* [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
@ 2026-11-20 14:45 ` Sebastian Andrzej Siewior
0 siblings, 0 replies; 7+ messages in thread
From: Sebastian Andrzej Siewior @ 2026-11-20 14:45 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel, linux-rt-devel, linux-perf-users,
loongarch
Cc: Mark Rutland, Ian Rogers, Peter Zijlstra, Catalin Marinas,
Oleg Nesterov, WANG Xuerui, Will Deacon, Huacai Chen,
Russell King, Alexander Shishkin, Ingo Molnar, Waiman Long,
Clark Williams, Luis Claudio R. Goncalves, James Clark,
Steven Rostedt, Arnaldo Carvalho de Melo, Namhyung Kim,
Chris Zankel, Max Filippov, Adrian Hunter, Jiri Olsa,
Ada Couprie Diaz
Waiman, Luis, Ada reported that HW breakpoints on ARM64 trigger
"sleeping while atomic" warnings on PREEMPT_RT. The hardware event is
delivered with disabled interrupts and perf intrastrucure expects
disabled interrupts while the overflow callback is invoked.
The callback then sends a SIGTRAP signal for which it acquires
sighand_struct::siglock, a spinlock_t which becomes a sleeping lock and
must not be acquired in atomic context.
Delay the event callback until the return to userland.
Add perf_hwbp_notify(), a generic perf callback which delayes the
actual callback invocation to task_work_add() callback. This callback
invokes the architecture defined callback perf_arch_hwbp_send_sig().
This requires struct callback_head and the functions require
ARCH_NEED_PERF_HW_NOTIFY to be defined.
This was reported against ARM64. ARM, LongARCH and Xtensa follow the
same pattern are also converted. Xtensa is the only not supporting
PREEMPT_RT but now we have all architectures using the same pattern.
Fixes: d8fccd9ca5f90 ("arm64: Allow to enable PREEMPT_RT.")
Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Reported-by: Waiman Long <longman@redhat.com>
Closes: https://lore.kernel.org/all/aho0eqjMESuHxECr@redhat.com/
Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v4…v5: https://lore.kernel.org/all/20261012090431.TF3iVDsk@linutronix.de/
- Collect tags
v3…v4: https://lore.kernel.org/all/20261001143516.Ew8C97WS@linutronix.de/
- Add fixes tag
- Rename the functions as suggested by Ada to use the pattern that perf
uses in other places:
- perf_arch_hwbp_notify() -> perf_hwbp_notify() (generic)
- arch_hwbp_send_sig() -> perf_arch_hwbp_send_sig() (arch specific)
- perf_arch_hwbp_send_sig() -> perf_hwbp_send_sig() (generic)
- Rename ARCH_NEED_PERF_HW_NOTIF -> ARCH_NEED_PERF_HW_NOTIFY
v2…v3: https://lore.kernel.org/all/20260814085118.OPEA_Ssn@linutronix.de/
- Add Xtensa for completion
- sashiko complains and wants TWA_SIGNAL instead TWA_RESUME. His
argument is that a syscall will trap via get_user() and loop forever
instead making progress. This is wrong IMHO. ARM64 will single step
over the watchpoint and continue execution. The only downside is that
userland will get notified after the syscall completed. So my theory.
Using TWA_SIGNAL is worse: Assume we have a watchpoint on UADDR and
are in a futex() syscall. The get_user() invocation will trigger the
exception, the debug handler will step over and queue a signal. The
futex code will notice this and return ERESTARTNOINTR. A signal will
be sent, the syscall restarts, traps onto UADDR again, the loop
continues. But this should be case now, too…
Now that I look into arch_build_bp_info() and do actual testing I must
say arm64 does not support mixed breakpoints. This means there is no
breakpoint in kernel on a userland address. \o/
v1…v2: https://lore.kernel.org/all/20260713144939.FuCj9yvZ@linutronix.de/
- sashiko complained that a memory breakpoint might trigger several
times before a signal is sent if the syscall touches the memory (via
get_user()) more than once before returning back. This would lead to
list corruption in task_work_add(). To handle this, there is now a
variable which is set via xchg before task_work_add() and cleared
after the signal has been sent.
