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, 795 insertions, 0 deletions

diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
new file mode 100644
index 000000000..3ddf05b42
--- /dev/null
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -0,0 +1,795 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated GHASH implementation with ARMv8 vmull.p64 instructions.
+ *
+ * Copyright (C) 2015 - 2018 Linaro Ltd.
+ * Copyright (C) 2023 Google LLC.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/gcm.h>
+#include <crypto/b128ops.h>
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/gf128mul.h>
+#include <crypto/scatterwalk.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH hash function using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ardb@kernel.org>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("ghash");
+MODULE_ALIAS_CRYPTO("gcm(aes)");
+MODULE_ALIAS_CRYPTO("rfc4106(gcm(aes))");
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+
+#define RFC4106_NONCE_SIZE	4
+
+struct ghash_key {
+	be128	k;
+	u64	h[][2];
+};
+
+struct gcm_key {
+	u64	h[4][2];
+	u32	rk[AES_MAX_KEYLENGTH_U32];
+	int	rounds;
+	u8	nonce[];	// for RFC4106 nonce
+};
+
+struct ghash_desc_ctx {
+	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+	u8 buf[GHASH_BLOCK_SIZE];
+	u32 count;
+};
+
+struct ghash_async_ctx {
+	struct cryptd_ahash *cryptd_tfm;
+};
+
+asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
+				       u64 const h[][2], const char *head);
+
+asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
+				      u64 const h[][2], const char *head);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_p64);
+
+static int ghash_init(struct shash_desc *desc)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static void ghash_do_update(int blocks, u64 dg[], const char *src,
+			    struct ghash_key *key, const char *head)
+{
+	if (likely(crypto_simd_usable())) {
+		kernel_neon_begin();
+		if (static_branch_likely(&use_p64))
+			pmull_ghash_update_p64(blocks, dg, src, key->h, head);
+		else
+			pmull_ghash_update_p8(blocks, dg, src, key->h, head);
+		kernel_neon_end();
+	} else {
+		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+
+		do {
+			const u8 *in = src;
+
+			if (head) {
+				in = head;
+				blocks++;
+				head = NULL;
+			} else {
+				src += GHASH_BLOCK_SIZE;
+			}
+
+			crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+			gf128mul_lle(&dst, &key->k);
+		} while (--blocks);
+
+		dg[0] = be64_to_cpu(dst.b);
+		dg[1] = be64_to_cpu(dst.a);
+	}
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	ctx->count += len;
+
+	if ((partial + len) >= GHASH_BLOCK_SIZE) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+		int blocks;
+
+		if (partial) {
+			int p = GHASH_BLOCK_SIZE - partial;
+
+			memcpy(ctx->buf + partial, src, p);
+			src += p;
+			len -= p;
+		}
+
+		blocks = len / GHASH_BLOCK_SIZE;
+		len %= GHASH_BLOCK_SIZE;
+
+		ghash_do_update(blocks, ctx->digest, src, key,
+				partial ? ctx->buf : NULL);
+		src += blocks * GHASH_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(ctx->buf + partial, src, len);
+	return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	if (partial) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL);
+	}
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static void ghash_reflect(u64 h[], const be128 *k)
+{
+	u64 carry = be64_to_cpu(k->a) >> 63;
+
+	h[0] = (be64_to_cpu(k->b) << 1) | carry;
+	h[1] = (be64_to_cpu(k->a) << 1) | (be64_to_cpu(k->b) >> 63);
+
+	if (carry)
+		h[1] ^= 0xc200000000000000UL;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+			const u8 *inkey, unsigned int keylen)
+{
+	struct ghash_key *key = crypto_shash_ctx(tfm);
+
+	if (keylen != GHASH_BLOCK_SIZE)
+		return -EINVAL;
+
+	/* needed for the fallback */
+	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
+	ghash_reflect(key->h[0], &key->k);
+
+	if (static_branch_likely(&use_p64)) {
+		be128 h = key->k;
+
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[1], &h);
+
