Skip to contentSkip to conversation

perf: Support the deferred unwinding infrastructure

PATCH In review Steven Rostedt 2 participants 17 messages Jul 1, 2025 – Jul 2, 2025

Subsystems (4)
lore
Share & tools
lore

Steven Rostedt

author maintainer
#0 lore raw

v12 cover perf: Support the deferred unwinding infrastructure

This is based on top of the deferred unwind core patch series:

https://lore.kernel.org/linux-trace-kernel/[email protected]/
git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git unwind/core

This series implements the perf interface to use deferred user space stack tracing.

The code can be found here:

git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git unwind/perf

Head SHA1: e00f51618c68b5b6fd6054488212504592c9e392

Changes since v11: https://lore.kernel.org/linux-trace-kernel/[email protected]/

- Also check against PF_USER_WORKER as io workers do not have PF_KTHREAD set.

- Removed deferred_request_nmi() and have NMIs just use the normal deferred_request() function. As Peter Zijlstra has stated, in_nmi() can nest because some exceptions set in_nmi() and a real NMI could come in.

Josh Poimboeuf (5):
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
perf: Support deferred user callchains

Namhyung Kim (4):
perf tools: Minimal CALLCHAIN_DEFERRED support perf record: Enable defer_callchain for user callchains perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED perf tools: Merge deferred user callchains

Steven Rostedt (2):
perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL
perf: Support deferred user callchains for per CPU events

----

 include/linux/perf_event.h                |  13 +-
 include/uapi/linux/perf_event.h           |  19 +-
 kernel/bpf/stackmap.c                     |   8 +-
 kernel/events/callchain.c                 |  49 ++--
 kernel/events/core.c                      | 410 +++++++++++++++++++++++++++++-
 tools/include/uapi/linux/perf_event.h     |  19 +-
 tools/lib/perf/include/perf/event.h       |   7 +
 tools/perf/Documentation/perf-script.txt  |   5 +
 tools/perf/builtin-script.c               |  92 +++++++
 tools/perf/util/callchain.c               |  24 ++
 tools/perf/util/callchain.h               |   3 +
 tools/perf/util/event.c                   |   1 +
 tools/perf/util/evlist.c                  |   1 +
 tools/perf/util/evlist.h                  |   1 +
 tools/perf/util/evsel.c                   |  39 +++
 tools/perf/util/evsel.h                   |   1 +
 tools/perf/util/machine.c                 |   1 +
 tools/perf/util/perf_event_attr_fprintf.c |   1 +
 tools/perf/util/sample.h                  |   3 +-
 tools/perf/util/session.c                 |  78 ++++++
 tools/perf/util/tool.c                    |   2 +
 tools/perf/util/tool.h                    |   4 +-
 22 files changed, 745 insertions(+), 36 deletions(-)
author maintainer
#1 lore raw

PATCH v12 1/11 perf: Remove get_perf_callchain() init_nr argument

From: Josh Poimboeuf <[email protected]>

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.

---
 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(-)
include/linux/perf_event.h +1 -1
index ec9d96025683..54e0d31afcad 100644
@@ -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);
kernel/bpf/stackmap.c +2 -2
index 3615c06b7dfa..ec3a57a5fba1 100644
@@ -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) {
kernel/events/callchain.c +6 -6
index 6c83ad674d01..b0f5bd228cd8 100644
@@ -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)
kernel/events/core.c +1 -1
index 7281230044d0..f2f7cff826e0 100644
@@ -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;
 }
Signature · 1 line
2.47.2
author maintainer
#2 lore raw

PATCH v12 2/11 perf: Have get_perf_callchain() return NULL if crosstask and user are set

In reply to Steven Rostedt

From: Josh Poimboeuf <[email protected]>

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.

---
 kernel/events/callchain.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
kernel/events/callchain.c +5 -5
index b0f5bd228cd8..cd0e3fc7ed05 100644
@@ -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;
Signature · 1 line
2.47.2
author maintainer
#3 lore raw

PATCH v12 3/11 perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL

In reply to Steven Rostedt

From: Steven Rostedt <[email protected]>

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.

---
Changes since v11: https://lore.kernel.org/[email protected]

- Also check against PF_USER_WORKER as io workers do not have PF_KTHREAD set.

 kernel/events/callchain.c | 6 +++---
 kernel/events/core.c      | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)
kernel/events/callchain.c +3 -3
index cd0e3fc7ed05..5982d18f169b 100644
@@ -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) {
kernel/events/core.c +2 -2
index f2f7cff826e0..2c524fe4bd19 100644
@@ -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)) {
 			struct page *p;
 
 			pagefault_disable();
Signature · 1 line
2.47.2
author maintainer
#4 lore raw

PATCH v12 4/11 perf: Simplify get_perf_callchain() user logic

In reply to Steven Rostedt

From: Josh Poimboeuf <[email protected]>

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

---
 kernel/events/callchain.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)
kernel/events/callchain.c +8 -10
index 5982d18f169b..808c0d7a31fa 100644
@@ -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;
Signature · 1 line
2.47.2
author maintainer
#5 lore raw
In reply to Steven Rostedt
Quoted 13 lines · On Tue, 01 Jul 2025 14:04:10 -0400 Steven Rostedt <[email protected]> wrote:

Josh Poimboeuf (5):
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
perf: Support deferred user callchains

Namhyung Kim (4):
perf tools: Minimal CALLCHAIN_DEFERRED support perf record: Enable defer_callchain for user callchains perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED perf tools: Merge deferred user callchains

Quoted 3 lines

Steven Rostedt (2):
perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL
perf: Support deferred user callchains for per CPU events

Hmm, patches 5-11 seemed to be dropped, and I sent out 12 patches of the latest sframe work that I can't find anywhere. I think my ISP is thinking I'm spamming so it dropped the emails. That's all I can figure.

I originally used kernel.org as my smtp server, but gmail starting putting my emails into spam because kernel.org can't validate goodmis.org with DKIM (my DNS has kernel.org set for SPF, but that's not enough these days :-p).

So I went back to my ISP (hover.com) as my SMTP server, but now I think it doesn't like my scripts that sends out a series of patches to a lot of people. It likely thinks I'm a spam bot (although maybe I am!).

