Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

16 files changed, 2152 insertions, 1095 deletions

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 72897c47b8c..e8d4db10c8f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -34,25 +34,16 @@
 
 #include "bnx2x_hsi.h"
 
-#if defined(CONFIG_CNIC) || defined(CONFIG_CNIC_MODULE)
-#define BCM_CNIC 1
 #include "../cnic_if.h"
-#endif
 
-#ifdef BCM_CNIC
-#define BNX2X_MIN_MSIX_VEC_CNT 3
-#define BNX2X_MSIX_VEC_FP_START 2
-#else
-#define BNX2X_MIN_MSIX_VEC_CNT 2
-#define BNX2X_MSIX_VEC_FP_START 1
-#endif
+
+#define BNX2X_MIN_MSIX_VEC_CNT(bp)		((bp)->min_msix_vec_cnt)
 
 #include <linux/mdio.h>
 
 #include "bnx2x_reg.h"
 #include "bnx2x_fw_defs.h"
 #include "bnx2x_mfw_req.h"
-#include "bnx2x_hsi.h"
 #include "bnx2x_link.h"
 #include "bnx2x_sp.h"
 #include "bnx2x_dcb.h"
@@ -256,15 +247,10 @@ enum {
 	/* FCoE L2 */
 #define	BNX2X_FCOE_ETH_CID(bp)		(BNX2X_CNIC_START_ETH_CID(bp) + 1)
 
-/** Additional rings budgeting */
-#ifdef BCM_CNIC
-#define CNIC_PRESENT			1
-#define FCOE_PRESENT			1
-#else
-#define CNIC_PRESENT			0
-#define FCOE_PRESENT			0
-#endif /* BCM_CNIC */
-#define NON_ETH_CONTEXT_USE	(FCOE_PRESENT)
+#define CNIC_SUPPORT(bp)		((bp)->cnic_support)
+#define CNIC_ENABLED(bp)		((bp)->cnic_enabled)
+#define CNIC_LOADED(bp)			((bp)->cnic_loaded)
+#define FCOE_INIT(bp)			((bp)->fcoe_init)
 
 #define AEU_IN_ATTN_BITS_PXPPCICLOCKCLIENT_PARITY_ERROR \
 	AEU_INPUTS_ATTN_BITS_PXPPCICLOCKCLIENT_PARITY_ERROR
@@ -297,9 +283,7 @@ enum {
 	OOO_TXQ_IDX_OFFSET,
 };
 #define MAX_ETH_TXQ_IDX(bp)	(BNX2X_NUM_NON_CNIC_QUEUES(bp) * (bp)->max_cos)
-#ifdef BCM_CNIC
 #define FCOE_TXQ_IDX(bp)	(MAX_ETH_TXQ_IDX(bp) + FCOE_TXQ_IDX_OFFSET)
-#endif
 
 /* fast path */
 /*
@@ -505,7 +489,7 @@ struct bnx2x_fastpath {
 	u32			ustorm_rx_prods_offset;
 
 	u32			rx_buf_size;
-
+	u32			rx_frag_size; /* 0 if kmalloced(), or rx_buf_size + NET_SKB_PAD */
 	dma_addr_t		status_blk_mapping;
 
 	enum bnx2x_tpa_mode_t	mode;
@@ -585,15 +569,9 @@ struct bnx2x_fastpath {
 						->var)
 
 
-#define IS_ETH_FP(fp)			(fp->index < \
-					 BNX2X_NUM_ETH_QUEUES(fp->bp))
-#ifdef BCM_CNIC
-#define IS_FCOE_FP(fp)			(fp->index == FCOE_IDX(fp->bp))
-#define IS_FCOE_IDX(idx)		((idx) == FCOE_IDX(bp))
-#else
-#define IS_FCOE_FP(fp)		false
-#define IS_FCOE_IDX(idx)	false
-#endif
+#define IS_ETH_FP(fp)		((fp)->index < BNX2X_NUM_ETH_QUEUES((fp)->bp))
+#define IS_FCOE_FP(fp)		((fp)->index == FCOE_IDX((fp)->bp))
+#define IS_FCOE_IDX(idx)	((idx) == FCOE_IDX(bp))
 
 
 /* MC hsi */
@@ -886,6 +864,18 @@ struct bnx2x_common {
 					 (CHIP_REV(bp) == CHIP_REV_Bx))
 #define CHIP_IS_E3A0(bp)		(CHIP_IS_E3(bp) && \
 					 (CHIP_REV(bp) == CHIP_REV_Ax))
+/* This define is used in two main places:
+ * 1. In the early stages of nic_load, to know if to configrue Parser / Searcher
+ * to nic-only mode or to offload mode. Offload mode is configured if either the
+ * chip is E1x (where MIC_MODE register is not applicable), or if cnic already
+ * registered for this port (which means that the user wants storage services).
+ * 2. During cnic-related load, to know if offload mode is already configured in
+ * the HW or needs to be configrued.
+ * Since the transition from nic-mode to offload-mode in HW causes traffic
+ * coruption, nic-mode is configured only in ports on which storage services
+ * where never requested.
+ */
+#define CONFIGURE_NIC_MODE(bp)		(!CHIP_IS_E1x(bp) && !CNIC_ENABLED(bp))
 
 	int			flash_size;
 #define BNX2X_NVRAM_1MB_SIZE			0x20000	/* 1M bit in bytes */
@@ -925,6 +915,7 @@ struct bnx2x_common {
 #define BNX2X_IGU_STAS_MSG_VF_CNT 64
 #define BNX2X_IGU_STAS_MSG_PF_CNT 4
 
