From: James Hogan jhogan@kernel.org
[ Upstream commit bbc25bee37d2b32cf3a1fab9195b6da3a185614a ]
Current MIPS64r6 toolchains aren't able to generate efficient DMULU/DMUHU based code for the C implementation of umul_ppmm(), which performs an unsigned 64 x 64 bit multiply and returns the upper and lower 64-bit halves of the 128-bit result. Instead it widens the 64-bit inputs to 128-bits and emits a __multi3 intrinsic call to perform a 128 x 128 multiply. This is both inefficient, and it results in a link error since we don't include __multi3 in MIPS linux.
For example commit 90a53e4432b1 ("cfg80211: implement regdb signature checking") merged in v4.15-rc1 recently broke the 64r6_defconfig and 64r6el_defconfig builds by indirectly selecting MPILIB. The same build errors can be reproduced on older kernels by enabling e.g. CRYPTO_RSA:
lib/mpi/generic_mpih-mul1.o: In function `mpihelp_mul_1': lib/mpi/generic_mpih-mul1.c:50: undefined reference to `__multi3' lib/mpi/generic_mpih-mul2.o: In function `mpihelp_addmul_1': lib/mpi/generic_mpih-mul2.c:49: undefined reference to `__multi3' lib/mpi/generic_mpih-mul3.o: In function `mpihelp_submul_1': lib/mpi/generic_mpih-mul3.c:49: undefined reference to `__multi3' lib/mpi/mpih-div.o In function `mpihelp_divrem': lib/mpi/mpih-div.c:205: undefined reference to `__multi3' lib/mpi/mpih-div.c:142: undefined reference to `__multi3'
Therefore add an efficient MIPS64r6 implementation of umul_ppmm() using inline assembly and the DMULU/DMUHU instructions, to prevent __multi3 calls being emitted.
Fixes: 7fd08ca58ae6 ("MIPS: Add build support for the MIPS R6 ISA") Signed-off-by: James Hogan jhogan@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Herbert Xu herbert@gondor.apana.org.au Cc: "David S. Miller" davem@davemloft.net Cc: linux-mips@linux-mips.org Cc: linux-crypto@vger.kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- lib/mpi/longlong.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h index b90e255c2a68..d2ecf0a09180 100644 --- a/lib/mpi/longlong.h +++ b/lib/mpi/longlong.h @@ -671,7 +671,23 @@ do { \ ************** MIPS/64 ************** ***************************************/ #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64 -#if (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4) +#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 +/* + * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C + * code below, so we special case MIPS64r6 until the compiler can do better. + */ +#define umul_ppmm(w1, w0, u, v) \ +do { \ + __asm__ ("dmulu %0,%1,%2" \ + : "=d" ((UDItype)(w0)) \ + : "d" ((UDItype)(u)), \ + "d" ((UDItype)(v))); \ + __asm__ ("dmuhu %0,%1,%2" \ + : "=d" ((UDItype)(w1)) \ + : "d" ((UDItype)(u)), \ + "d" ((UDItype)(v))); \ +} while (0) +#elif (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4) #define umul_ppmm(w1, w0, u, v) \ do { \ typedef unsigned int __ll_UTItype __attribute__((mode(TI))); \