[PATCH v4 19/35] locking/local_lock: Support Clang's context analysis

Add support for Clang's context analysis for local_lock_t and
local_trylock_t.

Signed-off-by: Marco Elver <[email protected]>
---
v4:
* Rename capability -> context analysis.

v3:
* Switch to DECLARE_LOCK_GUARD_1_ATTRS() (suggested by Peter)
* __assert -> __assume rename
* Rework __this_cpu_local_lock helper
* Support local_trylock_t
---
 Documentation/dev-tools/context-analysis.rst |  2 +-
 include/linux/local_lock.h                   | 45 ++++++------
 include/linux/local_lock_internal.h          | 71 +++++++++++++++----
 lib/test_context-analysis.c                  | 73 ++++++++++++++++++++
 4 files changed, 156 insertions(+), 35 deletions(-)

diff --git a/Documentation/dev-tools/context-analysis.rst b/Documentation/dev-tools/context-analysis.rst
index dc7ae4f641f2..8737de63a707 100644
--- a/Documentation/dev-tools/context-analysis.rst
+++ b/Documentation/dev-tools/context-analysis.rst
@@ -81,7 +81,7 @@ Supported Kernel Primitives
 
 Currently the following synchronization primitives are supported:
 `raw_spinlock_t`, `spinlock_t`, `rwlock_t`, `mutex`, `seqlock_t`,
-`bit_spinlock`, RCU, SRCU (`srcu_struct`), `rw_semaphore`.
+`bit_spinlock`, RCU, SRCU (`srcu_struct`), `rw_semaphore`, `local_lock_t`.
 
 For context guards with an initialization function (e.g., `spin_lock_init()`),
 calling this function before initializing any guarded members or globals
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index 0d91d060e3e9..a83458bebe97 100644
--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -13,13 +13,13 @@
  * local_lock - Acquire a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_lock(lock)		__local_lock(this_cpu_ptr(lock))
+#define local_lock(lock)		__local_lock(__this_cpu_local_lock(lock))
 
 /**
  * local_lock_irq - Acquire a per CPU local lock and disable interrupts
  * @lock:	The lock variable
  */
-#define local_lock_irq(lock)		__local_lock_irq(this_cpu_ptr(lock))
+#define local_lock_irq(lock)		__local_lock_irq(__this_cpu_local_lock(lock))
 
 /**
  * local_lock_irqsave - Acquire a per CPU local lock, save and disable
@@ -28,19 +28,19 @@
  * @flags:	Storage for interrupt flags
  */
 #define local_lock_irqsave(lock, flags)				\
-	__local_lock_irqsave(this_cpu_ptr(lock), flags)
+	__local_lock_irqsave(__this_cpu_local_lock(lock), flags)
 
 /**
  * local_unlock - Release a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_unlock(lock)		__local_unlock(this_cpu_ptr(lock))
+#define local_unlock(lock)		__local_unlock(__this_cpu_local_lock(lock))
 
 /**
  * local_unlock_irq - Release a per CPU local lock and enable interrupts
  * @lock:	The lock variable
  */
-#define local_unlock_irq(lock)		__local_unlock_irq(this_cpu_ptr(lock))
+#define local_unlock_irq(lock)		__local_unlock_irq(__this_cpu_local_lock(lock))
 
 /**
  * local_unlock_irqrestore - Release a per CPU local lock and restore
@@ -49,7 +49,7 @@
  * @flags:      Interrupt flags to restore
  */
 #define local_unlock_irqrestore(lock, flags)			\
-	__local_unlock_irqrestore(this_cpu_ptr(lock), flags)
+	__local_unlock_irqrestore(__this_cpu_local_lock(lock), flags)
 
 /**
  * local_lock_init - Runtime initialize a lock instance
@@ -64,7 +64,7 @@
  * locking constrains it will _always_ fail to acquire the lock in NMI or
  * HARDIRQ context on PREEMPT_RT.
  */
-#define local_trylock(lock)		__local_trylock(this_cpu_ptr(lock))
+#define local_trylock(lock)		__local_trylock(__this_cpu_local_lock(lock))
 
 #define local_lock_is_locked(lock)	__local_lock_is_locked(lock)
 
