powerpc/perf: Set cpumode flags using sample address

Currently in some cases, when the sampled instruction address register
latches to a specific address during sampling, the privilege bits
captured in the sampled event register are incorrect.

For example, a snippet from the perf report on a power10 system is:

  Overhead  Address             Command       Shared Object      Symbol
  ........  ..................  ............  .................  .......................
       2.41%  0x7fff9f94a02c      null_syscall  [unknown]          [k] 0x00007fff9f94a02c
       2.20%  0x7fff9f94a02c      null_syscall  libc.so.6          [.] syscall

perf_get_misc_flags() function looks at the privilege bits to return
the corresponding flags to be used for the address symbol and these
privilege bit details are read from the sampled event register. In the
above snippet, address "0x00007fff9f94a02c" is shown as "k" (kernel) due
to the incorrect privilege bits captured in the sampled event register.

To address this case check whether the sampled address is in the kernel
area. Since this is specific to the latest platform, a new pmu flag
is added called "PPMU_P10" and is used to contain the proposed fix.
PPMU_P10_DD1 marked events are also included under PPMU_P10, hence
remove the code specific to PPMU_P10_DD1 marked events.

Signed-off-by: Anjali K <anjalik@linux.ibm.com>
Reviewed-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com <mailto:atrajeev@linux.vnet.ibm.com>>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240528040356.2722275-1-anjalik@linux.ibm.com

1 files changed, 19 insertions, 26 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6b5f8a94e7d8..42867469752d 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -266,51 +266,44 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	bool use_siar = regs_use_siar(regs);
-	unsigned long mmcra = regs->dsisr;
-	int marked = mmcra & MMCRA_SAMPLE_ENABLE;
+	unsigned long siar;
+	unsigned long addr;
 
 	if (!use_siar)
 		return perf_flags_from_msr(regs);
 
 	/*
-	 * Check the address in SIAR to identify the
-	 * privilege levels since the SIER[MSR_HV, MSR_PR]
-	 * bits are not set for marked events in power10
-	 * DD1.
-	 */
-	if (marked && (ppmu->flags & PPMU_P10_DD1)) {
-		unsigned long siar = mfspr(SPRN_SIAR);
-		if (siar) {
-			if (is_kernel_addr(siar))
-				return PERF_RECORD_MISC_KERNEL;
-			return PERF_RECORD_MISC_USER;
-		} else {
-			if (is_kernel_addr(regs->nip))
-				return PERF_RECORD_MISC_KERNEL;
-			return PERF_RECORD_MISC_USER;
-		}
-	}
-
-	/*
 	 * If we don't have flags in MMCRA, rather than using
 	 * the MSR, we intuit the flags from the address in
 	 * SIAR which should give slightly more reliable
 	 * results
 	 */
 	if (ppmu->flags & PPMU_NO_SIPR) {
-		unsigned long siar = mfspr(SPRN_SIAR);
+		siar = mfspr(SPRN_SIAR);
 		if (is_kernel_addr(siar))
 			return PERF_RECORD_MISC_KERNEL;
 		return PERF_RECORD_MISC_USER;
 	}
 
 	/* PR has priority over HV, so order below is important */
-	if (regs_sipr(regs))
-		return PERF_RECORD_MISC_USER;
-
-	if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
+	if (regs_sipr(regs)) {
+		if (!(ppmu->flags & PPMU_P10))
+			return PERF_RECORD_MISC_USER;
+	} else if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
 		return PERF_RECORD_MISC_HYPERVISOR;
 
+	/*
+	 * Check the address in SIAR to identify the
+	 * privilege levels since the SIER[MSR_HV, MSR_PR]
+	 * bits are not set correctly in power10 sometimes
+	 */
+	if (ppmu->flags & PPMU_P10) {
+		siar = mfspr(SPRN_SIAR);
+		addr = siar ? siar : regs->nip;
+		if (!is_kernel_addr(addr))
+			return PERF_RECORD_MISC_USER;
+	}
+
 	return PERF_RECORD_MISC_KERNEL;
 }