On Tue, 15 Oct 2024 01:42:50 PDT (-0700), zhouquan@xxxxxxxxxxx wrote:
From: Quan Zhou <zhouquan@xxxxxxxxxxx>
Introduce basic guest support in perf, enabling it to distinguish
between PMU interrupts in the host or guest, and collect
fundamental information.
Reviewed-by: Andrew Jones <ajones@xxxxxxxxxxxxxxxx>
Signed-off-by: Quan Zhou <zhouquan@xxxxxxxxxxx>
---
arch/riscv/include/asm/perf_event.h | 6 +++++
arch/riscv/kernel/perf_callchain.c | 38 +++++++++++++++++++++++++++++
2 files changed, 44 insertions(+)
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index 665bbc9b2f84..38926b4a902d 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -8,7 +8,11 @@
#ifndef _ASM_RISCV_PERF_EVENT_H
#define _ASM_RISCV_PERF_EVENT_H
+#ifdef CONFIG_PERF_EVENTS
#include <linux/perf_event.h>
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs) perf_misc_flags(regs)
#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
#define perf_arch_fetch_caller_regs(regs, __ip) { \
@@ -17,4 +21,6 @@
(regs)->sp = current_stack_pointer; \
(regs)->status = SR_PP; \
}
+#endif
+
#endif /* _ASM_RISCV_PERF_EVENT_H */
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index c7468af77c66..c2c81a80f816 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -28,11 +28,49 @@ static bool fill_callchain(void *entry, unsigned long pc)
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
+ if (perf_guest_state()) {
+ /* TODO: We don't support guest os callchain now */
+ return;
That seems kind of weird, but it looks like almost exactly the same
thing Marc did in 75e424620a4f ("arm64: perf: add guest vs host
discrimination"). I think it's safe, as we'll basically just silently
display no backtrace and we can always just fail to backtrace.
That said: I don't understand why we can't backtrace inside a guest? If
we can get the registers and memory it seems like we should be able to.
Maybe I'm missing something?
+ }
+
arch_stack_walk_user(fill_callchain, entry, regs);
}
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
+ if (perf_guest_state()) {
+ /* TODO: We don't support guest os callchain now */
+ return;
+ }
+
walk_stackframe(NULL, regs, fill_callchain, entry);
}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+ if (perf_guest_state())
+ return perf_guest_get_ip();
+
+ return instruction_pointer(regs);
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+ unsigned int guest_state = perf_guest_state();
+ unsigned long misc = 0;
+
+ if (guest_state) {
+ if (guest_state & PERF_GUEST_USER)
+ misc |= PERF_RECORD_MISC_GUEST_USER;
+ else
+ misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+ } else {
+ if (user_mode(regs))
+ misc |= PERF_RECORD_MISC_USER;
+ else
+ misc |= PERF_RECORD_MISC_KERNEL;
+ }
+
+ return misc;
+}
