Message-ID: <20250227221924.265259-4-lyude@redhat.com>
Date: Thu, 27 Feb 2025 17:10:14 -0500
From: Lyude Paul <lyude@...hat.com>
To: rust-for-linux@...r.kernel.org,
	Thomas Gleixner <tglx@...utronix.de>
Cc: Boqun Feng <boqun.feng@...il.com>,
	Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>,
	Will Deacon <will@...nel.org>,
	Waiman Long <longman@...hat.com>,
	Miguel Ojeda <ojeda@...nel.org>,
	Alex Gaynor <alex.gaynor@...il.com>,
	Gary Guo <gary@...yguo.net>,
	Björn Roy Baron <bjorn3_gh@...tonmail.com>,
	Benno Lossin <benno.lossin@...ton.me>,
	Andreas Hindborg <a.hindborg@...nel.org>,
	Alice Ryhl <aliceryhl@...gle.com>,
	Trevor Gross <tmgross@...ch.edu>,
	David Woodhouse <dwmw@...zon.co.uk>,
	Arnd Bergmann <arnd@...db.de>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	NeilBrown <neilb@...e.de>,
	Zqiang <qiang.zhang1211@...il.com>,
	K Prateek Nayak <kprateek.nayak@....com>,
	Caleb Sander Mateos <csander@...estorage.com>,
	linux-kernel@...r.kernel.org (open list)
Subject: [PATCH v9 3/9] irq & spin_lock: Add counted interrupt disabling/enabling

From: Boqun Feng <boqun.feng@...il.com>

Currently the nested interrupt disabling and enabling is present by
_irqsave() and _irqrestore() APIs, which are relatively unsafe, for
example:

	<interrupts are enabled as beginning>
	spin_lock_irqsave(l1, flag1);
	spin_lock_irqsave(l2, flag2);
	spin_unlock_irqrestore(l1, flags1);
	<l2 is still held but interrupts are enabled>
	// accesses to interrupt-disable protect data will cause races.

This is even easier to triggered with guard facilities:

	unsigned long flag2;

	scoped_guard(spin_lock_irqsave, l1) {
		spin_lock_irqsave(l2, flag2);
	}
	// l2 locked but interrupts are enabled.
	spin_unlock_irqrestore(l2, flag2);

(Hand-to-hand locking critical sections are not uncommon for a
fine-grained lock design)

And because this unsafety, Rust cannot easily wrap the
interrupt-disabling locks in a safe API, which complicates the design.

To resolve this, introduce a new set of interrupt disabling APIs:

*	local_interrupt_disalbe();
*	local_interrupt_enable();

They work like local_irq_save() and local_irq_restore() except that 1)
the outermost local_interrupt_disable() call save the interrupt state
into a percpu variable, so that the outermost local_interrupt_enable()
can restore the state, and 2) a percpu counter is added to record the
nest level of these calls, so that interrupts are not accidentally
enabled inside the outermost critical section.

Also add the corresponding spin_lock primitives: spin_lock_irq_disable()
and spin_unlock_irq_enable(), as a result, code as follow:

	spin_lock_irq_disable(l1);
	spin_lock_irq_disable(l2);
	spin_unlock_irq_enable(l1);
	// Interrupts are still disabled.
	spin_unlock_irq_enable(l2);

doesn't have the issue that interrupts are accidentally enabled.

This also makes the wrapper of interrupt-disabling locks on Rust easier
to design.

Signed-off-by: Boqun Feng <boqun.feng@...il.com>
Signed-off-by: Lyude Paul <lyude@...hat.com>
---
 include/linux/irqflags.h         |  1 -
 include/linux/irqflags_types.h   |  6 ++++
 include/linux/preempt.h          |  4 +++
 include/linux/spinlock.h         | 62 ++++++++++++++++++++++++++++++++
 include/linux/spinlock_api_smp.h | 27 ++++++++++++++
 include/linux/spinlock_api_up.h  |  8 +++++
 include/linux/spinlock_rt.h      | 10 ++++++
 kernel/locking/spinlock.c        | 16 +++++++++
 kernel/softirq.c                 |  3 ++
 9 files changed, 136 insertions(+), 1 deletion(-)

diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 57b074e0cfbbb..3519d06db55e0 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -231,7 +231,6 @@ extern void warn_bogus_irq_restore(void);
 		raw_safe_halt();		\
 	} while (0)
 
