summaryrefslogtreecommitdiff
path: root/tools/perf/Documentation/perf-intel-pt.txt
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/Documentation/perf-intel-pt.txt')
-rw-r--r--tools/perf/Documentation/perf-intel-pt.txt165
1 files changed, 165 insertions, 0 deletions
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index ff58bd4c381b..238ab9d3cb93 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -468,6 +468,8 @@ ptw Enable PTWRITE packets which are produced when a ptwrite instruction
which contains "1" if the feature is supported and
"0" otherwise.
+ As an alternative, refer to "Emulated PTWRITE" further below.
+
fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet
provides the address of the ptwrite instruction. In the absence of
fup_on_ptw, the decoder will use the address of the previous branch
@@ -1398,6 +1400,76 @@ There were none.
:17006 17006 [001] 11500.262869216: ffffffff8220116e error_entry+0xe ([guest.kernel.kallsyms]) pushq %rax
+Tracing Virtual Machines - Guest Code
+-------------------------------------
+
+A common case for KVM test programs is that the test program acts as the
+hypervisor, creating, running and destroying the virtual machine, and
+providing the guest object code from its own object code. In this case,
+the VM is not running an OS, but only the functions loaded into it by the
+hypervisor test program, and conveniently, loaded at the same virtual
+addresses. To support that, option "--guest-code" has been added to perf script
+and perf kvm report.
+
+Here is an example tracing a test program from the kernel's KVM selftests:
+
+ # perf record --kcore -e intel_pt/cyc/ -- tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.280 MB perf.data ]
+ # perf script --guest-code --itrace=bep --ns -F-period,+addr,+flags
+ [SNIP]
+ tsc_msrs_test 18436 [007] 10897.962087733: branches: call ffffffffc13b2ff5 __vmx_vcpu_run+0x15 (vmlinux) => ffffffffc13b2f50 vmx_update_host_rsp+0x0 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962087733: branches: return ffffffffc13b2f5d vmx_update_host_rsp+0xd (vmlinux) => ffffffffc13b2ffa __vmx_vcpu_run+0x1a (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962087733: branches: call ffffffffc13b303b __vmx_vcpu_run+0x5b (vmlinux) => ffffffffc13b2f80 vmx_vmenter+0x0 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962087836: branches: vmentry ffffffffc13b2f82 vmx_vmenter+0x2 (vmlinux) => 0 [unknown] ([unknown])
+ [guest/18436] 18436 [007] 10897.962087836: branches: vmentry 0 [unknown] ([unknown]) => 402c81 guest_code+0x131 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962087836: branches: call 402c81 guest_code+0x131 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dba0 ucall+0x0 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962088248: branches: vmexit 40dba0 ucall+0x0 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 0 [unknown] ([unknown])
+ tsc_msrs_test 18436 [007] 10897.962088248: branches: vmexit 0 [unknown] ([unknown]) => ffffffffc13b2fa0 vmx_vmexit+0x0 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962088248: branches: jmp ffffffffc13b2fa0 vmx_vmexit+0x0 (vmlinux) => ffffffffc13b2fd2 vmx_vmexit+0x32 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962088256: branches: return ffffffffc13b2fd2 vmx_vmexit+0x32 (vmlinux) => ffffffffc13b3040 __vmx_vcpu_run+0x60 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962088270: branches: return ffffffffc13b30b6 __vmx_vcpu_run+0xd6 (vmlinux) => ffffffffc13b2f2e vmx_vcpu_enter_exit+0x4e (vmlinux)
+ [SNIP]
+ tsc_msrs_test 18436 [007] 10897.962089321: branches: call ffffffffc13b2ff5 __vmx_vcpu_run+0x15 (vmlinux) => ffffffffc13b2f50 vmx_update_host_rsp+0x0 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962089321: branches: return ffffffffc13b2f5d vmx_update_host_rsp+0xd (vmlinux) => ffffffffc13b2ffa __vmx_vcpu_run+0x1a (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962089321: branches: call ffffffffc13b303b __vmx_vcpu_run+0x5b (vmlinux) => ffffffffc13b2f80 vmx_vmenter+0x0 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962089424: branches: vmentry ffffffffc13b2f82 vmx_vmenter+0x2 (vmlinux) => 0 [unknown] ([unknown])
+ [guest/18436] 18436 [007] 10897.962089424: branches: vmentry 0 [unknown] ([unknown]) => 40dba0 ucall+0x0 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962089701: branches: jmp 40dc1b ucall+0x7b (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc39 ucall+0x99 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962089701: branches: jcc 40dc3c ucall+0x9c (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc20 ucall+0x80 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962089701: branches: jcc 40dc3c ucall+0x9c (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc20 ucall+0x80 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962089701: branches: jcc 40dc37 ucall+0x97 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc50 ucall+0xb0 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
+ [guest/18436] 18436 [007] 10897.962089878: branches: vmexit 40dc55 ucall+0xb5 (/home/user/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 0 [unknown] ([unknown])
+ tsc_msrs_test 18436 [007] 10897.962089878: branches: vmexit 0 [unknown] ([unknown]) => ffffffffc13b2fa0 vmx_vmexit+0x0 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962089878: branches: jmp ffffffffc13b2fa0 vmx_vmexit+0x0 (vmlinux) => ffffffffc13b2fd2 vmx_vmexit+0x32 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962089887: branches: return ffffffffc13b2fd2 vmx_vmexit+0x32 (vmlinux) => ffffffffc13b3040 __vmx_vcpu_run+0x60 (vmlinux)
+ tsc_msrs_test 18436 [007] 10897.962089901: branches: return ffffffffc13b30b6 __vmx_vcpu_run+0xd6 (vmlinux) => ffffffffc13b2f2e vmx_vcpu_enter_exit+0x4e (vmlinux)
+ [SNIP]
+
+ # perf kvm --guest-code --guest --host report -i perf.data --stdio | head -20
+
+ # To display the perf.data header info, please use --header/--header-only options.
