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, 137 insertions, 0 deletions

diff --git a/lib/crypto/sha256-generic.c b/lib/crypto/sha256-generic.c
new file mode 100644
index 000000000000..a16ad4f25ebb
--- /dev/null
+++ b/lib/crypto/sha256-generic.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256, as specified in
+ * http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf
+ *
+ * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>.
+ *
+ * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
+ * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ * Copyright (c) 2014 Red Hat Inc.
+ */
+
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
+
+static const u32 SHA256_K[] = {
+	0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
+	0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+	0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+	0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+	0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
+	0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+	0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
+	0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+	0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+	0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+	0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
+	0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+	0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
+	0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+	0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+	0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2,
+};
+
+static inline u32 Ch(u32 x, u32 y, u32 z)
+{
+	return z ^ (x & (y ^ z));
+}
+
+static inline u32 Maj(u32 x, u32 y, u32 z)
+{
+	return (x & y) | (z & (x | y));
+}
+
+#define e0(x)       (ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22))
+#define e1(x)       (ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25))
+#define s0(x)       (ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3))
+#define s1(x)       (ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10))
+
+static inline void LOAD_OP(int I, u32 *W, const u8 *input)
+{
+	W[I] = get_unaligned_be32((__u32 *)input + I);
+}
+
+static inline void BLEND_OP(int I, u32 *W)
+{
+	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
+}
+
+#define SHA256_ROUND(i, a, b, c, d, e, f, g, h) do {		\
+	u32 t1, t2;						\
+	t1 = h + e1(e) + Ch(e, f, g) + SHA256_K[i] + W[i];	\
+	t2 = e0(a) + Maj(a, b, c);				\
+	d += t1;						\
+	h = t1 + t2;						\
+} while (0)
+
+static void sha256_block_generic(u32 state[SHA256_STATE_WORDS],
+				 const u8 *input, u32 W[64])
+{
+	u32 a, b, c, d, e, f, g, h;
+	int i;
+
+	/* load the input */
+	for (i = 0; i < 16; i += 8) {
+		LOAD_OP(i + 0, W, input);
+		LOAD_OP(i + 1, W, input);
+		LOAD_OP(i + 2, W, input);
+		LOAD_OP(i + 3, W, input);
+		LOAD_OP(i + 4, W, input);
+		LOAD_OP(i + 5, W, input);
+		LOAD_OP(i + 6, W, input);
+		LOAD_OP(i + 7, W, input);
+	}
+
+	/* now blend */
+	for (i = 16; i < 64; i += 8) {
+		BLEND_OP(i + 0, W);
+		BLEND_OP(i + 1, W);
+		BLEND_OP(i + 2, W);
+		BLEND_OP(i + 3, W);
+		BLEND_OP(i + 4, W);
+		BLEND_OP(i + 5, W);
+		BLEND_OP(i + 6, W);
+		BLEND_OP(i + 7, W);
+	}
+
+	/* load the state into our registers */
+	a = state[0];  b = state[1];  c = state[2];  d = state[3];
+	e = state[4];  f = state[5];  g = state[6];  h = state[7];
+
+	/* now iterate */
+	for (i = 0; i < 64; i += 8) {
+		SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h);
+		SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g);
+		SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f);
+		SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e);
+		SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d);
+		SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c);
+		SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b);
+		SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a);
+	}
+
+	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
+	state[4] += e; state[5] += f; state[6] += g; state[7] += h;
+}
+
+void sha256_blocks_generic(u32 state[SHA256_STATE_WORDS],
+			   const u8 *data, size_t nblocks)
+{
+	u32 W[64];
+
+	do {
+		sha256_block_generic(state, data, W);
+		data += SHA256_BLOCK_SIZE;
+	} while (--nblocks);
+
+	memzero_explicit(W, sizeof(W));
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_generic);
+
+MODULE_DESCRIPTION("SHA-256 Algorithm (generic implementation)");
+MODULE_LICENSE("GPL");