+#define MAX_IGU_ATTN_ACK_TO       100
 /* end of common */
 
 /* port */
@@ -946,7 +937,6 @@ struct bnx2x_port {
 
 	/* used to synchronize phy accesses */
 	struct mutex		phy_mutex;
-	int			need_hw_lock;
 
 	u32			port_stx;
 
@@ -1003,18 +993,15 @@ union cdu_context {
 #define CDU_ILT_PAGE_SZ		(8192 << CDU_ILT_PAGE_SZ_HW) /* 32K */
 #define ILT_PAGE_CIDS		(CDU_ILT_PAGE_SZ / sizeof(union cdu_context))
 
-#ifdef BCM_CNIC
 #define CNIC_ISCSI_CID_MAX	256
 #define CNIC_FCOE_CID_MAX	2048
 #define CNIC_CID_MAX		(CNIC_ISCSI_CID_MAX + CNIC_FCOE_CID_MAX)
 #define CNIC_ILT_LINES		DIV_ROUND_UP(CNIC_CID_MAX, ILT_PAGE_CIDS)
-#endif
 
 #define QM_ILT_PAGE_SZ_HW	0
 #define QM_ILT_PAGE_SZ		(4096 << QM_ILT_PAGE_SZ_HW) /* 4K */
 #define QM_CID_ROUND		1024
 
-#ifdef BCM_CNIC
 /* TM (timers) host DB constants */
 #define TM_ILT_PAGE_SZ_HW	0
 #define TM_ILT_PAGE_SZ		(4096 << TM_ILT_PAGE_SZ_HW) /* 4K */
@@ -1032,8 +1019,6 @@ union cdu_context {
 #define SRC_T2_SZ		SRC_ILT_SZ
 #define SRC_ILT_LINES		DIV_ROUND_UP(SRC_ILT_SZ, SRC_ILT_PAGE_SZ)
 
-#endif
-
 #define MAX_DMAE_C		8
 
 /* DMA memory not used in fastpath */
@@ -1201,6 +1186,7 @@ struct bnx2x_prev_path_list {
 	u8 slot;
 	u8 path;
 	struct list_head list;
+	u8 undi;
 };
 
 struct bnx2x_sp_objs {
@@ -1227,7 +1213,6 @@ struct bnx2x {
 	struct bnx2x_sp_objs	*sp_objs;
 	struct bnx2x_fp_stats	*fp_stats;
 	struct bnx2x_fp_txdata	*bnx2x_txq;
-	int			bnx2x_txq_size;
 	void __iomem		*regview;
 	void __iomem		*doorbells;
 	u16			db_size;
@@ -1350,6 +1335,16 @@ struct bnx2x {
 #define NO_ISCSI_OOO(bp)	((bp)->flags & NO_ISCSI_OOO_FLAG)
 #define NO_FCOE(bp)		((bp)->flags & NO_FCOE_FLAG)
 
+	u8			cnic_support;
+	bool			cnic_enabled;
+	bool			cnic_loaded;
+	struct cnic_eth_dev	*(*cnic_probe)(struct net_device *);
+
+	/* Flag that indicates that we can start looking for FCoE L2 queue
+	 * completions in the default status block.
+	 */
+	bool			fcoe_init;
+
 	int			pm_cap;
 	int			mrrs;
 
@@ -1420,6 +1415,8 @@ struct bnx2x {
 #define BNX2X_MAX_COS			3
 #define BNX2X_MAX_TX_COS		2
 	int			num_queues;
+	uint			num_ethernet_queues;
+	uint			num_cnic_queues;
 	int			num_napi_queues;
 	int			disable_tpa;
 
@@ -1433,6 +1430,7 @@ struct bnx2x {
 	u8			igu_dsb_id;
 	u8			igu_base_sb;
 	u8			igu_sb_cnt;
+	u8			min_msix_vec_cnt;
 
 	dma_addr_t		def_status_blk_mapping;
 
@@ -1478,26 +1476,23 @@ struct bnx2x {
  * Maximum supported number of RSS queues: number of IGU SBs minus one that goes
  * to CNIC.
  */
-#define BNX2X_MAX_RSS_COUNT(bp)	((bp)->igu_sb_cnt - CNIC_PRESENT)
+#define BNX2X_MAX_RSS_COUNT(bp)	((bp)->igu_sb_cnt - CNIC_SUPPORT(bp))
 
