summaryrefslogtreecommitdiff
path: root/lib/xray
diff options
context:
space:
mode:
Diffstat (limited to 'lib/xray')
-rw-r--r--lib/xray/xray_fdr_logging.cc13
-rw-r--r--lib/xray/xray_inmemory_log.cc10
-rw-r--r--lib/xray/xray_trampoline_x86_64.S104
-rw-r--r--lib/xray/xray_x86_64.cc6
4 files changed, 74 insertions, 59 deletions
diff --git a/lib/xray/xray_fdr_logging.cc b/lib/xray/xray_fdr_logging.cc
index c5b63b0a564e..e538b477a3de 100644
--- a/lib/xray/xray_fdr_logging.cc
+++ b/lib/xray/xray_fdr_logging.cc
@@ -118,11 +118,15 @@ XRayLogFlushStatus fdrLoggingFlush() XRAY_NEVER_INSTRUMENT {
return Result;
}
+ // Test for required CPU features and cache the cycle frequency
+ static bool TSCSupported = probeRequiredCPUFeatures();
+ static uint64_t CycleFrequency = TSCSupported ? getTSCFrequency()
+ : __xray::NanosecondsPerSecond;
+
XRayFileHeader Header;
Header.Version = 1;
Header.Type = FileTypes::FDR_LOG;
- Header.CycleFrequency = probeRequiredCPUFeatures()
- ? getTSCFrequency() : __xray::NanosecondsPerSecond;
+ Header.CycleFrequency = CycleFrequency;
// FIXME: Actually check whether we have 'constant_tsc' and 'nonstop_tsc'
// before setting the values in the header.
Header.ConstantTSC = 1;
@@ -196,7 +200,10 @@ void fdrLoggingHandleArg0(int32_t FuncId,
unsigned char CPU;
uint64_t TSC;
- if(probeRequiredCPUFeatures()) {
+ // Test once for required CPU features
+ static bool TSCSupported = probeRequiredCPUFeatures();
+
+ if(TSCSupported) {
TSC = __xray::readTSC(CPU);
} else {
// FIXME: This code needs refactoring as it appears in multiple locations
diff --git a/lib/xray/xray_inmemory_log.cc b/lib/xray/xray_inmemory_log.cc
index cdaa6d1b5c86..83aecfaf7700 100644
--- a/lib/xray/xray_inmemory_log.cc
+++ b/lib/xray/xray_inmemory_log.cc
@@ -79,15 +79,19 @@ static int __xray_OpenLogFile() XRAY_NEVER_INSTRUMENT {
int F = getLogFD();
if (F == -1)
return -1;
+
+ // Test for required CPU features and cache the cycle frequency
+ static bool TSCSupported = probeRequiredCPUFeatures();
+ static uint64_t CycleFrequency = TSCSupported ? getTSCFrequency()
+ : __xray::NanosecondsPerSecond;
+
// Since we're here, we get to write the header. We set it up so that the
// header will only be written once, at the start, and let the threads
// logging do writes which just append.
XRayFileHeader Header;
Header.Version = 1;
Header.Type = FileTypes::NAIVE_LOG;
- Header.CycleFrequency = probeRequiredCPUFeatures()
- ? getTSCFrequency()
- : __xray::NanosecondsPerSecond;
+ Header.CycleFrequency = CycleFrequency;
// FIXME: Actually check whether we have 'constant_tsc' and 'nonstop_tsc'
// before setting the values in the header.
diff --git a/lib/xray/xray_trampoline_x86_64.S b/lib/xray/xray_trampoline_x86_64.S
index da0aae326bdc..847ecef8d425 100644
--- a/lib/xray/xray_trampoline_x86_64.S
+++ b/lib/xray/xray_trampoline_x86_64.S
@@ -16,41 +16,48 @@
#include "../builtins/assembly.h"
.macro SAVE_REGISTERS
- subq $200, %rsp
- movupd %xmm0, 184(%rsp)
- movupd %xmm1, 168(%rsp)
- movupd %xmm2, 152(%rsp)
- movupd %xmm3, 136(%rsp)
- movupd %xmm4, 120(%rsp)
- movupd %xmm5, 104(%rsp)
- movupd %xmm6, 88(%rsp)
- movupd %xmm7, 72(%rsp)
- movq %rdi, 64(%rsp)
- movq %rax, 56(%rsp)
- movq %rdx, 48(%rsp)
- movq %rsi, 40(%rsp)
- movq %rcx, 32(%rsp)
- movq %r8, 24(%rsp)
- movq %r9, 16(%rsp)
+ 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)
.endm
.macro RESTORE_REGISTERS
- movupd 184(%rsp), %xmm0
- movupd 168(%rsp), %xmm1
- movupd 152(%rsp), %xmm2
- movupd 136(%rsp), %xmm3
- movupd 120(%rsp), %xmm4
- movupd 104(%rsp), %xmm5
- movupd 88(%rsp) , %xmm6
- movupd 72(%rsp) , %xmm7
- movq 64(%rsp), %rdi
- movq 56(%rsp), %rax
- movq 48(%rsp), %rdx
- movq 40(%rsp), %rsi
- movq 32(%rsp), %rcx
- movq 24(%rsp), %r8
- movq 16(%rsp), %r9
- addq $200, %rsp
+ 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
+ .cfi_def_cfa_offset 8
.endm
.text
@@ -64,8 +71,6 @@
__xray_FunctionEntry:
.cfi_startproc
- pushq %rbp
- .cfi_def_cfa_offset 16
SAVE_REGISTERS
// This load has to be atomic, it's concurrent with __xray_patch().
