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, 75 insertions, 0 deletions

diff --git a/target/linux/generic/backport-5.4/080-wireguard-0028-crypto-lib-curve25519-work-around-Clang-stack-spilli.patch b/target/linux/generic/backport-5.4/080-wireguard-0028-crypto-lib-curve25519-work-around-Clang-stack-spilli.patch
new file mode 100644
index 0000000000..b38f3f74f0
--- /dev/null
+++ b/target/linux/generic/backport-5.4/080-wireguard-0028-crypto-lib-curve25519-work-around-Clang-stack-spilli.patch
@@ -0,0 +1,75 @@
+From 3c710fa0cdbf9362df4e3b36be338779662b30a6 Mon Sep 17 00:00:00 2001
+From: Ard Biesheuvel <ardb@kernel.org>
+Date: Fri, 8 Nov 2019 13:22:35 +0100
+Subject: [PATCH 028/124] crypto: lib/curve25519 - work around Clang stack
+ spilling issue
+
+commit 660bb8e1f833ea63185fe80fde847e3e42f18e3b upstream.
+
+Arnd reports that the 32-bit generic library code for Curve25119 ends
+up using an excessive amount of stack space when built with Clang:
+
+  lib/crypto/curve25519-fiat32.c:756:6: error: stack frame size
+      of 1384 bytes in function 'curve25519_generic'
+      [-Werror,-Wframe-larger-than=]
+
+Let's give some hints to the compiler regarding which routines should
+not be inlined, to prevent it from running out of registers and spilling
+to the stack. The resulting code performs identically under both GCC
+and Clang, and makes the warning go away.
+
+Suggested-by: Arnd Bergmann <arnd@arndb.de>
+Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
+Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ lib/crypto/curve25519-fiat32.c | 10 +++++-----
+ 1 file changed, 5 insertions(+), 5 deletions(-)
+
+--- a/lib/crypto/curve25519-fiat32.c
++++ b/lib/crypto/curve25519-fiat32.c
+@@ -223,7 +223,7 @@ static __always_inline void fe_1(fe *h)
+ 	h->v[0] = 1;
+ }
+ 
+-static void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
++static noinline void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
+ {
+ 	{ const u32 x20 = in1[9];
+ 	{ const u32 x21 = in1[8];
+@@ -266,7 +266,7 @@ static __always_inline void fe_add(fe_lo
+ 	fe_add_impl(h->v, f->v, g->v);
+ }
+ 
+-static void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
++static noinline void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
+ {
+ 	{ const u32 x20 = in1[9];
+ 	{ const u32 x21 = in1[8];
+@@ -309,7 +309,7 @@ static __always_inline void fe_sub(fe_lo
+ 	fe_sub_impl(h->v, f->v, g->v);
+ }
+ 
+-static void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
++static noinline void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
+ {
+ 	{ const u32 x20 = in1[9];
+ 	{ const u32 x21 = in1[8];
+@@ -441,7 +441,7 @@ fe_mul_tll(fe *h, const fe_loose *f, con
+ 	fe_mul_impl(h->v, f->v, g->v);
+ }
+ 
+-static void fe_sqr_impl(u32 out[10], const u32 in1[10])
++static noinline void fe_sqr_impl(u32 out[10], const u32 in1[10])
+ {
+ 	{ const u32 x17 = in1[9];
+ 	{ const u32 x18 = in1[8];
+@@ -619,7 +619,7 @@ static __always_inline void fe_invert(fe
+  *
+  * Preconditions: b in {0,1}
+  */
+-static __always_inline void fe_cswap(fe *f, fe *g, unsigned int b)
++static noinline void fe_cswap(fe *f, fe *g, unsigned int b)
+ {
+ 	unsigned i;
+ 	b = 0 - b;