[compiler-rt] r290077 - [XRay] [compiler-rt] Move machine-dependent code into machine-dependent files.
Diana Picus via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 19 04:57:11 PST 2016
Hi Dean,
I reverted this and all related fixups in r290101 because the AArch64
bots were still broken. AFAICT it was missing an include of
sanitizer_common/sanitizer_common.h in xray_emulate_tsc.h, but I'd
rather let you guys sort it out offline than continue this already too
long series of fixups.
Please let me know if you need any help testing this on AArch64 before
committing again.
Thanks,
Diana
On 19 December 2016 at 05:21, Dean Michael Berris via llvm-commits
<llvm-commits at lists.llvm.org> wrote:
> Author: dberris
> Date: Sun Dec 18 21:21:26 2016
> New Revision: 290077
>
> URL: http://llvm.org/viewvc/llvm-project?rev=290077&view=rev
> Log:
> [XRay] [compiler-rt] Move machine-dependent code into machine-dependent files.
>
> Summary: Include the necessary headers while there.
>
> Reviewers: dberris
>
> Subscribers: llvm-commits
>
> Differential Revision: https://reviews.llvm.org/D25360
>
> Added:
> compiler-rt/trunk/lib/xray/xray_emulate_tsc.h
> compiler-rt/trunk/lib/xray/xray_x86_64.h
> Modified:
> compiler-rt/trunk/lib/xray/xray_AArch64.cc
> compiler-rt/trunk/lib/xray/xray_arm.cc
> compiler-rt/trunk/lib/xray/xray_inmemory_log.cc
> compiler-rt/trunk/lib/xray/xray_interface_internal.h
> compiler-rt/trunk/lib/xray/xray_x86_64.cc
>
> Modified: compiler-rt/trunk/lib/xray/xray_AArch64.cc
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_AArch64.cc?rev=290077&r1=290076&r2=290077&view=diff
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_AArch64.cc (original)
> +++ compiler-rt/trunk/lib/xray/xray_AArch64.cc Sun Dec 18 21:21:26 2016
> @@ -14,12 +14,26 @@
> //===----------------------------------------------------------------------===//
> #include "sanitizer_common/sanitizer_common.h"
> #include "xray_defs.h"
> +#include "xray_emulate_tsc.h"
> #include "xray_interface_internal.h"
> #include <atomic>
> #include <cassert>
>
> namespace __xray {
>
> +uint64_t cycleFrequency() XRAY_NEVER_INSTRUMENT {
> + // There is no instruction like RDTSCP in user mode on ARM. ARM's CP15 does
> + // not have a constant frequency like TSC on x86[_64]; it may go faster or
> + // slower depending on CPU's turbo or power saving modes. Furthermore, to
> + // read from CP15 on ARM a kernel modification or a driver is needed.
> + // We can not require this from users of compiler-rt.
> + // So on ARM we use clock_gettime(2) which gives the result in nanoseconds.
> + // To get the measurements per second, we scale this by the number of
> + // nanoseconds per second, pretending that the TSC frequency is 1GHz and
> + // one TSC tick is 1 nanosecond.
> + return NanosecondsPerSecond;
> +}
> +
> // The machine codes for some instructions used in runtime patching.
> enum class PatchOpcodes : uint32_t {
> PO_StpX0X30SP_m16e = 0xA9BF7BE0, // STP X0, X30, [SP, #-16]!
>
> Modified: compiler-rt/trunk/lib/xray/xray_arm.cc
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_arm.cc?rev=290077&r1=290076&r2=290077&view=diff
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_arm.cc (original)
> +++ compiler-rt/trunk/lib/xray/xray_arm.cc Sun Dec 18 21:21:26 2016
> @@ -14,12 +14,26 @@
> //===----------------------------------------------------------------------===//
> #include "sanitizer_common/sanitizer_common.h"
> #include "xray_defs.h"
> +#include "xray_emulate_tsc.h"
> #include "xray_interface_internal.h"
> #include <atomic>
> #include <cassert>
>
> namespace __xray {
>
> +uint64_t cycleFrequency() XRAY_NEVER_INSTRUMENT {
> + // There is no instruction like RDTSCP in user mode on ARM. ARM's CP15 does
> + // not have a constant frequency like TSC on x86[_64]; it may go faster or
> + // slower depending on CPU's turbo or power saving modes. Furthermore, to
> + // read from CP15 on ARM a kernel modification or a driver is needed.
