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
  ...

6 files changed, 156 insertions, 2 deletions

diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index ef8860eb3f3d..5cf9781d68b4 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -4,6 +4,7 @@
 
 asflags-y := -ansi -DST_DIV0=0x02
 
+obj-y                 += crypto/
 lib-$(CONFIG_SPARC32) += ashrdi3.o
 lib-$(CONFIG_SPARC32) += memcpy.o memset.o
 lib-y                 += strlen.o
diff --git a/arch/sparc/lib/crc32c_asm.S b/arch/sparc/lib/crc32c_asm.S
index ee454fa6aed6..4db873850f44 100644
--- a/arch/sparc/lib/crc32c_asm.S
+++ b/arch/sparc/lib/crc32c_asm.S
@@ -1,10 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 
-#include "../crypto/opcodes.h"
-
 ENTRY(crc32c_sparc64)
 	/* %o0=crc32p, %o1=data_ptr, %o2=len */
 	VISEntryHalf
diff --git a/arch/sparc/lib/crypto/Kconfig b/arch/sparc/lib/crypto/Kconfig
new file mode 100644
index 000000000000..e5c3e4d3dba6
--- /dev/null
+++ b/arch/sparc/lib/crypto/Kconfig
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_SHA256_SPARC64
+	tristate
+	depends on SPARC64
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_LIB_SHA256_GENERIC
diff --git a/arch/sparc/lib/crypto/Makefile b/arch/sparc/lib/crypto/Makefile
new file mode 100644
index 000000000000..75ee244ad6f7
--- /dev/null
+++ b/arch/sparc/lib/crypto/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_SHA256_SPARC64) += sha256-sparc64.o
+sha256-sparc64-y := sha256.o sha256_asm.o
diff --git a/arch/sparc/lib/crypto/sha256.c b/arch/sparc/lib/crypto/sha256.c
new file mode 100644
index 000000000000..8bdec2db08b3
--- /dev/null
+++ b/arch/sparc/lib/crypto/sha256.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SHA-256 accelerated using the sparc64 sha256 opcodes
+ *
+ * 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>
+ * SHA224 Support Copyright 2007 Intel Corporation <jonathan.lynch@intel.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <asm/elf.h>
+#include <asm/opcodes.h>
+#include <asm/pstate.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sha256_opcodes);
+
+asmlinkage void sha256_sparc64_transform(u32 state[SHA256_STATE_WORDS],
+					 const u8 *data, size_t nblocks);
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (static_branch_likely(&have_sha256_opcodes))
+		sha256_sparc64_transform(state, data, nblocks);
+	else
+		sha256_blocks_generic(state, data, nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_sha256_opcodes);
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_sparc64_mod_init(void)
+{
+	unsigned long cfr;
+
+	if (!(sparc64_elf_hwcap & HWCAP_SPARC_CRYPTO))
+		return 0;
+
+	__asm__ __volatile__("rd %%asr26, %0" : "=r" (cfr));
+	if (!(cfr & CFR_SHA256))
+		return 0;
+
+	static_branch_enable(&have_sha256_opcodes);
+	pr_info("Using sparc64 sha256 opcode optimized SHA-256/SHA-224 implementation\n");
+	return 0;
+}
+subsys_initcall(sha256_sparc64_mod_init);
+
+static void __exit sha256_sparc64_mod_exit(void)
+{
+}
+module_exit(sha256_sparc64_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 accelerated using the sparc64 sha256 opcodes");
diff --git a/arch/sparc/lib/crypto/sha256_asm.S b/arch/sparc/lib/crypto/sha256_asm.S
new file mode 100644
index 000000000000..ddcdd3daf31e
--- /dev/null
+++ b/arch/sparc/lib/crypto/sha256_asm.S
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/opcodes.h>
+#include <asm/visasm.h>
+
+ENTRY(sha256_sparc64_transform)
+	/* %o0 = state, %o1 = data, %o2 = nblocks */
+	VISEntryHalf
+	ld	[%o0 + 0x00], %f0
+	ld	[%o0 + 0x04], %f1
+	ld	[%o0 + 0x08], %f2
+	ld	[%o0 + 0x0c], %f3
+	ld	[%o0 + 0x10], %f4
+	ld	[%o0 + 0x14], %f5
+	andcc	%o1, 0x7, %g0
+	ld	[%o0 + 0x18], %f6
+	bne,pn	%xcc, 10f
+	 ld	[%o0 + 0x1c], %f7
+
+1:
+	ldd	[%o1 + 0x00], %f8
+	ldd	[%o1 + 0x08], %f10
+	ldd	[%o1 + 0x10], %f12
+	ldd	[%o1 + 0x18], %f14
+	ldd	[%o1 + 0x20], %f16
+	ldd	[%o1 + 0x28], %f18
+	ldd	[%o1 + 0x30], %f20
+	ldd	[%o1 + 0x38], %f22
+
+	SHA256
+
+	subcc	%o2, 1, %o2
+	bne,pt	%xcc, 1b
+	 add	%o1, 0x40, %o1
+
+5:
+	st	%f0, [%o0 + 0x00]
+	st	%f1, [%o0 + 0x04]
+	st	%f2, [%o0 + 0x08]
+	st	%f3, [%o0 + 0x0c]
+	st	%f4, [%o0 + 0x10]
+	st	%f5, [%o0 + 0x14]
+	st	%f6, [%o0 + 0x18]
+	st	%f7, [%o0 + 0x1c]
+	retl
+	 VISExitHalf
+10:
+	alignaddr %o1, %g0, %o1
+
+	ldd	[%o1 + 0x00], %f10
+1:
+	ldd	[%o1 + 0x08], %f12
+	ldd	[%o1 + 0x10], %f14
+	ldd	[%o1 + 0x18], %f16
+	ldd	[%o1 + 0x20], %f18
+	ldd	[%o1 + 0x28], %f20
+	ldd	[%o1 + 0x30], %f22
+	ldd	[%o1 + 0x38], %f24
+	ldd	[%o1 + 0x40], %f26
+
+	faligndata %f10, %f12, %f8
+	faligndata %f12, %f14, %f10
+	faligndata %f14, %f16, %f12
+	faligndata %f16, %f18, %f14
+	faligndata %f18, %f20, %f16
+	faligndata %f20, %f22, %f18
+	faligndata %f22, %f24, %f20
+	faligndata %f24, %f26, %f22
+
+	SHA256
+
+	subcc	%o2, 1, %o2
+	fsrc2	%f26, %f10
+	bne,pt	%xcc, 1b
+	 add	%o1, 0x40, %o1
+
+	ba,a,pt	%xcc, 5b
+ENDPROC(sha256_sparc64_transform)