* [PATCH v6 7/7] locking: Add contended_release tracepoint to qrwlock
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
Extend the contended_release tracepoint to queued rwlocks, using the
same out-of-line traced unlock approach as queued spinlocks.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
---
include/asm-generic/qrwlock.h | 22 ++++++++++++++++++++++
kernel/locking/qrwlock.c | 16 ++++++++++++++++
2 files changed, 38 insertions(+)
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 4b627bafba8b..274c19006125 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -14,6 +14,7 @@
#define __ASM_GENERIC_QRWLOCK_H
#include <linux/atomic.h>
+#include <linux/tracepoint-defs.h>
#include <asm/barrier.h>
#include <asm/processor.h>
@@ -35,6 +36,10 @@
*/
extern void queued_read_lock_slowpath(struct qrwlock *lock);
extern void queued_write_lock_slowpath(struct qrwlock *lock);
+extern void queued_read_unlock_traced(struct qrwlock *lock);
+extern void queued_write_unlock_traced(struct qrwlock *lock);
+
+DECLARE_TRACEPOINT(contended_release);
/**
* queued_read_trylock - try to acquire read lock of a queued rwlock
@@ -115,6 +120,17 @@ static __always_inline void __queued_read_unlock(struct qrwlock *lock)
*/
static inline void queued_read_unlock(struct qrwlock *lock)
{
+ /*
+ * Trace and unlock are combined in the traced unlock variant so
+ * the compiler does not need to preserve the lock pointer across
+ * the function call, avoiding callee-saved register save/restore
+ * on the hot path.
+ */
+ if (tracepoint_enabled(contended_release)) {
+ queued_read_unlock_traced(lock);
+ return;
+ }
+
__queued_read_unlock(lock);
}
@@ -129,6 +145,12 @@ static __always_inline void __queued_write_unlock(struct qrwlock *lock)
*/
static inline void queued_write_unlock(struct qrwlock *lock)
{
+ /* See comment in queued_read_unlock(). */
+ if (tracepoint_enabled(contended_release)) {
+ queued_write_unlock_traced(lock);
+ return;
+ }
+
__queued_write_unlock(lock);
}
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index d2ef312a8611..5ae4b0372719 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -90,3 +90,19 @@ void __lockfunc queued_write_lock_slowpath(struct qrwlock *lock)
trace_contention_end(lock, 0);
}
EXPORT_SYMBOL(queued_write_lock_slowpath);
+
+void __lockfunc queued_read_unlock_traced(struct qrwlock *lock)
+{
+ if (queued_rwlock_is_contended(lock))
+ trace_call__contended_release(lock);
+ __queued_read_unlock(lock);
+}
+EXPORT_SYMBOL(queued_read_unlock_traced);
+
+void __lockfunc queued_write_unlock_traced(struct qrwlock *lock)
+{
+ if (queued_rwlock_is_contended(lock))
+ trace_call__contended_release(lock);
+ __queued_write_unlock(lock);
+}
+EXPORT_SYMBOL(queued_write_unlock_traced);
--
2.52.0
^ permalink raw reply related
* [PATCH v6 5/7] locking: Add contended_release tracepoint to qspinlock
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin,
Paul E. McKenney
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
Use the arch-overridable queued_spin_release(), introduced in the
previous commit, to ensure the tracepoint works correctly across all
architectures, including those with custom unlock implementations (e.g.
x86 paravirt).
When the tracepoint is disabled, the only addition to the hot path is a
single NOP instruction (the static branch). When enabled, the contention
check, trace call, and unlock are combined in an out-of-line function to
minimize hot path impact, avoiding the compiler needing to preserve the
lock pointer in a callee-saved register across the trace call.
Binary size impact (x86_64, defconfig):
uninlined unlock (common case): +680 bytes (+0.00%)
inlined unlock (worst case): +83659 bytes (+0.21%)
The inlined unlock case could not be achieved through Kconfig options on
x86_64 as PREEMPT_BUILD unconditionally selects UNINLINE_SPIN_UNLOCK on
x86_64. The UNINLINE_SPIN_UNLOCK guards were manually inverted to force
inline the unlock path and estimate the worst case binary size increase.
In practice, configurations with UNINLINE_SPIN_UNLOCK=n have already
opted against binary size optimization, so the inlined worst case is
unlikely to be a concern.
Architectures with fully custom qspinlock implementations (e.g.
PowerPC) are not covered by this change.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
---
include/asm-generic/qspinlock.h | 18 ++++++++++++++++++
kernel/locking/qspinlock.c | 8 ++++++++
2 files changed, 26 insertions(+)
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index df76f34645a0..915a4c2777f6 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -41,6 +41,7 @@
#include <asm-generic/qspinlock_types.h>
#include <linux/atomic.h>
+#include <linux/tracepoint-defs.h>
#ifndef queued_spin_is_locked
/**
@@ -129,12 +130,29 @@ static __always_inline void queued_spin_release(struct qspinlock *lock)
}
#endif
+DECLARE_TRACEPOINT(contended_release);
+
+extern void queued_spin_release_traced(struct qspinlock *lock);
+
/**
* queued_spin_unlock - unlock a queued spinlock
* @lock : Pointer to queued spinlock structure
+ *
+ * Generic tracing wrapper around the arch-overridable
+ * queued_spin_release().
*/
static __always_inline void queued_spin_unlock(struct qspinlock *lock)
{
+ /*
+ * Trace and release are combined in queued_spin_release_traced() so
+ * the compiler does not need to preserve the lock pointer across the
+ * function call, avoiding callee-saved register save/restore on the
+ * hot path.
+ */
+ if (tracepoint_enabled(contended_release)) {
+ queued_spin_release_traced(lock);
+ return;
+ }
queued_spin_release(lock);
}
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index af8d122bb649..649fdca69288 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -104,6 +104,14 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
#endif
+void __lockfunc queued_spin_release_traced(struct qspinlock *lock)
+{
+ if (queued_spin_is_contended(lock))
+ trace_call__contended_release(lock);
+ queued_spin_release(lock);
+}
+EXPORT_SYMBOL(queued_spin_release_traced);
+
#endif /* _GEN_PV_LOCK_SLOWPATH */
/**
--
2.52.0
^ permalink raw reply related
* [PATCH v6 6/7] locking: Factor out __queued_read_unlock()/__queued_write_unlock()
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin,
Paul E. McKenney
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
This is a preparatory refactoring for the next commit, which adds
contended_release tracepoint instrumentation and needs to call the
unlock from both traced and non-traced paths.
No functional change.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
---
include/asm-generic/qrwlock.h | 20 +++++++++++++++-----
1 file changed, 15 insertions(+), 5 deletions(-)
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 75b8f4601b28..4b627bafba8b 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -101,16 +101,26 @@ static inline void queued_write_lock(struct qrwlock *lock)
queued_write_lock_slowpath(lock);
}
+static __always_inline void __queued_read_unlock(struct qrwlock *lock)
+{
+ /*
+ * Atomically decrement the reader count
+ */
+ (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
+}
+
/**
* queued_read_unlock - release read lock of a queued rwlock
* @lock : Pointer to queued rwlock structure
*/
static inline void queued_read_unlock(struct qrwlock *lock)
{
- /*
- * Atomically decrement the reader count
- */
- (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
+ __queued_read_unlock(lock);
+}
+
+static __always_inline void __queued_write_unlock(struct qrwlock *lock)
+{
+ smp_store_release(&lock->wlocked, 0);
}
/**
@@ -119,7 +129,7 @@ static inline void queued_read_unlock(struct qrwlock *lock)
*/
static inline void queued_write_unlock(struct qrwlock *lock)
{
- smp_store_release(&lock->wlocked, 0);
+ __queued_write_unlock(lock);
}
/**
--
2.52.0
^ permalink raw reply related
* [PATCH v6 1/7] tracing/lock: Remove unnecessary linux/sched.h include
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin, Usama Arif
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
None of the trace events in lock.h reference anything from
linux/sched.h. Remove the unnecessary include.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Usama Arif <usama.arif@linux.dev>
---
include/trace/events/lock.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index 8e89baa3775f..da978f2afb45 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -5,7 +5,6 @@
#if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_LOCK_H
-#include <linux/sched.h>
#include <linux/tracepoint.h>
/* flags for lock:contention_begin */
--
2.52.0
^ permalink raw reply related
* [PATCH v6 3/7] locking: Add contended_release tracepoint to sleepable locks
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin,
Paul E. McKenney
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
Add the contended_release trace event. This tracepoint fires on the
holder side when a contended lock is released, complementing the
existing contention_begin/contention_end tracepoints which fire on the
waiter side.
This enables correlating lock hold time under contention with waiter
events by lock address.
Add trace_contended_release()/trace_call__contended_release() calls to
the slowpath unlock paths of sleepable locks: mutex, rtmutex, semaphore,
rwsem, percpu-rwsem, and RT-specific rwbase locks.
Where possible, trace_contended_release() fires before the lock is
released and before the waiter is woken. For some lock types, the
tracepoint fires after the release but before the wake. Making the
placement consistent across all lock types is not worth the added
complexity.
For reader/writer locks, the tracepoint fires for every reader releasing
while a writer is waiting, not only for the last reader.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
---
include/trace/events/lock.h | 17 +++++++++++++++++
kernel/locking/mutex.c | 4 ++++
kernel/locking/percpu-rwsem.c | 11 +++++++++++
kernel/locking/rtmutex.c | 1 +
kernel/locking/rwbase_rt.c | 6 ++++++
kernel/locking/rwsem.c | 10 ++++++++--
kernel/locking/semaphore.c | 4 ++++
7 files changed, 51 insertions(+), 2 deletions(-)
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index da978f2afb45..1ded869cd619 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -137,6 +137,23 @@ TRACE_EVENT(contention_end,
TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret)
);
+TRACE_EVENT(contended_release,
+
+ TP_PROTO(void *lock),
+
+ TP_ARGS(lock),
+
+ TP_STRUCT__entry(
+ __field(void *, lock_addr)
+ ),
+
+ TP_fast_assign(
+ __entry->lock_addr = lock;
+ ),
+
+ TP_printk("%p", __entry->lock_addr)
+);
+
#endif /* _TRACE_LOCK_H */
/* This part must be outside protection */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 09534628dc01..43b7f7e281a0 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1023,6 +1023,9 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
wake_q_add(&wake_q, next);
}
+ if (trace_contended_release_enabled() && waiter)
+ trace_call__contended_release(lock);
+
if (owner & MUTEX_FLAG_HANDOFF)
__mutex_handoff(lock, next);
@@ -1220,6 +1223,7 @@ EXPORT_SYMBOL(ww_mutex_lock_interruptible);
EXPORT_TRACEPOINT_SYMBOL_GPL(contention_begin);
EXPORT_TRACEPOINT_SYMBOL_GPL(contention_end);
+EXPORT_TRACEPOINT_SYMBOL_GPL(contended_release);
/**
* atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index f3ee7a0d6047..f7e152c40d6d 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -263,6 +263,9 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
{
rwsem_release(&sem->dep_map, _RET_IP_);
+ if (trace_contended_release_enabled() && wq_has_sleeper(&sem->waiters))
+ trace_call__contended_release(sem);
+
/*
* Signal the writer is done, no fast path yet.
*
@@ -292,6 +295,14 @@ EXPORT_SYMBOL_GPL(percpu_up_write);
void __percpu_up_read(struct percpu_rw_semaphore *sem)
{
lockdep_assert_preemption_disabled();
+ /*
+ * After percpu_up_write() completes, rcu_sync_is_idle() can still
+ * return false during the grace period, forcing readers into this
+ * slowpath. Only trace when a writer is actually waiting for
+ * readers to drain.