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[2], &h);
+
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[3], &h);
+	}
+	return 0;
+}
+
+static struct shash_alg ghash_alg = {
+	.digestsize		= GHASH_DIGEST_SIZE,
+	.init			= ghash_init,
+	.update			= ghash_update,
+	.final			= ghash_final,
+	.setkey			= ghash_setkey,
+	.descsize		= sizeof(struct ghash_desc_ctx),
+
+	.base.cra_name		= "ghash",
+	.base.cra_driver_name	= "ghash-ce-sync",
+	.base.cra_priority	= 300 - 1,
+	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int ghash_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+	desc->tfm = child;
+	return crypto_shash_init(desc);
+}
+
+static int ghash_async_update(struct ahash_request *req)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!crypto_simd_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_update(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		return shash_ahash_update(req, desc);
+	}
+}
+
+static int ghash_async_final(struct ahash_request *req)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!crypto_simd_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_final(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		return crypto_shash_final(desc, req->result);
+	}
+}
+
+static int ghash_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!crypto_simd_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_digest(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+		desc->tfm = child;
+		return shash_ahash_digest(req, desc);
+	}
+}
+
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+	desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
+
+	return crypto_shash_import(desc, in);
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+	return crypto_shash_export(desc, out);
+}
+
+static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct crypto_ahash *child = &ctx->cryptd_tfm->base;
+
+	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
+			       & CRYPTO_TFM_REQ_MASK);
+	return crypto_ahash_setkey(child, key, keylen);
+}
+
+static int ghash_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct cryptd_ahash *cryptd_tfm;
+	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_tfm = cryptd_alloc_ahash("ghash-ce-sync", 0, 0);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+	ctx->cryptd_tfm = cryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct ahash_request) +
+				 crypto_ahash_reqsize(&cryptd_tfm->base));
+
+	return 0;
+}
+
+static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_free_ahash(ctx->cryptd_tfm);
+}
+
+static struct ahash_alg ghash_async_alg = {
+	.init			= ghash_async_init,
+	.update			= ghash_async_update,
+	.final			= ghash_async_final,
+	.setkey			= ghash_async_setkey,
+	.digest			= ghash_async_digest,
+	.import			= ghash_async_import,
+	.export			= ghash_async_export,
+	.halg.digestsize	= GHASH_DIGEST_SIZE,
+	.halg.statesize		= sizeof(struct ghash_desc_ctx),
+	.halg.base		= {
+		.cra_name	= "ghash",
+		.cra_driver_name = "ghash-ce",
+		.cra_priority	= 300,
+		.cra_flags	= CRYPTO_ALG_ASYNC,
+		.cra_blocksize	= GHASH_BLOCK_SIZE,
+		.cra_ctxsize	= sizeof(struct ghash_async_ctx),
+		.cra_module	= THIS_MODULE,
+		.cra_init	= ghash_async_init_tfm,
+		.cra_exit	= ghash_async_exit_tfm,
+	},
+};
+
+
+void pmull_gcm_encrypt(int blocks, u64 dg[], const char *src,
+		       struct gcm_key const *k, char *dst,
+		       const char *iv, int rounds, u32 counter);
+
+void pmull_gcm_enc_final(int blocks, u64 dg[], char *tag,
+			 struct gcm_key const *k, char *head,
+			 const char *iv, int rounds, u32 counter);
+
+void pmull_gcm_decrypt(int bytes, u64 dg[], const char *src,
+		       struct gcm_key const *k, char *dst,
+		       const char *iv, int rounds, u32 counter);
+
+int pmull_gcm_dec_final(int bytes, u64 dg[], char *tag,
+			struct gcm_key const *k, char *head,
+			const char *iv, int rounds, u32 counter,
+			const char *otag, int authsize);
+
+static int gcm_aes_setkey(struct crypto_aead *tfm, const u8 *inkey,
+			  unsigned int keylen)
+{
