[XRay][compiler-rt+llvm] Update XRay register stashing semantics

Summary:
This change expands the amount of registers stashed by the entry and
`__xray_CustomEvent` trampolines.

We've found that since the `__xray_CustomEvent` trampoline calls can show up in
situations where the scratch registers are being used, and since we don't
typically want to affect the code-gen around the disabled
`__xray_customevent(...)` intrinsic calls, that we need to save and restore the
state of even the scratch registers in the handling of these custom events.

Reviewers: pcc, pelikan, dblaikie, eizan, kpw, echristo, chandlerc

Reviewed By: echristo

Subscribers: chandlerc, echristo, hiraditya, davide, dblaikie, llvm-commits

Differential Revision: https://reviews.llvm.org/D40894

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@323940 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 49 insertions, 41 deletions

diff --git a/lib/xray/xray_trampoline_x86_64.S b/lib/xray/xray_trampoline_x86_64.S
index 350afd926..370a561e1 100644
--- a/lib/xray/xray_trampoline_x86_64.S
+++ b/lib/xray/xray_trampoline_x86_64.S
@@ -19,47 +19,56 @@
 
 
 .macro SAVE_REGISTERS
-	subq $192, %rsp
-	CFI_DEF_CFA_OFFSET(200)
-	// At this point, the stack pointer should be aligned to an 8-byte boundary,
-	// because any call instructions that come after this will add another 8
-	// bytes and therefore align it to 16-bytes.
-	movq %rbp, 184(%rsp)
-	movupd	%xmm0, 168(%rsp)
-	movupd	%xmm1, 152(%rsp)
-	movupd	%xmm2, 136(%rsp)
-	movupd	%xmm3, 120(%rsp)
-	movupd	%xmm4, 104(%rsp)
-	movupd	%xmm5, 88(%rsp)
-	movupd	%xmm6, 72(%rsp)
-	movupd	%xmm7, 56(%rsp)
-	movq	%rdi, 48(%rsp)
-	movq	%rax, 40(%rsp)
-	movq	%rdx, 32(%rsp)
-	movq	%rsi, 24(%rsp)
-	movq	%rcx, 16(%rsp)
-	movq	%r8, 8(%rsp)
-	movq	%r9, 0(%rsp)
+	subq $240, %rsp
+	CFI_DEF_CFA_OFFSET(248)
+	movq %rbp, 232(%rsp)
+	movupd	%xmm0, 216(%rsp)
+	movupd	%xmm1, 200(%rsp)
+	movupd	%xmm2, 184(%rsp)
+	movupd	%xmm3, 168(%rsp)
+	movupd	%xmm4, 152(%rsp)
+	movupd	%xmm5, 136(%rsp)
+	movupd	%xmm6, 120(%rsp)
+	movupd	%xmm7, 104(%rsp)
+	movq	%rdi, 96(%rsp)
+	movq	%rax, 88(%rsp)
+	movq	%rdx, 80(%rsp)
+	movq	%rsi, 72(%rsp)
+	movq	%rcx, 64(%rsp)
+	movq	%r8, 56(%rsp)
+	movq	%r9, 48(%rsp)
+	movq  %r10, 40(%rsp)
+	movq  %r11, 32(%rsp)
+	movq  %r12, 24(%rsp)
+	movq  %r13, 16(%rsp)
+	movq  %r14, 8(%rsp)
+	movq  %r15, 0(%rsp)
 .endm
 
 .macro RESTORE_REGISTERS
-	movq  184(%rsp), %rbp
-	movupd	168(%rsp), %xmm0
-	movupd	152(%rsp), %xmm1
-	movupd	136(%rsp), %xmm2
-	movupd	120(%rsp), %xmm3
-	movupd	104(%rsp), %xmm4
-	movupd	88(%rsp), %xmm5
-	movupd	72(%rsp) , %xmm6
-	movupd	56(%rsp) , %xmm7
-	movq	48(%rsp), %rdi
-	movq	40(%rsp), %rax
-	movq	32(%rsp), %rdx
-	movq	24(%rsp), %rsi
-	movq	16(%rsp), %rcx
-	movq	8(%rsp), %r8
-	movq	0(%rsp), %r9
-	addq	$192, %rsp
+	movq  232(%rsp), %rbp
+	movupd	216(%rsp), %xmm0
+	movupd	200(%rsp), %xmm1
+	movupd	184(%rsp), %xmm2
+	movupd	168(%rsp), %xmm3
+	movupd	152(%rsp), %xmm4
+	movupd	136(%rsp), %xmm5
+	movupd	120(%rsp) , %xmm6
+	movupd	104(%rsp) , %xmm7
+	movq	96(%rsp), %rdi
+	movq	88(%rsp), %rax
+	movq	80(%rsp), %rdx
+	movq	72(%rsp), %rsi
+	movq	64(%rsp), %rcx
+	movq	56(%rsp), %r8
+	movq	48(%rsp), %r9
+	movq  40(%rsp), %r10
+	movq  32(%rsp), %r11
+	movq  24(%rsp), %r12
+	movq  16(%rsp), %r13
+	movq  8(%rsp), %r14
+	movq  0(%rsp), %r15
+	addq	$240, %rsp
 	CFI_DEF_CFA_OFFSET(8)
 .endm
 
@@ -100,7 +109,7 @@ ASM_SYMBOL(__xray_FunctionEntry):
 	testq	%rax, %rax
 	je	.Ltmp0
 
-	// The patched function prolog puts its xray_instr_map index into %r10d.
+	// The patched function prologue puts its xray_instr_map index into %r10d.
 	movl	%r10d, %edi
 	xor	%esi,%esi
 	ALIGNED_CALL_RAX
@@ -220,8 +229,7 @@ ASM_SYMBOL(__xray_CustomEvent):
 	SAVE_REGISTERS
 
 	// We take two arguments to this trampoline, which should be in rdi	and rsi
-	// already. We also make sure that we stash %rax because we use that register
-	// to call the logging handler.
+	// already.
 	movq ASM_SYMBOL(_ZN6__xray22XRayPatchedCustomEventE)(%rip), %rax
 	testq %rax,%rax
 	je .LcustomEventCleanup