+ */
+ if (trace_contended_release_enabled() && rcuwait_active(&sem->writer))
+ trace_call__contended_release(sem);
/*
* slowpath; reader will only ever wake a single blocked
* writer.
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 69759fde7d10..9a4c3bee50ac 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1470,6 +1470,7 @@ static void __sched rt_mutex_slowunlock(struct rt_mutex_base *lock)
raw_spin_lock_irqsave(&lock->wait_lock, flags);
}
+ trace_contended_release(lock);
/*
* The wakeup next waiter path does not suffer from the above
* race. See the comments there.
diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c
index 82e078c0665a..2835c9ef9b3f 100644
--- a/kernel/locking/rwbase_rt.c
+++ b/kernel/locking/rwbase_rt.c
@@ -174,6 +174,8 @@ static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb,
static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb,
unsigned int state)
{
+ if (trace_contended_release_enabled() && rt_mutex_owner(&rwb->rtmutex))
+ trace_call__contended_release(rwb);
/*
* rwb->readers can only hit 0 when a writer is waiting for the
* active readers to leave the critical section.
@@ -205,6 +207,8 @@ static inline void rwbase_write_unlock(struct rwbase_rt *rwb)
unsigned long flags;
raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+ if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm))
+ trace_call__contended_release(rwb);
__rwbase_write_unlock(rwb, WRITER_BIAS, flags);
}
@@ -214,6 +218,8 @@ static inline void rwbase_write_downgrade(struct rwbase_rt *rwb)
unsigned long flags;
raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+ if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm))
+ trace_call__contended_release(rwb);
/* Release it and account current as reader */
__rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags);
}
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index bf647097369c..b9c180ac1eee 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1387,6 +1387,8 @@ static inline void __up_read(struct rw_semaphore *sem)
rwsem_clear_reader_owned(sem);
tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
+ if (trace_contended_release_enabled() && (tmp & RWSEM_FLAG_WAITERS))
+ trace_call__contended_release(sem);
if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) ==
RWSEM_FLAG_WAITERS)) {
clear_nonspinnable(sem);
@@ -1413,8 +1415,10 @@ static inline void __up_write(struct rw_semaphore *sem)
preempt_disable();
rwsem_clear_owner(sem);
tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
- if (unlikely(tmp & RWSEM_FLAG_WAITERS))
+ if (unlikely(tmp & RWSEM_FLAG_WAITERS)) {
+ trace_contended_release(sem);
rwsem_wake(sem);
+ }
preempt_enable();
}
@@ -1437,8 +1441,10 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
tmp = atomic_long_fetch_add_release(
-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
rwsem_set_reader_owned(sem);
- if (tmp & RWSEM_FLAG_WAITERS)
+ if (tmp & RWSEM_FLAG_WAITERS) {
+ trace_contended_release(sem);
rwsem_downgrade_wake(sem);
+ }
preempt_enable();
}
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 74d41433ba13..233730c25933 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -230,6 +230,10 @@ void __sched up(struct semaphore *sem)
sem->count++;
else
__up(sem, &wake_q);
+
+ if (trace_contended_release_enabled() && !wake_q_empty(&wake_q))
+ trace_call__contended_release(sem);
+
raw_spin_unlock_irqrestore(&sem->lock, flags);
if (!wake_q_empty(&wake_q))
wake_up_q(&wake_q);
--
2.52.0
^ permalink raw reply related
* [PATCH v6 4/7] locking: Factor out queued_spin_release()
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin,
Paul E. McKenney
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
Introduce queued_spin_release() as an arch-overridable unlock primitive,
and make queued_spin_unlock() a generic wrapper around it.
This is a preparatory refactoring for the next commit, which adds
contended_release tracepoint instrumentation to queued_spin_unlock().
Rename the existing arch-specific queued_spin_unlock() overrides on
x86 (paravirt) and MIPS to queued_spin_release().
No functional change.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
---
arch/mips/include/asm/spinlock.h | 6 +++---
arch/x86/include/asm/paravirt-spinlock.h | 6 +++---
include/asm-generic/qspinlock.h | 15 ++++++++++++---
3 files changed, 18 insertions(+), 9 deletions(-)
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index 6ce2117e49f6..c349162f15eb 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -13,12 +13,12 @@
#include <asm-generic/qspinlock_types.h>
-#define queued_spin_unlock queued_spin_unlock
+#define queued_spin_release queued_spin_release
/**
- * queued_spin_unlock - release a queued spinlock
+ * queued_spin_release - release a queued spinlock
* @lock : Pointer to queued spinlock structure
*/
-static inline void queued_spin_unlock(struct qspinlock *lock)
+static inline void queued_spin_release(struct qspinlock *lock)
{
/* This could be optimised with ARCH_HAS_MMIOWB */
mmiowb();
diff --git a/arch/x86/include/asm/paravirt-spinlock.h b/arch/x86/include/asm/paravirt-spinlock.h
index 7beffcb08ed6..ac75e0736198 100644
--- a/arch/x86/include/asm/paravirt-spinlock.h
+++ b/arch/x86/include/asm/paravirt-spinlock.h
@@ -49,9 +49,9 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu)
ALT_NOT(X86_FEATURE_VCPUPREEMPT));
}
-#define queued_spin_unlock queued_spin_unlock
+#define queued_spin_release queued_spin_release
/**
- * queued_spin_unlock - release a queued spinlock
+ * queued_spin_release - release a queued spinlock
* @lock : Pointer to queued spinlock structure
*
* A smp_store_release() on the least-significant byte.
@@ -66,7 +66,7 @@ static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
pv_queued_spin_lock_slowpath(lock, val);
}
-static inline void queued_spin_unlock(struct qspinlock *lock)
+static inline void queued_spin_release(struct qspinlock *lock)
{
kcsan_release();
pv_queued_spin_unlock(lock);
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index bf47cca2c375..df76f34645a0 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -115,12 +115,12 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
}
#endif
-#ifndef queued_spin_unlock
+#ifndef queued_spin_release
/**
- * queued_spin_unlock - release a queued spinlock
+ * queued_spin_release - release a queued spinlock
* @lock : Pointer to queued spinlock structure
*/
-static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+static __always_inline void queued_spin_release(struct qspinlock *lock)
{
/*
* unlock() needs release semantics:
@@ -129,6 +129,15 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
}
#endif
+/**
+ * queued_spin_unlock - unlock a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ queued_spin_release(lock);
+}
+
#ifndef virt_spin_lock
static __always_inline bool virt_spin_lock(struct qspinlock *lock)
{
--
2.52.0
^ permalink raw reply related
* [PATCH v6 2/7] locking/percpu-rwsem: Extract __percpu_up_read()
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin, Usama Arif
In-Reply-To: <cover.1777999826.git.d@ilvokhin.com>
Move the percpu_up_read() slowpath out of the inline function into a new
__percpu_up_read() to avoid binary size increase from adding a
tracepoint to an inlined function.
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Usama Arif <usama.arif@linux.dev>
---
include/linux/percpu-rwsem.h | 15 +++------------
kernel/locking/percpu-rwsem.c | 18 ++++++++++++++++++
2 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index c8cb010d655e..39d5bf8e6562 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -107,6 +107,8 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
return ret;
}
+extern void __percpu_up_read(struct percpu_rw_semaphore *sem);
+
static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
{
rwsem_release(&sem->dep_map, _RET_IP_);
@@ -118,18 +120,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
if (likely(rcu_sync_is_idle(&sem->rss))) {
this_cpu_dec(*sem->read_count);
} else {
- /*
- * slowpath; reader will only ever wake a single blocked
- * writer.
- */
- smp_mb(); /* B matches C */
- /*
- * In other words, if they see our decrement (presumably to
- * aggregate zero, as that is the only time it matters) they
- * will also see our critical section.
- */
- this_cpu_dec(*sem->read_count);
- rcuwait_wake_up(&sem->writer);
+ __percpu_up_read(sem);
}
preempt_enable();
}
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index ef234469baac..f3ee7a0d6047 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -288,3 +288,21 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
rcu_sync_exit(&sem->rss);
}
EXPORT_SYMBOL_GPL(percpu_up_write);
+
+void __percpu_up_read(struct percpu_rw_semaphore *sem)
+{
+ lockdep_assert_preemption_disabled();
+ /*
+ * slowpath; reader will only ever wake a single blocked
+ * writer.
+ */
+ smp_mb(); /* B matches C */
+ /*
+ * In other words, if they see our decrement (presumably to
+ * aggregate zero, as that is the only time it matters) they
+ * will also see our critical section.
+ */
+ this_cpu_dec(*sem->read_count);
+ rcuwait_wake_up(&sem->writer);
+}
+EXPORT_SYMBOL_GPL(__percpu_up_read);
--
2.52.0
^ permalink raw reply related
* [PATCH v6 0/7] locking: contended_release tracepoint instrumentation
From: Dmitry Ilvokhin @ 2026-05-05 17:09 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-mips, virtualization, linux-arch, linux-mm,
linux-trace-kernel, kernel-team, Dmitry Ilvokhin
The existing contention_begin/contention_end tracepoints fire on the
waiter side. The lock holder's identity and stack can be captured at
contention_begin time (e.g. perf lock contention --lock-owner), but
this reflects the holder's state when a waiter arrives, not when the
lock is actually released.
This series adds a contended_release tracepoint that fires on the
holder side when a lock with waiters is released. This provides:
- Hold time estimation: when the holder's own acquisition was
contended, its contention_end (acquisition) and contended_release
can be correlated to measure how long the lock was held under
contention.
- The holder's stack at release time, which may differ from what perf lock
contention --lock-owner captures if the holder does significant work between
the waiter's arrival and the unlock.
Note: for reader/writer locks, the tracepoint fires for every reader
releasing while a writer is waiting, not only for the last reader.
v5 -> v6:
- Use trace_call__contended_release() instead of trace_contended_release(),
where appropriate to avoid a redundant static branch check when the caller
already guards with trace_contended_release_enabled().
- Added acked-by from Paul.
- Rebase on top of the fresh locking/core.
v4 -> v5:
- Split the combined spinning locks patch into separate qspinlock and
qrwlock patches (Paul E. McKenney).
- Factor out __queued_read_unlock()/__queued_write_unlock() as a
separate preparatory commit, mirroring the queued_spin_release()
split (Paul E. McKenney).
- Updated binary size numbers for qspinlock-only change.
- Added Acked-by and Reviewed-by tags where appropriate.
v3 -> v4:
- Fix spurious events in __percpu_up_read(): guard with
rcuwait_active(&sem->writer) to avoid tracing during the RCU grace
period after a writer releases (Sashiko).
- Fix possible use-after-free in semaphore up(): move
trace_contended_release() inside the sem->lock critical section
(Sashiko).
- Fix build failure with CONFIG_PARAVIRT_SPINLOCKS=y: introduce
queued_spin_release() as the arch-overridable unlock primitive,
so queued_spin_unlock() can be a generic tracing wrapper. Convert
x86 (paravirt) and MIPS overrides (Sashiko).
- Add EXPORT_TRACEPOINT_SYMBOL_GPL(contended_release) for module
support (Sashiko).
- Split spinning locks patch: factor out queued_spin_release() as a
separate preparatory commit (Sashiko).
- Make read unlock tracepoint behavior consistent across all
reader/writer lock types: fire for every reader releasing while
a writer is waiting (rwsem, rwbase_rt were previously last-reader
only).
v2 -> v3:
- Added new patch: extend contended_release tracepoint to queued spinlocks
and queued rwlocks (marked as RFC, requesting feedback). This is prompted by
Matthew Wilcox's suggestion to try to come up with generic instrumentation,
instead of instrumenting each "special" lock manually. See [1] for the
discussion.
- Reworked tracepoint placement to fire before the lock is released and
before the waiter is woken where possible, for consistency with
spinning locks where there is no explicit wake (inspired by Usama Arif's
suggestion).
