diff options
| author | Dean Michael Berris <dberris@google.com> | 2017-11-15 03:35:42 +0000 |
|---|---|---|
| committer | Dean Michael Berris <dberris@google.com> | 2017-11-15 03:35:42 +0000 |
| commit | e811c409bf2634f1845f5f14e36851255098b197 (patch) | |
| tree | 8ff593246f319bdac00365f3588abdfb48602cb8 /lib | |
| parent | 270a9d57af3a0b13214ca6e2cd33a820094cd6c3 (diff) | |
[XRay][compiler-rt][x86_64] Align the stack before and after calling handlers
Summary:
This change fixes the XRay trampolines aside from the __xray_CustomEvent
trampoline to align the stack to 16-byte boundaries before calling the
handler. Before this change we've not been explicitly aligning the stack
to 16-byte boundaries, which makes it dangerous when calling handlers
that leave the stack in a state that isn't strictly 16-byte aligned
after calling the handlers.
We add a test that makes sure we can handle these cases appropriately
after the changes, and prevents us from regressing the state moving
forward.
Fixes http://llvm.org/PR35294.
Reviewers: pelikan, pcc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D40004
git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@318261 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/xray/xray_trampoline_x86_64.S | 38 |
1 files changed, 22 insertions, 16 deletions
diff --git a/lib/xray/xray_trampoline_x86_64.S b/lib/xray/xray_trampoline_x86_64.S index ffbfb5c7e..33fa0e79d 100644 --- a/lib/xray/xray_trampoline_x86_64.S +++ b/lib/xray/xray_trampoline_x86_64.S @@ -60,6 +60,20 @@ .cfi_def_cfa_offset 8 .endm +.macro ALIGNED_CALL_RAX + // Call the logging handler, after aligning the stack to a 16-byte boundary. + // The approach we're taking here uses additional stack space to stash the + // stack pointer twice before aligning the pointer to 16-bytes. If the stack + // was 8-byte aligned, it will become 16-byte aligned -- when restoring the + // pointer, we can always look -8 bytes from the current position to get + // either of the values we've stashed in the first place. + pushq %rsp + pushq (%rsp) + andq $-0x10, %rsp + callq *%rax + movq 8(%rsp), %rsp +.endm + .text .file "xray_trampoline_x86.S" @@ -82,7 +96,8 @@ __xray_FunctionEntry: // The patched function prolog puts its xray_instr_map index into %r10d. movl %r10d, %edi xor %esi,%esi - callq *%rax + ALIGNED_CALL_RAX + .Ltmp0: RESTORE_REGISTERS retq @@ -113,7 +128,8 @@ __xray_FunctionExit: movl %r10d, %edi movl $1, %esi - callq *%rax + ALIGNED_CALL_RAX + .Ltmp2: // Restore the important registers. movq 48(%rsp), %rbp @@ -143,7 +159,8 @@ __xray_FunctionTailExit: movl %r10d, %edi movl $2, %esi - callq *%rax + + ALIGNED_CALL_RAX .Ltmp4: RESTORE_REGISTERS @@ -181,7 +198,7 @@ __xray_ArgLoggerEntry: // 32-bit function ID becomes the first movl %r10d, %edi - callq *%rax + ALIGNED_CALL_RAX .Larg1entryFail: RESTORE_REGISTERS @@ -207,18 +224,7 @@ __xray_CustomEvent: testq %rax,%rax je .LcustomEventCleanup - // At this point we know that rcx and rdx already has the data, so we just - // call the logging handler, after aligning the stack to a 16-byte boundary. - // The approach we're taking here uses additional stack space to stash the - // stack pointer twice before aligning the pointer to 16-bytes. If the stack - // was 8-byte aligned, it will become 16-byte aligned -- when restoring the - // pointer, we can always look -8 bytes from the current position to get - // either of the values we've stashed in the first place. - pushq %rsp - pushq (%rsp) - andq $-0x10, %rsp - callq *%rax - movq 8(%rsp), %rsp + ALIGNED_CALL_RAX .LcustomEventCleanup: RESTORE_REGISTERS |