perf intel-pt: Add guest_code support

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, a new option "--guest-code" has been added in
previous patches.

In this patch, add support also to Intel PT.

In particular, ensure guest_code thread is set up before attempting to
walk object code or synthesize samples.

Example:

# 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/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962087836: branches: call 402c81 guest_code+0x131 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dba0 ucall+0x0 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962088248: branches: vmexit 40dba0 ucall+0x0 (/home/ahunter/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/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962089701: branches: jmp 40dc1b ucall+0x7b (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc39 ucall+0x99 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962089701: branches: jcc 40dc3c ucall+0x9c (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc20 ucall+0x80 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962089701: branches: jcc 40dc3c ucall+0x9c (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc20 ucall+0x80 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962089701: branches: jcc 40dc37 ucall+0x97 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test) => 40dc50 ucall+0xb0 (/home/ahunter/git/work/tools/testing/selftests/kselftest_install/kvm/tsc_msrs_test)
[guest/18436] 18436 [007] 10897.962089878: branches: vmexit 40dc55 ucall+0xb5 (/home/ahunter/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

For more information about Perf tools support for Intel® Processor Trace
refer:

https://perf.wiki.kernel.org/index.php/Perf_tools_support_for_Intel%C2%AE_Processor_Trace

Signed-off-by: Adrian Hunter <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Leo Yan <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: [e-mail]
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-intel-pt.txt

···
           :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
 -----------
 

tools/perf/util/intel-pt.c

···
 	pid_t next_tid;
 	struct thread *thread;
 	struct machine *guest_machine;
+	struct thread *guest_thread;
 	struct thread *unknown_guest_thread;
 	pid_t guest_machine_pid;
 	bool exclude_kernel;
···
 	ptq->guest_machine = NULL;
 	thread__zput(ptq->unknown_guest_thread);
 
+	if (symbol_conf.guest_code) {
+		thread__zput(ptq->guest_thread);
+		ptq->guest_thread = machines__findnew_guest_code(machines, pid);
+	}
+
 	machine = machines__find_guest(machines, pid);
 	if (!machine)
 		return -1;
···
 	cpumode = intel_pt_nr_cpumode(ptq, *ip, nr);
 
 	if (nr) {
-		if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL ||
+		if ((!symbol_conf.guest_code && cpumode != PERF_RECORD_MISC_GUEST_KERNEL) ||
 		    intel_pt_get_guest(ptq))
 			return -EINVAL;
 		machine = ptq->guest_machine;
-		thread = ptq->unknown_guest_thread;
+		thread = ptq->guest_thread;
+		if (!thread) {
+			if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL)
+				return -EINVAL;
+			thread = ptq->unknown_guest_thread;
+		}
 	} else {
 		thread = ptq->thread;
 		if (!thread) {
···
 	if (!ptq)
 		return;
 	thread__zput(ptq->thread);
+	thread__zput(ptq->guest_thread);
 	thread__zput(ptq->unknown_guest_thread);
 	intel_pt_decoder_free(ptq->decoder);
 	zfree(&ptq->event_buf);
···
 		ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt;
 		ptq->sample_ipc = ptq->state->flags & INTEL_PT_SAMPLE_IPC;
 	}
+
+	/* Ensure guest code maps are set up */
+	if (symbol_conf.guest_code && (state->from_nr || state->to_nr))
+		intel_pt_get_guest(ptq);
 
 	/*
 	 * Do PEBS first to allow for the possibility that the PEBS timestamp