- Remove unnecessary linux/sched.h include from trace/events/lock.h.
RFC -> v2:
- Add trace_contended_release_enabled() guard before waiter checks that
exist only for the tracepoint (Steven Rostedt).
- Rename __percpu_up_read_slowpath() to __percpu_up_read() (Peter
Zijlstra).
- Add extern for __percpu_up_read() (Peter Zijlstra).
- Squashed tracepoint introduction and usage commits (Masami Hiramatsu).
v5: https://lore.kernel.org/all/cover.1776350944.git.d@ilvokhin.com/
v4: https://lore.kernel.org/all/cover.1774536681.git.d@ilvokhin.com/
v3: https://lore.kernel.org/all/cover.1773858853.git.d@ilvokhin.com/
v2: https://lore.kernel.org/all/cover.1773164180.git.d@ilvokhin.com/
RFC: https://lore.kernel.org/all/cover.1772642407.git.d@ilvokhin.com/
[1]: https://lore.kernel.org/all/aa7G1nD7Rd9F4eBH@casper.infradead.org/
Dmitry Ilvokhin (7):
tracing/lock: Remove unnecessary linux/sched.h include
locking/percpu-rwsem: Extract __percpu_up_read()
locking: Add contended_release tracepoint to sleepable locks
locking: Factor out queued_spin_release()
locking: Add contended_release tracepoint to qspinlock
locking: Factor out __queued_read_unlock()/__queued_write_unlock()
locking: Add contended_release tracepoint to qrwlock
arch/mips/include/asm/spinlock.h | 6 ++--
arch/x86/include/asm/paravirt-spinlock.h | 6 ++--
include/asm-generic/qrwlock.h | 38 ++++++++++++++++++++++--
include/asm-generic/qspinlock.h | 33 ++++++++++++++++++--
include/linux/percpu-rwsem.h | 15 ++--------
include/trace/events/lock.h | 18 ++++++++++-
kernel/locking/mutex.c | 4 +++
kernel/locking/percpu-rwsem.c | 29 ++++++++++++++++++
kernel/locking/qrwlock.c | 16 ++++++++++
kernel/locking/qspinlock.c | 8 +++++
kernel/locking/rtmutex.c | 1 +
kernel/locking/rwbase_rt.c | 6 ++++
kernel/locking/rwsem.c | 10 +++++--
kernel/locking/semaphore.c | 4 +++
14 files changed, 167 insertions(+), 27 deletions(-)
--
2.52.0
^ permalink raw reply
* Re: [PATCH v2 2/2] module/kallsyms: sort function symbols and use binary search
From: Petr Pavlu @ 2026-05-05 14:37 UTC (permalink / raw)
To: Petr Mladek
Cc: Stanislaw Gruszka, linux-modules, Sami Tolvanen, Luis Chamberlain,
linux-kernel, linux-trace-kernel, live-patching, Daniel Gomez,
Aaron Tomlin, Steven Rostedt, Masami Hiramatsu, Jordan Rome,
Viktor Malik, Miroslav Benes, Josh Poimboeuf, Joe Lawrence
In-Reply-To: <afnhidn7K7dZ_cPh@pathway.suse.cz>
On 5/5/26 2:24 PM, Petr Mladek wrote:
> On Fri 2026-03-27 12:00:05, Stanislaw Gruszka wrote:
>> Module symbol lookup via find_kallsyms_symbol() performs a linear scan
>> over the entire symtab when resolving an address. The number of symbols
>> in module symtabs has grown over the years, largely due to additional
>> metadata in non-standard sections, making this lookup very slow.
>>
>> Improve this by separating function symbols during module load, placing
>> them at the beginning of the symtab, sorting them by address, and using
>> binary search when resolving addresses in module text.
>>
>> This also should improve times for linear symbol name lookups, as valid
>> function symbols are now located at the beginning of the symtab.
>>
>> The cost of sorting is small relative to module load time. In repeated
>> module load tests [1], depending on .config options, this change
>> increases load time between 2% and 4%. With cold caches, the difference
>> is not measurable, as memory access latency dominates.
>>
>> The sorting theoretically could be done in compile time, but much more
>> complicated as we would have to simulate kernel addresses resolution
>> for symbols, and then correct relocation entries. That would be risky
>> if get out of sync.
>>
>> The improvement can be observed when listing ftrace filter functions.
>>
>> Before:
>>
>> root@nano:~# time cat /sys/kernel/tracing/available_filter_functions | wc -l
>> 74908
>>
>> real 0m1.315s
>> user 0m0.000s
>> sys 0m1.312s
>>
>> After:
>>
>> root@nano:~# time cat /sys/kernel/tracing/available_filter_functions | wc -l
>> 74911
>>
>> real 0m0.167s
>> user 0m0.004s
>> sys 0m0.175s
>>
>> (there are three more symbols introduced by the patch)
>>
>> For livepatch modules, the symtab layout is preserved and the existing
>> linear search is used. For this case, it should be possible to keep
>> the original ELF symtab instead of copying it 1:1, but that is outside
>> the scope of this patch.
>
> What is the exact motivation for the special handling of livepatch modules,
> please?
>
> Honestly, I am always a bit lost in the various symbol tables. It is
> possile that I have got something wrong.
>
> Anyway, my understanding is that there are two aspects which are important
> for livepatches:
>
> 1. Livepatches need to preserve special symbols which are used to
> relocate symbols which were local in the original code, see
> Documentation/livepatch/module-elf-format.rst
>
> IMHO, this is why layout_symtab() computes space for all core
> symbols in livepatch modules and copies them in add_kallsyms().
>
> The symtab is normally released when the module is loaded.
> But livepatch modules make its own copy of the important
> parts, see copy_module_elf().
>
> IMHO, the sorting of function symbols vs other symbols does
> not matter here. I believe that the special relocation
> symbols are not affected by this.
I'm not sure if I fully follow the conclusion in this point. My
understanding is that .klp.rela sections still refer to their special
symbols in the symbol table via Elf_Rela::r_info. If the symbol table is
filtered or reordered, these references will end up pointing to
incorrect symbols.
This is also described in Documentation/livepatch/module-elf-format.rst,
section "4.1 A livepatch module's symbol table".
>
>
> 2. Livepatches _rely on the sorting_ of symbols in the module.
> The special relocation symbols might define a symbol position,
> see
>
> .klp.sym.objname.symbol_name,sympos
>
> in the documentation. It defines the position of the symbol
> when there are more symbols of the same name, see
> klp_match_callback() in kernel/livepatch/core.c.
>
> I am afraid that _this patch might break_ this when it moves
> function symbols before non-funciton ones. I guess that
> the symbols of the same name will not longer be groupped.
I see. So if the module loader sorts the symbol table in a regular
module and a livepatch module exists for that module, the livepatch may
no longer function correctly. This means that the loader cannot even
reorder the symbol table in regular modules.
--
Thanks,
Petr
^ permalink raw reply
* Re: [PATCH v9 0/6] x86/vdso: VDSO updates and fixes for sframes
From: Jens Remus @ 2026-05-05 14:25 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: bpf, linux-mm, Namhyung Kim, Andrii Nakryiko, Jose E. Marchesi,
Beau Belgrave, Florian Weimer, Carlos O'Donell,
Masami Hiramatsu, Jiri Olsa, Arnaldo Carvalho de Melo,
Andrew Morton, David Hildenbrand, Lorenzo Stoakes,
Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
On 5/5/2026 2:33 PM, Jens Remus wrote:
> This enables generation of SFrame V3 stack trace information for VDSO on
> x86-64. It's a continuation of Josh's and Steve's work:
>
> https://lore.kernel.org/all/cover.1737511963.git.jpoimboe@kernel.org/
> https://lore.kernel.org/all/20250425023750.669174660@goodmis.org/
>
> This series focuses only on the VDSO code. They are helpful fixes
> and updates that doesn't rely on sframes (although the last patch
> is sframe related).
>
> This series applies on top of tip:master (a375022d6383):
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git master
>
> Like the unwind user sframe series [1] it depends on the binutils 2.46
> release to be used to build the VDSO with SFrame V3 stack trace
> information (using the assembler option --gsframe-3).
>
> [1]: [PATCH v14 00/19] unwind_deferred: Implement sframe handling,
> https://lore.kernel.org/all/20260505121718.3572346-1-jremus@linux.ibm.com/
>
> Changes in v10:
> - Rebased on tip:master (a375022d6383).
Apologies for the incorrect series version in the cover letter.
Regards,
Jens
--
Jens Remus
Linux on Z Development (D3303)
jremus@de.ibm.com / jremus@linux.ibm.com
IBM Deutschland Research & Development GmbH; Vorsitzender des Aufsichtsrats: Wolfgang Wendt; Geschäftsführung: David Faller; Sitz der Gesellschaft: Ehningen; Registergericht: Amtsgericht Stuttgart, HRB 243294
IBM Data Privacy Statement: https://www.ibm.com/privacy/
^ permalink raw reply
* [PATCH v10 6/6] x86/vdso: Enable sframe generation in VDSO
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
Enable .sframe generation in the VDSO library so kernel and user space
can unwind through it.
Starting with binutils 2.46 both GNU assembler and GNU linker
exclusively support generating and merging .sframe in SFrame V3 format.
For x86 SFrame is only supported for x86-64. Not for x86-32 nor x32.
Test whether the assembler supports option '--gsframe-3' to explicitly
select SFrame V3 format. Note that testing using Kconfig macro
'as-option' is not sufficient, as GNU assembler will accept the option
for any target, regardless of whether it is actually capable to generate
.sframe for it, as long the input does not trigger the generation.
Therefore it is necessary to use Kconfig macro 'as-instr' to provide
minimal CFI directives that trigger generation of .sframe.
For x86-64 VDSO, only if supported by the assembler, generate .sframe,
collect it, mark it as KEEP, and generate a GNU_SFRAME program table
entry.
For x86-32 and x32 VDSOs, given SFrame is not supported, do not generate
any .sframe nor GNU_SFRAME program table entry. Instead explicitly
discard any .sframe. The latter is required for x32 VDSO, as it is
built from x86-64 VDSO objects (potentially with .sframe) converted to
x32. In this regard discarding .sframe also prevents potential
issues with linkers, such as GNU linker prior to binutils 2.46 commit
7487c98ff07a ("x32: Allow R_X86_64_PC64 for SFrame V3"), that do not
support R_X86_64_PC64 relocations in x32, like those found in .sframe
in SFrame V3 format.
[ Jens Remus: Add support for SFrame V3. Prevent GNU_SFRAME program
table entry to empty .sframe section. Reword commit message. ]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
Notes (jremus):
Changes in v9:
- Always define KEEP_SFRAME to either true/false in specific VDSO linker
scripts and use #if instead of #ifdef in common one. (Peter)
- Reword commit message to provide more details.
arch/Kconfig | 7 +++++++
arch/x86/entry/vdso/common/vdso-layout.lds.S | 15 +++++++++++++++
arch/x86/entry/vdso/vdso32/vdso32.lds.S | 3 +++
arch/x86/entry/vdso/vdso64/Makefile | 1 +
arch/x86/entry/vdso/vdso64/vdso64.lds.S | 2 ++
arch/x86/entry/vdso/vdso64/vdsox32.lds.S | 6 ++++++
6 files changed, 34 insertions(+)
diff --git a/arch/Kconfig b/arch/Kconfig
index e86880045158..79aef9b67645 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -479,6 +479,13 @@ config HAVE_HARDLOCKUP_DETECTOR_ARCH
It uses the same command line parameters, and sysctl interface,
as the generic hardlockup detectors.