> + // We can not require this from users of compiler-rt.
> + // So on ARM we use clock_gettime(2) which gives the result in nanoseconds.
> + // To get the measurements per second, we scale this by the number of
> + // nanoseconds per second, pretending that the TSC frequency is 1GHz and
> + // one TSC tick is 1 nanosecond.
> + return NanosecondsPerSecond;
> +}
> +
> // The machine codes for some instructions used in runtime patching.
> enum class PatchOpcodes : uint32_t {
> PO_PushR0Lr = 0xE92D4001, // PUSH {r0, lr}
>
> Added: compiler-rt/trunk/lib/xray/xray_emulate_tsc.h
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_emulate_tsc.h?rev=290077&view=auto
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_emulate_tsc.h (added)
> +++ compiler-rt/trunk/lib/xray/xray_emulate_tsc.h Sun Dec 18 21:21:26 2016
> @@ -0,0 +1,23 @@
> +#pragma once
> +#include <time.h>
> +
> +#include "sanitizer_common/sanitizer_internal_defs.h"
> +#include "xray_defs.h"
> +
> +namespace __xray {
> +
> +static constexpr uint64_t NanosecondsPerSecond = 1000ULL * 1000 * 1000;
> +
> +ALWAYS_INLINE uint64_t readTSC(uint8_t &CPU) XRAY_NEVER_INSTRUMENT {
> + timespec TS;
> + int result = clock_gettime(CLOCK_REALTIME, &TS);
> + if (result != 0) {
> + Report("clock_gettime(2) returned %d, errno=%d.", result, int(errno));
> + TS.tv_sec = 0;
> + TS.tv_nsec = 0;
> + }
> + CPU = 0;
> + return TS.tv_sec * NanosecondsPerSecond + TS.tv_nsec;
> +}
> +
> +}
>
> Modified: compiler-rt/trunk/lib/xray/xray_inmemory_log.cc
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_inmemory_log.cc?rev=290077&r1=290076&r2=290077&view=diff
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_inmemory_log.cc (original)
> +++ compiler-rt/trunk/lib/xray/xray_inmemory_log.cc Sun Dec 18 21:21:26 2016
> @@ -26,12 +26,12 @@
> #include <unistd.h>
>
> #if defined(__x86_64__)
> -#include <x86intrin.h>
> +#include "xray_x86_64.h"
> #elif defined(__arm__) || defined(__aarch64__)
> -static const int64_t NanosecondsPerSecond = 1000LL * 1000 * 1000;
> +#include "xray_emulate_tsc.h"
> #else
> #error "Unsupported CPU Architecture"
> -#endif /* CPU architecture */
> +#endif /* Architecture-specific inline intrinsics */
>
> #include "sanitizer_common/sanitizer_libc.h"
> #include "xray/xray_records.h"
> @@ -71,52 +71,6 @@ static void retryingWriteAll(int Fd, cha
> }
> }
>
> -#if defined(__x86_64__)
> -static std::pair<ssize_t, bool>
> -retryingReadSome(int Fd, char *Begin, char *End) XRAY_NEVER_INSTRUMENT {
> - auto BytesToRead = std::distance(Begin, End);
> - ssize_t BytesRead;
> - ssize_t TotalBytesRead = 0;
> - while (BytesToRead && (BytesRead = read(Fd, Begin, BytesToRead))) {
> - if (BytesRead == -1) {
> - if (errno == EINTR)
> - continue;
> - Report("Read error; errno = %d\n", errno);
> - return std::make_pair(TotalBytesRead, false);
> - }
> -
> - TotalBytesRead += BytesRead;
> - BytesToRead -= BytesRead;
> - Begin += BytesRead;
> - }
> - return std::make_pair(TotalBytesRead, true);
> -}
> -
> -static bool readValueFromFile(const char *Filename,
> - long long *Value) XRAY_NEVER_INSTRUMENT {
> - int Fd = open(Filename, O_RDONLY | O_CLOEXEC);
> - if (Fd == -1)
> - return false;
> - static constexpr size_t BufSize = 256;
> - char Line[BufSize] = {};
> - ssize_t BytesRead;
> - bool Success;
> - std::tie(BytesRead, Success) = retryingReadSome(Fd, Line, Line + BufSize);
> - if (!Success)
> - return false;
> - close(Fd);
> - char *End = nullptr;
> - long long Tmp = internal_simple_strtoll(Line, &End, 10);
> - bool Result = false;
> - if (Line[0] != '\0' && (*End == '\n' || *End == '\0')) {
> - *Value = Tmp;
> - Result = true;
> - }
> - return Result;
> -}
> -
> -#endif /* CPU architecture */
> -
> class ThreadExitFlusher {
> int Fd;
> XRayRecord *Start;
> @@ -151,6 +105,47 @@ void PrintToStdErr(const char *Buffer) X
> fprintf(stderr, "%s", Buffer);
> }
>
> +static int __xray_OpenLogFile() XRAY_NEVER_INSTRUMENT {
> + // FIXME: Figure out how to make this less stderr-dependent.
