Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 912 insertions, 0 deletions

diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
new file mode 100644
index 000000000..c9dc06f97
--- /dev/null
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
@@ -0,0 +1,912 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sun8i-ss-core.c - hardware cryptographic offloader for
+ * Allwinner A80/A83T SoC
+ *
+ * Copyright (C) 2015-2019 Corentin Labbe <clabbe.montjoie@gmail.com>
+ *
+ * Core file which registers crypto algorithms supported by the SecuritySystem
+ *
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
+ */
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <crypto/internal/rng.h>
+#include <crypto/internal/skcipher.h>
+
+#include "sun8i-ss.h"
+
+static const struct ss_variant ss_a80_variant = {
+	.alg_cipher = { SS_ALG_AES, SS_ALG_DES, SS_ALG_3DES,
+	},
+	.alg_hash = { SS_ID_NOTSUPP, SS_ID_NOTSUPP, SS_ID_NOTSUPP, SS_ID_NOTSUPP,
+	},
+	.op_mode = { SS_OP_ECB, SS_OP_CBC,
+	},
+	.ss_clks = {
+		{ "bus", 0, 300 * 1000 * 1000 },
+		{ "mod", 0, 300 * 1000 * 1000 },
+	}
+};
+
+static const struct ss_variant ss_a83t_variant = {
+	.alg_cipher = { SS_ALG_AES, SS_ALG_DES, SS_ALG_3DES,
+	},
+	.alg_hash = { SS_ALG_MD5, SS_ALG_SHA1, SS_ALG_SHA224, SS_ALG_SHA256,
+	},
+	.op_mode = { SS_OP_ECB, SS_OP_CBC,
+	},
+	.ss_clks = {
+		{ "bus", 0, 300 * 1000 * 1000 },
+		{ "mod", 0, 300 * 1000 * 1000 },
+	}
+};
+
+/*
+ * sun8i_ss_get_engine_number() get the next channel slot
+ * This is a simple round-robin way of getting the next channel
+ */
+int sun8i_ss_get_engine_number(struct sun8i_ss_dev *ss)
+{
+	return atomic_inc_return(&ss->flow) % MAXFLOW;
+}
+
+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;
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	ss->flows[flow].stat_req++;
+#endif
+
+	/* choose between stream0/stream1 */
+	if (flow)
+		v |= SS_FLOW1;
+	else
+		v |= SS_FLOW0;
+
+	v |= rctx->op_mode;
+	v |= rctx->method;
+
+	if (rctx->op_dir)
+		v |= SS_DECRYPTION;
+
+	switch (rctx->keylen) {
+	case 128 / 8:
+		v |= SS_AES_128BITS << 7;
+		break;
+	case 192 / 8:
+		v |= SS_AES_192BITS << 7;
+		break;
+	case 256 / 8:
+		v |= SS_AES_256BITS << 7;
+		break;
+	}
+
+	for (i = 0; i < MAX_SG; i++) {
+		if (!rctx->t_dst[i].addr)
+			break;
+
+		mutex_lock(&ss->mlock);
+		writel(rctx->p_key, ss->base + SS_KEY_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_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);
+			}
+		}
+
+		dev_dbg(ss->dev,
+			"Processing SG %d on flow %d %s ctl=%x %d to %d method=%x opmode=%x opdir=%x srclen=%d\n",
+			i, flow, name, v,
+			rctx->t_src[i].len, rctx->t_dst[i].len,
+			rctx->method, rctx->op_mode,
+			rctx->op_dir, rctx->t_src[i].len);
+
+		writel(rctx->t_src[i].addr, ss->base + SS_SRC_ADR_REG);
+		writel(rctx->t_dst[i].addr, ss->base + SS_DST_ADR_REG);
+		writel(rctx->t_src[i].len, ss->base + SS_LEN_ADR_REG);
+
+		reinit_completion(&ss->flows[flow].complete);
+		ss->flows[flow].status = 0;
+		wmb();
+
+		writel(v, ss->base + SS_CTL_REG);
+		mutex_unlock(&ss->mlock);
+		wait_for_completion_interruptible_timeout(&ss->flows[flow].complete,
+							  msecs_to_jiffies(2000));
+		if (ss->flows[flow].status == 0) {
+			dev_err(ss->dev, "DMA timeout for %s\n", name);
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+static irqreturn_t ss_irq_handler(int irq, void *data)
+{
+	struct sun8i_ss_dev *ss = (struct sun8i_ss_dev *)data;
+	int flow = 0;
+	u32 p;
+
+	p = readl(ss->base + SS_INT_STA_REG);
+	for (flow = 0; flow < MAXFLOW; flow++) {
+		if (p & (BIT(flow))) {