+config AS_SFRAME
+ bool
+
+config AS_SFRAME3
+ def_bool $(as-instr,.cfi_startproc\n.cfi_endproc,-Wa$(comma)--gsframe-3)
+ select AS_SFRAME
+
config UNWIND_USER
bool
diff --git a/arch/x86/entry/vdso/common/vdso-layout.lds.S b/arch/x86/entry/vdso/common/vdso-layout.lds.S
index 856b8b9d278c..c486b07b195a 100644
--- a/arch/x86/entry/vdso/common/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/common/vdso-layout.lds.S
@@ -60,6 +60,13 @@ SECTIONS
*(.eh_frame.*)
} :text
+#if KEEP_SFRAME
+ .sframe : {
+ KEEP (*(.sframe))
+ *(.sframe.*)
+ } :text :sframe
+#endif
+
/*
* Text is well-separated from actual data: there's plenty of
* stuff that isn't used at runtime in between.
@@ -80,6 +87,10 @@ SECTIONS
*(.discard)
*(.discard.*)
*(__bug_table)
+#if !KEEP_SFRAME
+ *(.sframe)
+ *(.sframe.*)
+#endif
}
}
@@ -89,6 +100,7 @@ SECTIONS
#define PT_GNU_EH_FRAME 0x6474e550
#define PT_GNU_STACK 0x6474e551
#define PT_GNU_PROPERTY 0x6474e553
+#define PT_GNU_SFRAME 0x6474e554
/*
* We must supply the ELF program headers explicitly to get just one
@@ -104,6 +116,9 @@ PHDRS
dynamic PT_DYNAMIC PF_R;
note PT_NOTE PF_R;
eh_frame_hdr PT_GNU_EH_FRAME PF_R;
+#if KEEP_SFRAME
+ sframe PT_GNU_SFRAME PF_R;
+#endif
gnu_stack PT_GNU_STACK PF_RW;
gnu_property PT_GNU_PROPERTY PF_R;
}
diff --git a/arch/x86/entry/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
index 55554f80d930..a18b65749ce3 100644
--- a/arch/x86/entry/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
@@ -11,6 +11,9 @@
#define BUILD_VDSO32
+/* Discard .sframe if any. SFrame does not support x86-32. */
+#define KEEP_SFRAME 0
+
#include "common/vdso-layout.lds.S"
/* The ELF entry point can be used to set the AT_SYSINFO value. */
diff --git a/arch/x86/entry/vdso/vdso64/Makefile b/arch/x86/entry/vdso/vdso64/Makefile
index bfffaf1aeecc..459f8026531e 100644
--- a/arch/x86/entry/vdso/vdso64/Makefile
+++ b/arch/x86/entry/vdso/vdso64/Makefile
@@ -14,6 +14,7 @@ vobjs-$(CONFIG_X86_SGX) += vsgx.o
# Compilation flags
flags-y := -DBUILD_VDSO64 -m64 -mcmodel=small
+flags-$(CONFIG_AS_SFRAME3) += -Wa,--gsframe-3
# The location of this include matters!
include $(src)/../common/Makefile.include
diff --git a/arch/x86/entry/vdso/vdso64/vdso64.lds.S b/arch/x86/entry/vdso/vdso64/vdso64.lds.S
index 5ce3f2b6373a..6685cf385fc1 100644
--- a/arch/x86/entry/vdso/vdso64/vdso64.lds.S
+++ b/arch/x86/entry/vdso/vdso64/vdso64.lds.S
@@ -9,6 +9,8 @@
#define BUILD_VDSO64
+#define KEEP_SFRAME IS_ENABLED(CONFIG_AS_SFRAME)
+
#include "common/vdso-layout.lds.S"
/*
diff --git a/arch/x86/entry/vdso/vdso64/vdsox32.lds.S b/arch/x86/entry/vdso/vdso64/vdsox32.lds.S
index 3dbd20c8dacc..5270fd0bdd0f 100644
--- a/arch/x86/entry/vdso/vdso64/vdsox32.lds.S
+++ b/arch/x86/entry/vdso/vdso64/vdsox32.lds.S
@@ -9,6 +9,12 @@
#define BUILD_VDSOX32
+/*
+ * Discard .sframe from x86-64 compiles. SFrame does not support x32 and
+ * it contains R_X86_64_PC64 relocations, which linkers may not expect.
+ */
+#define KEEP_SFRAME 0
+
#include "common/vdso-layout.lds.S"
/*
--
2.51.0
^ permalink raw reply related
* [PATCH v10 2/6] x86/asm: Avoid emitting DWARF CFI for non-VDSO
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
It was decided years ago that .cfi_* annotations aren't maintainable in
the kernel. They were replaced by objtool unwind hints. For the kernel
proper, ensure the CFI_* macros don't do anything.
On the other hand the VDSO library *does* use them, so user space can
unwind through it.
Make sure these macros only work for VDSO. They aren't actually being
used outside of VDSO anyway, so there's no functional change.
[ Jens Remus: Define CFI_SIGNAL_FRAME for !BUILD_VDSO. ]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
arch/x86/include/asm/dwarf2.h | 52 ++++++++++++++++++++++++-----------
1 file changed, 36 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 09c9684d3ad6..13e2e64ef265 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -6,6 +6,15 @@
#warning "asm/dwarf2.h should be only included in pure assembly files"
#endif
+#ifdef BUILD_VDSO
+
+ /*
+ * For the vDSO, emit both runtime unwind information and debug
+ * symbols for the .dbg file.
+ */
+
+ .cfi_sections .eh_frame, .debug_frame
+
#define CFI_STARTPROC .cfi_startproc
#define CFI_ENDPROC .cfi_endproc
#define CFI_DEF_CFA .cfi_def_cfa
@@ -22,21 +31,32 @@
#define CFI_ESCAPE .cfi_escape
#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#ifndef BUILD_VDSO
- /*
- * Emit CFI data in .debug_frame sections, not .eh_frame sections.
- * The latter we currently just discard since we don't do DWARF
- * unwinding at runtime. So only the offline DWARF information is
- * useful to anyone. Note we should not use this directive if we
- * ever decide to enable DWARF unwinding at runtime.
- */
- .cfi_sections .debug_frame
-#else
- /*
- * For the vDSO, emit both runtime unwind information and debug
- * symbols for the .dbg file.
- */
- .cfi_sections .eh_frame, .debug_frame
-#endif
+#else /* !BUILD_VDSO */
+
+/*
+ * On x86, these macros aren't used outside VDSO. As well they shouldn't be:
+ * they're fragile and very difficult to maintain.
+ */
+
+.macro nocfi args:vararg
+.endm
+
+#define CFI_STARTPROC nocfi
+#define CFI_ENDPROC nocfi
+#define CFI_DEF_CFA nocfi
+#define CFI_DEF_CFA_REGISTER nocfi
+#define CFI_DEF_CFA_OFFSET nocfi
+#define CFI_ADJUST_CFA_OFFSET nocfi
+#define CFI_OFFSET nocfi
+#define CFI_REL_OFFSET nocfi
+#define CFI_REGISTER nocfi
+#define CFI_RESTORE nocfi
+#define CFI_REMEMBER_STATE nocfi
+#define CFI_RESTORE_STATE nocfi
+#define CFI_UNDEFINED nocfi
+#define CFI_ESCAPE nocfi
+#define CFI_SIGNAL_FRAME nocfi
+
+#endif /* !BUILD_VDSO */
#endif /* _ASM_X86_DWARF2_H */
--
2.51.0
^ permalink raw reply related
* [PATCH v9 0/6] x86/vdso: VDSO updates and fixes for sframes
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich
This enables generation of SFrame V3 stack trace information for VDSO on
x86-64. It's a continuation of Josh's and Steve's work:
https://lore.kernel.org/all/cover.1737511963.git.jpoimboe@kernel.org/
https://lore.kernel.org/all/20250425023750.669174660@goodmis.org/
This series focuses only on the VDSO code. They are helpful fixes
and updates that doesn't rely on sframes (although the last patch
is sframe related).
This series applies on top of tip:master (a375022d6383):
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git master
Like the unwind user sframe series [1] it depends on the binutils 2.46
release to be used to build the VDSO with SFrame V3 stack trace
information (using the assembler option --gsframe-3).
[1]: [PATCH v14 00/19] unwind_deferred: Implement sframe handling,
https://lore.kernel.org/all/20260505121718.3572346-1-jremus@linux.ibm.com/
Changes in v10:
- Rebased on tip:master (a375022d6383).
Changes in v9 (see indivicual patch notes):
- Always define KEEP_SFRAME to either true/false in specific VDSO linker
scripts and use #if instead of #ifdef in common one. (Peter)
- Reword patch 6 commit message to provide more details.
- Note: Binutils 2.46 with SFrame V3 support has been released.
Changes in v8:
- Discard .sframe for x32 and x86-32 VDSOs. (Josh/Indu)
- Define CFI_SIGNAL_FRAME for !BUILD_VDSO.
- Drop .cfi_sections .sframe in dwarf2.h in favor of the explicitly
specified more specific assembler option --gsframe-3.
- Incorporate missing changes and review feedback from Steven's v6
(I erroneously based my v6 on Steven's v5):
- Reword patch 3 commit subject to Steven's v6 one.
- Remove SYM_F_ALIGN in __vdso_sgx_enter_enclave(). (Josh)
Changes in v7:
- Rebase on H. Peter Anvin's vDSO changes on tip:x86/entry. (Peter)
- Simplify adding assembler option -Wa,--gsframe-3. Add for vdso64
only.
- Align to .eh_frame and mark .sframe as KEEP in vDSO linker script.
Note that GNU linker 2.46 will mark .sframe as KEEP in its default
linker script as well.
Changes in v6:
- SFrame V3 support (SFrame V2 is not supported).
- Prevent GNU_SFRAME program table entry to empty .sframe section.
- Integrate v5 review feedback. (Josh)
Regards,
Jens
Josh Poimboeuf (6):
x86/vdso: Fix DWARF generation for getrandom()
x86/asm: Avoid emitting DWARF CFI for non-VDSO
x86/asm: Use CFI_* macros in SYM_FUNC_* macros so they can be added to
VDSO
x86/vdso: Use SYM_FUNC_{START,END} in __kernel_vsyscall()
x86/vdso: Use CFI macros in __vdso_sgx_enter_enclave()
x86/vdso: Enable sframe generation in VDSO
arch/Kconfig | 7 +++
arch/x86/entry/vdso/common/vdso-layout.lds.S | 17 +++++-
arch/x86/entry/vdso/vdso32/system_call.S | 10 +---
arch/x86/entry/vdso/vdso32/vdso32.lds.S | 3 ++
arch/x86/entry/vdso/vdso64/Makefile | 1 +
arch/x86/entry/vdso/vdso64/vdso64.lds.S | 2 +
arch/x86/entry/vdso/vdso64/vdsox32.lds.S | 6 +++
.../x86/entry/vdso/vdso64/vgetrandom-chacha.S | 3 +-
arch/x86/entry/vdso/vdso64/vsgx.S | 18 +++----
arch/x86/include/asm/dwarf2.h | 52 +++++++++++++------
arch/x86/include/asm/linkage.h | 33 +++++++++---
arch/x86/include/asm/vdso.h | 1 -
12 files changed, 107 insertions(+), 46 deletions(-)
--
2.51.0
^ permalink raw reply
* [PATCH v10 5/6] x86/vdso: Use CFI macros in __vdso_sgx_enter_enclave()
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
Use the CFI macros instead of the raw .cfi_* directives to be consistent
with the rest of the VDSO asm. It's also easier on the eyes.
No functional changes.
