e1000: multi-queue defines/modification to data structures

defines/modifies data structures, function prototypes and changes to the
driver rendering it capable of handling <n> tx/rx queues

Signed-off-by: Mallikarjuna R Chilakala <mallikarjuna.chilakala@intel.com>
Signed-off-by: Ganesh Venkatesan <ganesh.venkatesan@intel.com>
Signed-off-by: John Ronciak <john.ronciak@intel.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>

drivers/net/e1000/e1000.h

@@ -72,6 +72,10 @@
 #include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
+#ifdef CONFIG_E1000_MQ
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#endif
 
 #define BAR_0		0
 #define BAR_1		1
@@ -168,7 +172,30 @@ struct e1000_buffer {
 struct e1000_ps_page { struct page *ps_page[MAX_PS_BUFFERS]; };
 struct e1000_ps_page_dma { uint64_t ps_page_dma[MAX_PS_BUFFERS]; };
 
-struct e1000_desc_ring {
+struct e1000_tx_ring {
+	/* pointer to the descriptor ring memory */
+	void *desc;
+	/* physical address of the descriptor ring */
+	dma_addr_t dma;
+	/* length of descriptor ring in bytes */
+	unsigned int size;
+	/* number of descriptors in the ring */
+	unsigned int count;
+	/* next descriptor to associate a buffer with */
+	unsigned int next_to_use;
+	/* next descriptor to check for DD status bit */
+	unsigned int next_to_clean;
+	/* array of buffer information structs */
+	struct e1000_buffer *buffer_info;
+
+	struct e1000_buffer previous_buffer_info;
+	spinlock_t tx_lock;
+	uint16_t tdh;
+	uint16_t tdt;
+	uint64_t pkt;
+};
+
+struct e1000_rx_ring {
 	/* pointer to the descriptor ring memory */
 	void *desc;
 	/* physical address of the descriptor ring */
@@ -186,6 +213,10 @@ struct e1000_desc_ring {
 	/* arrays of page information for packet split */
 	struct e1000_ps_page *ps_page;
 	struct e1000_ps_page_dma *ps_page_dma;
+
+	uint16_t rdh;
+	uint16_t rdt;
+	uint64_t pkt;
 };
 
 #define E1000_DESC_UNUSED(R) \
@@ -227,9 +258,10 @@ struct e1000_adapter {
 	unsigned long led_status;
 
 	/* TX */
-	struct e1000_desc_ring tx_ring;
-	struct e1000_buffer previous_buffer_info;
-	spinlock_t tx_lock;
+	struct e1000_tx_ring *tx_ring;      /* One per active queue */
+#ifdef CONFIG_E1000_MQ
+	struct e1000_tx_ring **cpu_tx_ring; /* per-cpu */
+#endif
 	uint32_t txd_cmd;
 	uint32_t tx_int_delay;
 	uint32_t tx_abs_int_delay;
@@ -246,13 +278,26 @@ struct e1000_adapter {
 
 	/* RX */
 #ifdef CONFIG_E1000_NAPI
-	boolean_t (*clean_rx) (struct e1000_adapter *adapter, int *work_done,
-			  int work_to_do);
+	boolean_t (*clean_rx) (struct e1000_adapter *adapter,
+			       struct e1000_rx_ring *rx_ring,
+			       int *work_done, int work_to_do);
 #else
-	boolean_t (*clean_rx) (struct e1000_adapter *adapter);
+	boolean_t (*clean_rx) (struct e1000_adapter *adapter,
+			       struct e1000_rx_ring *rx_ring);
 #endif
-	void (*alloc_rx_buf) (struct e1000_adapter *adapter);
-	struct e1000_desc_ring rx_ring;
+	void (*alloc_rx_buf) (struct e1000_adapter *adapter,
+			      struct e1000_rx_ring *rx_ring);
+	struct e1000_rx_ring *rx_ring;      /* One per active queue */
+#ifdef CONFIG_E1000_NAPI
+	struct net_device *polling_netdev;  /* One per active queue */
+#endif
+#ifdef CONFIG_E1000_MQ
+	struct net_device **cpu_netdev;     /* per-cpu */
+	struct call_async_data_struct rx_sched_call_data;
+	int cpu_for_queue[4];
+#endif
+	int num_queues;
+
 	uint64_t hw_csum_err;
 	uint64_t hw_csum_good;
 	uint32_t rx_int_delay;
@@ -278,8 +323,8 @@ struct e1000_adapter {
 	struct e1000_phy_stats phy_stats;
 
 	uint32_t test_icr;
-	struct e1000_desc_ring test_tx_ring;
-	struct e1000_desc_ring test_rx_ring;
+	struct e1000_tx_ring test_tx_ring;
+	struct e1000_rx_ring test_rx_ring;
 
 
 	int msg_enable;