> + SetPrintfAndReportCallback(PrintToStdErr);
> + // Open a temporary file once for the log.
> + static char TmpFilename[256] = {};
> + static char TmpWildcardPattern[] = "XXXXXX";
> + auto E = internal_strncat(TmpFilename, flags()->xray_logfile_base,
> + sizeof(TmpFilename) - 10);
> + if (static_cast<size_t>((E + 6) - TmpFilename) >
> + (sizeof(TmpFilename) - 1)) {
> + Report("XRay log file base too long: %s\n", flags()->xray_logfile_base);
> + return -1;
> + }
> + internal_strncat(TmpFilename, TmpWildcardPattern,
> + sizeof(TmpWildcardPattern) - 1);
> + int Fd = mkstemp(TmpFilename);
> + if (Fd == -1) {
> + Report("XRay: Failed opening temporary file '%s'; not logging events.\n",
> + TmpFilename);
> + return -1;
> + }
> + if (Verbosity())
> + fprintf(stderr, "XRay: Log file in '%s'\n", TmpFilename);
> +
> + // 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 = __xray::cycleFrequency();
> +
> + // FIXME: Actually check whether we have 'constant_tsc' and 'nonstop_tsc'
> + // before setting the values in the header.
> + Header.ConstantTSC = 1;
> + Header.NonstopTSC = 1;
> + retryingWriteAll(Fd, reinterpret_cast<char *>(&Header),
> + reinterpret_cast<char *>(&Header) + sizeof(Header));
> + return Fd;
> +}
> +
> void __xray_InMemoryRawLog(int32_t FuncId,
> XRayEntryType Type) XRAY_NEVER_INSTRUMENT {
> using Buffer =
> @@ -158,75 +153,7 @@ void __xray_InMemoryRawLog(int32_t FuncI
> static constexpr size_t BuffLen = 1024;
> thread_local static Buffer InMemoryBuffer[BuffLen] = {};
> thread_local static size_t Offset = 0;
> - static int Fd = [] {
> - // FIXME: Figure out how to make this less stderr-dependent.
> - SetPrintfAndReportCallback(PrintToStdErr);
> - // Open a temporary file once for the log.
> - static char TmpFilename[256] = {};
> - static char TmpWildcardPattern[] = "XXXXXX";
> - auto E = internal_strncat(TmpFilename, flags()->xray_logfile_base,
> - sizeof(TmpFilename) - 10);
> - if (static_cast<size_t>((E + 6) - TmpFilename) >
> - (sizeof(TmpFilename) - 1)) {
> - Report("XRay log file base too long: %s\n", flags()->xray_logfile_base);
> - return -1;
> - }
> - internal_strncat(TmpFilename, TmpWildcardPattern,
> - sizeof(TmpWildcardPattern) - 1);
> - int Fd = mkstemp(TmpFilename);
> - if (Fd == -1) {
> - Report("XRay: Failed opening temporary file '%s'; not logging events.\n",
> - TmpFilename);
> - return -1;
> - }
> - if (Verbosity())
> - fprintf(stderr, "XRay: Log file in '%s'\n", TmpFilename);
> -
> - // Get the cycle frequency from SysFS on Linux.
