[PATCH 0/5] perf: Clean ups and simplifications

[PATCH 0/5] perf: Clean ups and simplifications

[Steven Rostedt]

The ongoing work to support sframes[1] in the kernel required a few clean ups
to the perf kernel side. Instead of having these changes in the ongoing
work, there's no reason they cannot be applied now.

These are just clean ups to the perf code to help simplify the updates that
will be made later.

[1] https://lore.kernel.org/linux-trace-kernel/20250708020003.565862284@kernel.org

Josh Poimboeuf (4):
      perf: Remove get_perf_callchain() init_nr argument
      perf: Have get_perf_callchain() return NULL if crosstask and user are set
      perf: Simplify get_perf_callchain() user logic
      perf: Skip user unwind if the task is a kernel thread

Steven Rostedt (1):
      perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL

----
 include/linux/perf_event.h |  2 +-
 kernel/bpf/stackmap.c      |  4 ++--
 kernel/events/callchain.c  | 40 +++++++++++++++++++---------------------
 kernel/events/core.c       |  9 +++++----
 4 files changed, 27 insertions(+), 28 deletions(-)

[PATCH 1/5] perf: Remove get_perf_callchain() init_nr argument

[Steven Rostedt]

From: Josh Poimboeuf <jpoimboe@kernel.org>

The 'init_nr' argument has double duty: it's used to initialize both the
number of contexts and the number of stack entries.  That's confusing
and the callers always pass zero anyway.  Hard code the zero.

Acked-by: Namhyung Kim <Namhyung@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/perf_event.h |  2 +-
 kernel/bpf/stackmap.c      |  4 ++--
 kernel/events/callchain.c  | 12 ++++++------
 kernel/events/core.c       |  2 +-
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ec9d96025683..54e0d31afcad 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1719,7 +1719,7 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
 extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern struct perf_callchain_entry *
-get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
+get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 3615c06b7dfa..ec3a57a5fba1 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -314,7 +314,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	if (max_depth > sysctl_perf_event_max_stack)
 		max_depth = sysctl_perf_event_max_stack;
 
-	trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
+	trace = get_perf_callchain(regs, kernel, user, max_depth,
 				   false, false);
 
 	if (unlikely(!trace))
@@ -451,7 +451,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else if (kernel && task)
 		trace = get_callchain_entry_for_task(task, max_depth);
 	else
-		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
+		trace = get_perf_callchain(regs, kernel, user, max_depth,
 					   crosstask, false);
 
 	if (unlikely(!trace) || trace->nr < skip) {
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 6c83ad674d01..b0f5bd228cd8 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -217,7 +217,7 @@ static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entr
 }
 
 struct perf_callchain_entry *
-get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
+get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark)
 {
 	struct perf_callchain_entry *entry;
@@ -228,11 +228,11 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 	if (!entry)
 		return NULL;
 
-	ctx.entry     = entry;
-	ctx.max_stack = max_stack;
-	ctx.nr	      = entry->nr = init_nr;
-	ctx.contexts       = 0;
-	ctx.contexts_maxed = false;
+	ctx.entry		= entry;
+	ctx.max_stack		= max_stack;
+	ctx.nr			= entry->nr = 0;
+	ctx.contexts		= 0;
+	ctx.contexts_maxed	= false;
 
 	if (kernel && !user_mode(regs)) {
 		if (add_mark)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0db36b2b2448..b2a53cabcb17 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8178,7 +8178,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	if (!kernel && !user)
 		return &__empty_callchain;
 
-	callchain = get_perf_callchain(regs, 0, kernel, user,
+	callchain = get_perf_callchain(regs, kernel, user,
 				       max_stack, crosstask, true);
 	return callchain ?: &__empty_callchain;
 }
-- 
2.47.2

[PATCH 2/5] perf: Have get_perf_callchain() return NULL if crosstask and user are set

[Steven Rostedt]

From: Josh Poimboeuf <jpoimboe@kernel.org>

get_perf_callchain() doesn't support cross-task unwinding for user space
stacks, have it return NULL if both the crosstask and user arguments are
set.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/events/callchain.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index b0f5bd228cd8..cd0e3fc7ed05 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -224,6 +224,10 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 	struct perf_callchain_entry_ctx ctx;
 	int rctx, start_entry_idx;
 