arch/arm/include/asm/hw_breakpoint.h | 1 +
arch/arm/kernel/ptrace.c | 7 ++----
arch/arm64/include/asm/hw_breakpoint.h | 1 +
arch/arm64/kernel/ptrace.c | 6 ++---
arch/loongarch/include/asm/hw_breakpoint.h | 1 +
arch/loongarch/kernel/ptrace.c | 6 ++---
arch/xtensa/include/asm/hw_breakpoint.h | 1 +
arch/xtensa/kernel/ptrace.c | 7 ++----
include/linux/hw_breakpoint.h | 3 +++
include/linux/perf_event.h | 4 ++++
kernel/events/core.c | 26 ++++++++++++++++++++++
11 files changed, 45 insertions(+), 18 deletions(-)
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index e7f9961c53b2d..fa7fb2b2a392a 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -7,6 +7,7 @@
struct task_struct;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
struct arch_hw_breakpoint_ctrl {
u32 __reserved : 9,
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ed7a2a87a6707..db4b28c6e15a4 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -347,9 +347,7 @@ static long ptrace_hbp_idx_to_num(int idx)
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
long num;
@@ -424,8 +422,7 @@ static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
attr.bp_type = type;
attr.disabled = 1;
- return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL,
- tsk);
+ return register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
}
static int ptrace_gethbpregs(struct task_struct *tsk, long num,
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index bd81cf17744af..0bc75f42b0da6 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -124,6 +124,7 @@ extern void hw_breakpoint_pmu_read(struct perf_event *bp);
extern int hw_breakpoint_slots(int type);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
extern void hw_breakpoint_thread_switch(struct task_struct *next);
extern void ptrace_hw_copy_thread(struct task_struct *task);
#else
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6a0b3a9b6125e..7c3df2007c108 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -168,9 +168,7 @@ void ptrace_disable(struct task_struct *child)
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
const char *desc = "Hardware breakpoint trap (ptrace)";
@@ -312,7 +310,7 @@ static struct perf_event *ptrace_hbp_create(unsigned int note_type,
attr.bp_type = type;
attr.disabled = 1;
- bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk);
+ bp = register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
if (IS_ERR(bp))
return bp;
diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h
index f4478936787d6..3921c461dc2d9 100644
--- a/arch/loongarch/include/asm/hw_breakpoint.h
+++ b/arch/loongarch/include/asm/hw_breakpoint.h
@@ -120,6 +120,7 @@ bool breakpoint_handler(struct pt_regs *regs);
bool watchpoint_handler(struct pt_regs *regs);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
extern void ptrace_hw_copy_thread(struct task_struct *task);
extern void hw_breakpoint_thread_switch(struct task_struct *prev, struct task_struct *next);
#else
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index be38430f7e280..27e7e64591592 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -384,9 +384,7 @@ static int lbt_set(struct task_struct *target,
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
int i;
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
@@ -479,7 +477,7 @@ static struct perf_event *ptrace_hbp_create(unsigned int note_type,
attr.bp_type = type;
attr.disabled = 1;
- bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk);
+ bp = register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
if (IS_ERR(bp))
return bp;
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index 9ec86f440a48e..44ea340c88742 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -12,6 +12,7 @@
#define __ASM_XTENSA_HW_BREAKPOINT_H
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
#include <linux/kdebug.h>
#include <linux/types.h>
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 364e4fdabb00d..c9f583d650de2 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -361,9 +361,7 @@ static int ptrace_pokeusr(struct task_struct *child, long regno, long val)
}
#ifdef CONFIG_HAVE_HW_BREAKPOINT
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
int i;
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
@@ -395,8 +393,7 @@ static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
attr.bp_type = type;
attr.disabled = 1;
- return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL,
- tsk);
+ return register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
}
/*
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index db199d653dd1a..91e8d80220c54 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -85,6 +85,9 @@ extern int register_perf_hw_breakpoint(struct perf_event *bp);
extern void unregister_hw_breakpoint(struct perf_event *bp);
extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
extern bool hw_breakpoint_is_used(void);