+			writel(BIT(flow), ss->base + SS_INT_STA_REG);
+			ss->flows[flow].status = 1;
+			complete(&ss->flows[flow].complete);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct sun8i_ss_alg_template ss_algs[] = {
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_AES,
+	.ss_blockmode = SS_ID_OP_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "cbc-aes-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY |
+				CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= sun8i_ss_aes_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_AES,
+	.ss_blockmode = SS_ID_OP_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "ecb-aes-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY |
+				CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.setkey		= sun8i_ss_aes_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_DES3,
+	.ss_blockmode = SS_ID_OP_CBC,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "cbc-des3-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY |
+				CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.setkey		= sun8i_ss_des3_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+{
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+	.ss_algo_id = SS_ID_CIPHER_DES3,
+	.ss_blockmode = SS_ID_OP_ECB,
+	.alg.skcipher = {
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "ecb-des3-sun8i-ss",
+			.cra_priority = 400,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY |
+				CRYPTO_ALG_NEED_FALLBACK,
+			.cra_ctxsize = sizeof(struct sun8i_cipher_tfm_ctx),
+			.cra_module = THIS_MODULE,
+			.cra_alignmask = 0xf,
+			.cra_init = sun8i_ss_cipher_init,
+			.cra_exit = sun8i_ss_cipher_exit,
+		},
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+		.setkey		= sun8i_ss_des3_setkey,
+		.encrypt	= sun8i_ss_skencrypt,
+		.decrypt	= sun8i_ss_skdecrypt,
+	}
+},
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_PRNG
+{
+	.type = CRYPTO_ALG_TYPE_RNG,
+	.alg.rng = {
+		.base = {
+			.cra_name		= "stdrng",
+			.cra_driver_name	= "sun8i-ss-prng",
+			.cra_priority		= 300,
+			.cra_ctxsize = sizeof(struct sun8i_ss_rng_tfm_ctx),
+			.cra_module		= THIS_MODULE,
+			.cra_init		= sun8i_ss_prng_init,
+			.cra_exit		= sun8i_ss_prng_exit,
+		},
+		.generate               = sun8i_ss_prng_generate,
+		.seed                   = sun8i_ss_prng_seed,
+		.seedsize               = PRNG_SEED_SIZE,
+	}
+},
+#endif
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_HASH
+{	.type = CRYPTO_ALG_TYPE_AHASH,
+	.ss_algo_id = SS_ID_HASH_MD5,
+	.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,
+		.halg = {
+			.digestsize = MD5_DIGEST_SIZE,
+			.statesize = sizeof(struct md5_state),
+			.base = {
+				.cra_name = "md5",
+				.cra_driver_name = "md5-sun8i-ss",
+				.cra_priority = 300,
+				.cra_alignmask = 3,
+				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
+					CRYPTO_ALG_ASYNC |
+					CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = MD5_HMAC_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,
+			}
+		}
+	}
+},
+{	.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,
+		.halg = {
+			.digestsize = SHA1_DIGEST_SIZE,
+			.statesize = sizeof(struct sha1_state),
+			.base = {
+				.cra_name = "sha1",
+				.cra_driver_name = "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,
+			}
+		}
+	}
+},
+{	.type = CRYPTO_ALG_TYPE_AHASH,
+	.ss_algo_id = SS_ID_HASH_SHA224,
+	.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,
+		.halg = {
+			.digestsize = SHA224_DIGEST_SIZE,
+			.statesize = sizeof(struct sha256_state),
+			.base = {
+				.cra_name = "sha224",
+				.cra_driver_name = "sha224-sun8i-ss",
