Skip to contentSkip to conversation

lib/atomic64: ring-buffer: Fix infinite recursion on some 32bit archs

PATCH In review Steven Rostedt 2 participants 5 messages Jan 20, 2025 – Jan 21, 2025

Subsystems (4)
lore
Share & tools
lore

Steven Rostedt

author maintainer
#0 lore raw

cover lib/atomic64: ring-buffer: Fix infinite recursion on some 32bit archs

It was reported that the tracing ring buffer code would cause an infinite recursion and crash on risc32 and sparc32 architectures. The reason is that they use the generic atomic64 operations which call raw_spin_locks. As raw_spin_locks can be traced this would cause an infinite recursion, because the atomic64 operations call raw_spin_locks. Instead, the generic atomic64 operations should be calling arch_spin_locks as this is architecture specific implementation and the locks that are taken should never have any other locks taken while they are held, and are always taking with interrupts disabled. This means they do not need to be tested by lockdep either.

Another issue was that locks should not be taken in NMI context and the ring buffer can be called in NMI. If the arch uses the generic atomic64 operations, do not allow events to be recorded in NMI as the atomic64 operations are not safe in NMI context.

Steven Rostedt (2):
ring-buffer: Do not allow events in NMI with generic atomic64 cmpxchg()
atomic64: Use arch_spin_locks instead of raw_spin_locks

----

 kernel/trace/ring_buffer.c |  9 ++++--
 lib/atomic64.c             | 78 ++++++++++++++++++++++++++++------------------
 2 files changed, 55 insertions(+), 32 deletions(-)
author maintainer
#1 lore raw

PATCH 1/2 ring-buffer: Do not allow events in NMI with generic atomic64 cmpxchg()

From: Steven Rostedt <[email protected]>

Some architectures can not safely do atomic64 operations in NMI context. Since the ring buffer relies on atomic64 operations to do its time keeping, if an event is requested in NMI context, reject it for these architectures.

Fixes c84897c0ff592 ("ring-buffer: Remove 32bit timestamp logic")
---
 kernel/trace/ring_buffer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
kernel/trace/ring_buffer.c +7 -2
index 6d61ff78926b..b8e0ae15ca5b 100644
@@ -4398,8 +4398,13 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	int nr_loops = 0;
 	int add_ts_default;
 
-	/* ring buffer does cmpxchg, make sure it is safe in NMI context */
-	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+	/*
+	 * ring buffer does cmpxchg as well as atomic64 operations
+	 * (which some archs use locking for atomic64), make sure this
+	 * is safe in NMI context
+	 */
+	if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) ||
+	     IS_ENABLED(CONFIG_GENERIC_ATOMIC64)) &&
 	    (unlikely(in_nmi()))) {
 		return NULL;
 	}
Signature · 1 line
2.45.2
maintainer Reviewed-by on v1 1/2
#2 lore raw

Re: [PATCH 1/2] ring-buffer: Do not allow events in NMI with generic atomic64 cmpxchg()

Quoted 7 lines · On Mon, 20 Jan 2025 18:56:56 -0500 Steven Rostedt <[email protected]> wrote:

From: Steven Rostedt <[email protected]>

Some architectures can not safely do atomic64 operations in NMI context. Since the ring buffer relies on atomic64 operations to do its time keeping, if an event is requested in NMI context, reject it for these architectures.

Looks good to me.

Quoted 33 lines
Fixes c84897c0ff592 ("ring-buffer: Remove 32bit timestamp logic")
---
 kernel/trace/ring_buffer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
kernel/trace/ring_buffer.c +7 -2
index 6d61ff78926b..b8e0ae15ca5b 100644
@@ -4398,8 +4398,13 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	int nr_loops = 0;
 	int add_ts_default;
 
-	/* ring buffer does cmpxchg, make sure it is safe in NMI context */
-	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+	/*
+	 * ring buffer does cmpxchg as well as atomic64 operations
+	 * (which some archs use locking for atomic64), make sure this
+	 * is safe in NMI context
+	 */
+	if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) ||
+	     IS_ENABLED(CONFIG_GENERIC_ATOMIC64)) &&
 	    (unlikely(in_nmi()))) {
 		return NULL;
 	}
Signature · 1 line
2.45.2
Signature · 1 line
Masami Hiramatsu (Google) <[email protected]>
author maintainer
#3 lore raw

PATCH 2/2 atomic64: Use arch_spin_locks instead of raw_spin_locks

In reply to Steven Rostedt

From: Steven Rostedt <[email protected]>

raw_spin_locks can be traced by lockdep or tracing itself. Atomic64 operations can be used in the tracing infrastructure. When an architecture does not have true atomic64 operations it can use the generic version that disables interrupts and uses spin_locks.

The tracing ring buffer code uses atomic64 operations for the time keeping. But because some architectures use the default operations, the locking inside the atomic operations can cause an infinite recursion.

As atomic64 is an architecture specific operation, it should not be using raw_spin_locks() but instead arch_spin_locks as that is the purpose of arch_spin_locks. To be used in architecture specific implementations of generic infrastructure like atomic64 operations.