+extern void perf_arch_hwbp_send_sig(struct perf_event *bp);
+extern void perf_hwbp_notify(struct perf_event *bp, struct perf_sample_data *data,
+ struct pt_regs *regs);
extern int dbg_reserve_bp_slot(struct perf_event *bp);
extern int dbg_release_bp_slot(struct perf_event *bp);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e1e11500df097..f4f88e3ce586a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -215,6 +215,10 @@ struct hw_perf_event {
/* Last sync'ed generation of filters */
unsigned long addr_filters_gen;
+#ifdef ARCH_NEED_PERF_HW_NOTIFY
+ struct callback_head arch_hw_notif;
+ int arch_hw_notif_busy;
+#endif
/*
* hw_perf_event::state flags; used to track the PERF_EF_* state.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e870f12c3ad81..ee6a5ec48e7c4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -13485,6 +13485,28 @@ static void account_event(struct perf_event *event)
account_pmu_sb_event(event);
}
+#ifdef ARCH_NEED_PERF_HW_NOTIFY
+static void perf_hwbp_send_sig(struct callback_head *head)
+{
+ struct perf_event *bp;
+
+ bp = container_of(head, struct perf_event, hw.arch_hw_notif);
+ perf_arch_hwbp_send_sig(bp);
+ xchg_relaxed(&bp->hw.arch_hw_notif_busy, 0);
+ put_event(bp);
+}
+
+void perf_hwbp_notify(struct perf_event *bp, struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ if (WARN_ON_ONCE(!atomic_long_inc_not_zero(&bp->refcount)))
+ return;
+ if (xchg_relaxed(&bp->hw.arch_hw_notif_busy, 1) ||
+ WARN_ON_ONCE(task_work_add(current, &bp->hw.arch_hw_notif, TWA_RESUME)))
+ put_event(bp);
+}
+#endif
+
/*
* Allocate and initialize an event structure
*/
@@ -13590,6 +13612,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
if (overflow_handler) {
+#ifdef ARCH_NEED_PERF_HW_NOTIFY
+ if (overflow_handler == perf_hwbp_notify)
+ init_task_work(&event->hw.arch_hw_notif, perf_hwbp_send_sig);
+#endif
event->overflow_handler = overflow_handler;
event->overflow_handler_context = context;
} else if (is_write_backward(event)){
--
2.55.0
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
@ 2026-11-20 14:45 ` Sebastian Andrzej Siewior
0 siblings, 0 replies; 7+ messages in thread
From: Sebastian Andrzej Siewior @ 2026-11-20 14:45 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel, linux-rt-devel, linux-perf-users,
loongarch
Cc: Mark Rutland, Ian Rogers, Peter Zijlstra, Catalin Marinas,
Adrian Hunter, Max Filippov, WANG Xuerui, Will Deacon,
Huacai Chen, Russell King, Alexander Shishkin, Ingo Molnar,
Waiman Long, Clark Williams, Luis Claudio R. Goncalves,
James Clark, Steven Rostedt, Arnaldo Carvalho de Melo,
Namhyung Kim, Chris Zankel, Oleg Nesterov, Jiri Olsa
Waiman, Luis, Ada reported that HW breakpoints on ARM64 trigger
"sleeping while atomic" warnings on PREEMPT_RT. The hardware event is
delivered with disabled interrupts and perf intrastrucure expects
disabled interrupts while the overflow callback is invoked.
The callback then sends a SIGTRAP signal for which it acquires
sighand_struct::siglock, a spinlock_t which becomes a sleeping lock and
must not be acquired in atomic context.
Delay the event callback until the return to userland.
Add perf_hwbp_notify(), a generic perf callback which delayes the
actual callback invocation to task_work_add() callback. This callback
invokes the architecture defined callback perf_arch_hwbp_send_sig().
This requires struct callback_head and the functions require
ARCH_NEED_PERF_HW_NOTIFY to be defined.
This was reported against ARM64. ARM, LongARCH and Xtensa follow the
same pattern are also converted. Xtensa is the only not supporting
PREEMPT_RT but now we have all architectures using the same pattern.
Fixes: d8fccd9ca5f90 ("arm64: Allow to enable PREEMPT_RT.")
Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Reported-by: Waiman Long <longman@redhat.com>
Closes: https://lore.kernel.org/all/aho0eqjMESuHxECr@redhat.com/
Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v4…v5: https://lore.kernel.org/all/20261012090431.TF3iVDsk@linutronix.de/
- Collect tags
v3…v4: https://lore.kernel.org/all/20261001143516.Ew8C97WS@linutronix.de/
- Add fixes tag
- Rename the functions as suggested by Ada to use the pattern that perf
uses in other places:
- perf_arch_hwbp_notify() -> perf_hwbp_notify() (generic)
- arch_hwbp_send_sig() -> perf_arch_hwbp_send_sig() (arch specific)
- perf_arch_hwbp_send_sig() -> perf_hwbp_send_sig() (generic)
- Rename ARCH_NEED_PERF_HW_NOTIF -> ARCH_NEED_PERF_HW_NOTIFY
v2…v3: https://lore.kernel.org/all/20260814085118.OPEA_Ssn@linutronix.de/
- Add Xtensa for completion
- sashiko complains and wants TWA_SIGNAL instead TWA_RESUME. His
argument is that a syscall will trap via get_user() and loop forever
instead making progress. This is wrong IMHO. ARM64 will single step
over the watchpoint and continue execution. The only downside is that
userland will get notified after the syscall completed. So my theory.
