summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorAlexander Duyck <alexander.h.duyck@redhat.com>2014-12-11 15:02:06 -0800
committerDavid S. Miller <davem@davemloft.net>2014-12-11 21:15:06 -0500
commit1077fa36f23e259858caf6f269a47393a5aff523 (patch)
tree569b84cfd3b409f07ce6a10f0166ca78307705e1 /arch
parent8a449718414ff10b9d5559ed3e8e09c7178774f2 (diff)
arch: Add lightweight memory barriers dma_rmb() and dma_wmb()
There are a number of situations where the mandatory barriers rmb() and wmb() are used to order memory/memory operations in the device drivers and those barriers are much heavier than they actually need to be. For example in the case of PowerPC wmb() calls the heavy-weight sync instruction when for coherent memory operations all that is really needed is an lsync or eieio instruction. This commit adds a coherent only version of the mandatory memory barriers rmb() and wmb(). In most cases this should result in the barrier being the same as the SMP barriers for the SMP case, however in some cases we use a barrier that is somewhere in between rmb() and smp_rmb(). For example on ARM the rmb barriers break down as follows: Barrier Call Explanation --------- -------- ---------------------------------- rmb() dsb() Data synchronization barrier - system dma_rmb() dmb(osh) data memory barrier - outer sharable smp_rmb() dmb(ish) data memory barrier - inner sharable These new barriers are not as safe as the standard rmb() and wmb(). Specifically they do not guarantee ordering between coherent and incoherent memories. The primary use case for these would be to enforce ordering of reads and writes when accessing coherent memory that is shared between the CPU and a device. It may also be noted that there is no dma_mb(). Most architectures don't provide a good mechanism for performing a coherent only full barrier without resorting to the same mechanism used in mb(). As such there isn't much to be gained in trying to define such a function. 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: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: David Miller <davem@davemloft.net> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/barrier.h4
-rw-r--r--arch/arm64/include/asm/barrier.h3
-rw-r--r--arch/ia64/include/asm/barrier.h3
-rw-r--r--arch/metag/include/asm/barrier.h14
-rw-r--r--arch/mips/include/asm/barrier.h9
-rw-r--r--arch/powerpc/include/asm/barrier.h13
-rw-r--r--arch/s390/include/asm/barrier.h2
-rw-r--r--arch/sparc/include/asm/barrier_64.h3
-rw-r--r--arch/x86/include/asm/barrier.h11
-rw-r--r--arch/x86/um/asm/barrier.h13
10 files changed, 49 insertions, 26 deletions
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index c6a3e73a6e2..d2f81e6b8c1 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -43,10 +43,14 @@
#define mb() do { dsb(); outer_sync(); } while (0)
#define rmb() dsb()
#define wmb() do { dsb(st); outer_sync(); } while (0)
+#define dma_rmb() dmb(osh)
+#define dma_wmb() dmb(oshst)
#else
#define mb() barrier()
#define rmb() barrier()
#define wmb() barrier()
+#define dma_rmb() barrier()
+#define dma_wmb() barrier()
#endif
#ifndef CONFIG_SMP
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 6389d60574d..a5abb0062d6 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -32,6 +32,9 @@
#define rmb() dsb(ld)
#define wmb() dsb(st)
+#define dma_rmb() dmb(oshld)
+#define dma_wmb() dmb(oshst)
+
#ifndef CONFIG_SMP
#define smp_mb() barrier()
#define smp_rmb() barrier()
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index e8fffb03963..f6769eb2bbf 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -39,6 +39,9 @@
#define rmb() mb()
#define wmb() mb()
+#define dma_rmb() mb()
+#define dma_wmb() mb()
+
#ifdef CONFIG_SMP
# define smp_mb() mb()
#else
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index 6d8b8c9b7c2..d703d8e26a6 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -4,8 +4,6 @@
#include <asm/metag_mem.h>
#define nop() asm volatile ("NOP")
-#define mb() wmb()
-#define rmb() barrier()
#ifdef CONFIG_METAG_META21
@@ -41,11 +39,13 @@ static inline void wr_fence(void)