 /*
  * Maximum CID count that might be required by the bnx2x:
  * Max RSS * Max_Tx_Multi_Cos + FCoE + iSCSI
  */
 #define BNX2X_L2_CID_COUNT(bp)	(BNX2X_NUM_ETH_QUEUES(bp) * BNX2X_MULTI_TX_COS \
-				+ NON_ETH_CONTEXT_USE + CNIC_PRESENT)
+				+ 2 * CNIC_SUPPORT(bp))
 #define BNX2X_L2_MAX_CID(bp)	(BNX2X_MAX_RSS_COUNT(bp) * BNX2X_MULTI_TX_COS \
-				+ NON_ETH_CONTEXT_USE + CNIC_PRESENT)
+				+ 2 * CNIC_SUPPORT(bp))
 #define L2_ILT_LINES(bp)	(DIV_ROUND_UP(BNX2X_L2_CID_COUNT(bp),\
 					ILT_PAGE_CIDS))
 
 	int			qm_cid_count;
 
-	int			dropless_fc;
+	bool			dropless_fc;
 
-#ifdef BCM_CNIC
-	u32			cnic_flags;
-#define BNX2X_CNIC_FLAG_MAC_SET		1
 	void			*t2;
 	dma_addr_t		t2_mapping;
 	struct cnic_ops	__rcu	*cnic_ops;
@@ -1518,7 +1513,6 @@ struct bnx2x {
 
 	/* Start index of the "special" (CNIC related) L2 cleints */
 	u8				cnic_base_cl_id;
-#endif
 
 	int			dmae_ready;
 	/* used to synchronize dmae accesses */
@@ -1647,9 +1641,9 @@ struct bnx2x {
 /* Tx queues may be less or equal to Rx queues */
 extern int num_queues;
 #define BNX2X_NUM_QUEUES(bp)	(bp->num_queues)
-#define BNX2X_NUM_ETH_QUEUES(bp) (BNX2X_NUM_QUEUES(bp) - NON_ETH_CONTEXT_USE)
+#define BNX2X_NUM_ETH_QUEUES(bp) ((bp)->num_ethernet_queues)
 #define BNX2X_NUM_NON_CNIC_QUEUES(bp)	(BNX2X_NUM_QUEUES(bp) - \
-					 NON_ETH_CONTEXT_USE)
+					 (bp)->num_cnic_queues)
 #define BNX2X_NUM_RX_QUEUES(bp)	BNX2X_NUM_QUEUES(bp)
 
 #define is_multi(bp)		(BNX2X_NUM_QUEUES(bp) > 1)
@@ -1689,6 +1683,13 @@ struct bnx2x_func_init_params {
 	u16		spq_prod;	/* valid iff FUNC_FLG_SPQ */
 };
 
+#define for_each_cnic_queue(bp, var) \
+	for ((var) = BNX2X_NUM_ETH_QUEUES(bp); (var) < BNX2X_NUM_QUEUES(bp); \
+	     (var)++) \
+		if (skip_queue(bp, var))	\
+			continue;		\
+		else
+
 #define for_each_eth_queue(bp, var) \
 	for ((var) = 0; (var) < BNX2X_NUM_ETH_QUEUES(bp); (var)++)
 
@@ -1702,6 +1703,22 @@ struct bnx2x_func_init_params {
 		else
 
 /* Skip forwarding FP */
+#define for_each_valid_rx_queue(bp, var)			\
+	for ((var) = 0;						\
+	     (var) < (CNIC_LOADED(bp) ? BNX2X_NUM_QUEUES(bp) :	\
+		      BNX2X_NUM_ETH_QUEUES(bp));		\
+	     (var)++)						\
+		if (skip_rx_queue(bp, var))			\
+			continue;				\
+		else
+
+#define for_each_rx_queue_cnic(bp, var) \
+	for ((var) = BNX2X_NUM_ETH_QUEUES(bp); (var) < BNX2X_NUM_QUEUES(bp); \
+	     (var)++) \
+		if (skip_rx_queue(bp, var))	\
+			continue;		\
+		else
+
 #define for_each_rx_queue(bp, var) \
 	for ((var) = 0; (var) < BNX2X_NUM_QUEUES(bp); (var)++) \
 		if (skip_rx_queue(bp, var))	\
@@ -1709,6 +1726,22 @@ struct bnx2x_func_init_params {
 		else
 
 /* Skip OOO FP */
+#define for_each_valid_tx_queue(bp, var)			\
+	for ((var) = 0;						\
+	     (var) < (CNIC_LOADED(bp) ? BNX2X_NUM_QUEUES(bp) :	\
+		      BNX2X_NUM_ETH_QUEUES(bp));		\
+	     (var)++)						\
+		if (skip_tx_queue(bp, var))			\
+			continue;				\
+		else
+
+#define for_each_tx_queue_cnic(bp, var) \
+	for ((var) = BNX2X_NUM_ETH_QUEUES(bp); (var) < BNX2X_NUM_QUEUES(bp); \
+	     (var)++) \
+		if (skip_tx_queue(bp, var))	\
+			continue;		\
+		else
+
 #define for_each_tx_queue(bp, var) \
 	for ((var) = 0; (var) < BNX2X_NUM_QUEUES(bp); (var)++) \
 		if (skip_tx_queue(bp, var))	\
@@ -2179,7 +2212,6 @@ void bnx2x_notify_link_changed(struct bnx2x *bp);
 #define BNX2X_MF_SD_PROTOCOL(bp) \
 	((bp)->mf_config[BP_VN(bp)] & FUNC_MF_CFG_PROTOCOL_MASK)
 
