Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull another networking update from David Miller:
 "Small follow-up to the main merge pull from the other day:

  1) Alexander Duyck's DMA memory barrier patch set.

  2) cxgb4 driver fixes from Karen Xie.

  3) Add missing export of fixed_phy_register() to modules, from Mark
     Salter.

  4) DSA bug fixes from Florian Fainelli"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (24 commits)
  net/macb: add TX multiqueue support for gem
  linux/interrupt.h: remove the definition of unused tasklet_hi_enable
  jme: replace calls to redundant function
  net: ethernet: davicom: Allow to select DM9000 for nios2
  net: ethernet: smsc: Allow to select SMC91X for nios2
  cxgb4: Add support for QSA modules
  libcxgbi: fix freeing skb prematurely
  cxgb4i: use set_wr_txq() to set tx queues
  cxgb4i: handle non-pdu-aligned rx data
  cxgb4i: additional types of negative advice
  cxgb4/cxgb4i: set the max. pdu length in firmware
  cxgb4i: fix credit check for tx_data_wr
  cxgb4i: fix tx immediate data credit check
  net: phy: export fixed_phy_register()
  fib_trie: Fix trie balancing issue if new node pushes down existing node
  vlan: Add ability to always enable TSO/UFO
  r8169:update rtl8168g pcie ephy parameter
  net: dsa: bcm_sf2: force link for all fixed PHY devices
  fm10k/igb/ixgbe: Use dma_rmb on Rx descriptor reads
  r8169: Use dma_rmb() and dma_wmb() for DescOwn checks
  ...

12 files changed, 177 insertions, 160 deletions

diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 3832bdb794fe..77516c87255d 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -7,6 +7,57 @@
 #define rmb()	__asm__ __volatile__("mb": : :"memory")
 #define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	b = 2;
+ *	memory_barrier();
+ *	p = &b;				q = p;
+ *					read_barrier_depends();
+ *					d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	a = 2;
+ *	memory_barrier();
+ *	b = 3;				y = b;
+ *					read_barrier_depends();
+ *					x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ */
 #define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
 
 #ifdef CONFIG_SMP
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index c6a3e73a6e24..d2f81e6b8c1c 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 6389d60574d9..a5abb0062d6e 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/blackfin/include/asm/barrier.h b/arch/blackfin/include/asm/barrier.h
index 420006877998..dfb66fe88b34 100644
--- a/arch/blackfin/include/asm/barrier.h
+++ b/arch/blackfin/include/asm/barrier.h
@@ -22,6 +22,57 @@
 # define mb()	do { barrier(); smp_check_barrier(); smp_mark_barrier(); } while (0)
 # define rmb()	do { barrier(); smp_check_barrier(); } while (0)
 # define wmb()	do { barrier(); smp_mark_barrier(); } while (0)
+/*
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	b = 2;
+ *	memory_barrier();
+ *	p = &b;				q = p;
+ *					read_barrier_depends();
+ *					d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	a = 2;
+ *	memory_barrier();
+ *	b = 3;				y = b;
+ *					read_barrier_depends();
+ *					x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ */
 # define read_barrier_depends()	do { barrier(); smp_check_barrier(); } while (0)
 #endif
 
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index a48957c7b445..f6769eb2bbf9 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -35,26 +35,25 @@
  * it's (presumably) much slower than mf and (b) mf.a is supported for
  * sequential memory pages only.
  */
-#define mb()	ia64_mf()
-#define rmb()	mb()
-#define wmb()	mb()
-#define read_barrier_depends()	do { } while(0)
+#define mb()		ia64_mf()
+#define rmb()		mb()
+#define wmb()		mb()
+
+#define dma_rmb()	mb()
+#define dma_wmb()	mb()
 