@@ -79,27 +79,32 @@
  * HARDIRQ context on PREEMPT_RT.
  */
 #define local_trylock_irqsave(lock, flags)			\
-	__local_trylock_irqsave(this_cpu_ptr(lock), flags)
-
-DEFINE_GUARD(local_lock, local_lock_t __percpu*,
-	     local_lock(_T),
-	     local_unlock(_T))
-DEFINE_GUARD(local_lock_irq, local_lock_t __percpu*,
-	     local_lock_irq(_T),
-	     local_unlock_irq(_T))
+	__local_trylock_irqsave(__this_cpu_local_lock(lock), flags)
+
+DEFINE_LOCK_GUARD_1(local_lock, local_lock_t __percpu,
+		    local_lock(_T->lock),
+		    local_unlock(_T->lock))
+DEFINE_LOCK_GUARD_1(local_lock_irq, local_lock_t __percpu,
+		    local_lock_irq(_T->lock),
+		    local_unlock_irq(_T->lock))
 DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu,
 		    local_lock_irqsave(_T->lock, _T->flags),
 		    local_unlock_irqrestore(_T->lock, _T->flags),
 		    unsigned long flags)
 
 #define local_lock_nested_bh(_lock)				\
-	__local_lock_nested_bh(this_cpu_ptr(_lock))
+	__local_lock_nested_bh(__this_cpu_local_lock(_lock))
 
 #define local_unlock_nested_bh(_lock)				\
-	__local_unlock_nested_bh(this_cpu_ptr(_lock))
+	__local_unlock_nested_bh(__this_cpu_local_lock(_lock))
 
-DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*,
-	     local_lock_nested_bh(_T),
-	     local_unlock_nested_bh(_T))
+DEFINE_LOCK_GUARD_1(local_lock_nested_bh, local_lock_t __percpu,
+		    local_lock_nested_bh(_T->lock),
+		    local_unlock_nested_bh(_T->lock))
+
+DECLARE_LOCK_GUARD_1_ATTRS(local_lock, __assumes_ctx_guard(_T), /* */)
+DECLARE_LOCK_GUARD_1_ATTRS(local_lock_irq, __assumes_ctx_guard(_T), /* */)
+DECLARE_LOCK_GUARD_1_ATTRS(local_lock_irqsave, __assumes_ctx_guard(_T), /* */)
+DECLARE_LOCK_GUARD_1_ATTRS(local_lock_nested_bh, __assumes_ctx_guard(_T), /* */)
 
 #endif
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 9f6cb32f04b0..17b8135bd2c3 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -10,21 +10,23 @@
 
 #ifndef CONFIG_PREEMPT_RT
 
-typedef struct {
+context_guard_struct(local_lock) {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 	struct task_struct	*owner;
 #endif
-} local_lock_t;
+};
+typedef struct local_lock local_lock_t;
 
 /* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */
-typedef struct {
+context_guard_struct(local_trylock) {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 	struct task_struct	*owner;
 #endif
 	u8		acquired;
-} local_trylock_t;
+};
+typedef struct local_trylock local_trylock_t;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define LOCAL_LOCK_DEBUG_INIT(lockname)		\
@@ -84,9 +86,14 @@ do {								\
 			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
 			      LD_LOCK_PERCPU);			\
 	local_lock_debug_init(lock);				\
+	__assume_ctx_guard(lock);				\
 } while (0)
 
-#define __local_trylock_init(lock) __local_lock_init((local_lock_t *)lock)
+#define __local_trylock_init(lock)				\
+do {								\
+	__local_lock_init((local_lock_t *)lock);		\
+	__assume_ctx_guard(lock);				\
+} while (0)
 
 #define __spinlock_nested_bh_init(lock)				\
 do {								\
@@ -97,6 +104,7 @@ do {								\
 			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
 			      LD_LOCK_NORMAL);			\
 	local_lock_debug_init(lock);				\
+	__assume_ctx_guard(lock);				\
 } while (0)
 
 #define __local_lock_acquire(lock)					\
@@ -119,22 +127,25 @@ do {								\
 	do {							\
 		preempt_disable();				\
 		__local_lock_acquire(lock);			\
+		__acquire(lock);				\
 	} while (0)
 