-#ifdef BCM_CNIC
 #define BNX2X_IS_MF_SD_PROTOCOL_ISCSI(bp) \
 	(BNX2X_MF_SD_PROTOCOL(bp) == FUNC_MF_CFG_PROTOCOL_ISCSI)
 
@@ -2196,9 +2228,12 @@ void bnx2x_notify_link_changed(struct bnx2x *bp);
 #define IS_MF_STORAGE_SD(bp) (IS_MF_SD(bp) && \
 				(BNX2X_IS_MF_SD_PROTOCOL_ISCSI(bp) || \
 				 BNX2X_IS_MF_SD_PROTOCOL_FCOE(bp)))
-#else
-#define IS_MF_FCOE_AFEX(bp)	false
-#endif
 
+enum {
+	SWITCH_UPDATE,
+	AFEX_UPDATE,
+};
+
+#define NUM_MACS	8
 
 #endif /* bnx2x.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 4833b6a9031..a2998bea5d4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -552,6 +552,23 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 	return 0;
 }
 
+static void bnx2x_frag_free(const struct bnx2x_fastpath *fp, void *data)
+{
+	if (fp->rx_frag_size)
+		put_page(virt_to_head_page(data));
+	else
+		kfree(data);
+}
+
+static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp)
+{
+	if (fp->rx_frag_size)
+		return netdev_alloc_frag(fp->rx_frag_size);
+
+	return kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
+}
+
+
 static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 			   struct bnx2x_agg_info *tpa_info,
 			   u16 pages,
@@ -574,15 +591,14 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 		goto drop;
 
 	/* Try to allocate the new data */
-	new_data = kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
-
+	new_data = bnx2x_frag_alloc(fp);
 	/* Unmap skb in the pool anyway, as we are going to change
 	   pool entry status to BNX2X_TPA_STOP even if new skb allocation
 	   fails. */
 	dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping),
 			 fp->rx_buf_size, DMA_FROM_DEVICE);
 	if (likely(new_data))
-		skb = build_skb(data, 0);
+		skb = build_skb(data, fp->rx_frag_size);
 
 	if (likely(skb)) {
 #ifdef BNX2X_STOP_ON_ERROR
@@ -619,7 +635,7 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 
 		return;
 	}
-	kfree(new_data);
+	bnx2x_frag_free(fp, new_data);
 drop:
 	/* drop the packet and keep the buffer in the bin */
 	DP(NETIF_MSG_RX_STATUS,
@@ -635,7 +651,7 @@ static int bnx2x_alloc_rx_data(struct bnx2x *bp,
 	struct eth_rx_bd *rx_bd = &fp->rx_desc_ring[index];
 	dma_addr_t mapping;
 
-	data = kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
+	data = bnx2x_frag_alloc(fp);
 	if (unlikely(data == NULL))
 		return -ENOMEM;
 
@@ -643,7 +659,7 @@ static int bnx2x_alloc_rx_data(struct bnx2x *bp,
 				 fp->rx_buf_size,
 				 DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
-		kfree(data);
+		bnx2x_frag_free(fp, data);
 		BNX2X_ERR("Can't map rx data\n");
 		return -ENOMEM;
 	}
@@ -845,9 +861,9 @@ int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 						 dma_unmap_addr(rx_buf, mapping),
 						 fp->rx_buf_size,
 						 DMA_FROM_DEVICE);
-				skb = build_skb(data, 0);
+				skb = build_skb(data, fp->rx_frag_size);
 				if (unlikely(!skb)) {
-					kfree(data);
+					bnx2x_frag_free(fp, data);
 					bnx2x_fp_qstats(bp, fp)->
 							rx_skb_alloc_failed++;
 					goto next_rx;
@@ -948,14 +964,12 @@ void bnx2x_acquire_phy_lock(struct bnx2x *bp)
 {
 	mutex_lock(&bp->port.phy_mutex);
 
-	if (bp->port.need_hw_lock)
-		bnx2x_acquire_hw_lock(bp, HW_LOCK_RESOURCE_MDIO);
+	bnx2x_acquire_hw_lock(bp, HW_LOCK_RESOURCE_MDIO);
 }
 
 void bnx2x_release_phy_lock(struct bnx2x *bp)
 {
-	if (bp->port.need_hw_lock)
-		bnx2x_release_hw_lock(bp, HW_LOCK_RESOURCE_MDIO);
+	bnx2x_release_hw_lock(bp, HW_LOCK_RESOURCE_MDIO);
 
 	mutex_unlock(&bp->port.phy_mutex);
 }
@@ -1147,11 +1161,30 @@ static void bnx2x_free_tpa_pool(struct bnx2x *bp,
 			dma_unmap_single(&bp->pdev->dev,
 					 dma_unmap_addr(first_buf, mapping),
 					 fp->rx_buf_size, DMA_FROM_DEVICE);
-		kfree(data);
+		bnx2x_frag_free(fp, data);
 		first_buf->data = NULL;
 	}
 }
 
