[PATCH AUTOSEL 6.1 097/212] perf/hw_breakpoint: Return EOPNOTSUPP for unsupported breakpoint type

[PATCH AUTOSEL 6.1 097/212] perf/hw_breakpoint: Return EOPNOTSUPP for unsupported breakpoint type

[Sasha Levin]

From: Saket Kumar Bhaskar <skb99@linux.ibm.com>

[ Upstream commit 061c991697062f3bf87b72ed553d1d33a0e370dd ]

Currently, __reserve_bp_slot() returns -ENOSPC for unsupported
breakpoint types on the architecture. For example, powerpc
does not support hardware instruction breakpoints. This causes
the perf_skip BPF selftest to fail, as neither ENOENT nor
EOPNOTSUPP is returned by perf_event_open for unsupported
breakpoint types. As a result, the test that should be skipped
for this arch is not correctly identified.

To resolve this, hw_breakpoint_event_init() should exit early by
checking for unsupported breakpoint types using
hw_breakpoint_slots_cached() and return the appropriate error
(-EOPNOTSUPP).

Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: https://lore.kernel.org/r/20250303092451.1862862-1-skb99@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/events/hw_breakpoint.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index c3797701339cb..382a3b04f6d33 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -978,9 +978,10 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
 		return -ENOENT;
 
 	/*
-	 * no branch sampling for breakpoint events
+	 * Check if breakpoint type is supported before proceeding.
+	 * Also, no branch sampling for breakpoint events.
 	 */
-	if (has_branch_stack(bp))
+	if (!hw_breakpoint_slots_cached(find_slot_idx(bp->attr.bp_type)) || has_branch_stack(bp))
 		return -EOPNOTSUPP;
 
 	err = register_perf_hw_breakpoint(bp);
-- 
2.39.5

[PATCH AUTOSEL 6.1 193/212] perf: Avoid the read if the count is already updated

[Sasha Levin]

From: "Peter Zijlstra (Intel)" <peterz@infradead.org>

[ Upstream commit 8ce939a0fa194939cc1f92dbd8bc1a7806e7d40a ]

The event may have been updated in the PMU-specific implementation,
e.g., Intel PEBS counters snapshotting. The common code should not
read and overwrite the value.

The PERF_SAMPLE_READ in the data->sample_type can be used to detect
whether the PMU-specific value is available. If yes, avoid the
pmu->read() in the common code. Add a new flag, skip_read, to track the
case.

Factor out a perf_pmu_read() to clean up the code.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250121152303.3128733-3-kan.liang@linux.intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/perf_event.h  |  8 +++++++-
 kernel/events/core.c        | 33 ++++++++++++++++-----------------
 kernel/events/ring_buffer.c |  1 +
 3 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 27b694552d58b..41ff70f315a92 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -935,7 +935,13 @@ struct perf_output_handle {
 	struct perf_buffer		*rb;
 	unsigned long			wakeup;
 	unsigned long			size;
-	u64				aux_flags;
+	union {
+		u64			flags;		/* perf_output*() */
+		u64			aux_flags;	/* perf_aux_output*() */
+		struct {
+			u64		skip_read : 1;
+		};
+	};
 	union {
 		void			*addr;
 		unsigned long		head;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8fc2bc5646ee2..552bb00bfceb0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1180,6 +1180,12 @@ static void perf_event_ctx_deactivate(struct perf_event_context *ctx)
 	list_del_init(&ctx->active_ctx_list);
 }
 
+static inline void perf_pmu_read(struct perf_event *event)
+{
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		event->pmu->read(event);
+}
+
 static void get_ctx(struct perf_event_context *ctx)
 {
 	refcount_inc(&ctx->refcount);
@@ -3389,8 +3395,7 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	 * we know the event must be on the current CPU, therefore we
 	 * don't need to use it.
 	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		event->pmu->read(event);
+	perf_pmu_read(event);
 
 	perf_event_update_time(event);
 
@@ -4444,15 +4449,8 @@ static void __perf_event_read(void *info)
 
 	pmu->read(event);
 
-	for_each_sibling_event(sub, event) {
-		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
-			/*
-			 * Use sibling's PMU rather than @event's since
-			 * sibling could be on different (eg: software) PMU.
-			 */
-			sub->pmu->read(sub);
-		}
-	}
+	for_each_sibling_event(sub, event)
+		perf_pmu_read(sub);
 
 	data->ret = pmu->commit_txn(pmu);
 
