diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 7ee2ae6d5451d120126a04e3deeb07c02f2f9671..70a09f8a0383b2cdc25ab35f6aef43e8ac2905b4 100644
--- a/Documentation/memory-barriers.txt
+++ b/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
------------------
diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 3832bdb794fec83d0df010413b009a311b57fec4..77516c87255d6e7abc909f827b930c4bbb154756 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 c6a3e73a6e2407215f3f9859212e41097071f492..d2f81e6b8c1cc5adb914ce38a7ab991b25801137 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 6389d60574d9c320f69744b28a6051108f0dfff5..a5abb0062d6e943d67ca4ff5479e887194482367 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 420006877998ffc82a8de4300ec6bca859b2e560..dfb66fe88b34542e6e9286593e6284fd73a8ece2 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 a48957c7b445a2ad08a22d6bc7911b5d2d6049f0..f6769eb2bbf9b5ff8774017ac0eb332fcc7309d9 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 c7591e80067c0e9fc150872262d9375a0faad6e6..d703d8e26a656c1560202d3c1af6a39ed95771e5 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 d0101dd0575eecce92dbda6f03b6daada470fb47..2b8bbbcb9be0e9f8c5c6f7dbc1a2c6f692185443 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 bab79a110c7b05ceb8a4320efe4290257e186250..a3bf5be111ff1d073eb329476ce773c07ce32ed5 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 b5dce6544d76e3357e4e8629333817008a0ee183..8d724718ec21c8d0331e1b8fbc14c96cb5892649 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 305dcc3dc721261b3a84fd402acd247956b60a08..76648941fea71b4327e058d6e995a3331587541c 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 0f4460b5636ded85a3e9ad4d6d755dbe32b745eb..2ab1eb33106eec42eff90d27b98cb698b5c4c835 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 cc04e67bfd0589966e1c4b4b2fa29079c439ae24..2d7d9a1f5b531ee399b7a0e6a1f9eb4a190fd820 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
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 4f4c2a7888e5d74ee06ae58df8feaf5f1dea3123..feb29c4526f7eea698ef8568b784daafe467980d 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -684,10 +684,9 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
struct fixed_phy_status *status)
{
struct bcm_sf2_priv *priv = ds_to_priv(ds);
- u32 link, duplex, pause, speed;
+ u32 duplex, pause, speed;
u32 reg;
- link = core_readl(priv, CORE_LNKSTS);
duplex = core_readl(priv, CORE_DUPSTS);
pause = core_readl(priv, CORE_PAUSESTS);
speed = core_readl(priv, CORE_SPDSTS);
@@ -701,22 +700,26 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
* which means that we need to force the link at the port override
* level to get the data to flow. We do use what the interrupt handler
* did determine before.
+ *
+ * For the other ports, we just force the link status, since this is
+ * a fixed PHY device.
*/
if (port == 7) {
status->link = priv->port_sts[port].link;
- reg = core_readl(priv, CORE_STS_OVERRIDE_GMIIP_PORT(7));
- reg |= SW_OVERRIDE;
- if (status->link)
- reg |= LINK_STS;
- else
- reg &= ~LINK_STS;
- core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(7));
status->duplex = 1;
} else {
- status->link = !!(link & (1 << port));
+ status->link = 1;
status->duplex = !!(duplex & (1 << port));
}
+ reg = core_readl(priv, CORE_STS_OVERRIDE_GMIIP_PORT(port));
+ reg |= SW_OVERRIDE;
+ if (status->link)
+ reg |= LINK_STS;
+ else
+ reg &= ~LINK_STS;
+ core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port));
+
switch (speed) {
case SPDSTS_10:
status->speed = SPEED_10;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index b6bc318b148e34a0e502ab1dd1a8c3fc88583cc3..0987d2a77f9f70ebd8c22ace98964093b40d0ebd 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -66,23 +66,25 @@ static unsigned int macb_tx_ring_wrap(unsigned int index)
return index & (TX_RING_SIZE - 1);
}
-static struct macb_dma_desc *macb_tx_desc(struct macb *bp, unsigned int index)
+static struct macb_dma_desc *macb_tx_desc(struct macb_queue *queue,
+ unsigned int index)
{
- return &bp->tx_ring[macb_tx_ring_wrap(index)];
+ return &queue->tx_ring[macb_tx_ring_wrap(index)];
}
-static struct macb_tx_skb *macb_tx_skb(struct macb *bp, unsigned int index)
+static struct macb_tx_skb *macb_tx_skb(struct macb_queue *queue,
+ unsigned int index)
{
- return &bp->tx_skb[macb_tx_ring_wrap(index)];
+ return &queue->tx_skb[macb_tx_ring_wrap(index)];
}
-static dma_addr_t macb_tx_dma(struct macb *bp, unsigned int index)
+static dma_addr_t macb_tx_dma(struct macb_queue *queue, unsigned int index)
{
dma_addr_t offset;
offset = macb_tx_ring_wrap(index) * sizeof(struct macb_dma_desc);
- return bp->tx_ring_dma + offset;
+ return queue->tx_ring_dma + offset;
}
static unsigned int macb_rx_ring_wrap(unsigned int index)
@@ -490,38 +492,49 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb)
static void macb_tx_error_task(struct work_struct *work)
{
- struct macb *bp = container_of(work, struct macb, tx_error_task);
+ struct macb_queue *queue = container_of(work, struct macb_queue,
+ tx_error_task);
+ struct macb *bp = queue->bp;
struct macb_tx_skb *tx_skb;
+ struct macb_dma_desc *desc;
struct sk_buff *skb;
unsigned int tail;
+ unsigned long flags;
+
+ netdev_vdbg(bp->dev, "macb_tx_error_task: q = %u, t = %u, h = %u\n",
+ (unsigned int)(queue - bp->queues),
+ queue->tx_tail, queue->tx_head);
- netdev_vdbg(bp->dev, "macb_tx_error_task: t = %u, h = %u\n",
- bp->tx_tail, bp->tx_head);
+ /* Prevent the queue IRQ handlers from running: each of them may call
+ * macb_tx_interrupt(), which in turn may call netif_wake_subqueue().
+ * As explained below, we have to halt the transmission before updating
+ * TBQP registers so we call netif_tx_stop_all_queues() to notify the
+ * network engine about the macb/gem being halted.
+ */
+ spin_lock_irqsave(&bp->lock, flags);
/* Make sure nobody is trying to queue up new packets */
- netif_stop_queue(bp->dev);
+ netif_tx_stop_all_queues(bp->dev);
/*
* Stop transmission now
* (in case we have just queued new packets)
+ * macb/gem must be halted to write TBQP register
*/
if (macb_halt_tx(bp))
/* Just complain for now, reinitializing TX path can be good */
netdev_err(bp->dev, "BUG: halt tx timed out\n");
- /* No need for the lock here as nobody will interrupt us anymore */
-
/*
* Treat frames in TX queue including the ones that caused the error.
* Free transmit buffers in upper layer.
*/
- for (tail = bp->tx_tail; tail != bp->tx_head; tail++) {
- struct macb_dma_desc *desc;
- u32 ctrl;
+ for (tail = queue->tx_tail; tail != queue->tx_head; tail++) {
+ u32 ctrl;
- desc = macb_tx_desc(bp, tail);
+ desc = macb_tx_desc(queue, tail);
ctrl = desc->ctrl;
- tx_skb = macb_tx_skb(bp, tail);
+ tx_skb = macb_tx_skb(queue, tail);
skb = tx_skb->skb;
if (ctrl & MACB_BIT(TX_USED)) {
@@ -529,7 +542,7 @@ static void macb_tx_error_task(struct work_struct *work)
while (!skb) {
macb_tx_unmap(bp, tx_skb);
tail++;
- tx_skb = macb_tx_skb(bp, tail);
+ tx_skb = macb_tx_skb(queue, tail);
skb = tx_skb->skb;
}
@@ -558,45 +571,56 @@ static void macb_tx_error_task(struct work_struct *work)
macb_tx_unmap(bp, tx_skb);
}
+ /* Set end of TX queue */
+ desc = macb_tx_desc(queue, 0);
+ desc->addr = 0;
+ desc->ctrl = MACB_BIT(TX_USED);
+
/* Make descriptor updates visible to hardware */
wmb();
/* Reinitialize the TX desc queue */
- macb_writel(bp, TBQP, bp->tx_ring_dma);
+ queue_writel(queue, TBQP, queue->tx_ring_dma);
/* Make TX ring reflect state of hardware */
- bp->tx_head = bp->tx_tail = 0;
-
- /* Now we are ready to start transmission again */
- netif_wake_queue(bp->dev);
+ queue->tx_head = 0;
+ queue->tx_tail = 0;
/* Housework before enabling TX IRQ */
macb_writel(bp, TSR, macb_readl(bp, TSR));
- macb_writel(bp, IER, MACB_TX_INT_FLAGS);
+ queue_writel(queue, IER, MACB_TX_INT_FLAGS);
+
+ /* Now we are ready to start transmission again */
+ netif_tx_start_all_queues(bp->dev);
+ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
+
+ spin_unlock_irqrestore(&bp->lock, flags);
}
-static void macb_tx_interrupt(struct macb *bp)
+static void macb_tx_interrupt(struct macb_queue *queue)
{
unsigned int tail;
unsigned int head;
u32 status;
+ struct macb *bp = queue->bp;
+ u16 queue_index = queue - bp->queues;
status = macb_readl(bp, TSR);
macb_writel(bp, TSR, status);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
- macb_writel(bp, ISR, MACB_BIT(TCOMP));
+ queue_writel(queue, ISR, MACB_BIT(TCOMP));
netdev_vdbg(bp->dev, "macb_tx_interrupt status = 0x%03lx\n",
(unsigned long)status);
- head = bp->tx_head;
- for (tail = bp->tx_tail; tail != head; tail++) {
+ head = queue->tx_head;
+ for (tail = queue->tx_tail; tail != head; tail++) {
struct macb_tx_skb *tx_skb;
struct sk_buff *skb;
struct macb_dma_desc *desc;
u32 ctrl;
- desc = macb_tx_desc(bp, tail);
+ desc = macb_tx_desc(queue, tail);
/* Make hw descriptor updates visible to CPU */
rmb();
@@ -611,7 +635,7 @@ static void macb_tx_interrupt(struct macb *bp)
/* Process all buffers of the current transmitted frame */
for (;; tail++) {
- tx_skb = macb_tx_skb(bp, tail);
+ tx_skb = macb_tx_skb(queue, tail);
skb = tx_skb->skb;
/* First, update TX stats if needed */
@@ -634,11 +658,11 @@ static void macb_tx_interrupt(struct macb *bp)
}
}
- bp->tx_tail = tail;
- if (netif_queue_stopped(bp->dev)
- && CIRC_CNT(bp->tx_head, bp->tx_tail,
- TX_RING_SIZE) <= MACB_TX_WAKEUP_THRESH)
- netif_wake_queue(bp->dev);
+ queue->tx_tail = tail;
+ if (__netif_subqueue_stopped(bp->dev, queue_index) &&
+ CIRC_CNT(queue->tx_head, queue->tx_tail,
+ TX_RING_SIZE) <= MACB_TX_WAKEUP_THRESH)
+ netif_wake_subqueue(bp->dev, queue_index);
}
static void gem_rx_refill(struct macb *bp)
@@ -949,11 +973,12 @@ static int macb_poll(struct napi_struct *napi, int budget)
static irqreturn_t macb_interrupt(int irq, void *dev_id)
{
- struct net_device *dev = dev_id;
- struct macb *bp = netdev_priv(dev);
+ struct macb_queue *queue = dev_id;
+ struct macb *bp = queue->bp;
+ struct net_device *dev = bp->dev;
u32 status;
- status = macb_readl(bp, ISR);
+ status = queue_readl(queue, ISR);
if (unlikely(!status))
return IRQ_NONE;
@@ -963,11 +988,13 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
while (status) {
/* close possible race with dev_close */
if (unlikely(!netif_running(dev))) {
- macb_writel(bp, IDR, -1);
+ queue_writel(queue, IDR, -1);
break;
}
- netdev_vdbg(bp->dev, "isr = 0x%08lx\n", (unsigned long)status);
+ netdev_vdbg(bp->dev, "queue = %u, isr = 0x%08lx\n",
+ (unsigned int)(queue - bp->queues),
+ (unsigned long)status);
if (status & MACB_RX_INT_FLAGS) {
/*
@@ -977,9 +1004,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
* is already scheduled, so disable interrupts
* now.
*/
- macb_writel(bp, IDR, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IDR, MACB_RX_INT_FLAGS);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
- macb_writel(bp, ISR, MACB_BIT(RCOMP));
+ queue_writel(queue, ISR, MACB_BIT(RCOMP));
if (napi_schedule_prep(&bp->napi)) {
netdev_vdbg(bp->dev, "scheduling RX softirq\n");
@@ -988,17 +1015,17 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
}
if (unlikely(status & (MACB_TX_ERR_FLAGS))) {
- macb_writel(bp, IDR, MACB_TX_INT_FLAGS);
- schedule_work(&bp->tx_error_task);
+ queue_writel(queue, IDR, MACB_TX_INT_FLAGS);
+ schedule_work(&queue->tx_error_task);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
- macb_writel(bp, ISR, MACB_TX_ERR_FLAGS);
+ queue_writel(queue, ISR, MACB_TX_ERR_FLAGS);
break;
}
if (status & MACB_BIT(TCOMP))
- macb_tx_interrupt(bp);
+ macb_tx_interrupt(queue);
/*
* Link change detection isn't possible with RMII, so we'll
@@ -1013,7 +1040,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
bp->hw_stats.macb.rx_overruns++;
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
- macb_writel(bp, ISR, MACB_BIT(ISR_ROVR));
+ queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
}
if (status & MACB_BIT(HRESP)) {
@@ -1025,10 +1052,10 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
netdev_err(dev, "DMA bus error: HRESP not OK\n");
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
- macb_writel(bp, ISR, MACB_BIT(HRESP));
+ queue_writel(queue, ISR, MACB_BIT(HRESP));
}
- status = macb_readl(bp, ISR);
+ status = queue_readl(queue, ISR);
}
spin_unlock(&bp->lock);
@@ -1043,10 +1070,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
*/
static void macb_poll_controller(struct net_device *dev)
{
+ struct macb *bp = netdev_priv(dev);
+ struct macb_queue *queue;
unsigned long flags;
+ unsigned int q;
local_irq_save(flags);
- macb_interrupt(dev->irq, dev);
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+ macb_interrupt(dev->irq, queue);
local_irq_restore(flags);
}
#endif
@@ -1058,10 +1089,11 @@ static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
}
static unsigned int macb_tx_map(struct macb *bp,
+ struct macb_queue *queue,
struct sk_buff *skb)
{
dma_addr_t mapping;
- unsigned int len, entry, i, tx_head = bp->tx_head;
+ unsigned int len, entry, i, tx_head = queue->tx_head;
struct macb_tx_skb *tx_skb = NULL;
struct macb_dma_desc *desc;
unsigned int offset, size, count = 0;
@@ -1075,7 +1107,7 @@ static unsigned int macb_tx_map(struct macb *bp,
while (len) {
size = min(len, bp->max_tx_length);
entry = macb_tx_ring_wrap(tx_head);
- tx_skb = &bp->tx_skb[entry];
+ tx_skb = &queue->tx_skb[entry];
mapping = dma_map_single(&bp->pdev->dev,
skb->data + offset,
@@ -1104,7 +1136,7 @@ static unsigned int macb_tx_map(struct macb *bp,
while (len) {
size = min(len, bp->max_tx_length);
entry = macb_tx_ring_wrap(tx_head);
- tx_skb = &bp->tx_skb[entry];
+ tx_skb = &queue->tx_skb[entry];
mapping = skb_frag_dma_map(&bp->pdev->dev, frag,
offset, size, DMA_TO_DEVICE);
@@ -1143,14 +1175,14 @@ static unsigned int macb_tx_map(struct macb *bp,
i = tx_head;
entry = macb_tx_ring_wrap(i);
ctrl = MACB_BIT(TX_USED);
- desc = &bp->tx_ring[entry];
+ desc = &queue->tx_ring[entry];
desc->ctrl = ctrl;
do {
i--;
entry = macb_tx_ring_wrap(i);
- tx_skb = &bp->tx_skb[entry];
- desc = &bp->tx_ring[entry];
+ tx_skb = &queue->tx_skb[entry];
+ desc = &queue->tx_ring[entry];
ctrl = (u32)tx_skb->size;
if (eof) {
@@ -1167,17 +1199,17 @@ static unsigned int macb_tx_map(struct macb *bp,
*/
wmb();
desc->ctrl = ctrl;
- } while (i != bp->tx_head);
+ } while (i != queue->tx_head);
- bp->tx_head = tx_head;
+ queue->tx_head = tx_head;
return count;
dma_error:
netdev_err(bp->dev, "TX DMA map failed\n");
- for (i = bp->tx_head; i != tx_head; i++) {
- tx_skb = macb_tx_skb(bp, i);
+ for (i = queue->tx_head; i != tx_head; i++) {
+ tx_skb = macb_tx_skb(queue, i);
macb_tx_unmap(bp, tx_skb);
}
@@ -1187,14 +1219,16 @@ static unsigned int macb_tx_map(struct macb *bp,
static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ u16 queue_index = skb_get_queue_mapping(skb);
struct macb *bp = netdev_priv(dev);
+ struct macb_queue *queue = &bp->queues[queue_index];
unsigned long flags;
unsigned int count, nr_frags, frag_size, f;
#if defined(DEBUG) && defined(VERBOSE_DEBUG)
netdev_vdbg(bp->dev,
- "start_xmit: len %u head %p data %p tail %p end %p\n",
- skb->len, skb->head, skb->data,
+ "start_xmit: queue %hu len %u head %p data %p tail %p end %p\n",
+ queue_index, skb->len, skb->head, skb->data,
skb_tail_pointer(skb), skb_end_pointer(skb));
print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_OFFSET, 16, 1,
skb->data, 16, true);
@@ -1214,16 +1248,16 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
spin_lock_irqsave(&bp->lock, flags);
/* This is a hard error, log it. */
- if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < count) {
- netif_stop_queue(dev);
+ if (CIRC_SPACE(queue->tx_head, queue->tx_tail, TX_RING_SIZE) < count) {
+ netif_stop_subqueue(dev, queue_index);
spin_unlock_irqrestore(&bp->lock, flags);
netdev_dbg(bp->dev, "tx_head = %u, tx_tail = %u\n",
- bp->tx_head, bp->tx_tail);
+ queue->tx_head, queue->tx_tail);
return NETDEV_TX_BUSY;
}
/* Map socket buffer for DMA transfer */
- if (!macb_tx_map(bp, skb)) {
+ if (!macb_tx_map(bp, queue, skb)) {
dev_kfree_skb_any(skb);
goto unlock;
}
@@ -1235,8 +1269,8 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
- if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1)
- netif_stop_queue(dev);
+ if (CIRC_SPACE(queue->tx_head, queue->tx_tail, TX_RING_SIZE) < 1)
+ netif_stop_subqueue(dev, queue_index);
unlock:
spin_unlock_irqrestore(&bp->lock, flags);
@@ -1304,20 +1338,24 @@ static void macb_free_rx_buffers(struct macb *bp)
static void macb_free_consistent(struct macb *bp)
{
- if (bp->tx_skb) {
- kfree(bp->tx_skb);
- bp->tx_skb = NULL;
- }
+ struct macb_queue *queue;
+ unsigned int q;
+
bp->macbgem_ops.mog_free_rx_buffers(bp);
if (bp->rx_ring) {
dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES,
bp->rx_ring, bp->rx_ring_dma);
bp->rx_ring = NULL;
}
- if (bp->tx_ring) {
- dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES,
- bp->tx_ring, bp->tx_ring_dma);
- bp->tx_ring = NULL;
+
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+ kfree(queue->tx_skb);
+ queue->tx_skb = NULL;
+ if (queue->tx_ring) {
+ dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES,
+ queue->tx_ring, queue->tx_ring_dma);
+ queue->tx_ring = NULL;
+ }
}
}
@@ -1354,12 +1392,27 @@ static int macb_alloc_rx_buffers(struct macb *bp)
static int macb_alloc_consistent(struct macb *bp)
{
+ struct macb_queue *queue;
+ unsigned int q;
int size;
- size = TX_RING_SIZE * sizeof(struct macb_tx_skb);
- bp->tx_skb = kmalloc(size, GFP_KERNEL);
- if (!bp->tx_skb)
- goto out_err;
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+ size = TX_RING_BYTES;
+ queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
+ &queue->tx_ring_dma,
+ GFP_KERNEL);
+ if (!queue->tx_ring)
+ goto out_err;
+ netdev_dbg(bp->dev,
+ "Allocated TX ring for queue %u of %d bytes at %08lx (mapped %p)\n",
+ q, size, (unsigned long)queue->tx_ring_dma,
+ queue->tx_ring);
+
+ size = TX_RING_SIZE * sizeof(struct macb_tx_skb);
+ queue->tx_skb = kmalloc(size, GFP_KERNEL);
+ if (!queue->tx_skb)
+ goto out_err;
+ }
size = RX_RING_BYTES;
bp->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
@@ -1370,15 +1423,6 @@ static int macb_alloc_consistent(struct macb *bp)
"Allocated RX ring of %d bytes at %08lx (mapped %p)\n",
size, (unsigned long)bp->rx_ring_dma, bp->rx_ring);
- size = TX_RING_BYTES;
- bp->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
- &bp->tx_ring_dma, GFP_KERNEL);
- if (!bp->tx_ring)
- goto out_err;
- netdev_dbg(bp->dev,
- "Allocated TX ring of %d bytes at %08lx (mapped %p)\n",
- size, (unsigned long)bp->tx_ring_dma, bp->tx_ring);
-
if (bp->macbgem_ops.mog_alloc_rx_buffers(bp))
goto out_err;
@@ -1391,15 +1435,22 @@ static int macb_alloc_consistent(struct macb *bp)
static void gem_init_rings(struct macb *bp)
{
+ struct macb_queue *queue;
+ unsigned int q;
int i;
- for (i = 0; i < TX_RING_SIZE; i++) {
- bp->tx_ring[i].addr = 0;
- bp->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+ for (i = 0; i < TX_RING_SIZE; i++) {
+ queue->tx_ring[i].addr = 0;
+ queue->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ }
+ queue->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
+ queue->tx_head = 0;
+ queue->tx_tail = 0;
}
- bp->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
- bp->rx_tail = bp->rx_prepared_head = bp->tx_head = bp->tx_tail = 0;
+ bp->rx_tail = 0;
+ bp->rx_prepared_head = 0;
gem_rx_refill(bp);
}
@@ -1418,16 +1469,21 @@ static void macb_init_rings(struct macb *bp)
bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP);
for (i = 0; i < TX_RING_SIZE; i++) {
- bp->tx_ring[i].addr = 0;
- bp->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ bp->queues[0].tx_ring[i].addr = 0;
+ bp->queues[0].tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ bp->queues[0].tx_head = 0;
+ bp->queues[0].tx_tail = 0;
}
- bp->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
+ bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
- bp->rx_tail = bp->tx_head = bp->tx_tail = 0;
+ bp->rx_tail = 0;
}
static void macb_reset_hw(struct macb *bp)
{
+ struct macb_queue *queue;
+ unsigned int q;
+
/*
* Disable RX and TX (XXX: Should we halt the transmission
* more gracefully?)
@@ -1442,8 +1498,10 @@ static void macb_reset_hw(struct macb *bp)
macb_writel(bp, RSR, -1);
/* Disable all interrupts */
- macb_writel(bp, IDR, -1);
- macb_readl(bp, ISR);
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+ queue_writel(queue, IDR, -1);
+ queue_readl(queue, ISR);
+ }
}
static u32 gem_mdc_clk_div(struct macb *bp)
@@ -1540,6 +1598,9 @@ static void macb_configure_dma(struct macb *bp)
static void macb_init_hw(struct macb *bp)
{
+ struct macb_queue *queue;
+ unsigned int q;
+
u32 config;
macb_reset_hw(bp);
@@ -1565,16 +1626,18 @@ static void macb_init_hw(struct macb *bp)
/* Initialize TX and RX buffers */
macb_writel(bp, RBQP, bp->rx_ring_dma);
- macb_writel(bp, TBQP, bp->tx_ring_dma);
+ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+ queue_writel(queue, TBQP, queue->tx_ring_dma);
+
+ /* Enable interrupts */
+ queue_writel(queue, IER,
+ MACB_RX_INT_FLAGS |
+ MACB_TX_INT_FLAGS |
+ MACB_BIT(HRESP));
+ }
/* Enable TX and RX */
macb_writel(bp, NCR, MACB_BIT(RE) | MACB_BIT(TE) | MACB_BIT(MPE));
-
- /* Enable interrupts */
- macb_writel(bp, IER, (MACB_RX_INT_FLAGS
- | MACB_TX_INT_FLAGS
- | MACB_BIT(HRESP)));
-
}
/*
@@ -1736,7 +1799,7 @@ static int macb_open(struct net_device *dev)
/* schedule a link state check */
phy_start(bp->phy_dev);
- netif_start_queue(dev);
+ netif_tx_start_all_queues(dev);
return 0;
}
@@ -1746,7 +1809,7 @@ static int macb_close(struct net_device *dev)
struct macb *bp = netdev_priv(dev);
unsigned long flags;
- netif_stop_queue(dev);
+ netif_tx_stop_all_queues(dev);
napi_disable(&bp->napi);
if (bp->phy_dev)
@@ -1895,8 +1958,8 @@ static void macb_get_regs(struct net_device *dev, struct ethtool_regs *regs,
regs->version = (macb_readl(bp, MID) & ((1 << MACB_REV_SIZE) - 1))
| MACB_GREGS_VERSION;
- tail = macb_tx_ring_wrap(bp->tx_tail);
- head = macb_tx_ring_wrap(bp->tx_head);
+ tail = macb_tx_ring_wrap(bp->queues[0].tx_tail);
+ head = macb_tx_ring_wrap(bp->queues[0].tx_head);
regs_buff[0] = macb_readl(bp, NCR);
regs_buff[1] = macb_or_gem_readl(bp, NCFGR);
@@ -1909,8 +1972,8 @@ static void macb_get_regs(struct net_device *dev, struct ethtool_regs *regs,
regs_buff[8] = tail;
regs_buff[9] = head;
- regs_buff[10] = macb_tx_dma(bp, tail);
- regs_buff[11] = macb_tx_dma(bp, head);
+ regs_buff[10] = macb_tx_dma(&bp->queues[0], tail);
+ regs_buff[11] = macb_tx_dma(&bp->queues[0], head);
if (macb_is_gem(bp)) {
regs_buff[12] = gem_readl(bp, USRIO);
@@ -2061,16 +2124,44 @@ static void macb_configure_caps(struct macb *bp)
netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
}
+static void macb_probe_queues(void __iomem *mem,
+ unsigned int *queue_mask,
+ unsigned int *num_queues)
+{
+ unsigned int hw_q;
+ u32 mid;
+
+ *queue_mask = 0x1;
+ *num_queues = 1;
+
+ /* is it macb or gem ? */
+ mid = __raw_readl(mem + MACB_MID);
+ if (MACB_BFEXT(IDNUM, mid) != 0x2)
+ return;
+
+ /* bit 0 is never set but queue 0 always exists */
+ *queue_mask = __raw_readl(mem + GEM_DCFG6) & 0xff;
+ *queue_mask |= 0x1;
+
+ for (hw_q = 1; hw_q < MACB_MAX_QUEUES; ++hw_q)
+ if (*queue_mask & (1 << hw_q))
+ (*num_queues)++;
+}
+
static int __init macb_probe(struct platform_device *pdev)
{
struct macb_platform_data *pdata;
struct resource *regs;
struct net_device *dev;
struct macb *bp;
+ struct macb_queue *queue;
struct phy_device *phydev;
u32 config;
int err = -ENXIO;
const char *mac;
+ void __iomem *mem;
+ unsigned int hw_q, queue_mask, q, num_queues, q_irq = 0;
+ struct clk *pclk, *hclk, *tx_clk;
regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!regs) {
@@ -2078,72 +2169,112 @@ static int __init macb_probe(struct platform_device *pdev)
goto err_out;
}
- err = -ENOMEM;
- dev = alloc_etherdev(sizeof(*bp));
- if (!dev)
- goto err_out;
-
- SET_NETDEV_DEV(dev, &pdev->dev);
-
- bp = netdev_priv(dev);
- bp->pdev = pdev;
- bp->dev = dev;
-
- spin_lock_init(&bp->lock);
- INIT_WORK(&bp->tx_error_task, macb_tx_error_task);
-
- bp->pclk = devm_clk_get(&pdev->dev, "pclk");
- if (IS_ERR(bp->pclk)) {
- err = PTR_ERR(bp->pclk);
+ pclk = devm_clk_get(&pdev->dev, "pclk");
+ if (IS_ERR(pclk)) {
+ err = PTR_ERR(pclk);
dev_err(&pdev->dev, "failed to get macb_clk (%u)\n", err);
- goto err_out_free_dev;
+ goto err_out;
}
- bp->hclk = devm_clk_get(&pdev->dev, "hclk");
- if (IS_ERR(bp->hclk)) {
- err = PTR_ERR(bp->hclk);
+ hclk = devm_clk_get(&pdev->dev, "hclk");
+ if (IS_ERR(hclk)) {
+ err = PTR_ERR(hclk);
dev_err(&pdev->dev, "failed to get hclk (%u)\n", err);
- goto err_out_free_dev;
+ goto err_out;
}
- bp->tx_clk = devm_clk_get(&pdev->dev, "tx_clk");
+ tx_clk = devm_clk_get(&pdev->dev, "tx_clk");
- err = clk_prepare_enable(bp->pclk);
+ err = clk_prepare_enable(pclk);
if (err) {
dev_err(&pdev->dev, "failed to enable pclk (%u)\n", err);
- goto err_out_free_dev;
+ goto err_out;
}
- err = clk_prepare_enable(bp->hclk);
+ err = clk_prepare_enable(hclk);
if (err) {
dev_err(&pdev->dev, "failed to enable hclk (%u)\n", err);
goto err_out_disable_pclk;
}
- if (!IS_ERR(bp->tx_clk)) {
- err = clk_prepare_enable(bp->tx_clk);
+ if (!IS_ERR(tx_clk)) {
+ err = clk_prepare_enable(tx_clk);
if (err) {
dev_err(&pdev->dev, "failed to enable tx_clk (%u)\n",
- err);
+ err);
goto err_out_disable_hclk;
}
}
- bp->regs = devm_ioremap(&pdev->dev, regs->start, resource_size(regs));
- if (!bp->regs) {
+ err = -ENOMEM;
+ mem = devm_ioremap(&pdev->dev, regs->start, resource_size(regs));
+ if (!mem) {
dev_err(&pdev->dev, "failed to map registers, aborting.\n");
- err = -ENOMEM;
goto err_out_disable_clocks;
}
- dev->irq = platform_get_irq(pdev, 0);
- err = devm_request_irq(&pdev->dev, dev->irq, macb_interrupt, 0,
- dev->name, dev);
- if (err) {
- dev_err(&pdev->dev, "Unable to request IRQ %d (error %d)\n",
- dev->irq, err);
+ macb_probe_queues(mem, &queue_mask, &num_queues);
+ dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
+ if (!dev)
goto err_out_disable_clocks;
+
+ SET_NETDEV_DEV(dev, &pdev->dev);
+
+ bp = netdev_priv(dev);
+ bp->pdev = pdev;
+ bp->dev = dev;
+ bp->regs = mem;
+ bp->num_queues = num_queues;
+ bp->pclk = pclk;
+ bp->hclk = hclk;
+ bp->tx_clk = tx_clk;
+
+ spin_lock_init(&bp->lock);
+
+ /* set the queue register mapping once for all: queue0 has a special
+ * register mapping but we don't want to test the queue index then
+ * compute the corresponding register offset at run time.
+ */
+ for (hw_q = 0; hw_q < MACB_MAX_QUEUES; ++hw_q) {
+ if (!(queue_mask & (1 << hw_q)))
+ continue;
+
+ queue = &bp->queues[q_irq];
+ queue->bp = bp;
+ if (hw_q) {
+ queue->ISR = GEM_ISR(hw_q - 1);
+ queue->IER = GEM_IER(hw_q - 1);
+ queue->IDR = GEM_IDR(hw_q - 1);
+ queue->IMR = GEM_IMR(hw_q - 1);
+ queue->TBQP = GEM_TBQP(hw_q - 1);
+ } else {
+ /* queue0 uses legacy registers */
+ queue->ISR = MACB_ISR;
+ queue->IER = MACB_IER;
+ queue->IDR = MACB_IDR;
+ queue->IMR = MACB_IMR;
+ queue->TBQP = MACB_TBQP;
+ }
+
+ /* get irq: here we use the linux queue index, not the hardware
+ * queue index. the queue irq definitions in the device tree
+ * must remove the optional gaps that could exist in the
+ * hardware queue mask.
+ */
+ queue->irq = platform_get_irq(pdev, q_irq);
+ err = devm_request_irq(&pdev->dev, queue->irq, macb_interrupt,
+ 0, dev->name, queue);
+ if (err) {
+ dev_err(&pdev->dev,
+ "Unable to request IRQ %d (error %d)\n",
+ queue->irq, err);
+ goto err_out_free_irq;
+ }
+
+ INIT_WORK(&queue->tx_error_task, macb_tx_error_task);
+ q_irq++;
}
+ dev->irq = bp->queues[0].irq;
dev->netdev_ops = &macb_netdev_ops;
netif_napi_add(dev, &bp->napi, macb_poll, 64);
@@ -2219,7 +2350,7 @@ static int __init macb_probe(struct platform_device *pdev)
err = register_netdev(dev);
if (err) {
dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
- goto err_out_disable_clocks;
+ goto err_out_free_irq;
}
err = macb_mii_init(bp);
@@ -2242,15 +2373,17 @@ static int __init macb_probe(struct platform_device *pdev)
err_out_unregister_netdev:
unregister_netdev(dev);
+err_out_free_irq:
+ for (q = 0, queue = bp->queues; q < q_irq; ++q, ++queue)
+ devm_free_irq(&pdev->dev, queue->irq, queue);
+ free_netdev(dev);
err_out_disable_clocks:
- if (!IS_ERR(bp->tx_clk))
- clk_disable_unprepare(bp->tx_clk);
+ if (!IS_ERR(tx_clk))
+ clk_disable_unprepare(tx_clk);
err_out_disable_hclk:
- clk_disable_unprepare(bp->hclk);
+ clk_disable_unprepare(hclk);
err_out_disable_pclk:
- clk_disable_unprepare(bp->pclk);
-err_out_free_dev:
- free_netdev(dev);
+ clk_disable_unprepare(pclk);
err_out:
return err;
}
@@ -2259,6 +2392,8 @@ static int __exit macb_remove(struct platform_device *pdev)
{
struct net_device *dev;
struct macb *bp;
+ struct macb_queue *queue;
+ unsigned int q;
dev = platform_get_drvdata(pdev);
@@ -2270,11 +2405,14 @@ static int __exit macb_remove(struct platform_device *pdev)
kfree(bp->mii_bus->irq);
mdiobus_free(bp->mii_bus);
unregister_netdev(dev);
+ queue = bp->queues;
+ for (q = 0; q < bp->num_queues; ++q, ++queue)
+ devm_free_irq(&pdev->dev, queue->irq, queue);
+ free_netdev(dev);
if (!IS_ERR(bp->tx_clk))
clk_disable_unprepare(bp->tx_clk);
clk_disable_unprepare(bp->hclk);
clk_disable_unprepare(bp->pclk);
- free_netdev(dev);
}
return 0;
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 517c09d72c4a5c2e27de75d95495bbc17f8602d7..084191b6fad2065331947c2b1d377ae943a545d1 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -12,6 +12,7 @@
#define MACB_GREGS_NBR 16
#define MACB_GREGS_VERSION 1
+#define MACB_MAX_QUEUES 8
/* MACB register offsets */
#define MACB_NCR 0x0000
@@ -89,6 +90,13 @@
#define GEM_DCFG6 0x0294
#define GEM_DCFG7 0x0298
+#define GEM_ISR(hw_q) (0x0400 + ((hw_q) << 2))
+#define GEM_TBQP(hw_q) (0x0440 + ((hw_q) << 2))
+#define GEM_RBQP(hw_q) (0x0480 + ((hw_q) << 2))
+#define GEM_IER(hw_q) (0x0600 + ((hw_q) << 2))
+#define GEM_IDR(hw_q) (0x0620 + ((hw_q) << 2))
+#define GEM_IMR(hw_q) (0x0640 + ((hw_q) << 2))
+
/* Bitfields in NCR */
#define MACB_LB_OFFSET 0
#define MACB_LB_SIZE 1
@@ -376,6 +384,10 @@
__raw_readl((port)->regs + GEM_##reg)
#define gem_writel(port, reg, value) \
__raw_writel((value), (port)->regs + GEM_##reg)
+#define queue_readl(queue, reg) \
+ __raw_readl((queue)->bp->regs + (queue)->reg)
+#define queue_writel(queue, reg, value) \
+ __raw_writel((value), (queue)->bp->regs + (queue)->reg)
/*
* Conditional GEM/MACB macros. These perform the operation to the correct
@@ -597,6 +609,23 @@ struct macb_config {
unsigned int dma_burst_length;
};
+struct macb_queue {
+ struct macb *bp;
+ int irq;
+
+ unsigned int ISR;
+ unsigned int IER;
+ unsigned int IDR;
+ unsigned int IMR;
+ unsigned int TBQP;
+
+ unsigned int tx_head, tx_tail;
+ struct macb_dma_desc *tx_ring;
+ struct macb_tx_skb *tx_skb;
+ dma_addr_t tx_ring_dma;
+ struct work_struct tx_error_task;
+};
+
struct macb {
void __iomem *regs;
@@ -607,9 +636,8 @@ struct macb {
void *rx_buffers;
size_t rx_buffer_size;
- unsigned int tx_head, tx_tail;
- struct macb_dma_desc *tx_ring;
- struct macb_tx_skb *tx_skb;
+ unsigned int num_queues;
+ struct macb_queue queues[MACB_MAX_QUEUES];
spinlock_t lock;
struct platform_device *pdev;
@@ -618,7 +646,6 @@ struct macb {
struct clk *tx_clk;
struct net_device *dev;
struct napi_struct napi;
- struct work_struct tx_error_task;
struct net_device_stats stats;
union {
struct macb_stats macb;
@@ -626,7 +653,6 @@ struct macb {
} hw_stats;
dma_addr_t rx_ring_dma;
- dma_addr_t tx_ring_dma;
dma_addr_t rx_buffers_dma;
struct macb_or_gem_ops macbgem_ops;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index a18d33fdb27107e2252bc12177d21b4f0f4aeb99..5ab5c3133acd3136df281f22487ae7ea5a5d86bf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -392,7 +392,7 @@ struct port_info {
s16 xact_addr_filt; /* index of exact MAC address filter */
u16 rss_size; /* size of VI's RSS table slice */
s8 mdio_addr;
- u8 port_type;
+ enum fw_port_type port_type;
u8 mod_type;
u8 port_id;
u8 tx_chan;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 973dbb7938c3f7c8107a5ca2bbb577f6e452e0ff..ccf3436024bc8ce8ffdc814553469a523db73c92 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2325,7 +2325,7 @@ static int identify_port(struct net_device *dev,
return t4_identify_port(adap, adap->fn, netdev2pinfo(dev)->viid, val);
}
-static unsigned int from_fw_linkcaps(unsigned int type, unsigned int caps)
+static unsigned int from_fw_linkcaps(enum fw_port_type type, unsigned int caps)
{
unsigned int v = 0;
@@ -2354,14 +2354,20 @@ static unsigned int from_fw_linkcaps(unsigned int type, unsigned int caps)
SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full |
SUPPORTED_10000baseKX4_Full;
else if (type == FW_PORT_TYPE_FIBER_XFI ||
- type == FW_PORT_TYPE_FIBER_XAUI || type == FW_PORT_TYPE_SFP) {
+ type == FW_PORT_TYPE_FIBER_XAUI ||
+ type == FW_PORT_TYPE_SFP ||
+ type == FW_PORT_TYPE_QSFP_10G ||
+ type == FW_PORT_TYPE_QSA) {
v |= SUPPORTED_FIBRE;
if (caps & FW_PORT_CAP_SPEED_1G)
v |= SUPPORTED_1000baseT_Full;
if (caps & FW_PORT_CAP_SPEED_10G)
v |= SUPPORTED_10000baseT_Full;
- } else if (type == FW_PORT_TYPE_BP40_BA)
+ } else if (type == FW_PORT_TYPE_BP40_BA ||
+ type == FW_PORT_TYPE_QSFP) {
v |= SUPPORTED_40000baseSR4_Full;
+ v |= SUPPORTED_FIBRE;
+ }
if (caps & FW_PORT_CAP_ANEG)
v |= SUPPORTED_Autoneg;
@@ -2396,6 +2402,7 @@ static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
cmd->port = PORT_FIBRE;
else if (p->port_type == FW_PORT_TYPE_SFP ||
p->port_type == FW_PORT_TYPE_QSFP_10G ||
+ p->port_type == FW_PORT_TYPE_QSA ||
p->port_type == FW_PORT_TYPE_QSFP) {
if (p->mod_type == FW_PORT_MOD_TYPE_LR ||
p->mod_type == FW_PORT_MOD_TYPE_SR ||
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index beaf80a6214b9175d36b0c32d15ed3eccb866dd2..291b6f219708c946c5ad01c9bc0485d06dc7f19c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -560,6 +560,7 @@ enum fw_flowc_mnem {
FW_FLOWC_MNEM_RCVNXT,
FW_FLOWC_MNEM_SNDBUF,
FW_FLOWC_MNEM_MSS,
+ FW_FLOWC_MNEM_TXDATAPLEN_MAX,
};
struct fw_flowc_mnemval {
@@ -2470,6 +2471,7 @@ enum fw_port_type {
FW_PORT_TYPE_BP4_AP,
FW_PORT_TYPE_QSFP_10G,
FW_PORT_TYPE_QSFP,
+ FW_PORT_TYPE_QSA,
FW_PORT_TYPE_BP40_BA,
FW_PORT_TYPE_NONE = FW_PORT_CMD_PTYPE_M
diff --git a/drivers/net/ethernet/davicom/Kconfig b/drivers/net/ethernet/davicom/Kconfig
index 316c5e5a92ad450372cd5eb8fa81b70a7df795a7..7ec2d74f94d3f3fdf70edef20779b3a2bc40bd7c 100644
--- a/drivers/net/ethernet/davicom/Kconfig
+++ b/drivers/net/ethernet/davicom/Kconfig
@@ -4,7 +4,7 @@
config DM9000
tristate "DM9000 support"
- depends on ARM || BLACKFIN || MIPS || COLDFIRE
+ depends on ARM || BLACKFIN || MIPS || COLDFIRE || NIOS2
select CRC32
select MII
---help---
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index ee1ecb146df7de40e126cbffca7c80528254ef8e..eb088b129bc717ae786880b4d08d5d3260ddc1c7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -615,14 +615,14 @@ static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
rx_desc = FM10K_RX_DESC(rx_ring, rx_ring->next_to_clean);
- if (!fm10k_test_staterr(rx_desc, FM10K_RXD_STATUS_DD))
+ if (!rx_desc->d.staterr)
break;
/* This memory barrier is needed to keep us from reading
* any other fields out of the rx_desc until we know the
- * RXD_STATUS_DD bit is set
+ * descriptor has been written back
*/
- rmb();
+ dma_rmb();
/* retrieve a buffer from the ring */
skb = fm10k_fetch_rx_buffer(rx_ring, rx_desc, skb);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 2e526d4904a6912638030297a9f60abd792d5f53..ff59897a946363442d657e84784962c6a600a45b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6910,14 +6910,14 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean);
- if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_DD))
+ if (!rx_desc->wb.upper.status_error)
break;
/* This memory barrier is needed to keep us from reading
* any other fields out of the rx_desc until we know the
- * RXD_STAT_DD bit is set
+ * descriptor has been written back
*/
- rmb();
+ dma_rmb();
/* retrieve a buffer from the ring */
skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 798b05556e1bcced693bc680ac076992e1a59e85..2ed2c7de230444f88c3f06451d7cc8a7167f5f05 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2009,15 +2009,14 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
- if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD))
+ if (!rx_desc->wb.upper.status_error)
break;
- /*
- * This memory barrier is needed to keep us from reading
+ /* This memory barrier is needed to keep us from reading
* any other fields out of the rx_desc until we know the
- * RXD_STAT_DD bit is set
+ * descriptor has been written back
*/
- rmb();
+ dma_rmb();
/* retrieve a buffer from the ring */
skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc);
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 4a1be34d7214c9971e5c254f61bbfa3ff647bfe9..44ce7d88f554638035090cf165f0ffdbf1b2902f 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1364,8 +1364,8 @@ jme_link_change_tasklet(unsigned long arg)
jme_free_rx_resources(jme);
out_enable_tasklet:
tasklet_enable(&jme->txclean_task);
- tasklet_hi_enable(&jme->rxclean_task);
- tasklet_hi_enable(&jme->rxempty_task);
+ tasklet_enable(&jme->rxclean_task);
+ tasklet_enable(&jme->rxempty_task);
out:
atomic_inc(&jme->link_changing);
}
@@ -2408,8 +2408,8 @@ static inline void jme_resume_rx(struct jme_adapter *jme)
if (test_bit(JME_FLAG_POLL, &jme->flags)) {
JME_NAPI_ENABLE(jme);
} else {
- tasklet_hi_enable(&jme->rxclean_task);
- tasklet_hi_enable(&jme->rxempty_task);
+ tasklet_enable(&jme->rxclean_task);
+ tasklet_enable(&jme->rxempty_task);
}
dpi->cur = PCC_P1;
dpi->attempt = PCC_P1;
@@ -3290,8 +3290,8 @@ jme_suspend(struct device *dev)
}
tasklet_enable(&jme->txclean_task);
- tasklet_hi_enable(&jme->rxclean_task);
- tasklet_hi_enable(&jme->rxempty_task);
+ tasklet_enable(&jme->rxclean_task);
+ tasklet_enable(&jme->rxempty_task);
jme_powersave_phy(jme);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3dad7e88495210710a800951c8c7849ccbfa3c5f..14a1c5cec3a59fc8699858a507ca3b077b45981b 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5919,7 +5919,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0x0000, ERIAR_EXGMAC);
}
-static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
+static void rtl_hw_start_8168g(struct rtl8169_private *tp)
{
void __iomem *ioaddr = tp->mmio_addr;
struct pci_dev *pdev = tp->pci_dev;
@@ -5954,6 +5954,24 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
rtl_pcie_state_l2l3_enable(tp, false);
}
+static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+ static const struct ephy_info e_info_8168g_1[] = {
+ { 0x00, 0x0000, 0x0008 },
+ { 0x0c, 0x37d0, 0x0820 },
+ { 0x1e, 0x0000, 0x0001 },
+ { 0x19, 0x8000, 0x0000 }
+ };
+
+ rtl_hw_start_8168g(tp);
+
+ /* disable aspm and clock request before access ephy */
+ RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn);
+ RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en);
+ rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1));
+}
+
static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
{
void __iomem *ioaddr = tp->mmio_addr;
@@ -5964,7 +5982,7 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
{ 0x1e, 0xffff, 0x20eb }
};
- rtl_hw_start_8168g_1(tp);
+ rtl_hw_start_8168g(tp);
/* disable aspm and clock request before access ephy */
RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn);
@@ -5983,7 +6001,7 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
{ 0x1e, 0x0000, 0x2000 }
};
- rtl_hw_start_8168g_1(tp);
+ rtl_hw_start_8168g(tp);
/* disable aspm and clock request before access ephy */
RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn);
@@ -6605,6 +6623,9 @@ static inline void rtl8169_mark_to_asic(struct RxDesc *desc, u32 rx_buf_sz)
{
u32 eor = le32_to_cpu(desc->opts1) & RingEnd;
+ /* Force memory writes to complete before releasing descriptor */
+ dma_wmb();
+
desc->opts1 = cpu_to_le32(DescOwn | eor | rx_buf_sz);
}
@@ -6612,7 +6633,6 @@ static inline void rtl8169_map_to_asic(struct RxDesc *desc, dma_addr_t mapping,
u32 rx_buf_sz)
{
desc->addr = cpu_to_le64(mapping);
- wmb();
rtl8169_mark_to_asic(desc, rx_buf_sz);
}
@@ -7073,16 +7093,18 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
skb_tx_timestamp(skb);
- wmb();
+ /* Force memory writes to complete before releasing descriptor */
+ dma_wmb();
/* Anti gcc 2.95.3 bugware (sic) */
status = opts[0] | len | (RingEnd * !((entry + 1) % NUM_TX_DESC));
txd->opts1 = cpu_to_le32(status);
- tp->cur_tx += frags + 1;
-
+ /* Force all memory writes to complete before notifying device */
wmb();
+ tp->cur_tx += frags + 1;
+
RTL_W8(TxPoll, NPQ);
mmiowb();
@@ -7181,11 +7203,16 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
struct ring_info *tx_skb = tp->tx_skb + entry;
u32 status;
- rmb();
status = le32_to_cpu(tp->TxDescArray[entry].opts1);
if (status & DescOwn)
break;
+ /* This barrier is needed to keep us from reading
+ * any other fields out of the Tx descriptor until
+ * we know the status of DescOwn
+ */
+ dma_rmb();
+
rtl8169_unmap_tx_skb(&tp->pci_dev->dev, tx_skb,
tp->TxDescArray + entry);
if (status & LastFrag) {
@@ -7280,11 +7307,16 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget
struct RxDesc *desc = tp->RxDescArray + entry;
u32 status;
- rmb();
status = le32_to_cpu(desc->opts1) & tp->opts1_mask;
-
if (status & DescOwn)
break;
+
+ /* This barrier is needed to keep us from reading
+ * any other fields out of the Rx descriptor until
+ * we know the status of DescOwn
+ */
+ dma_rmb();
+
if (unlikely(status & RxRES)) {
netif_info(tp, rx_err, dev, "Rx ERROR. status = %08x\n",
status);
@@ -7346,7 +7378,6 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget
}
release_descriptor:
desc->opts2 = 0;
- wmb();
rtl8169_mark_to_asic(desc, rx_buf_sz);
}
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 753630f5d3d35d15ad0d596ccff5c082bcc7bbbe..627926800ff38fe16467c099cb58517cf37456a1 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -6,7 +6,7 @@ config NET_VENDOR_SMSC
bool "SMC (SMSC)/Western Digital devices"
default y
depends on ARM || ISA || MAC || ARM64 || MIPS || M32R || SUPERH || \
- BLACKFIN || MN10300 || COLDFIRE || XTENSA || PCI || PCMCIA
+ BLACKFIN || MN10300 || COLDFIRE || XTENSA || NIOS2 || PCI || PCMCIA
---help---
If you have a network (Ethernet) card belonging to this class, say Y
and read the Ethernet-HOWTO, available from
@@ -39,7 +39,7 @@ config SMC91X
select CRC32
select MII
depends on (ARM || M32R || SUPERH || MIPS || BLACKFIN || \
- MN10300 || COLDFIRE || ARM64 || XTENSA)
+ MN10300 || COLDFIRE || ARM64 || XTENSA || NIOS2)
---help---
This is a driver for SMC's 91x series of Ethernet chipsets,
including the SMC91C94 and the SMC91C111. Say Y if you want it
diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
index 47872caa0081dbc1974c4aa199f035d83986757d..3ad0e6e16c395e61c0f31bd9ab6b30b3fb6adf4e 100644
--- a/drivers/net/phy/fixed.c
+++ b/drivers/net/phy/fixed.c
@@ -274,6 +274,7 @@ struct phy_device *fixed_phy_register(unsigned int irq,
return phy;
}
+EXPORT_SYMBOL_GPL(fixed_phy_register);
static int __init fixed_mdio_bus_init(void)
{
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 69fbfc89efb697ba139228b71e8e9bb111ea185d..a83d2ceded83e033e322343009cc3a054dfb2fdf 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -75,6 +75,7 @@ typedef void (*cxgb4i_cplhandler_func)(struct cxgbi_device *, struct sk_buff *);
static void *t4_uld_add(const struct cxgb4_lld_info *);
static int t4_uld_rx_handler(void *, const __be64 *, const struct pkt_gl *);
static int t4_uld_state_change(void *, enum cxgb4_state state);
+static inline int send_tx_flowc_wr(struct cxgbi_sock *);
static const struct cxgb4_uld_info cxgb4i_uld_info = {
.name = DRV_MODULE_NAME,
@@ -157,12 +158,6 @@ static struct scsi_transport_template *cxgb4i_stt;
#define RCV_BUFSIZ_MASK 0x3FFU
#define MAX_IMM_TX_PKT_LEN 128
-static inline void set_queue(struct sk_buff *skb, unsigned int queue,
- const struct cxgbi_sock *csk)
-{
- skb->queue_mapping = queue;
-}
-
static int push_tx_frames(struct cxgbi_sock *, int);
/*
@@ -172,10 +167,14 @@ static int push_tx_frames(struct cxgbi_sock *, int);
* Returns true if a packet can be sent as an offload WR with immediate
* data. We currently use the same limit as for Ethernet packets.
*/
-static inline int is_ofld_imm(const struct sk_buff *skb)
+static inline bool is_ofld_imm(const struct sk_buff *skb)
{
- return skb->len <= (MAX_IMM_TX_PKT_LEN -
- sizeof(struct fw_ofld_tx_data_wr));
+ int len = skb->len;
+
+ if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR)))
+ len += sizeof(struct fw_ofld_tx_data_wr);
+
+ return len <= MAX_IMM_TX_PKT_LEN;
}
static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
@@ -388,13 +387,19 @@ static void send_abort_req(struct cxgbi_sock *csk)
if (unlikely(csk->state == CTP_ABORTING) || !skb || !csk->cdev)
return;
+
+ if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
+ send_tx_flowc_wr(csk);
+ cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
+ }
+
cxgbi_sock_set_state(csk, CTP_ABORTING);
cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_PENDING);
cxgbi_sock_purge_write_queue(csk);
csk->cpl_abort_req = NULL;
req = (struct cpl_abort_req *)skb->head;
- set_queue(skb, CPL_PRIORITY_DATA, csk);
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
req->cmd = CPL_ABORT_SEND_RST;
t4_set_arp_err_handler(skb, csk, abort_arp_failure);
INIT_TP_WR(req, csk->tid);
@@ -420,7 +425,7 @@ static void send_abort_rpl(struct cxgbi_sock *csk, int rst_status)
csk, csk->state, csk->flags, csk->tid, rst_status);
csk->cpl_abort_rpl = NULL;
- set_queue(skb, CPL_PRIORITY_DATA, csk);
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
INIT_TP_WR(rpl, csk->tid);
OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, csk->tid));
rpl->cmd = rst_status;
@@ -491,20 +496,40 @@ static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb)
return flits + sgl_len(cnt);
}
-static inline void send_tx_flowc_wr(struct cxgbi_sock *csk)
+#define FLOWC_WR_NPARAMS_MIN 9
+static inline int tx_flowc_wr_credits(int *nparamsp, int *flowclenp)
+{
+ int nparams, flowclen16, flowclen;
+
+ nparams = FLOWC_WR_NPARAMS_MIN;
+ flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]);
+ flowclen16 = DIV_ROUND_UP(flowclen, 16);
+ flowclen = flowclen16 * 16;
+ /*
+ * Return the number of 16-byte credits used by the FlowC request.
+ * Pass back the nparams and actual FlowC length if requested.
+ */
+ if (nparamsp)
+ *nparamsp = nparams;
+ if (flowclenp)
+ *flowclenp = flowclen;
+
+ return flowclen16;
+}
+
+static inline int send_tx_flowc_wr(struct cxgbi_sock *csk)
{
struct sk_buff *skb;
struct fw_flowc_wr *flowc;
- int flowclen, i;
+ int nparams, flowclen16, flowclen;
- flowclen = 80;
+ flowclen16 = tx_flowc_wr_credits(&nparams, &flowclen);
skb = alloc_wr(flowclen, 0, GFP_ATOMIC);
flowc = (struct fw_flowc_wr *)skb->head;
flowc->op_to_nparams =
- htonl(FW_WR_OP_V(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS_V(8));
+ htonl(FW_WR_OP_V(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS_V(nparams));
flowc->flowid_len16 =
- htonl(FW_WR_LEN16_V(DIV_ROUND_UP(72, 16)) |
- FW_WR_FLOWID_V(csk->tid));
+ htonl(FW_WR_LEN16_V(flowclen16) | FW_WR_FLOWID_V(csk->tid));
flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN;
flowc->mnemval[0].val = htonl(csk->cdev->pfvf);
flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH;
@@ -523,12 +548,10 @@ static inline void send_tx_flowc_wr(struct cxgbi_sock *csk)
flowc->mnemval[7].val = htonl(csk->advmss);
flowc->mnemval[8].mnemonic = 0;
flowc->mnemval[8].val = 0;
- for (i = 0; i < 9; i++) {
- flowc->mnemval[i].r4[0] = 0;
- flowc->mnemval[i].r4[1] = 0;
- flowc->mnemval[i].r4[2] = 0;
- }
- set_queue(skb, CPL_PRIORITY_DATA, csk);
+ flowc->mnemval[8].mnemonic = FW_FLOWC_MNEM_TXDATAPLEN_MAX;
+ flowc->mnemval[8].val = 16384;
+
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
"csk 0x%p, tid 0x%x, %u,%u,%u,%u,%u,%u,%u.\n",
@@ -537,6 +560,8 @@ static inline void send_tx_flowc_wr(struct cxgbi_sock *csk)
csk->advmss);
cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+
+ return flowclen16;
}
static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb,
@@ -545,10 +570,11 @@ static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb,
struct fw_ofld_tx_data_wr *req;
unsigned int submode = cxgbi_skcb_ulp_mode(skb) & 3;
unsigned int wr_ulp_mode = 0, val;
+ bool imm = is_ofld_imm(skb);
req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, sizeof(*req));
- if (is_ofld_imm(skb)) {
+ if (imm) {
req->op_to_immdlen = htonl(FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
FW_WR_COMPL_F |
FW_WR_IMMDLEN_V(dlen));
@@ -597,16 +623,32 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
int dlen = skb->len;
int len = skb->len;
unsigned int credits_needed;
+ int flowclen16 = 0;
skb_reset_transport_header(skb);
if (is_ofld_imm(skb))
- credits_needed = DIV_ROUND_UP(dlen +
- sizeof(struct fw_ofld_tx_data_wr), 16);
+ credits_needed = DIV_ROUND_UP(dlen, 16);
else
- credits_needed = DIV_ROUND_UP(8*calc_tx_flits_ofld(skb)
- + sizeof(struct fw_ofld_tx_data_wr),
+ credits_needed = DIV_ROUND_UP(
+ 8 * calc_tx_flits_ofld(skb),
+ 16);
+
+ if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR)))
+ credits_needed += DIV_ROUND_UP(
+ sizeof(struct fw_ofld_tx_data_wr),
16);
+ /*
+ * Assumes the initial credits is large enough to support
+ * fw_flowc_wr plus largest possible first payload
+ */
+ if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
+ flowclen16 = send_tx_flowc_wr(csk);
+ csk->wr_cred -= flowclen16;
+ csk->wr_una_cred += flowclen16;
+ cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
+ }
+
if (csk->wr_cred < credits_needed) {
log_debug(1 << CXGBI_DBG_PDU_TX,
"csk 0x%p, skb %u/%u, wr %d < %u.\n",
@@ -615,8 +657,8 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
break;
}
__skb_unlink(skb, &csk->write_queue);
- set_queue(skb, CPL_PRIORITY_DATA, csk);
- skb->csum = credits_needed;
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
+ skb->csum = credits_needed + flowclen16;
csk->wr_cred -= credits_needed;
csk->wr_una_cred += credits_needed;
cxgbi_sock_enqueue_wr(csk, skb);
@@ -627,12 +669,6 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
csk->wr_cred, csk->wr_una_cred);
if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR))) {
- if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
- send_tx_flowc_wr(csk);
- skb->csum += 5;
- csk->wr_cred -= 5;
- csk->wr_una_cred += 5;
- }
len += cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
make_tx_data_wr(csk, skb, dlen, len, credits_needed,
req_completion);
@@ -807,6 +843,13 @@ static void csk_act_open_retry_timer(unsigned long data)
}
+static inline bool is_neg_adv(unsigned int status)
+{
+ return status == CPL_ERR_RTX_NEG_ADVICE ||
+ status == CPL_ERR_KEEPALV_NEG_ADVICE ||
+ status == CPL_ERR_PERSIST_NEG_ADVICE;
+}
+
static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
{
struct cxgbi_sock *csk;
@@ -828,7 +871,7 @@ static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
"csk 0x%p,%u,0x%lx. ", (&csk->saddr), (&csk->daddr),
atid, tid, status, csk, csk->state, csk->flags);
- if (status == CPL_ERR_RTX_NEG_ADVICE)
+ if (is_neg_adv(status))
goto rel_skb;
module_put(THIS_MODULE);
@@ -934,8 +977,7 @@ static void do_abort_req_rss(struct cxgbi_device *cdev, struct sk_buff *skb)
(&csk->saddr), (&csk->daddr),
csk, csk->state, csk->flags, csk->tid, req->status);
- if (req->status == CPL_ERR_RTX_NEG_ADVICE ||
- req->status == CPL_ERR_PERSIST_NEG_ADVICE)
+ if (is_neg_adv(req->status))
goto rel_skb;
cxgbi_sock_get(csk);
@@ -989,6 +1031,27 @@ static void do_abort_rpl_rss(struct cxgbi_device *cdev, struct sk_buff *skb)
__kfree_skb(skb);
}
+static void do_rx_data(struct cxgbi_device *cdev, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_rx_data *cpl = (struct cpl_rx_data *)skb->data;
+ unsigned int tid = GET_TID(cpl);
+ struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
+ struct tid_info *t = lldi->tids;
+
+ csk = lookup_tid(t, tid);
+ if (!csk) {
+ pr_err("can't find connection for tid %u.\n", tid);
+ } else {
+ /* not expecting this, reset the connection. */
+ pr_err("csk 0x%p, tid %u, rcv cpl_rx_data.\n", csk, tid);
+ spin_lock_bh(&csk->lock);
+ send_abort_req(csk);
+ spin_unlock_bh(&csk->lock);
+ }
+ __kfree_skb(skb);
+}
+
static void do_rx_iscsi_hdr(struct cxgbi_device *cdev, struct sk_buff *skb)
{
struct cxgbi_sock *csk;
@@ -1408,6 +1471,7 @@ cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
[CPL_SET_TCB_RPL] = do_set_tcb_rpl,
[CPL_RX_DATA_DDP] = do_rx_data_ddp,
[CPL_RX_ISCSI_DDP] = do_rx_data_ddp,
+ [CPL_RX_DATA] = do_rx_data,
};
int cxgb4i_ofld_init(struct cxgbi_device *cdev)
@@ -1485,7 +1549,7 @@ static int ddp_ppod_write_idata(struct cxgbi_device *cdev, unsigned int port_id,
return -ENOMEM;
}
req = (struct ulp_mem_io *)skb->head;
- set_queue(skb, CPL_PRIORITY_CONTROL, NULL);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);
ulp_mem_io_set_hdr(lldi, req, wr_len, dlen, pm_addr);
idata = (struct ulptx_idata *)(req + 1);
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 7da59c38a69ec97cf15507876122151222e52fe1..eb58afcfb73b4c7bbff39a33da272ab9d52e1c39 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -2294,10 +2294,12 @@ int cxgbi_conn_xmit_pdu(struct iscsi_task *task)
return err;
}
- kfree_skb(skb);
log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
"itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
task->itt, skb, skb->len, skb->data_len, err);
+
+ kfree_skb(skb);
+
iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
return err;
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index 2c7cb1c0c453d307418afc2eb4d73bb103c6c1f0..aba1af720df653548a6c1b03934780d804c05500 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -317,8 +317,8 @@ static inline void cxgbi_skcb_clear_flag(struct sk_buff *skb,
__clear_bit(flag, &(cxgbi_skcb_flags(skb)));
}
-static inline int cxgbi_skcb_test_flag(struct sk_buff *skb,
- enum cxgbi_skcb_flags flag)
+static inline int cxgbi_skcb_test_flag(const struct sk_buff *skb,
+ enum cxgbi_skcb_flags flag)
{
return test_bit(flag, &(cxgbi_skcb_flags(skb)));
}
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 1402fa855388985282ff05e157b3388e85114d92..f5c40b0fadc2a50be563304727db2e7ad7fe6699 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -42,6 +42,14 @@
#define wmb() mb()
#endif
+#ifndef dma_rmb
+#define dma_rmb() rmb()
+#endif
+
+#ifndef dma_wmb
+#define dma_wmb() wmb()
+#endif
+
#ifndef read_barrier_depends
#define read_barrier_depends() do { } while (0)
#endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 69517a24bc50678e4f2d69d931b9586cb76a9b69..d9b05b5bf8c7954f63ace548e0a6348f5fa0e327 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -556,12 +556,6 @@ static inline void tasklet_enable(struct tasklet_struct *t)
atomic_dec(&t->count);
}
-static inline void tasklet_hi_enable(struct tasklet_struct *t)
-{
- smp_mb__before_atomic();
- atomic_dec(&t->count);
-}
-
extern void tasklet_kill(struct tasklet_struct *t);
extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
extern void tasklet_init(struct tasklet_struct *t,
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 376805005cc7f8a6d18dab16229a2560d877ed19..118956448cf6e4aa9a3609ccf7455a04596e24bf 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -579,11 +579,12 @@ static int vlan_dev_init(struct net_device *dev)
(1<<__LINK_STATE_PRESENT);
dev->hw_features = NETIF_F_ALL_CSUM | NETIF_F_SG |
- NETIF_F_FRAGLIST | NETIF_F_ALL_TSO |
+ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
NETIF_F_HIGHDMA | NETIF_F_SCTP_CSUM |
NETIF_F_ALL_FCOE;
- dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
+ dev->features |= real_dev->vlan_features | NETIF_F_LLTX |
+ NETIF_F_GSO_SOFTWARE;
dev->gso_max_size = real_dev->gso_max_size;
if (dev->features & NETIF_F_VLAN_FEATURES)
netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n");
@@ -648,7 +649,7 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
features |= NETIF_F_RXCSUM;
features = netdev_intersect_features(features, real_dev->features);
- features |= old_features & NETIF_F_SOFT_FEATURES;
+ features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE);
features |= NETIF_F_LLTX;
return features;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 528380a3e296001b9c727e9f35e07f403d7f050b..515569ffde8a16af9eea82cc85ded4f8d5ce59cc 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -512,7 +512,7 @@ static int dsa_slave_fixed_link_update(struct net_device *dev,
}
/* slave device setup *******************************************************/
-static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
+static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
struct net_device *slave_dev)
{
struct dsa_switch *ds = p->parent;
@@ -533,7 +533,7 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
ret = of_phy_register_fixed_link(port_dn);
if (ret) {
netdev_err(slave_dev, "failed to register fixed PHY\n");
- return;
+ return ret;
}
phy_is_fixed = true;
phy_dn = port_dn;
@@ -555,12 +555,17 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
*/
if (!p->phy) {
p->phy = ds->slave_mii_bus->phy_map[p->port];
+ if (!p->phy)
+ return -ENODEV;
+
phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
p->phy_interface);
} else {
netdev_info(slave_dev, "attached PHY at address %d [%s]\n",
p->phy->addr, p->phy->drv->name);
}
+
+ return 0;
}
int dsa_slave_suspend(struct net_device *slave_dev)
@@ -653,12 +658,17 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
p->old_link = -1;
p->old_duplex = -1;
- dsa_slave_phy_setup(p, slave_dev);
+ ret = dsa_slave_phy_setup(p, slave_dev);
+ if (ret) {
+ free_netdev(slave_dev);
+ return NULL;
+ }
ret = register_netdev(slave_dev);
if (ret) {
netdev_err(master, "error %d registering interface %s\n",
ret, slave_dev->name);
+ phy_disconnect(p->phy);
free_netdev(slave_dev);
return NULL;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e9cb2588e4161c41613c0e50a17ea91b7416a514..18bcaf2ff2fd54627894f6ac28ebc07833739585 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1143,8 +1143,9 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen)
put_child(tp, cindex, (struct rt_trie_node *)tn);
} else {
rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
- tp = tn;
}
+
+ tp = tn;
}
if (tp && tp->pos + tp->bits > 32)