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
arch/x86/entry/vdso/vdso64/vsgx.S | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/arch/x86/entry/vdso/vdso64/vsgx.S b/arch/x86/entry/vdso/vdso64/vsgx.S
index c0342238c976..76efbeb1e287 100644
--- a/arch/x86/entry/vdso/vdso64/vsgx.S
+++ b/arch/x86/entry/vdso/vdso64/vsgx.S
@@ -25,12 +25,12 @@
SYM_FUNC_START(__vdso_sgx_enter_enclave)
push %rbp
- .cfi_adjust_cfa_offset 8
- .cfi_rel_offset %rbp, 0
+ CFI_ADJUST_CFA_OFFSET 8
+ CFI_REL_OFFSET %rbp, 0
mov %rsp, %rbp
- .cfi_def_cfa_register %rbp
+ CFI_DEF_CFA_REGISTER %rbp
push %rbx
- .cfi_rel_offset %rbx, -8
+ CFI_REL_OFFSET %rbx, -8
mov %ecx, %eax
.Lenter_enclave:
@@ -77,13 +77,11 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave)
.Lout:
pop %rbx
leave
- .cfi_def_cfa %rsp, 8
+ CFI_DEF_CFA %rsp, 8
RET
- /* The out-of-line code runs with the pre-leave stack frame. */
- .cfi_def_cfa %rbp, 16
-
.Linvalid_input:
+ CFI_DEF_CFA %rbp, 16
mov $(-EINVAL), %eax
jmp .Lout
--
2.51.0
^ permalink raw reply related
* [PATCH v10 3/6] x86/asm: Use CFI_* macros in SYM_FUNC_* macros so they can be added to VDSO
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
Add CFI_STARTPROC and CFI_ENDPROC annotations to the SYM_FUNC_* macros
so the VDSO asm functions don't need to add them manually. Note this
only affects VDSO, the CFI_* macros are empty for the kernel proper.
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
arch/x86/entry/vdso/common/vdso-layout.lds.S | 2 +-
.../x86/entry/vdso/vdso64/vgetrandom-chacha.S | 2 --
arch/x86/entry/vdso/vdso64/vsgx.S | 4 ---
arch/x86/include/asm/linkage.h | 33 +++++++++++++++----
arch/x86/include/asm/vdso.h | 1 -
5 files changed, 28 insertions(+), 14 deletions(-)
diff --git a/arch/x86/entry/vdso/common/vdso-layout.lds.S b/arch/x86/entry/vdso/common/vdso-layout.lds.S
index a1e30be3e83d..856b8b9d278c 100644
--- a/arch/x86/entry/vdso/common/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/common/vdso-layout.lds.S
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm/vdso.h>
+#include <asm/page_types.h>
#include <asm/vdso/vsyscall.h>
#include <vdso/datapage.h>
diff --git a/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S b/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S
index cc82da9216fb..a33212594731 100644
--- a/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S
+++ b/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S
@@ -22,7 +22,6 @@ CONSTANTS: .octa 0x6b20657479622d323320646e61707865
* rcx: number of 64-byte blocks to write to output
*/
SYM_FUNC_START(__arch_chacha20_blocks_nostack)
- CFI_STARTPROC
.set output, %rdi
.set key, %rsi
.set counter, %rdx
@@ -175,5 +174,4 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
pxor temp,temp
ret
- CFI_ENDPROC
SYM_FUNC_END(__arch_chacha20_blocks_nostack)
diff --git a/arch/x86/entry/vdso/vdso64/vsgx.S b/arch/x86/entry/vdso/vdso64/vsgx.S
index 37a3d4c02366..c0342238c976 100644
--- a/arch/x86/entry/vdso/vdso64/vsgx.S
+++ b/arch/x86/entry/vdso/vdso64/vsgx.S
@@ -24,8 +24,6 @@
.section .text, "ax"
SYM_FUNC_START(__vdso_sgx_enter_enclave)
- /* Prolog */
- .cfi_startproc
push %rbp
.cfi_adjust_cfa_offset 8
.cfi_rel_offset %rbp, 0
@@ -143,8 +141,6 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave)
jle .Lout
jmp .Lenter_enclave
- .cfi_endproc
-
_ASM_VDSO_EXTABLE_HANDLE(.Lenclu_eenter_eresume, .Lhandle_exception)
SYM_FUNC_END(__vdso_sgx_enter_enclave)
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index a7294656ad90..c2ca8117376f 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -40,6 +40,10 @@
#ifdef __ASSEMBLER__
+#ifndef LINKER_SCRIPT
+#include <asm/dwarf2.h>
+#endif
+
#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
#define RET jmp __x86_return_thunk
#else /* CONFIG_MITIGATION_RETPOLINE */
@@ -112,34 +116,51 @@
# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
#endif
+#define __SYM_FUNC_START \
+ CFI_STARTPROC ASM_NL
+
+#define __SYM_FUNC_END \
+ CFI_ENDPROC ASM_NL
+
/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
#define SYM_TYPED_FUNC_START(name) \
SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
+ __SYM_FUNC_START \
ENDBR
/* SYM_FUNC_START -- use for global functions */
#define SYM_FUNC_START(name) \
- SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)
+ SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
+ __SYM_FUNC_START
/* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
#define SYM_FUNC_START_NOALIGN(name) \
- SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) \
+ __SYM_FUNC_START
/* SYM_FUNC_START_LOCAL -- use for local functions */
#define SYM_FUNC_START_LOCAL(name) \
- SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)
+ SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN) \
+ __SYM_FUNC_START
/* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
#define SYM_FUNC_START_LOCAL_NOALIGN(name) \
- SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
+ SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) \
+ __SYM_FUNC_START
/* SYM_FUNC_START_WEAK -- use for weak functions */
#define SYM_FUNC_START_WEAK(name) \
- SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)
+ SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN) \
+ __SYM_FUNC_START
/* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */
#define SYM_FUNC_START_WEAK_NOALIGN(name) \
- SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
+ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \
+ __SYM_FUNC_START
+
+#define SYM_FUNC_END(name) \
+ __SYM_FUNC_END \
+ SYM_END(name, SYM_T_FUNC)
/*
* Expose 'sym' to the startup code in arch/x86/boot/startup/, by emitting an
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index f2d49212ae90..bbe270483e3e 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -2,7 +2,6 @@
#ifndef _ASM_X86_VDSO_H
#define _ASM_X86_VDSO_H
-#include <asm/page_types.h>
#include <linux/linkage.h>
#include <linux/init.h>
--
2.51.0
^ permalink raw reply related
* [PATCH v10 1/6] x86/vdso: Fix DWARF generation for getrandom()
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
Add CFI annotations to the VDSO implementation of getrandom() so it will
have valid DWARF unwinding metadata.
Fixes: 33385150ac45 ("x86: vdso: Wire up getrandom() vDSO implementation")
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S b/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S
index bcba5639b8ee..cc82da9216fb 100644
--- a/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S
+++ b/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S
@@ -4,7 +4,7 @@
*/
#include <linux/linkage.h>
-#include <asm/frame.h>
+#include <asm/dwarf2.h>
.section .rodata, "a"
.align 16
@@ -22,7 +22,7 @@ CONSTANTS: .octa 0x6b20657479622d323320646e61707865
* rcx: number of 64-byte blocks to write to output
*/
SYM_FUNC_START(__arch_chacha20_blocks_nostack)
-
+ CFI_STARTPROC
.set output, %rdi
.set key, %rsi
.set counter, %rdx
@@ -175,4 +175,5 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
pxor temp,temp
ret
+ CFI_ENDPROC
SYM_FUNC_END(__arch_chacha20_blocks_nostack)
--
2.51.0
^ permalink raw reply related
* [PATCH v10 4/6] x86/vdso: Use SYM_FUNC_{START,END} in __kernel_vsyscall()
From: Jens Remus @ 2026-05-05 12:33 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James,
Andy Lutomirski
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505123340.3770025-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
Use SYM_FUNC_{START,END} instead of all the boilerplate. No functional
change.
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
arch/x86/entry/vdso/vdso32/system_call.S | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 9157cf9c5749..a90f4f7de396 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -9,11 +9,7 @@
#include <asm/alternative.h>
.text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
- CFI_STARTPROC
+SYM_FUNC_START(__kernel_vsyscall)
/*
* If using int $0x80, there is no reason to muck about with the
@@ -85,7 +81,5 @@ SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL)
CFI_RESTORE ecx
CFI_ADJUST_CFA_OFFSET -4
RET
- CFI_ENDPROC
-
- .size __kernel_vsyscall,.-__kernel_vsyscall
+SYM_FUNC_END(__kernel_vsyscall)
.previous
--
2.51.0
^ permalink raw reply related
* Re: [PATCH v14 00/19] unwind_deferred: Implement sframe handling
From: Jens Remus @ 2026-05-05 12:25 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: bpf, linux-mm, Namhyung Kim, Andrii Nakryiko, Jose E. Marchesi,
Beau Belgrave, Florian Weimer, Carlos O'Donell,
Masami Hiramatsu, Jiri Olsa, Arnaldo Carvalho de Melo,
Andrew Morton, David Hildenbrand, Lorenzo Stoakes,
Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich
In-Reply-To: <20260505121718.3572346-1-jremus@linux.ibm.com>
On 5/5/2026 2:16 PM, Jens Remus wrote:
> This is the implementation of parsing the SFrame V3 stack trace information
> from an .sframe section in an ELF file. It's a continuation of Josh's and
> Steve's work that can be found here:
>
> https://lore.kernel.org/all/cover.1737511963.git.jpoimboe@kernel.org/
> https://lore.kernel.org/all/20250827201548.448472904@kernel.org/
I forgot to mention that Steven is working on a system call for dynamic
linkers to register .sframe for .text in dynamic libraries (DSOs), that
is supposed to replace the last test-patch of this series. Feedback
on that is much appreciated as well:
[RFC][PATCH] unwind: Add stacktrace_setup system call
https://lore.kernel.org/all/20260429114355.6c712e6a@gandalf.local.home/
Regards,
Jens
--
Jens Remus
Linux on Z Development (D3303)
jremus@de.ibm.com / jremus@linux.ibm.com
IBM Deutschland Research & Development GmbH; Vorsitzender des Aufsichtsrats: Wolfgang Wendt; Geschäftsführung: David Faller; Sitz der Gesellschaft: Ehningen; Registergericht: Amtsgericht Stuttgart, HRB 243294
IBM Data Privacy Statement: https://www.ibm.com/privacy/
^ permalink raw reply
* Re: [PATCH v2 2/2] module/kallsyms: sort function symbols and use binary search
From: Petr Mladek @ 2026-05-05 12:24 UTC (permalink / raw)
To: Stanislaw Gruszka
Cc: linux-modules, Sami Tolvanen, Luis Chamberlain, Petr Pavlu,
linux-kernel, linux-trace-kernel, live-patching, Daniel Gomez,
Aaron Tomlin, Steven Rostedt, Masami Hiramatsu, Jordan Rome,
Viktor Malik, Miroslav Benes, Josh Poimboeuf, Joe Lawrence
In-Reply-To: <20260327110005.16499-2-stf_xl@wp.pl>
On Fri 2026-03-27 12:00:05, Stanislaw Gruszka wrote:
> Module symbol lookup via find_kallsyms_symbol() performs a linear scan
> over the entire symtab when resolving an address. The number of symbols
> in module symtabs has grown over the years, largely due to additional
> metadata in non-standard sections, making this lookup very slow.
>
> Improve this by separating function symbols during module load, placing
> them at the beginning of the symtab, sorting them by address, and using
> binary search when resolving addresses in module text.
>
> This also should improve times for linear symbol name lookups, as valid
> function symbols are now located at the beginning of the symtab.
>
> The cost of sorting is small relative to module load time. In repeated
> module load tests [1], depending on .config options, this change
> increases load time between 2% and 4%. With cold caches, the difference
> is not measurable, as memory access latency dominates.
>
> The sorting theoretically could be done in compile time, but much more
> complicated as we would have to simulate kernel addresses resolution
> for symbols, and then correct relocation entries. That would be risky
> if get out of sync.
