Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1436 commits)
  cassini: Use local-mac-address prom property for Cassini MAC address
  net: remove the duplicate #ifdef __KERNEL__
  net: bridge: check the length of skb after nf_bridge_maybe_copy_header()
  netconsole: clarify stopping message
  netconsole: don't announce stopping if nothing happened
  cnic: Fix the type field in SPQ messages
  netfilter: fix export secctx error handling
  netfilter: fix the race when initializing nf_ct_expect_hash_rnd
  ipv4: IP defragmentation must be ECN aware
  net: r6040: Return proper error for r6040_init_one
  dcb: use after free in dcb_flushapp()
  dcb: unlock on error in dcbnl_ieee_get()
  net: ixp4xx_eth: Return proper error for eth_init_one
  include/linux/if_ether.h: Add #define ETH_P_LINK_CTL for HPNA and wlan local tunnel
  net: add POLLPRI to sock_def_readable()
  af_unix: Avoid socket->sk NULL OOPS in stream connect security hooks.
  net_sched: pfifo_head_drop problem
  mac80211: remove stray extern
  mac80211: implement off-channel TX using hw r-o-c offload
  mac80211: implement hardware offload for remain-on-channel
  ...

1 files changed, 15 insertions, 7 deletions

diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
index 17022258ed68..311471b439a8 100644
--- a/drivers/net/cxgb4/sge.c
+++ b/drivers/net/cxgb4/sge.c
@@ -579,6 +579,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
  *	@phys: the physical address of the allocated ring
  *	@metadata: address of the array holding the SW state for the ring
  *	@stat_size: extra space in HW ring for status information
+ *	@node: preferred node for memory allocations
  *
  *	Allocates resources for an SGE descriptor ring, such as Tx queues,
  *	free buffer lists, or response queues.  Each SGE ring requires
@@ -590,7 +591,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
  */
 static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 			size_t sw_size, dma_addr_t *phys, void *metadata,
-			size_t stat_size)
+			size_t stat_size, int node)
 {
 	size_t len = nelem * elem_size + stat_size;
 	void *s = NULL;
@@ -599,7 +600,7 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 	if (!p)
 		return NULL;
 	if (sw_size) {
-		s = kcalloc(nelem, sw_size, GFP_KERNEL);
+		s = kzalloc_node(nelem * sw_size, GFP_KERNEL, node);
 
 		if (!s) {
 			dma_free_coherent(dev, len, p, *phys);
@@ -1982,7 +1983,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	iq->size = roundup(iq->size, 16);
 
 	iq->desc = alloc_ring(adap->pdev_dev, iq->size, iq->iqe_len, 0,
-			      &iq->phys_addr, NULL, 0);
+			      &iq->phys_addr, NULL, 0, NUMA_NO_NODE);
 	if (!iq->desc)
 		return -ENOMEM;
 
@@ -2008,12 +2009,14 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		fl->size = roundup(fl->size, 8);
 		fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64),
 				      sizeof(struct rx_sw_desc), &fl->addr,
-				      &fl->sdesc, STAT_LEN);
+				      &fl->sdesc, STAT_LEN, NUMA_NO_NODE);
 		if (!fl->desc)
 			goto fl_nomem;
 
 		flsz = fl->size / 8 + STAT_LEN / sizeof(struct tx_desc);
 		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_FL0PACKEN |
+					    FW_IQ_CMD_FL0FETCHRO(1) |
+					    FW_IQ_CMD_FL0DATARO(1) |
 					    FW_IQ_CMD_FL0PADEN);
 		c.fl0dcaen_to_fl0cidxfthresh = htons(FW_IQ_CMD_FL0FBMIN(2) |
 				FW_IQ_CMD_FL0FBMAX(3));
@@ -2093,7 +2096,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN);
+			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			netdev_queue_numa_node_read(netdevq));
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2106,6 +2110,7 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	c.viid_pkd = htonl(FW_EQ_ETH_CMD_VIID(pi->viid));
 	c.fetchszm_to_iqid = htonl(FW_EQ_ETH_CMD_HOSTFCMODE(2) |
 				   FW_EQ_ETH_CMD_PCIECHN(pi->tx_chan) |
+				   FW_EQ_ETH_CMD_FETCHRO(1) |
 				   FW_EQ_ETH_CMD_IQID(iqid));
 	c.dcaen_to_eqsize = htonl(FW_EQ_ETH_CMD_FBMIN(2) |
 				  FW_EQ_ETH_CMD_FBMAX(3) |
@@ -2144,7 +2149,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, nentries,
 				 sizeof(struct tx_desc), 0, &txq->q.phys_addr,
-				 NULL, 0);
+				 NULL, 0, NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2158,6 +2163,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 	c.physeqid_pkd = htonl(0);
 	c.fetchszm_to_iqid = htonl(FW_EQ_CTRL_CMD_HOSTFCMODE(2) |
 				   FW_EQ_CTRL_CMD_PCIECHN(pi->tx_chan) |
+				   FW_EQ_CTRL_CMD_FETCHRO |
 				   FW_EQ_CTRL_CMD_IQID(iqid));
 	c.dcaen_to_eqsize = htonl(FW_EQ_CTRL_CMD_FBMIN(2) |
 				  FW_EQ_CTRL_CMD_FBMAX(3) |
@@ -2194,7 +2200,8 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN);
+			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2207,6 +2214,7 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 				 FW_EQ_OFLD_CMD_EQSTART | FW_LEN16(c));
 	c.fetchszm_to_iqid = htonl(FW_EQ_OFLD_CMD_HOSTFCMODE(2) |
 				   FW_EQ_OFLD_CMD_PCIECHN(pi->tx_chan) |
+				   FW_EQ_OFLD_CMD_FETCHRO(1) |
 				   FW_EQ_OFLD_CMD_IQID(iqid));
 	c.dcaen_to_eqsize = htonl(FW_EQ_OFLD_CMD_FBMIN(2) |
 				  FW_EQ_OFLD_CMD_FBMAX(3) |