+				.cra_priority = 300,
+				.cra_alignmask = 3,
+				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
+					CRYPTO_ALG_ASYNC |
+					CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA224_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,
+			}
+		}
+	}
+},
+{	.type = CRYPTO_ALG_TYPE_AHASH,
+	.ss_algo_id = SS_ID_HASH_SHA256,
+	.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,
+		.halg = {
+			.digestsize = SHA256_DIGEST_SIZE,
+			.statesize = sizeof(struct sha256_state),
+			.base = {
+				.cra_name = "sha256",
+				.cra_driver_name = "sha256-sun8i-ss",
+				.cra_priority = 300,
+				.cra_alignmask = 3,
+				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
+					CRYPTO_ALG_ASYNC |
+					CRYPTO_ALG_NEED_FALLBACK,
+				.cra_blocksize = SHA256_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,
+			}
+		}
+	}
+},
+{	.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
+};
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+static int sun8i_ss_debugfs_show(struct seq_file *seq, void *v)
+{
+	struct sun8i_ss_dev *ss = seq->private;
+	unsigned int i;
+
+	for (i = 0; i < MAXFLOW; i++)
+		seq_printf(seq, "Channel %d: nreq %lu\n", i, ss->flows[i].stat_req);
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		if (!ss_algs[i].ss)
+			continue;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			seq_printf(seq, "%s %s reqs=%lu fallback=%lu\n",
+				   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",
+				   ss_algs[i].alg.rng.base.cra_driver_name,
+				   ss_algs[i].alg.rng.base.cra_name,
+				   ss_algs[i].stat_req, ss_algs[i].stat_bytes);
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			seq_printf(seq, "%s %s reqs=%lu fallback=%lu\n",
+				   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;
+		}
+	}
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(sun8i_ss_debugfs);
+#endif
+
+static void sun8i_ss_free_flows(struct sun8i_ss_dev *ss, int i)
+{
+	while (i >= 0) {
+		crypto_engine_exit(ss->flows[i].engine);
+		i--;
+	}
+}
+
+/*
+ * Allocate the flow list structure
+ */
+static int allocate_flows(struct sun8i_ss_dev *ss)
+{
+	int i, j, err;
+
+	ss->flows = devm_kcalloc(ss->dev, MAXFLOW, sizeof(struct sun8i_ss_flow),
+				 GFP_KERNEL);
+	if (!ss->flows)
+		return -ENOMEM;
+
+	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);
+		if (!ss->flows[i].biv) {
+			err = -ENOMEM;
+			goto error_engine;
+		}
+
+		for (j = 0; j < MAX_SG; j++) {
+			ss->flows[i].iv[j] = devm_kmalloc(ss->dev, AES_BLOCK_SIZE,
+							  GFP_KERNEL);
+			if (!ss->flows[i].iv[j]) {
+				err = -ENOMEM;
+				goto error_engine;
+			}
+		}
+
+		/* the padding could be up to two block. */
+		ss->flows[i].pad = devm_kmalloc(ss->dev, MAX_PAD_SIZE,
+						GFP_KERNEL);
+		if (!ss->flows[i].pad) {
+			err = -ENOMEM;
+			goto error_engine;
+		}
+		ss->flows[i].result =
+			devm_kmalloc(ss->dev, max(SHA256_DIGEST_SIZE,
+						  dma_get_cache_alignment()),
+				     GFP_KERNEL);
+		if (!ss->flows[i].result) {
+			err = -ENOMEM;
+			goto error_engine;
+		}
+
+		ss->flows[i].engine = crypto_engine_alloc_init(ss->dev, true);
+		if (!ss->flows[i].engine) {
+			dev_err(ss->dev, "Cannot allocate engine\n");
+			i--;
+			err = -ENOMEM;
+			goto error_engine;
+		}
+		err = crypto_engine_start(ss->flows[i].engine);
+		if (err) {
+			dev_err(ss->dev, "Cannot start engine\n");
+			goto error_engine;
+		}
+	}
+	return 0;
+error_engine:
+	sun8i_ss_free_flows(ss, i);
+	return err;
+}
+
+/*
+ * Power management strategy: The device is suspended unless a TFM exists for
+ * one of the algorithms proposed by this driver.