@@ -80,7 +85,6 @@ __xray_FunctionEntry:
callq *%rax
.Ltmp0:
RESTORE_REGISTERS
- popq %rbp
retq
.Ltmp1:
.size __xray_FunctionEntry, .Ltmp1-__xray_FunctionEntry
@@ -96,14 +100,13 @@ __xray_FunctionExit:
// Save the important registers first. Since we're assuming that this
// function is only jumped into, we only preserve the registers for
// returning.
- pushq %rbp
- .cfi_def_cfa_offset 16
subq $56, %rsp
- .cfi_def_cfa_offset 32
- movupd %xmm0, 40(%rsp)
- movupd %xmm1, 24(%rsp)
- movq %rax, 16(%rsp)
- movq %rdx, 8(%rsp)
+ .cfi_def_cfa_offset 64
+ movq %rbp, 48(%rsp)
+ movupd %xmm0, 32(%rsp)
+ movupd %xmm1, 16(%rsp)
+ movq %rax, 8(%rsp)
+ movq %rdx, 0(%rsp)
movq _ZN6__xray19XRayPatchedFunctionE(%rip), %rax
testq %rax,%rax
je .Ltmp2
@@ -113,12 +116,13 @@ __xray_FunctionExit:
callq *%rax
.Ltmp2:
// Restore the important registers.
- movupd 40(%rsp), %xmm0
- movupd 24(%rsp), %xmm1
- movq 16(%rsp), %rax
- movq 8(%rsp), %rdx
+ movq 48(%rsp), %rbp
+ movupd 32(%rsp), %xmm0
+ movupd 16(%rsp), %xmm1
+ movq 8(%rsp), %rax
+ movq 0(%rsp), %rdx
addq $56, %rsp
- popq %rbp
+ .cfi_def_cfa_offset 8
retq
.Ltmp3:
.size __xray_FunctionExit, .Ltmp3-__xray_FunctionExit
@@ -135,8 +139,6 @@ __xray_FunctionTailExit:
// this is an exit. In the future, we will introduce a new entry type that
// differentiates between a normal exit and a tail exit, but we'd have to do
// this and increment the version number for the header.
- pushq %rbp
- .cfi_def_cfa_offset 16
SAVE_REGISTERS
movq _ZN6__xray19XRayPatchedFunctionE(%rip), %rax
@@ -149,7 +151,6 @@ __xray_FunctionTailExit:
.Ltmp4:
RESTORE_REGISTERS
- popq %rbp
retq
.Ltmp5:
.size __xray_FunctionTailExit, .Ltmp5-__xray_FunctionTailExit
@@ -162,8 +163,6 @@ __xray_FunctionTailExit:
.type __xray_ArgLoggerEntry,@function
__xray_ArgLoggerEntry:
.cfi_startproc
- pushq %rbp
- .cfi_def_cfa_offset 16
SAVE_REGISTERS
// Again, these function pointer loads must be atomic; MOV is fine.
@@ -184,7 +183,6 @@ __xray_ArgLoggerEntry:
.Larg1entryFail:
RESTORE_REGISTERS
- popq %rbp
retq
.Larg1entryEnd:
diff --git a/lib/xray/xray_x86_64.cc b/lib/xray/xray_x86_64.cc
index 8c2a4e313e3a..2e9a8d270c33 100644
--- a/lib/xray/xray_x86_64.cc
+++ b/lib/xray/xray_x86_64.cc
@@ -214,6 +214,12 @@ bool probeRequiredCPUFeatures() XRAY_NEVER_INSTRUMENT {
Report("Missing rdtscp support.\n");
return false;
}
+ // Also check whether we can determine the CPU frequency, since if we cannot,
+ // we should use the emulated TSC instead.
+ if (!getTSCFrequency()) {
+ Report("Unable to determine CPU frequency.\n");
+ return false;
+ }
return true;
}
generated by cgit v1.3 (git 2.53.0) at 2026-07-24 19:52:31 +0000