-
 #else /* !CONFIG_TRACE_IRQFLAGS */
 
 #define local_irq_enable()	do { raw_local_irq_enable(); } while (0)
diff --git a/include/linux/irqflags_types.h b/include/linux/irqflags_types.h
index c13f0d915097a..277433f7f53eb 100644
--- a/include/linux/irqflags_types.h
+++ b/include/linux/irqflags_types.h
@@ -19,4 +19,10 @@ struct irqtrace_events {
 
 #endif
 
+/* Per-cpu interrupt disabling state for local_interrupt_{disable,enable}() */
+struct interrupt_disable_state {
+	unsigned long flags;
+	long count;
+};
+
 #endif /* _LINUX_IRQFLAGS_TYPES_H */
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index e74ab9cf02af0..be6acec83e067 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -148,6 +148,10 @@ static __always_inline unsigned char interrupt_context_level(void)
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
 
+#define hardirq_disable_count()	((preempt_count() & HARDIRQ_DISABLE_MASK) >> HARDIRQ_DISABLE_SHIFT)
+#define hardirq_disable_enter()	__preempt_count_add_return(HARDIRQ_DISABLE_OFFSET)
+#define hardirq_disable_exit()	__preempt_count_sub_return(HARDIRQ_DISABLE_OFFSET)
+
 /*
  * The preempt_count offset after preempt_disable();
  */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 63dd8cf3c3c2b..897114d60cfd4 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -272,9 +272,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 #endif
 
 #define raw_spin_lock_irq(lock)		_raw_spin_lock_irq(lock)
+#define raw_spin_lock_irq_disable(lock)	_raw_spin_lock_irq_disable(lock)
 #define raw_spin_lock_bh(lock)		_raw_spin_lock_bh(lock)
 #define raw_spin_unlock(lock)		_raw_spin_unlock(lock)
 #define raw_spin_unlock_irq(lock)	_raw_spin_unlock_irq(lock)
+#define raw_spin_unlock_irq_enable(lock)	_raw_spin_unlock_irq_enable(lock)
 
 #define raw_spin_unlock_irqrestore(lock, flags)		\
 	do {							\
@@ -300,11 +302,56 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 	1 : ({ local_irq_restore(flags); 0; }); \
 })
 
+#define raw_spin_trylock_irq_disable(lock) \
+({ \
+	local_interrupt_disable(); \
+	raw_spin_trylock(lock) ? \
+	1 : ({ local_interrupt_enable(); 0; }); \
+})
+
 #ifndef CONFIG_PREEMPT_RT
 /* Include rwlock functions for !RT */
 #include <linux/rwlock.h>
 #endif
 
+DECLARE_PER_CPU(struct interrupt_disable_state, local_interrupt_disable_state);
+
+static inline void local_interrupt_disable(void)
+{
+	unsigned long flags;
+	int new_count;
+
+	new_count = hardirq_disable_enter();
+
+	if ((new_count & HARDIRQ_DISABLE_MASK) == HARDIRQ_DISABLE_OFFSET) {
+		local_irq_save(flags);
+		raw_cpu_write(local_interrupt_disable_state.flags, flags);
+	}
+}
+
+static inline void local_interrupt_enable(void)
+{
+	int new_count;
+
+	new_count = hardirq_disable_exit();
+
+	if ((new_count & HARDIRQ_DISABLE_MASK) == 0) {
+		unsigned long flags;
+
+		flags = raw_cpu_read(local_interrupt_disable_state.flags);
+		local_irq_restore(flags);
+		/*
+		 * TODO: re-read preempt count can be avoided, but it needs
+		 * should_resched() taking another parameter as the current
+		 * preempt count
+		 */
+#ifdef PREEMPTION
+		if (should_resched(0))
+			__preempt_schedule();
+#endif
+	}
+}
+
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
  */
@@ -376,6 +423,11 @@ static __always_inline void spin_lock_irq(spinlock_t *lock)
 	raw_spin_lock_irq(&lock->rlock);
 }
 