+void bnx2x_init_rx_rings_cnic(struct bnx2x *bp)
+{
+	int j;
+
+	for_each_rx_queue_cnic(bp, j) {
+		struct bnx2x_fastpath *fp = &bp->fp[j];
+
+		fp->rx_bd_cons = 0;
+
+		/* Activate BD ring */
+		/* Warning!
+		 * this will generate an interrupt (to the TSTORM)
+		 * must only be done after chip is initialized
+		 */
+		bnx2x_update_rx_prod(bp, fp, fp->rx_bd_prod, fp->rx_comp_prod,
+				     fp->rx_sge_prod);
+	}
+}
+
 void bnx2x_init_rx_rings(struct bnx2x *bp)
 {
 	int func = BP_FUNC(bp);
@@ -1159,7 +1192,7 @@ void bnx2x_init_rx_rings(struct bnx2x *bp)
 	int i, j;
 
 	/* Allocate TPA resources */
-	for_each_rx_queue(bp, j) {
+	for_each_eth_queue(bp, j) {
 		struct bnx2x_fastpath *fp = &bp->fp[j];
 
 		DP(NETIF_MSG_IFUP,
@@ -1173,8 +1206,7 @@ void bnx2x_init_rx_rings(struct bnx2x *bp)
 				struct sw_rx_bd *first_buf =
 					&tpa_info->first_buf;
 
-				first_buf->data = kmalloc(fp->rx_buf_size + NET_SKB_PAD,
-							  GFP_ATOMIC);
+				first_buf->data = bnx2x_frag_alloc(fp);
 				if (!first_buf->data) {
 					BNX2X_ERR("Failed to allocate TPA skb pool for queue[%d] - disabling TPA on this queue!\n",
 						  j);
@@ -1217,7 +1249,7 @@ void bnx2x_init_rx_rings(struct bnx2x *bp)
 		}
 	}
 
-	for_each_rx_queue(bp, j) {
+	for_each_eth_queue(bp, j) {
 		struct bnx2x_fastpath *fp = &bp->fp[j];
 
 		fp->rx_bd_cons = 0;
@@ -1244,29 +1276,45 @@ void bnx2x_init_rx_rings(struct bnx2x *bp)
 	}
 }
 
-static void bnx2x_free_tx_skbs(struct bnx2x *bp)
+static void bnx2x_free_tx_skbs_queue(struct bnx2x_fastpath *fp)
 {
-	int i;
 	u8 cos;
+	struct bnx2x *bp = fp->bp;
 
-	for_each_tx_queue(bp, i) {
-		struct bnx2x_fastpath *fp = &bp->fp[i];
-		for_each_cos_in_tx_queue(fp, cos) {
-			struct bnx2x_fp_txdata *txdata = fp->txdata_ptr[cos];
-			unsigned pkts_compl = 0, bytes_compl = 0;
+	for_each_cos_in_tx_queue(fp, cos) {
+		struct bnx2x_fp_txdata *txdata = fp->txdata_ptr[cos];
+		unsigned pkts_compl = 0, bytes_compl = 0;
 
-			u16 sw_prod = txdata->tx_pkt_prod;
-			u16 sw_cons = txdata->tx_pkt_cons;
+		u16 sw_prod = txdata->tx_pkt_prod;
+		u16 sw_cons = txdata->tx_pkt_cons;
 
-			while (sw_cons != sw_prod) {
-				bnx2x_free_tx_pkt(bp, txdata, TX_BD(sw_cons),
-				    &pkts_compl, &bytes_compl);
-				sw_cons++;
-			}
-			netdev_tx_reset_queue(
-				netdev_get_tx_queue(bp->dev,
-						    txdata->txq_index));
+		while (sw_cons != sw_prod) {
+			bnx2x_free_tx_pkt(bp, txdata, TX_BD(sw_cons),
+					  &pkts_compl, &bytes_compl);
+			sw_cons++;
 		}
+
+		netdev_tx_reset_queue(
+			netdev_get_tx_queue(bp->dev,
+					    txdata->txq_index));
+	}
+}
+
+static void bnx2x_free_tx_skbs_cnic(struct bnx2x *bp)
+{
+	int i;
+
+	for_each_tx_queue_cnic(bp, i) {
+		bnx2x_free_tx_skbs_queue(&bp->fp[i]);
+	}
+}
+
+static void bnx2x_free_tx_skbs(struct bnx2x *bp)
+{
+	int i;
+
+	for_each_eth_queue(bp, i) {
+		bnx2x_free_tx_skbs_queue(&bp->fp[i]);
 	}
 }
 