 #ifdef CONFIG_SMP
 # define smp_mb()	mb()
-# define smp_rmb()	rmb()
-# define smp_wmb()	wmb()
-# define smp_read_barrier_depends()	read_barrier_depends()
-
 #else
-
 # define smp_mb()	barrier()
-# define smp_rmb()	barrier()
-# define smp_wmb()	barrier()
-# define smp_read_barrier_depends()	do { } while(0)
-
 #endif
 
+#define smp_rmb()	smp_mb()
+#define smp_wmb()	smp_mb()
+
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
+
 #define smp_mb__before_atomic()	barrier()
 #define smp_mb__after_atomic()	barrier()
 
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index c7591e80067c..d703d8e26a65 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
 
@@ -41,13 +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 read_barrier_depends()  do { } while (0)
+#define dma_rmb()	rmb()
+#define dma_wmb()	wmb()
 
 #ifndef CONFIG_SMP
 #define fence()		do { } while (0)
@@ -82,7 +80,10 @@ static inline void fence(void)
 #define smp_wmb()       barrier()
 #endif
 #endif
-#define smp_read_barrier_depends()     do { } while (0)
+
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
+
 #define set_mb(var, value) do { var = value; smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index d0101dd0575e..2b8bbbcb9be0 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -10,58 +10,6 @@
 
 #include <asm/addrspace.h>
 
-/*
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
@@ -127,20 +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 bab79a110c7b..a3bf5be111ff 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -33,12 +33,9 @@
 #define mb()   __asm__ __volatile__ ("sync" : : : "memory")
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
-#define read_barrier_depends()  do { } while(0)
 
 #define set_mb(var, value)	do { var = value; mb(); } while (0)
 
-#ifdef CONFIG_SMP
-
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
 #else
@@ -46,20 +43,26 @@
 #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")
-#define smp_read_barrier_depends()	read_barrier_depends()
 #else
-#define __lwsync()	barrier()
+#define smp_lwsync()	barrier()
 
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
 #endif /* CONFIG_SMP */
 
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
+
 /*
  * This is a barrier which prevents following instructions from being
  * started until the value of the argument x is known.  For example, if
@@ -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 b5dce6544d76..8d724718ec21 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -24,11 +24,14 @@
 
 #define rmb()				mb()
 #define wmb()				mb()
-#define read_barrier_depends()		do { } while(0)
+#define dma_rmb()			rmb()
+#define dma_wmb()			wmb()
 #define smp_mb()			mb()
 #define smp_rmb()			rmb()
 #define smp_wmb()			wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
+
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
 
 #define smp_mb__before_atomic()		smp_mb()
 #define smp_mb__after_atomic()		smp_mb()
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 305dcc3dc721..76648941fea7 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -37,7 +37,9 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define rmb()	__asm__ __volatile__("":::"memory")
 #define wmb()	__asm__ __volatile__("":::"memory")
 
-#define read_barrier_depends()		do { } while(0)
+#define dma_rmb()	rmb()
+#define dma_wmb()	wmb()
+
 #define set_mb(__var, __value) \
 	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
 
@@ -51,7 +53,8 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define smp_wmb()	__asm__ __volatile__("":::"memory")
 #endif
 
-#define smp_read_barrier_depends()	do { } while(0)
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 0f4460b5636d..2ab1eb33106e 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -24,78 +24,28 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#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 smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
 #endif /* SMP */
 
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
+
 #if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index cc04e67bfd05..2d7d9a1f5b53 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -29,20 +29,18 @@
 
 #endif /* CONFIG_X86_32 */
 
-#define read_barrier_depends()	do { } while (0)
-
-#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_read_barrier_depends()	read_barrier_depends()
+#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 */
@@ -50,11 +48,13 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
 
 #endif /* CONFIG_SMP */
 
+#define read_barrier_depends()		do { } while (0)
+#define smp_read_barrier_depends()	do { } while (0)
+
 /*
  * Stop RDTSC speculation. This is needed when you need to use RDTSC
  * (or get_cycles or vread that possibly accesses the TSC) in a defined