+static __always_inline void spin_lock_irq_disable(spinlock_t *lock)
+{
+	raw_spin_lock_irq_disable(&lock->rlock);
+}
+
 #define spin_lock_irqsave(lock, flags)				\
 do {								\
 	raw_spin_lock_irqsave(spinlock_check(lock), flags);	\
@@ -401,6 +453,11 @@ static __always_inline void spin_unlock_irq(spinlock_t *lock)
 	raw_spin_unlock_irq(&lock->rlock);
 }
 
+static __always_inline void spin_unlock_irq_enable(spinlock_t *lock)
+{
+	raw_spin_unlock_irq_enable(&lock->rlock);
+}
+
 static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 {
 	raw_spin_unlock_irqrestore(&lock->rlock, flags);
@@ -421,6 +478,11 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock)
 	raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
 })
 
+static __always_inline int spin_trylock_irq_disable(spinlock_t *lock)
+{
+	return raw_spin_trylock_irq_disable(&lock->rlock);
+}
+
 /**
  * spin_is_locked() - Check whether a spinlock is locked.
  * @lock: Pointer to the spinlock.
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 9ecb0ab504e32..92532103b9eaa 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -28,6 +28,8 @@ _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map)
 void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)		__acquires(lock);
 void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
 								__acquires(lock);
+void __lockfunc _raw_spin_lock_irq_disable(raw_spinlock_t *lock)
+								__acquires(lock);
 
 unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
 								__acquires(lock);
@@ -39,6 +41,7 @@ int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock);
 void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)		__releases(lock);
 void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)	__releases(lock);
 void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)	__releases(lock);
+void __lockfunc _raw_spin_unlock_irq_enable(raw_spinlock_t *lock)	__releases(lock);
 void __lockfunc
 _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
 								__releases(lock);
@@ -55,6 +58,11 @@ _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
 #define _raw_spin_lock_irq(lock) __raw_spin_lock_irq(lock)
 #endif
 
+/* Use the same config as spin_lock_irq() temporarily. */
+#ifdef CONFIG_INLINE_SPIN_LOCK_IRQ
+#define _raw_spin_lock_irq_disable(lock) __raw_spin_lock_irq_disable(lock)
+#endif
+
 #ifdef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
 #define _raw_spin_lock_irqsave(lock) __raw_spin_lock_irqsave(lock)
 #endif
@@ -79,6 +87,11 @@ _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
 #define _raw_spin_unlock_irq(lock) __raw_spin_unlock_irq(lock)
 #endif
 
+/* Use the same config as spin_unlock_irq() temporarily. */
+#ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQ
+#define _raw_spin_unlock_irq_enable(lock) __raw_spin_unlock_irq_enable(lock)
+#endif
+
 #ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
 #define _raw_spin_unlock_irqrestore(lock, flags) __raw_spin_unlock_irqrestore(lock, flags)
 #endif
@@ -120,6 +133,13 @@ static inline void __raw_spin_lock_irq(raw_spinlock_t *lock)
 	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
 }
 
+static inline void __raw_spin_lock_irq_disable(raw_spinlock_t *lock)
+{
+	local_interrupt_disable();
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+
 static inline void __raw_spin_lock_bh(raw_spinlock_t *lock)
 {
 	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
@@ -160,6 +180,13 @@ static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock)
 	preempt_enable();
 }
 
+static inline void __raw_spin_unlock_irq_enable(raw_spinlock_t *lock)
+{
+	spin_release(&lock->dep_map, _RET_IP_);
+	do_raw_spin_unlock(lock);
+	local_interrupt_enable();
+}
+
 static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock)
 {
 	spin_release(&lock->dep_map, _RET_IP_);
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index 819aeba1c87e6..d02a73671713b 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -36,6 +36,9 @@
 #define __LOCK_IRQ(lock) \
   do { local_irq_disable(); __LOCK(lock); } while (0)
 
+#define __LOCK_IRQ_DISABLE(lock) \
+  do { local_interrupt_disable(); __LOCK(lock); } while (0)
+
 #define __LOCK_IRQSAVE(lock, flags) \
   do { local_irq_save(flags); __LOCK(lock); } while (0)
 
@@ -52,6 +55,9 @@
 #define __UNLOCK_IRQ(lock) \
   do { local_irq_enable(); __UNLOCK(lock); } while (0)
 