 #define __local_lock_irq(lock)					\
 	do {							\
 		local_irq_disable();				\
 		__local_lock_acquire(lock);			\
+		__acquire(lock);				\
 	} while (0)
 
 #define __local_lock_irqsave(lock, flags)			\
 	do {							\
 		local_irq_save(flags);				\
 		__local_lock_acquire(lock);			\
+		__acquire(lock);				\
 	} while (0)
 
 #define __local_trylock(lock)					\
-	({							\
+	__try_acquire_ctx_guard(lock, ({				\
 		local_trylock_t *tl;				\
 								\
 		preempt_disable();				\
@@ -148,10 +159,10 @@ do {								\
 				(local_lock_t *)tl);		\
 		}						\
 		!!tl;						\
-	})
+	}))
 
 #define __local_trylock_irqsave(lock, flags)			\
-	({							\
+	__try_acquire_ctx_guard(lock, ({				\
 		local_trylock_t *tl;				\
 								\
 		local_irq_save(flags);				\
@@ -165,7 +176,7 @@ do {								\
 				(local_lock_t *)tl);		\
 		}						\
 		!!tl;						\
-	})
+	}))
 
 /* preemption or migration must be disabled before calling __local_lock_is_locked */
 #define __local_lock_is_locked(lock) READ_ONCE(this_cpu_ptr(lock)->acquired)
@@ -188,18 +199,21 @@ do {								\
 
 #define __local_unlock(lock)					\
 	do {							\
+		__release(lock);				\
 		__local_lock_release(lock);			\
 		preempt_enable();				\
 	} while (0)
 
 #define __local_unlock_irq(lock)				\
 	do {							\
+		__release(lock);				\
 		__local_lock_release(lock);			\
 		local_irq_enable();				\
 	} while (0)
 
 #define __local_unlock_irqrestore(lock, flags)			\
 	do {							\
+		__release(lock);				\
 		__local_lock_release(lock);			\
 		local_irq_restore(flags);			\
 	} while (0)
@@ -208,13 +222,19 @@ do {								\
 	do {							\
 		lockdep_assert_in_softirq();			\
 		local_lock_acquire((lock));			\
+		__acquire(lock);				\
 	} while (0)
 
 #define __local_unlock_nested_bh(lock)				\
-	local_lock_release((lock))
+	do {							\
+		__release(lock);				\
+		local_lock_release((lock));			\
+	} while (0)
 
 #else /* !CONFIG_PREEMPT_RT */
 
+#include <linux/spinlock.h>
+
 /*
  * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the
  * critical section while staying preemptible.
@@ -269,7 +289,7 @@ do {								\
 } while (0)
 
 #define __local_trylock(lock)					\
-	({							\
+	__try_acquire_ctx_guard(lock, context_unsafe(({		\
 		int __locked;					\
 								\
 		if (in_nmi() | in_hardirq()) {			\
@@ -281,17 +301,40 @@ do {								\
 				migrate_enable();		\
 		}						\
 		__locked;					\
-	})
+	})))
 
 #define __local_trylock_irqsave(lock, flags)			\
-	({							\
+	__try_acquire_ctx_guard(lock, ({			\
 		typecheck(unsigned long, flags);		\
 		flags = 0;					\
 		__local_trylock(lock);				\
-	})
+	}))
 
 /* migration must be disabled before calling __local_lock_is_locked */
 #define __local_lock_is_locked(__lock)					\
 	(rt_mutex_owner(&this_cpu_ptr(__lock)->lock) == current)
 
