From e665bfda5b8fea586ddd028b26a6e2ed9e987c6b Mon Sep 17 00:00:00 2001
From: Michael Chan <mchan@broadcom.com>
Date: Sat, 10 Oct 2009 13:46:54 +0000
Subject: bnx2x: Refactor MAC address setup code.

For iSCSI MAC address setup in later patches.

Signed-off-by: Shmulik Ravid - Rabinovitz <shmulikr@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Acked-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index bbf842284ebb..1f0706328a3f 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -863,8 +863,8 @@ struct bnx2x {
 
 	/* Flags for marking that there is a STAT_QUERY or
 	   SET_MAC ramrod pending */
-	u8			stats_pending;
-	u8			set_mac_pending;
+	int			stats_pending;
+	int			set_mac_pending;
 
 	/* End of fields used in the performance code paths */
 
-- 
cgit v1.2.3


From 37b091bacba7bd329eced9a56998b6247da414c4 Mon Sep 17 00:00:00 2001
From: Michael Chan <mchan@broadcom.com>
Date: Sat, 10 Oct 2009 13:46:55 +0000
Subject: bnx2x: Add hw init code to support iSCSI.

Add code to initialize hardware blocks used for iSCSI.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Shmulik Ravid - Rabinovitz <shmulikr@broadcom.com>
Acked-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h      |  59 ++++++++++---
 drivers/net/bnx2x_main.c | 210 ++++++++++++++++++++++++++++++++++-------------
 2 files changed, 200 insertions(+), 69 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index 1f0706328a3f..e94ce8370253 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -762,7 +762,11 @@ struct bnx2x_eth_stats {
 			(offsetof(struct bnx2x_eth_stats, stat_name) / 4)
 
 
+#ifdef BCM_CNIC
+#define MAX_CONTEXT			15
+#else
 #define MAX_CONTEXT			16
+#endif
 
 union cdu_context {
 	struct eth_context eth;
@@ -811,13 +815,21 @@ struct bnx2x {
 	struct bnx2x_fastpath	fp[MAX_CONTEXT];
 	void __iomem		*regview;
 	void __iomem		*doorbells;
+#ifdef BCM_CNIC
+#define BNX2X_DB_SIZE		(18*BCM_PAGE_SIZE)
+#else
 #define BNX2X_DB_SIZE		(16*BCM_PAGE_SIZE)
+#endif
 
 	struct net_device	*dev;
 	struct pci_dev		*pdev;
 
 	atomic_t		intr_sem;
+#ifdef BCM_CNIC
+	struct msix_entry	msix_table[MAX_CONTEXT+2];
+#else
 	struct msix_entry	msix_table[MAX_CONTEXT+1];
+#endif
 #define INT_MODE_INTx			1
 #define INT_MODE_MSI			2
 #define INT_MODE_MSIX			3
@@ -891,6 +903,11 @@ struct bnx2x {
 #define BP_E1HVN(bp)			(bp->func >> 1)
 #define BP_L_ID(bp)			(BP_E1HVN(bp) << 2)
 
+#ifdef BCM_CNIC
+#define BCM_CNIC_CID_START		16
+#define BCM_ISCSI_ETH_CL_ID		17
+#endif
+
 	int			pm_cap;
 	int			pcie_cap;
 	int			mrrs;
@@ -960,24 +977,44 @@ struct bnx2x {
 #define BNX2X_MAX_MULTICAST		64
 #define BNX2X_MAX_EMUL_MULTI		16
 
+	u32 			rx_mode_cl_mask;
+
 	dma_addr_t		def_status_blk_mapping;
 
 	struct bnx2x_slowpath	*slowpath;
 	dma_addr_t		slowpath_mapping;
 
-#ifdef BCM_ISCSI
-	void    		*t1;
-	dma_addr_t      	t1_mapping;
-	void    		*t2;
-	dma_addr_t      	t2_mapping;
-	void    		*timers;
-	dma_addr_t      	timers_mapping;
-	void    		*qm;
-	dma_addr_t      	qm_mapping;
-#endif
-
 	int			dropless_fc;
 
+#ifdef BCM_CNIC
+	u32			cnic_flags;
+#define BNX2X_CNIC_FLAG_MAC_SET		1
+
+	void			*t1;
+	dma_addr_t		t1_mapping;
+	void			*t2;
+	dma_addr_t		t2_mapping;
+	void			*timers;
+	dma_addr_t		timers_mapping;
+	void			*qm;
+	dma_addr_t		qm_mapping;
+	struct cnic_ops		*cnic_ops;
+	void			*cnic_data;
+	u32			cnic_tag;
+	struct cnic_eth_dev	cnic_eth_dev;
+	struct host_status_block *cnic_sb;
+	dma_addr_t		cnic_sb_mapping;
+#define CNIC_SB_ID(bp)			BP_L_ID(bp)
+	struct eth_spe		*cnic_kwq;
+	struct eth_spe		*cnic_kwq_prod;
+	struct eth_spe		*cnic_kwq_cons;
+	struct eth_spe		*cnic_kwq_last;
+	u16			cnic_kwq_pending;
+	u16			cnic_spq_pending;
+	struct mutex		cnic_mutex;
+	u8			iscsi_mac[6];
+#endif
+
 	int			dmae_ready;
 	/* used to synchronize dmae accesses */
 	struct mutex		dmae_mutex;
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index 02ce3b31050c..f7b71100e95c 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -742,6 +742,9 @@ static void bnx2x_int_disable_sync(struct bnx2x *bp, int disable_hw)
 	if (msix) {
 		synchronize_irq(bp->msix_table[0].vector);
 		offset = 1;
+#ifdef BCM_CNIC
+		offset++;
+#endif
 		for_each_queue(bp, i)
 			synchronize_irq(bp->msix_table[i + offset].vector);
 	} else
@@ -5252,7 +5255,7 @@ static void bnx2x_set_storm_rx_mode(struct bnx2x *bp)
 {
 	struct tstorm_eth_mac_filter_config tstorm_mac_filter = {0};
 	int mode = bp->rx_mode;
-	int mask = (1 << BP_L_ID(bp));
+	int mask = bp->rx_mode_cl_mask;
 	int func = BP_FUNC(bp);
 	int port = BP_PORT(bp);
 	int i;
@@ -5365,6 +5368,7 @@ static void bnx2x_init_internal_func(struct bnx2x *bp)
 	       (*(u32 *)&tstorm_config));
 
 	bp->rx_mode = BNX2X_RX_MODE_NONE; /* no rx until link is up */
+	bp->rx_mode_cl_mask = (1 << BP_L_ID(bp));
 	bnx2x_set_storm_rx_mode(bp);
 
 	for_each_queue(bp, i) {
@@ -5582,7 +5586,11 @@ static void bnx2x_nic_init(struct bnx2x *bp, u32 load_code)
 		fp->state = BNX2X_FP_STATE_CLOSED;
 		fp->index = i;
 		fp->cl_id = BP_L_ID(bp) + i;
+#ifdef BCM_CNIC
+		fp->sb_id = fp->cl_id + 1;
+#else
 		fp->sb_id = fp->cl_id;
+#endif
 		/* Suitable Rx and Tx SBs are served by the same client */
 		if (i >= bp->num_rx_queues)
 			fp->cl_id -= bp->num_rx_queues;
@@ -5884,7 +5892,7 @@ static int bnx2x_int_mem_test(struct bnx2x *bp)
 	msleep(50);
 	bnx2x_init_block(bp, BRB1_BLOCK, COMMON_STAGE);
 	bnx2x_init_block(bp, PRS_BLOCK, COMMON_STAGE);
-#ifndef BCM_ISCSI
+#ifndef BCM_CNIC
 	/* set NIC mode */
 	REG_WR(bp, PRS_REG_NIC_MODE, 1);
 #endif
@@ -6023,6 +6031,9 @@ static void bnx2x_setup_fan_failure_detection(struct bnx2x *bp)
 static int bnx2x_init_common(struct bnx2x *bp)
 {
 	u32 val, i;
+#ifdef BCM_CNIC
+	u32 wb_write[2];
+#endif
 
 	DP(BNX2X_MSG_MCP, "starting common init  func %d\n", BP_FUNC(bp));
 
@@ -6065,7 +6076,7 @@ static int bnx2x_init_common(struct bnx2x *bp)
 #endif
 
 	REG_WR(bp, PXP2_REG_RQ_CDU_P_SIZE, 2);
-#ifdef BCM_ISCSI
+#ifdef BCM_CNIC
 	REG_WR(bp, PXP2_REG_RQ_TM_P_SIZE, 5);
 	REG_WR(bp, PXP2_REG_RQ_QM_P_SIZE, 5);
 	REG_WR(bp, PXP2_REG_RQ_SRC_P_SIZE, 5);
@@ -6108,11 +6119,26 @@ static int bnx2x_init_common(struct bnx2x *bp)
 	bnx2x_read_dmae(bp, USEM_REG_PASSIVE_BUFFER, 3);
 
 	bnx2x_init_block(bp, QM_BLOCK, COMMON_STAGE);
+
+#ifdef BCM_CNIC
+	wb_write[0] = 0;
+	wb_write[1] = 0;
+	for (i = 0; i < 64; i++) {
+		REG_WR(bp, QM_REG_BASEADDR + i*4, 1024 * 4 * (i%16));
+		bnx2x_init_ind_wr(bp, QM_REG_PTRTBL + i*8, wb_write, 2);
+
+		if (CHIP_IS_E1H(bp)) {
+			REG_WR(bp, QM_REG_BASEADDR_EXT_A + i*4, 1024*4*(i%16));
+			bnx2x_init_ind_wr(bp, QM_REG_PTRTBL_EXT_A + i*8,
+					  wb_write, 2);
+		}
+	}
+#endif
 	/* soft reset pulse */
 	REG_WR(bp, QM_REG_SOFT_RESET, 1);
 	REG_WR(bp, QM_REG_SOFT_RESET, 0);
 
-#ifdef BCM_ISCSI
+#ifdef BCM_CNIC
 	bnx2x_init_block(bp, TIMERS_BLOCK, COMMON_STAGE);
 #endif
 
@@ -6126,8 +6152,10 @@ static int bnx2x_init_common(struct bnx2x *bp)
 	bnx2x_init_block(bp, BRB1_BLOCK, COMMON_STAGE);
 	bnx2x_init_block(bp, PRS_BLOCK, COMMON_STAGE);
 	REG_WR(bp, PRS_REG_A_PRSU_20, 0xf);
+#ifndef BCM_CNIC
 	/* set NIC mode */
 	REG_WR(bp, PRS_REG_NIC_MODE, 1);
+#endif
 	if (CHIP_IS_E1H(bp))
 		REG_WR(bp, PRS_REG_E1HOV_MODE, IS_E1HMF(bp));
 