> - long long CPUFrequency = -1;
> -#if defined(__x86_64__)
> - if (readValueFromFile("/sys/devices/system/cpu/cpu0/tsc_freq_khz",
> - &CPUFrequency)) {
> - CPUFrequency *= 1000;
> - } else if (readValueFromFile(
> - "/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq",
> - &CPUFrequency)) {
> - CPUFrequency *= 1000;
> - } else {
> - Report("Unable to determine CPU frequency for TSC accounting.\n");
> - }
> -#elif defined(__arm__) || defined(__aarch64__)
> - // There is no instruction like RDTSCP in user mode on ARM. ARM's CP15 does
> - // not have a constant frequency like TSC on x86(_64), it may go faster
> - // or slower depending on CPU turbo or power saving mode. Furthermore,
> - // to read from CP15 on ARM a kernel modification or a driver is needed.
> - // We can not require this from users of compiler-rt.
> - // So on ARM we use clock_gettime() which gives the result in nanoseconds.
> - // To get the measurements per second, we scale this by the number of
> - // nanoseconds per second, pretending that the TSC frequency is 1GHz and
> - // one TSC tick is 1 nanosecond.
> - CPUFrequency = NanosecondsPerSecond;
> -#else
> -#error "Unsupported CPU Architecture"
> -#endif /* CPU architecture */
> -
> - // 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 =
> - CPUFrequency == -1 ? 0 : static_cast<uint64_t>(CPUFrequency);
> -
> - // FIXME: Actually check whether we have 'constant_tsc' and 'nonstop_tsc'
> - // before setting the values in the header.
> - Header.ConstantTSC = 1;
> - Header.NonstopTSC = 1;
> - retryingWriteAll(Fd, reinterpret_cast<char *>(&Header),
> - reinterpret_cast<char *>(&Header) + sizeof(Header));
> - return Fd;
> - }();
> + static int Fd = __xray_OpenLogFile();
> if (Fd == -1)
> return;
> thread_local __xray::ThreadExitFlusher Flusher(
> @@ -237,27 +164,7 @@ void __xray_InMemoryRawLog(int32_t FuncI
> // through a pointer offset.
> auto &R = reinterpret_cast<__xray::XRayRecord *>(InMemoryBuffer)[Offset];
> R.RecordType = RecordTypes::NORMAL;
> -#if defined(__x86_64__)
> - {
> - unsigned CPU;
> - R.TSC = __rdtscp(&CPU);
> - R.CPU = CPU;
> - }
> -#elif defined(__arm__) || defined(__aarch64__)
> - {
> - timespec TS;
> - int result = clock_gettime(CLOCK_REALTIME, &TS);
> - if (result != 0) {
> - Report("clock_gettime() returned %d, errno=%d.\n", result, int(errno));
> - TS.tv_sec = 0;
> - TS.tv_nsec = 0;
> - }
> - R.TSC = TS.tv_sec * NanosecondsPerSecond + TS.tv_nsec;
> - R.CPU = 0;
> - }
> -#else
> -#error "Unsupported CPU Architecture"
> -#endif /* CPU architecture */
> + R.TSC = __xray::readTSC(R.CPU);
> R.TId = TId;
> R.Type = Type;
> R.FuncId = FuncId;
>
> Modified: compiler-rt/trunk/lib/xray/xray_interface_internal.h
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_interface_internal.h?rev=290077&r1=290076&r2=290077&view=diff
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_interface_internal.h (original)
> +++ compiler-rt/trunk/lib/xray/xray_interface_internal.h Sun Dec 18 21:21:26 2016
> @@ -48,6 +48,8 @@ struct XRaySledMap {
> size_t Entries;
> };
>
> +uint64_t cycleFrequency();
> +
> bool patchFunctionEntry(bool Enable, uint32_t FuncId,
> const XRaySledEntry &Sled);
> bool patchFunctionExit(bool Enable, uint32_t FuncId, const XRaySledEntry &Sled);
>