I guess I'll change my scripts to use [email protected] to send and go back to using kernel.org as the SMTP server for my scripts. :-/

Expect a resend. Sorry for all the noise.

-- Steve

author maintainer
#6 lore raw
Quoted 3 lines · On Tue, 1 Jul 2025 15:17:15 -0400 Steven Rostedt <[email protected]> wrote:

Hmm, patches 5-11 seemed to be dropped, and I sent out 12 patches of the latest sframe work that I can't find anywhere. I think my ISP is thinking I'm spamming so it dropped the emails. That's all I can figure.

Hah! After I write this, my patches start showing up! :-p

OK, no resend.

-- Steve

author maintainer
#7 lore raw

PATCH v12 5/11 perf: Skip user unwind if the task is a kernel thread

In reply to Steven Rostedt

From: Josh Poimboeuf <[email protected]>

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

---
Changes since v11: https://lore.kernel.org/[email protected]

- Added test against PF_USER_WORKER as well as PF_KTHREAD

 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/events/core.c +2 -1
index 2c524fe4bd19..43d76ed882da 100644
@@ -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;
Signature · 1 line
2.47.2
author maintainer
#8 lore raw

PATCH v12 6/11 perf: Support deferred user callchains

In reply to Steven Rostedt

From: Josh Poimboeuf <[email protected]>

Use the new unwind_deferred_trace() interface (if available) to defer unwinds to task context. This will allow the use of .sframe (when it becomes available) and also prevents duplicate userspace unwinds.

---
Changes since v11: https://lore.kernel.org/[email protected]

- Removed deferred_request_nmi() and have NMIs just use the normal deferred_request() function. As Peter Zijlstra has stated, in_nmi() can nest because some exceptions set in_nmi() and another NMI could come in.

- Added test against PF_USER_WORKER as well as PF_KTHREAD

 include/linux/perf_event.h            |   7 +-
 include/uapi/linux/perf_event.h       |  19 +++-
 kernel/bpf/stackmap.c                 |   4 +-
 kernel/events/callchain.c             |  11 +-
 kernel/events/core.c                  | 149 +++++++++++++++++++++++++-
 tools/include/uapi/linux/perf_event.h |  19 +++-
 6 files changed, 201 insertions(+), 8 deletions(-)
include/linux/perf_event.h +6 -1
index 54e0d31afcad..c7d474391e51 100644
@@ -53,6 +53,7 @@
 #include <linux/security.h>
 #include <linux/static_call.h>
 #include <linux/lockdep.h>
+#include <linux/unwind_deferred.h>
 
 #include <asm/local.h>
 
@@ -880,6 +881,10 @@ struct perf_event {
 	struct callback_head		pending_task;
 	unsigned int			pending_work;
 
+	unsigned int			pending_unwind_callback;
+	struct callback_head		pending_unwind_work;
+	struct rcuwait			pending_unwind_wait;
+
 	atomic_t			event_limit;
 
 	/* address range filters */
@@ -1720,7 +1725,7 @@ extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct p
 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, bool kernel, bool user,
-		   u32 max_stack, bool crosstask, bool add_mark);
+		   u32 max_stack, bool crosstask, bool add_mark, bool defer_user);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
include/uapi/linux/perf_event.h +18 -1
index 78a362b80027..184740d1e79d 100644
@@ -463,7 +463,8 @@ struct perf_event_attr {
 				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
 				remove_on_exec :  1, /* event is removed from task on exec */
 				sigtrap        :  1, /* send synchronous SIGTRAP on event */
-				__reserved_1   : 26;
+				defer_callchain:  1, /* generate PERF_RECORD_CALLCHAIN_DEFERRED records */
+				__reserved_1   : 25;
 
 	union {
 		__u32		wakeup_events;	  /* wake up every n events */
@@ -1239,6 +1240,21 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
 
+	/*
+	 * This user callchain capture was deferred until shortly before
+	 * returning to user space.  Previous samples would have kernel
+	 * callchains only and they need to be stitched with this to make full
+	 * callchains.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				nr;
+	 *	u64				ips[nr];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CALLCHAIN_DEFERRED		= 22,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -1269,6 +1285,7 @@ enum perf_callchain_context {
 	PERF_CONTEXT_HV				= (__u64)-32,
 	PERF_CONTEXT_KERNEL			= (__u64)-128,
 	PERF_CONTEXT_USER			= (__u64)-512,
+	PERF_CONTEXT_USER_DEFERRED		= (__u64)-640,
 
 	PERF_CONTEXT_GUEST			= (__u64)-2048,
 	PERF_CONTEXT_GUEST_KERNEL		= (__u64)-2176,
kernel/bpf/stackmap.c +2 -2
index ec3a57a5fba1..339f7cbbcf36 100644
@@ -315,7 +315,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 		max_depth = sysctl_perf_event_max_stack;
 
 	trace = get_perf_callchain(regs, kernel, user, max_depth,
-				   false, false);
+				   false, false, false);
 
 	if (unlikely(!trace))
 		/* couldn't fetch the stack trace */
@@ -452,7 +452,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 		trace = get_callchain_entry_for_task(task, max_depth);
 	else
 		trace = get_perf_callchain(regs, kernel, user, max_depth,
-					   crosstask, false);
+					   crosstask, false, false);
 
 	if (unlikely(!trace) || trace->nr < skip) {
 		if (may_fault)
kernel/events/callchain.c +10 -1
index 808c0d7a31fa..d0e0da66a164 100644
@@ -218,7 +218,7 @@ static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entr
 
 struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
-		   u32 max_stack, bool crosstask, bool add_mark)
+		   u32 max_stack, bool crosstask, bool add_mark, bool defer_user)
 {
 	struct perf_callchain_entry *entry;
 	struct perf_callchain_entry_ctx ctx;
@@ -251,6 +251,15 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 			regs = task_pt_regs(current);
 		}
 
+		if (defer_user) {
+			/*
+			 * Foretell the coming of PERF_RECORD_CALLCHAIN_DEFERRED
+			 * which can be stitched to this one.
+			 */
+			perf_callchain_store_context(&ctx, PERF_CONTEXT_USER_DEFERRED);
+			goto exit_put;
+		}
+
 		if (add_mark)
 			perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
kernel/events/core.c +147 -2

