diff options
Diffstat (limited to 'sysdeps/x86_64/dl-trampoline.S')
| -rw-r--r-- | sysdeps/x86_64/dl-trampoline.S | 462 |
1 files changed, 73 insertions, 389 deletions
diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S index 678c57fc24..8475d26d07 100644 --- a/sysdeps/x86_64/dl-trampoline.S +++ b/sysdeps/x86_64/dl-trampoline.S @@ -20,23 +20,40 @@ #include <sysdep.h> #include <link-defines.h> -#if (RTLD_SAVESPACE_SSE % 32) != 0 -# error RTLD_SAVESPACE_SSE must be aligned to 32 bytes +#ifndef DL_STACK_ALIGNMENT +/* Due to GCC bug: + + https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58066 + + __tls_get_addr may be called with 8-byte stack alignment. Although + this bug has been fixed in GCC 4.9.4, 5.3 and 6, we can't assume + that stack will be always aligned at 16 bytes. We use unaligned + 16-byte move to load and store SSE registers, which has no penalty + on modern processors if stack is 16-byte aligned. */ +# define DL_STACK_ALIGNMENT 8 +#endif + +#ifndef DL_RUNIME_UNALIGNED_VEC_SIZE +/* The maximum size of unaligned vector load and store. */ +# define DL_RUNIME_UNALIGNED_VEC_SIZE 16 #endif +/* True if _dl_runtime_resolve should align stack to VEC_SIZE bytes. */ +#define DL_RUNIME_RESOLVE_REALIGN_STACK \ + (VEC_SIZE > DL_STACK_ALIGNMENT \ + && VEC_SIZE > DL_RUNIME_UNALIGNED_VEC_SIZE) + +/* Align vector register save area to 16 bytes. */ +#define REGISTER_SAVE_VEC_OFF 0 + /* Area on stack to save and restore registers used for parameter passing when calling _dl_fixup. */ #ifdef __ILP32__ -/* X32 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX. */ -# define REGISTER_SAVE_AREA (8 * 7) -# define REGISTER_SAVE_RAX 0 +# define REGISTER_SAVE_RAX (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8) # define PRESERVE_BND_REGS_PREFIX #else -/* X86-64 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as BND0, - BND1, BND2, BND3. */ -# define REGISTER_SAVE_AREA (8 * 7 + 16 * 4) /* Align bound register save area to 16 bytes. */ -# define REGISTER_SAVE_BND0 0 +# define REGISTER_SAVE_BND0 (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8) # define REGISTER_SAVE_BND1 (REGISTER_SAVE_BND0 + 16) # define REGISTER_SAVE_BND2 (REGISTER_SAVE_BND1 + 16) # define REGISTER_SAVE_BND3 (REGISTER_SAVE_BND2 + 16) @@ -54,386 +71,53 @@ #define REGISTER_SAVE_R8 (REGISTER_SAVE_RDI + 8) #define REGISTER_SAVE_R9 (REGISTER_SAVE_R8 + 8) - .text - .globl _dl_runtime_resolve - .type _dl_runtime_resolve, @function - .align 16 - cfi_startproc -_dl_runtime_resolve: - cfi_adjust_cfa_offset(16) # Incorporate PLT - subq $REGISTER_SAVE_AREA,%rsp - cfi_adjust_cfa_offset(REGISTER_SAVE_AREA) - # Preserve registers otherwise clobbered. - movq %rax, REGISTER_SAVE_RAX(%rsp) - movq %rcx, REGISTER_SAVE_RCX(%rsp) - movq %rdx, REGISTER_SAVE_RDX(%rsp) - movq %rsi, REGISTER_SAVE_RSI(%rsp) - movq %rdi, REGISTER_SAVE_RDI(%rsp) - movq %r8, REGISTER_SAVE_R8(%rsp) - movq %r9, REGISTER_SAVE_R9(%rsp) -#ifndef __ILP32__ - # We also have to preserve bound registers. These are nops if - # Intel MPX isn't available or disabled. -# ifdef HAVE_MPX_SUPPORT - bndmov %bnd0, REGISTER_SAVE_BND0(%rsp) - bndmov %bnd1, REGISTER_SAVE_BND1(%rsp) - bndmov %bnd2, REGISTER_SAVE_BND2(%rsp) - bndmov %bnd3, REGISTER_SAVE_BND3(%rsp) -# else -# if REGISTER_SAVE_BND0 == 0 - .byte 0x66,0x0f,0x1b,0x04,0x24 -# else - .byte 0x66,0x0f,0x1b,0x44,0x24,REGISTER_SAVE_BND0 -# endif - .byte 0x66,0x0f,0x1b,0x4c,0x24,REGISTER_SAVE_BND1 - .byte 0x66,0x0f,0x1b,0x54,0x24,REGISTER_SAVE_BND2 - .byte 0x66,0x0f,0x1b,0x5c,0x24,REGISTER_SAVE_BND3 -# endif -#endif - # Copy args pushed by PLT in register. - # %rdi: link_map, %rsi: reloc_index - movq (REGISTER_SAVE_AREA + 8)(%rsp), %rsi - movq REGISTER_SAVE_AREA(%rsp), %rdi - call _dl_fixup # Call resolver. - movq %rax, %r11 # Save return value -#ifndef __ILP32__ - # Restore bound registers. These are nops if Intel MPX isn't - # avaiable or disabled. -# ifdef HAVE_MPX_SUPPORT - bndmov REGISTER_SAVE_BND3(%rsp), %bnd3 - bndmov REGISTER_SAVE_BND2(%rsp), %bnd2 - bndmov REGISTER_SAVE_BND1(%rsp), %bnd1 - bndmov REGISTER_SAVE_BND0(%rsp), %bnd0 -# else - .byte 0x66,0x0f,0x1a,0x5c,0x24,REGISTER_SAVE_BND3 - .byte 0x66,0x0f,0x1a,0x54,0x24,REGISTER_SAVE_BND2 - .byte 0x66,0x0f,0x1a,0x4c,0x24,REGISTER_SAVE_BND1 -# if REGISTER_SAVE_BND0 == 0 - .byte 0x66,0x0f,0x1a,0x04,0x24 -# else - .byte 0x66,0x0f,0x1a,0x44,0x24,REGISTER_SAVE_BND0 -# endif -# endif +#define VEC_SIZE 64 +#define VMOVA vmovdqa64 +#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT +# define VMOV vmovdqa64 +#else +# define VMOV vmovdqu64 #endif - # Get register content back. - movq REGISTER_SAVE_R9(%rsp), %r9 - movq REGISTER_SAVE_R8(%rsp), %r8 - movq REGISTER_SAVE_RDI(%rsp), %rdi - movq REGISTER_SAVE_RSI(%rsp), %rsi - movq REGISTER_SAVE_RDX(%rsp), %rdx - movq REGISTER_SAVE_RCX(%rsp), %rcx - movq REGISTER_SAVE_RAX(%rsp), %rax - # Adjust stack(PLT did 2 pushes) - addq $(REGISTER_SAVE_AREA + 16), %rsp - cfi_adjust_cfa_offset(-(REGISTER_SAVE_AREA + 16)) - # Preserve bound registers. - PRESERVE_BND_REGS_PREFIX - jmp *%r11 # Jump to function address. - cfi_endproc - .size _dl_runtime_resolve, .-_dl_runtime_resolve - - -#ifndef PROF - .globl _dl_runtime_profile - .type _dl_runtime_profile, @function - .align 16 - cfi_startproc - -_dl_runtime_profile: - cfi_adjust_cfa_offset(16) # Incorporate PLT - /* The La_x86_64_regs data structure pointed to by the - fourth paramater must be 16-byte aligned. This must - be explicitly enforced. We have the set up a dynamically - sized stack frame. %rbx points to the top half which - has a fixed size and preserves the original stack pointer. */ - - subq $32, %rsp # Allocate the local storage. - cfi_adjust_cfa_offset(32) - movq %rbx, (%rsp) - cfi_rel_offset(%rbx, 0) - - /* On the stack: - 56(%rbx) parameter #1 - 48(%rbx) return address - - 40(%rbx) reloc index - 32(%rbx) link_map - - 24(%rbx) La_x86_64_regs pointer - 16(%rbx) framesize - 8(%rbx) rax - (%rbx) rbx - */ - - movq %rax, 8(%rsp) - movq %rsp, %rbx - cfi_def_cfa_register(%rbx) - - /* Actively align the La_x86_64_regs structure. */ - andq $0xfffffffffffffff0, %rsp -# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT - /* sizeof(La_x86_64_regs). Need extra space for 8 SSE registers - to detect if any xmm0-xmm7 registers are changed by audit - module. */ - subq $(LR_SIZE + XMM_SIZE*8), %rsp -# else - subq $LR_SIZE, %rsp # sizeof(La_x86_64_regs) -# endif - movq %rsp, 24(%rbx) - - /* Fill the La_x86_64_regs structure. */ - movq %rdx, LR_RDX_OFFSET(%rsp) - movq %r8, LR_R8_OFFSET(%rsp) - movq %r9, LR_R9_OFFSET(%rsp) - movq %rcx, LR_RCX_OFFSET(%rsp) - movq %rsi, LR_RSI_OFFSET(%rsp) - movq %rdi, LR_RDI_OFFSET(%rsp) - movq %rbp, LR_RBP_OFFSET(%rsp) - - leaq 48(%rbx), %rax - movq %rax, LR_RSP_OFFSET(%rsp) - - /* We always store the XMM registers even if AVX is available. - This is to provide backward binary compatibility for existing - audit modules. */ - movaps %xmm0, (LR_XMM_OFFSET)(%rsp) - movaps %xmm1, (LR_XMM_OFFSET + XMM_SIZE)(%rsp) - movaps %xmm2, (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp) - movaps %xmm3, (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp) - movaps %xmm4, (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp) - movaps %xmm5, (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp) - movaps %xmm6, (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp) - movaps %xmm7, (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp) - -# ifndef __ILP32__ -# ifdef HAVE_MPX_SUPPORT - bndmov %bnd0, (LR_BND_OFFSET)(%rsp) # Preserve bound - bndmov %bnd1, (LR_BND_OFFSET + BND_SIZE)(%rsp) # registers. Nops if - bndmov %bnd2, (LR_BND_OFFSET + BND_SIZE*2)(%rsp) # MPX not available - bndmov %bnd3, (LR_BND_OFFSET + BND_SIZE*3)(%rsp) # or disabled. -# else - .byte 0x66,0x0f,0x1b,0x84,0x24;.long (LR_BND_OFFSET) - .byte 0x66,0x0f,0x1b,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE) - .byte 0x66,0x0f,0x1b,0x94,0x24;.long (LR_BND_OFFSET + BND_SIZE*2) - .byte 0x66,0x0f,0x1b,0x9c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3) -# endif -# endif - -# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT - .data -L(have_avx): - .zero 4 - .size L(have_avx), 4 - .previous - - cmpl $0, L(have_avx)(%rip) - jne L(defined) - movq %rbx, %r11 # Save rbx - movl $1, %eax - cpuid - movq %r11,%rbx # Restore rbx - xorl %eax, %eax - // AVX and XSAVE supported? - andl $((1 << 28) | (1 << 27)), %ecx - cmpl $((1 << 28) | (1 << 27)), %ecx - jne 10f -# ifdef HAVE_AVX512_ASM_SUPPORT - // AVX512 supported in processor? - movq %rbx, %r11 # Save rbx - xorl %ecx, %ecx - mov $0x7, %eax - cpuid - andl $(1 << 16), %ebx -# endif - xorl %ecx, %ecx - // Get XFEATURE_ENABLED_MASK - xgetbv -# ifdef HAVE_AVX512_ASM_SUPPORT - test %ebx, %ebx - movq %r11, %rbx # Restore rbx - je 20f - // Verify that XCR0[7:5] = '111b' and - // XCR0[2:1] = '11b' which means - // that zmm state is enabled - andl $0xe6, %eax - cmpl $0xe6, %eax - jne 20f - movl %eax, L(have_avx)(%rip) -L(avx512): -# define RESTORE_AVX -# define VMOV vmovdqu64 -# define VEC(i) zmm##i -# define MORE_CODE -# include "dl-trampoline.h" -# undef VMOV -# undef VEC -# undef RESTORE_AVX -# endif -20: andl $0x6, %eax -10: subl $0x5, %eax - movl %eax, L(have_avx)(%rip) - cmpl $0, %eax - -L(defined): - js L(no_avx) -# ifdef HAVE_AVX512_ASM_SUPPORT - cmpl $0xe6, L(have_avx)(%rip) - je L(avx512) -# endif - -# define RESTORE_AVX -# define VMOV vmovdqu -# define VEC(i) ymm##i -# define MORE_CODE -# include "dl-trampoline.h" - - .align 16 -L(no_avx): -# endif - -# undef RESTORE_AVX -# include "dl-trampoline.h" - - cfi_endproc - .size _dl_runtime_profile, .-_dl_runtime_profile +#define VEC(i) zmm##i +#define _dl_runtime_resolve _dl_runtime_resolve_avx512 +#define _dl_runtime_profile _dl_runtime_profile_avx512 +#define RESTORE_AVX +#include "dl-trampoline.h" +#undef _dl_runtime_resolve +#undef _dl_runtime_profile +#undef VEC +#undef VMOV +#undef VMOVA +#undef VEC_SIZE + +#define VEC_SIZE 32 +#define VMOVA vmovdqa +#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT +# define VMOV vmovdqa +#else +# define VMOV vmovdqu #endif - - -#ifdef SHARED - .globl _dl_x86_64_save_sse - .type _dl_x86_64_save_sse, @function - .align 16 - cfi_startproc -_dl_x86_64_save_sse: -# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT - cmpl $0, L(have_avx)(%rip) - jne L(defined_5) - movq %rbx, %r11 # Save rbx - movl $1, %eax - cpuid - movq %r11,%rbx # Restore rbx - xorl %eax, %eax - // AVX and XSAVE supported? - andl $((1 << 28) | (1 << 27)), %ecx - cmpl $((1 << 28) | (1 << 27)), %ecx - jne 1f -# ifdef HAVE_AVX512_ASM_SUPPORT - // AVX512 supported in a processor? - movq %rbx, %r11 # Save rbx - xorl %ecx,%ecx - mov $0x7,%eax - cpuid - andl $(1 << 16), %ebx -# endif - xorl %ecx, %ecx - // Get XFEATURE_ENABLED_MASK - xgetbv -# ifdef HAVE_AVX512_ASM_SUPPORT - test %ebx, %ebx - movq %r11, %rbx # Restore rbx - je 2f - // Verify that XCR0[7:5] = '111b' and - // XCR0[2:1] = '11b' which means - // that zmm state is enabled - andl $0xe6, %eax - movl %eax, L(have_avx)(%rip) - cmpl $0xe6, %eax - je L(avx512_5) -# endif - -2: andl $0x6, %eax -1: subl $0x5, %eax - movl %eax, L(have_avx)(%rip) - cmpl $0, %eax - -L(defined_5): - js L(no_avx5) -# ifdef HAVE_AVX512_ASM_SUPPORT - cmpl $0xe6, L(have_avx)(%rip) - je L(avx512_5) -# endif - - vmovdqa %ymm0, %fs:RTLD_SAVESPACE_SSE+0*YMM_SIZE - vmovdqa %ymm1, %fs:RTLD_SAVESPACE_SSE+1*YMM_SIZE - vmovdqa %ymm2, %fs:RTLD_SAVESPACE_SSE+2*YMM_SIZE - vmovdqa %ymm3, %fs:RTLD_SAVESPACE_SSE+3*YMM_SIZE - vmovdqa %ymm4, %fs:RTLD_SAVESPACE_SSE+4*YMM_SIZE - vmovdqa %ymm5, %fs:RTLD_SAVESPACE_SSE+5*YMM_SIZE - vmovdqa %ymm6, %fs:RTLD_SAVESPACE_SSE+6*YMM_SIZE - vmovdqa %ymm7, %fs:RTLD_SAVESPACE_SSE+7*YMM_SIZE - ret -# ifdef HAVE_AVX512_ASM_SUPPORT -L(avx512_5): - vmovdqu64 %zmm0, %fs:RTLD_SAVESPACE_SSE+0*ZMM_SIZE - vmovdqu64 %zmm1, %fs:RTLD_SAVESPACE_SSE+1*ZMM_SIZE - vmovdqu64 %zmm2, %fs:RTLD_SAVESPACE_SSE+2*ZMM_SIZE - vmovdqu64 %zmm3, %fs:RTLD_SAVESPACE_SSE+3*ZMM_SIZE - vmovdqu64 %zmm4, %fs:RTLD_SAVESPACE_SSE+4*ZMM_SIZE - vmovdqu64 %zmm5, %fs:RTLD_SAVESPACE_SSE+5*ZMM_SIZE - vmovdqu64 %zmm6, %fs:RTLD_SAVESPACE_SSE+6*ZMM_SIZE - vmovdqu64 %zmm7, %fs:RTLD_SAVESPACE_SSE+7*ZMM_SIZE - ret -# endif -L(no_avx5): -# endif - movdqa %xmm0, %fs:RTLD_SAVESPACE_SSE+0*XMM_SIZE - movdqa %xmm1, %fs:RTLD_SAVESPACE_SSE+1*XMM_SIZE - movdqa %xmm2, %fs:RTLD_SAVESPACE_SSE+2*XMM_SIZE - movdqa %xmm3, %fs:RTLD_SAVESPACE_SSE+3*XMM_SIZE - movdqa %xmm4, %fs:RTLD_SAVESPACE_SSE+4*XMM_SIZE - movdqa %xmm5, %fs:RTLD_SAVESPACE_SSE+5*XMM_SIZE - movdqa %xmm6, %fs:RTLD_SAVESPACE_SSE+6*XMM_SIZE - movdqa %xmm7, %fs:RTLD_SAVESPACE_SSE+7*XMM_SIZE - ret - cfi_endproc - .size _dl_x86_64_save_sse, .-_dl_x86_64_save_sse - - - .globl _dl_x86_64_restore_sse - .type _dl_x86_64_restore_sse, @function - .align 16 - cfi_startproc -_dl_x86_64_restore_sse: -# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT - cmpl $0, L(have_avx)(%rip) - js L(no_avx6) -# ifdef HAVE_AVX512_ASM_SUPPORT - cmpl $0xe6, L(have_avx)(%rip) - je L(avx512_6) -# endif - - vmovdqa %fs:RTLD_SAVESPACE_SSE+0*YMM_SIZE, %ymm0 - vmovdqa %fs:RTLD_SAVESPACE_SSE+1*YMM_SIZE, %ymm1 - vmovdqa %fs:RTLD_SAVESPACE_SSE+2*YMM_SIZE, %ymm2 - vmovdqa %fs:RTLD_SAVESPACE_SSE+3*YMM_SIZE, %ymm3 - vmovdqa %fs:RTLD_SAVESPACE_SSE+4*YMM_SIZE, %ymm4 - vmovdqa %fs:RTLD_SAVESPACE_SSE+5*YMM_SIZE, %ymm5 - vmovdqa %fs:RTLD_SAVESPACE_SSE+6*YMM_SIZE, %ymm6 - vmovdqa %fs:RTLD_SAVESPACE_SSE+7*YMM_SIZE, %ymm7 - ret -# ifdef HAVE_AVX512_ASM_SUPPORT -L(avx512_6): - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+0*ZMM_SIZE, %zmm0 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+1*ZMM_SIZE, %zmm1 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+2*ZMM_SIZE, %zmm2 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+3*ZMM_SIZE, %zmm3 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+4*ZMM_SIZE, %zmm4 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+5*ZMM_SIZE, %zmm5 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+6*ZMM_SIZE, %zmm6 - vmovdqu64 %fs:RTLD_SAVESPACE_SSE+7*ZMM_SIZE, %zmm7 - ret -# endif -L(no_avx6): -# endif - movdqa %fs:RTLD_SAVESPACE_SSE+0*XMM_SIZE, %xmm0 - movdqa %fs:RTLD_SAVESPACE_SSE+1*XMM_SIZE, %xmm1 - movdqa %fs:RTLD_SAVESPACE_SSE+2*XMM_SIZE, %xmm2 - movdqa %fs:RTLD_SAVESPACE_SSE+3*XMM_SIZE, %xmm3 - movdqa %fs:RTLD_SAVESPACE_SSE+4*XMM_SIZE, %xmm4 - movdqa %fs:RTLD_SAVESPACE_SSE+5*XMM_SIZE, %xmm5 - movdqa %fs:RTLD_SAVESPACE_SSE+6*XMM_SIZE, %xmm6 - movdqa %fs:RTLD_SAVESPACE_SSE+7*XMM_SIZE, %xmm7 - ret - cfi_endproc - .size _dl_x86_64_restore_sse, .-_dl_x86_64_restore_sse +#define VEC(i) ymm##i +#define _dl_runtime_resolve _dl_runtime_resolve_avx +#define _dl_runtime_profile _dl_runtime_profile_avx +#include "dl-trampoline.h" +#undef _dl_runtime_resolve +#undef _dl_runtime_profile +#undef VEC +#undef VMOV +#undef VMOVA +#undef VEC_SIZE + +/* movaps/movups is 1-byte shorter. */ +#define VEC_SIZE 16 +#define VMOVA movaps +#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT +# define VMOV movaps +#else +# define VMOV movups #endif +#define VEC(i) xmm##i +#define _dl_runtime_resolve _dl_runtime_resolve_sse +#define _dl_runtime_profile _dl_runtime_profile_sse +#undef RESTORE_AVX +#include "dl-trampoline.h" |