kcsan: Prefer __always_inline for fast-path

Prefer __always_inline for fast-path functions that are called outside
of user_access_save, to avoid generating UACCESS warnings when
optimizing for size (CC_OPTIMIZE_FOR_SIZE). It will also avoid future
surprises with compiler versions that change the inlining heuristic even
when optimizing for performance.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/58708908-84a0-0a81-a836-ad97e33dbb62@infradead.org

kernel/kcsan/atomic.h

@@ -18,7 +18,7 @@
  * than cast to volatile. Eventually, we hope to be able to remove this
  * function.
  */
-static inline bool kcsan_is_atomic(const volatile void *ptr)
+static __always_inline bool kcsan_is_atomic(const volatile void *ptr)
 {
 	/* only jiffies for now */
 	return ptr == &jiffies;

kernel/kcsan/core.c

@@ -78,10 +78,10 @@ static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
  */
 static DEFINE_PER_CPU(long, kcsan_skip);
 
-static inline atomic_long_t *find_watchpoint(unsigned long addr,
-					     size_t size,
-					     bool expect_write,
-					     long *encoded_watchpoint)
+static __always_inline atomic_long_t *find_watchpoint(unsigned long addr,
+						      size_t size,
+						      bool expect_write,
+						      long *encoded_watchpoint)
 {
 	const int slot = watchpoint_slot(addr);
 	const unsigned long addr_masked = addr & WATCHPOINT_ADDR_MASK;
@@ -146,7 +146,7 @@ insert_watchpoint(unsigned long addr, size_t size, bool is_write)
  *	2. the thread that set up the watchpoint already removed it;
  *	3. the watchpoint was removed and then re-used.
  */
-static inline bool
+static __always_inline bool
 try_consume_watchpoint(atomic_long_t *watchpoint, long encoded_watchpoint)
 {
 	return atomic_long_try_cmpxchg_relaxed(watchpoint, &encoded_watchpoint, CONSUMED_WATCHPOINT);
@@ -160,7 +160,7 @@ static inline bool remove_watchpoint(atomic_long_t *watchpoint)
 	return atomic_long_xchg_relaxed(watchpoint, INVALID_WATCHPOINT) != CONSUMED_WATCHPOINT;
 }
 
-static inline struct kcsan_ctx *get_ctx(void)
+static __always_inline struct kcsan_ctx *get_ctx(void)
 {
 	/*
 	 * In interrupts, use raw_cpu_ptr to avoid unnecessary checks, that would
@@ -169,7 +169,7 @@ static inline struct kcsan_ctx *get_ctx(void)
 	return in_task() ? &current->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx);
 }
 
-static inline bool is_atomic(const volatile void *ptr)
+static __always_inline bool is_atomic(const volatile void *ptr)
 {
 	struct kcsan_ctx *ctx = get_ctx();
 
@@ -193,7 +193,7 @@ static inline bool is_atomic(const volatile void *ptr)
 	return kcsan_is_atomic(ptr);
 }
 
-static inline bool should_watch(const volatile void *ptr, int type)
+static __always_inline bool should_watch(const volatile void *ptr, int type)
 {
 	/*
 	 * Never set up watchpoints when memory operations are atomic.
@@ -226,7 +226,7 @@ static inline void reset_kcsan_skip(void)
 	this_cpu_write(kcsan_skip, skip_count);
 }
 
-static inline bool kcsan_is_enabled(void)
+static __always_inline bool kcsan_is_enabled(void)
 {
 	return READ_ONCE(kcsan_enabled) && get_ctx()->disable_count == 0;
 }

kernel/kcsan/encoding.h

@@ -59,10 +59,10 @@ encode_watchpoint(unsigned long addr, size_t size, bool is_write)
 		      (addr & WATCHPOINT_ADDR_MASK));
 }
 
-static inline bool decode_watchpoint(long watchpoint,
-				     unsigned long *addr_masked,
-				     size_t *size,
-				     bool *is_write)
+static __always_inline bool decode_watchpoint(long watchpoint,
+					      unsigned long *addr_masked,
+					      size_t *size,
+					      bool *is_write)
 {
 	if (watchpoint == INVALID_WATCHPOINT ||
 	    watchpoint == CONSUMED_WATCHPOINT)
@@ -78,13 +78,13 @@ static inline bool decode_watchpoint(long watchpoint,
 /*
  * Return watchpoint slot for an address.
  */
-static inline int watchpoint_slot(unsigned long addr)
+static __always_inline int watchpoint_slot(unsigned long addr)
 {
 	return (addr / PAGE_SIZE) % CONFIG_KCSAN_NUM_WATCHPOINTS;
 }
 
-static inline bool matching_access(unsigned long addr1, size_t size1,
-				   unsigned long addr2, size_t size2)
+static __always_inline bool matching_access(unsigned long addr1, size_t size1,
+					    unsigned long addr2, size_t size2)
 {
 	unsigned long end_range1 = addr1 + size1 - 1;
 	unsigned long end_range2 = addr2 + size2 - 1;