191 lines not on this page · raw message

tools/include/uapi/linux/perf_event.h +18 -1
index 78a362b80027..184740d1e79d 100644
@@ -463,7 +463,8 @@ struct perf_event_attr {
 				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
 				remove_on_exec :  1, /* event is removed from task on exec */
 				sigtrap        :  1, /* send synchronous SIGTRAP on event */
-				__reserved_1   : 26;
+				defer_callchain:  1, /* generate PERF_RECORD_CALLCHAIN_DEFERRED records */
+				__reserved_1   : 25;
 
 	union {
 		__u32		wakeup_events;	  /* wake up every n events */
@@ -1239,6 +1240,21 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
 
+	/*
+	 * This user callchain capture was deferred until shortly before
+	 * returning to user space.  Previous samples would have kernel
+	 * callchains only and they need to be stitched with this to make full
+	 * callchains.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				nr;
+	 *	u64				ips[nr];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CALLCHAIN_DEFERRED		= 22,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -1269,6 +1285,7 @@ enum perf_callchain_context {
 	PERF_CONTEXT_HV				= (__u64)-32,
 	PERF_CONTEXT_KERNEL			= (__u64)-128,
 	PERF_CONTEXT_USER			= (__u64)-512,
+	PERF_CONTEXT_USER_DEFERRED		= (__u64)-640,
 
 	PERF_CONTEXT_GUEST			= (__u64)-2048,
 	PERF_CONTEXT_GUEST_KERNEL		= (__u64)-2176,
Signature · 1 line
2.47.2
author maintainer
#9 lore raw

PATCH v12 7/11 perf: Support deferred user callchains for per CPU events

In reply to Steven Rostedt

From: Steven Rostedt <[email protected]>

The deferred unwinder works fine for task events (events that trace only a specific task), as it can use a task_work from an interrupt or NMI and when the task goes back to user space it will call the event's callback to do the deferred unwinding.

But for per CPU events things are not so simple. When a per CPU event wants a deferred unwinding to occur, it cannot simply use a task_work as there's a many to many relationship. If the task migrates and another task is scheduled in where the per CPU event wants a deferred unwinding to occur on that task as well, and the task that migrated to another CPU has that CPU's event want to unwind it too, each CPU may need unwinding from more than one task, and each task may have requests from many CPUs.

To solve this, when a per CPU event is created that has defer_callchain attribute set, it will do a lookup from a global list (unwind_deferred_list), for a perf_unwind_deferred descriptor that has the id that matches the PID of the current task's group_leader.

If it is not found, then it will create one and add it to the global list. This descriptor contains an array of all possible CPUs, where each element is a perf_unwind_cpu descriptor.

The perf_unwind_cpu descriptor has a list of all the per CPU events that is tracing the matching CPU that corresponds to its index in the array, where the events belong to a task that has the same group_leader. It also has a processing bit and rcuwait to handle removal.

For each occupied perf_unwind_cpu descriptor in the array, the perf_deferred_unwind descriptor increments its nr_cpu_events. When a perf_unwind_cpu descriptor is empty, the nr_cpu_events is decremented. This is used to know when to free the perf_deferred_unwind descriptor, as when it becomes empty, it is no longer referenced.

Finally, the perf_deferred_unwind descriptor has an id that holds the PID of the group_leader for the tasks that the events were created by.

When a second (or more) per CPU event is created where the perf_deferred_unwind descriptor is already created, it just adds itself to the perf_unwind_cpu array of that descriptor. Updating the necessary counter. This is used to map different per CPU events to each other based on their group leader PID.

Each of these perf_deferred_unwind descriptors have a unwind_work that registers with the deferred unwind infrastructure via unwind_deferred_init(), where it also registers a callback to perf_event_deferred_cpu().

Now when a per CPU event requests a deferred unwinding, it calls unwind_deferred_request() with the associated perf_deferred_unwind descriptor. It is expected that the program that uses this has events on all CPUs, as the deferred trace may not be called on the CPU event that requested it. That is, the task may migrate and its user stack trace will be recorded on the CPU event of the CPU that it exits back to user space on.

---
 include/linux/perf_event.h |   4 +
 kernel/events/core.c       | 306 +++++++++++++++++++++++++++++++++----
 2 files changed, 284 insertions(+), 26 deletions(-)
include/linux/perf_event.h +4 -0
index c7d474391e51..546a7f81be96 100644
@@ -733,6 +733,7 @@ struct swevent_hlist {
 struct bpf_prog;
 struct perf_cgroup;
 struct perf_buffer;
+struct perf_unwind_deferred;
 
 struct pmu_event_list {
 	raw_spinlock_t			lock;
@@ -885,6 +886,9 @@ struct perf_event {
 	struct callback_head		pending_unwind_work;
 	struct rcuwait			pending_unwind_wait;
 
+	struct perf_unwind_deferred	*unwind_deferred;
+	struct list_head		unwind_list;
+
 	atomic_t			event_limit;
 
 	/* address range filters */
kernel/events/core.c +280 -26

388 lines not on this page · raw message

Signature · 1 line
2.47.2
#10 lore raw

Re: [PATCH v12 07/11] perf: Support deferred user callchains for per CPU events

Hello Steve!

kernel/events/core.c static void perf_pending_unwind_sync(struct perf_event *event) · line 5790

Quoted 10 lines · Steven Rostedt
kernel/events/core.c +1 -0
@@ -5609,62 +5784,119 @@ static void perf_pending_unwind_sync(struct perf_event *event)
 
 struct perf_callchain_deferred_event {
 	struct perf_event_header	header;
+	u64				timestamp;
 	u64				nr;
 	u64				ips[];
 };

Nit: Please update the following related comments when making changes to struct perf_callchain_deferred_event.