Using TWA_SIGNAL is worse: Assume we have a watchpoint on UADDR and
are in a futex() syscall. The get_user() invocation will trigger the
exception, the debug handler will step over and queue a signal. The
futex code will notice this and return ERESTARTNOINTR. A signal will
be sent, the syscall restarts, traps onto UADDR again, the loop
continues. But this should be case now, too…
Now that I look into arch_build_bp_info() and do actual testing I must
say arm64 does not support mixed breakpoints. This means there is no
breakpoint in kernel on a userland address. \o/
v1…v2: https://lore.kernel.org/all/20260713144939.FuCj9yvZ@linutronix.de/
- sashiko complained that a memory breakpoint might trigger several
times before a signal is sent if the syscall touches the memory (via
get_user()) more than once before returning back. This would lead to
list corruption in task_work_add(). To handle this, there is now a
variable which is set via xchg before task_work_add() and cleared
after the signal has been sent.
arch/arm/include/asm/hw_breakpoint.h | 1 +
arch/arm/kernel/ptrace.c | 7 ++----
arch/arm64/include/asm/hw_breakpoint.h | 1 +
arch/arm64/kernel/ptrace.c | 6 ++---
arch/loongarch/include/asm/hw_breakpoint.h | 1 +
arch/loongarch/kernel/ptrace.c | 6 ++---
arch/xtensa/include/asm/hw_breakpoint.h | 1 +
arch/xtensa/kernel/ptrace.c | 7 ++----
include/linux/hw_breakpoint.h | 3 +++
include/linux/perf_event.h | 4 ++++
kernel/events/core.c | 26 ++++++++++++++++++++++
11 files changed, 45 insertions(+), 18 deletions(-)
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index e7f9961c53b2d..fa7fb2b2a392a 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -7,6 +7,7 @@
struct task_struct;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
struct arch_hw_breakpoint_ctrl {
u32 __reserved : 9,
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ed7a2a87a6707..db4b28c6e15a4 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -347,9 +347,7 @@ static long ptrace_hbp_idx_to_num(int idx)
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
long num;
@@ -424,8 +422,7 @@ static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
attr.bp_type = type;
attr.disabled = 1;
- return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL,
- tsk);
+ return register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
}
static int ptrace_gethbpregs(struct task_struct *tsk, long num,
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index bd81cf17744af..0bc75f42b0da6 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -124,6 +124,7 @@ extern void hw_breakpoint_pmu_read(struct perf_event *bp);
extern int hw_breakpoint_slots(int type);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
extern void hw_breakpoint_thread_switch(struct task_struct *next);
extern void ptrace_hw_copy_thread(struct task_struct *task);
#else
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6a0b3a9b6125e..7c3df2007c108 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -168,9 +168,7 @@ void ptrace_disable(struct task_struct *child)
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
const char *desc = "Hardware breakpoint trap (ptrace)";
@@ -312,7 +310,7 @@ static struct perf_event *ptrace_hbp_create(unsigned int note_type,
attr.bp_type = type;
attr.disabled = 1;
- bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk);
+ bp = register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
if (IS_ERR(bp))
return bp;
diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h
index f4478936787d6..3921c461dc2d9 100644
--- a/arch/loongarch/include/asm/hw_breakpoint.h
+++ b/arch/loongarch/include/asm/hw_breakpoint.h
@@ -120,6 +120,7 @@ bool breakpoint_handler(struct pt_regs *regs);
bool watchpoint_handler(struct pt_regs *regs);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
extern void ptrace_hw_copy_thread(struct task_struct *task);
extern void hw_breakpoint_thread_switch(struct task_struct *prev, struct task_struct *next);
#else
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index be38430f7e280..27e7e64591592 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -384,9 +384,7 @@ static int lbt_set(struct task_struct *target,
/*
* Handle hitting a HW-breakpoint.