>
> The improvement can be observed when listing ftrace filter functions.
>
> Before:
>
> root@nano:~# time cat /sys/kernel/tracing/available_filter_functions | wc -l
> 74908
>
> real 0m1.315s
> user 0m0.000s
> sys 0m1.312s
>
> After:
>
> root@nano:~# time cat /sys/kernel/tracing/available_filter_functions | wc -l
> 74911
>
> real 0m0.167s
> user 0m0.004s
> sys 0m0.175s
>
> (there are three more symbols introduced by the patch)
>
> For livepatch modules, the symtab layout is preserved and the existing
> linear search is used. For this case, it should be possible to keep
> the original ELF symtab instead of copying it 1:1, but that is outside
> the scope of this patch.
What is the exact motivation for the special handling of livepatch modules,
please?
Honestly, I am always a bit lost in the various symbol tables. It is
possile that I have got something wrong.
Anyway, my understanding is that there are two aspects which are important
for livepatches:
1. Livepatches need to preserve special symbols which are used to
relocate symbols which were local in the original code, see
Documentation/livepatch/module-elf-format.rst
IMHO, this is why layout_symtab() computes space for all core
symbols in livepatch modules and copies them in add_kallsyms().
The symtab is normally released when the module is loaded.
But livepatch modules make its own copy of the important
parts, see copy_module_elf().
IMHO, the sorting of function symbols vs other symbols does
not matter here. I believe that the special relocation
symbols are not affected by this.
2. Livepatches _rely on the sorting_ of symbols in the module.
The special relocation symbols might define a symbol position,
see
.klp.sym.objname.symbol_name,sympos
in the documentation. It defines the position of the symbol
when there are more symbols of the same name, see
klp_match_callback() in kernel/livepatch/core.c.
I am afraid that _this patch might break_ this when it moves
function symbols before non-funciton ones. I guess that
the symbols of the same name will not longer be groupped.
Idea: Is the shufling really important for the performance, please?
I would expect that binary search would have a good performance
even without the shuffling. It puts aside half of the symbols in
one cycle.
Note that the binary search in find_kallsyms_symbol() is perfectly
fine. The livepatch code explicitly iterates over all symbols using
module_kallsyms_on_each_symbol(), see klp_find_object_symbol().
Best Regards,
Petr
^ permalink raw reply
* [PATCH v14 11/19] unwind_user/sframe: Show file name in debug output
From: Jens Remus @ 2026-05-05 12:17 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505121718.3572346-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
When debugging sframe issues, the error messages aren't all that helpful
without knowing what file a corresponding .sframe section belongs to.
Prefix debug output strings with the file name.
[ Jens Remus: Fix checkpatch error "space prohibited before that close
parenthesis ')'". ]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Indu Bhagat <ibhagatgnu@gmail.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
Notes (jremus):
Changes in v14:
- Uppercase terms FDE and FRE in debug messages.
include/linux/sframe.h | 4 +++-
kernel/unwind/sframe.c | 23 ++++++++++--------
kernel/unwind/sframe_debug.h | 45 +++++++++++++++++++++++++++++++-----
3 files changed, 56 insertions(+), 16 deletions(-)
diff --git a/include/linux/sframe.h b/include/linux/sframe.h
index 9a72209696f9..b79c5ec09229 100644
--- a/include/linux/sframe.h
+++ b/include/linux/sframe.h
@@ -10,7 +10,9 @@
struct sframe_section {
struct rcu_head rcu;
-
+#ifdef CONFIG_DYNAMIC_DEBUG
+ const char *filename;
+#endif
unsigned long sframe_start;
unsigned long sframe_end;
unsigned long text_start;
diff --git a/kernel/unwind/sframe.c b/kernel/unwind/sframe.c
index 8eed6a7d9625..4419626f0173 100644
--- a/kernel/unwind/sframe.c
+++ b/kernel/unwind/sframe.c
@@ -359,14 +359,17 @@ int sframe_find(unsigned long ip, struct unwind_user_frame *frame)
end:
user_read_access_end();
- if (ret == -EFAULT)
+ if (ret == -EFAULT) {
+ dbg_sec("removing bad .sframe section\n");
WARN_ON_ONCE(sframe_remove_section(sec->sframe_start));
+ }
return ret;
}
static void free_section(struct sframe_section *sec)
{
+ dbg_free(sec);
kfree(sec);
}
@@ -377,7 +380,7 @@ static int sframe_read_header(struct sframe_section *sec)
unsigned int num_fdes;
if (copy_from_user(&shdr, (void __user *)sec->sframe_start, sizeof(shdr))) {
- dbg("header usercopy failed\n");
+ dbg_sec("header usercopy failed\n");
return -EFAULT;
}
@@ -386,18 +389,18 @@ static int sframe_read_header(struct sframe_section *sec)
!(shdr.preamble.flags & SFRAME_F_FDE_SORTED) ||
!(shdr.preamble.flags & SFRAME_F_FDE_FUNC_START_PCREL) ||
shdr.auxhdr_len) {
- dbg("bad/unsupported sframe header\n");
+ dbg_sec("bad/unsupported sframe header\n");
return -EINVAL;
}
if (!shdr.num_fdes || !shdr.num_fres) {
- dbg("no fde/fre entries\n");
+ dbg_sec("no FDE/FRE entries\n");
return -EINVAL;
}
header_end = sec->sframe_start + SFRAME_HEADER_SIZE(shdr);
if (header_end >= sec->sframe_end) {
- dbg("header doesn't fit in section\n");
+ dbg_sec("header doesn't fit in section\n");
return -EINVAL;
}
@@ -409,7 +412,7 @@ static int sframe_read_header(struct sframe_section *sec)
fres_end = fres_start + shdr.fre_len;
if (fres_start < fdes_end || fres_end > sec->sframe_end) {
- dbg("inconsistent fde/fre offsets\n");
+ dbg_sec("inconsistent FDE/FRE offsets\n");
return -EINVAL;
}
@@ -465,6 +468,8 @@ int sframe_add_section(unsigned long sframe_start, unsigned long sframe_end,
sec->text_start = text_start;
sec->text_end = text_end;
+ dbg_init(sec);
+
ret = sframe_read_header(sec);
if (ret) {
dbg_print_header(sec);
@@ -473,8 +478,8 @@ int sframe_add_section(unsigned long sframe_start, unsigned long sframe_end,
ret = mtree_insert_range(sframe_mt, sec->text_start, sec->text_end, sec, GFP_KERNEL);
if (ret) {
- dbg("mtree_insert_range failed: text=%lx-%lx\n",
- sec->text_start, sec->text_end);
+ dbg_sec("mtree_insert_range failed: text=%lx-%lx\n",
+ sec->text_start, sec->text_end);
goto err_free;
}
@@ -496,7 +501,7 @@ static int __sframe_remove_section(struct mm_struct *mm,
struct sframe_section *sec)
{
if (!mtree_erase(&mm->sframe_mt, sec->text_start)) {
- dbg("mtree_erase failed: text=%lx\n", sec->text_start);
+ dbg_sec("mtree_erase failed: text=%lx\n", sec->text_start);
return -EINVAL;
}
diff --git a/kernel/unwind/sframe_debug.h b/kernel/unwind/sframe_debug.h
index 36352124cde8..e568be4172b1 100644
--- a/kernel/unwind/sframe_debug.h
+++ b/kernel/unwind/sframe_debug.h
@@ -10,26 +10,59 @@
#define dbg(fmt, ...) \
pr_debug("%s (%d): " fmt, current->comm, current->pid, ##__VA_ARGS__)
+#define dbg_sec(fmt, ...) \
+ dbg("%s: " fmt, sec->filename, ##__VA_ARGS__)
+
static __always_inline void dbg_print_header(struct sframe_section *sec)
{
unsigned long fdes_end;
fdes_end = sec->fdes_start + (sec->num_fdes * sizeof(struct sframe_fde_v3));
- dbg("SEC: sframe:0x%lx-0x%lx text:0x%lx-0x%lx "
- "fdes:0x%lx-0x%lx fres:0x%lx-0x%lx "
- "ra_off:%d fp_off:%d\n",
- sec->sframe_start, sec->sframe_end, sec->text_start, sec->text_end,
- sec->fdes_start, fdes_end, sec->fres_start, sec->fres_end,
- sec->ra_off, sec->fp_off);
+ dbg_sec("SEC: sframe:0x%lx-0x%lx text:0x%lx-0x%lx "
+ "fdes:0x%lx-0x%lx fres:0x%lx-0x%lx "
+ "ra_off:%d fp_off:%d\n",
+ sec->sframe_start, sec->sframe_end, sec->text_start, sec->text_end,
+ sec->fdes_start, fdes_end, sec->fres_start, sec->fres_end,
+ sec->ra_off, sec->fp_off);
+}
+
+static inline void dbg_init(struct sframe_section *sec)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+
+ guard(mmap_read_lock)(mm);
+ vma = vma_lookup(mm, sec->sframe_start);
+ if (!vma)
+ sec->filename = kstrdup("(vma gone???)", GFP_KERNEL);
+ else if (vma->vm_file)
+ sec->filename = kstrdup_quotable_file(vma->vm_file, GFP_KERNEL);
+ else if (vma->vm_ops && vma->vm_ops->name)
+ sec->filename = kstrdup(vma->vm_ops->name(vma), GFP_KERNEL);
+ else if (arch_vma_name(vma))
+ sec->filename = kstrdup(arch_vma_name(vma), GFP_KERNEL);
+ else if (!vma->vm_mm)
+ sec->filename = kstrdup("(vdso)", GFP_KERNEL);
+ else
+ sec->filename = kstrdup("(anonymous)", GFP_KERNEL);
+}
+
+static inline void dbg_free(struct sframe_section *sec)
+{
+ kfree(sec->filename);
}
#else /* !CONFIG_DYNAMIC_DEBUG */
#define dbg(args...) no_printk(args)
+#define dbg_sec(args...) no_printk(args)
static inline void dbg_print_header(struct sframe_section *sec) {}
+static inline void dbg_init(struct sframe_section *sec) {}
+static inline void dbg_free(struct sframe_section *sec) {}
+
#endif /* !CONFIG_DYNAMIC_DEBUG */
#endif /* _SFRAME_DEBUG_H */
--
2.51.0
^ permalink raw reply related
* [PATCH v14 19/19] unwind_user/sframe: Add prctl() interface for registering .sframe sections
From: Jens Remus @ 2026-05-05 12:17 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505121718.3572346-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
The kernel doesn't have direct visibility to the ELF contents of shared
libraries. Add some prctl() interfaces which allow glibc to tell the
kernel where to find .sframe sections.
[
This adds an interface for prctl() for testing loading of sframes for
libraries. But this interface should really be a system call. This patch
is for testing purposes only and should not be applied to mainline.
]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Indu Bhagat <ibhagatgnu@gmail.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
Notes (jremus):
Changes in v14:
- Bump PR_ADD_SFRAME and PR_REMOVE_SFRAME.
include/uapi/linux/prctl.h | 6 +++++-
kernel/sys.c | 8 ++++++++
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index b6ec6f693719..0aa0ec971843 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -368,7 +368,7 @@ struct prctl_mm_map {
* configuration. All bits may be locked via this call, including
* undefined bits.
*/
-#define PR_LOCK_SHADOW_STACK_STATUS 76
+#define PR_LOCK_SHADOW_STACK_STATUS 76
/*
* Controls the mode of timer_create() for CRIU restore operations.