include/uapi/linux/perf_event.h +1 -0
index 184740d1e79d..08ce721e79bc 100644
@@ -1248,6 +1248,7 @@ enum perf_event_type {
 	 *
 	 * struct {
 	 *	struct perf_event_header	header;
+	 *	u64				timestamp;
 	 *	u64				nr;
 	 *	u64				ips[nr];
 	 *	struct sample_id		sample_id;
tools/include/uapi/linux/perf_event.h +1 -0
index 184740d1e79d..08ce721e79bc 100644
@@ -1248,6 +1248,7 @@ enum perf_event_type {
 	 *
 	 * struct {
 	 *	struct perf_event_header	header;
+	 *	u64				timestamp;
 	 *	u64				nr;
 	 *	u64				ips[nr];
 	 *	struct sample_id		sample_id;

Thanks and regards,
Jens

Signature · 9 lines
Jens Remus
Linux on Z Development (D3303)
+49-7031-16-1128 Office
[email protected]

IBM

IBM Deutschland Research & Development GmbH; Vorsitzender des Aufsichtsrats: Wolfgang Wendt; Geschäftsführung: David Faller; Sitz der Gesellschaft: Böblingen; Registergericht: Amtsgericht Stuttgart, HRB 243294
IBM Data Privacy Statement: https://www.ibm.com/privacy/
author maintainer
#11 lore raw

PATCH v12 8/11 perf tools: Minimal CALLCHAIN_DEFERRED support

In reply to Steven Rostedt

From: Namhyung Kim <[email protected]>

Add a new event type for deferred callchains and a new callback for the struct perf_tool. For now it doesn't actually handle the deferred callchains but it just marks the sample if it has the PERF_CONTEXT_ USER_DEFFERED in the callchain array.

At least, perf report can dump the raw data with this change. Actually this requires the next commit to enable attr.defer_callchain, but if you already have a data file, it'll show the following result.

  $ perf report -D
  ...
  [email protected] [0x40]: event: 22
  .
  . ... raw event: size 64 bytes
  .  0000:  16 00 00 00 02 00 40 00 02 00 00 00 00 00 00 00  ......@.........
  .  0010:  00 fe ff ff ff ff ff ff 4b d3 3f 25 45 7f 00 00  ........K.?%E...
  .  0020:  21 03 00 00 21 03 00 00 43 02 12 ab 05 00 00 00  !...!...C.......
  .  0030:  00 00 00 00 00 00 00 00 09 00 00 00 00 00 00 00  ................

0 24344920643 0x5fe0 [0x40]: PERF_RECORD_CALLCHAIN_DEFERRED(IP, 0x2): 801/801: 0 ... FP chain: nr:2
..... 0: fffffffffffffe00
..... 1: 00007f45253fd34b
: unhandled!

---
 tools/lib/perf/include/perf/event.h       |  7 +++++++
 tools/perf/util/event.c                   |  1 +
 tools/perf/util/evsel.c                   | 15 +++++++++++++++
 tools/perf/util/machine.c                 |  1 +
 tools/perf/util/perf_event_attr_fprintf.c |  1 +
 tools/perf/util/sample.h                  |  3 ++-
 tools/perf/util/session.c                 | 17 +++++++++++++++++
 tools/perf/util/tool.c                    |  1 +
 tools/perf/util/tool.h                    |  3 ++-
 9 files changed, 47 insertions(+), 2 deletions(-)
tools/lib/perf/include/perf/event.h +7 -0
index 09b7c643ddac..4590d62ca913 100644
@@ -151,6 +151,12 @@ struct perf_record_switch {
 	__u32			 next_prev_tid;
 };
 
+struct perf_record_callchain_deferred {
+	struct perf_event_header header;
+	__u64			 nr;
+	__u64			 ips[];
+};
+
 struct perf_record_header_attr {
 	struct perf_event_header header;
 	struct perf_event_attr	 attr;
@@ -505,6 +511,7 @@ union perf_event {
 	struct perf_record_read			read;
 	struct perf_record_throttle		throttle;
 	struct perf_record_sample		sample;
+	struct perf_record_callchain_deferred	callchain_deferred;
 	struct perf_record_bpf_event		bpf;
 	struct perf_record_ksymbol		ksymbol;
 	struct perf_record_text_poke_event	text_poke;
tools/perf/util/event.c +1 -0
index 7544a3104e21..720682fea9be 100644
@@ -58,6 +58,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_CGROUP]			= "CGROUP",
 	[PERF_RECORD_TEXT_POKE]			= "TEXT_POKE",
 	[PERF_RECORD_AUX_OUTPUT_HW_ID]		= "AUX_OUTPUT_HW_ID",
+	[PERF_RECORD_CALLCHAIN_DEFERRED]	= "CALLCHAIN_DEFERRED",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
tools/perf/util/evsel.c +15 -0
index d55482f094bf..6176c31b57ea 100644
@@ -2978,6 +2978,18 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	data->vcpu = -1;
 