+	/* crosstask is not supported for user stacks */
+	if (crosstask && user && !kernel)
+		return NULL;
+
 	entry = get_callchain_entry(&rctx);
 	if (!entry)
 		return NULL;
@@ -240,7 +244,7 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		perf_callchain_kernel(&ctx, regs);
 	}
 
-	if (user) {
+	if (user && !crosstask) {
 		if (!user_mode(regs)) {
 			if  (current->mm)
 				regs = task_pt_regs(current);
@@ -249,9 +253,6 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		}
 
 		if (regs) {
-			if (crosstask)
-				goto exit_put;
-
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
@@ -261,7 +262,6 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		}
 	}
 
-exit_put:
 	put_callchain_entry(rctx);
 
 	return entry;
-- 
2.47.2

[PATCH 3/5] perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL

[Steven Rostedt]

From: Steven Rostedt <rostedt@goodmis.org>

To determine if a task is a kernel thread or not, it is more reliable to
use (current->flags & (PF_KTHREAD|PF_USER_WORKERi)) than to rely on
current->mm being NULL.  That is because some kernel tasks (io_uring
helpers) may have a mm field.

Link: https://lore.kernel.org/linux-trace-kernel/20250424163607.GE18306@noisy.programming.kicks-ass.net/
Link: https://lore.kernel.org/all/20250624130744.602c5b5f@batman.local.home/

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/events/callchain.c | 6 +++---
 kernel/events/core.c      | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index cd0e3fc7ed05..5982d18f169b 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -246,10 +246,10 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 
 	if (user && !crosstask) {
 		if (!user_mode(regs)) {
-			if  (current->mm)
-				regs = task_pt_regs(current);
-			else
+			if (current->flags & (PF_KTHREAD | PF_USER_WORKER))
 				regs = NULL;
+			else
+				regs = task_pt_regs(current);
 		}
 
 		if (regs) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b2a53cabcb17..1fa554e2666d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7414,7 +7414,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
-	} else if (!(current->flags & PF_KTHREAD)) {
+	} else if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) {
 		perf_get_regs_user(regs_user, regs);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
@@ -8054,7 +8054,7 @@ static u64 perf_virt_to_phys(u64 virt)
 		 * Try IRQ-safe get_user_page_fast_only first.
 		 * If failed, leave phys_addr as 0.
 		 */
-		if (current->mm != NULL) {
+		if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) {
 			struct page *p;
 
 			pagefault_disable();
-- 
2.47.2

[PATCH 4/5] perf: Simplify get_perf_callchain() user logic

[Steven Rostedt]

From: Josh Poimboeuf <jpoimboe@kernel.org>

Simplify the get_perf_callchain() user logic a bit.  task_pt_regs()
should never be NULL.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/events/callchain.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 5982d18f169b..808c0d7a31fa 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -247,21 +247,19 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 	if (user && !crosstask) {
 		if (!user_mode(regs)) {
 			if (current->flags & (PF_KTHREAD | PF_USER_WORKER))
-				regs = NULL;
-			else
-				regs = task_pt_regs(current);
+				goto exit_put;
+			regs = task_pt_regs(current);
 		}
 
-		if (regs) {
-			if (add_mark)
-				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+		if (add_mark)
+			perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
-			start_entry_idx = entry->nr;
-			perf_callchain_user(&ctx, regs);
-			fixup_uretprobe_trampoline_entries(entry, start_entry_idx);
-		}
+		start_entry_idx = entry->nr;
+		perf_callchain_user(&ctx, regs);
+		fixup_uretprobe_trampoline_entries(entry, start_entry_idx);
 	}
 
+exit_put:
 	put_callchain_entry(rctx);
 
 	return entry;
-- 
2.47.2

[PATCH 5/5] perf: Skip user unwind if the task is a kernel thread

[Steven Rostedt]

From: Josh Poimboeuf <jpoimboe@kernel.org>

If the task is not a user thread, there's no user stack to unwind.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1fa554e2666d..bd0a33f389d2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8166,7 +8166,8 @@ struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
 	bool kernel = !event->attr.exclude_callchain_kernel;
-	bool user   = !event->attr.exclude_callchain_user;
+	bool user   = !event->attr.exclude_callchain_user &&
+		!(current->flags & (PF_KTHREAD | PF_USER_WORKER));
 	/* Disallow cross-task user callchains. */
 	bool crosstask = event->ctx->task && event->ctx->task != current;
 	const u32 max_stack = event->attr.sample_max_stack;
-- 
2.47.2