878,6 @@ 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)
 {
@@ -3053,9 +3226,17 @@ 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)
@@ -3367,24 +3548,6 @@ 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;
@@ -3498,6 +3661,17 @@ static void hisi_qm_set_state(struct hisi_qm *qm, u8 state)
 		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;
+}
+
 /**
  * hisi_qm_uninit() - Uninitialize qm.
  * @qm: The qm needed uninit.
@@ -3509,6 +3683,8 @@ 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);
 	down_write(&qm->qps_lock);
@@ -3550,7 +3726,7 @@ 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;
@@ -3562,7 +3738,6 @@ 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.
@@ -4484,6 +4659,7 @@ 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;
@@ -4499,6 +4675,10 @@ 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);
@@ -5181,6 +5361,24 @@ 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;
@@ -5196,6 +5394,10 @@ 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);
@@ -5906,6 +6108,26 @@ err_alloc_qdma:
 	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.
@@ -5958,6 +6180,8 @@ int hisi_qm_init(struct hisi_qm *qm)
 	qm_cmd_init(qm);
 	atomic_set(&qm->status.flags, QM_INIT);
 
+	qm_last_regs_init(qm);
+
 	return 0;
 
 err_alloc_uacce:
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index a91635c348b5..6eebe739893c 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -2113,7 +2113,6 @@ 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),\
@@ -2366,7 +2365,6 @@ 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),\
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index 92fae706bdb2..4d85d2cbf376 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -110,6 +110,15 @@
 #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
+
 struct sec_hw_error {
 	u32 int_msk;
 	const char *msg;
@@ -226,6 +235,34 @@ 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, PCI_DEVICE_ID_HUAWEI_SEC_PF);
@@ -729,6 +766,7 @@ 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;
@@ -749,6 +787,9 @@ static int sec_core_debug_init(struct hisi_qm *qm)
 
 	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 +
@@ -790,6 +831,14 @@ 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);
@@ -799,15 +848,66 @@ 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;
@@ -874,6 +974,7 @@ 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,
 };
 
@@ -892,8 +993,11 @@ 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 0;
+	return ret;
 }
 
 static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
@@ -1067,6 +1171,7 @@ 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);
@@ -1091,6 +1196,7 @@ 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);
 
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index f7efc02b065f..2b6f2281cfd6 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -1,5 +1,6 @@
 // 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>
@@ -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/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c
index 9520a4113c81..67869513e48c 100644
--- a/drivers/crypto/hisilicon/zip/zip_crypto.c
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.c
@@ -521,7 +521,7 @@ static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx,
 static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx)
 {
 	hisi_qm_stop_qp(ctx->qp);
-	hisi_qm_release_qp(ctx->qp);
+	hisi_qm_free_qps(&ctx->qp, 1);
 }
 
 static const struct hisi_zip_sqe_ops hisi_zip_ops_v1 = {
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index 4534e1e107d1..9c925e9c0a2d 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -49,14 +49,18 @@
 
 #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
@@ -230,6 +234,64 @@ 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,
@@ -621,6 +683,7 @@ 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;
@@ -634,6 +697,10 @@ 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)
@@ -666,6 +733,13 @@ 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) {
@@ -679,6 +753,8 @@ 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;
 }
@@ -703,6 +779,8 @@ 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) {
@@ -711,6 +789,87 @@ 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;
+	int i, j, idx;
+
+	debug->last_words = kcalloc(core_dfx_regs_num * HZIP_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 < HZIP_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);
+	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);
+	}
+
+	for (i = 0; i < HZIP_CORE_NUM; i++) {
+		if (i < HZIP_COMP_CORE_NUM)
+			scnprintf(buf, sizeof(buf), "Comp_core-%d", i);
+		else
+			scnprintf(buf, sizeof(buf), "Decomp_core-%d",
+				  i - HZIP_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;
@@ -798,6 +957,7 @@ 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,
 };
 
@@ -805,6 +965,7 @@ 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)
@@ -820,7 +981,11 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
 	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)
@@ -964,6 +1129,7 @@ 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:
@@ -985,6 +1151,7 @@ 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);
 }
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 9ff885d50edf..9b1a158aec29 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1997,3 +1997,12 @@ 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/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/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/octeontx2/otx2_cptvf_algs.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c
index f8f8542ce3e4..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,
diff --git a/drivers/crypto/qat/qat_4xxx/adf_drv.c b/drivers/crypto/qat/qat_4xxx/adf_drv.c
index fa4c350c1bf9..181fa1c8b3c7 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);
@@ -75,13 +76,6 @@ static int adf_crypto_dev_config(struct adf_accel_dev *accel_dev)
 	if (ret)
 		goto err;
 