+	if (event->header.type == PERF_RECORD_CALLCHAIN_DEFERRED) {
+		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
+
+		data->callchain = (struct ip_callchain *)&event->callchain_deferred.nr;
+		if (data->callchain->nr > max_callchain_nr)
+			return -EFAULT;
+
+		if (evsel->core.attr.sample_id_all)
+			perf_evsel__parse_id_sample(evsel, event, data);
+		return 0;
+	}
+
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->core.attr.sample_id_all)
 			return 0;
@@ -3108,6 +3120,9 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		if (data->callchain->nr > max_callchain_nr)
 			return -EFAULT;
 		sz = data->callchain->nr * sizeof(u64);
+		if (evsel->core.attr.defer_callchain && data->callchain->nr >= 1 &&
+		    data->callchain->ips[data->callchain->nr - 1] == PERF_CONTEXT_USER_DEFERRED)
+			data->deferred_callchain = true;
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
 	}
tools/perf/util/machine.c +1 -0
index 7ec12c207970..de6100366eee 100644
@@ -2124,6 +2124,7 @@ static int add_callchain_ip(struct thread *thread,
 				*cpumode = PERF_RECORD_MISC_KERNEL;
 				break;
 			case PERF_CONTEXT_USER:
+			case PERF_CONTEXT_USER_DEFERRED:
 				*cpumode = PERF_RECORD_MISC_USER;
 				break;
 			default:
tools/perf/util/perf_event_attr_fprintf.c +1 -0
index 66b666d9ce64..abfd9b9a718c 100644
@@ -343,6 +343,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(inherit_thread, p_unsigned);
 	PRINT_ATTRf(remove_on_exec, p_unsigned);
 	PRINT_ATTRf(sigtrap, p_unsigned);
+	PRINT_ATTRf(defer_callchain, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned, false);
 	PRINT_ATTRf(bp_type, p_unsigned);
tools/perf/util/sample.h +2 -1
index 0e96240052e9..9d6e2f14551c 100644
@@ -108,7 +108,8 @@ struct perf_sample {
 		u16 p_stage_cyc;
 		u16 retire_lat;
 	};
-	bool no_hw_idx;		/* No hw_idx collected in branch_stack */
+	bool no_hw_idx;			/* No hw_idx collected in branch_stack */
+	bool deferred_callchain;	/* Has deferred user callchains */
 	char insn[MAX_INSN];
 	void *raw_data;
 	struct ip_callchain *callchain;
tools/perf/util/session.c +17 -0
index a320672c264e..e6be01459352 100644
@@ -715,6 +715,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_CGROUP]		  = perf_event__cgroup_swap,
 	[PERF_RECORD_TEXT_POKE]		  = perf_event__text_poke_swap,
 	[PERF_RECORD_AUX_OUTPUT_HW_ID]	  = perf_event__all64_swap,
+	[PERF_RECORD_CALLCHAIN_DEFERRED]  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1118,6 +1119,19 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		sample_read__printf(sample, evsel->core.attr.read_format);
 }
 
+static void dump_deferred_callchain(struct evsel *evsel, union perf_event *event,
+				    struct perf_sample *sample)
+{
+	if (!dump_trace)
+		return;
+
+	printf("(IP, 0x%x): %d/%d: %#" PRIx64 "\n",
+	       event->header.misc, sample->pid, sample->tid, sample->ip);
+
+	if (evsel__has_callchain(evsel))
+		callchain__printf(evsel, sample);
+}
+
 static void dump_read(struct evsel *evsel, union perf_event *event)
 {
 	struct perf_record_read *read_event = &event->read;
@@ -1348,6 +1362,9 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->text_poke(tool, event, sample, machine);
 	case PERF_RECORD_AUX_OUTPUT_HW_ID:
 		return tool->aux_output_hw_id(tool, event, sample, machine);
+	case PERF_RECORD_CALLCHAIN_DEFERRED:
+		dump_deferred_callchain(evsel, event, sample);
+		return tool->callchain_deferred(tool, event, sample, evsel, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
tools/perf/util/tool.c +1 -0
index 37bd8ac63b01..e1d60abb4e41 100644
@@ -266,6 +266,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events)
 	tool->read = process_event_sample_stub;
 	tool->throttle = process_event_stub;
 	tool->unthrottle = process_event_stub;
+	tool->callchain_deferred = process_event_sample_stub;
 	tool->attr = process_event_synth_attr_stub;
 	tool->event_update = process_event_synth_event_update_stub;
 	tool->tracing_data = process_event_synth_tracing_data_stub;
tools/perf/util/tool.h +2 -1
index db1c7642b0d1..9987bbde6d5e 100644
@@ -42,7 +42,8 @@ enum show_feature_header {
 
 struct perf_tool {
 	event_sample	sample,
-			read;
+			read,
+			callchain_deferred;
 	event_op	mmap,
 			mmap2,
 			comm,
Signature · 1 line
2.47.2
#12 lore raw

Re: [PATCH v12 08/11] perf tools: Minimal CALLCHAIN_DEFERRED support

Hello Steve!

Quoted 10 lines · Steven Rostedt

From: Namhyung Kim <[email protected]>

Add a new event type for deferred callchains and a new callback for the struct perf_tool. For now it doesn't actually handle the deferred callchains but it just marks the sample if it has the PERF_CONTEXT_ USER_DEFFERED in the callchain array.

tools/lib/perf/include/perf/event.h struct perf_record_switch { · line 155

Quoted 5 lines
tools/lib/perf/include/perf/event.h +2 -0
@@ -151,6 +151,12 @@ struct perf_record_switch {
 	__u32			 next_prev_tid;
 };
 
+struct perf_record_callchain_deferred {
+	struct perf_event_header header;

At minimum the timestamp field added to perf with "[PATCH v12 07/11]
perf: Support deferred user callchains for per CPU events" needs to be added here as well:

	__u64			 timestamp;

Otherwise this and any subsequent enhancements of the perf tools do no longer work at all. But probably the timestamp field also needs to be used for some purpose?

tools/lib/perf/include/perf/event.h struct perf_record_switch { · line 159

Quoted 4 lines
tools/lib/perf/include/perf/event.h +4 -0
+	__u64			 nr;
+	__u64			 ips[];
+};
+

Thanks and regards,
Jens

Signature · 9 lines
Jens Remus
Linux on Z Development (D3303)
+49-7031-16-1128 Office
[email protected]

IBM

IBM Deutschland Research & Development GmbH; Vorsitzender des Aufsichtsrats: Wolfgang Wendt; Geschäftsführung: David Faller; Sitz der Gesellschaft: Böblingen; Registergericht: Amtsgericht Stuttgart, HRB 243294
IBM Data Privacy Statement: https://www.ibm.com/privacy/
author maintainer
#13 lore raw

Re: [PATCH v12 08/11] perf tools: Minimal CALLCHAIN_DEFERRED support

Quoted 6 lines · On Wed, 2 Jul 2025 14:23:24 +0200 Jens Remus <[email protected]> wrote:

tools/lib/perf/include/perf/event.h struct perf_record_switch { · line 155

Quoted 2 lines
tools/lib/perf/include/perf/event.h +2 -0
+struct perf_record_callchain_deferred {
+	struct perf_event_header header;  

At minimum the timestamp field added to perf with "[PATCH v12 07/11]
perf: Support deferred user callchains for per CPU events" needs to be added here as well:

Thanks for the review.

Quoted 6 lines
	__u64			 timestamp;

Otherwise this and any subsequent enhancements of the perf tools do no longer work at all. But probably the timestamp field also needs to be used for some purpose?

