This is a note to let you know that I've just added the patch titled lib/mpi: Fix umul_ppmm() for MIPS64r6 to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: lib-mpi-fix-umul_ppmm-for-mips64r6.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From foo@baz Wed Feb 28 16:23:28 CET 2018 From: James Hogan <jhogan@xxxxxxxxxx> Date: Tue, 5 Dec 2017 23:31:35 +0000 Subject: lib/mpi: Fix umul_ppmm() for MIPS64r6 From: James Hogan <jhogan@xxxxxxxxxx> [ 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@xxxxxxxxxx> Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx> Cc: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> Cc: "David S. Miller" <davem@xxxxxxxxxxxxx> Cc: linux-mips@xxxxxxxxxxxxxx Cc: linux-crypto@xxxxxxxxxxxxxxx Signed-off-by: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- lib/mpi/longlong.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) --- 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))); \ Patches currently in stable-queue which might be from jhogan@xxxxxxxxxx are queue-4.14/lib-mpi-fix-umul_ppmm-for-mips64r6.patch