+ */
+static int sun8i_ss_pm_suspend(struct device *dev)
+{
+	struct sun8i_ss_dev *ss = dev_get_drvdata(dev);
+	int i;
+
+	reset_control_assert(ss->reset);
+	for (i = 0; i < SS_MAX_CLOCKS; i++)
+		clk_disable_unprepare(ss->ssclks[i]);
+	return 0;
+}
+
+static int sun8i_ss_pm_resume(struct device *dev)
+{
+	struct sun8i_ss_dev *ss = dev_get_drvdata(dev);
+	int err, i;
+
+	for (i = 0; i < SS_MAX_CLOCKS; i++) {
+		if (!ss->variant->ss_clks[i].name)
+			continue;
+		err = clk_prepare_enable(ss->ssclks[i]);
+		if (err) {
+			dev_err(ss->dev, "Cannot prepare_enable %s\n",
+				ss->variant->ss_clks[i].name);
+			goto error;
+		}
+	}
+	err = reset_control_deassert(ss->reset);
+	if (err) {
+		dev_err(ss->dev, "Cannot deassert reset control\n");
+		goto error;
+	}
+	/* enable interrupts for all flows */
+	writel(BIT(0) | BIT(1), ss->base + SS_INT_CTL_REG);
+
+	return 0;
+error:
+	sun8i_ss_pm_suspend(dev);
+	return err;
+}
+
+static const struct dev_pm_ops sun8i_ss_pm_ops = {
+	SET_RUNTIME_PM_OPS(sun8i_ss_pm_suspend, sun8i_ss_pm_resume, NULL)
+};
+
+static int sun8i_ss_pm_init(struct sun8i_ss_dev *ss)
+{
+	int err;
+
+	pm_runtime_use_autosuspend(ss->dev);
+	pm_runtime_set_autosuspend_delay(ss->dev, 2000);
+
+	err = pm_runtime_set_suspended(ss->dev);
+	if (err)
+		return err;
+	pm_runtime_enable(ss->dev);
+	return err;
+}
+
+static void sun8i_ss_pm_exit(struct sun8i_ss_dev *ss)
+{
+	pm_runtime_disable(ss->dev);
+}
+
+static int sun8i_ss_register_algs(struct sun8i_ss_dev *ss)
+{
+	int ss_method, err, id;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		ss_algs[i].ss = ss;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			id = ss_algs[i].ss_algo_id;
+			ss_method = ss->variant->alg_cipher[id];
+			if (ss_method == SS_ID_NOTSUPP) {
+				dev_info(ss->dev,
+					 "DEBUG: Algo of %s not supported\n",
+					 ss_algs[i].alg.skcipher.base.cra_name);
+				ss_algs[i].ss = NULL;
+				break;
+			}
+			id = ss_algs[i].ss_blockmode;
+			ss_method = ss->variant->op_mode[id];
+			if (ss_method == SS_ID_NOTSUPP) {
+				dev_info(ss->dev, "DEBUG: Blockmode of %s not supported\n",
+					 ss_algs[i].alg.skcipher.base.cra_name);
+				ss_algs[i].ss = NULL;
+				break;
+			}
+			dev_info(ss->dev, "DEBUG: Register %s\n",
+				 ss_algs[i].alg.skcipher.base.cra_name);
+			err = crypto_register_skcipher(&ss_algs[i].alg.skcipher);
+			if (err) {
+				dev_err(ss->dev, "Fail to register %s\n",
+					ss_algs[i].alg.skcipher.base.cra_name);
+				ss_algs[i].ss = NULL;
+				return err;
+			}
+			break;
+		case CRYPTO_ALG_TYPE_RNG:
+			err = crypto_register_rng(&ss_algs[i].alg.rng);
+			if (err) {
+				dev_err(ss->dev, "Fail to register %s\n",
+					ss_algs[i].alg.rng.base.cra_name);
+				ss_algs[i].ss = NULL;
+			}
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			id = ss_algs[i].ss_algo_id;
+			ss_method = ss->variant->alg_hash[id];
+			if (ss_method == SS_ID_NOTSUPP) {