Fixes c84897c0ff592 ("ring-buffer: Remove 32bit timestamp logic")
---
 lib/atomic64.c | 78 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 48 insertions(+), 30 deletions(-)
lib/atomic64.c +48 -30
index caf895789a1e..1a72bba36d24 100644
@@ -25,15 +25,15 @@
  * Ensure each lock is in a separate cacheline.
  */
 static union {
-	raw_spinlock_t lock;
+	arch_spinlock_t lock;
 	char pad[L1_CACHE_BYTES];
 } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp = {
 	[0 ... (NR_LOCKS - 1)] = {
-		.lock =  __RAW_SPIN_LOCK_UNLOCKED(atomic64_lock.lock),
+		.lock =  __ARCH_SPIN_LOCK_UNLOCKED,
 	},
 };
 
-static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
+static inline arch_spinlock_t *lock_addr(const atomic64_t *v)
 {
 	unsigned long addr = (unsigned long) v;
 
@@ -45,12 +45,14 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 s64 generic_atomic64_read(const atomic64_t *v)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_read);
@@ -58,11 +60,13 @@ EXPORT_SYMBOL(generic_atomic64_read);
 void generic_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	v->counter = i;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(generic_atomic64_set);
 
@@ -70,11 +74,13 @@ EXPORT_SYMBOL(generic_atomic64_set);
 void generic_atomic64_##op(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
-	raw_spinlock_t *lock = lock_addr(v);				\
+	arch_spinlock_t *lock = lock_addr(v);				\
 									\
-	raw_spin_lock_irqsave(lock, flags);				\
+	local_irq_save(flags);						\
+	arch_spin_lock(lock);						\
 	v->counter c_op a;						\
-	raw_spin_unlock_irqrestore(lock, flags);			\
+	arch_spin_unlock(lock);						\
+	local_irq_restore(flags);					\
 }									\
 EXPORT_SYMBOL(generic_atomic64_##op);
 
@@ -82,12 +88,14 @@ EXPORT_SYMBOL(generic_atomic64_##op);
 s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v)		\
 {									\
 	unsigned long flags;						\
-	raw_spinlock_t *lock = lock_addr(v);				\
+	arch_spinlock_t *lock = lock_addr(v);				\
 	s64 val;							\
 									\
-	raw_spin_lock_irqsave(lock, flags);				\
+	local_irq_save(flags);						\
+	arch_spin_lock(lock);						\
 	val = (v->counter c_op a);					\
-	raw_spin_unlock_irqrestore(lock, flags);			\
+	arch_spin_unlock(lock);						\
+	local_irq_restore(flags);					\
 	return val;							\
 }									\
 EXPORT_SYMBOL(generic_atomic64_##op##_return);
@@ -96,13 +104,15 @@ EXPORT_SYMBOL(generic_atomic64_##op##_return);
 s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
-	raw_spinlock_t *lock = lock_addr(v);				\
+	arch_spinlock_t *lock = lock_addr(v);				\
 	s64 val;							\
 									\
-	raw_spin_lock_irqsave(lock, flags);				\
+	local_irq_save(flags);						\
+	arch_spin_lock(lock);						\
 	val = v->counter;						\
 	v->counter c_op a;						\
-	raw_spin_unlock_irqrestore(lock, flags);			\
+	arch_spin_unlock(lock);						\
+	local_irq_restore(flags);					\
 	return val;							\
 }									\
 EXPORT_SYMBOL(generic_atomic64_fetch_##op);
@@ -131,14 +141,16 @@ ATOMIC64_OPS(xor, ^=)
 s64 generic_atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter - 1;
 	if (val >= 0)
 		v->counter = val;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_dec_if_positive);
@@ -146,14 +158,16 @@ EXPORT_SYMBOL(generic_atomic64_dec_if_positive);
 s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
 	if (val == o)
 		v->counter = n;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_cmpxchg);
@@ -161,13 +175,15 @@ EXPORT_SYMBOL(generic_atomic64_cmpxchg);
 s64 generic_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
 	v->counter = new;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_xchg);
@@ -175,14 +191,16 @@ EXPORT_SYMBOL(generic_atomic64_xchg);
 s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
 	if (val != u)
 		v->counter += a;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 
 	return val;
 }
Signature · 1 line
2.45.2
maintainer Reviewed-by on v1 2/2
#4 lore raw

Re: [PATCH 2/2] atomic64: Use arch_spin_locks instead of raw_spin_locks

Quoted 7 lines · On Mon, 20 Jan 2025 18:56:57 -0500 Steven Rostedt <[email protected]> wrote:

From: Steven Rostedt <[email protected]>

raw_spin_locks can be traced by lockdep or tracing itself. Atomic64 operations can be used in the tracing infrastructure. When an architecture does not have true atomic64 operations it can use the generic version that disables interrupts and uses spin_locks.

Quoted 9 lines

The tracing ring buffer code uses atomic64 operations for the time keeping. But because some architectures use the default operations, the locking inside the atomic operations can cause an infinite recursion.