@@ -1290,7 +1338,16 @@ static void bnx2x_free_rx_bds(struct bnx2x_fastpath *fp)
 				 fp->rx_buf_size, DMA_FROM_DEVICE);
 
 		rx_buf->data = NULL;
-		kfree(data);
+		bnx2x_frag_free(fp, data);
+	}
+}
+
+static void bnx2x_free_rx_skbs_cnic(struct bnx2x *bp)
+{
+	int j;
+
+	for_each_rx_queue_cnic(bp, j) {
+		bnx2x_free_rx_bds(&bp->fp[j]);
 	}
 }
 
@@ -1298,7 +1355,7 @@ static void bnx2x_free_rx_skbs(struct bnx2x *bp)
 {
 	int j;
 
-	for_each_rx_queue(bp, j) {
+	for_each_eth_queue(bp, j) {
 		struct bnx2x_fastpath *fp = &bp->fp[j];
 
 		bnx2x_free_rx_bds(fp);
@@ -1308,6 +1365,12 @@ static void bnx2x_free_rx_skbs(struct bnx2x *bp)
 	}
 }
 
+void bnx2x_free_skbs_cnic(struct bnx2x *bp)
+{
+	bnx2x_free_tx_skbs_cnic(bp);
+	bnx2x_free_rx_skbs_cnic(bp);
+}
+
 void bnx2x_free_skbs(struct bnx2x *bp)
 {
 	bnx2x_free_tx_skbs(bp);
@@ -1347,11 +1410,12 @@ static void bnx2x_free_msix_irqs(struct bnx2x *bp, int nvecs)
 	DP(NETIF_MSG_IFDOWN, "released sp irq (%d)\n",
 	   bp->msix_table[offset].vector);
 	offset++;
-#ifdef BCM_CNIC
-	if (nvecs == offset)
-		return;
-	offset++;
-#endif
+
+	if (CNIC_SUPPORT(bp)) {
+		if (nvecs == offset)
+			return;
+		offset++;
+	}
 
 	for_each_eth_queue(bp, i) {
 		if (nvecs == offset)
@@ -1368,7 +1432,7 @@ void bnx2x_free_irq(struct bnx2x *bp)
 	if (bp->flags & USING_MSIX_FLAG &&
 	    !(bp->flags & USING_SINGLE_MSIX_FLAG))
 		bnx2x_free_msix_irqs(bp, BNX2X_NUM_ETH_QUEUES(bp) +
-				     CNIC_PRESENT + 1);
+				     CNIC_SUPPORT(bp) + 1);
 	else
 		free_irq(bp->dev->irq, bp->dev);
 }
@@ -1382,12 +1446,14 @@ int bnx2x_enable_msix(struct bnx2x *bp)
 	   bp->msix_table[0].entry);
 	msix_vec++;
 
-#ifdef BCM_CNIC
-	bp->msix_table[msix_vec].entry = msix_vec;
-	BNX2X_DEV_INFO("msix_table[%d].entry = %d (CNIC)\n",
-	   bp->msix_table[msix_vec].entry, bp->msix_table[msix_vec].entry);
-	msix_vec++;
-#endif
+	/* Cnic requires an msix vector for itself */
+	if (CNIC_SUPPORT(bp)) {
+		bp->msix_table[msix_vec].entry = msix_vec;
+		BNX2X_DEV_INFO("msix_table[%d].entry = %d (CNIC)\n",
+			       msix_vec, bp->msix_table[msix_vec].entry);
+		msix_vec++;
+	}
+
 	/* We need separate vectors for ETH queues only (not FCoE) */
 	for_each_eth_queue(bp, i) {
 		bp->msix_table[msix_vec].entry = msix_vec;
@@ -1396,7 +1462,7 @@ int bnx2x_enable_msix(struct bnx2x *bp)
 		msix_vec++;
 	}
 
-	req_cnt = BNX2X_NUM_ETH_QUEUES(bp) + CNIC_PRESENT + 1;
+	req_cnt = BNX2X_NUM_ETH_QUEUES(bp) + CNIC_SUPPORT(bp) + 1;
 
 	rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], req_cnt);
 
@@ -1404,7 +1470,7 @@ int bnx2x_enable_msix(struct bnx2x *bp)
 	 * reconfigure number of tx/rx queues according to available
 	 * MSI-X vectors
 	 */
-	if (rc >= BNX2X_MIN_MSIX_VEC_CNT) {
+	if (rc >= BNX2X_MIN_MSIX_VEC_CNT(bp)) {
 		/* how less vectors we will have? */
 		int diff = req_cnt - rc;
 
@@ -1419,7 +1485,8 @@ int bnx2x_enable_msix(struct bnx2x *bp)
 		/*
 		 * decrease number of queues by number of unallocated entries
 		 */
-		bp->num_queues -= diff;
+		bp->num_ethernet_queues -= diff;
+		bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
 
 		BNX2X_DEV_INFO("New queue configuration set: %d\n",
 			       bp->num_queues);
@@ -1435,6 +1502,9 @@ int bnx2x_enable_msix(struct bnx2x *bp)
 		BNX2X_DEV_INFO("Using single MSI-X vector\n");
 		bp->flags |= USING_SINGLE_MSIX_FLAG;
 
