From: 沈子俊 shenzijun@kylinos.cn
mainline inclusion from mainline-v5.16 commit 4a7e1e5fc294687a8941fa3eeb4a7e8539ca5e2f category: bugfix bugzilla: NA CVE: NA
-----------------------------------------------------------------
When building with clang and GNU as, there is a warning about ignored changed section attributes:
/tmp/sm4-c916c8.s: Assembler messages: /tmp/sm4-c916c8.s:677: Warning: ignoring changed section attributes for .data..cacheline_aligned
"static const" places the data in .rodata but __cacheline_aligned has the section attribute to place it in .data..cacheline_aligned, in addition to the aligned attribute.
To keep the alignment but avoid attempting to change sections, use the ____cacheline_aligned attribute, which is just the aligned attribute.
Fixes: 2b31277af577 ("crypto: sm4 - create SM4 library based on sm4 generic code") Link: https://github.com/ClangBuiltLinux/linux/issues/1441 Signed-off-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Tianjia Zhang tianjia.zhang@linux.alibaba.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: 沈子俊 shenzijun@kylinos.cn --- lib/crypto/sm4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/crypto/sm4.c b/lib/crypto/sm4.c index 633b59fed9db..284e62576d0c 100644 --- a/lib/crypto/sm4.c +++ b/lib/crypto/sm4.c @@ -15,7 +15,7 @@ static const u32 fk[4] = { 0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc };
-static const u32 __cacheline_aligned ck[32] = { +static const u32 ____cacheline_aligned ck[32] = { 0x00070e15, 0x1c232a31, 0x383f464d, 0x545b6269, 0x70777e85, 0x8c939aa1, 0xa8afb6bd, 0xc4cbd2d9, 0xe0e7eef5, 0xfc030a11, 0x181f262d, 0x343b4249, @@ -26,7 +26,7 @@ static const u32 __cacheline_aligned ck[32] = { 0x10171e25, 0x2c333a41, 0x484f565d, 0x646b7279 };
-static const u8 __cacheline_aligned sbox[256] = { +static const u8 ____cacheline_aligned sbox[256] = { 0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7, 0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05, 0x2b, 0x67, 0x9a, 0x76, 0x2a, 0xbe, 0x04, 0xc3,
From: 沈子俊 shenzijun@kylinos.cn
mainline inclusion from mainline-v5.15 commit 0e14ef38669ce4faa80589247fe8ed8a3780f414 category: bugfix bugzilla: NA CVE: NA
-----------------------------------------------------------------------
sm4_aesni_avx_crypt8() sets up the frame pointer (which includes pushing RBP) before doing a conditional sibling call to sm4_aesni_avx_crypt4(), which sets up an additional frame pointer. Things will not go well when sm4_aesni_avx_crypt4() pops only the innermost single frame pointer and then tries to return to the outermost frame pointer.
Sibling calls need to occur with an empty stack frame. Do the conditional sibling call *before* setting up the stack pointer.
This fixes the following warning:
arch/x86/crypto/sm4-aesni-avx-asm_64.o: warning: objtool: sm4_aesni_avx_crypt8()+0x8: sibling call from callable instruction with modified stack frame
Fixes: a7ee22ee1445 ("crypto: x86/sm4 - add AES-NI/AVX/x86_64 implementation") Reported-by: kernel test robot lkp@intel.com Reported-by: Arnd Bergmann arnd@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Tianjia Zhang tianjia.zhang@linux.alibaba.com Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: 沈子俊 shenzijun@kylinos.cn --- arch/x86/crypto/sm4-aesni-avx-asm_64.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index fa2c3f50aecb..18d2f5199194 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -367,10 +367,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8) * %rdx: src (1..8 blocks) * %rcx: num blocks (1..8) */ - FRAME_BEGIN - cmpq $5, %rcx; jb sm4_aesni_avx_crypt4; + + FRAME_BEGIN + vmovdqu (0 * 16)(%rdx), RA0; vmovdqu (1 * 16)(%rdx), RA1; vmovdqu (2 * 16)(%rdx), RA2;
From: 沈子俊 shenzijun@kylinos.cn
mainline inclusion from mainline-v5.15 commit f8690a4b5a1b64f74ae5c4f7c4ea880d8a8e1a0d category: bugfix bugzilla: NA CVE: NA
--------------------------------------------------------------
This fixes the following warning:
vmlinux.o: warning: objtool: elf_update: invalid section entry size
The size of the rodata section is 164 bytes, directly using the entry_size of 164 bytes will cause errors in some versions of the gcc compiler, while using 16 bytes directly will cause errors in the clang compiler. This patch correct it by filling the size of rodata to a 16-byte boundary.
Fixes: a7ee22ee1445 ("crypto: x86/sm4 - add AES-NI/AVX/x86_64 implementation") Fixes: 5b2efa2bb865 ("crypto: x86/sm4 - add AES-NI/AVX2/x86_64 implementation") Reported-by: Peter Zijlstra peterz@infradead.org Reported-by: Abaci Robot abaci@linux.alibaba.com Signed-off-by: Tianjia Zhang tianjia.zhang@linux.alibaba.com Tested-by: Heyuan Shi heyuan@linux.alibaba.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: 沈子俊 shenzijun@kylinos.cn --- arch/x86/crypto/sm4-aesni-avx-asm_64.S | 6 +++++- arch/x86/crypto/sm4-aesni-avx2-asm_64.S | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index 18d2f5199194..1cc72b4804fa 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -78,7 +78,7 @@ vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164 +.section .rodata.cst16, "aM", @progbits, 16 .align 16
/* @@ -133,6 +133,10 @@ .L0f0f0f0f: .long 0x0f0f0f0f
+/* 12 bytes, only for padding */ +.Lpadding_deadbeef: + .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef +
.text .align 16 diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S index d2ffd7f76ee2..9c5d3f3ad45a 100644 --- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S @@ -93,7 +93,7 @@ vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164 +.section .rodata.cst16, "aM", @progbits, 16 .align 16
/* @@ -148,6 +148,10 @@ .L0f0f0f0f: .long 0x0f0f0f0f
+/* 12 bytes, only for padding */ +.Lpadding_deadbeef: + .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef + .text .align 16
-
shenzijun