*/
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
int i;
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
@@ -479,7 +477,7 @@ static struct perf_event *ptrace_hbp_create(unsigned int note_type,
attr.bp_type = type;
attr.disabled = 1;
- bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk);
+ bp = register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
if (IS_ERR(bp))
return bp;
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index 9ec86f440a48e..44ea340c88742 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -12,6 +12,7 @@
#define __ASM_XTENSA_HW_BREAKPOINT_H
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define ARCH_NEED_PERF_HW_NOTIFY
#include <linux/kdebug.h>
#include <linux/types.h>
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 364e4fdabb00d..c9f583d650de2 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -361,9 +361,7 @@ static int ptrace_pokeusr(struct task_struct *child, long regno, long val)
}
#ifdef CONFIG_HAVE_HW_BREAKPOINT
-static void ptrace_hbptriggered(struct perf_event *bp,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_arch_hwbp_send_sig(struct perf_event *bp)
{
int i;
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
@@ -395,8 +393,7 @@ static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
attr.bp_type = type;
attr.disabled = 1;
- return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL,
- tsk);
+ return register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
}
/*
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index db199d653dd1a..91e8d80220c54 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -85,6 +85,9 @@ extern int register_perf_hw_breakpoint(struct perf_event *bp);
extern void unregister_hw_breakpoint(struct perf_event *bp);
extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
extern bool hw_breakpoint_is_used(void);
+extern void perf_arch_hwbp_send_sig(struct perf_event *bp);
+extern void perf_hwbp_notify(struct perf_event *bp, struct perf_sample_data *data,
+ struct pt_regs *regs);
extern int dbg_reserve_bp_slot(struct perf_event *bp);
extern int dbg_release_bp_slot(struct perf_event *bp);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e1e11500df097..f4f88e3ce586a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -215,6 +215,10 @@ struct hw_perf_event {
/* Last sync'ed generation of filters */
unsigned long addr_filters_gen;
+#ifdef ARCH_NEED_PERF_HW_NOTIFY
+ struct callback_head arch_hw_notif;
+ int arch_hw_notif_busy;
+#endif
/*
* hw_perf_event::state flags; used to track the PERF_EF_* state.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e870f12c3ad81..ee6a5ec48e7c4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -13485,6 +13485,28 @@ static void account_event(struct perf_event *event)
account_pmu_sb_event(event);
}
+#ifdef ARCH_NEED_PERF_HW_NOTIFY
+static void perf_hwbp_send_sig(struct callback_head *head)
+{
+ struct perf_event *bp;
+
+ bp = container_of(head, struct perf_event, hw.arch_hw_notif);
+ perf_arch_hwbp_send_sig(bp);
+ xchg_relaxed(&bp->hw.arch_hw_notif_busy, 0);
+ put_event(bp);
+}
+
+void perf_hwbp_notify(struct perf_event *bp, struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ if (WARN_ON_ONCE(!atomic_long_inc_not_zero(&bp->refcount)))
+ return;
+ if (xchg_relaxed(&bp->hw.arch_hw_notif_busy, 1) ||
+ WARN_ON_ONCE(task_work_add(current, &bp->hw.arch_hw_notif, TWA_RESUME)))
+ put_event(bp);
+}
+#endif
+
/*
* Allocate and initialize an event structure
*/
@@ -13590,6 +13612,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
if (overflow_handler) {
+#ifdef ARCH_NEED_PERF_HW_NOTIFY
+ if (overflow_handler == perf_hwbp_notify)
+ init_task_work(&event->hw.arch_hw_notif, perf_hwbp_send_sig);
+#endif
event->overflow_handler = overflow_handler;
event->overflow_handler_context = context;
} else if (is_write_backward(event)){
--
2.55.0
^ permalink raw reply related [flat|nested] 7+ messages in thread* Re: [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
2026-11-20 14:45 ` Sebastian Andrzej Siewior
@ 2026-11-20 15:03 ` Peter Zijlstra
-1 siblings, 0 replies; 7+ messages in thread
From: Peter Zijlstra @ 2026-11-20 15:03 UTC (permalink / raw)
To: Sebastian Andrzej Siewior
Cc: linux-arm-kernel, linux-kernel, linux-rt-devel, linux-perf-users,
loongarch, Mark Rutland, Ian Rogers, Catalin Marinas,
Oleg Nesterov, WANG Xuerui, Will Deacon, Huacai Chen,
Russell King, Alexander Shishkin, Ingo Molnar, Waiman Long,
Clark Williams, Luis Claudio R. Goncalves, James Clark,
Steven Rostedt, Arnaldo Carvalho de Melo, Namhyung Kim,
Chris Zankel, Max Filippov, Adrian Hunter, Jiri Olsa,
Ada Couprie Diaz
On Fri, Nov 20, 2026 at 03:45:53PM +0100, Sebastian Andrzej Siewior wrote:
> Waiman, Luis, Ada reported that HW breakpoints on ARM64 trigger
> "sleeping while atomic" warnings on PREEMPT_RT. The hardware event is
> delivered with disabled interrupts and perf intrastrucure expects
> disabled interrupts while the overflow callback is invoked.