+		BNX2X_DEV_INFO("set number of queues to 1\n");
+		bp->num_ethernet_queues = 1;
+		bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
 	} else if (rc < 0) {
 		BNX2X_DEV_INFO("MSI-X is not attainable  rc %d\n", rc);
 		goto no_msix;
@@ -1464,9 +1534,9 @@ static int bnx2x_req_msix_irqs(struct bnx2x *bp)
 		return -EBUSY;
 	}
 
-#ifdef BCM_CNIC
-	offset++;
-#endif
+	if (CNIC_SUPPORT(bp))
+		offset++;
+
 	for_each_eth_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
@@ -1485,7 +1555,7 @@ static int bnx2x_req_msix_irqs(struct bnx2x *bp)
 	}
 
 	i = BNX2X_NUM_ETH_QUEUES(bp);
-	offset = 1 + CNIC_PRESENT;
+	offset = 1 + CNIC_SUPPORT(bp);
 	netdev_info(bp->dev, "using MSI-X  IRQs: sp %d  fp[%d] %d ... fp[%d] %d\n",
 	       bp->msix_table[0].vector,
 	       0, bp->msix_table[offset].vector,
@@ -1556,19 +1626,35 @@ static int bnx2x_setup_irqs(struct bnx2x *bp)
 	return 0;
 }
 
+static void bnx2x_napi_enable_cnic(struct bnx2x *bp)
+{
+	int i;
+
+	for_each_rx_queue_cnic(bp, i)
+		napi_enable(&bnx2x_fp(bp, i, napi));
+}
+
 static void bnx2x_napi_enable(struct bnx2x *bp)
 {
 	int i;
 
-	for_each_rx_queue(bp, i)
+	for_each_eth_queue(bp, i)
 		napi_enable(&bnx2x_fp(bp, i, napi));
 }
 
+static void bnx2x_napi_disable_cnic(struct bnx2x *bp)
+{
+	int i;
+
+	for_each_rx_queue_cnic(bp, i)
+		napi_disable(&bnx2x_fp(bp, i, napi));
+}
+
 static void bnx2x_napi_disable(struct bnx2x *bp)
 {
 	int i;
 
-	for_each_rx_queue(bp, i)
+	for_each_eth_queue(bp, i)
 		napi_disable(&bnx2x_fp(bp, i, napi));
 }
 
@@ -1576,6 +1662,8 @@ void bnx2x_netif_start(struct bnx2x *bp)
 {
 	if (netif_running(bp->dev)) {
 		bnx2x_napi_enable(bp);
+		if (CNIC_LOADED(bp))
+			bnx2x_napi_enable_cnic(bp);
 		bnx2x_int_enable(bp);
 		if (bp->state == BNX2X_STATE_OPEN)
 			netif_tx_wake_all_queues(bp->dev);
@@ -1586,14 +1674,15 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 {
 	bnx2x_int_disable_sync(bp, disable_hw);
 	bnx2x_napi_disable(bp);
+	if (CNIC_LOADED(bp))
+		bnx2x_napi_disable_cnic(bp);
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
-#ifdef BCM_CNIC
-	if (!NO_FCOE(bp)) {
+	if (CNIC_LOADED(bp) && !NO_FCOE(bp)) {
 		struct ethhdr *hdr = (struct ethhdr *)skb->data;
 		u16 ether_type = ntohs(hdr->h_proto);
 
@@ -1609,7 +1698,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
 		if ((ether_type == ETH_P_FCOE) || (ether_type == ETH_P_FIP))
 			return bnx2x_fcoe_tx(bp, txq_index);
 	}
-#endif
+
 	/* select a non-FCoE queue */
 	return __skb_tx_hash(dev, skb, BNX2X_NUM_ETH_QUEUES(bp));
 }
@@ -1618,15 +1707,15 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
 void bnx2x_set_num_queues(struct bnx2x *bp)
 {
 	/* RSS queues */
-	bp->num_queues = bnx2x_calc_num_queues(bp);
+	bp->num_ethernet_queues = bnx2x_calc_num_queues(bp);
 
-#ifdef BCM_CNIC
 	/* override in STORAGE SD modes */
 	if (IS_MF_STORAGE_SD(bp) || IS_MF_FCOE_AFEX(bp))
-		bp->num_queues = 1;
-#endif
+		bp->num_ethernet_queues = 1;
+
 	/* Add special queues */
-	bp->num_queues += NON_ETH_CONTEXT_USE;
+	bp->num_cnic_queues = CNIC_SUPPORT(bp); /* For FCOE */
+	bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
 
 	BNX2X_DEV_INFO("set number of queues to %d\n", bp->num_queues);
 }
@@ -1653,20 +1742,18 @@ void bnx2x_set_num_queues(struct bnx2x *bp)
  * bnx2x_setup_tc() takes care of the proper TC mappings so that __skb_tx_hash()
  * will return a proper Tx index if TC is enabled (netdev->num_tc > 0).
  */
-static int bnx2x_set_real_num_queues(struct bnx2x *bp)
+static int bnx2x_set_real_num_queues(struct bnx2x *bp, int include_cnic)
 {
 	int rc, tx, rx;
 
 	tx = BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos;
-	rx = BNX2X_NUM_QUEUES(bp) - NON_ETH_CONTEXT_USE;
+	rx = BNX2X_NUM_ETH_QUEUES(bp);
 
