crypto: lib/curve25519 - work around Clang stack spilling issue

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>

diff --git a/lib/crypto/curve25519-fiat32.c b/lib/crypto/curve25519-fiat32.c
index 1c455207341d3f81345f2b1f2bb8c294c446b22e..2fde0ec33dbd0873147c064ac9afec8eccd7e690 100644 (file)
--- 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_loose *h, const fe *f, const fe *g)
        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_loose *h, const fe *f, const fe *g)
        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, const fe_loose *g)
        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 *out, const fe *z)
  *
  * 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;