kernel: 5.4: import wireguard backport

Rather than using the clunky, old, slower wireguard-linux-compat out of
tree module, this commit does a patch-by-patch backport of upstream's
wireguard to 5.4. This specific backport is in widespread use, being
part of SUSE's enterprise kernel, Oracle's enterprise kernel, Google's
Android kernel, Gentoo's distro kernel, and probably more I've forgotten
about. It's definately the "more proper" way of adding wireguard to a
kernel than the ugly compat.h hell of the wireguard-linux-compat repo.
And most importantly for OpenWRT, it allows using the same module
configuration code for 5.10 as for 5.4, with no need for bifurcation.

These patches are from the backport tree which is maintained in the
open here: https://git.zx2c4.com/wireguard-linux/log/?h=backport-5.4.y
I'll be sending PRs to update this as needed.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

1 files changed, 148 insertions, 0 deletions

diff --git a/target/linux/generic/backport-5.4/080-wireguard-0059-crypto-x86-chacha-sse3-use-unaligned-loads-for-state.patch b/target/linux/generic/backport-5.4/080-wireguard-0059-crypto-x86-chacha-sse3-use-unaligned-loads-for-state.patch
new file mode 100644
index 0000000000..652439393b
--- /dev/null
+++ b/target/linux/generic/backport-5.4/080-wireguard-0059-crypto-x86-chacha-sse3-use-unaligned-loads-for-state.patch
@@ -0,0 +1,148 @@
+From 833ca409e17c10f4affb5879e22a03fdf1933439 Mon Sep 17 00:00:00 2001
+From: Ard Biesheuvel <ardb@kernel.org>
+Date: Wed, 8 Jul 2020 12:11:18 +0300
+Subject: [PATCH 059/124] crypto: x86/chacha-sse3 - use unaligned loads for
+ state array
+
+commit e79a31715193686e92dadb4caedfbb1f5de3659c upstream.
+
+Due to the fact that the x86 port does not support allocating objects
+on the stack with an alignment that exceeds 8 bytes, we have a rather
+ugly hack in the x86 code for ChaCha to ensure that the state array is
+aligned to 16 bytes, allowing the SSE3 implementation of the algorithm
+to use aligned loads.
+
+Given that the performance benefit of using of aligned loads appears to
+be limited (~0.25% for 1k blocks using tcrypt on a Corei7-8650U), and
+the fact that this hack has leaked into generic ChaCha code, let's just
+remove it.
+
+Cc: Martin Willi <martin@strongswan.org>
+Cc: Herbert Xu <herbert@gondor.apana.org.au>
+Cc: Eric Biggers <ebiggers@kernel.org>
+Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
+Reviewed-by: Martin Willi <martin@strongswan.org>
+Reviewed-by: Eric Biggers <ebiggers@google.com>
+Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ arch/x86/crypto/chacha-ssse3-x86_64.S | 16 ++++++++--------
+ arch/x86/crypto/chacha_glue.c         | 17 ++---------------
+ include/crypto/chacha.h               |  4 ----
+ 3 files changed, 10 insertions(+), 27 deletions(-)
+
+--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
++++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
+@@ -120,10 +120,10 @@ ENTRY(chacha_block_xor_ssse3)
+ 	FRAME_BEGIN
+ 
+ 	# x0..3 = s0..3
+-	movdqa		0x00(%rdi),%xmm0
+-	movdqa		0x10(%rdi),%xmm1
+-	movdqa		0x20(%rdi),%xmm2
+-	movdqa		0x30(%rdi),%xmm3
++	movdqu		0x00(%rdi),%xmm0
++	movdqu		0x10(%rdi),%xmm1
++	movdqu		0x20(%rdi),%xmm2
++	movdqu		0x30(%rdi),%xmm3
+ 	movdqa		%xmm0,%xmm8
+ 	movdqa		%xmm1,%xmm9
+ 	movdqa		%xmm2,%xmm10
+@@ -205,10 +205,10 @@ ENTRY(hchacha_block_ssse3)
+ 	# %edx: nrounds
+ 	FRAME_BEGIN
+ 
+-	movdqa		0x00(%rdi),%xmm0
+-	movdqa		0x10(%rdi),%xmm1
+-	movdqa		0x20(%rdi),%xmm2
+-	movdqa		0x30(%rdi),%xmm3
++	movdqu		0x00(%rdi),%xmm0
++	movdqu		0x10(%rdi),%xmm1
++	movdqu		0x20(%rdi),%xmm2
++	movdqu		0x30(%rdi),%xmm3
+ 
+ 	mov		%edx,%r8d
+ 	call		chacha_permute
+--- a/arch/x86/crypto/chacha_glue.c
++++ b/arch/x86/crypto/chacha_glue.c
+@@ -14,8 +14,6 @@
+ #include <linux/module.h>
+ #include <asm/simd.h>
+ 
+-#define CHACHA_STATE_ALIGN 16
+-
+ asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
+ 				       unsigned int len, int nrounds);
+ asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
+@@ -125,8 +123,6 @@ static void chacha_dosimd(u32 *state, u8
+ 
+ void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+ {
+-	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+-
+ 	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
+ 		hchacha_block_generic(state, stream, nrounds);
+ 	} else {
+@@ -139,8 +135,6 @@ EXPORT_SYMBOL(hchacha_block_arch);
+ 
+ void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+ {
+-	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+-
+ 	chacha_init_generic(state, key, iv);
+ }
+ EXPORT_SYMBOL(chacha_init_arch);
+@@ -148,8 +142,6 @@ EXPORT_SYMBOL(chacha_init_arch);
+ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ 		       int nrounds)
+ {
+-	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+-
+ 	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
+ 	    bytes <= CHACHA_BLOCK_SIZE)
+ 		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+@@ -171,15 +163,12 @@ EXPORT_SYMBOL(chacha_crypt_arch);
+ static int chacha_simd_stream_xor(struct skcipher_request *req,
+ 				  const struct chacha_ctx *ctx, const u8 *iv)
+ {
+-	u32 *state, state_buf[16 + 2] __aligned(8);
++	u32 state[CHACHA_STATE_WORDS] __aligned(8);
+ 	struct skcipher_walk walk;
+ 	int err;
+ 
+ 	err = skcipher_walk_virt(&walk, req, false);
+ 
+-	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
+-	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
+-
+ 	chacha_init_generic(state, ctx->key, iv);
+ 
+ 	while (walk.nbytes > 0) {
+@@ -218,12 +207,10 @@ static int xchacha_simd(struct skcipher_
+ {
+ 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+-	u32 *state, state_buf[16 + 2] __aligned(8);
++	u32 state[CHACHA_STATE_WORDS] __aligned(8);
+ 	struct chacha_ctx subctx;
+ 	u8 real_iv[16];
+ 
+-	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
+-	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
+ 	chacha_init_generic(state, ctx->key, req->iv);
+ 
+ 	if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
+--- a/include/crypto/chacha.h
++++ b/include/crypto/chacha.h
+@@ -25,11 +25,7 @@
+ #define CHACHA_BLOCK_SIZE	64
+ #define CHACHAPOLY_IV_SIZE	12
+ 
+-#ifdef CONFIG_X86_64
+-#define CHACHA_STATE_WORDS	((CHACHA_BLOCK_SIZE + 12) / sizeof(u32))
+-#else
+ #define CHACHA_STATE_WORDS	(CHACHA_BLOCK_SIZE / sizeof(u32))
+-#endif
+ 
+ /* 192-bit nonce, then 64-bit stream position */
+ #define XCHACHA_IV_SIZE		32