@@ -416,4 +416,8 @@ struct prctl_mm_map {
# define PR_CFI_DISABLE _BITUL(1)
# define PR_CFI_LOCK _BITUL(2)
+/* SFRAME management */
+#define PR_ADD_SFRAME 82
+#define PR_REMOVE_SFRAME 83
+
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 62e842055cc9..6e81e82bc991 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -65,6 +65,7 @@
#include <linux/rcupdate.h>
#include <linux/uidgid.h>
#include <linux/cred.h>
+#include <linux/sframe.h>
#include <linux/nospec.h>
@@ -2906,6 +2907,13 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
break;
if (arg3 & PR_CFI_LOCK && !(arg3 & PR_CFI_DISABLE))
error = arch_prctl_lock_branch_landing_pad_state(me);
+ case PR_ADD_SFRAME:
+ error = sframe_add_section(arg2, arg3, arg4, arg5);
+ break;
+ case PR_REMOVE_SFRAME:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = sframe_remove_section(arg2);
break;
default:
trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5);
--
2.51.0
^ permalink raw reply related
* [PATCH v14 12/19] unwind_user/sframe: Add .sframe validation option
From: Jens Remus @ 2026-05-05 12:17 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505121718.3572346-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
Add a debug feature to validate all .sframe sections when first loading
the file rather than on demand.
[ Jens Remus: Add support for SFrame V3. Add support for PC-relative
FDE function start offset. Adjust to rename of struct sframe_fre to
sframe_fre_internal. Use %#x/%#lx format specifiers. ]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Indu Bhagat <ibhagatgnu@gmail.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
Notes (jremus):
Changes in v14:
- Add debug message if safe_read_fde() fails.
- Update function names in debug messages.
- Uppercase terms FDE and FRE in debug messages.
Changes in v13:
- Update to SFrame V3:
- Print struct sframe_fde_internal fields fda_off and info2 in debug
message.
- Adjust to rename of struct sframe_fde_internal field func_start_addr
to func_addr.
- Use format strings "%#x" and "%#lx" instead of "0x%x" and "0x%lx".
- Reword commit message (my changes).
arch/Kconfig | 19 ++++++++
kernel/unwind/sframe.c | 101 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 120 insertions(+)
diff --git a/arch/Kconfig b/arch/Kconfig
index 37549832bd1f..132249d342a3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -490,6 +490,25 @@ config HAVE_UNWIND_USER_SFRAME
bool
select UNWIND_USER
+config SFRAME_VALIDATION
+ bool "Enable .sframe section debugging"
+ depends on HAVE_UNWIND_USER_SFRAME
+ depends on DYNAMIC_DEBUG
+ help
+ When adding an .sframe section for a task, validate the entire
+ section immediately rather than on demand.
+
+ This is a debug feature which is helpful for rooting out .sframe
+ section issues. If the .sframe section is corrupt, it will fail to
+ load immediately, with more information provided in dynamic printks.
+
+ This has a significant page cache footprint due to its reading of the
+ entire .sframe section for every loaded executable and shared
+ library. Also, it's done for all processes, even those which don't
+ get stack traced by the kernel. Not recommended for general use.
+
+ If unsure, say N.
+
config HAVE_PERF_REGS
bool
help
diff --git a/kernel/unwind/sframe.c b/kernel/unwind/sframe.c
index 4419626f0173..45988cdc5c37 100644
--- a/kernel/unwind/sframe.c
+++ b/kernel/unwind/sframe.c
@@ -367,6 +367,103 @@ int sframe_find(unsigned long ip, struct unwind_user_frame *frame)
return ret;
}
+#ifdef CONFIG_SFRAME_VALIDATION
+
+static int safe_read_fde(struct sframe_section *sec,
+ unsigned int fde_num, struct sframe_fde_internal *fde)
+{
+ int ret;
+
+ if (!user_read_access_begin((void __user *)sec->sframe_start,
+ sec->sframe_end - sec->sframe_start))
+ return -EFAULT;
+ ret = __read_fde(sec, fde_num, fde);
+ user_read_access_end();
+ return ret;
+}
+
+static int safe_read_fre(struct sframe_section *sec,
+ struct sframe_fde_internal *fde,
+ unsigned long fre_addr,
+ struct sframe_fre_internal *fre)
+{
+ int ret;
+
+ if (!user_read_access_begin((void __user *)sec->sframe_start,
+ sec->sframe_end - sec->sframe_start))
+ return -EFAULT;
+ ret = __read_fre(sec, fde, fre_addr, fre);
+ user_read_access_end();
+ return ret;
+}
+
+static int sframe_validate_section(struct sframe_section *sec)
+{
+ unsigned long prev_ip = 0;
+ unsigned int i;
+
+ for (i = 0; i < sec->num_fdes; i++) {
+ struct sframe_fre_internal *fre, *prev_fre = NULL;
+ unsigned long ip, fre_addr;
+ struct sframe_fde_internal fde;
+ struct sframe_fre_internal fres[2];
+ bool which = false;
+ unsigned int j;
+ int ret;
+
+ ret = safe_read_fde(sec, i, &fde);
+ if (ret) {
+ dbg_sec("safe_read_fde(%u) failed\n", i);
+ return ret;
+ }
+
+ ip = fde.func_addr;
+ if (ip <= prev_ip) {
+ dbg_sec("FDE %u not sorted\n", i);
+ return -EFAULT;
+ }
+ prev_ip = ip;
+
+ fre_addr = sec->fres_start + fde.fres_off;
+ for (j = 0; j < fde.fres_num; j++) {
+ int ret;
+
+ fre = which ? fres : fres + 1;
+ which = !which;
+
+ ret = safe_read_fre(sec, &fde, fre_addr, fre);
+ if (ret) {
+ dbg_sec("FDE %u: safe_read_fre(%u) failed\n", i, j);
+ dbg_sec("FDE: func_addr:%#lx func_size:%#x fda_off:%#x fres_off:%#x fres_num:%d info:%u info2:%u rep_size:%u\n",
+ fde.func_addr, fde.func_size,
+ fde.fda_off,
+ fde.fres_off, fde.fres_num,
+ fde.info, fde.info2,
+ fde.rep_size);
+ return ret;
+ }
+
+ fre_addr += fre->size;
+
+ if (prev_fre && fre->ip_off <= prev_fre->ip_off) {
+ dbg_sec("FDE %u: FRE %u not sorted\n", i, j);
+ return -EFAULT;
+ }
+
+ prev_fre = fre;
+ }
+ }
+
+ return 0;
+}
+
+#else /* !CONFIG_SFRAME_VALIDATION */
+
+static int sframe_validate_section(struct sframe_section *sec) { return 0; }
+
+#endif /* !CONFIG_SFRAME_VALIDATION */
+
+
static void free_section(struct sframe_section *sec)
{
dbg_free(sec);
@@ -476,6 +573,10 @@ int sframe_add_section(unsigned long sframe_start, unsigned long sframe_end,
goto err_free;
}
+ ret = sframe_validate_section(sec);
+ if (ret)
+ goto err_free;
+
ret = mtree_insert_range(sframe_mt, sec->text_start, sec->text_end, sec, GFP_KERNEL);
if (ret) {
dbg_sec("mtree_insert_range failed: text=%lx-%lx\n",
--
2.51.0
^ permalink raw reply related
* [PATCH v14 18/19] unwind_user/sframe/x86: Enable sframe unwinding on x86
From: Jens Remus @ 2026-05-05 12:17 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505121718.3572346-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
The x86 SFrame V3 implementation works fairly well, starting with
binutils 2.46. Enable it.
[ Jens Remus: Reword commit message for SFrame V3, starting with
binutils 2.46. ]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Indu Bhagat <ibhagatgnu@gmail.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
Notes (jremus):
Changes in v14:
- Drop superfluous empty line in unwind_user_get_reg().
Changes in v13:
- Naive implementation of unwind_user_get_reg() to support SFrame V3
flexible FDEs (e.g. used to represent DRAP pattern).
- Define SFRAME_REG_SP and SFRAME_REG_FP to the respective x86-64
DWARF register numbers.
- Reword commit message for SFrame V3 and (upcoming) binutils 2.46.
arch/x86/Kconfig | 1 +
arch/x86/include/asm/unwind_user.h | 33 +++++++++++++++++++++++
arch/x86/include/asm/unwind_user_sframe.h | 12 +++++++++
3 files changed, 46 insertions(+)
create mode 100644 arch/x86/include/asm/unwind_user_sframe.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f3f7cb01d69d..51286dfdb5f4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -302,6 +302,7 @@ config X86
select HAVE_UACCESS_VALIDATION if HAVE_OBJTOOL
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_UNWIND_USER_FP if X86_64
+ select HAVE_UNWIND_USER_SFRAME if X86_64
select HAVE_USER_RETURN_NOTIFIER
select HAVE_GENERIC_VDSO
select VDSO_GETRANDOM if X86_64
diff --git a/arch/x86/include/asm/unwind_user.h b/arch/x86/include/asm/unwind_user.h
index f38f7c5ff1de..b80f0ec0f7a7 100644
--- a/arch/x86/include/asm/unwind_user.h
+++ b/arch/x86/include/asm/unwind_user.h
@@ -15,6 +15,39 @@ static inline int unwind_user_word_size(struct pt_regs *regs)
return user_64bit_mode(regs) ? 8 : 4;
}
+static inline int unwind_user_get_reg(unsigned long *val, unsigned int regnum)
+{
+#ifdef CONFIG_X86_64
+ const struct pt_regs *regs = task_pt_regs(current);
+
+ switch (regnum) {
+ /* DWARF register numbers 0..15 */
+ case 0: *val = regs->ax; break;
+ case 1: *val = regs->dx; break;
+ case 2: *val = regs->cx; break;
+ case 3: *val = regs->bx; break;
+ case 4: *val = regs->si; break;
+ case 5: *val = regs->di; break;
+ case 6: *val = regs->bp; break;
+ case 7: *val = regs->sp; break;
+ case 8: *val = regs->r8; break;
+ case 9: *val = regs->r9; break;
+ case 10: *val = regs->r10; break;
+ case 11: *val = regs->r11; break;
+ case 12: *val = regs->r12; break;
+ case 13: *val = regs->r13; break;
+ case 14: *val = regs->r14; break;
+ case 15: *val = regs->r15; break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+#else /* !CONFIG_X86_64 */
+ return -EINVAL;
+#endif /* !CONFIG_X86_64 */
+}
+#define unwind_user_get_reg unwind_user_get_reg
+
#endif /* CONFIG_UNWIND_USER */
#ifdef CONFIG_HAVE_UNWIND_USER_FP
diff --git a/arch/x86/include/asm/unwind_user_sframe.h b/arch/x86/include/asm/unwind_user_sframe.h
new file mode 100644
index 000000000000..d828ae1a4aac
--- /dev/null
+++ b/arch/x86/include/asm/unwind_user_sframe.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_UNWIND_USER_SFRAME_H
+#define _ASM_X86_UNWIND_USER_SFRAME_H
+
+#ifdef CONFIG_X86_64
+
+#define SFRAME_REG_SP 7
+#define SFRAME_REG_FP 6
+
+#endif
+
+#endif /* _ASM_X86_UNWIND_USER_SFRAME_H */
--
2.51.0
^ permalink raw reply related
* [PATCH v14 00/19] unwind_deferred: Implement sframe handling
From: Jens Remus @ 2026-05-05 12:16 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich
This is the implementation of parsing the SFrame V3 stack trace information
from an .sframe section in an ELF file. It's a continuation of Josh's and
Steve's work that can be found here:
https://lore.kernel.org/all/cover.1737511963.git.jpoimboe@kernel.org/
https://lore.kernel.org/all/20250827201548.448472904@kernel.org/
Currently the only way to get a user space stack trace from a stack
walk (and not just copying large amount of user stack into the kernel
ring buffer) is to use frame pointers. This has a few issues. The biggest
one is that compiling frame pointers into every application and library
has been shown to cause performance overhead.
Another issue is that the format of the frames may not always be consistent
between different compilers and some architectures (s390) has no defined
format to do a reliable stack walk. The only way to perform user space
profiling on these architectures is to copy the user stack into the kernel
buffer.