@@ -6162,6 +6190,18 @@ static int bnx2x_init_common(struct bnx2x *bp)
 		/* TODO: replace with something meaningful */
 	}
 	bnx2x_init_block(bp, SRCH_BLOCK, COMMON_STAGE);
+#ifdef BCM_CNIC
+	REG_WR(bp, SRC_REG_KEYSEARCH_0, 0x63285672);
+	REG_WR(bp, SRC_REG_KEYSEARCH_1, 0x24b8f2cc);
+	REG_WR(bp, SRC_REG_KEYSEARCH_2, 0x223aef9b);
+	REG_WR(bp, SRC_REG_KEYSEARCH_3, 0x26001e3a);
+	REG_WR(bp, SRC_REG_KEYSEARCH_4, 0x7ae91116);
+	REG_WR(bp, SRC_REG_KEYSEARCH_5, 0x5ce5230b);
+	REG_WR(bp, SRC_REG_KEYSEARCH_6, 0x298d8adf);
+	REG_WR(bp, SRC_REG_KEYSEARCH_7, 0x6eb0ff09);
+	REG_WR(bp, SRC_REG_KEYSEARCH_8, 0x1830f82f);
+	REG_WR(bp, SRC_REG_KEYSEARCH_9, 0x01e46be7);
+#endif
 	REG_WR(bp, SRC_REG_SOFT_RST, 0);
 
 	if (sizeof(union cdu_context) != 1024)
@@ -6278,38 +6318,14 @@ static int bnx2x_init_port(struct bnx2x *bp)
 	bnx2x_init_block(bp, TCM_BLOCK, init_stage);
 	bnx2x_init_block(bp, UCM_BLOCK, init_stage);
 	bnx2x_init_block(bp, CCM_BLOCK, init_stage);
-#ifdef BCM_ISCSI
-	/* Port0  1
-	 * Port1  385 */
-	i++;
-	wb_write[0] = ONCHIP_ADDR1(bp->timers_mapping);
-	wb_write[1] = ONCHIP_ADDR2(bp->timers_mapping);
-	REG_WR_DMAE(bp, PXP2_REG_RQ_ONCHIP_AT + i*8, wb_write, 2);
-	REG_WR(bp, PXP2_REG_PSWRQ_TM0_L2P + func*4, PXP_ONE_ILT(i));
-
-	/* Port0  2
-	 * Port1  386 */
-	i++;
-	wb_write[0] = ONCHIP_ADDR1(bp->qm_mapping);
-	wb_write[1] = ONCHIP_ADDR2(bp->qm_mapping);
-	REG_WR_DMAE(bp, PXP2_REG_RQ_ONCHIP_AT + i*8, wb_write, 2);
-	REG_WR(bp, PXP2_REG_PSWRQ_QM0_L2P + func*4, PXP_ONE_ILT(i));
-
-	/* Port0  3
-	 * Port1  387 */
-	i++;
-	wb_write[0] = ONCHIP_ADDR1(bp->t1_mapping);
-	wb_write[1] = ONCHIP_ADDR2(bp->t1_mapping);
-	REG_WR_DMAE(bp, PXP2_REG_RQ_ONCHIP_AT + i*8, wb_write, 2);
-	REG_WR(bp, PXP2_REG_PSWRQ_SRC0_L2P + func*4, PXP_ONE_ILT(i));
-#endif
 	bnx2x_init_block(bp, XCM_BLOCK, init_stage);
 
-#ifdef BCM_ISCSI
-	REG_WR(bp, TM_REG_LIN0_SCAN_TIME + func*4, 1024/64*20);
-	REG_WR(bp, TM_REG_LIN0_MAX_ACTIVE_CID + func*4, 31);
+#ifdef BCM_CNIC
+	REG_WR(bp, QM_REG_CONNNUM_0 + port*4, 1024/16 - 1);
 
 	bnx2x_init_block(bp, TIMERS_BLOCK, init_stage);
+	REG_WR(bp, TM_REG_LIN0_SCAN_TIME + port*4, 20);
+	REG_WR(bp, TM_REG_LIN0_MAX_ACTIVE_CID + port*4, 31);
 #endif
 	bnx2x_init_block(bp, DQ_BLOCK, init_stage);
 
@@ -6367,18 +6383,8 @@ static int bnx2x_init_port(struct bnx2x *bp)
 	msleep(5);
 	REG_WR(bp, PBF_REG_INIT_P0 + port*4, 0);
 
-#ifdef BCM_ISCSI
-	/* tell the searcher where the T2 table is */
-	REG_WR(bp, SRC_REG_COUNTFREE0 + func*4, 16*1024/64);
-
-	wb_write[0] = U64_LO(bp->t2_mapping);
-	wb_write[1] = U64_HI(bp->t2_mapping);
-	REG_WR_DMAE(bp, SRC_REG_FIRSTFREE0 + func*4, wb_write, 2);
-	wb_write[0] = U64_LO((u64)bp->t2_mapping + 16*1024 - 64);
-	wb_write[1] = U64_HI((u64)bp->t2_mapping + 16*1024 - 64);
-	REG_WR_DMAE(bp, SRC_REG_LASTFREE0 + func*4, wb_write, 2);
-
-	REG_WR(bp, SRC_REG_NUMBER_HASH_BITS0 + func*4, 10);
+#ifdef BCM_CNIC
+	bnx2x_init_block(bp, SRCH_BLOCK, init_stage);
 #endif
 	bnx2x_init_block(bp, CDU_BLOCK, init_stage);
 	bnx2x_init_block(bp, CFC_BLOCK, init_stage);
@@ -6487,7 +6493,12 @@ static int bnx2x_init_port(struct bnx2x *bp)
 #define PXP_ONE_ILT(x)		(((x) << 10) | x)
 #define PXP_ILT_RANGE(f, l)	(((l) << 10) | f)
 
+#ifdef BCM_CNIC
+#define CNIC_ILT_LINES		127
+#define CNIC_CTX_PER_ILT	16
+#else
 #define CNIC_ILT_LINES		0
+#endif
 
 static void bnx2x_ilt_wr(struct bnx2x *bp, u32 index, dma_addr_t addr)
 {
@@ -6526,6 +6537,46 @@ static int bnx2x_init_func(struct bnx2x *bp)
 		REG_WR(bp, PXP2_REG_PSWRQ_CDU0_L2P + func*4,
 		       PXP_ILT_RANGE(i, i + CNIC_ILT_LINES));
 
+#ifdef BCM_CNIC
+	i += 1 + CNIC_ILT_LINES;
+	bnx2x_ilt_wr(bp, i, bp->timers_mapping);
+	if (CHIP_IS_E1(bp))
+		REG_WR(bp, PXP2_REG_PSWRQ_TM0_L2P + func*4, PXP_ONE_ILT(i));
+	else {
+		REG_WR(bp, PXP2_REG_RQ_TM_FIRST_ILT, i);
+		REG_WR(bp, PXP2_REG_RQ_TM_LAST_ILT, i);
+	}
+
+	i++;
+	bnx2x_ilt_wr(bp, i, bp->qm_mapping);
+	if (CHIP_IS_E1(bp))
+		REG_WR(bp, PXP2_REG_PSWRQ_QM0_L2P + func*4, PXP_ONE_ILT(i));
+	else {
+		REG_WR(bp, PXP2_REG_RQ_QM_FIRST_ILT, i);
+		REG_WR(bp, PXP2_REG_RQ_QM_LAST_ILT, i);
+	}
+
+	i++;
+	bnx2x_ilt_wr(bp, i, bp->t1_mapping);
+	if (CHIP_IS_E1(bp))
+		REG_WR(bp, PXP2_REG_PSWRQ_SRC0_L2P + func*4, PXP_ONE_ILT(i));
+	else {
+		REG_WR(bp, PXP2_REG_RQ_SRC_FIRST_ILT, i);
+		REG_WR(bp, PXP2_REG_RQ_SRC_LAST_ILT, i);
+	}
+
+	/* tell the searcher where the T2 table is */
+	REG_WR(bp, SRC_REG_COUNTFREE0 + port*4, 16*1024/64);
+
+	bnx2x_wb_wr(bp, SRC_REG_FIRSTFREE0 + port*16,
+		    U64_LO(bp->t2_mapping), U64_HI(bp->t2_mapping));
+
+	bnx2x_wb_wr(bp, SRC_REG_LASTFREE0 + port*16,
+		    U64_LO((u64)bp->t2_mapping + 16*1024 - 64),
+		    U64_HI((u64)bp->t2_mapping + 16*1024 - 64));
+
+	REG_WR(bp, SRC_REG_NUMBER_HASH_BITS0 + port*4, 10);
+#endif
 
 	if (CHIP_IS_E1H(bp)) {
 		bnx2x_init_block(bp, MISC_BLOCK, FUNC0_STAGE + func);
@@ -6610,6 +6661,9 @@ static int bnx2x_init_hw(struct bnx2x *bp, u32 load_code)
 	bnx2x_zero_def_sb(bp);
 	for_each_queue(bp, i)
 		bnx2x_zero_sb(bp, BP_L_ID(bp) + i);
+#ifdef BCM_CNIC
+	bnx2x_zero_sb(bp, BP_L_ID(bp) + i);
+#endif
 
 init_hw_err:
 	bnx2x_gunzip_end(bp);
@@ -6685,11 +6739,13 @@ static void bnx2x_free_mem(struct bnx2x *bp)
 	BNX2X_PCI_FREE(bp->slowpath, bp->slowpath_mapping,
 		       sizeof(struct bnx2x_slowpath));
 
-#ifdef BCM_ISCSI
+#ifdef BCM_CNIC
 	BNX2X_PCI_FREE(bp->t1, bp->t1_mapping, 64*1024);
 	BNX2X_PCI_FREE(bp->t2, bp->t2_mapping, 16*1024);
 	BNX2X_PCI_FREE(bp->timers, bp->timers_mapping, 8*1024);
 	BNX2X_PCI_FREE(bp->qm, bp->qm_mapping, 128*1024);
+	BNX2X_PCI_FREE(bp->cnic_sb, bp->cnic_sb_mapping,
+		       sizeof(struct host_status_block));
 #endif
 	BNX2X_PCI_FREE(bp->spq, bp->spq_mapping, BCM_PAGE_SIZE);
 
@@ -6768,32 +6824,26 @@ static int bnx2x_alloc_mem(struct bnx2x *bp)
 	BNX2X_PCI_ALLOC(bp->slowpath, &bp->slowpath_mapping,
 			sizeof(struct bnx2x_slowpath));
 
-#ifdef BCM_ISCSI
+#ifdef BCM_CNIC
 	BNX2X_PCI_ALLOC(bp->t1, &bp->t1_mapping, 64*1024);
 
-	/* Initialize T1 */
-	for (i = 0; i < 64*1024; i += 64) {
-		*(u64 *)((char *)bp->t1 + i + 56) = 0x0UL;
-		*(u64 *)((char *)bp->t1 + i + 3) = 0x0UL;
-	}
-
 	/* allocate searcher T2 table
 	   we allocate 1/4 of alloc num for T2
 	  (which is not entered into the ILT) */
 	BNX2X_PCI_ALLOC(bp->t2, &bp->t2_mapping, 16*1024);
 
-	/* Initialize T2 */
+	/* Initialize T2 (for 1024 connections) */
 	for (i = 0; i < 16*1024; i += 64)
-		* (u64 *)((char *)bp->t2 + i + 56) = bp->t2_mapping + i + 64;
-
-	/* now fixup the last line in the block to point to the next block */
-	*(u64 *)((char *)bp->t2 + 1024*16-8) = bp->t2_mapping;
+		*(u64 *)((char *)bp->t2 + i + 56) = bp->t2_mapping + i + 64;
 
-	/* Timer block array (MAX_CONN*8) phys uncached for now 1024 conns */
+	/* Timer block array (8*MAX_CONN) phys uncached for now 1024 conns */
 	BNX2X_PCI_ALLOC(bp->timers, &bp->timers_mapping, 8*1024);
 
 	/* QM queues (128*MAX_CONN) */
 	BNX2X_PCI_ALLOC(bp->qm, &bp->qm_mapping, 128*1024);
+
+	BNX2X_PCI_ALLOC(bp->cnic_sb, &bp->cnic_sb_mapping,
+			sizeof(struct host_status_block));
 #endif
 
 	/* Slow path ring */
@@ -6869,6 +6919,9 @@ static void bnx2x_free_msix_irqs(struct bnx2x *bp)
 	DP(NETIF_MSG_IFDOWN, "released sp irq (%d)\n",
 	   bp->msix_table[0].vector);
 
+#ifdef BCM_CNIC
+	offset++;
+#endif
 	for_each_queue(bp, i) {
 		DP(NETIF_MSG_IFDOWN, "about to release fp #%d->%d irq  "
 		   "state %x\n", i, bp->msix_table[i + offset].vector,
@@ -6902,6 +6955,12 @@ static int bnx2x_enable_msix(struct bnx2x *bp)
 	bp->msix_table[0].entry = igu_vec;
 	DP(NETIF_MSG_IFUP, "msix_table[0].entry = %d (slowpath)\n", igu_vec);
 
+#ifdef BCM_CNIC
+	igu_vec = BP_L_ID(bp) + offset;
+	bp->msix_table[1].entry = igu_vec;
+	DP(NETIF_MSG_IFUP, "msix_table[1].entry = %d (CNIC)\n", igu_vec);
+	offset++;
+#endif
 	for_each_queue(bp, i) {
 		igu_vec = BP_L_ID(bp) + offset + i;
 		bp->msix_table[i + offset].entry = igu_vec;
@@ -6932,6 +6991,9 @@ static int bnx2x_req_msix_irqs(struct bnx2x *bp)
 		return -EBUSY;
 	}
 