-	/* Temporarily set the number of crypto instances to zero to avoid
-	 * registering the crypto algorithms.
-	 * This will be removed when the algorithms will support the
-	 * CRYPTO_TFM_REQ_MAY_BACKLOG flag
-	 */
-	instances = 0;
-
 	for (i = 0; i < instances; i++) {
 		val = i;
 		bank = i * 2;
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 f25a6c8edfc7..04f058acc4d3 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -16,6 +16,7 @@ intel_qat-objs := adf_cfg.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 a03c6cf72331..ede6458c9dbf 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,
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index e8c9b77c0d66..0464fa257929 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -195,10 +195,8 @@ 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);
@@ -217,14 +215,6 @@ 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;
@@ -243,10 +233,6 @@ 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_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_pfvf.c b/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c
index d80d493a7756..8e8efe93f3ee 100644
--- a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c
+++ b/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c
@@ -15,6 +15,7 @@
 /* VF2PF interrupt source registers */
 #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
@@ -36,32 +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)
 {
-	u32 sou, mask;
+	u32 val;
 
-	sou = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_SOU);
-	mask = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK);
-
-	return sou & ~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)
 {
-	unsigned int val;
-
-	val = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK) & ~vf_mask;
-	ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, 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)
 {
-	unsigned int val;
+	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, ADF_4XXX_VM2PF_MSK) | vf_mask;
-	ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, val);
+	/* Return the sources of the (new) interrupt(s) */
+	return pending;
 }
 
 static int adf_gen4_pfvf_send(struct adf_accel_dev *accel_dev,
@@ -96,10 +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
@@ -115,9 +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_isr.c b/drivers/crypto/qat/qat_common/adf_isr.c
index a35149f8bf1e..ad9e135b8560 100644
--- a/drivers/crypto/qat/qat_common/adf_isr.c
+++ b/drivers/crypto/qat/qat_common/adf_isr.c
@@ -66,42 +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.
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_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c
index b960bca1f9d2..f38b2ffde146 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
@@ -104,22 +102,18 @@ 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;
@@ -176,7 +170,7 @@ 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) {
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_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/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index f998ed58457c..148edbe379e3 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 {
@@ -693,7 +680,10 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 				 bl->bufers[i].len, DMA_BIDIRECTIONAL);
 
 	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;
@@ -704,14 +694,17 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 					 DMA_BIDIRECTIONAL);
 		}
 		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 +714,24 @@ 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));
 
 	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;
+	}
 
 	for_each_sg(sgl, sg, n, i)
 		bufl->bufers[i].addr = DMA_MAPPING_ERROR;
@@ -760,12 +762,18 @@ 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)
@@ -810,7 +818,9 @@ err_out:
 			dma_unmap_single(dev, buflout->bufers[i].addr,
 					 buflout->bufers[i].len,
 					 DMA_BIDIRECTIONAL);
-	kfree(buflout);
+
+	if (!qat_req->buf.sgl_dst_valid)
+		kfree(buflout);
 
 err_in:
 	if (!dma_mapping_error(dev, blp))
@@ -823,7 +833,8 @@ err_in:
 					 bufl->bufers[i].len,
 					 DMA_BIDIRECTIONAL);
 
-	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 +936,25 @@ 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 +967,15 @@ 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 +994,12 @@ 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 +1010,15 @@ 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 +1040,11 @@ 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,
@@ -1173,13 +1196,14 @@ 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 +1222,11 @@ 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 +1262,14 @@ 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 +1289,11 @@ 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..16d97db9ea15 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
@@ -302,20 +316,18 @@ 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;
@@ -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;
 	}
@@ -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);
@@ -679,40 +694,39 @@ 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,
@@ -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);
@@ -823,40 +838,37 @@ 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;
@@ -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;
 }
 
@@ -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 67c9588e89df..9341d892533a 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.c
+++ b/drivers/crypto/qat/qat_common/qat_crypto.c
@@ -161,13 +161,6 @@ int qat_crypto_dev_config(struct adf_accel_dev *accel_dev)
 	if (ret)
 		goto err;
 
-	/* Temporarily set the number of crypto instances to zero to avoid
-	 * registering the crypto algorithms.
-	 * This will be removed when the algorithms will support the
-	 * CRYPTO_TFM_REQ_MAY_BACKLOG flag
-	 */
-	instances = 0;
-
 	for (i = 0; i < instances; i++) {
 		val = i;
 		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_BANK_NUM, i);
@@ -353,6 +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 6356402a2c9e..0fe5a474aa45 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -519,7 +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)
 {
@@ -731,6 +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",
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/sa2ul.c b/drivers/crypto/sa2ul.c
index 51b58e57153f..6957a125b447 100644
--- a/drivers/crypto/sa2ul.c
+++ b/drivers/crypto/sa2ul.c
@@ -2379,6 +2379,7 @@ 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);
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/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 5157c118d642..265ef3e96fdd 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -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,
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