+	struct gcm_key *ctx = crypto_aead_ctx(tfm);
+	struct crypto_aes_ctx aes_ctx;
+	be128 h, k;
+	int ret;
+
+	ret = aes_expandkey(&aes_ctx, inkey, keylen);
+	if (ret)
+		return -EINVAL;
+
+	aes_encrypt(&aes_ctx, (u8 *)&k, (u8[AES_BLOCK_SIZE]){});
+
+	memcpy(ctx->rk, aes_ctx.key_enc, sizeof(ctx->rk));
+	ctx->rounds = 6 + keylen / 4;
+
+	memzero_explicit(&aes_ctx, sizeof(aes_ctx));
+
+	ghash_reflect(ctx->h[0], &k);
+
+	h = k;
+	gf128mul_lle(&h, &k);
+	ghash_reflect(ctx->h[1], &h);
+
+	gf128mul_lle(&h, &k);
+	ghash_reflect(ctx->h[2], &h);
+
+	gf128mul_lle(&h, &k);
+	ghash_reflect(ctx->h[3], &h);
+
+	return 0;
+}
+
+static int gcm_aes_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	return crypto_gcm_check_authsize(authsize);
+}
+
+static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[],
+			   int *buf_count, struct gcm_key *ctx)
+{
+	if (*buf_count > 0) {
+		int buf_added = min(count, GHASH_BLOCK_SIZE - *buf_count);
+
+		memcpy(&buf[*buf_count], src, buf_added);
+
+		*buf_count += buf_added;
+		src += buf_added;
+		count -= buf_added;
+	}
+
+	if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) {
+		int blocks = count / GHASH_BLOCK_SIZE;
+
+		pmull_ghash_update_p64(blocks, dg, src, ctx->h,
+				       *buf_count ? buf : NULL);
+
+		src += blocks * GHASH_BLOCK_SIZE;
+		count %= GHASH_BLOCK_SIZE;
+		*buf_count = 0;
+	}
+
+	if (count > 0) {
+		memcpy(buf, src, count);
+		*buf_count = count;
+	}
+}
+
+static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[], u32 len)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_key *ctx = crypto_aead_ctx(aead);
+	u8 buf[GHASH_BLOCK_SIZE];
+	struct scatter_walk walk;
+	int buf_count = 0;
+
+	scatterwalk_start(&walk, req->src);
+
+	do {
+		u32 n = scatterwalk_clamp(&walk, len);
+		u8 *p;
+
+		if (!n) {
+			scatterwalk_start(&walk, sg_next(walk.sg));
+			n = scatterwalk_clamp(&walk, len);
+		}
+
+		p = scatterwalk_map(&walk);
+		gcm_update_mac(dg, p, n, buf, &buf_count, ctx);
+		scatterwalk_unmap(p);
+
+		if (unlikely(len / SZ_4K > (len - n) / SZ_4K)) {
+			kernel_neon_end();
+			kernel_neon_begin();
+		}
+
+		len -= n;
+		scatterwalk_advance(&walk, n);
+		scatterwalk_done(&walk, 0, len);
+	} while (len);
+
+	if (buf_count) {
+		memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count);
+		pmull_ghash_update_p64(1, dg, buf, ctx->h, NULL);
+	}
+}
+
+static int gcm_encrypt(struct aead_request *req, const u8 *iv, u32 assoclen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_key *ctx = crypto_aead_ctx(aead);
+	struct skcipher_walk walk;
+	u8 buf[AES_BLOCK_SIZE];
+	u32 counter = 2;
+	u64 dg[2] = {};
+	be128 lengths;
+	const u8 *src;
+	u8 *tag, *dst;
+	int tail, err;
+
+	if (WARN_ON_ONCE(!may_use_simd()))
+		return -EBUSY;
+
+	err = skcipher_walk_aead_encrypt(&walk, req, false);
+
+	kernel_neon_begin();
+
+	if (assoclen)
+		gcm_calculate_auth_mac(req, dg, assoclen);
+
+	src = walk.src.virt.addr;
+	dst = walk.dst.virt.addr;
+
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		int nblocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		pmull_gcm_encrypt(nblocks, dg, src, ctx, dst, iv,
+				  ctx->rounds, counter);
+		counter += nblocks;
+
+		if (walk.nbytes == walk.total) {
+			src += nblocks * AES_BLOCK_SIZE;
+			dst += nblocks * AES_BLOCK_SIZE;
+			break;
+		}
+
+		kernel_neon_end();
+
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes % AES_BLOCK_SIZE);
+		if (err)
+			return err;
+
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+
+		kernel_neon_begin();
+	}
+
+
+	lengths.a = cpu_to_be64(assoclen * 8);
+	lengths.b = cpu_to_be64(req->cryptlen * 8);
+
+	tag = (u8 *)&lengths;
+	tail = walk.nbytes % AES_BLOCK_SIZE;
+
+	/*
+	 * Bounce via a buffer unless we are encrypting in place and src/dst
+	 * are not pointing to the start of the walk buffer. In that case, we
+	 * can do a NEON load/xor/store sequence in place as long as we move
+	 * the plain/ciphertext and keystream to the start of the register. If
+	 * not, do a memcpy() to the end of the buffer so we can reuse the same
+	 * logic.