+				dev_info(ss->dev,
+					"DEBUG: Algo of %s not supported\n",
+					ss_algs[i].alg.hash.halg.base.cra_name);
+				ss_algs[i].ss = NULL;
+				break;
+			}
+			dev_info(ss->dev, "Register %s\n",
+				 ss_algs[i].alg.hash.halg.base.cra_name);
+			err = crypto_register_ahash(&ss_algs[i].alg.hash);
+			if (err) {
+				dev_err(ss->dev, "ERROR: Fail to register %s\n",
+					ss_algs[i].alg.hash.halg.base.cra_name);
+				ss_algs[i].ss = NULL;
+				return err;
+			}
+			break;
+		default:
+			ss_algs[i].ss = NULL;
+			dev_err(ss->dev, "ERROR: tried to register an unknown algo\n");
+		}
+	}
+	return 0;
+}
+
+static void sun8i_ss_unregister_algs(struct sun8i_ss_dev *ss)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		if (!ss_algs[i].ss)
+			continue;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			dev_info(ss->dev, "Unregister %d %s\n", i,
+				 ss_algs[i].alg.skcipher.base.cra_name);
+			crypto_unregister_skcipher(&ss_algs[i].alg.skcipher);
+			break;
+		case CRYPTO_ALG_TYPE_RNG:
+			dev_info(ss->dev, "Unregister %d %s\n", i,
+				 ss_algs[i].alg.rng.base.cra_name);
+			crypto_unregister_rng(&ss_algs[i].alg.rng);
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			dev_info(ss->dev, "Unregister %d %s\n", i,
+				 ss_algs[i].alg.hash.halg.base.cra_name);
+			crypto_unregister_ahash(&ss_algs[i].alg.hash);
+			break;
+		}
+	}
+}
+
+static int sun8i_ss_get_clks(struct sun8i_ss_dev *ss)
+{
+	unsigned long cr;
+	int err, i;
+
+	for (i = 0; i < SS_MAX_CLOCKS; i++) {
+		if (!ss->variant->ss_clks[i].name)
+			continue;
+		ss->ssclks[i] = devm_clk_get(ss->dev, ss->variant->ss_clks[i].name);
+		if (IS_ERR(ss->ssclks[i])) {
+			err = PTR_ERR(ss->ssclks[i]);
+			dev_err(ss->dev, "Cannot get %s SS clock err=%d\n",
+				ss->variant->ss_clks[i].name, err);
+			return err;
+		}
+		cr = clk_get_rate(ss->ssclks[i]);
+		if (!cr)
+			return -EINVAL;
+		if (ss->variant->ss_clks[i].freq > 0 &&
+		    cr != ss->variant->ss_clks[i].freq) {
+			dev_info(ss->dev, "Set %s clock to %lu (%lu Mhz) from %lu (%lu Mhz)\n",
+				 ss->variant->ss_clks[i].name,
+				 ss->variant->ss_clks[i].freq,
+				 ss->variant->ss_clks[i].freq / 1000000,
+				 cr, cr / 1000000);
+			err = clk_set_rate(ss->ssclks[i], ss->variant->ss_clks[i].freq);
+			if (err)
+				dev_err(ss->dev, "Fail to set %s clk speed to %lu hz\n",
+					ss->variant->ss_clks[i].name,
+					ss->variant->ss_clks[i].freq);
+		}
+		if (ss->variant->ss_clks[i].max_freq > 0 &&
+		    cr > ss->variant->ss_clks[i].max_freq)
+			dev_warn(ss->dev, "Frequency for %s (%lu hz) is higher than datasheet's recommendation (%lu hz)",
+				 ss->variant->ss_clks[i].name, cr,
+				 ss->variant->ss_clks[i].max_freq);
+	}
+	return 0;
+}
+
+static int sun8i_ss_probe(struct platform_device *pdev)
+{
+	struct sun8i_ss_dev *ss;
+	int err, irq;
+	u32 v;
+
+	ss = devm_kzalloc(&pdev->dev, sizeof(*ss), GFP_KERNEL);