#endif /* !CONFIG_METAG_META21 */
-static inline void wmb(void)
-{
- /* flush writes through the write combiner */
- wr_fence();
-}
+/* flush writes through the write combiner */
+#define mb() wr_fence()
+#define rmb() barrier()
+#define wmb() mb()
+
+#define dma_rmb() rmb()
+#define dma_wmb() wmb()
#ifndef CONFIG_SMP
#define fence() do { } while (0)
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 3d69aa829a7..2b8bbbcb9be 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -75,20 +75,21 @@
#include <asm/wbflush.h>
-#define wmb() fast_wmb()
-#define rmb() fast_rmb()
#define mb() wbflush()
#define iob() wbflush()
#else /* !CONFIG_CPU_HAS_WB */
-#define wmb() fast_wmb()
-#define rmb() fast_rmb()
#define mb() fast_mb()
#define iob() fast_iob()
#endif /* !CONFIG_CPU_HAS_WB */
+#define wmb() fast_wmb()
+#define rmb() fast_rmb()
+#define dma_wmb() fast_wmb()
+#define dma_rmb() fast_rmb()
+
#if defined(CONFIG_WEAK_ORDERING) && defined(CONFIG_SMP)
# ifdef CONFIG_CPU_CAVIUM_OCTEON
# define smp_mb() __sync()
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index cb6d66c6e3e..a3bf5be111f 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -36,8 +36,6 @@
#define set_mb(var, value) do { var = value; mb(); } while (0)
-#ifdef CONFIG_SMP
-
#ifdef __SUBARCH_HAS_LWSYNC
# define SMPWMB LWSYNC
#else
@@ -45,12 +43,17 @@
#endif
#define __lwsync() __asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define dma_rmb() __lwsync()
+#define dma_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
+
+#ifdef CONFIG_SMP
+#define smp_lwsync() __lwsync()
#define smp_mb() mb()
#define smp_rmb() __lwsync()
#define smp_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
#else
-#define __lwsync() barrier()
+#define smp_lwsync() barrier()
#define smp_mb() barrier()
#define smp_rmb() barrier()
@@ -72,7 +75,7 @@
#define smp_store_release(p, v) \
do { \
compiletime_assert_atomic_type(*p); \
- __lwsync(); \
+ smp_lwsync(); \
ACCESS_ONCE(*p) = (v); \
} while (0)
@@ -80,7 +83,7 @@ do { \
({ \
typeof(*p) ___p1 = ACCESS_ONCE(*p); \
compiletime_assert_atomic_type(*p); \
- __lwsync(); \
+ smp_lwsync(); \
___p1; \
})
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 33d191d295e..8d724718ec2 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -24,6 +24,8 @@
#define rmb() mb()
#define wmb() mb()
+#define dma_rmb() rmb()
+#define dma_wmb() wmb()
#define smp_mb() mb()
#define smp_rmb() rmb()
#define smp_wmb() wmb()
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 6c974c0977a..76648941fea 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -37,6 +37,9 @@ do { __asm__ __volatile__("ba,pt %%xcc, 1f\n\t" \
#define rmb() __asm__ __volatile__("":::"memory")
#define wmb() __asm__ __volatile__("":::"memory")
+#define dma_rmb() rmb()
+#define dma_wmb() wmb()
+
#define set_mb(__var, __value) \
do { __var = __value; membar_safe("#StoreLoad"); } while(0)
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 5238000285c..2ab1eb33106 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -24,13 +24,16 @@
#define wmb() asm volatile("sfence" ::: "memory")
#endif
-#ifdef CONFIG_SMP
-#define smp_mb() mb()
#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb() rmb()
+#define dma_rmb() rmb()
#else
-# define smp_rmb() barrier()
+#define dma_rmb() barrier()
#endif
+#define dma_wmb() barrier()
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() dma_rmb()
#define smp_wmb() barrier()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index d6511d954e2..2d7d9a1f5b5 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -29,17 +29,18 @@
#endif /* CONFIG_X86_32 */
-#ifdef CONFIG_SMP
-
-#define smp_mb() mb()
#ifdef CONFIG_X86_PPRO_FENCE
-#define smp_rmb() rmb()
+#define dma_rmb() rmb()
#else /* CONFIG_X86_PPRO_FENCE */
-#define smp_rmb() barrier()
+#define dma_rmb() barrier()
#endif /* CONFIG_X86_PPRO_FENCE */
+#define dma_wmb() barrier()
-#define smp_wmb() barrier()
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() dma_rmb()
+#define smp_wmb() barrier()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* CONFIG_SMP */