OK, so this may be part of the discussion about using this as a timestamp. The timestamp is the timestamp given by the deferred trace infrastructure. It holds the time that this stack trace is valid for. But that's assuming that the timestamp is the same as what perf is using.

In case of dropped events, we could have the case of:

  system_call() {
    <nmi> {
      take kernel stack trace
      ask for deferred trace.
   [EVENTS START DROPPING HERE]
    }
    Call deferred callback to record trace [ BUT IS DROPPED ]
  }
  system_call() {
    <nmi> {
      take kernel stack trace
      ask for deferred trace [ STILL DROPPING ]
    }
    [ READER CATCHES UP AND STARTS READING EVENTS AGAIN]

Call deferred callback to record trace
}

The user space tool will see that kernel stack traces of the first system call, then it will see events dropped, and then it will see the deferred user space stack trace of the second call.

If the timestamps are in sync with perf and what is passed in, then the tool will see that the kernel stack traces from the first system call are older than the timestamp of the user stack trace and know that they are not related.

Without either saving the timestamp along with the kernel stack traces, or having the timestamps in sync, user space will not know whether or not if the user space stack trace of the second system call belongs to the kernel stack traces that were recorded in the first system call.

I guess the question is, do we just not associate stack traces beyond where events are dropped? If so, we don't even need to save the timestamp.

-- Steve

Quoted 4 lines
Quoted 4 lines
tools/lib/perf/include/perf/event.h +3 -0
+	__u64			 nr;
+	__u64			 ips[];
+};
author maintainer
#14 lore raw

PATCH v12 9/11 perf record: Enable defer_callchain for user callchains

In reply to Steven Rostedt

From: Namhyung Kim <[email protected]>

And add the missing feature detection logic to clear the flag on old kernels.

  $ perf record -g -vv true
  ...
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|CALLCHAIN|PERIOD
    read_format                      ID|LOST
    disabled                         1
    inherit                          1
    mmap                             1
    comm                             1
    freq                             1
    enable_on_exec                   1
    task                             1
    sample_id_all                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
    bpf_event                        1
    defer_callchain                  1
  ------------------------------------------------------------
  sys_perf_event_open: pid 162755  cpu 0  group_fd -1  flags 0x8
  sys_perf_event_open failed, error -22
  switching off deferred callchain support
---
 tools/perf/util/evsel.c | 24 ++++++++++++++++++++++++
 tools/perf/util/evsel.h |  1 +
 2 files changed, 25 insertions(+)
tools/perf/util/evsel.c +24 -0
index 6176c31b57ea..c942983b870e 100644
@@ -1076,6 +1076,14 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 		}
 	}
 
+	if (param->record_mode == CALLCHAIN_FP && !attr->exclude_callchain_user) {
+		/*
+		 * Enable deferred callchains optimistically.  It'll be switched
+		 * off later if the kernel doesn't support it.
+		 */
+		attr->defer_callchain = 1;
+	}
+
 	if (function) {
 		pr_info("Disabling user space callchains for function trace event.\n");
 		attr->exclude_callchain_user = 1;
@@ -2124,6 +2132,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.defer_callchain)
+		evsel->core.attr.defer_callchain = 0;
 	if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit &&
 	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ))
 		evsel->core.attr.inherit = 0;
@@ -2398,6 +2408,15 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
 
 	/* Please add new feature detection here. */
 
+	attr.defer_callchain = true;
+	attr.sample_type = PERF_SAMPLE_CALLCHAIN;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.defer_callchain = true;
+	pr_debug2("switching off deferred callchain support\n");
+	attr.defer_callchain = false;
+	attr.sample_type = 0;
+
 	attr.inherit = true;
 	attr.sample_type = PERF_SAMPLE_READ;
 	if (has_attr_feature(&attr, /*flags=*/0))
@@ -2509,6 +2528,11 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
 	errno = old_errno;
 
 check:
+	if (evsel->core.attr.defer_callchain &&
+	    evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN &&
+	    perf_missing_features.defer_callchain)
+		return true;
+
 	if (evsel->core.attr.inherit &&
 	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ) &&
 	    perf_missing_features.inherit_sample_read)
tools/perf/util/evsel.h +1 -0
index 6dbc9690e0c9..a01c1de8f95f 100644
@@ -221,6 +221,7 @@ struct perf_missing_features {
 	bool branch_counters;
 	bool aux_action;
 	bool inherit_sample_read;
+	bool defer_callchain;
 };
 
 extern struct perf_missing_features perf_missing_features;
Signature · 1 line
2.47.2
author maintainer
#15 lore raw

PATCH v12 10/11 perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED

In reply to Steven Rostedt

From: Namhyung Kim <[email protected]>

Handle the deferred callchains in the script output.

  $ perf script
  perf     801 [000]    18.031793:          1 cycles:P:
          ffffffff91a14c36 __intel_pmu_enable_all.isra.0+0x56 ([kernel.kallsyms])
          ffffffff91d373e9 perf_ctx_enable+0x39 ([kernel.kallsyms])
          ffffffff91d36af7 event_function+0xd7 ([kernel.kallsyms])
          ffffffff91d34222 remote_function+0x42 ([kernel.kallsyms])
          ffffffff91c1ebe1 generic_exec_single+0x61 ([kernel.kallsyms])
          ffffffff91c1edac smp_call_function_single+0xec ([kernel.kallsyms])
          ffffffff91d37a9d event_function_call+0x10d ([kernel.kallsyms])
          ffffffff91d33557 perf_event_for_each_child+0x37 ([kernel.kallsyms])
          ffffffff91d47324 _perf_ioctl+0x204 ([kernel.kallsyms])
          ffffffff91d47c43 perf_ioctl+0x33 ([kernel.kallsyms])
          ffffffff91e2f216 __x64_sys_ioctl+0x96 ([kernel.kallsyms])
          ffffffff9265f1ae do_syscall_64+0x9e ([kernel.kallsyms])
          ffffffff92800130 entry_SYSCALL_64+0xb0 ([kernel.kallsyms])

perf 801 [000] 18.031814: DEFERRED CALLCHAIN

              7fb5fc22034b __GI___ioctl+0x3b (/usr/lib/x86_64-linux-gnu/libc.so.6)
---
 tools/perf/builtin-script.c | 89 +++++++++++++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)
tools/perf/builtin-script.c +89 -0
index 6c3bf74dd78c..a6f8209256fe 100644
@@ -2483,6 +2483,93 @@ static int process_sample_event(const struct perf_tool *tool,
 	return ret;
 }
 