 #endif /* CONFIG_PREEMPT_RT */
+
+#if defined(WARN_CONTEXT_ANALYSIS)
+/*
+ * Because the compiler only knows about the base per-CPU variable, use this
+ * helper function to make the compiler think we lock/unlock the @base variable,
+ * and hide the fact we actually pass the per-CPU instance to lock/unlock
+ * functions.
+ */
+static __always_inline local_lock_t *__this_cpu_local_lock(local_lock_t __percpu *base)
+	__returns_ctx_guard(base) __attribute__((overloadable))
+{
+	return this_cpu_ptr(base);
+}
+#ifndef CONFIG_PREEMPT_RT
+static __always_inline local_trylock_t *__this_cpu_local_lock(local_trylock_t __percpu *base)
+	__returns_ctx_guard(base) __attribute__((overloadable))
+{
+	return this_cpu_ptr(base);
+}
+#endif /* CONFIG_PREEMPT_RT */
+#else  /* WARN_CONTEXT_ANALYSIS */
+#define __this_cpu_local_lock(base) this_cpu_ptr(base)
+#endif /* WARN_CONTEXT_ANALYSIS */
diff --git a/lib/test_context-analysis.c b/lib/test_context-analysis.c
index 2203a57cd40d..74eca21f7aaa 100644
--- a/lib/test_context-analysis.c
+++ b/lib/test_context-analysis.c
@@ -6,7 +6,9 @@
 
 #include <linux/bit_spinlock.h>
 #include <linux/build_bug.h>
+#include <linux/local_lock.h>
 #include <linux/mutex.h>
+#include <linux/percpu.h>
 #include <linux/rcupdate.h>
 #include <linux/rwsem.h>
 #include <linux/seqlock.h>
@@ -450,3 +452,74 @@ static void __used test_srcu_guard(struct test_srcu_data *d)
 	guard(srcu)(&d->srcu);
 	(void)srcu_dereference(d->data, &d->srcu);
 }
+
+struct test_local_lock_data {
+	local_lock_t lock;
+	int counter __guarded_by(&lock);
+};
+
+static DEFINE_PER_CPU(struct test_local_lock_data, test_local_lock_data) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
+
+static void __used test_local_lock_init(struct test_local_lock_data *d)
+{
+	local_lock_init(&d->lock);
+	d->counter = 0;
+}
+
+static void __used test_local_lock(void)
+{
+	unsigned long flags;
+
+	local_lock(&test_local_lock_data.lock);
+	this_cpu_add(test_local_lock_data.counter, 1);
+	local_unlock(&test_local_lock_data.lock);
+
+	local_lock_irq(&test_local_lock_data.lock);
+	this_cpu_add(test_local_lock_data.counter, 1);
+	local_unlock_irq(&test_local_lock_data.lock);
+
+	local_lock_irqsave(&test_local_lock_data.lock, flags);
+	this_cpu_add(test_local_lock_data.counter, 1);
+	local_unlock_irqrestore(&test_local_lock_data.lock, flags);
+
+	local_lock_nested_bh(&test_local_lock_data.lock);
+	this_cpu_add(test_local_lock_data.counter, 1);
+	local_unlock_nested_bh(&test_local_lock_data.lock);
+}
+
+static void __used test_local_lock_guard(void)
+{
+	{ guard(local_lock)(&test_local_lock_data.lock); this_cpu_add(test_local_lock_data.counter, 1); }
+	{ guard(local_lock_irq)(&test_local_lock_data.lock); this_cpu_add(test_local_lock_data.counter, 1); }
+	{ guard(local_lock_irqsave)(&test_local_lock_data.lock); this_cpu_add(test_local_lock_data.counter, 1); }
+	{ guard(local_lock_nested_bh)(&test_local_lock_data.lock); this_cpu_add(test_local_lock_data.counter, 1); }
+}
+
+struct test_local_trylock_data {
+	local_trylock_t lock;
+	int counter __guarded_by(&lock);
+};
+
+static DEFINE_PER_CPU(struct test_local_trylock_data, test_local_trylock_data) = {
+	.lock = INIT_LOCAL_TRYLOCK(lock),
+};
+
+static void __used test_local_trylock_init(struct test_local_trylock_data *d)
+{
+	local_trylock_init(&d->lock);
+	d->counter = 0;
+}
+
+static void __used test_local_trylock(void)
+{
+	local_lock(&test_local_trylock_data.lock);
+	this_cpu_add(test_local_trylock_data.counter, 1);
+	local_unlock(&test_local_trylock_data.lock);
+
+	if (local_trylock(&test_local_trylock_data.lock)) {
+		this_cpu_add(test_local_trylock_data.counter, 1);
+		local_unlock(&test_local_trylock_data.lock);
+	}
+}
-- 
2.52.0.rc1.455.g30608eb744-goog