Staging: Improvments to Octeon Ethernet driver.

index 6f2acf0..1460d08 100644
@@ -193,7 +193,7 @@ static void octeon_irq_ciu0_enable_v2(unsigned int irq)
  * Disable the irq on the current core for chips that have the EN*_W1{S,C}
  * registers.
  */
-static void octeon_irq_ciu0_disable_v2(unsigned int irq)
+static void octeon_irq_ciu0_ack_v2(unsigned int irq)
 {
 	int index = cvmx_get_core_num() * 2;
 	u64 mask = 1ull << (irq - OCTEON_IRQ_WORKQ0);

@@ -202,6 +202,20 @@ static void octeon_irq_ciu0_disable_v2(unsigned int irq)
 }
 
 /*
+ * Enable the irq on the current core for chips that have the EN*_W1{S,C}
+ * registers.
+ */
+static void octeon_irq_ciu0_eoi_v2(unsigned int irq)
+{
+	struct irq_desc *desc = irq_desc + irq;
+	int index = cvmx_get_core_num() * 2;
+	u64 mask = 1ull << (irq - OCTEON_IRQ_WORKQ0);
+
+	if ((desc->status & IRQ_DISABLED) == 0)
+		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1S(index), mask);
+}
+
+/*
  * Disable the irq on the all cores for chips that have the EN*_W1{S,C}
  * registers.
  */

@@ -272,8 +286,8 @@ static struct irq_chip octeon_irq_chip_ciu0_v2 = {
 	.name = "CIU0",
 	.enable = octeon_irq_ciu0_enable_v2,
 	.disable = octeon_irq_ciu0_disable_all_v2,
-	.ack = octeon_irq_ciu0_disable_v2,
-	.eoi = octeon_irq_ciu0_enable_v2,
+	.ack = octeon_irq_ciu0_ack_v2,
+	.eoi = octeon_irq_ciu0_eoi_v2,
 #ifdef CONFIG_SMP
 	.set_affinity = octeon_irq_ciu0_set_affinity_v2,
 #endif

@@ -374,7 +388,7 @@ static void octeon_irq_ciu1_enable_v2(unsigned int irq)
  * Disable the irq on the current core for chips that have the EN*_W1{S,C}
  * registers.
  */
-static void octeon_irq_ciu1_disable_v2(unsigned int irq)
+static void octeon_irq_ciu1_ack_v2(unsigned int irq)
 {
 	int index = cvmx_get_core_num() * 2 + 1;
 	u64 mask = 1ull << (irq - OCTEON_IRQ_WDOG0);

@@ -383,6 +397,20 @@ static void octeon_irq_ciu1_disable_v2(unsigned int irq)
 }
 
 /*
+ * Enable the irq on the current core for chips that have the EN*_W1{S,C}
+ * registers.
+ */
+static void octeon_irq_ciu1_eoi_v2(unsigned int irq)
+{
+	struct irq_desc *desc = irq_desc + irq;
+	int index = cvmx_get_core_num() * 2 + 1;
+	u64 mask = 1ull << (irq - OCTEON_IRQ_WDOG0);
+
+	if ((desc->status & IRQ_DISABLED) == 0)
+		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1S(index), mask);
+}
+
+/*
  * Disable the irq on the all cores for chips that have the EN*_W1{S,C}
  * registers.
  */

@@ -455,8 +483,8 @@ static struct irq_chip octeon_irq_chip_ciu1_v2 = {
 	.name = "CIU0",
 	.enable = octeon_irq_ciu1_enable_v2,
 	.disable = octeon_irq_ciu1_disable_all_v2,
-	.ack = octeon_irq_ciu1_disable_v2,
-	.eoi = octeon_irq_ciu1_enable_v2,
+	.ack = octeon_irq_ciu1_ack_v2,
+	.eoi = octeon_irq_ciu1_eoi_v2,
 #ifdef CONFIG_SMP
 	.set_affinity = octeon_irq_ciu1_set_affinity_v2,
 #endif

index f13131b..9c4910e 100644
@@ -41,17 +41,10 @@
  *      Tells the driver to populate the packet buffers with kernel skbuffs.
  *      This allows the driver to receive packets without copying them. It also
  *      means that 32bit userspace can't access the packet buffers.
- *  USE_32BIT_SHARED
- *      This define tells the driver to allocate memory for buffers from the
- *      32bit sahred region instead of the kernel memory space.
  *  USE_HW_TCPUDP_CHECKSUM
  *      Controls if the Octeon TCP/UDP checksum engine is used for packet
  *      output. If this is zero, the kernel will perform the checksum in
  *      software.
- *  USE_MULTICORE_RECEIVE
- *      Process receive interrupts on multiple cores. This spreads the network
- *      load across the first 8 processors. If ths is zero, only one core
- *      processes incomming packets.
  *  USE_ASYNC_IOBDMA
  *      Use asynchronous IO access to hardware. This uses Octeon's asynchronous
  *      IOBDMAs to issue IO accesses without stalling. Set this to zero

@@ -75,29 +68,15 @@
 #define CONFIG_CAVIUM_RESERVE32 0
 #endif
 
-#if CONFIG_CAVIUM_RESERVE32
-#define USE_32BIT_SHARED            1
-#define USE_SKBUFFS_IN_HW           0
-#define REUSE_SKBUFFS_WITHOUT_FREE  0
-#else
-#define USE_32BIT_SHARED            0
 #define USE_SKBUFFS_IN_HW           1
 #ifdef CONFIG_NETFILTER
 #define REUSE_SKBUFFS_WITHOUT_FREE  0
 #else
 #define REUSE_SKBUFFS_WITHOUT_FREE  1
 #endif
-#endif
-
-/* Max interrupts per second per core */
-#define INTERRUPT_LIMIT             10000
 
-/* Don't limit the number of interrupts */
-/*#define INTERRUPT_LIMIT             0     */
 #define USE_HW_TCPUDP_CHECKSUM      1
 
-#define USE_MULTICORE_RECEIVE       1
-
 /* Enable Random Early Dropping under load */
 #define USE_RED                     1
 #define USE_ASYNC_IOBDMA            (CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0)

@@ -115,17 +94,10 @@
 /* Use this to not have FPA frees control L2 */
 /*#define DONT_WRITEBACK(x)         0   */
 
-/* Maximum number of packets to process per interrupt. */
-#define MAX_RX_PACKETS 120
 /* Maximum number of SKBs to try to free per xmit packet. */
 #define MAX_SKB_TO_FREE 10
 #define MAX_OUT_QUEUE_DEPTH 1000
 
-#ifndef CONFIG_SMP
-#undef USE_MULTICORE_RECEIVE
-#define USE_MULTICORE_RECEIVE 0
-#endif
-
 #define IP_PROTOCOL_TCP             6
 #define IP_PROTOCOL_UDP             0x11
 

132 lines not on this page · raw message

544 lines not on this page · raw message

index a9b72b8..a0743b8 100644
@@ -24,10 +24,29 @@
  * This file may also be available under a different license from Cavium.
  * Contact Cavium Networks for more information
 *********************************************************************/
+#include "cvmx-fau.h"
 
-irqreturn_t cvm_oct_do_interrupt(int cpl, void *dev_id);
 void cvm_oct_poll_controller(struct net_device *dev);
-void cvm_oct_tasklet_rx(unsigned long unused);
-
 void cvm_oct_rx_initialize(void);
 void cvm_oct_rx_shutdown(void);
+
+static inline void cvm_oct_rx_refill_pool(int fill_threshold)
+{
+	int number_to_free;
+	int num_freed;
+	/* Refill the packet buffer pool */
+	number_to_free =
+		cvmx_fau_fetch_and_add32(FAU_NUM_PACKET_BUFFERS_TO_FREE, 0);
+
+	if (number_to_free > fill_threshold) {
+		cvmx_fau_atomic_add32(FAU_NUM_PACKET_BUFFERS_TO_FREE,
+				      -number_to_free);
+		num_freed = cvm_oct_mem_fill_fpa(CVMX_FPA_PACKET_POOL,
+						 CVMX_FPA_PACKET_POOL_SIZE,
+						 number_to_free);
+		if (num_freed != number_to_free) {
+			cvmx_fau_atomic_add32(FAU_NUM_PACKET_BUFFERS_TO_FREE,
+					number_to_free - num_freed);
+		}
+	}
+}

358 lines not on this page · raw message

index c0bebf7..b628d8c 100644
@@ -30,28 +30,5 @@ int cvm_oct_xmit_pow(struct sk_buff *skb, struct net_device *dev);
 int cvm_oct_transmit_qos(struct net_device *dev, void *work_queue_entry,
 			 int do_free, int qos);
 void cvm_oct_tx_shutdown(struct net_device *dev);
-
-/**
- * Free dead transmit skbs.
- *
- * @priv:		The driver data
- * @skb_to_free:	The number of SKBs to free (free none if negative).
- * @qos:		The queue to free from.
- * @take_lock:		If true, acquire the skb list lock.
- */
-static inline void cvm_oct_free_tx_skbs(struct octeon_ethernet *priv,
-					int skb_to_free,
-					int qos, int take_lock)
-{
-	/* Free skbuffs not in use by the hardware.  */
-	if (skb_to_free > 0) {
-		if (take_lock)
-			spin_lock(&priv->tx_free_list[qos].lock);
-		while (skb_to_free > 0) {
-			dev_kfree_skb(__skb_dequeue(&priv->tx_free_list[qos]));
-			skb_to_free--;
-		}
-		if (take_lock)
-			spin_unlock(&priv->tx_free_list[qos].lock);
-	}
-}
+void cvm_oct_free_tx_skbs(struct octeon_ethernet *priv);
+enum hrtimer_restart cvm_oct_restart_tx(struct hrtimer *timer);

229 lines not on this page · raw message

70 lines not on this page · raw message

index 28e2de6..c4007a6 100644
@@ -53,6 +53,8 @@
 
 #include "cvmx-gmxx-defs.h"
 
+#define CVM_OCT_SKB_CB(skb)	((u64 *)((skb)->cb))
+
 /*
  * You can define GET_SKBUFF_QOS() to override how the skbuff output
  * function determines which output queue is used. The default

@@ -121,6 +123,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	uint64_t old_scratch;
 	uint64_t old_scratch2;
 	int qos;
+	int i;
 	enum {QUEUE_CORE, QUEUE_HW, QUEUE_DROP} queue_type;
 	struct octeon_ethernet *priv = netdev_priv(dev);
 	struct sk_buff *to_free_list;

@@ -171,6 +174,28 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/*
+	 * We have space for 6 segment pointers, If there will be more
+	 * than that, we must linearize.
+	 */
+	if (unlikely(skb_shinfo(skb)->nr_frags > 5)) {
+		if (unlikely(__skb_linearize(skb))) {
+			queue_type = QUEUE_DROP;
+			if (USE_ASYNC_IOBDMA) {
+				/* Get the number of skbuffs in use by the hardware */
+				CVMX_SYNCIOBDMA;
+				skb_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
+			} else {
+				/* Get the number of skbuffs in use by the hardware */
+				skb_to_free = cvmx_fau_fetch_and_add32(priv->fau + qos * 4,
+								       MAX_SKB_TO_FREE);
+			}
+			skb_to_free = cvm_oct_adjust_skb_to_free(skb_to_free, priv->fau + qos * 4);
+			spin_lock_irqsave(&priv->tx_free_list[qos].lock, flags);
+			goto skip_xmit;
+		}
+	}
+
+	/*
 	 * The CN3XXX series of parts has an errata (GMX-401) which
 	 * causes the GMX block to hang if a collision occurs towards
 	 * the end of a <68 byte packet. As a workaround for this, we

@@ -198,13 +223,6 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	/* Build the PKO buffer pointer */
-	hw_buffer.u64 = 0;
-	hw_buffer.s.addr = cvmx_ptr_to_phys(skb->data);
-	hw_buffer.s.pool = 0;
-	hw_buffer.s.size =
-	    (unsigned long)skb_end_pointer(skb) - (unsigned long)skb->head;
-
 	/* Build the PKO command */
 	pko_command.u64 = 0;
 	pko_command.s.n2 = 1;	/* Don't pollute L2 with the outgoing packet */

@@ -215,6 +233,31 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	pko_command.s.dontfree = 1;
 	pko_command.s.reg0 = priv->fau + qos * 4;
+
+	/* Build the PKO buffer pointer */
+	hw_buffer.u64 = 0;
+	if (skb_shinfo(skb)->nr_frags == 0) {
+		hw_buffer.s.addr = XKPHYS_TO_PHYS(skb->data);
+		hw_buffer.s.pool = 0;
+		hw_buffer.s.size = skb->len;
+	} else {
+		hw_buffer.s.addr = XKPHYS_TO_PHYS(skb->data);
+		hw_buffer.s.pool = 0;
+		hw_buffer.s.size = skb_headlen(skb);
+		CVM_OCT_SKB_CB(skb)[0] = hw_buffer.u64;
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			struct skb_frag_struct *fs = skb_shinfo(skb)->frags + i;
+			hw_buffer.s.addr = XKPHYS_TO_PHYS(page_address(fs->page) + fs->page_offset);
+			hw_buffer.s.size = fs->size;
+			CVM_OCT_SKB_CB(skb)[i + 1] = hw_buffer.u64;
+		}
+		hw_buffer.s.addr = XKPHYS_TO_PHYS(CVM_OCT_SKB_CB(skb));
+		hw_buffer.s.size = skb_shinfo(skb)->nr_frags + 1;
+		pko_command.s.segs = skb_shinfo(skb)->nr_frags + 1;
+		pko_command.s.gather = 1;
+		goto dont_put_skbuff_in_hw;
+	}
+
 	/*
 	 * See if we can put this skb in the FPA pool. Any strange
 	 * behavior from the Linux networking stack will most likely

index 2fc1e8e..3bc9a7c 100644
@@ -485,8 +485,11 @@ int cvm_oct_common_init(struct net_device *dev)
 	    && (always_use_pow || strstr(pow_send_list, dev->name)))
 		priv->queue = -1;
 
-	if (priv->queue != -1 && USE_HW_TCPUDP_CHECKSUM)
-		dev->features |= NETIF_F_IP_CSUM;
+	if (priv->queue != -1) {
+		dev->features |= NETIF_F_SG;
+		if (USE_HW_TCPUDP_CHECKSUM)
+			dev->features |= NETIF_F_IP_CSUM;
+	}
 
 	/* We do our own locking, Linux doesn't need to */
 	dev->features |= NETIF_F_LLTX;