+	 */
+	if (unlikely(tail && (tail == walk.nbytes || src != dst)))
+		src = memcpy(buf + sizeof(buf) - tail, src, tail);
+
+	pmull_gcm_enc_final(tail, dg, tag, ctx, (u8 *)src, iv,
+			    ctx->rounds, counter);
+	kernel_neon_end();
+
+	if (unlikely(tail && src != dst))
+		memcpy(dst, src, tail);
+
+	if (walk.nbytes) {
+		err = skcipher_walk_done(&walk, 0);
+		if (err)
+			return err;
+	}
+
+	/* copy authtag to end of dst */
+	scatterwalk_map_and_copy(tag, req->dst, req->assoclen + req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int gcm_decrypt(struct aead_request *req, const u8 *iv, u32 assoclen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_key *ctx = crypto_aead_ctx(aead);
+	int authsize = crypto_aead_authsize(aead);
+	struct skcipher_walk walk;
+	u8 otag[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 counter = 2;
+	u64 dg[2] = {};
+	be128 lengths;
+	const u8 *src;
+	u8 *tag, *dst;
+	int tail, err, ret;
+
+	if (WARN_ON_ONCE(!may_use_simd()))
+		return -EBUSY;
+
+	scatterwalk_map_and_copy(otag, req->src,
+				 req->assoclen + req->cryptlen - authsize,
+				 authsize, 0);
+
+	err = skcipher_walk_aead_decrypt(&walk, req, false);
+
+	kernel_neon_begin();
+
+	if (assoclen)
+		gcm_calculate_auth_mac(req, dg, assoclen);
+
+	src = walk.src.virt.addr;
+	dst = walk.dst.virt.addr;
+
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		int nblocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		pmull_gcm_decrypt(nblocks, dg, src, ctx, dst, iv,
+				  ctx->rounds, counter);
+		counter += nblocks;
+
+		if (walk.nbytes == walk.total) {
+			src += nblocks * AES_BLOCK_SIZE;
+			dst += nblocks * AES_BLOCK_SIZE;
+			break;
+		}
+
+		kernel_neon_end();
+
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes % AES_BLOCK_SIZE);
+		if (err)
+			return err;
+
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+
+		kernel_neon_begin();
+	}
+
+	lengths.a = cpu_to_be64(assoclen * 8);
+	lengths.b = cpu_to_be64((req->cryptlen - authsize) * 8);
+
+	tag = (u8 *)&lengths;
+	tail = walk.nbytes % AES_BLOCK_SIZE;
+
+	if (unlikely(tail && (tail == walk.nbytes || src != dst)))
+		src = memcpy(buf + sizeof(buf) - tail, src, tail);
+
+	ret = pmull_gcm_dec_final(tail, dg, tag, ctx, (u8 *)src, iv,
+				  ctx->rounds, counter, otag, authsize);
+	kernel_neon_end();
+
+	if (unlikely(tail && src != dst))
+		memcpy(dst, src, tail);
+
+	if (walk.nbytes) {
+		err = skcipher_walk_done(&walk, 0);
+		if (err)
+			return err;
+	}
+
+	return ret ? -EBADMSG : 0;
+}
+
+static int gcm_aes_encrypt(struct aead_request *req)
+{
+	return gcm_encrypt(req, req->iv, req->assoclen);
+}
+
+static int gcm_aes_decrypt(struct aead_request *req)
+{
+	return gcm_decrypt(req, req->iv, req->assoclen);
+}
+
+static int rfc4106_setkey(struct crypto_aead *tfm, const u8 *inkey,
+			  unsigned int keylen)
+{
+	struct gcm_key *ctx = crypto_aead_ctx(tfm);
+	int err;
+
+	keylen -= RFC4106_NONCE_SIZE;
+	err = gcm_aes_setkey(tfm, inkey, keylen);
+	if (err)
+		return err;
+
+	memcpy(ctx->nonce, inkey + keylen, RFC4106_NONCE_SIZE);
+	return 0;
+}
+
+static int rfc4106_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	return crypto_rfc4106_check_authsize(authsize);
+}
+
+static int rfc4106_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_key *ctx = crypto_aead_ctx(aead);
+	u8 iv[GCM_AES_IV_SIZE];
+
+	memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+	memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+	return crypto_ipsec_check_assoclen(req->assoclen) ?:
+	       gcm_encrypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE);
+}
+
+static int rfc4106_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_key *ctx = crypto_aead_ctx(aead);
+	u8 iv[GCM_AES_IV_SIZE];
+
+	memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+	memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+	return crypto_ipsec_check_assoclen(req->assoclen) ?:
+	       gcm_decrypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE);
+}
+
+static struct aead_alg gcm_aes_algs[] = {{
+	.ivsize			= GCM_AES_IV_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.maxauthsize		= AES_BLOCK_SIZE,
+	.setkey			= gcm_aes_setkey,
+	.setauthsize		= gcm_aes_setauthsize,
+	.encrypt		= gcm_aes_encrypt,
+	.decrypt		= gcm_aes_decrypt,
+
+	.base.cra_name		= "gcm(aes)",
+	.base.cra_driver_name	= "gcm-aes-ce",
+	.base.cra_priority	= 400,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct gcm_key),
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.ivsize			= GCM_RFC4106_IV_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.maxauthsize		= AES_BLOCK_SIZE,
+	.setkey			= rfc4106_setkey,
+	.setauthsize		= rfc4106_setauthsize,
+	.encrypt		= rfc4106_encrypt,
+	.decrypt		= rfc4106_decrypt,
+
+	.base.cra_name		= "rfc4106(gcm(aes))",
+	.base.cra_driver_name	= "rfc4106-gcm-aes-ce",
+	.base.cra_priority	= 400,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct gcm_key) + RFC4106_NONCE_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}};
+
+static int __init ghash_ce_mod_init(void)
+{
+	int err;
+
+	if (!(elf_hwcap & HWCAP_NEON))
+		return -ENODEV;
+
+	if (elf_hwcap2 & HWCAP2_PMULL) {
+		err = crypto_register_aeads(gcm_aes_algs,
+					    ARRAY_SIZE(gcm_aes_algs));
+		if (err)
+			return err;
+		ghash_alg.base.cra_ctxsize += 3 * sizeof(u64[2]);
+		static_branch_enable(&use_p64);
+	}
+
+	err = crypto_register_shash(&ghash_alg);
+	if (err)
+		goto err_aead;
+	err = crypto_register_ahash(&ghash_async_alg);
+	if (err)
+		goto err_shash;
+
+	return 0;
+
+err_shash:
+	crypto_unregister_shash(&ghash_alg);
+err_aead:
+	if (elf_hwcap2 & HWCAP2_PMULL)
+		crypto_unregister_aeads(gcm_aes_algs,
+					ARRAY_SIZE(gcm_aes_algs));
+	return err;
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+	crypto_unregister_ahash(&ghash_async_alg);
+	crypto_unregister_shash(&ghash_alg);
+	if (elf_hwcap2 & HWCAP2_PMULL)
+		crypto_unregister_aeads(gcm_aes_algs,
+					ARRAY_SIZE(gcm_aes_algs));
+}
+
+module_init(ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);