drivers/net/e1000/e1000_ethtool.c

@@ -39,10 +39,10 @@ extern int e1000_up(struct e1000_adapter *adapter);
 extern void e1000_down(struct e1000_adapter *adapter);
 extern void e1000_reset(struct e1000_adapter *adapter);
 extern int e1000_set_spd_dplx(struct e1000_adapter *adapter, uint16_t spddplx);
-extern int e1000_setup_rx_resources(struct e1000_adapter *adapter);
-extern int e1000_setup_tx_resources(struct e1000_adapter *adapter);
-extern void e1000_free_rx_resources(struct e1000_adapter *adapter);
-extern void e1000_free_tx_resources(struct e1000_adapter *adapter);
+extern int e1000_setup_all_rx_resources(struct e1000_adapter *adapter);
+extern int e1000_setup_all_tx_resources(struct e1000_adapter *adapter);
+extern void e1000_free_all_rx_resources(struct e1000_adapter *adapter);
+extern void e1000_free_all_tx_resources(struct e1000_adapter *adapter);
 extern void e1000_update_stats(struct e1000_adapter *adapter);
 
 struct e1000_stats {
@@ -576,8 +576,8 @@ e1000_get_ringparam(struct net_device *netdev,
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	e1000_mac_type mac_type = adapter->hw.mac_type;
-	struct e1000_desc_ring *txdr = &adapter->tx_ring;
-	struct e1000_desc_ring *rxdr = &adapter->rx_ring;
+	struct e1000_tx_ring *txdr = adapter->tx_ring;
+	struct e1000_rx_ring *rxdr = adapter->rx_ring;
 
 	ring->rx_max_pending = (mac_type < e1000_82544) ? E1000_MAX_RXD :
 		E1000_MAX_82544_RXD;
@@ -597,20 +597,40 @@ e1000_set_ringparam(struct net_device *netdev,
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	e1000_mac_type mac_type = adapter->hw.mac_type;
-	struct e1000_desc_ring *txdr = &adapter->tx_ring;
-	struct e1000_desc_ring *rxdr = &adapter->rx_ring;
-	struct e1000_desc_ring tx_old, tx_new, rx_old, rx_new;
-	int err;
+	struct e1000_tx_ring *txdr, *tx_old, *tx_new;
+	struct e1000_rx_ring *rxdr, *rx_old, *rx_new;
+	int i, err, tx_ring_size, rx_ring_size;
+
+	tx_ring_size = sizeof(struct e1000_tx_ring) * adapter->num_queues;
+	rx_ring_size = sizeof(struct e1000_rx_ring) * adapter->num_queues;
+
+	if (netif_running(adapter->netdev))
+		e1000_down(adapter);
 
 	tx_old = adapter->tx_ring;
 	rx_old = adapter->rx_ring;
 
+	adapter->tx_ring = kmalloc(tx_ring_size, GFP_KERNEL);
+	if (!adapter->tx_ring) {
+		err = -ENOMEM;
+		goto err_setup_rx;
+	}
+	memset(adapter->tx_ring, 0, tx_ring_size);
+
+	adapter->rx_ring = kmalloc(rx_ring_size, GFP_KERNEL);
+	if (!adapter->rx_ring) {
+		kfree(adapter->tx_ring);
+		err = -ENOMEM;
+		goto err_setup_rx;
+	}
+	memset(adapter->rx_ring, 0, rx_ring_size);
+
+	txdr = adapter->tx_ring;
+	rxdr = adapter->rx_ring;
+
 	if((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	if(netif_running(adapter->netdev))
-		e1000_down(adapter);
-
 	rxdr->count = max(ring->rx_pending,(uint32_t)E1000_MIN_RXD);
 	rxdr->count = min(rxdr->count,(uint32_t)(mac_type < e1000_82544 ?
 		E1000_MAX_RXD : E1000_MAX_82544_RXD));
@@ -621,11 +641,16 @@ e1000_set_ringparam(struct net_device *netdev,
 		E1000_MAX_TXD : E1000_MAX_82544_TXD));
 	E1000_ROUNDUP(txdr->count, REQ_TX_DESCRIPTOR_MULTIPLE); 
 
+	for (i = 0; i < adapter->num_queues; i++) {
+		txdr[i].count = txdr->count;
+		rxdr[i].count = rxdr->count;
+	}
+
 	if(netif_running(adapter->netdev)) {
 		/* Try to get new resources before deleting old */
-		if((err = e1000_setup_rx_resources(adapter)))
+		if ((err = e1000_setup_all_rx_resources(adapter)))
 			goto err_setup_rx;
-		if((err = e1000_setup_tx_resources(adapter)))
+		if ((err = e1000_setup_all_tx_resources(adapter)))
 			goto err_setup_tx;
 
 		/* save the new, restore the old in order to free it,
@@ -635,8 +660,10 @@ e1000_set_ringparam(struct net_device *netdev,
 		tx_new = adapter->tx_ring;
 		adapter->rx_ring = rx_old;
 		adapter->tx_ring = tx_old;
-		e1000_free_rx_resources(adapter);
-		e1000_free_tx_resources(adapter);
+		e1000_free_all_rx_resources(adapter);
+		e1000_free_all_tx_resources(adapter);
+		kfree(tx_old);
+		kfree(rx_old);
 		adapter->rx_ring = rx_new;
 		adapter->tx_ring = tx_new;
 		if((err = e1000_up(adapter)))
@@ -645,7 +672,7 @@ e1000_set_ringparam(struct net_device *netdev,
 
 	return 0;
 err_setup_tx:
-	e1000_free_rx_resources(adapter);
+	e1000_free_all_rx_resources(adapter);
 err_setup_rx:
 	adapter->rx_ring = rx_old;
 	adapter->tx_ring = tx_old;
@@ -903,8 +930,8 @@ e1000_intr_test(struct e1000_adapter *adapter, uint64_t *data)
 static void
 e1000_free_desc_rings(struct e1000_adapter *adapter)
 {
-	struct e1000_desc_ring *txdr = &adapter->test_tx_ring;
-	struct e1000_desc_ring *rxdr = &adapter->test_rx_ring;
+	struct e1000_tx_ring *txdr = &adapter->test_tx_ring;
+	struct e1000_rx_ring *rxdr = &adapter->test_rx_ring;
 	struct pci_dev *pdev = adapter->pdev;
 	int i;
 
@@ -946,8 +973,8 @@ e1000_free_desc_rings(struct e1000_adapter *adapter)
 static int
 e1000_setup_desc_rings(struct e1000_adapter *adapter)
 {
-	struct e1000_desc_ring *txdr = &adapter->test_tx_ring;
-	struct e1000_desc_ring *rxdr = &adapter->test_rx_ring;
+	struct e1000_tx_ring *txdr = &adapter->test_tx_ring;
+	struct e1000_rx_ring *rxdr = &adapter->test_rx_ring;
 	struct pci_dev *pdev = adapter->pdev;
 	uint32_t rctl;
 	int size, i, ret_val;
@@ -1347,8 +1374,8 @@ e1000_check_lbtest_frame(struct sk_buff *skb, unsigned int frame_size)
 static int
 e1000_run_loopback_test(struct e1000_adapter *adapter)
 {
-	struct e1000_desc_ring *txdr = &adapter->test_tx_ring;
-	struct e1000_desc_ring *rxdr = &adapter->test_rx_ring;
+	struct e1000_tx_ring *txdr = &adapter->test_tx_ring;
+	struct e1000_rx_ring *rxdr = &adapter->test_rx_ring;
 	struct pci_dev *pdev = adapter->pdev;
 	int i, j, k, l, lc, good_cnt, ret_val=0;
 	unsigned long time;

drivers/net/e1000/e1000_param.c

@@ -306,7 +306,8 @@ e1000_check_options(struct e1000_adapter *adapter)
 			.def  = E1000_DEFAULT_TXD,
 			.arg  = { .r = { .min = E1000_MIN_TXD }}
 		};
-		struct e1000_desc_ring *tx_ring = &adapter->tx_ring;
+		struct e1000_tx_ring *tx_ring = adapter->tx_ring;
+		int i;
 		e1000_mac_type mac_type = adapter->hw.mac_type;
 		opt.arg.r.max = mac_type < e1000_82544 ?
 			E1000_MAX_TXD : E1000_MAX_82544_TXD;
@@ -319,6 +320,8 @@ e1000_check_options(struct e1000_adapter *adapter)
 		} else {
 			tx_ring->count = opt.def;
 		}
+		for (i = 0; i < adapter->num_queues; i++)
+			tx_ring[i].count = tx_ring->count;
 	}
 	{ /* Receive Descriptor Count */
 		struct e1000_option opt = {
@@ -329,7 +332,8 @@ e1000_check_options(struct e1000_adapter *adapter)
 			.def  = E1000_DEFAULT_RXD,
 			.arg  = { .r = { .min = E1000_MIN_RXD }}
 		};
-		struct e1000_desc_ring *rx_ring = &adapter->rx_ring;
+		struct e1000_rx_ring *rx_ring = adapter->rx_ring;
+		int i;
 		e1000_mac_type mac_type = adapter->hw.mac_type;
 		opt.arg.r.max = mac_type < e1000_82544 ? E1000_MAX_RXD :
 			E1000_MAX_82544_RXD;
@@ -342,6 +346,8 @@ e1000_check_options(struct e1000_adapter *adapter)
 		} else {
 			rx_ring->count = opt.def;
 		}
+		for (i = 0; i < adapter->num_queues; i++)
+			rx_ring[i].count = rx_ring->count;
 	}
 	{ /* Checksum Offload Enable/Disable */
 		struct e1000_option opt = {