SFrame [1] is now supported in binutils (x86-64, ARM64, and s390). There is
discussions going on about supporting SFrame in LLVM. SFrame acts more like
ORC, and lives in the ELF executable file as its own section. Like ORC it
has two tables where the first table is sorted by instruction pointers (IP)
and using the current IP and finding it's entry in the first table, it will
take you to the second table which will tell you where the return address
of the current function is located and then you can use that address to
look it up in the first table to find the return address of that function,
and so on. This performs a user space stack walk.
Now because the .sframe section lives in the ELF file it needs to be faulted
into memory when it is used. This means that walking the user space stack
requires being in a faultable context. As profilers like perf request a stack
trace in interrupt or NMI context, it cannot do the walking when it is
requested. Instead it must be deferred until it is safe to fault in user
space. One place this is known to be safe is when the task is about to return
back to user space.
This series makes the deferred unwind user code implement SFrame format V3
and enables it on x86-64.
[1]: https://sourceware.org/binutils/wiki/sframe
This series applies on top of v7.1-rc2 tag:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git v7.1-rc2
The to be stack-traced user space programs (and libraries) need to be
built with the recent SFrame stack trace information format V3, as
generated by binutils 2.46+ with assembler option --gsframe-3.
Namhyung Kim's related perf tools deferred callchain support can be used
for testing ("perf record --call-graph fp,defer" and "perf report/script").
Changes since v13 (see patch notes for details):
- Rebase on v7.1-rc2.
- Correct SFRAME_V3_FDE_TYPE_MASK value.
- Fix FDE function start address check in __read_fde().
- Rename SFrame V3 definitions accoring to final specification. (Indu)
- Improve comments on why UNWIND_USER_RULE_CFA_OFFSET is not
implemented. (Mark Rutland)
- Add/update/improve sframe debug messages.
- Add generic and arch-specific unwind_user.h to MAINTAINERS.
- Add arch-specific unwind_user_sframe.h to MAINTAINERS.
Changes since v12 (see patch notes for details):
- Add support for SFrame V3, including its new flexible FDEs. SFrame V2
is not supported.
Changes since v11 (see patch notes for details):
- Adjust to Peter's latest undwind user enhancements.
- Simplify logic by using an internal SFrame FDE representation, whose
FDE function start address field is an address instead of a PC-relative
offset (from FDE).
- Rename struct sframe_fre to sframe_fre_internal to align with
struct sframe_fde_internal.
- Remove unused pt_regs from unwind_user_next_common() and its
callers. (Peter)
- Simplify unwind_user_next_sframe(). (Peter)
- Fix a few checkpatch errors and warnings.
- Minor cleanups (e.g. move includes, fix indentation).
Changes since v10:
- Support for SFrame V2 PC-relative FDE function start address.
- Support for SFrame V2 representing RA undefined as indication for
outermost frames.
Patch 1 (new), as a preparatory cleanup, adds the generic and arch-specific
unwind_user.h to MAINTAINERS.
Patches 2, 5, 12, and 18 have been updated to exclusively support the
latest SFrame V3 stack trace information format, that is generated by
binutils 2.46+. Old SFrame V2 sections get rejected with dynamic debug
message "bad/unsupported sframe header".
Patches 8 and 9 add support to unwind user (sframe) for outermost frames.
Patches 13-16 add support to unwind user (sframe) for the new SFrame V3
flexible FDEs.
Patch 17 improves the performance of searching the SFrame FRE for an IP.
Regards,
Jens
Jens Remus (8):
unwind_user: Add generic and arch-specific headers to MAINTAINERS
unwind_user: Stop when reaching an outermost frame
unwind_user/sframe: Add support for outermost frame indication
unwind_user: Enable archs that pass RA in a register
unwind_user: Flexible FP/RA recovery rules
unwind_user: Flexible CFA recovery rules
unwind_user/sframe: Add support for SFrame V3 flexible FDEs
unwind_user/sframe: Separate reading of FRE from reading of FRE data
words
Josh Poimboeuf (11):
unwind_user/sframe: Add support for reading .sframe headers
unwind_user/sframe: Store .sframe section data in per-mm maple tree
x86/uaccess: Add unsafe_copy_from_user() implementation
unwind_user/sframe: Add support for reading .sframe contents
unwind_user/sframe: Detect .sframe sections in executables
unwind_user/sframe: Wire up unwind_user to sframe
unwind_user/sframe: Remove .sframe section on detected corruption
unwind_user/sframe: Show file name in debug output
unwind_user/sframe: Add .sframe validation option
unwind_user/sframe/x86: Enable sframe unwinding on x86
unwind_user/sframe: Add prctl() interface for registering .sframe
sections
MAINTAINERS | 4 +
arch/Kconfig | 23 +
arch/x86/Kconfig | 1 +
arch/x86/include/asm/mmu.h | 2 +-
arch/x86/include/asm/uaccess.h | 39 +-
arch/x86/include/asm/unwind_user.h | 68 +-
arch/x86/include/asm/unwind_user_sframe.h | 12 +
fs/binfmt_elf.c | 48 +-
include/linux/mm_types.h | 3 +
include/linux/sframe.h | 60 ++
include/linux/unwind_user.h | 18 +
include/linux/unwind_user_types.h | 46 +-
include/uapi/linux/elf.h | 1 +
include/uapi/linux/prctl.h | 6 +-
kernel/fork.c | 10 +
kernel/sys.c | 8 +
kernel/unwind/Makefile | 3 +-
kernel/unwind/sframe.c | 842 ++++++++++++++++++++++
kernel/unwind/sframe.h | 87 +++
kernel/unwind/sframe_debug.h | 68 ++
kernel/unwind/user.c | 111 ++-
mm/init-mm.c | 2 +
22 files changed, 1423 insertions(+), 39 deletions(-)
create mode 100644 arch/x86/include/asm/unwind_user_sframe.h
create mode 100644 include/linux/sframe.h
create mode 100644 kernel/unwind/sframe.c
create mode 100644 kernel/unwind/sframe.h
create mode 100644 kernel/unwind/sframe_debug.h
--
2.51.0
^ permalink raw reply
* [PATCH v14 06/19] unwind_user/sframe: Detect .sframe sections in executables
From: Jens Remus @ 2026-05-05 12:17 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, x86, Steven Rostedt,
Josh Poimboeuf, Indu Bhagat, Peter Zijlstra, Dylan Hatch,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H. Peter Anvin, Mathieu Desnoyers, Kees Cook, Sam James
Cc: Jens Remus, bpf, linux-mm, Namhyung Kim, Andrii Nakryiko,
Jose E. Marchesi, Beau Belgrave, Florian Weimer,
Carlos O'Donell, Masami Hiramatsu, Jiri Olsa,
Arnaldo Carvalho de Melo, Andrew Morton, David Hildenbrand,
Lorenzo Stoakes, Liam R. Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Heiko Carstens, Vasily Gorbik,
Ilya Leoshkevich, Steven Rostedt (Google)
In-Reply-To: <20260505121718.3572346-1-jremus@linux.ibm.com>
From: Josh Poimboeuf <jpoimboe@kernel.org>
When loading an ELF executable, automatically detect an .sframe section
and associate it with the mm_struct.
[ Jens Remus: Fix checkpatch warning "braces {} are not necessary for
single statement blocks". ]
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Reviewed-by: Indu Bhagat <ibhagatgnu@gmail.com>
Signed-off-by: Jens Remus <jremus@linux.ibm.com>
---
fs/binfmt_elf.c | 48 +++++++++++++++++++++++++++++++++++++---
include/uapi/linux/elf.h | 1 +
2 files changed, 46 insertions(+), 3 deletions(-)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 16a56b6b3f6c..55047659a3cf 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -48,6 +48,7 @@
#include <linux/uaccess.h>
#include <uapi/linux/rseq.h>
#include <linux/rseq.h>
+#include <linux/sframe.h>
#include <asm/param.h>
#include <asm/page.h>
@@ -637,6 +638,21 @@ static inline int make_prot(u32 p_flags, struct arch_elf_state *arch_state,
return arch_elf_adjust_prot(prot, arch_state, has_interp, is_interp);
}
+static void elf_add_sframe(struct elf_phdr *text, struct elf_phdr *sframe,
+ unsigned long base_addr)
+{
+ unsigned long sframe_start, sframe_end, text_start, text_end;
+
+ sframe_start = base_addr + sframe->p_vaddr;
+ sframe_end = sframe_start + sframe->p_memsz;
+
+ text_start = base_addr + text->p_vaddr;
+ text_end = text_start + text->p_memsz;
+
+ /* Ignore return value, sframe section isn't critical */
+ sframe_add_section(sframe_start, sframe_end, text_start, text_end);
+}
+
/* This is much more generalized than the library routine read function,
so we keep this separate. Technically the library read function
is only provided so that we can read a.out libraries that have
@@ -647,7 +663,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
unsigned long no_base, struct elf_phdr *interp_elf_phdata,
struct arch_elf_state *arch_state)
{
- struct elf_phdr *eppnt;
+ struct elf_phdr *eppnt, *sframe_phdr = NULL;
unsigned long load_addr = 0;
int load_addr_set = 0;
unsigned long error = ~0UL;
@@ -673,7 +689,8 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
eppnt = interp_elf_phdata;
for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
- if (eppnt->p_type == PT_LOAD) {
+ switch (eppnt->p_type) {
+ case PT_LOAD: {
int elf_type = MAP_PRIVATE;
int elf_prot = make_prot(eppnt->p_flags, arch_state,
true, true);
@@ -712,6 +729,19 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
error = -ENOMEM;
goto out;
}
+ break;
+ }
+ case PT_GNU_SFRAME:
+ sframe_phdr = eppnt;
+ break;
+ }
+ }
+
+ if (sframe_phdr) {
+ eppnt = interp_elf_phdata;
+ for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
+ if (eppnt->p_flags & PF_X)
+ elf_add_sframe(eppnt, sframe_phdr, load_addr);
}
}
@@ -836,7 +866,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
int first_pt_load = 1;
unsigned long error;
struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
- struct elf_phdr *elf_property_phdata = NULL;
+ struct elf_phdr *elf_property_phdata = NULL, *sframe_phdr = NULL;
unsigned long elf_brk;
bool brk_moved = false;
int retval, i;
@@ -945,6 +975,10 @@ static int load_elf_binary(struct linux_binprm *bprm)
executable_stack = EXSTACK_DISABLE_X;
break;
+ case PT_GNU_SFRAME:
+ sframe_phdr = elf_ppnt;
+ break;
+
case PT_LOPROC ... PT_HIPROC:
retval = arch_elf_pt_proc(elf_ex, elf_ppnt,
bprm->file, false,
@@ -1242,6 +1276,14 @@ static int load_elf_binary(struct linux_binprm *bprm)
elf_brk = k;
}
+ if (sframe_phdr) {
+ for (i = 0, elf_ppnt = elf_phdata;
+ i < elf_ex->e_phnum; i++, elf_ppnt++) {
+ if ((elf_ppnt->p_flags & PF_X))
+ elf_add_sframe(elf_ppnt, sframe_phdr, load_bias);
+ }
+ }
+
e_entry = elf_ex->e_entry + load_bias;
phdr_addr += load_bias;
elf_brk += load_bias;
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index ee30dcd80901..e2a7dbed2e80 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -41,6 +41,7 @@ typedef __u16 Elf64_Versym;
#define PT_GNU_STACK (PT_LOOS + 0x474e551)
#define PT_GNU_RELRO (PT_LOOS + 0x474e552)
#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553)
+#define PT_GNU_SFRAME (PT_LOOS + 0x474e554)
/* ARM MTE memory tag segment type */
--
2.51.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox