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
  ...

Documentation/memory-barriers.txt

@@ -1633,6 +1633,48 @@ There are some more advanced barrier functions:
      operations" subsection for information on where to use these.
 
 
+ (*) dma_wmb();
+ (*) dma_rmb();
+
+     These are for use with consistent memory to guarantee the ordering
+     of writes or reads of shared memory accessible to both the CPU and a
+     DMA capable device.
+
+     For example, consider a device driver that shares memory with a device
+     and uses a descriptor status value to indicate if the descriptor belongs
+     to the device or the CPU, and a doorbell to notify it when new
+     descriptors are available:
+
+	if (desc->status != DEVICE_OWN) {
+		/* do not read data until we own descriptor */
+		dma_rmb();
+
+		/* read/modify data */
+		read_data = desc->data;
+		desc->data = write_data;
+
+		/* flush modifications before status update */
+		dma_wmb();
+
+		/* assign ownership */
+		desc->status = DEVICE_OWN;
+
+		/* force memory to sync before notifying device via MMIO */
+		wmb();
+
+		/* notify device of new descriptors */
+		writel(DESC_NOTIFY, doorbell);
+	}
+
+     The dma_rmb() allows us guarantee the device has released ownership
+     before we read the data from the descriptor, and he dma_wmb() allows
+     us to guarantee the data is written to the descriptor before the device
+     can see it now has ownership.  The wmb() is needed to guarantee that the
+     cache coherent memory writes have completed before attempting a write to
+     the cache incoherent MMIO region.
+
+     See Documentation/DMA-API.txt for more information on consistent memory.
+
 MMIO WRITE BARRIER
 ------------------
 

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

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

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()

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
 

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()
 

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)						\

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()