> Modified: compiler-rt/trunk/lib/xray/xray_x86_64.cc
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_x86_64.cc?rev=290077&r1=290076&r2=290077&view=diff
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_x86_64.cc (original)
> +++ compiler-rt/trunk/lib/xray/xray_x86_64.cc Sun Dec 18 21:21:26 2016
> @@ -3,10 +3,71 @@
> #include "xray_interface_internal.h"
> #include <atomic>
> #include <cstdint>
> +#include <fcntl.h>
> #include <limits>
> +#include <tuple>
> +#include <unistd.h>
>
> namespace __xray {
>
> +static std::pair<ssize_t, bool>
> +retryingReadSome(int Fd, char *Begin, char *End) XRAY_NEVER_INSTRUMENT {
> + auto BytesToRead = std::distance(Begin, End);
> + ssize_t BytesRead;
> + ssize_t TotalBytesRead = 0;
> + while (BytesToRead && (BytesRead = read(Fd, Begin, BytesToRead))) {
> + if (BytesRead == -1) {
> + if (errno == EINTR)
> + continue;
> + Report("Read error; errno = %d\n", errno);
> + return std::make_pair(TotalBytesRead, false);
> + }
> +
> + TotalBytesRead += BytesRead;
> + BytesToRead -= BytesRead;
> + Begin += BytesRead;
> + }
> + return std::make_pair(TotalBytesRead, true);
> +}
> +
> +static bool readValueFromFile(const char *Filename,
> + long long *Value) XRAY_NEVER_INSTRUMENT {
> + int Fd = open(Filename, O_RDONLY | O_CLOEXEC);
> + if (Fd == -1)
> + return false;
> + static constexpr size_t BufSize = 256;
> + char Line[BufSize] = {};
> + ssize_t BytesRead;
> + bool Success;
> + std::tie(BytesRead, Success) = retryingReadSome(Fd, Line, Line + BufSize);
> + if (!Success)
> + return false;
> + close(Fd);
> + char *End = nullptr;
> + long long Tmp = internal_simple_strtoll(Line, &End, 10);
> + bool Result = false;
> + if (Line[0] != '\0' && (*End == '\n' || *End == '\0')) {
> + *Value = Tmp;
> + Result = true;
> + }
> + return Result;
> +}
> +
> +uint64_t cycleFrequency() XRAY_NEVER_INSTRUMENT {
> + long long CPUFrequency = -1;
> + if (readValueFromFile("/sys/devices/system/cpu/cpu0/tsc_freq_khz",
> + &CPUFrequency)) {
> + CPUFrequency *= 1000;
> + } else if (readValueFromFile(
> + "/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq",
> + &CPUFrequency)) {
> + CPUFrequency *= 1000;
> + } else {
> + Report("Unable to determine CPU frequency for TSC accounting.\n");
> + }
> + return CPUFrequency == -1 ? 0 : static_cast<uint64_t>(CPUFrequency);
> +}
> +
> static constexpr uint8_t CallOpCode = 0xe8;
> static constexpr uint16_t MovR10Seq = 0xba41;
> static constexpr uint16_t Jmp9Seq = 0x09eb;
>
> Added: compiler-rt/trunk/lib/xray/xray_x86_64.h
> URL: http://llvm.org/viewvc/llvm-project/compiler-rt/trunk/lib/xray/xray_x86_64.h?rev=290077&view=auto
> ==============================================================================
> --- compiler-rt/trunk/lib/xray/xray_x86_64.h (added)
> +++ compiler-rt/trunk/lib/xray/xray_x86_64.h Sun Dec 18 21:21:26 2016
> @@ -0,0 +1,16 @@
> +#pragma once
> +#include <x86intrin.h>
> +
> +#include "sanitizer_common/sanitizer_internal_defs.h"
> +#include "xray_defs.h"
> +
> +namespace __xray {
> +
> +ALWAYS_INLINE uint64_t readTSC(uint8_t &CPU) XRAY_NEVER_INSTRUMENT {
> + unsigned LongCPU;
> + uint64_t TSC = __rdtscp(&LongCPU);
> + CPU = LongCPU;
> + return TSC;
> +}
> +
> +}
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
More information about the llvm-commits
mailing list