>
> The callback then sends a SIGTRAP signal for which it acquires
> sighand_struct::siglock, a spinlock_t which becomes a sleeping lock and
> must not be acquired in atomic context.
>
> Delay the event callback until the return to userland.
> Add perf_hwbp_notify(), a generic perf callback which delayes the
> actual callback invocation to task_work_add() callback. This callback
> invokes the architecture defined callback perf_arch_hwbp_send_sig().
> This requires struct callback_head and the functions require
> ARCH_NEED_PERF_HW_NOTIFY to be defined.
>
> This was reported against ARM64. ARM, LongARCH and Xtensa follow the
> same pattern are also converted. Xtensa is the only not supporting
> PREEMPT_RT but now we have all architectures using the same pattern.
>
> Fixes: d8fccd9ca5f90 ("arm64: Allow to enable PREEMPT_RT.")
> Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
> Reported-by: Waiman Long <longman@redhat.com>
> Closes: https://lore.kernel.org/all/aho0eqjMESuHxECr@redhat.com/
> Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
Mark; you was going to stare at this :-)
I'm thinking the archs are doing it wrong and should be sending the
signal elsewhere.
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
@ 2026-11-20 15:03 ` Peter Zijlstra
0 siblings, 0 replies; 7+ messages in thread
From: Peter Zijlstra @ 2026-11-20 15:03 UTC (permalink / raw)
To: Sebastian Andrzej Siewior
Cc: Mark Rutland, Ian Rogers, Alexander Shishkin, Catalin Marinas,
linux-rt-devel, Oleg Nesterov, Max Filippov, WANG Xuerui,
Will Deacon, Huacai Chen, Russell King, Ingo Molnar, Waiman Long,
Clark Williams, Luis Claudio R. Goncalves, James Clark,
Arnaldo Carvalho de Melo, Steven Rostedt, loongarch, Namhyung Kim,
Adrian Hunter, linux-arm-kernel, Chris Zankel, linux-kernel,
linux-perf-users, Jiri Olsa
On Fri, Nov 20, 2026 at 03:45:53PM +0100, Sebastian Andrzej Siewior wrote:
> Waiman, Luis, Ada reported that HW breakpoints on ARM64 trigger
> "sleeping while atomic" warnings on PREEMPT_RT. The hardware event is
> delivered with disabled interrupts and perf intrastrucure expects
> disabled interrupts while the overflow callback is invoked.
>
> The callback then sends a SIGTRAP signal for which it acquires
> sighand_struct::siglock, a spinlock_t which becomes a sleeping lock and
> must not be acquired in atomic context.
>
> Delay the event callback until the return to userland.
> Add perf_hwbp_notify(), a generic perf callback which delayes the
> actual callback invocation to task_work_add() callback. This callback
> invokes the architecture defined callback perf_arch_hwbp_send_sig().
> This requires struct callback_head and the functions require
> ARCH_NEED_PERF_HW_NOTIFY to be defined.
>
> This was reported against ARM64. ARM, LongARCH and Xtensa follow the
> same pattern are also converted. Xtensa is the only not supporting
> PREEMPT_RT but now we have all architectures using the same pattern.
>
> Fixes: d8fccd9ca5f90 ("arm64: Allow to enable PREEMPT_RT.")
> Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
> Reported-by: Waiman Long <longman@redhat.com>
> Closes: https://lore.kernel.org/all/aho0eqjMESuHxECr@redhat.com/
> Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
Mark; you was going to stare at this :-)
I'm thinking the archs are doing it wrong and should be sending the
signal elsewhere.
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
2026-11-20 15:03 ` Peter Zijlstra
@ 2026-11-20 15:58 ` Peter Zijlstra
-1 siblings, 0 replies; 7+ messages in thread
From: Peter Zijlstra @ 2026-11-20 15:58 UTC (permalink / raw)
To: Sebastian Andrzej Siewior
Cc: linux-arm-kernel, linux-kernel, linux-rt-devel, linux-perf-users,
loongarch, Mark Rutland, Ian Rogers, Catalin Marinas,
Oleg Nesterov, WANG Xuerui, Will Deacon, Huacai Chen,
Russell King, Alexander Shishkin, Ingo Molnar, Waiman Long,
Clark Williams, Luis Claudio R. Goncalves, James Clark,
Steven Rostedt, Arnaldo Carvalho de Melo, Namhyung Kim,
Chris Zankel, Max Filippov, Adrian Hunter, Jiri Olsa,
Ada Couprie Diaz
On Fri, Nov 20, 2026 at 04:03:20PM +0100, Peter Zijlstra wrote:
> On Fri, Nov 20, 2026 at 03:45:53PM +0100, Sebastian Andrzej Siewior wrote:
> > Waiman, Luis, Ada reported that HW breakpoints on ARM64 trigger
> > "sleeping while atomic" warnings on PREEMPT_RT. The hardware event is
> > delivered with disabled interrupts and perf intrastrucure expects
> > disabled interrupts while the overflow callback is invoked.