+static int process_deferred_sample_event(const struct perf_tool *tool,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct evsel *evsel,
+					 struct machine *machine)
+{
+	struct perf_script *scr = container_of(tool, struct perf_script, tool);
+	struct perf_event_attr *attr = &evsel->core.attr;
+	struct evsel_script *es = evsel->priv;
+	unsigned int type = output_type(attr->type);
+	struct addr_location al;
+	FILE *fp = es->fp;
+	int ret = 0;
+
+	if (output[type].fields == 0)
+		return 0;
+
+	/* Set thread to NULL to indicate addr_al and al are not initialized */
+	addr_location__init(&al);
+
+	if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num,
+					  sample->time)) {
+		goto out_put;
+	}
+
+	if (debug_mode) {
+		if (sample->time < last_timestamp) {
+			pr_err("Samples misordered, previous: %" PRIu64
+				" this: %" PRIu64 "\n", last_timestamp,
+				sample->time);
+			nr_unordered++;
+		}
+		last_timestamp = sample->time;
+		goto out_put;
+	}
+
+	if (filter_cpu(sample))
+		goto out_put;
+
+	if (machine__resolve(machine, &al, sample) < 0) {
+		pr_err("problem processing %d event, skipping it.\n",
+		       event->header.type);
+		ret = -1;
+		goto out_put;
+	}
+
+	if (al.filtered)
+		goto out_put;
+
+	if (!show_event(sample, evsel, al.thread, &al, NULL))
+		goto out_put;
+
+	if (evswitch__discard(&scr->evswitch, evsel))
+		goto out_put;
+
+	perf_sample__fprintf_start(scr, sample, al.thread, evsel,
+				   PERF_RECORD_CALLCHAIN_DEFERRED, fp);
+	fprintf(fp, "DEFERRED CALLCHAIN");
+
+	if (PRINT_FIELD(IP)) {
+		struct callchain_cursor *cursor = NULL;
+
+		if (symbol_conf.use_callchain && sample->callchain) {
+			cursor = get_tls_callchain_cursor();
+			if (thread__resolve_callchain(al.thread, cursor, evsel,
+						      sample, NULL, NULL,
+						      scripting_max_stack)) {
+				pr_info("cannot resolve deferred callchains\n");
+				cursor = NULL;
+			}
+		}
+
+		fputc(cursor ? '\n' : ' ', fp);
+		sample__fprintf_sym(sample, &al, 0, output[type].print_ip_opts,
+				    cursor, symbol_conf.bt_stop_list, fp);
+	}
+
+	fprintf(fp, "\n");
+
+	if (verbose > 0)
+		fflush(fp);
+
+out_put:
+	addr_location__exit(&al);
+	return ret;
+}
+
 // Used when scr->per_event_dump is not set
 static struct evsel_script es_stdout;
 
@@ -4069,6 +4156,7 @@ int cmd_script(int argc, const char **argv)
 
 	perf_tool__init(&script.tool, !unsorted_dump);
 	script.tool.sample		 = process_sample_event;
+	script.tool.callchain_deferred	 = process_deferred_sample_event;
 	script.tool.mmap		 = perf_event__process_mmap;
 	script.tool.mmap2		 = perf_event__process_mmap2;
 	script.tool.comm		 = perf_event__process_comm;
@@ -4095,6 +4183,7 @@ int cmd_script(int argc, const char **argv)
 	script.tool.throttle		 = process_throttle_event;
 	script.tool.unthrottle		 = process_throttle_event;
 	script.tool.ordering_requires_timestamps = true;
+	script.tool.merge_deferred_callchains = false;
 	session = perf_session__new(&data, &script.tool);
 	if (IS_ERR(session))
 		return PTR_ERR(session);
Signature · 1 line
2.47.2
author maintainer
#16 lore raw

PATCH v12 11/11 perf tools: Merge deferred user callchains

In reply to Steven Rostedt

From: Namhyung Kim <[email protected]>

Save samples with deferred callchains in a separate list and deliver them after merging the user callchains. If users don't want to merge they can set tool->merge_deferred_callchains to false to prevent the behavior.

With previous result, now perf script will show the merged callchains.

  $ perf script
  perf     801 [000]    18.031793:          1 cycles:P:
          ffffffff91a14c36 __intel_pmu_enable_all.isra.0+0x56 ([kernel.kallsyms])
          ffffffff91d373e9 perf_ctx_enable+0x39 ([kernel.kallsyms])
          ffffffff91d36af7 event_function+0xd7 ([kernel.kallsyms])
          ffffffff91d34222 remote_function+0x42 ([kernel.kallsyms])
          ffffffff91c1ebe1 generic_exec_single+0x61 ([kernel.kallsyms])
          ffffffff91c1edac smp_call_function_single+0xec ([kernel.kallsyms])
          ffffffff91d37a9d event_function_call+0x10d ([kernel.kallsyms])
          ffffffff91d33557 perf_event_for_each_child+0x37 ([kernel.kallsyms])
          ffffffff91d47324 _perf_ioctl+0x204 ([kernel.kallsyms])
          ffffffff91d47c43 perf_ioctl+0x33 ([kernel.kallsyms])
          ffffffff91e2f216 __x64_sys_ioctl+0x96 ([kernel.kallsyms])
          ffffffff9265f1ae do_syscall_64+0x9e ([kernel.kallsyms])
          ffffffff92800130 entry_SYSCALL_64+0xb0 ([kernel.kallsyms])
              7fb5fc22034b __GI___ioctl+0x3b (/usr/lib/x86_64-linux-gnu/libc.so.6)
  ...

The old output can be get using --no-merge-callchain option. Also perf report can get the user callchain entry at the end.