 /* account for fcoe queue */
-#ifdef BCM_CNIC
-	if (!NO_FCOE(bp)) {
-		rx += FCOE_PRESENT;
-		tx += FCOE_PRESENT;
+	if (include_cnic && !NO_FCOE(bp)) {
+		rx++;
+		tx++;
 	}
-#endif
 
 	rc = netif_set_real_num_tx_queues(bp->dev, tx);
 	if (rc) {
@@ -1710,6 +1797,10 @@ static void bnx2x_set_rx_buf_size(struct bnx2x *bp)
 				  mtu +
 				  BNX2X_FW_RX_ALIGN_END;
 		/* Note : rx_buf_size doesnt take into account NET_SKB_PAD */
+		if (fp->rx_buf_size + NET_SKB_PAD <= PAGE_SIZE)
+			fp->rx_frag_size = fp->rx_buf_size + NET_SKB_PAD;
+		else
+			fp->rx_frag_size = 0;
 	}
 }
 
@@ -1859,14 +1950,26 @@ static void bnx2x_squeeze_objects(struct bnx2x *bp)
 		(bp)->state = BNX2X_STATE_ERROR; \
 		goto label; \
 	} while (0)
-#else
+
+#define LOAD_ERROR_EXIT_CNIC(bp, label) \
+	do { \
+		bp->cnic_loaded = false; \
+		goto label; \
+	} while (0)
+#else /*BNX2X_STOP_ON_ERROR*/
 #define LOAD_ERROR_EXIT(bp, label) \
 	do { \
 		(bp)->state = BNX2X_STATE_ERROR; \
 		(bp)->panic = 1; \
 		return -EBUSY; \
 	} while (0)
-#endif
+#define LOAD_ERROR_EXIT_CNIC(bp, label) \
+	do { \
+		bp->cnic_loaded = false; \
+		(bp)->panic = 1; \
+		return -EBUSY; \
+	} while (0)
+#endif /*BNX2X_STOP_ON_ERROR*/
 
 bool bnx2x_test_firmware_version(struct bnx2x *bp, bool is_err)
 {
@@ -1959,10 +2062,8 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index)
 		fp->max_cos = 1;
 
 	/* Init txdata pointers */
-#ifdef BCM_CNIC
 	if (IS_FCOE_FP(fp))
 		fp->txdata_ptr[0] = &bp->bnx2x_txq[FCOE_TXQ_IDX(bp)];
-#endif
 	if (IS_ETH_FP(fp))
 		for_each_cos_in_tx_queue(fp, cos)
 			fp->txdata_ptr[cos] = &bp->bnx2x_txq[cos *
@@ -1980,11 +2081,95 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index)
 	else if (bp->flags & GRO_ENABLE_FLAG)
 		fp->mode = TPA_MODE_GRO;
 
-#ifdef BCM_CNIC
 	/* We don't want TPA on an FCoE L2 ring */
 	if (IS_FCOE_FP(fp))
 		fp->disable_tpa = 1;
-#endif
+}
+
+int bnx2x_load_cnic(struct bnx2x *bp)
+{
+	int i, rc, port = BP_PORT(bp);
+
+	DP(NETIF_MSG_IFUP, "Starting CNIC-related load\n");
+
+	mutex_init(&bp->cnic_mutex);
+
+	rc = bnx2x_alloc_mem_cnic(bp);
+	if (rc) {
+		BNX2X_ERR("Unable to allocate bp memory for cnic\n");
+		LOAD_ERROR_EXIT_CNIC(bp, load_error_cnic0);
+	}
+
+	rc = bnx2x_alloc_fp_mem_cnic(bp);
+	if (rc) {
+		BNX2X_ERR("Unable to allocate memory for cnic fps\n");
+		LOAD_ERROR_EXIT_CNIC(bp, load_error_cnic0);
+	}
+
+	/* Update the number of queues with the cnic queues */
+	rc = bnx2x_set_real_num_queues(bp, 1);
+	if (rc) {
+		BNX2X_ERR("Unable to set real_num_queues including cnic\n");
+		LOAD_ERROR_EXIT_CNIC(bp, load_error_cnic0);
+	}
+
+	/* Add all CNIC NAPI objects */
+	bnx2x_add_all_napi_cnic(bp);
+	DP(NETIF_MSG_IFUP, "cnic napi added\n");
+	bnx2x_napi_enable_cnic(bp);
+
+	rc = bnx2x_init_hw_func_cnic(bp);
+	if (rc)
+		LOAD_ERROR_EXIT_CNIC(bp, load_error_cnic1);
+
+	bnx2x_nic_init_cnic(bp);
+
+	/* Enable Timer scan */