> >
> > The callback then sends a SIGTRAP signal for which it acquires
> > sighand_struct::siglock, a spinlock_t which becomes a sleeping lock and
> > must not be acquired in atomic context.
> >
> > Delay the event callback until the return to userland.
> > Add perf_hwbp_notify(), a generic perf callback which delayes the
> > actual callback invocation to task_work_add() callback. This callback
> > invokes the architecture defined callback perf_arch_hwbp_send_sig().
> > This requires struct callback_head and the functions require
> > ARCH_NEED_PERF_HW_NOTIFY to be defined.
> >
> > This was reported against ARM64. ARM, LongARCH and Xtensa follow the
> > same pattern are also converted. Xtensa is the only not supporting
> > PREEMPT_RT but now we have all architectures using the same pattern.
> >
> > Fixes: d8fccd9ca5f90 ("arm64: Allow to enable PREEMPT_RT.")
> > Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
> > Reported-by: Waiman Long <longman@redhat.com>
> > Closes: https://lore.kernel.org/all/aho0eqjMESuHxECr@redhat.com/
> > Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> > Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> > Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
> > Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> > ---
>
> Mark; you was going to stare at this :-)
>
> I'm thinking the archs are doing it wrong and should be sending the
> signal elsewhere.
Notably, I'm thinking arm64 should be sending the signal from either
do_watchpoint()/do_breakpoint(), after it has done perf_bp_event(),
or from el0_watchpt()/el0_breakpt().
Perf overflow handlers are not the place to send signals from.
That is very much what x86 also does, we send the signal from
exc_debug_user(); which is roughly equivalent to the above mentioned
functions.
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
@ 2026-11-20 15:58 ` Peter Zijlstra
0 siblings, 0 replies; 7+ messages in thread
From: Peter Zijlstra @ 2026-11-20 15:58 UTC (permalink / raw)
To: Sebastian Andrzej Siewior
Cc: Mark Rutland, Ian Rogers, Alexander Shishkin, Catalin Marinas,
linux-rt-devel, Oleg Nesterov, Max Filippov, WANG Xuerui,
Will Deacon, Huacai Chen, Russell King, Ingo Molnar, Waiman Long,
Clark Williams, Luis Claudio R. Goncalves, James Clark,
Arnaldo Carvalho de Melo, Steven Rostedt, loongarch, Namhyung Kim,
Adrian Hunter, linux-arm-kernel, Chris Zankel, linux-kernel,
linux-perf-users, Jiri Olsa
On Fri, Nov 20, 2026 at 04:03:20PM +0100, Peter Zijlstra wrote:
> On Fri, Nov 20, 2026 at 03:45:53PM +0100, Sebastian Andrzej Siewior wrote:
> > Waiman, Luis, Ada reported that HW breakpoints on ARM64 trigger
> > "sleeping while atomic" warnings on PREEMPT_RT. The hardware event is
> > delivered with disabled interrupts and perf intrastrucure expects
> > disabled interrupts while the overflow callback is invoked.
> >
> > The callback then sends a SIGTRAP signal for which it acquires
> > sighand_struct::siglock, a spinlock_t which becomes a sleeping lock and
> > must not be acquired in atomic context.
> >
> > Delay the event callback until the return to userland.
> > Add perf_hwbp_notify(), a generic perf callback which delayes the
> > actual callback invocation to task_work_add() callback. This callback
> > invokes the architecture defined callback perf_arch_hwbp_send_sig().
> > This requires struct callback_head and the functions require
> > ARCH_NEED_PERF_HW_NOTIFY to be defined.
> >
> > This was reported against ARM64. ARM, LongARCH and Xtensa follow the
> > same pattern are also converted. Xtensa is the only not supporting
> > PREEMPT_RT but now we have all architectures using the same pattern.
> >
> > Fixes: d8fccd9ca5f90 ("arm64: Allow to enable PREEMPT_RT.")
> > Reported-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
> > Reported-by: Waiman Long <longman@redhat.com>
> > Closes: https://lore.kernel.org/all/aho0eqjMESuHxECr@redhat.com/
> > Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> > Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
> > Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
> > Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> > ---
>
> Mark; you was going to stare at this :-)
>
> I'm thinking the archs are doing it wrong and should be sending the
> signal elsewhere.