+#ifdef BCM_CNIC
+	offset++;
+#endif
 	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
@@ -7496,10 +7558,18 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 		}
 
 	if (bp->state == BNX2X_STATE_OPEN) {
+#ifdef BCM_CNIC
+		/* Enable Timer scan */
+		REG_WR(bp, TM_REG_EN_LINEAR0_TIMER + BP_PORT(bp)*4, 1);
+#endif
 		for_each_nondefault_queue(bp, i) {
 			rc = bnx2x_setup_multi(bp, i);
 			if (rc)
+#ifdef BCM_CNIC
+				goto load_error4;
+#else
 				goto load_error3;
+#endif
 		}
 
 		if (CHIP_IS_E1(bp))
@@ -7549,6 +7619,11 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 
 	return 0;
 
+#ifdef BCM_CNIC
+load_error4:
+	/* Disable Timer scan */
+	REG_WR(bp, TM_REG_EN_LINEAR0_TIMER + BP_PORT(bp)*4, 0);
+#endif
 load_error3:
 	bnx2x_int_disable_sync(bp, 1);
 	if (!BP_NOMCP(bp)) {
@@ -7656,6 +7731,19 @@ static void bnx2x_reset_func(struct bnx2x *bp)
 	REG_WR(bp, HC_REG_LEADING_EDGE_0 + port*8, 0);
 	REG_WR(bp, HC_REG_TRAILING_EDGE_0 + port*8, 0);
 
+#ifdef BCM_CNIC
+	/* Disable Timer scan */
+	REG_WR(bp, TM_REG_EN_LINEAR0_TIMER + port*4, 0);
+	/*
+	 * Wait for at least 10ms and up to 2 second for the timers scan to
+	 * complete
+	 */
+	for (i = 0; i < 200; i++) {
+		msleep(10);
+		if (!REG_RD(bp, TM_REG_LIN0_SCAN_ON + port*4))
+			break;
+	}
+#endif
 	/* Clear ILT */
 	base = FUNC_ILT_BASE(func);
 	for (i = base; i < base + ILT_PER_FUNC; i++)
@@ -8666,6 +8754,12 @@ static void __devinit bnx2x_get_port_hwinfo(struct bnx2x *bp)
 	bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2);
 	memcpy(bp->link_params.mac_addr, bp->dev->dev_addr, ETH_ALEN);
 	memcpy(bp->dev->perm_addr, bp->dev->dev_addr, ETH_ALEN);
+
+#ifdef BCM_CNIC
+	val2 = SHMEM_RD(bp, dev_info.port_hw_config[port].iscsi_mac_upper);
+	val = SHMEM_RD(bp, dev_info.port_hw_config[port].iscsi_mac_lower);
+	bnx2x_set_mac_buf(bp->iscsi_mac, val, val2);
+#endif
 }
 
 static int __devinit bnx2x_get_hwinfo(struct bnx2x *bp)
-- 
cgit v1.2.3


From 993ac7b5183f82edc9696cd17faae03523e00e09 Mon Sep 17 00:00:00 2001
From: Michael Chan <mchan@broadcom.com>
Date: Sat, 10 Oct 2009 13:46:56 +0000
Subject: bnx2x: Add main CNIC interface functions.

Add the main CNIC registration, callback, MAC addr. setup functions.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Shmulik Ravid - Rabinovitz <shmulikr@broadcom.com>
Acked-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h      |   4 +
 drivers/net/bnx2x_main.c | 388 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/cnic_if.h    |  14 +-
 3 files changed, 404 insertions(+), 2 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index e94ce8370253..60fa14f31d73 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -24,6 +24,10 @@
 #define BCM_VLAN			1
 #endif
 
+#if defined(CONFIG_CNIC) || defined(CONFIG_CNIC_MODULE)
+#define BCM_CNIC 1
+#include "cnic_if.h"
+#endif
 
 #define BNX2X_MULTI_QUEUE
 
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index f7b71100e95c..b4e9c6ebac54 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -969,6 +969,9 @@ static void bnx2x_tx_int(struct bnx2x_fastpath *fp)
 	}
 }
 
+#ifdef BCM_CNIC
+static void bnx2x_cnic_cfc_comp(struct bnx2x *bp, int cid);
+#endif
 
 static void bnx2x_sp_event(struct bnx2x_fastpath *fp,
 			   union eth_rx_cqe *rr_cqe)
@@ -1025,6 +1028,12 @@ static void bnx2x_sp_event(struct bnx2x_fastpath *fp,
 		bnx2x_fp(bp, cid, state) = BNX2X_FP_STATE_CLOSED;
 		break;
 
+#ifdef BCM_CNIC
+	case (RAMROD_CMD_ID_ETH_CFC_DEL | BNX2X_STATE_OPEN):
+		DP(NETIF_MSG_IFDOWN, "got delete ramrod for CID %d\n", cid);
+		bnx2x_cnic_cfc_comp(bp, cid);
+		break;
+#endif
 
 	case (RAMROD_CMD_ID_ETH_SET_MAC | BNX2X_STATE_OPEN):
 	case (RAMROD_CMD_ID_ETH_SET_MAC | BNX2X_STATE_DIAG):
@@ -1810,6 +1819,20 @@ static irqreturn_t bnx2x_interrupt(int irq, void *dev_instance)
 		}
 	}
 
+#ifdef BCM_CNIC
+	mask = 0x2 << CNIC_SB_ID(bp);
+	if (status & (mask | 0x1)) {
+		struct cnic_ops *c_ops = NULL;
+
+		rcu_read_lock();
+		c_ops = rcu_dereference(bp->cnic_ops);
+		if (c_ops)
+			c_ops->cnic_handler(bp->cnic_data, NULL);
+		rcu_read_unlock();
+
+		status &= ~mask;
+	}
+#endif
 
 	if (unlikely(status & 0x1)) {
 		queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
@@ -3247,6 +3270,17 @@ static irqreturn_t bnx2x_msix_sp_int(int irq, void *dev_instance)
 		return IRQ_HANDLED;
 #endif
 
+#ifdef BCM_CNIC
+	{
+		struct cnic_ops *c_ops;
+
+		rcu_read_lock();
+		c_ops = rcu_dereference(bp->cnic_ops);
+		if (c_ops)
+			c_ops->cnic_handler(bp->cnic_data, NULL);
+		rcu_read_unlock();
+	}
+#endif
 	queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
 
 	return IRQ_HANDLED;
@@ -7291,6 +7325,44 @@ static void bnx2x_set_eth_mac_addr_e1(struct bnx2x *bp, int set)
 	bnx2x_wait_ramrod(bp, 0, 0, &bp->set_mac_pending, set ? 0 : 1);
 }
 
+#ifdef BCM_CNIC
+/**
+ * Set iSCSI MAC(s) at the next enties in the CAM after the ETH
+ * MAC(s). This function will wait until the ramdord completion
+ * returns.
+ *
+ * @param bp driver handle
+ * @param set set or clear the CAM entry
+ *
+ * @return 0 if cussess, -ENODEV if ramrod doesn't return.
+ */
+static int bnx2x_set_iscsi_eth_mac_addr(struct bnx2x *bp, int set)
+{
+	u32 cl_bit_vec = (1 << BCM_ISCSI_ETH_CL_ID);
+
+	bp->set_mac_pending++;
+	smp_wmb();
+
+	/* Send a SET_MAC ramrod */
+	if (CHIP_IS_E1(bp))
+		bnx2x_set_mac_addr_e1_gen(bp, set, bp->iscsi_mac,
+				  cl_bit_vec, (BP_PORT(bp) ? 32 : 0) + 2,
+				  1);
+	else
+		/* CAM allocation for E1H
+		* unicasts: by func number
+		* multicast: 20+FUNC*20, 20 each
+		*/
+		bnx2x_set_mac_addr_e1h_gen(bp, set, bp->iscsi_mac,
+				   cl_bit_vec, E1H_FUNC_MAX + BP_FUNC(bp));
+
+	/* Wait for a completion when setting */
+	bnx2x_wait_ramrod(bp, 0, 0, &bp->set_mac_pending, set ? 0 : 1);
+
+	return 0;
+}
+#endif
+
 static int bnx2x_setup_leading(struct bnx2x *bp)
 {
 	int rc;
@@ -7416,6 +7488,10 @@ static int bnx2x_set_int_mode(struct bnx2x *bp)
 	return rc;
 }
 
+#ifdef BCM_CNIC
+static int bnx2x_cnic_notify(struct bnx2x *bp, int cmd);
+static void bnx2x_setup_cnic_irq_info(struct bnx2x *bp);
+#endif
 
 /* must be called with rtnl_lock */
 static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
@@ -7576,6 +7652,15 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 			bnx2x_set_eth_mac_addr_e1(bp, 1);
 		else
 			bnx2x_set_eth_mac_addr_e1h(bp, 1);
+#ifdef BCM_CNIC
+		/* Set iSCSI L2 MAC */
+		mutex_lock(&bp->cnic_mutex);
+		if (bp->cnic_eth_dev.drv_state & CNIC_DRV_STATE_REGD) {
+			bnx2x_set_iscsi_eth_mac_addr(bp, 1);
+			bp->cnic_flags |= BNX2X_CNIC_FLAG_MAC_SET;
+		}
+		mutex_unlock(&bp->cnic_mutex);
+#endif
 	}
 
 	if (bp->port.pmf)
@@ -7616,6 +7701,11 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 	/* start the timer */
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 
+#ifdef BCM_CNIC
+	bnx2x_setup_cnic_irq_info(bp);
+	if (bp->state == BNX2X_STATE_OPEN)
+		bnx2x_cnic_notify(bp, CNIC_CTL_START_CMD);
+#endif
 
 	return 0;
 
@@ -7810,6 +7900,9 @@ static int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode)
 	u32 reset_code = 0;
 	int i, cnt, rc;
 
+#ifdef BCM_CNIC
+	bnx2x_cnic_notify(bp, CNIC_CTL_STOP_CMD);
+#endif
 	bp->state = BNX2X_STATE_CLOSING_WAIT4_HALT;
 
 	/* Set "drop all" */
@@ -7886,6 +7979,15 @@ static int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode)
 
 		REG_WR(bp, MISC_REG_E1HMF_MODE, 0);
 	}
+#ifdef BCM_CNIC
+	/* Clear iSCSI L2 MAC */
+	mutex_lock(&bp->cnic_mutex);
+	if (bp->cnic_flags & BNX2X_CNIC_FLAG_MAC_SET) {
+		bnx2x_set_iscsi_eth_mac_addr(bp, 0);
+		bp->cnic_flags &= ~BNX2X_CNIC_FLAG_MAC_SET;
+	}
+	mutex_unlock(&bp->cnic_mutex);
+#endif
 
 	if (unload_mode == UNLOAD_NORMAL)
 		reset_code = DRV_MSG_CODE_UNLOAD_REQ_WOL_DIS;
@@ -8855,6 +8957,9 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
 	smp_wmb(); /* Ensure that bp->intr_sem update is SMP-safe */
 
 	mutex_init(&bp->port.phy_mutex);
+#ifdef BCM_CNIC
+	mutex_init(&bp->cnic_mutex);
+#endif
 
 	INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
 	INIT_WORK(&bp->reset_task, bnx2x_reset_task);
@@ -12448,4 +12553,287 @@ static void __exit bnx2x_cleanup(void)
 module_init(bnx2x_init);
 module_exit(bnx2x_cleanup);
 
+#ifdef BCM_CNIC
+
+/* count denotes the number of new completions we have seen */
+static void bnx2x_cnic_sp_post(struct bnx2x *bp, int count)
+{
+	struct eth_spe *spe;
+
+#ifdef BNX2X_STOP_ON_ERROR
+	if (unlikely(bp->panic))
+		return;
+#endif
+
+	spin_lock_bh(&bp->spq_lock);
+	bp->cnic_spq_pending -= count;
+
+	for (; bp->cnic_spq_pending < bp->cnic_eth_dev.max_kwqe_pending;
+	     bp->cnic_spq_pending++) {
+
+		if (!bp->cnic_kwq_pending)
+			break;
+
+		spe = bnx2x_sp_get_next(bp);
+		*spe = *bp->cnic_kwq_cons;
+
+		bp->cnic_kwq_pending--;
+
+		DP(NETIF_MSG_TIMER, "pending on SPQ %d, on KWQ %d count %d\n",
+		   bp->cnic_spq_pending, bp->cnic_kwq_pending, count);
+
+		if (bp->cnic_kwq_cons == bp->cnic_kwq_last)
+			bp->cnic_kwq_cons = bp->cnic_kwq;
+		else
+			bp->cnic_kwq_cons++;
+	}
+	bnx2x_sp_prod_update(bp);
+	spin_unlock_bh(&bp->spq_lock);
+}
+
+static int bnx2x_cnic_sp_queue(struct net_device *dev,
+			       struct kwqe_16 *kwqes[], u32 count)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+	int i;
+
+#ifdef BNX2X_STOP_ON_ERROR
+	if (unlikely(bp->panic))
+		return -EIO;
+#endif
+
+	spin_lock_bh(&bp->spq_lock);
+
+	for (i = 0; i < count; i++) {
+		struct eth_spe *spe = (struct eth_spe *)kwqes[i];
+
+		if (bp->cnic_kwq_pending == MAX_SP_DESC_CNT)
+			break;
+
+		*bp->cnic_kwq_prod = *spe;
+
+		bp->cnic_kwq_pending++;
+
+		DP(NETIF_MSG_TIMER, "L5 SPQE %x %x %x:%x pos %d\n",
+		   spe->hdr.conn_and_cmd_data, spe->hdr.type,
+		   spe->data.mac_config_addr.hi,
+		   spe->data.mac_config_addr.lo,
+		   bp->cnic_kwq_pending);
+
+		if (bp->cnic_kwq_prod == bp->cnic_kwq_last)
+			bp->cnic_kwq_prod = bp->cnic_kwq;
+		else
+			bp->cnic_kwq_prod++;
+	}
+
+	spin_unlock_bh(&bp->spq_lock);
+
+	if (bp->cnic_spq_pending < bp->cnic_eth_dev.max_kwqe_pending)
+		bnx2x_cnic_sp_post(bp, 0);
+
+	return i;
+}
+
+static int bnx2x_cnic_ctl_send(struct bnx2x *bp, struct cnic_ctl_info *ctl)
+{
+	struct cnic_ops *c_ops;
+	int rc = 0;
+
+	mutex_lock(&bp->cnic_mutex);
+	c_ops = bp->cnic_ops;
+	if (c_ops)
+		rc = c_ops->cnic_ctl(bp->cnic_data, ctl);
+	mutex_unlock(&bp->cnic_mutex);
+
+	return rc;
+}
+
+static int bnx2x_cnic_ctl_send_bh(struct bnx2x *bp, struct cnic_ctl_info *ctl)
+{
+	struct cnic_ops *c_ops;
+	int rc = 0;
+
+	rcu_read_lock();
+	c_ops = rcu_dereference(bp->cnic_ops);
+	if (c_ops)
+		rc = c_ops->cnic_ctl(bp->cnic_data, ctl);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+/*
+ * for commands that have no data
+ */
+static int bnx2x_cnic_notify(struct bnx2x *bp, int cmd)
+{
+	struct cnic_ctl_info ctl = {0};
+
+	ctl.cmd = cmd;
+
+	return bnx2x_cnic_ctl_send(bp, &ctl);
+}
+
+static void bnx2x_cnic_cfc_comp(struct bnx2x *bp, int cid)
+{
+	struct cnic_ctl_info ctl;
+
+	/* first we tell CNIC and only then we count this as a completion */
+	ctl.cmd = CNIC_CTL_COMPLETION_CMD;
+	ctl.data.comp.cid = cid;
+
+	bnx2x_cnic_ctl_send_bh(bp, &ctl);
+	bnx2x_cnic_sp_post(bp, 1);
+}
+
+static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+	int rc = 0;
+
+	switch (ctl->cmd) {
+	case DRV_CTL_CTXTBL_WR_CMD: {
+		u32 index = ctl->data.io.offset;
+		dma_addr_t addr = ctl->data.io.dma_addr;
+
+		bnx2x_ilt_wr(bp, index, addr);
+		break;
+	}
+
+	case DRV_CTL_COMPLETION_CMD: {
+		int count = ctl->data.comp.comp_count;
+
+		bnx2x_cnic_sp_post(bp, count);
+		break;
+	}
+
+	/* rtnl_lock is held.  */
+	case DRV_CTL_START_L2_CMD: {
+		u32 cli = ctl->data.ring.client_id;
+
+		bp->rx_mode_cl_mask |= (1 << cli);
+		bnx2x_set_storm_rx_mode(bp);
+		break;
+	}
+
+	/* rtnl_lock is held.  */
+	case DRV_CTL_STOP_L2_CMD: {
+		u32 cli = ctl->data.ring.client_id;
+
+		bp->rx_mode_cl_mask &= ~(1 << cli);
+		bnx2x_set_storm_rx_mode(bp);
+		break;
+	}
+
+	default:
+		BNX2X_ERR("unknown command %x\n", ctl->cmd);
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void bnx2x_setup_cnic_irq_info(struct bnx2x *bp)
+{
+	struct cnic_eth_dev *cp = &bp->cnic_eth_dev;
+
+	if (bp->flags & USING_MSIX_FLAG) {
+		cp->drv_state |= CNIC_DRV_STATE_USING_MSIX;
+		cp->irq_arr[0].irq_flags |= CNIC_IRQ_FL_MSIX;
+		cp->irq_arr[0].vector = bp->msix_table[1].vector;
+	} else {
+		cp->drv_state &= ~CNIC_DRV_STATE_USING_MSIX;
+		cp->irq_arr[0].irq_flags &= ~CNIC_IRQ_FL_MSIX;
+	}
+	cp->irq_arr[0].status_blk = bp->cnic_sb;
+	cp->irq_arr[0].status_blk_num = CNIC_SB_ID(bp);
+	cp->irq_arr[1].status_blk = bp->def_status_blk;
+	cp->irq_arr[1].status_blk_num = DEF_SB_ID;
+
+	cp->num_irq = 2;
+}
+
+static int bnx2x_register_cnic(struct net_device *dev, struct cnic_ops *ops,
+			       void *data)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+	struct cnic_eth_dev *cp = &bp->cnic_eth_dev;
+
+	if (ops == NULL)
+		return -EINVAL;
+
+	if (atomic_read(&bp->intr_sem) != 0)
+		return -EBUSY;
+
+	bp->cnic_kwq = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!bp->cnic_kwq)
+		return -ENOMEM;
+
+	bp->cnic_kwq_cons = bp->cnic_kwq;
+	bp->cnic_kwq_prod = bp->cnic_kwq;
+	bp->cnic_kwq_last = bp->cnic_kwq + MAX_SP_DESC_CNT;
+
+	bp->cnic_spq_pending = 0;
+	bp->cnic_kwq_pending = 0;
+
+	bp->cnic_data = data;
+
+	cp->num_irq = 0;
+	cp->drv_state = CNIC_DRV_STATE_REGD;
+
+	bnx2x_init_sb(bp, bp->cnic_sb, bp->cnic_sb_mapping, CNIC_SB_ID(bp));
+
+	bnx2x_setup_cnic_irq_info(bp);
+	bnx2x_set_iscsi_eth_mac_addr(bp, 1);
+	bp->cnic_flags |= BNX2X_CNIC_FLAG_MAC_SET;
+	rcu_assign_pointer(bp->cnic_ops, ops);
+
+	return 0;
+}
+
+static int bnx2x_unregister_cnic(struct net_device *dev)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+	struct cnic_eth_dev *cp = &bp->cnic_eth_dev;
+
+	mutex_lock(&bp->cnic_mutex);
+	if (bp->cnic_flags & BNX2X_CNIC_FLAG_MAC_SET) {
+		bp->cnic_flags &= ~BNX2X_CNIC_FLAG_MAC_SET;
+		bnx2x_set_iscsi_eth_mac_addr(bp, 0);
+	}
+	cp->drv_state = 0;
+	rcu_assign_pointer(bp->cnic_ops, NULL);
+	mutex_unlock(&bp->cnic_mutex);
+	synchronize_rcu();
+	kfree(bp->cnic_kwq);
+	bp->cnic_kwq = NULL;
+
+	return 0;
+}
+
+struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+	struct cnic_eth_dev *cp = &bp->cnic_eth_dev;
+
+	cp->drv_owner = THIS_MODULE;
+	cp->chip_id = CHIP_ID(bp);
+	cp->pdev = bp->pdev;
+	cp->io_base = bp->regview;
+	cp->io_base2 = bp->doorbells;
+	cp->max_kwqe_pending = 8;
+	cp->ctx_blk_size = CNIC_CTX_PER_ILT * sizeof(union cdu_context);
+	cp->ctx_tbl_offset = FUNC_ILT_BASE(BP_FUNC(bp)) + 1;
+	cp->ctx_tbl_len = CNIC_ILT_LINES;
+	cp->starting_cid = BCM_CNIC_CID_START;
+	cp->drv_submit_kwqes_16 = bnx2x_cnic_sp_queue;
+	cp->drv_ctl = bnx2x_drv_ctl;
+	cp->drv_register_cnic = bnx2x_register_cnic;
+	cp->drv_unregister_cnic = bnx2x_unregister_cnic;
+
+	return cp;
+}
+EXPORT_SYMBOL(bnx2x_cnic_probe);
+
+#endif /* BCM_CNIC */
 
diff --git a/drivers/net/cnic_if.h b/drivers/net/cnic_if.h
index d8b09efdcb52..8aaf98bdd4f7 100644
--- a/drivers/net/cnic_if.h
+++ b/drivers/net/cnic_if.h
@@ -12,8 +12,8 @@
 #ifndef CNIC_IF_H
 #define CNIC_IF_H
 
-#define CNIC_MODULE_VERSION	"2.0.1"
-#define CNIC_MODULE_RELDATE	"Oct 01, 2009"
+#define CNIC_MODULE_VERSION	"2.1.0"
+#define CNIC_MODULE_RELDATE	"Oct 10, 2009"
 
 #define CNIC_ULP_RDMA		0
 #define CNIC_ULP_ISCSI		1
@@ -81,6 +81,8 @@ struct kcqe {
 #define DRV_CTL_CTX_WR_CMD		0x103
 #define DRV_CTL_CTXTBL_WR_CMD		0x104
 #define DRV_CTL_COMPLETION_CMD		0x105
+#define DRV_CTL_START_L2_CMD		0x106
+#define DRV_CTL_STOP_L2_CMD		0x107
 
 struct cnic_ctl_completion {
 	u32	cid;
@@ -105,11 +107,17 @@ struct drv_ctl_io {
 	dma_addr_t	dma_addr;
 };
 
+struct drv_ctl_l2_ring {
+	u32		client_id;
+	u32		cid;
+};
+
 struct drv_ctl_info {
 	int	cmd;
 	union {
 		struct drv_ctl_completion comp;
 		struct drv_ctl_io io;
+		struct drv_ctl_l2_ring ring;
 		char bytes[MAX_DRV_CTL_DATA];
 	} data;
 };
@@ -143,6 +151,7 @@ struct cnic_eth_dev {
 	u32		max_kwqe_pending;
 	struct pci_dev	*pdev;
 	void __iomem	*io_base;
+	void __iomem	*io_base2;
 
 	u32		ctx_tbl_offset;
 	u32		ctx_tbl_len;
@@ -298,5 +307,6 @@ extern int cnic_register_driver(int ulp_type, struct cnic_ulp_ops *ulp_ops);
 extern int cnic_unregister_driver(int ulp_type);
 
 extern struct cnic_eth_dev *bnx2_cnic_probe(struct net_device *dev);
+extern struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev);
 
 #endif
-- 
cgit v1.2.3


From f34d28ea0174df63253dc20a95de0b48e3d8145a Mon Sep 17 00:00:00 2001
From: Eilon Greenstein <eilong@broadcom.com>
Date: Thu, 15 Oct 2009 00:18:08 -0700
Subject: bnx2x: Changing the Disabled state to a flag

When working with DCC, a function can be disabled or enabled (virtual link down
or up). Using the function state introduced some race conditions with the
load/unload flow.
Using a separate flag to indicate that the function is disabled.

Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h      |  2 +-
 drivers/net/bnx2x_main.c | 34 +++++++++++++++++++---------------
 2 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index 60fa14f31d73..185a6bab2227 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -900,6 +900,7 @@ struct bnx2x {
 #define BP_NOMCP(bp)			(bp->flags & NO_MCP_FLAG)
 #define HW_VLAN_TX_FLAG			0x400
 #define HW_VLAN_RX_FLAG			0x800
+#define MF_FUNC_DIS			0x1000
 
 	int			func;
 #define BP_PORT(bp)			(bp->func % PORT_MAX)
@@ -965,7 +966,6 @@ struct bnx2x {
 #define BNX2X_STATE_CLOSING_WAIT4_HALT	0x4000
 #define BNX2X_STATE_CLOSING_WAIT4_DELETE 0x5000
 #define BNX2X_STATE_CLOSING_WAIT4_UNLOAD 0x6000
-#define BNX2X_STATE_DISABLED		0xd000
 #define BNX2X_STATE_DIAG		0xe000
 #define BNX2X_STATE_ERROR		0xf000
 
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index 691cf1541892..e7b3b27d16b6 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -1043,7 +1043,6 @@ static void bnx2x_sp_event(struct bnx2x_fastpath *fp,
 		break;
 
 	case (RAMROD_CMD_ID_ETH_SET_MAC | BNX2X_STATE_CLOSING_WAIT4_HALT):
-	case (RAMROD_CMD_ID_ETH_SET_MAC | BNX2X_STATE_DISABLED):
 		DP(NETIF_MSG_IFDOWN, "got (un)set mac ramrod\n");
 		bp->set_mac_pending--;
 		smp_wmb();
@@ -2157,7 +2156,7 @@ static void bnx2x_calc_fc_adv(struct bnx2x *bp)
 
 static void bnx2x_link_report(struct bnx2x *bp)
 {
-	if (bp->state == BNX2X_STATE_DISABLED) {
+	if (bp->flags & MF_FUNC_DIS) {
 		netif_carrier_off(bp->dev);
 		printk(KERN_ERR PFX "%s NIC Link is Down\n", bp->dev->name);
 		return;
@@ -2437,8 +2436,7 @@ static void bnx2x_link_attn(struct bnx2x *bp)
 			memset(&(pstats->mac_stx[0]), 0,
 			       sizeof(struct mac_stx));
 		}
-		if ((bp->state == BNX2X_STATE_OPEN) ||
-		    (bp->state == BNX2X_STATE_DISABLED))
+		if (bp->state == BNX2X_STATE_OPEN)
 			bnx2x_stats_handle(bp, STATS_EVENT_LINK_UP);
 	}
 
@@ -2481,9 +2479,7 @@ static void bnx2x_link_attn(struct bnx2x *bp)
 
 static void bnx2x__link_status_update(struct bnx2x *bp)
 {
-	int func = BP_FUNC(bp);
-
-	if (bp->state != BNX2X_STATE_OPEN)
+	if ((bp->state != BNX2X_STATE_OPEN) || (bp->flags & MF_FUNC_DIS))
 		return;
 
 	bnx2x_link_status_update(&bp->link_params, &bp->link_vars);
@@ -2640,14 +2636,19 @@ static void bnx2x_dcc_event(struct bnx2x *bp, u32 dcc_event)
 
 	if (dcc_event & DRV_STATUS_DCC_DISABLE_ENABLE_PF) {
 
+		/*
+		 * This is the only place besides the function initialization
+		 * where the bp->flags can change so it is done without any
+		 * locks
+		 */
 		if (bp->mf_config & FUNC_MF_CFG_FUNC_DISABLED) {
 			DP(NETIF_MSG_IFDOWN, "mf_cfg function disabled\n");
-			bp->state = BNX2X_STATE_DISABLED;
+			bp->flags |= MF_FUNC_DIS;
 
 			bnx2x_e1h_disable(bp);
 		} else {
 			DP(NETIF_MSG_IFUP, "mf_cfg function enabled\n");
-			bp->state = BNX2X_STATE_OPEN;
+			bp->flags &= ~MF_FUNC_DIS;
 
 			bnx2x_e1h_enable(bp);
 		}
@@ -4695,8 +4696,7 @@ static void bnx2x_timer(unsigned long data)
 		}
 	}
 
-	if ((bp->state == BNX2X_STATE_OPEN) ||
-	    (bp->state == BNX2X_STATE_DISABLED))
+	if (bp->state == BNX2X_STATE_OPEN)
 		bnx2x_stats_handle(bp, STATS_EVENT_UPDATE);
 
 timer_restart:
@@ -7629,7 +7629,7 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 	if (CHIP_IS_E1H(bp))
 		if (bp->mf_config & FUNC_MF_CFG_FUNC_DISABLED) {
 			DP(NETIF_MSG_IFUP, "mf_cfg function disabled\n");
-			bp->state = BNX2X_STATE_DISABLED;
+			bp->flags |= MF_FUNC_DIS;
 		}
 
 	if (bp->state == BNX2X_STATE_OPEN) {
@@ -9034,7 +9034,9 @@ static int bnx2x_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	cmd->supported = bp->port.supported;
 	cmd->advertising = bp->port.advertising;
 
-	if (netif_carrier_ok(dev)) {
+	if ((bp->state == BNX2X_STATE_OPEN) &&
+	    !(bp->flags & MF_FUNC_DIS) &&
+	    (bp->link_vars.link_up)) {
 		cmd->speed = bp->link_vars.line_speed;
 		cmd->duplex = bp->link_vars.duplex;
 		if (IS_E1HMF(bp)) {
@@ -9433,6 +9435,9 @@ static u32 bnx2x_get_link(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
+	if (bp->flags & MF_FUNC_DIS)
+		return 0;
+
 	return bp->link_vars.link_up;
 }
 
@@ -9837,8 +9842,7 @@ static int bnx2x_set_eeprom(struct net_device *dev,
 
 	} else if (eeprom->magic == 0x50485952) {
 		/* 'PHYR' (0x50485952): re-init link after FW upgrade */
-		if ((bp->state == BNX2X_STATE_OPEN) ||
-		    (bp->state == BNX2X_STATE_DISABLED)) {
+		if (bp->state == BNX2X_STATE_OPEN) {
 			bnx2x_acquire_phy_lock(bp);
 			rc |= bnx2x_link_reset(&bp->link_params,
 					       &bp->link_vars, 1);
-- 
cgit v1.2.3


From c4ff7cbf88be8bb0e3f942089f0ef0a40d98d654 Mon Sep 17 00:00:00 2001
From: Eilon Greenstein <eilong@broadcom.com>
Date: Thu, 15 Oct 2009 00:18:27 -0700
Subject: bnx2x: Adding FW mailbox mutex

DCC commands are not protected with the RTNL lock, so a mutex should be added

Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h      | 3 +++
 drivers/net/bnx2x_main.c | 7 +++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index 185a6bab2227..c3b32f71e024 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -1023,6 +1023,9 @@ struct bnx2x {
 	/* used to synchronize dmae accesses */
 	struct mutex		dmae_mutex;
 
+	/* used to protect the FW mail box */
+	struct mutex		fw_mb_mutex;
+
 	/* used to synchronize stats collecting */
 	int			stats_state;
 	/* used by dmae command loader */
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index e7b3b27d16b6..7c5c3000bbb4 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -2528,6 +2528,7 @@ u32 bnx2x_fw_command(struct bnx2x *bp, u32 command)
 	u32 cnt = 1;
 	u8 delay = CHIP_REV_IS_SLOW(bp) ? 100 : 10;
 
+	mutex_lock(&bp->fw_mb_mutex);
 	SHMEM_WR(bp, func_mb[func].drv_mb_header, (command | seq));
 	DP(BNX2X_MSG_MCP, "wrote command (%x) to FW MB\n", (command | seq));
 
@@ -2537,8 +2538,8 @@ u32 bnx2x_fw_command(struct bnx2x *bp, u32 command)
 
 		rc = SHMEM_RD(bp, func_mb[func].fw_mb_header);
 
-		/* Give the FW up to 2 second (200*10ms) */
-	} while ((seq != (rc & FW_MSG_SEQ_NUMBER_MASK)) && (cnt++ < 200));
+		/* Give the FW up to 5 second (500*10ms) */
+	} while ((seq != (rc & FW_MSG_SEQ_NUMBER_MASK)) && (cnt++ < 500));
 
 	DP(BNX2X_MSG_MCP, "[after %d ms] read (%x) seq is (%x) from FW MB\n",
 	   cnt*delay, rc, seq);
@@ -2552,6 +2553,7 @@ u32 bnx2x_fw_command(struct bnx2x *bp, u32 command)
 		bnx2x_fw_dump(bp);
 		rc = 0;
 	}
+	mutex_unlock(&bp->fw_mb_mutex);
 
 	return rc;
 }
@@ -8956,6 +8958,7 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
 	smp_wmb(); /* Ensure that bp->intr_sem update is SMP-safe */
 
 	mutex_init(&bp->port.phy_mutex);
+	mutex_init(&bp->fw_mb_mutex);
 #ifdef BCM_CNIC
 	mutex_init(&bp->cnic_mutex);
 #endif
-- 
cgit v1.2.3


From 7d323bfdc056a9142b8bdbab88e4d3ac6e4989e4 Mon Sep 17 00:00:00 2001
From: Eilon Greenstein <eilong@broadcom.com>
Date: Mon, 9 Nov 2009 06:09:35 +0000
Subject: bnx2x: Change coalescing granularity to 4us

Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h      |  2 +-
 drivers/net/bnx2x_main.c | 13 +++++++------
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index c3b32f71e024..928942b74ce6 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -1191,7 +1191,7 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms,
 #define MAX_SP_DESC_CNT			(SP_DESC_CNT - 1)
 
 
-#define BNX2X_BTR			3
+#define BNX2X_BTR			1
 #define MAX_SPQ_PENDING			8
 
 
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index ed56973794e8..08e6a35cfc20 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -4928,21 +4928,21 @@ static void bnx2x_update_coalesce(struct bnx2x *bp)
 		REG_WR8(bp, BAR_CSTRORM_INTMEM +
 			CSTORM_SB_HC_TIMEOUT_U_OFFSET(port, sb_id,
 						      U_SB_ETH_RX_CQ_INDEX),
-			bp->rx_ticks/12);
+			bp->rx_ticks/(4 * BNX2X_BTR));
 		REG_WR16(bp, BAR_CSTRORM_INTMEM +
 			 CSTORM_SB_HC_DISABLE_U_OFFSET(port, sb_id,
 						       U_SB_ETH_RX_CQ_INDEX),
-			 (bp->rx_ticks/12) ? 0 : 1);
+			 (bp->rx_ticks/(4 * BNX2X_BTR)) ? 0 : 1);
 
 		/* HC_INDEX_C_ETH_TX_CQ_CONS */
 		REG_WR8(bp, BAR_CSTRORM_INTMEM +
 			CSTORM_SB_HC_TIMEOUT_C_OFFSET(port, sb_id,
 						      C_SB_ETH_TX_CQ_INDEX),
-			bp->tx_ticks/12);
+			bp->tx_ticks/(4 * BNX2X_BTR));
 		REG_WR16(bp, BAR_CSTRORM_INTMEM +
 			 CSTORM_SB_HC_DISABLE_C_OFFSET(port, sb_id,
 						       C_SB_ETH_TX_CQ_INDEX),
-			 (bp->tx_ticks/12) ? 0 : 1);
+			 (bp->tx_ticks/(4 * BNX2X_BTR)) ? 0 : 1);
 	}
 }
 
@@ -9016,8 +9016,9 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
 
 	bp->rx_csum = 1;
 
-	bp->tx_ticks = 50;
-	bp->rx_ticks = 25;
+	/* make sure that the numbers are in the right granularity */
+	bp->tx_ticks = (50 / (4 * BNX2X_BTR)) * (4 * BNX2X_BTR);
+	bp->rx_ticks = (25 / (4 * BNX2X_BTR)) * (4 * BNX2X_BTR);
 
 	timer_interval = (CHIP_REV_IS_SLOW(bp) ? 5*HZ : HZ);
 	bp->current_interval = (poll ? poll : timer_interval);
-- 
cgit v1.2.3


From 54b9ddaa68414fad72ab2e1042be067c902441a6 Mon Sep 17 00:00:00 2001
From: Vladislav Zolotarov <vladz@broadcom.com>
Date: Mon, 16 Nov 2009 06:05:58 +0000
Subject: bnx2x: Handle Rx and Tx together in NAPI

Put Tx and Rx DPC to be handled in the NAPI:
  - Saves status blocks.
  - Moves the Tx work from hardIRQ to NAPI.

Signed-off-by: Vladislav Zolotarov <vladz@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2x.h      |  21 +--
 drivers/net/bnx2x_main.c | 367 +++++++++++++++++++----------------------------
 2 files changed, 157 insertions(+), 231 deletions(-)

(limited to 'drivers/net/bnx2x.h')

diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index 928942b74ce6..602ab86b6392 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -259,9 +259,6 @@ struct bnx2x_eth_q_stats {
 struct bnx2x_fastpath {
 
 	struct napi_struct	napi;
-
-	u8			is_rx_queue;
-
 	struct host_status_block *status_blk;
 	dma_addr_t		status_blk_mapping;
 
@@ -970,8 +967,7 @@ struct bnx2x {
 #define BNX2X_STATE_ERROR		0xf000
 
 	int			multi_mode;
-	int			num_rx_queues;
-	int			num_tx_queues;
+	int			num_queues;
 
 	u32			rx_mode;
 #define BNX2X_RX_MODE_NONE		0
@@ -1074,20 +1070,15 @@ struct bnx2x {
 };
 
 
-#define BNX2X_MAX_QUEUES(bp)	(IS_E1HMF(bp) ? (MAX_CONTEXT/(2 * E1HVN_MAX)) \
-					      : (MAX_CONTEXT/2))
-#define BNX2X_NUM_QUEUES(bp)	(bp->num_rx_queues + bp->num_tx_queues)
-#define is_multi(bp)		(BNX2X_NUM_QUEUES(bp) > 2)
+#define BNX2X_MAX_QUEUES(bp)	(IS_E1HMF(bp) ? (MAX_CONTEXT/E1HVN_MAX) \
+					      : MAX_CONTEXT)
+#define BNX2X_NUM_QUEUES(bp)	(bp->num_queues)
+#define is_multi(bp)		(BNX2X_NUM_QUEUES(bp) > 1)
 
-#define for_each_rx_queue(bp, var) \
-			for (var = 0; var < bp->num_rx_queues; var++)
-#define for_each_tx_queue(bp, var) \
-			for (var = bp->num_rx_queues; \
-			     var < BNX2X_NUM_QUEUES(bp); var++)
 #define for_each_queue(bp, var) \
 			for (var = 0; var < BNX2X_NUM_QUEUES(bp); var++)
 #define for_each_nondefault_queue(bp, var) \
-			for (var = 1; var < bp->num_rx_queues; var++)
+			for (var = 1; var < BNX2X_NUM_QUEUES(bp); var++)
 
 
 void bnx2x_read_dmae(struct bnx2x *bp, u32 src_addr, u32 len32);
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index e2cf686d1118..bdecd42d2b29 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -57,7 +57,7 @@
 #include "bnx2x_init_ops.h"
 #include "bnx2x_dump.h"
 
-#define DRV_MODULE_VERSION	"1.52.1-4"
+#define DRV_MODULE_VERSION	"1.52.1-5"
 #define DRV_MODULE_RELDATE	"2009/11/09"
 #define BNX2X_BC_VER		0x040200
 
@@ -91,15 +91,10 @@ module_param(multi_mode, int, 0);
 MODULE_PARM_DESC(multi_mode, " Multi queue mode "
 			     "(0 Disable; 1 Enable (default))");
 
-static int num_rx_queues;
-module_param(num_rx_queues, int, 0);
-MODULE_PARM_DESC(num_rx_queues, " Number of Rx queues for multi_mode=1"
-				" (default is half number of CPUs)");
-
-static int num_tx_queues;
-module_param(num_tx_queues, int, 0);
-MODULE_PARM_DESC(num_tx_queues, " Number of Tx queues for multi_mode=1"
-				" (default is half number of CPUs)");
+static int num_queues;
+module_param(num_queues, int, 0);
+MODULE_PARM_DESC(num_queues, " Number of queues for multi_mode=1"
+				" (default is as a number of CPUs)");
 
 static int disable_tpa;
 module_param(disable_tpa, int, 0);
@@ -558,7 +553,7 @@ static void bnx2x_panic_dump(struct bnx2x *bp)
 		  bp->def_att_idx, bp->attn_state, bp->spq_prod_idx);
 
 	/* Rx */
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		BNX2X_ERR("fp%d: rx_bd_prod(%x)  rx_bd_cons(%x)"
@@ -575,7 +570,7 @@ static void bnx2x_panic_dump(struct bnx2x *bp)
 	}
 
 	/* Tx */
-	for_each_tx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		BNX2X_ERR("fp%d: tx_pkt_prod(%x)  tx_pkt_cons(%x)"
@@ -590,7 +585,7 @@ static void bnx2x_panic_dump(struct bnx2x *bp)
 
 	/* Rings */
 	/* Rx */
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		start = RX_BD(le16_to_cpu(*fp->rx_cons_sb) - 10);
@@ -624,7 +619,7 @@ static void bnx2x_panic_dump(struct bnx2x *bp)
 	}
 
 	/* Tx */
-	for_each_tx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		start = TX_BD(le16_to_cpu(*fp->tx_cons_sb) - 10);
@@ -792,21 +787,13 @@ static inline void bnx2x_ack_sb(struct bnx2x *bp, u8 sb_id,
 	barrier();
 }
 
-static inline u16 bnx2x_update_fpsb_idx(struct bnx2x_fastpath *fp)
+static inline void bnx2x_update_fpsb_idx(struct bnx2x_fastpath *fp)
 {
 	struct host_status_block *fpsb = fp->status_blk;
-	u16 rc = 0;
 
 	barrier(); /* status block is written to by the chip */
-	if (fp->fp_c_idx != fpsb->c_status_block.status_block_index) {
-		fp->fp_c_idx = fpsb->c_status_block.status_block_index;
-		rc |= 1;
-	}
-	if (fp->fp_u_idx != fpsb->u_status_block.status_block_index) {
-		fp->fp_u_idx = fpsb->u_status_block.status_block_index;
-		rc |= 2;
-	}
-	return rc;
+	fp->fp_c_idx = fpsb->c_status_block.status_block_index;
+	fp->fp_u_idx = fpsb->u_status_block.status_block_index;
 }
 
 static u16 bnx2x_ack_int(struct bnx2x *bp)
@@ -846,6 +833,9 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 	u16 bd_idx = TX_BD(tx_buf->first_bd), new_cons;
 	int nbd;
 
+	/* prefetch skb end pointer to speedup dev_kfree_skb() */
+	prefetch(&skb->end);
+
 	DP(BNX2X_MSG_OFF, "pkt_idx %d  buff @(%p)->skb %p\n",
 	   idx, tx_buf, skb);
 
@@ -890,7 +880,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 
 	/* release skb */
 	WARN_ON(!skb);
-	dev_kfree_skb_any(skb);
+	dev_kfree_skb(skb);
 	tx_buf->first_bd = 0;
 	tx_buf->skb = NULL;
 
@@ -920,19 +910,28 @@ static inline u16 bnx2x_tx_avail(struct bnx2x_fastpath *fp)
 	return (s16)(fp->bp->tx_ring_size) - used;
 }
 
-static void bnx2x_tx_int(struct bnx2x_fastpath *fp)
+static inline int bnx2x_has_tx_work(struct bnx2x_fastpath *fp)
+{
+	u16 hw_cons;
+
+	/* Tell compiler that status block fields can change */
+	barrier();
+	hw_cons = le16_to_cpu(*fp->tx_cons_sb);
+	return hw_cons != fp->tx_pkt_cons;
+}
+
+static int bnx2x_tx_int(struct bnx2x_fastpath *fp)
 {
 	struct bnx2x *bp = fp->bp;
 	struct netdev_queue *txq;
 	u16 hw_cons, sw_cons, bd_cons = fp->tx_bd_cons;
-	int done = 0;
 
 #ifdef BNX2X_STOP_ON_ERROR
 	if (unlikely(bp->panic))
-		return;
+		return -1;
 #endif
 
-	txq = netdev_get_tx_queue(bp->dev, fp->index - bp->num_rx_queues);
+	txq = netdev_get_tx_queue(bp->dev, fp->index);
 	hw_cons = le16_to_cpu(*fp->tx_cons_sb);
 	sw_cons = fp->tx_pkt_cons;
 
@@ -953,7 +952,6 @@ static void bnx2x_tx_int(struct bnx2x_fastpath *fp)
 */
 		bd_cons = bnx2x_free_tx_pkt(bp, fp, pkt_cons);
 		sw_cons++;
-		done++;
 	}
 
 	fp->tx_pkt_cons = sw_cons;
@@ -975,6 +973,7 @@ static void bnx2x_tx_int(struct bnx2x_fastpath *fp)
 		    (bnx2x_tx_avail(fp) >= MAX_SKB_FRAGS + 3))
 			netif_tx_wake_queue(txq);
 	}
+	return 0;
 }
 
 #ifdef BCM_CNIC
@@ -1561,6 +1560,8 @@ static int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 		} else {
 			rx_buf = &fp->rx_buf_ring[bd_cons];
 			skb = rx_buf->skb;
+			prefetch(skb);
+			prefetch((u8 *)skb + 256);
 			len = le16_to_cpu(cqe->fast_path_cqe.pkt_len);
 			pad = cqe->fast_path_cqe.placement_offset;
 
@@ -1742,27 +1743,13 @@ static irqreturn_t bnx2x_msix_fp_int(int irq, void *fp_cookie)
 	if (unlikely(bp->panic))
 		return IRQ_HANDLED;
 #endif
-	/* Handle Rx or Tx according to MSI-X vector */
-	if (fp->is_rx_queue) {
-		prefetch(fp->rx_cons_sb);
-		prefetch(&fp->status_blk->u_status_block.status_block_index);
-
-		napi_schedule(&bnx2x_fp(bp, fp->index, napi));
-
-	} else {
-		prefetch(fp->tx_cons_sb);
-		prefetch(&fp->status_blk->c_status_block.status_block_index);
-
-		bnx2x_update_fpsb_idx(fp);
-		rmb();
-		bnx2x_tx_int(fp);
 
-		/* Re-enable interrupts */
-		bnx2x_ack_sb(bp, fp->sb_id, USTORM_ID,
-			     le16_to_cpu(fp->fp_u_idx), IGU_INT_NOP, 1);
-		bnx2x_ack_sb(bp, fp->sb_id, CSTORM_ID,
-			     le16_to_cpu(fp->fp_c_idx), IGU_INT_ENABLE, 1);
-	}
+	/* Handle Rx and Tx according to MSI-X vector */
+	prefetch(fp->rx_cons_sb);
+	prefetch(fp->tx_cons_sb);
+	prefetch(&fp->status_blk->u_status_block.status_block_index);
+	prefetch(&fp->status_blk->c_status_block.status_block_index);
+	napi_schedule(&bnx2x_fp(bp, fp->index, napi));
 
 	return IRQ_HANDLED;
 }
@@ -1797,31 +1784,14 @@ static irqreturn_t bnx2x_interrupt(int irq, void *dev_instance)
 
 		mask = 0x2 << fp->sb_id;
 		if (status & mask) {
-			/* Handle Rx or Tx according to SB id */
-			if (fp->is_rx_queue) {
-				prefetch(fp->rx_cons_sb);
-				prefetch(&fp->status_blk->u_status_block.
-							status_block_index);
-
-				napi_schedule(&bnx2x_fp(bp, fp->index, napi));
-
-			} else {
-				prefetch(fp->tx_cons_sb);
-				prefetch(&fp->status_blk->c_status_block.
-							status_block_index);
-
-				bnx2x_update_fpsb_idx(fp);
-				rmb();
-				bnx2x_tx_int(fp);
-
-				/* Re-enable interrupts */
-				bnx2x_ack_sb(bp, fp->sb_id, USTORM_ID,
-					     le16_to_cpu(fp->fp_u_idx),
-					     IGU_INT_NOP, 1);
-				bnx2x_ack_sb(bp, fp->sb_id, CSTORM_ID,
-					     le16_to_cpu(fp->fp_c_idx),
-					     IGU_INT_ENABLE, 1);
-			}
+			/* Handle Rx and Tx according to SB id */
+			prefetch(fp->rx_cons_sb);
+			prefetch(&fp->status_blk->u_status_block.
+						status_block_index);
+			prefetch(fp->tx_cons_sb);
+			prefetch(&fp->status_blk->c_status_block.
+						status_block_index);
+			napi_schedule(&bnx2x_fp(bp, fp->index, napi));
 			status &= ~mask;
 		}
 	}
@@ -4027,7 +3997,7 @@ static int bnx2x_storm_stats_update(struct bnx2x *bp)
 	estats->no_buff_discard_hi = 0;
 	estats->no_buff_discard_lo = 0;
 
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 		int cl_id = fp->cl_id;
 		struct tstorm_per_client_stats *tclient =
@@ -4244,7 +4214,7 @@ static void bnx2x_net_stats_update(struct bnx2x *bp)
 	nstats->tx_bytes = bnx2x_hilo(&estats->total_bytes_transmitted_hi);
 
 	nstats->rx_dropped = estats->mac_discard;
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		nstats->rx_dropped +=
 			le32_to_cpu(bp->fp[i].old_tclient.checksum_discard);
 
@@ -4298,7 +4268,7 @@ static void bnx2x_drv_stats_update(struct bnx2x *bp)
 	estats->rx_err_discard_pkt = 0;
 	estats->rx_skb_alloc_failed = 0;
 	estats->hw_csum_err = 0;
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_eth_q_stats *qstats = &bp->fp[i].eth_q_stats;
 
 		estats->driver_xoff += qstats->driver_xoff;
@@ -4329,7 +4299,7 @@ static void bnx2x_stats_update(struct bnx2x *bp)
 
 	if (bp->msglevel & NETIF_MSG_TIMER) {
 		struct bnx2x_fastpath *fp0_rx = bp->fp;
-		struct bnx2x_fastpath *fp0_tx = &(bp->fp[bp->num_rx_queues]);
+		struct bnx2x_fastpath *fp0_tx = bp->fp;
 		struct tstorm_per_client_stats *old_tclient =
 							&bp->fp->old_tclient;
 		struct bnx2x_eth_q_stats *qstats = &bp->fp->eth_q_stats;
@@ -4984,7 +4954,7 @@ static void bnx2x_init_rx_rings(struct bnx2x *bp)
 
 	if (bp->flags & TPA_ENABLE_FLAG) {
 
-		for_each_rx_queue(bp, j) {
+		for_each_queue(bp, j) {
 			struct bnx2x_fastpath *fp = &bp->fp[j];
 
 			for (i = 0; i < max_agg_queues; i++) {
@@ -5007,16 +4977,13 @@ static void bnx2x_init_rx_rings(struct bnx2x *bp)
 		}
 	}
 
-	for_each_rx_queue(bp, j) {
+	for_each_queue(bp, j) {
 		struct bnx2x_fastpath *fp = &bp->fp[j];
 
 		fp->rx_bd_cons = 0;
 		fp->rx_cons_sb = BNX2X_RX_SB_INDEX;
 		fp->rx_bd_cons_sb = BNX2X_RX_SB_BD_INDEX;
 
-		/* Mark queue as Rx */
-		fp->is_rx_queue = 1;
-
 		/* "next page" elements initialization */
 		/* SGE ring */
 		for (i = 1; i <= NUM_RX_SGE_PAGES; i++) {
@@ -5122,7 +5089,7 @@ static void bnx2x_init_tx_ring(struct bnx2x *bp)
 {
 	int i, j;
 
-	for_each_tx_queue(bp, j) {
+	for_each_queue(bp, j) {
 		struct bnx2x_fastpath *fp = &bp->fp[j];
 
 		for (i = 1; i <= NUM_TX_RINGS; i++) {
@@ -5148,10 +5115,6 @@ static void bnx2x_init_tx_ring(struct bnx2x *bp)
 		fp->tx_cons_sb = BNX2X_TX_SB_INDEX;
 		fp->tx_pkt = 0;
 	}
-
-	/* clean tx statistics */
-	for_each_rx_queue(bp, i)
-		bnx2x_fp(bp, i, tx_pkt) = 0;
 }
 
 static void bnx2x_init_sp_ring(struct bnx2x *bp)
@@ -5180,7 +5143,8 @@ static void bnx2x_init_context(struct bnx2x *bp)
 {
 	int i;
 
-	for_each_rx_queue(bp, i) {
+	/* Rx */
+	for_each_queue(bp, i) {
 		struct eth_context *context = bnx2x_sp(bp, context[i].eth);
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 		u8 cl_id = fp->cl_id;
@@ -5232,10 +5196,11 @@ static void bnx2x_init_context(struct bnx2x *bp)
 					       ETH_CONNECTION_TYPE);
 	}
 
-	for_each_tx_queue(bp, i) {
+	/* Tx */
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 		struct eth_context *context =
-			bnx2x_sp(bp, context[i - bp->num_rx_queues].eth);
+			bnx2x_sp(bp, context[i].eth);
 
 		context->cstorm_st_context.sb_index_number =
 						C_SB_ETH_TX_CQ_INDEX;
@@ -5263,7 +5228,7 @@ static void bnx2x_init_ind_table(struct bnx2x *bp)
 	for (i = 0; i < TSTORM_INDIRECTION_TABLE_SIZE; i++)
 		REG_WR8(bp, BAR_TSTRORM_INTMEM +
 			TSTORM_INDIRECTION_TABLE_OFFSET(func) + i,
-			bp->fp->cl_id + (i % bp->num_rx_queues));
+			bp->fp->cl_id + (i % bp->num_queues));
 }
 
 static void bnx2x_set_client_config(struct bnx2x *bp)
@@ -5507,7 +5472,7 @@ static void bnx2x_init_internal_func(struct bnx2x *bp)
 		min((u32)(min((u32)8, (u32)MAX_SKB_FRAGS) *
 			  SGE_PAGE_SIZE * PAGES_PER_SGE),
 		    (u32)0xffff);
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		REG_WR(bp, BAR_USTRORM_INTMEM +
@@ -5542,7 +5507,7 @@ static void bnx2x_init_internal_func(struct bnx2x *bp)
 		rx_pause.cqe_thr_high = 350;
 		rx_pause.sge_thr_high = 0;
 
-		for_each_rx_queue(bp, i) {
+		for_each_queue(bp, i) {
 			struct bnx2x_fastpath *fp = &bp->fp[i];
 
 			if (!fp->disable_tpa) {
@@ -5637,9 +5602,6 @@ static void bnx2x_nic_init(struct bnx2x *bp, u32 load_code)
 #else
 		fp->sb_id = fp->cl_id;
 #endif
-		/* Suitable Rx and Tx SBs are served by the same client */
-		if (i >= bp->num_rx_queues)
-			fp->cl_id -= bp->num_rx_queues;
 		DP(NETIF_MSG_IFUP,
 		   "queue[%d]:  bnx2x_init_sb(%p,%p)  cl_id %d  sb %d\n",
 		   i, bp, fp->status_blk, fp->cl_id, fp->sb_id);
@@ -6749,7 +6711,7 @@ static void bnx2x_free_mem(struct bnx2x *bp)
 			       sizeof(struct host_status_block));
 	}
 	/* Rx */
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 
 		/* fastpath rx rings: rx_buf rx_desc rx_comp */
 		BNX2X_FREE(bnx2x_fp(bp, i, rx_buf_ring));
@@ -6769,7 +6731,7 @@ static void bnx2x_free_mem(struct bnx2x *bp)
 			       BCM_PAGE_SIZE * NUM_RX_SGE_PAGES);
 	}
 	/* Tx */
-	for_each_tx_queue(bp, i) {
+	for_each_queue(bp, i) {
 
 		/* fastpath tx rings: tx_buf tx_desc */
 		BNX2X_FREE(bnx2x_fp(bp, i, tx_buf_ring));
@@ -6831,7 +6793,7 @@ static int bnx2x_alloc_mem(struct bnx2x *bp)
 				sizeof(struct host_status_block));
 	}
 	/* Rx */
-	for_each_rx_queue(bp, i) {
+	for_each_queue(bp, i) {
 
 		/* fastpath rx rings: rx_buf rx_desc rx_comp */
 		BNX2X_ALLOC(bnx2x_fp(bp, i, rx_buf_ring),
@@ -6853,7 +6815,7 @@ static int bnx2x_alloc_mem(struct bnx2x *bp)
 				BCM_PAGE_SIZE * NUM_RX_SGE_PAGES);
 	}
 	/* Tx */
-	for_each_tx_queue(bp, i) {
+	for_each_queue(bp, i) {
 
 		/* fastpath tx rings: tx_buf tx_desc */
 		BNX2X_ALLOC(bnx2x_fp(bp, i, tx_buf_ring),
@@ -6909,7 +6871,7 @@ static void bnx2x_free_tx_skbs(struct bnx2x *bp)
 {
 	int i;
 
-	for_each_tx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		u16 bd_cons = fp->tx_bd_cons;
@@ -6927,7 +6889,7 @@ static void bnx2x_free_rx_skbs(struct bnx2x *bp)
 {
 	int i, j;
 
-	for_each_rx_queue(bp, j) {
+	for_each_queue(bp, j) {
 		struct bnx2x_fastpath *fp = &bp->fp[j];
 
 		for (i = 0; i < NUM_RX_BD; i++) {
@@ -7042,12 +7004,8 @@ static int bnx2x_req_msix_irqs(struct bnx2x *bp)
 #endif
 	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
-
-		if (i < bp->num_rx_queues)
-			sprintf(fp->name, "%s-rx-%d", bp->dev->name, i);
-		else
-			sprintf(fp->name, "%s-tx-%d",
-				bp->dev->name, i - bp->num_rx_queues);
+		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
+			 bp->dev->name, i);
 
 		rc = request_irq(bp->msix_table[i + offset].vector,
 				 bnx2x_msix_fp_int, 0, fp->name, fp);
@@ -7106,7 +7064,7 @@ static void bnx2x_napi_enable(struct bnx2x *bp)
 {
 	int i;
 
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		napi_enable(&bnx2x_fp(bp, i, napi));
 }
 
@@ -7114,7 +7072,7 @@ static void bnx2x_napi_disable(struct bnx2x *bp)
 {
 	int i;
 
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		napi_disable(&bnx2x_fp(bp, i, napi));
 }
 
@@ -7410,88 +7368,60 @@ static int bnx2x_setup_multi(struct bnx2x *bp, int index)
 
 static int bnx2x_poll(struct napi_struct *napi, int budget);
 
-static void bnx2x_set_int_mode_msix(struct bnx2x *bp, int *num_rx_queues_out,
-				    int *num_tx_queues_out)
+static void bnx2x_set_num_queues_msix(struct bnx2x *bp)
 {
-	int _num_rx_queues = 0, _num_tx_queues = 0;
 
 	switch (bp->multi_mode) {
 	case ETH_RSS_MODE_DISABLED:
-		_num_rx_queues = 1;
-		_num_tx_queues = 1;
+		bp->num_queues = 1;
 		break;
 
 	case ETH_RSS_MODE_REGULAR:
-		if (num_rx_queues)
-			_num_rx_queues = min_t(u32, num_rx_queues,
-					       BNX2X_MAX_QUEUES(bp));
-		else
-			_num_rx_queues = min_t(u32, num_online_cpus(),
-					       BNX2X_MAX_QUEUES(bp));
-
-		if (num_tx_queues)
-			_num_tx_queues = min_t(u32, num_tx_queues,
-					       BNX2X_MAX_QUEUES(bp));
+		if (num_queues)
+			bp->num_queues = min_t(u32, num_queues,
+						  BNX2X_MAX_QUEUES(bp));
 		else
-			_num_tx_queues = min_t(u32, num_online_cpus(),
-					       BNX2X_MAX_QUEUES(bp));
-
-		/* There must be not more Tx queues than Rx queues */
-		if (_num_tx_queues > _num_rx_queues) {
-			BNX2X_ERR("number of tx queues (%d) > "
-				  "number of rx queues (%d)"
-				  "  defaulting to %d\n",
-				  _num_tx_queues, _num_rx_queues,
-				  _num_rx_queues);
-			_num_tx_queues = _num_rx_queues;
-		}
+			bp->num_queues = min_t(u32, num_online_cpus(),
+						  BNX2X_MAX_QUEUES(bp));
 		break;
 
 
 	default:
-		_num_rx_queues = 1;
-		_num_tx_queues = 1;
+		bp->num_queues = 1;
 		break;
 	}
-
-	*num_rx_queues_out = _num_rx_queues;
-	*num_tx_queues_out = _num_tx_queues;
 }
 
-static int bnx2x_set_int_mode(struct bnx2x *bp)
+static int bnx2x_set_num_queues(struct bnx2x *bp)
 {
 	int rc = 0;
 
 	switch (int_mode) {
 	case INT_MODE_INTx:
 	case INT_MODE_MSI:
-		bp->num_rx_queues = 1;
-		bp->num_tx_queues = 1;
+		bp->num_queues = 1;
 		DP(NETIF_MSG_IFUP, "set number of queues to 1\n");
 		break;
 
 	case INT_MODE_MSIX:
 	default:
-		/* Set interrupt mode according to bp->multi_mode value */
-		bnx2x_set_int_mode_msix(bp, &bp->num_rx_queues,
-					&bp->num_tx_queues);
+		/* Set number of queues according to bp->multi_mode value */
+		bnx2x_set_num_queues_msix(bp);
 
-		DP(NETIF_MSG_IFUP, "set number of queues to: rx %d tx %d\n",
-		   bp->num_rx_queues, bp->num_tx_queues);
+		DP(NETIF_MSG_IFUP, "set number of queues to %d\n",
+		   bp->num_queues);
 
 		/* if we can't use MSI-X we only need one fp,
 		 * so try to enable MSI-X with the requested number of fp's
 		 * and fallback to MSI or legacy INTx with one fp
 		 */
 		rc = bnx2x_enable_msix(bp);
-		if (rc) {
+		if (rc)
 			/* failed to enable MSI-X */
-			bp->num_rx_queues = 1;
-			bp->num_tx_queues = 1;
-		}
+			bp->num_queues = 1;
 		break;
 	}
-	bp->dev->real_num_tx_queues = bp->num_tx_queues;
+	bp->dev->real_num_tx_queues = bp->num_queues;
 	return rc;
 }
 
@@ -7513,16 +7443,16 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 
 	bp->state = BNX2X_STATE_OPENING_WAIT4_LOAD;
 
-	rc = bnx2x_set_int_mode(bp);
+	rc = bnx2x_set_num_queues(bp);
 
 	if (bnx2x_alloc_mem(bp))
 		return -ENOMEM;
 
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		bnx2x_fp(bp, i, disable_tpa) =
 					((bp->flags & TPA_ENABLE_FLAG) == 0);
 
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi),
 			       bnx2x_poll, 128);
 
@@ -7536,7 +7466,7 @@ static int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 		}
 	} else {
 		/* Fall to INTx if failed to enable MSI-X due to lack of
-		   memory (in bnx2x_set_int_mode()) */
+		   memory (in bnx2x_set_num_queues()) */
 		if ((rc != -ENOMEM) && (int_mode != INT_MODE_INTx))
 			bnx2x_enable_msi(bp);
 		bnx2x_ack_int(bp);
@@ -7730,14 +7660,14 @@ load_error3:
 	bp->port.pmf = 0;
 	/* Free SKBs, SGEs, TPA pool and driver internals */
 	bnx2x_free_skbs(bp);
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		bnx2x_free_rx_sge_range(bp, bp->fp + i, NUM_RX_SGE);
 load_error2:
 	/* Release IRQs */
 	bnx2x_free_irq(bp);
 load_error1:
 	bnx2x_napi_disable(bp);
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		netif_napi_del(&bnx2x_fp(bp, i, napi));
 	bnx2x_free_mem(bp);
 
@@ -7928,7 +7858,7 @@ static int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode)
 	bnx2x_free_irq(bp);
 
 	/* Wait until tx fastpath tasks complete */
-	for_each_tx_queue(bp, i) {
+	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 
 		cnt = 1000;
@@ -8071,9 +8001,9 @@ unload_error:
 
 	/* Free SKBs, SGEs, TPA pool and driver internals */
 	bnx2x_free_skbs(bp);
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		bnx2x_free_rx_sge_range(bp, bp->fp + i, NUM_RX_SGE);
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		netif_napi_del(&bnx2x_fp(bp, i, napi));
 	bnx2x_free_mem(bp);
 
@@ -10269,7 +10199,7 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode, u8 link_up)
 	struct sk_buff *skb;
 	unsigned char *packet;
 	struct bnx2x_fastpath *fp_rx = &bp->fp[0];
-	struct bnx2x_fastpath *fp_tx = &bp->fp[bp->num_rx_queues];
+	struct bnx2x_fastpath *fp_tx = &bp->fp[0];
 	u16 tx_start_idx, tx_idx;
 	u16 rx_start_idx, rx_idx;
 	u16 pkt_prod, bd_prod;
@@ -10346,7 +10276,7 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode, u8 link_up)
 
 	fp_tx->tx_db.data.prod += 2;
 	barrier();
-	DOORBELL(bp, fp_tx->index - bp->num_rx_queues, fp_tx->tx_db.raw);
+	DOORBELL(bp, fp_tx->index, fp_tx->tx_db.raw);
 
 	mmiowb();
 
@@ -10725,7 +10655,7 @@ static int bnx2x_get_sset_count(struct net_device *dev, int stringset)
 	switch(stringset) {
 	case ETH_SS_STATS:
 		if (is_multi(bp)) {
-			num_stats = BNX2X_NUM_Q_STATS * bp->num_rx_queues;
+			num_stats = BNX2X_NUM_Q_STATS * bp->num_queues;
 			if (!IS_E1HMF_MODE_STAT(bp))
 				num_stats += BNX2X_NUM_STATS;
 		} else {
@@ -10756,7 +10686,7 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 	case ETH_SS_STATS:
 		if (is_multi(bp)) {
 			k = 0;
-			for_each_rx_queue(bp, i) {
+			for_each_queue(bp, i) {
 				for (j = 0; j < BNX2X_NUM_Q_STATS; j++)
 					sprintf(buf + (k + j)*ETH_GSTRING_LEN,
 						bnx2x_q_stats_arr[j].string, i);
@@ -10793,7 +10723,7 @@ static void bnx2x_get_ethtool_stats(struct net_device *dev,
 
 	if (is_multi(bp)) {
 		k = 0;
-		for_each_rx_queue(bp, i) {
+		for_each_queue(bp, i) {
 			hw_stats = (u32 *)&bp->fp[i].eth_q_stats;
 			for (j = 0; j < BNX2X_NUM_Q_STATS; j++) {
 				if (bnx2x_q_stats_arr[j].size == 0) {
@@ -10989,54 +10919,60 @@ static inline int bnx2x_has_rx_work(struct bnx2x_fastpath *fp)
 
 static int bnx2x_poll(struct napi_struct *napi, int budget)
 {
+	int work_done = 0;
 	struct bnx2x_fastpath *fp = container_of(napi, struct bnx2x_fastpath,
 						 napi);
 	struct bnx2x *bp = fp->bp;
-	int work_done = 0;
 
+	while (1) {
 #ifdef BNX2X_STOP_ON_ERROR
-	if (unlikely(bp->panic))
-		goto poll_panic;
+		if (unlikely(bp->panic)) {
+			napi_complete(napi);
+			return 0;
+		}
 #endif
 
-	prefetch(fp->rx_buf_ring[RX_BD(fp->rx_bd_cons)].skb);
-	prefetch((char *)(fp->rx_buf_ring[RX_BD(fp->rx_bd_cons)].skb) + 256);
-
-	bnx2x_update_fpsb_idx(fp);
-
-	if (bnx2x_has_rx_work(fp)) {
-		work_done = bnx2x_rx_int(fp, budget);
+		if (bnx2x_has_tx_work(fp))
+			bnx2x_tx_int(fp);
 
-		/* must not complete if we consumed full budget */
-		if (work_done >= budget)
-			goto poll_again;
-	}
+		if (bnx2x_has_rx_work(fp)) {
+			work_done += bnx2x_rx_int(fp, budget - work_done);
 
-	/* bnx2x_has_rx_work() reads the status block, thus we need to
-	 * ensure that status block indices have been actually read
-	 * (bnx2x_update_fpsb_idx) prior to this check (bnx2x_has_rx_work)
-	 * so that we won't write the "newer" value of the status block to IGU
-	 * (if there was a DMA right after bnx2x_has_rx_work and
-	 * if there is no rmb, the memory reading (bnx2x_update_fpsb_idx)
-	 * may be postponed to right before bnx2x_ack_sb). In this case
-	 * there will never be another interrupt until there is another update
-	 * of the status block, while there is still unhandled work.
-	 */
-	rmb();
+			/* must not complete if we consumed full budget */
+			if (work_done >= budget)
+				break;
+		}
 
-	if (!bnx2x_has_rx_work(fp)) {
-#ifdef BNX2X_STOP_ON_ERROR
-poll_panic:
-#endif
-		napi_complete(napi);
+		/* Fall out from the NAPI loop if needed */
+		if (!(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
+			bnx2x_update_fpsb_idx(fp);
+		/* bnx2x_has_rx_work() reads the status block, thus we need
+		 * to ensure that status block indices have been actually read
+		 * (bnx2x_update_fpsb_idx) prior to this check
+		 * (bnx2x_has_rx_work) so that we won't write the "newer"
+		 * value of the status block to IGU (if there was a DMA right
+		 * after bnx2x_has_rx_work and if there is no rmb, the memory
+		 * reading (bnx2x_update_fpsb_idx) may be postponed to right
+		 * before bnx2x_ack_sb). In this case there will never be
+		 * another interrupt until there is another update of the
+		 * status block, while there is still unhandled work.
+		 */
+			rmb();
 
-		bnx2x_ack_sb(bp, fp->sb_id, USTORM_ID,
-			     le16_to_cpu(fp->fp_u_idx), IGU_INT_NOP, 1);
-		bnx2x_ack_sb(bp, fp->sb_id, CSTORM_ID,
-			     le16_to_cpu(fp->fp_c_idx), IGU_INT_ENABLE, 1);
+			if (!(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
+				napi_complete(napi);
+				/* Re-enable interrupts */
+				bnx2x_ack_sb(bp, fp->sb_id, CSTORM_ID,
+					     le16_to_cpu(fp->fp_c_idx),
+					     IGU_INT_NOP, 1);
+				bnx2x_ack_sb(bp, fp->sb_id, USTORM_ID,
+					     le16_to_cpu(fp->fp_u_idx),
+					     IGU_INT_ENABLE, 1);
+				break;
+			}
+		}
 	}
 
-poll_again:
 	return work_done;
 }
 
@@ -11221,7 +11157,7 @@ exit_lbl:
 static netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
-	struct bnx2x_fastpath *fp, *fp_stat;
+	struct bnx2x_fastpath *fp;
 	struct netdev_queue *txq;
 	struct sw_tx_bd *tx_buf;
 	struct eth_tx_start_bd *tx_start_bd;
@@ -11243,11 +11179,10 @@ static netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	fp_index = skb_get_queue_mapping(skb);
 	txq = netdev_get_tx_queue(dev, fp_index);
 
-	fp = &bp->fp[fp_index + bp->num_rx_queues];
-	fp_stat = &bp->fp[fp_index];
+	fp = &bp->fp[fp_index];
 
 	if (unlikely(bnx2x_tx_avail(fp) < (skb_shinfo(skb)->nr_frags + 3))) {
-		fp_stat->eth_q_stats.driver_xoff++;
+		fp->eth_q_stats.driver_xoff++;
 		netif_tx_stop_queue(txq);
 		BNX2X_ERR("BUG! Tx ring full when queue awake!\n");
 		return NETDEV_TX_BUSY;
@@ -11473,7 +11408,7 @@ static netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	fp->tx_db.data.prod += nbd;
 	barrier();
-	DOORBELL(bp, fp->index - bp->num_rx_queues, fp->tx_db.raw);
+	DOORBELL(bp, fp->index, fp->tx_db.raw);
 
 	mmiowb();
 
@@ -11484,11 +11419,11 @@ static netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* We want bnx2x_tx_int to "see" the updated tx_bd_prod
 		   if we put Tx into XOFF state. */
 		smp_mb();
-		fp_stat->eth_q_stats.driver_xoff++;
+		fp->eth_q_stats.driver_xoff++;
 		if (bnx2x_tx_avail(fp) >= MAX_SKB_FRAGS + 3)
 			netif_tx_wake_queue(txq);
 	}
-	fp_stat->tx_pkt++;
+	fp->tx_pkt++;
 
 	return NETDEV_TX_OK;
 }
@@ -12376,9 +12311,9 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp)
 
 	/* Free SKBs, SGEs, TPA pool and driver internals */
 	bnx2x_free_skbs(bp);
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		bnx2x_free_rx_sge_range(bp, bp->fp + i, NUM_RX_SGE);
-	for_each_rx_queue(bp, i)
+	for_each_queue(bp, i)
 		netif_napi_del(&bnx2x_fp(bp, i, napi));
 	bnx2x_free_mem(bp);
 
-- 
cgit v1.2.3