diff options
Diffstat (limited to 'lld/COFF/DLL.cpp')
| -rw-r--r-- | lld/COFF/DLL.cpp | 94 |
1 files changed, 48 insertions, 46 deletions
diff --git a/lld/COFF/DLL.cpp b/lld/COFF/DLL.cpp index c327da28ce13..10bc898244a4 100644 --- a/lld/COFF/DLL.cpp +++ b/lld/COFF/DLL.cpp @@ -244,40 +244,36 @@ static const uint8_t thunkX64[] = { }; static const uint8_t tailMergeX64[] = { - 0x51, // push rcx - 0x52, // push rdx - 0x41, 0x50, // push r8 - 0x41, 0x51, // push r9 - 0x48, 0x83, 0xEC, 0x48, // sub rsp, 48h - 0x66, 0x0F, 0x7F, 0x04, 0x24, // movdqa xmmword ptr [rsp], xmm0 - 0x66, 0x0F, 0x7F, 0x4C, 0x24, 0x10, // movdqa xmmword ptr [rsp+10h], xmm1 - 0x66, 0x0F, 0x7F, 0x54, 0x24, 0x20, // movdqa xmmword ptr [rsp+20h], xmm2 - 0x66, 0x0F, 0x7F, 0x5C, 0x24, 0x30, // movdqa xmmword ptr [rsp+30h], xmm3 - 0x48, 0x8B, 0xD0, // mov rdx, rax - 0x48, 0x8D, 0x0D, 0, 0, 0, 0, // lea rcx, [___DELAY_IMPORT_...] - 0xE8, 0, 0, 0, 0, // call __delayLoadHelper2 - 0x66, 0x0F, 0x6F, 0x04, 0x24, // movdqa xmm0, xmmword ptr [rsp] - 0x66, 0x0F, 0x6F, 0x4C, 0x24, 0x10, // movdqa xmm1, xmmword ptr [rsp+10h] - 0x66, 0x0F, 0x6F, 0x54, 0x24, 0x20, // movdqa xmm2, xmmword ptr [rsp+20h] - 0x66, 0x0F, 0x6F, 0x5C, 0x24, 0x30, // movdqa xmm3, xmmword ptr [rsp+30h] - 0x48, 0x83, 0xC4, 0x48, // add rsp, 48h - 0x41, 0x59, // pop r9 - 0x41, 0x58, // pop r8 - 0x5A, // pop rdx - 0x59, // pop rcx - 0xFF, 0xE0, // jmp rax + 0x48, 0x89, 0x4C, 0x24, 0x08, // mov qword ptr [rsp+8], rcx + 0x48, 0x89, 0x54, 0x24, 0x10, // mov qword ptr [rsp+10h], rdx + 0x4C, 0x89, 0x44, 0x24, 0x18, // mov qword ptr [rsp+18h], r8 + 0x4C, 0x89, 0x4C, 0x24, 0x20, // mov qword ptr [rsp+20h], r9 + 0x48, 0x83, 0xEC, 0x68, // sub rsp, 68h + 0x66, 0x0F, 0x7F, 0x44, 0x24, 0x20, // movdqa xmmword ptr [rsp+20h], xmm0 + 0x66, 0x0F, 0x7F, 0x4C, 0x24, 0x30, // movdqa xmmword ptr [rsp+30h], xmm1 + 0x66, 0x0F, 0x7F, 0x54, 0x24, 0x40, // movdqa xmmword ptr [rsp+40h], xmm2 + 0x66, 0x0F, 0x7F, 0x5C, 0x24, 0x50, // movdqa xmmword ptr [rsp+50h], xmm3 + 0x48, 0x8B, 0xD0, // mov rdx, rax + 0x48, 0x8D, 0x0D, 0, 0, 0, 0, // lea rcx, [___DELAY_IMPORT_...] + 0xE8, 0, 0, 0, 0, // call __delayLoadHelper2 + 0x66, 0x0F, 0x6F, 0x44, 0x24, 0x20, // movdqa xmm0, xmmword ptr [rsp+20h] + 0x66, 0x0F, 0x6F, 0x4C, 0x24, 0x30, // movdqa xmm1, xmmword ptr [rsp+30h] + 0x66, 0x0F, 0x6F, 0x54, 0x24, 0x40, // movdqa xmm2, xmmword ptr [rsp+40h] + 0x66, 0x0F, 0x6F, 0x5C, 0x24, 0x50, // movdqa xmm3, xmmword ptr [rsp+50h] + 0x48, 0x8B, 0x4C, 0x24, 0x70, // mov rcx, qword ptr [rsp+70h] + 0x48, 0x8B, 0x54, 0x24, 0x78, // mov rdx, qword ptr [rsp+78h] + 0x4C, 0x8B, 0x84, 0x24, 0x80, 0, 0, 0, // mov r8, qword ptr [rsp+80h] + 0x4C, 0x8B, 0x8C, 0x24, 0x88, 0, 0, 0, // mov r9, qword ptr [rsp+88h] + 0x48, 0x83, 0xC4, 0x68, // add rsp, 68h + 0xFF, 0xE0, // jmp rax }; static const uint8_t tailMergeUnwindInfoX64[] = { 0x01, // Version=1, Flags=UNW_FLAG_NHANDLER - 0x0a, // Size of prolog - 0x05, // Count of unwind codes + 0x18, // Size of prolog + 0x01, // Count of unwind codes 0x00, // No frame register - 0x0a, 0x82, // Offset 0xa: UWOP_ALLOC_SMALL(0x48) - 0x06, 0x02, // Offset 6: UWOP_ALLOC_SMALL(8) - 0x04, 0x02, // Offset 4: UWOP_ALLOC_SMALL(8) - 0x02, 0x02, // Offset 2: UWOP_ALLOC_SMALL(8) - 0x01, 0x02, // Offset 1: UWOP_ALLOC_SMALL(8) + 0x18, 0xC2, // Offset 0x18: UWOP_ALLOC_SMALL(0x68) 0x00, 0x00 // Padding to align on 32-bits }; @@ -324,30 +320,34 @@ static const uint8_t thunkARM64[] = { }; static const uint8_t tailMergeARM64[] = { - 0xfd, 0x7b, 0xb3, 0xa9, // stp x29, x30, [sp, #-208]! + 0xfd, 0x7b, 0xb2, 0xa9, // stp x29, x30, [sp, #-224]! 