As atomic64 is an architecture specific operation, it should not be using raw_spin_locks() but instead arch_spin_locks as that is the purpose of arch_spin_locks. To be used in architecture specific implementations of generic infrastructure like atomic64 operations.

Looks good to me.

Thanks,

Quoted 204 lines
Fixes c84897c0ff592 ("ring-buffer: Remove 32bit timestamp logic")
---
 lib/atomic64.c | 78 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 48 insertions(+), 30 deletions(-)
lib/atomic64.c +48 -30
index caf895789a1e..1a72bba36d24 100644
@@ -25,15 +25,15 @@
  * Ensure each lock is in a separate cacheline.
  */
 static union {
-	raw_spinlock_t lock;
+	arch_spinlock_t lock;
 	char pad[L1_CACHE_BYTES];
 } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp = {
 	[0 ... (NR_LOCKS - 1)] = {
-		.lock =  __RAW_SPIN_LOCK_UNLOCKED(atomic64_lock.lock),
+		.lock =  __ARCH_SPIN_LOCK_UNLOCKED,
 	},
 };
 
-static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
+static inline arch_spinlock_t *lock_addr(const atomic64_t *v)
 {
 	unsigned long addr = (unsigned long) v;
 
@@ -45,12 +45,14 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 s64 generic_atomic64_read(const atomic64_t *v)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_read);
@@ -58,11 +60,13 @@ EXPORT_SYMBOL(generic_atomic64_read);
 void generic_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	v->counter = i;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(generic_atomic64_set);
 
@@ -70,11 +74,13 @@ EXPORT_SYMBOL(generic_atomic64_set);
 void generic_atomic64_##op(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
-	raw_spinlock_t *lock = lock_addr(v);				\
+	arch_spinlock_t *lock = lock_addr(v);				\
 									\
-	raw_spin_lock_irqsave(lock, flags);				\
+	local_irq_save(flags);						\
+	arch_spin_lock(lock);						\
 	v->counter c_op a;						\
-	raw_spin_unlock_irqrestore(lock, flags);			\
+	arch_spin_unlock(lock);						\
+	local_irq_restore(flags);					\
 }									\
 EXPORT_SYMBOL(generic_atomic64_##op);
 
@@ -82,12 +88,14 @@ EXPORT_SYMBOL(generic_atomic64_##op);
 s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v)		\
 {									\
 	unsigned long flags;						\
-	raw_spinlock_t *lock = lock_addr(v);				\
+	arch_spinlock_t *lock = lock_addr(v);				\
 	s64 val;							\
 									\
-	raw_spin_lock_irqsave(lock, flags);				\
+	local_irq_save(flags);						\
+	arch_spin_lock(lock);						\
 	val = (v->counter c_op a);					\
-	raw_spin_unlock_irqrestore(lock, flags);			\
+	arch_spin_unlock(lock);						\
+	local_irq_restore(flags);					\
 	return val;							\
 }									\
 EXPORT_SYMBOL(generic_atomic64_##op##_return);
@@ -96,13 +104,15 @@ EXPORT_SYMBOL(generic_atomic64_##op##_return);
 s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
-	raw_spinlock_t *lock = lock_addr(v);				\
+	arch_spinlock_t *lock = lock_addr(v);				\
 	s64 val;							\
 									\
-	raw_spin_lock_irqsave(lock, flags);				\
+	local_irq_save(flags);						\
+	arch_spin_lock(lock);						\
 	val = v->counter;						\
 	v->counter c_op a;						\
-	raw_spin_unlock_irqrestore(lock, flags);			\
+	arch_spin_unlock(lock);						\
+	local_irq_restore(flags);					\
 	return val;							\
 }									\
 EXPORT_SYMBOL(generic_atomic64_fetch_##op);
@@ -131,14 +141,16 @@ ATOMIC64_OPS(xor, ^=)
 s64 generic_atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter - 1;
 	if (val >= 0)
 		v->counter = val;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_dec_if_positive);
@@ -146,14 +158,16 @@ EXPORT_SYMBOL(generic_atomic64_dec_if_positive);
 s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
 	if (val == o)
 		v->counter = n;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_cmpxchg);
@@ -161,13 +175,15 @@ EXPORT_SYMBOL(generic_atomic64_cmpxchg);
 s64 generic_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
 	v->counter = new;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 	return val;
 }
 EXPORT_SYMBOL(generic_atomic64_xchg);
@@ -175,14 +191,16 @@ EXPORT_SYMBOL(generic_atomic64_xchg);
 s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
+	arch_spinlock_t *lock = lock_addr(v);
 	s64 val;
 
-	raw_spin_lock_irqsave(lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(lock);
 	val = v->counter;
 	if (val != u)
 		v->counter += a;
-	raw_spin_unlock_irqrestore(lock, flags);
+	arch_spin_unlock(lock);
+	local_irq_restore(flags);
 
 	return val;
 }
Signature · 1 line
2.45.2
Signature · 1 line
Masami Hiramatsu (Google) <[email protected]>