Merge tag 'v6.16-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Fix memcpy_sglist to handle partially overlapping SG lists
   - Use memcpy_sglist to replace null skcipher
   - Rename CRYPTO_TESTS to CRYPTO_BENCHMARK
   - Flip CRYPTO_MANAGER_DISABLE_TEST into CRYPTO_SELFTESTS
   - Hide CRYPTO_MANAGER
   - Add delayed freeing of driver crypto_alg structures

  Compression:
   - Allocate large buffers on first use instead of initialisation in scomp
   - Drop destination linearisation buffer in scomp
   - Move scomp stream allocation into acomp
   - Add acomp scatter-gather walker
   - Remove request chaining
   - Add optional async request allocation

  Hashing:
   - Remove request chaining
   - Add optional async request allocation
   - Move partial block handling into API
   - Add ahash support to hmac
   - Fix shash documentation to disallow usage in hard IRQs

  Algorithms:
   - Remove unnecessary SIMD fallback code on x86 and arm/arm64
   - Drop avx10_256 xts(aes)/ctr(aes) on x86
   - Improve avx-512 optimisations for xts(aes)
   - Move chacha arch implementations into lib/crypto
   - Move poly1305 into lib/crypto and drop unused Crypto API algorithm
   - Disable powerpc/poly1305 as it has no SIMD fallback
   - Move sha256 arch implementations into lib/crypto
   - Convert deflate to acomp
   - Set block size correctly in cbcmac

  Drivers:
   - Do not use sg_dma_len before mapping in sun8i-ss
   - Fix warm-reboot failure by making shutdown do more work in qat
   - Add locking in zynqmp-sha
   - Remove cavium/zip
   - Add support for PCI device 0x17D8 to ccp
   - Add qat_6xxx support in qat
   - Add support for RK3576 in rockchip-rng
   - Add support for i.MX8QM in caam

  Others:
   - Fix irq_fpu_usable/kernel_fpu_begin inconsistency during CPU bring-up
   - Add new SEV/SNP platform shutdown API in ccp"

* tag 'v6.16-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (382 commits)
  x86/fpu: Fix irq_fpu_usable() to return false during CPU onlining
  crypto: qat - add missing header inclusion
  crypto: api - Redo lookup on EEXIST
  Revert "crypto: testmgr - Add hash export format testing"
  crypto: marvell/cesa - Do not chain submitted requests
  crypto: powerpc/poly1305 - add depends on BROKEN for now
  Revert "crypto: powerpc/poly1305 - Add SIMD fallback"
  crypto: ccp - Add missing tee info reg for teev2
  crypto: ccp - Add missing bootloader info reg for pspv5
  crypto: sun8i-ce - move fallback ahash_request to the end of the struct
  crypto: octeontx2 - Use dynamic allocated memory region for lmtst
  crypto: octeontx2 - Initialize cptlfs device info once
  crypto: xts - Only add ecb if it is not already there
  crypto: lrw - Only add ecb if it is not already there
  crypto: testmgr - Add hash export format testing
  crypto: testmgr - Use ahash for generic tfm
  crypto: hmac - Add ahash support
  crypto: testmgr - Ignore EEXIST on shash allocation
  crypto: algapi - Add driver template support to crypto_inst_setname
  crypto: shash - Set reqsize in shash_alg
  ...

1 files changed, 129 insertions, 0 deletions

diff --git a/arch/x86/lib/crypto/poly1305_glue.c b/arch/x86/lib/crypto/poly1305_glue.c
new file mode 100644
index 000000000000..b7e78a583e07
--- /dev/null
+++ b/arch/x86/lib/crypto/poly1305_glue.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <asm/cpu_device_id.h>
+#include <asm/fpu/api.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <linux/unaligned.h>
+
+struct poly1305_arch_internal {
+	union {
+		struct {
+			u32 h[5];
+			u32 is_base2_26;
+		};
+		u64 hs[3];
+	};
+	u64 r[2];
+	u64 pad;
+	struct { u32 r2, r1, r4, r3; } rn[9];
+};
+
+asmlinkage void poly1305_block_init_arch(
+	struct poly1305_block_state *state,
+	const u8 raw_key[POLY1305_BLOCK_SIZE]);
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+asmlinkage void poly1305_blocks_x86_64(struct poly1305_arch_internal *ctx,
+				       const u8 *inp,
+				       const size_t len, const u32 padbit);
+asmlinkage void poly1305_emit_x86_64(const struct poly1305_state *ctx,
+				     u8 mac[POLY1305_DIGEST_SIZE],
+				     const u32 nonce[4]);
+asmlinkage void poly1305_emit_avx(const struct poly1305_state *ctx,
+				  u8 mac[POLY1305_DIGEST_SIZE],
+				  const u32 nonce[4]);
+asmlinkage void poly1305_blocks_avx(struct poly1305_arch_internal *ctx,
+				    const u8 *inp, const size_t len,
+				    const u32 padbit);
+asmlinkage void poly1305_blocks_avx2(struct poly1305_arch_internal *ctx,
+				     const u8 *inp, const size_t len,
+				     const u32 padbit);
+asmlinkage void poly1305_blocks_avx512(struct poly1305_arch_internal *ctx,
+				       const u8 *inp,
+				       const size_t len, const u32 padbit);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx512);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp,
+			  unsigned int len, u32 padbit)
+{
+	struct poly1305_arch_internal *ctx =
+		container_of(&state->h.h, struct poly1305_arch_internal, h);
+
+	/* SIMD disables preemption, so relax after processing each page. */
+	BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE ||
+		     SZ_4K % POLY1305_BLOCK_SIZE);
+
+	if (!static_branch_likely(&poly1305_use_avx)) {
+		poly1305_blocks_x86_64(ctx, inp, len, padbit);
+		return;
+	}
+
+	do {
+		const unsigned int bytes = min(len, SZ_4K);
+
+		kernel_fpu_begin();
+		if (static_branch_likely(&poly1305_use_avx512))
+			poly1305_blocks_avx512(ctx, inp, bytes, padbit);
+		else if (static_branch_likely(&poly1305_use_avx2))
+			poly1305_blocks_avx2(ctx, inp, bytes, padbit);
+		else
+			poly1305_blocks_avx(ctx, inp, bytes, padbit);
+		kernel_fpu_end();
+
+		len -= bytes;
+		inp += bytes;
+	} while (len);
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+void poly1305_emit_arch(const struct poly1305_state *ctx,
+			u8 mac[POLY1305_DIGEST_SIZE], const u32 nonce[4])
+{
+	if (!static_branch_likely(&poly1305_use_avx))
+		poly1305_emit_x86_64(ctx, mac, nonce);
+	else
+		poly1305_emit_avx(ctx, mac, nonce);
+}
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	return static_key_enabled(&poly1305_use_avx);
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init poly1305_simd_mod_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		static_branch_enable(&poly1305_use_avx);
+	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		static_branch_enable(&poly1305_use_avx2);
+	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) &&
+	    /* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */
+	    boot_cpu_data.x86_vfm != INTEL_SKYLAKE_X)
+		static_branch_enable(&poly1305_use_avx512);
+	return 0;
+}
+subsys_initcall(poly1305_simd_mod_init);
+
+static void __exit poly1305_simd_mod_exit(void)
+{
+}
+module_exit(poly1305_simd_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
+MODULE_DESCRIPTION("Poly1305 authenticator");