0xfd, 0x03, 0x00, 0x91, // mov x29, sp 0xe0, 0x07, 0x01, 0xa9, // stp x0, x1, [sp, #16] 0xe2, 0x0f, 0x02, 0xa9, // stp x2, x3, [sp, #32] 0xe4, 0x17, 0x03, 0xa9, // stp x4, x5, [sp, #48] 0xe6, 0x1f, 0x04, 0xa9, // stp x6, x7, [sp, #64] - 0xe0, 0x87, 0x02, 0xad, // stp q0, q1, [sp, #80] - 0xe2, 0x8f, 0x03, 0xad, // stp q2, q3, [sp, #112] - 0xe4, 0x97, 0x04, 0xad, // stp q4, q5, [sp, #144] - 0xe6, 0x9f, 0x05, 0xad, // stp q6, q7, [sp, #176] + 0xe8, 0x2b, 0x00, 0xf9, // str x8, [sp, #80] + 0xe0, 0x07, 0x03, 0xad, // stp q0, q1, [sp, #96] + 0xe2, 0x0f, 0x04, 0xad, // stp q2, q3, [sp, #128] + 0xe4, 0x17, 0x05, 0xad, // stp q4, q5, [sp, #160] + 0xe6, 0x1f, 0x06, 0xad, // stp q6, q7, [sp, #192] 0xe1, 0x03, 0x11, 0xaa, // mov x1, x17 0x00, 0x00, 0x00, 0x90, // adrp x0, #0 DELAY_IMPORT_DESCRIPTOR 0x00, 0x00, 0x00, 0x91, // add x0, x0, #0 :lo12:DELAY_IMPORT_DESCRIPTOR - 0x00, 0x00, 0x00, 0x94, // bl #0 __delayLoadHelper2 + 0x02, 0x00, 0x00, 0x90, // adrp x2, #0 __delayLoadHelper2 + 0x42, 0x00, 0x00, 0x91, // add x2, x2, #0 :lo12:__delayLoadHelper2 + 0x40, 0x00, 0x3f, 0xd6, // blr x2 0xf0, 0x03, 0x00, 0xaa, // mov x16, x0 - 0xe6, 0x9f, 0x45, 0xad, // ldp q6, q7, [sp, #176] - 0xe4, 0x97, 0x44, 0xad, // ldp q4, q5, [sp, #144] - 0xe2, 0x8f, 0x43, 0xad, // ldp q2, q3, [sp, #112] - 0xe0, 0x87, 0x42, 0xad, // ldp q0, q1, [sp, #80] + 0xe6, 0x1f, 0x46, 0xad, // ldp q6, q7, [sp, #192] + 0xe4, 0x17, 0x45, 0xad, // ldp q4, q5, [sp, #160] + 0xe2, 0x0f, 0x44, 0xad, // ldp q2, q3, [sp, #128] + 0xe0, 0x07, 0x43, 0xad, // ldp q0, q1, [sp, #96] + 0xe8, 0x2b, 0x40, 0xf9, // ldr x8, [sp, #80] 0xe6, 0x1f, 0x44, 0xa9, // ldp x6, x7, [sp, #64] 0xe4, 0x17, 0x43, 0xa9, // ldp x4, x5, [sp, #48] 0xe2, 0x0f, 0x42, 0xa9, // ldp x2, x3, [sp, #32] 0xe0, 0x07, 0x41, 0xa9, // ldp x0, x1, [sp, #16] - 0xfd, 0x7b, 0xcd, 0xa8, // ldp x29, x30, [sp], #208 + 0xfd, 0x7b, 0xce, 0xa8, // ldp x29, x30, [sp], #224 0x00, 0x02, 0x1f, 0xd6, // br x16 }; @@ -378,8 +378,8 @@ public: void writeTo(uint8_t *buf) const override { memcpy(buf, tailMergeX64, sizeof(tailMergeX64)); - write32le(buf + 39, desc->getRVA() - rva - 43); - write32le(buf + 44, helper->getRVA() - rva - 48); + write32le(buf + 54, desc->getRVA() - rva - 58); + write32le(buf + 59, helper->getRVA() - rva - 63); } Chunk *desc = nullptr; @@ -558,10 +558,12 @@ public: void writeTo(uint8_t *buf) const override { memcpy(buf, tailMergeARM64, sizeof(tailMergeARM64)); - applyArm64Addr(buf + 44, desc->getRVA(), rva + 44, 12); - applyArm64Imm(buf + 48, desc->getRVA() & 0xfff, 0); - if (helper) - applyArm64Branch26(buf + 52, helper->getRVA() - rva - 52); + applyArm64Addr(buf + 48, desc->getRVA(), rva + 48, 12); + applyArm64Imm(buf + 52, desc->getRVA() & 0xfff, 0); + if (helper) { + applyArm64Addr(buf + 56, helper->getRVA(), rva + 56, 12); + applyArm64Imm(buf + 60, helper->getRVA() & 0xfff, 0); + } } Chunk *desc = nullptr; |