[PATCH v6 13/13] alpha/perf: honor exclude_user and exclude_kernel for ProfileMe events

[Matt Turner]

The PMU sets PERF_PMU_CAP_NO_EXCLUDE, as the counters count in every
mode. perf record then fails for unprivileged users: at the default
perf_event_paranoid of 2, the tool sets exclude_kernel for them.

A ProfileMe sample says which mode the profiled instruction ran in, so
the excluded samples can be dropped, as AMD IBS does with swfilt. Do
that for ProfileMe events, counting PALmode as kernel, and ignore
exclude_hv, as there is no hypervisor. A sample that falls back to the
interrupted PC is dropped if either its PC or the profiled instruction
is in an excluded mode. Aggregate events cannot tell, so event_init
now rejects their exclude bits itself, along with exclude_idle,
exclude_guest and exclude_host for all events.

The event count, and what PCTR1 counted during a window, still include
the excluded modes, as they do for IBS.

Suggested-by: Ian Rogers <irogers@xxxxxxxxxx>
Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Matt Turner <mattst88@xxxxxxxxx>
---
 arch/alpha/kernel/perf_event.c | 47 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 38 insertions(+), 9 deletions(-)

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 7e34eac0ea47..c75d204076fa 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -832,6 +832,18 @@ static int __hw_perf_event_init(struct perf_event *event)
 		return -EINVAL;
 	hwc->flags = profileme ? ALPHA_PERF_FLAG_PROFILEME : 0;
 
+	/*
+	 * The counters count in every mode, but ProfileMe samples say which
+	 * mode the profiled instruction ran in, so those that are excluded can
+	 * be dropped. PALmode counts as kernel, and exclude_hv is ignored, as
+	 * there is no hypervisor.
+	 */
+	if (attr->exclude_idle || attr->exclude_guest || attr->exclude_host)
+		return -EINVAL;
+	if (!profileme &&
+	    (attr->exclude_user || attr->exclude_kernel || attr->exclude_hv))
+		return -EINVAL;
+
 	if (attr->config1 & ~ALPHA_PERF_CONFIG1_FILTERS)
 		return -EINVAL;
 	if (attr->config1 && !profileme)
@@ -983,7 +995,6 @@ static struct pmu pmu = {
 	.stop		= alpha_pmu_stop,
 	.read		= alpha_pmu_read,
 	.attr_groups	= ev67_attr_groups,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 
@@ -1140,6 +1151,24 @@ static u64 alpha_profileme_status(unsigned long i_stat,
 	return status;
 }
 
+/*
+ * Whether exclude_user or exclude_kernel rules out a sample of the profiled
+ * instruction at pmpc, reported at pc. A PALmode PMPC counts as kernel. The
+ * two differ only when the sample falls back to the interrupted PC, and
+ * such a sample is then dropped if either mode is excluded.
+ */
+static bool alpha_profileme_excluded(struct perf_event *event,
+				     unsigned long pmpc, unsigned long pc)
+{
+	bool pm_user = !(pmpc & EV67_PMPC_PAL) &&
+		       (pmpc & EV67_PMPC_PC_MASK) < TASK_SIZE;
+	bool user = pc < TASK_SIZE;
+
+	if (event->attr.exclude_user && (pm_user || user))
+		return true;
+	return event->attr.exclude_kernel && !(pm_user && user);
+}
+
 /* What the memory instruction at pc does, or PERF_MEM_OP_NA. */
 static u64 alpha_profileme_mem_op(unsigned long pc)
 {
@@ -1250,14 +1279,6 @@ static void alpha_perf_event_profileme(struct perf_event *event,
 		local64_add(ovr, &hwc->period_left);
 	}
 
-	/* A dropped sample still counts, for throttling and frequency mode. */
-	if ((alpha_profileme_status(i_stat, pctr_ctl, pmpc) & hwc->config) !=
-	    hwc->config) {
-		if (alpha_perf_event_set_period(event, hwc, 0))
-			perf_event_account_interrupt(event);
-		return;
-	}
-
 	/*
 	 * Attribute the sample to the profiled instruction rather than to
 	 * wherever the interrupt landed. perf takes the sample's mode,
@@ -1303,6 +1324,14 @@ static void alpha_perf_event_profileme(struct perf_event *event,
 		memset(pm_regs, 0, sizeof(*pm_regs));
 	}
 
+	/* A dropped sample still counts, for throttling and frequency mode. */
+	if ((alpha_profileme_status(i_stat, pctr_ctl, pmpc) & hwc->config) !=
+	    hwc->config || alpha_profileme_excluded(event, pmpc, pc)) {
+		if (alpha_perf_event_set_period(event, hwc, 0))
+			perf_event_account_interrupt(event);
+		return;
+	}
+
 	perf_sample_data_init(&data, 0, hwc->last_period);
 	if (pc_only)
 		alpha_profileme_drop_regs(event, &data, PERF_SAMPLE_REGS_USER |

-- 
2.55.0