  $ perf report --no-children --percent-limit=0 --stdio -q -S __intel_pmu_enable_all.isra.0
  # symbol: __intel_pmu_enable_all.isra.0
       0.00%  perf     [kernel.kallsyms]
              |
              ---__intel_pmu_enable_all.isra.0
                 perf_ctx_enable
                 event_function
                 remote_function
                 generic_exec_single
                 smp_call_function_single
                 event_function_call
                 perf_event_for_each_child
                 _perf_ioctl
                 perf_ioctl
                 __x64_sys_ioctl
                 do_syscall_64
                 entry_SYSCALL_64
                 __GI___ioctl
---
 tools/perf/Documentation/perf-script.txt |  5 ++
 tools/perf/builtin-script.c              |  5 +-
 tools/perf/util/callchain.c              | 24 +++++++++
 tools/perf/util/callchain.h              |  3 ++
 tools/perf/util/evlist.c                 |  1 +
 tools/perf/util/evlist.h                 |  1 +
 tools/perf/util/session.c                | 63 +++++++++++++++++++++++-
 tools/perf/util/tool.c                   |  1 +
 tools/perf/util/tool.h                   |  1 +
 9 files changed, 102 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-script.txt +5 -0
index 28bec7e78bc8..03d112960632 100644
@@ -527,6 +527,11 @@ include::itrace.txt[]
 	The known limitations include exception handing such as
 	setjmp/longjmp will have calls/returns not match.
 
+--merge-callchains::
+	Enable merging deferred user callchains if available.  This is the
+	default behavior.  If you want to see separate CALLCHAIN_DEFERRED
+	records for some reason, use --no-merge-callchains explicitly.
+
 :GMEXAMPLECMD: script
 :GMEXAMPLESUBCMD:
 include::guest-files.txt[]
tools/perf/builtin-script.c +4 -1
index a6f8209256fe..b50442cca540 100644
@@ -3775,6 +3775,7 @@ int cmd_script(int argc, const char **argv)
 	bool header_only = false;
 	bool script_started = false;
 	bool unsorted_dump = false;
+	bool merge_deferred_callchains = true;
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
@@ -3928,6 +3929,8 @@ int cmd_script(int argc, const char **argv)
 		    "Guest code can be found in hypervisor process"),
 	OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr,
 		    "Enable LBR callgraph stitching approach"),
+	OPT_BOOLEAN('\0', "merge-callchains", &merge_deferred_callchains,
+		    "Enable merge deferred user callchains"),
 	OPTS_EVSWITCH(&script.evswitch),
 	OPT_END()
 	};
@@ -4183,7 +4186,7 @@ int cmd_script(int argc, const char **argv)
 	script.tool.throttle		 = process_throttle_event;
 	script.tool.unthrottle		 = process_throttle_event;
 	script.tool.ordering_requires_timestamps = true;
-	script.tool.merge_deferred_callchains = false;
+	script.tool.merge_deferred_callchains = merge_deferred_callchains;
 	session = perf_session__new(&data, &script.tool);
 	if (IS_ERR(session))
 		return PTR_ERR(session);
tools/perf/util/callchain.c +24 -0
index d7b7eef740b9..6d423d92861b 100644
@@ -1828,3 +1828,27 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
 	}
 	return 0;
 }
+
+int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
+				     struct perf_sample *sample_callchain)
+{
+	u64 nr_orig = sample_orig->callchain->nr - 1;
+	u64 nr_deferred = sample_callchain->callchain->nr;
+	struct ip_callchain *callchain;
+
+	callchain = calloc(1 + nr_orig + nr_deferred, sizeof(u64));
+	if (callchain == NULL) {
+		sample_orig->deferred_callchain = false;
+		return -ENOMEM;
+	}
+
+	callchain->nr = nr_orig + nr_deferred;
+	/* copy except for the last PERF_CONTEXT_USER_DEFERRED */
+	memcpy(callchain->ips, sample_orig->callchain->ips, nr_orig * sizeof(u64));
+	/* copy deferred use callchains */
+	memcpy(&callchain->ips[nr_orig], sample_callchain->callchain->ips,
+	       nr_deferred * sizeof(u64));
+
+	sample_orig->callchain = callchain;
+	return 0;
+}
tools/perf/util/callchain.h +3 -0
index 86ed9e4d04f9..89785125ed25 100644
@@ -317,4 +317,7 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
 				    struct perf_sample *sample, int max_stack,
 				    bool symbols, callchain_iter_fn cb, void *data);
 
+int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
+				     struct perf_sample *sample_callchain);
+
 #endif	/* __PERF_CALLCHAIN_H */
tools/perf/util/evlist.c +1 -0
index dcd1130502df..1d5f50f83b31 100644
@@ -83,6 +83,7 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
 	evlist->ctl_fd.ack = -1;
 	evlist->ctl_fd.pos = -1;
 	evlist->nr_br_cntr = -1;
+	INIT_LIST_HEAD(&evlist->deferred_samples);
 }
 
 struct evlist *evlist__new(void)
tools/perf/util/evlist.h +1 -0
index 85859708393e..d2895c8be167 100644
@@ -86,6 +86,7 @@ struct evlist {
 		int	pos;	/* index at evlist core object to check signals */
 	} ctl_fd;
 	struct event_enable_timer *eet;
+	struct list_head deferred_samples;
 };
 
 struct evsel_str_handler {
tools/perf/util/session.c +62 -1

81 lines not on this page · raw message

tools/perf/util/tool.c +1 -0
index e1d60abb4e41..61fdba70b0a4 100644
@@ -245,6 +245,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events)
 	tool->cgroup_events = false;
 	tool->no_warn = false;
 	tool->show_feat_hdr = SHOW_FEAT_NO_HEADER;
+	tool->merge_deferred_callchains = true;
 
 	tool->sample = process_event_sample_stub;
 	tool->mmap = process_event_stub;
tools/perf/util/tool.h +1 -0
index 9987bbde6d5e..d06580478ab1 100644
@@ -87,6 +87,7 @@ struct perf_tool {
 	bool		cgroup_events;
 	bool		no_warn;
 	bool		dont_split_sample_group;
+	bool		merge_deferred_callchains;
 	enum show_feature_header show_feat_hdr;
 };
 
Signature · 1 line
2.47.2