summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2013-11-06 14:57:36 +0100
committerJiri Slaby <jslaby@suse.cz>2015-08-25 16:56:59 +0200
commitad3b8fca4a918003cc03e8546b2f35506fd5d2e7 (patch)
tree77250da8ab6df8f83ff48f8c03904e363ba65566 /include
parente0de15fc45a83f94d1ef578f54b427b86a33ab21 (diff)
arch: Introduce smp_load_acquire(), smp_store_release()
commit 47933ad41a86a4a9b50bed7c9b9bd2ba242aac63 upstream. A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/barrier.h15
-rw-r--r--include/linux/compiler.h9
2 files changed, 24 insertions, 0 deletions
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 639d7a4d033b..01613b382b0e 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -46,5 +46,20 @@
#define read_barrier_depends() do {} while (0)
#define smp_read_barrier_depends() do {} while (0)
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index a2329c5e6206..2472740d7ab2 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -302,6 +302,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
#endif
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
/* Compile time object size, -1 for unknown */
#ifndef __compiletime_object_size
# define __compiletime_object_size(obj) -1
@@ -341,6 +346,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
#define compiletime_assert(condition, msg) \
_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
+#define compiletime_assert_atomic_type(t) \
+ compiletime_assert(__native_word(t), \
+ "Need native word sized stores/loads for atomicity.")
+
/*
* Prevent the compiler from merging or refetching accesses. The compiler
* is also forbidden from reordering successive instances of ACCESS_ONCE(),