+#define __UNLOCK_IRQ_ENABLE(lock) \
+  do { __UNLOCK(lock); local_interrupt_enable(); } while (0)
+
 #define __UNLOCK_IRQRESTORE(lock, flags) \
   do { local_irq_restore(flags); __UNLOCK(lock); } while (0)
 
@@ -64,6 +70,7 @@
 #define _raw_read_lock_bh(lock)			__LOCK_BH(lock)
 #define _raw_write_lock_bh(lock)		__LOCK_BH(lock)
 #define _raw_spin_lock_irq(lock)		__LOCK_IRQ(lock)
+#define _raw_spin_lock_irq_disable(lock)	__LOCK_IRQ_DISABLE(lock)
 #define _raw_read_lock_irq(lock)		__LOCK_IRQ(lock)
 #define _raw_write_lock_irq(lock)		__LOCK_IRQ(lock)
 #define _raw_spin_lock_irqsave(lock, flags)	__LOCK_IRQSAVE(lock, flags)
@@ -80,6 +87,7 @@
 #define _raw_write_unlock_bh(lock)		__UNLOCK_BH(lock)
 #define _raw_read_unlock_bh(lock)		__UNLOCK_BH(lock)
 #define _raw_spin_unlock_irq(lock)		__UNLOCK_IRQ(lock)
+#define _raw_spin_unlock_irq_enable(lock)	__UNLOCK_IRQ_ENABLE(lock)
 #define _raw_read_unlock_irq(lock)		__UNLOCK_IRQ(lock)
 #define _raw_write_unlock_irq(lock)		__UNLOCK_IRQ(lock)
 #define _raw_spin_unlock_irqrestore(lock, flags) \
diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
index f6499c37157df..6ea08fafa6d7b 100644
--- a/include/linux/spinlock_rt.h
+++ b/include/linux/spinlock_rt.h
@@ -93,6 +93,11 @@ static __always_inline void spin_lock_irq(spinlock_t *lock)
 	rt_spin_lock(lock);
 }
 
+static __always_inline void spin_lock_irq_disable(spinlock_t *lock)
+{
+	rt_spin_lock(lock);
+}
+
 #define spin_lock_irqsave(lock, flags)			 \
 	do {						 \
 		typecheck(unsigned long, flags);	 \
@@ -116,6 +121,11 @@ static __always_inline void spin_unlock_irq(spinlock_t *lock)
 	rt_spin_unlock(lock);
 }
 
+static __always_inline void spin_unlock_irq_enable(spinlock_t *lock)
+{
+	rt_spin_unlock(lock);
+}
+
 static __always_inline void spin_unlock_irqrestore(spinlock_t *lock,
 						   unsigned long flags)
 {
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 7685defd7c526..a2e01ec4a0c85 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -172,6 +172,14 @@ noinline void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
 EXPORT_SYMBOL(_raw_spin_lock_irq);
 #endif
 
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
+noinline void __lockfunc _raw_spin_lock_irq_disable(raw_spinlock_t *lock)
+{
+	__raw_spin_lock_irq_disable(lock);
+}
+EXPORT_SYMBOL_GPL(_raw_spin_lock_irq_disable);
+#endif
+
 #ifndef CONFIG_INLINE_SPIN_LOCK_BH
 noinline void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
 {
@@ -204,6 +212,14 @@ noinline void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
 EXPORT_SYMBOL(_raw_spin_unlock_irq);
 #endif
 
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
+noinline void __lockfunc _raw_spin_unlock_irq_enable(raw_spinlock_t *lock)
+{
+	__raw_spin_unlock_irq_enable(lock);
+}
+EXPORT_SYMBOL_GPL(_raw_spin_unlock_irq_enable);
+#endif
+
 #ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
 noinline void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
 {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 4dae6ac2e83fb..320a371967b62 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -88,6 +88,9 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
 EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
 #endif
 
+DEFINE_PER_CPU(struct interrupt_disable_state, local_interrupt_disable_state);
+EXPORT_PER_CPU_SYMBOL_GPL(local_interrupt_disable_state);
+
 /*
  * SOFTIRQ_OFFSET usage:
  *
-- 
2.48.1

Powered by blists - more mailing lists