+	if (!ss)
+		return -ENOMEM;
+
+	ss->dev = &pdev->dev;
+	platform_set_drvdata(pdev, ss);
+
+	ss->variant = of_device_get_match_data(&pdev->dev);
+	if (!ss->variant) {
+		dev_err(&pdev->dev, "Missing Crypto Engine variant\n");
+		return -EINVAL;
+	}
+
+	ss->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ss->base))
+		return PTR_ERR(ss->base);
+
+	err = sun8i_ss_get_clks(ss);
+	if (err)
+		return err;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ss->reset = devm_reset_control_get(&pdev->dev, NULL);
+	if (IS_ERR(ss->reset))
+		return dev_err_probe(&pdev->dev, PTR_ERR(ss->reset),
+				     "No reset control found\n");
+
+	mutex_init(&ss->mlock);
+
+	err = allocate_flows(ss);
+	if (err)
+		return err;
+
+	err = sun8i_ss_pm_init(ss);
+	if (err)
+		goto error_pm;
+
+	err = devm_request_irq(&pdev->dev, irq, ss_irq_handler, 0, "sun8i-ss", ss);
+	if (err) {
+		dev_err(ss->dev, "Cannot request SecuritySystem IRQ (err=%d)\n", err);
+		goto error_irq;
+	}
+
+	err = sun8i_ss_register_algs(ss);
+	if (err)
+		goto error_alg;
+
+	err = pm_runtime_resume_and_get(ss->dev);
+	if (err < 0)
+		goto error_alg;
+
+	v = readl(ss->base + SS_CTL_REG);
+	v >>= SS_DIE_ID_SHIFT;
+	v &= SS_DIE_ID_MASK;
+	dev_info(&pdev->dev, "Security System Die ID %x\n", v);
+
+	pm_runtime_put_sync(ss->dev);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	/* Ignore error of debugfs */
+	ss->dbgfs_dir = debugfs_create_dir("sun8i-ss", NULL);
+	ss->dbgfs_stats = debugfs_create_file("stats", 0444,
+					      ss->dbgfs_dir, ss,
+					      &sun8i_ss_debugfs_fops);
+#endif
+
+	return 0;
+error_alg:
+	sun8i_ss_unregister_algs(ss);
+error_irq:
+	sun8i_ss_pm_exit(ss);
+error_pm:
+	sun8i_ss_free_flows(ss, MAXFLOW - 1);
+	return err;
+}
+
+static int sun8i_ss_remove(struct platform_device *pdev)
+{
+	struct sun8i_ss_dev *ss = platform_get_drvdata(pdev);
+
+	sun8i_ss_unregister_algs(ss);
+
+#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
+	debugfs_remove_recursive(ss->dbgfs_dir);
+#endif
+
+	sun8i_ss_free_flows(ss, MAXFLOW - 1);
+
+	sun8i_ss_pm_exit(ss);
+
+	return 0;
+}
+
+static const struct of_device_id sun8i_ss_crypto_of_match_table[] = {
+	{ .compatible = "allwinner,sun8i-a83t-crypto",
+	  .data = &ss_a83t_variant },
+	{ .compatible = "allwinner,sun9i-a80-crypto",
+	  .data = &ss_a80_variant },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun8i_ss_crypto_of_match_table);
+
+static struct platform_driver sun8i_ss_driver = {
+	.probe		 = sun8i_ss_probe,
+	.remove		 = sun8i_ss_remove,
+	.driver		 = {
+		.name		= "sun8i-ss",
+		.pm             = &sun8i_ss_pm_ops,
+		.of_match_table	= sun8i_ss_crypto_of_match_table,
+	},
+};
+
+module_platform_driver(sun8i_ss_driver);
+
+MODULE_DESCRIPTION("Allwinner SecuritySystem cryptographic offloader");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Corentin Labbe <clabbe.montjoie@gmail.com>");