+ #
+ #
+ # Total Lost Samples: 0
+ #
+ # Samples: 12 of event 'instructions'
+ # Event count (approx.): 2274583
+ #
+ # Children Self Command Shared Object Symbol
+ # ........ ........ ............. .................... ...........................................
+ #
+ 54.70% 0.00% tsc_msrs_test [kernel.vmlinux] [k] entry_SYSCALL_64_after_hwframe
+ |
+ ---entry_SYSCALL_64_after_hwframe
+ do_syscall_64
+ |
+ |--29.44%--syscall_exit_to_user_mode
+ | exit_to_user_mode_prepare
+ | task_work_run
+ | __fput
+
+
Event Trace
-----------
@@ -1471,6 +1543,99 @@ In that case the --itrace q option is forced because walking executable code
to reconstruct the control flow is not possible.
+Emulated PTWRITE
+----------------
+
+Later perf tools support a method to emulate the ptwrite instruction, which
+can be useful if hardware does not support the ptwrite instruction.
+
+Instead of using the ptwrite instruction, a function is used which produces
+a trace that encodes the payload data into TNT packets. Here is an example
+of the function:
+
+ #include <stdint.h>
+
+ void perf_emulate_ptwrite(uint64_t x)
+ __attribute__((externally_visible, noipa, no_instrument_function, naked));
+
+ #define PERF_EMULATE_PTWRITE_8_BITS \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n" \
+ "1: shl %rax\n" \
+ " jc 1f\n"
+
+ /* Undefined instruction */
+ #define PERF_EMULATE_PTWRITE_UD2 ".byte 0x0f, 0x0b\n"
+
+ #define PERF_EMULATE_PTWRITE_MAGIC PERF_EMULATE_PTWRITE_UD2 ".ascii \"perf,ptwrite \"\n"
+
+ void perf_emulate_ptwrite(uint64_t x __attribute__ ((__unused__)))
+ {
+ /* Assumes SysV ABI : x passed in rdi */
+ __asm__ volatile (
+ "jmp 1f\n"
+ PERF_EMULATE_PTWRITE_MAGIC
+ "1: mov %rdi, %rax\n"
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ PERF_EMULATE_PTWRITE_8_BITS
+ "1: ret\n"
+ );
+ }
+
+For example, a test program with the function above:
+
+ #include <stdio.h>
+ #include <stdint.h>
+ #include <stdlib.h>
+
+ #include "perf_emulate_ptwrite.h"
+
+ int main(int argc, char *argv[])
+ {
+ uint64_t x = 0;
+
+ if (argc > 1)
+ x = strtoull(argv[1], NULL, 0);
+ perf_emulate_ptwrite(x);
+ return 0;
+ }
+
+Can be compiled and traced:
+
+ $ gcc -Wall -Wextra -O3 -g -o eg_ptw eg_ptw.c
+ $ perf record -e intel_pt//u ./eg_ptw 0x1234567890abcdef
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.017 MB perf.data ]
+ $ perf script --itrace=ew
+ eg_ptw 19875 [007] 8061.235912: ptwrite: IP: 0 payload: 0x1234567890abcdef 55701249a196 perf_emulate_ptwrite+0x16 (/home/user/eg_ptw)
+ $
+
+
+EXAMPLE
+-------
+
+Examples can be found on perf wiki page "Perf tools support for Intel® Processor Trace":
+
+https://perf.wiki.kernel.org/index.php/Perf_tools_support_for_Intel%C2%AE_Processor_Trace
+
SEE ALSO
--------
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-11-23 08:36:28 +0000