@@ -7101,9 +7099,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		values[n++] = running;
 
-	if ((leader != event) &&
-	    (leader->state == PERF_EVENT_STATE_ACTIVE))
-		leader->pmu->read(leader);
+	if ((leader != event) && !handle->skip_read)
+		perf_pmu_read(leader);
 
 	values[n++] = perf_event_count(leader);
 	if (read_format & PERF_FORMAT_ID)
@@ -7116,9 +7113,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	for_each_sibling_event(sub, leader) {
 		n = 0;
 
-		if ((sub != event) &&
-		    (sub->state == PERF_EVENT_STATE_ACTIVE))
-			sub->pmu->read(sub);
+		if ((sub != event) && !handle->skip_read)
+			perf_pmu_read(sub);
 
 		values[n++] = perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
@@ -7173,6 +7169,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 {
 	u64 sample_type = data->type;
 
+	if (data->sample_flags & PERF_SAMPLE_READ)
+		handle->skip_read = 1;
+
 	perf_output_put(handle, *header);
 
 	if (sample_type & PERF_SAMPLE_IDENTIFIER)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 3e1655374c2ed..4c4894de6e5d1 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -181,6 +181,7 @@ __perf_output_begin(struct perf_output_handle *handle,
 
 	handle->rb    = rb;
 	handle->event = event;
+	handle->flags = 0;
 
 	have_lost = local_read(&rb->lost);
 	if (unlikely(have_lost)) {
-- 
2.39.5

[PATCH AUTOSEL 6.1 203/212] perf/amd/ibs: Fix perf_ibs_op.cnt_mask for CurCnt

[Sasha Levin]

From: Ravi Bangoria <ravi.bangoria@amd.com>

[ Upstream commit 46dcf85566170d4528b842bf83ffc350d71771fa ]

IBS Op uses two counters: MaxCnt and CurCnt. MaxCnt is programmed with
the desired sample period. IBS hw generates sample when CurCnt reaches
to MaxCnt. The size of these counter used to be 20 bits but later they
were extended to 27 bits. The 7 bit extension is indicated by CPUID
Fn8000_001B_EAX[6 / OpCntExt].

perf_ibs->cnt_mask variable contains bit masks for MaxCnt and CurCnt.
But IBS driver does not set upper 7 bits of CurCnt in cnt_mask even
when OpCntExt CPUID bit is set. Fix this.

IBS driver uses cnt_mask[CurCnt] bits only while disabling an event.
Fortunately, CurCnt bits are not read from MSR while re-enabling the
event, instead MaxCnt is programmed with desired period and CurCnt is
set to 0. Hence, we did not see any issues so far.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20250115054438.1021-5-ravi.bangoria@amd.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/events/amd/ibs.c         | 3 ++-
 arch/x86/include/asm/perf_event.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 37cbbc5c659a5..8c385e231e070 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1216,7 +1216,8 @@ static __init int perf_ibs_op_init(void)
 	if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 		perf_ibs_op.max_period  |= IBS_OP_MAX_CNT_EXT_MASK;
 		perf_ibs_op.config_mask	|= IBS_OP_MAX_CNT_EXT_MASK;
-		perf_ibs_op.cnt_mask    |= IBS_OP_MAX_CNT_EXT_MASK;
+		perf_ibs_op.cnt_mask    |= (IBS_OP_MAX_CNT_EXT_MASK |
+					    IBS_OP_CUR_CNT_EXT_MASK);
 	}
 
 	if (ibs_caps & IBS_CAPS_ZEN4)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 4d810b9478a43..fa3576ef19daa 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -456,6 +456,7 @@ struct pebs_xmm {
  */
 #define IBS_OP_CUR_CNT		(0xFFF80ULL<<32)
 #define IBS_OP_CUR_CNT_RAND	(0x0007FULL<<32)
+#define IBS_OP_CUR_CNT_EXT_MASK	(0x7FULL<<52)
 #define IBS_OP_CNT_CTL		(1ULL<<19)
 #define IBS_OP_VAL		(1ULL<<18)
 #define IBS_OP_ENABLE		(1ULL<<17)
-- 
2.39.5