diff options
author | Peter Zijlstra <peterz@infradead.org> | 2013-11-06 08:57:36 -0500 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2014-01-12 04:37:17 -0500 |
commit | 47933ad41a86a4a9b50bed7c9b9bd2ba242aac63 (patch) | |
tree | 4f1d94f4b09ecf0c1d99f295f2c31b22eebed492 /arch/arm64/include | |
parent | 93ea02bb84354370e51de803a9405f171f3edf88 (diff) |
arch: Introduce smp_load_acquire(), smp_store_release()
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>
Diffstat (limited to 'arch/arm64/include')
-rw-r--r-- | arch/arm64/include/asm/barrier.h | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index d4a63338a53c..78e20ba8806b 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h | |||
@@ -35,10 +35,60 @@ | |||
35 | #define smp_mb() barrier() | 35 | #define smp_mb() barrier() |
36 | #define smp_rmb() barrier() | 36 | #define smp_rmb() barrier() |
37 | #define smp_wmb() barrier() | 37 | #define smp_wmb() barrier() |
38 | |||
39 | #define smp_store_release(p, v) \ | ||
40 | do { \ | ||
41 | compiletime_assert_atomic_type(*p); \ | ||
42 | smp_mb(); \ | ||
43 | ACCESS_ONCE(*p) = (v); \ | ||
44 | } while (0) | ||
45 | |||
46 | #define smp_load_acquire(p) \ | ||
47 | ({ \ | ||
48 | typeof(*p) ___p1 = ACCESS_ONCE(*p); \ | ||
49 | compiletime_assert_atomic_type(*p); \ | ||
50 | smp_mb(); \ | ||
51 | ___p1; \ | ||
52 | }) | ||
53 | |||
38 | #else | 54 | #else |
55 | |||
39 | #define smp_mb() asm volatile("dmb ish" : : : "memory") | 56 | #define smp_mb() asm volatile("dmb ish" : : : "memory") |
40 | #define smp_rmb() asm volatile("dmb ishld" : : : "memory") | 57 | #define smp_rmb() asm volatile("dmb ishld" : : : "memory") |
41 | #define smp_wmb() asm volatile("dmb ishst" : : : "memory") | 58 | #define smp_wmb() asm volatile("dmb ishst" : : : "memory") |
59 | |||
60 | #define smp_store_release(p, v) \ | ||
61 | do { \ | ||
62 | compiletime_assert_atomic_type(*p); \ | ||
63 | switch (sizeof(*p)) { \ | ||
64 | case 4: \ | ||
65 | asm volatile ("stlr %w1, %0" \ | ||
66 | : "=Q" (*p) : "r" (v) : "memory"); \ | ||
67 | break; \ | ||
68 | case 8: \ | ||
69 | asm volatile ("stlr %1, %0" \ | ||
70 | : "=Q" (*p) : "r" (v) : "memory"); \ | ||
71 | break; \ | ||
72 | } \ | ||
73 | } while (0) | ||
74 | |||
75 | #define smp_load_acquire(p) \ | ||
76 | ({ \ | ||
77 | typeof(*p) ___p1; \ | ||
78 | compiletime_assert_atomic_type(*p); \ | ||
79 | switch (sizeof(*p)) { \ | ||
80 | case 4: \ | ||
81 | asm volatile ("ldar %w0, %1" \ | ||
82 | : "=r" (___p1) : "Q" (*p) : "memory"); \ | ||
83 | break; \ | ||
84 | case 8: \ | ||
85 | asm volatile ("ldar %0, %1" \ | ||
86 | : "=r" (___p1) : "Q" (*p) : "memory"); \ | ||
87 | break; \ | ||
88 | } \ | ||
89 | ___p1; \ | ||
90 | }) | ||
91 | |||
42 | #endif | 92 | #endif |
43 | 93 | ||
44 | #define read_barrier_depends() do { } while(0) | 94 | #define read_barrier_depends() do { } while(0) |