Notably, I'm thinking arm64 should be sending the signal from either
do_watchpoint()/do_breakpoint(), after it has done perf_bp_event(),
or from el0_watchpt()/el0_breakpt().
Perf overflow handlers are not the place to send signals from.
That is very much what x86 also does, we send the signal from
exc_debug_user(); which is roughly equivalent to the above mentioned
functions.
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
2026-11-20 14:45 ` Sebastian Andrzej Siewior
(?)
(?)
@ 2026-11-20 15:15 ` sashiko-bot
-1 siblings, 0 replies; 7+ messages in thread
From: sashiko-bot @ 2026-11-20 15:15 UTC (permalink / raw)
To: Sebastian Andrzej Siewior, linux-rt-devel, linux-perf-users; +Cc: linux-kernel
Thank you for your contribution! Sashiko AI review found 1 potential
issue to consider:
- [High] loongarch: ptrace: do_watch() forces SIGTRAP before
perf_arch_hwbp_send_sig()
--
commit e42e3194215f3def1d0ba2e055fc294e66e5d8ac
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work()
This commit defers ptrace hardware breakpoint signal notifications on ARM,
ARM64, LoongArch, and Xtensa to task_work via perf_hwbp_notify() so that
sighand->siglock is not acquired with interrupts disabled on PREEMPT_RT.
> diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
> index be38430f7e280..27e7e64591592 100644
> --- a/arch/loongarch/kernel/ptrace.c
> +++ b/arch/loongarch/kernel/ptrace.c
> @@ -384,9 +384,7 @@ static int lbt_set(struct task_struct *target,
> /*
> * Handle hitting a HW-breakpoint.
> */
> -static void ptrace_hbptriggered(struct perf_event *bp,
> - struct perf_sample_data *data,
> - struct pt_regs *regs)
> +void perf_arch_hwbp_send_sig(struct perf_event *bp)
> {
> int i;
> struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
> @@ -479,7 +477,7 @@ static struct perf_event *ptrace_hbp_create(unsigned int note_type,
> attr.bp_type = type;
> attr.disabled = 1;
>
> - bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk);
> + bp = register_user_hw_breakpoint(&attr, perf_hwbp_notify, NULL, tsk);
> if (IS_ERR(bp))
> return bp;
[Severity: High]
Does deferring force_sig_ptrace_errno_trap() to task_work cause do_watch()
to queue a generic SI_KERNEL SIGTRAP first and drop the TRAP_HWBKPT
siginfo?
On LoongArch, do_watch() runs with interrupts disabled and forces SIGTRAP
before returning through irqentry_exit():
arch/loongarch/kernel/traps.c:do_watch() {
...
bool need_sigtrap = !!current->ptrace;
...
if (test_tsk_thread_flag(current, TIF_SINGLESTEP)) {
...
} else {
need_sigtrap |= breakpoint_handler(regs);
need_sigtrap |= watchpoint_handler(regs);
}
if (need_sigtrap)
force_sig(SIGTRAP);
out:
#endif
irqentry_exit(regs, state);
}
Previously, breakpoint_handler() and watchpoint_handler() ran
ptrace_hbptriggered() synchronously, queueing SIGTRAP with TRAP_HWBKPT, the
slot index in si_errno, and the breakpoint address in si_addr before
do_watch() reached force_sig(SIGTRAP), which __send_signal_locked() then
ignored via legacy_queue().
With perf_arch_hwbp_send_sig() deferred to TWA_RESUME, force_sig(SIGTRAP)
in do_watch() now runs first while interrupts are still disabled. That
queues a generic SI_KERNEL SIGTRAP, causing __send_signal_locked() to drop
the subsequent TRAP_HWBKPT siginfo from perf_arch_hwbp_send_sig(), and
still acquires sighand->siglock in atomic context on PREEMPT_RT.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20261120144553.TjgAd_G6@linutronix.de?part=1
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2026-11-20 15:58 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-20 14:45 [PATCH v5] ARM, ARM64, LONGARCH, XTENSA: Delay HW BP notification to task_work() Sebastian Andrzej Siewior
2026-11-20 14:45 ` Sebastian Andrzej Siewior
2026-11-20 15:03 ` Peter Zijlstra
2026-11-20 15:03 ` Peter Zijlstra
2026-11-20 15:58 ` Peter Zijlstra
2026-11-20 15:58 ` Peter Zijlstra
2026-11-20 15:15 ` sashiko-bot
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.