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

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (166 commits)
  Revert "ax25: zero length frame filtering in AX25"
  Revert "netrom: zero length frame filtering in NetRom"
  cfg80211: default CONFIG_WIRELESS_OLD_REGULATORY to n
  mac80211/iwlwifi: move virtual A-MDPU queue bookkeeping to iwlwifi
  mac80211: fix aggregation to not require queue stop
  mac80211: add skb length sanity checking
  mac80211: unify and fix TX aggregation start
  mac80211: clean up __ieee80211_tx args
  mac80211: rework the pending packets code
  mac80211: fix A-MPDU queue assignment
  mac80211: rewrite fragmentation
  iwlwifi: show current driver status in user readable format
  b43: Add BCM4307 PCI-ID
  cfg80211: fix locking in nl80211_set_wiphy
  mac80211: fix RX path
  ath5k: properly drop packets from ops->tx
  ar9170: single module build
  ath9k: fix dma mapping leak of rx buffer upon rmmod
  rt2x00: New USB ID for rt73usb
  ath5k: warn and correct rate for unknown hw rate indexes
  ...

1 files changed, 125 insertions, 39 deletions

diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index a7555cb3fa4..26d3587f339 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -50,6 +50,7 @@
 #define SGE_RX_COPY_THRES  256
 #define SGE_RX_PULL_LEN    128
 
+#define SGE_PG_RSVD SMP_CACHE_BYTES
 /*
  * Page chunk size for FL0 buffers if FL0 is to be populated with page chunks.
  * It must be a divisor of PAGE_SIZE.  If set to 0 FL0 will use sk_buffs
@@ -57,8 +58,10 @@
  */
 #define FL0_PG_CHUNK_SIZE  2048
 #define FL0_PG_ORDER 0
+#define FL0_PG_ALLOC_SIZE (PAGE_SIZE << FL0_PG_ORDER)
 #define FL1_PG_CHUNK_SIZE (PAGE_SIZE > 8192 ? 16384 : 8192)
 #define FL1_PG_ORDER (PAGE_SIZE > 8192 ? 0 : 1)
+#define FL1_PG_ALLOC_SIZE (PAGE_SIZE << FL1_PG_ORDER)
 
 #define SGE_RX_DROP_THRES 16
 #define RX_RECLAIM_PERIOD (HZ/4)
@@ -345,13 +348,21 @@ static inline int should_restart_tx(const struct sge_txq *q)
 	return q->in_use - r < (q->size >> 1);
 }
 
-static void clear_rx_desc(const struct sge_fl *q, struct rx_sw_desc *d)
+static void clear_rx_desc(struct pci_dev *pdev, const struct sge_fl *q,
+			  struct rx_sw_desc *d)
 {
-	if (q->use_pages) {
-		if (d->pg_chunk.page)
-			put_page(d->pg_chunk.page);
+	if (q->use_pages && d->pg_chunk.page) {
+		(*d->pg_chunk.p_cnt)--;
+		if (!*d->pg_chunk.p_cnt)
+			pci_unmap_page(pdev,
+				       pci_unmap_addr(&d->pg_chunk, mapping),
+				       q->alloc_size, PCI_DMA_FROMDEVICE);
+
+		put_page(d->pg_chunk.page);
 		d->pg_chunk.page = NULL;
 	} else {
+		pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr),
+				 q->buf_size, PCI_DMA_FROMDEVICE);
 		kfree_skb(d->skb);
 		d->skb = NULL;
 	}
@@ -372,9 +383,8 @@ static void free_rx_bufs(struct pci_dev *pdev, struct sge_fl *q)
 	while (q->credits--) {
 		struct rx_sw_desc *d = &q->sdesc[cidx];
 
-		pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr),
-				 q->buf_size, PCI_DMA_FROMDEVICE);
-		clear_rx_desc(q, d);
+
+		clear_rx_desc(pdev, q, d);
 		if (++cidx == q->size)
 			cidx = 0;
 	}
@@ -417,18 +427,39 @@ static inline int add_one_rx_buf(void *va, unsigned int len,
 	return 0;
 }
 
-static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp,
+static inline int add_one_rx_chunk(dma_addr_t mapping, struct rx_desc *d,
+				   unsigned int gen)
+{
+	d->addr_lo = cpu_to_be32(mapping);
+	d->addr_hi = cpu_to_be32((u64) mapping >> 32);
+	wmb();
+	d->len_gen = cpu_to_be32(V_FLD_GEN1(gen));
+	d->gen2 = cpu_to_be32(V_FLD_GEN2(gen));
+	return 0;
+}
+
+static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q,
+			  struct rx_sw_desc *sd, gfp_t gfp,
 			  unsigned int order)
 {
 	if (!q->pg_chunk.page) {
+		dma_addr_t mapping;
+
 		q->pg_chunk.page = alloc_pages(gfp, order);
 		if (unlikely(!q->pg_chunk.page))
 			return -ENOMEM;
 		q->pg_chunk.va = page_address(q->pg_chunk.page);
+		q->pg_chunk.p_cnt = q->pg_chunk.va + (PAGE_SIZE << order) -
+				    SGE_PG_RSVD;
 		q->pg_chunk.offset = 0;
+		mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
+				       0, q->alloc_size, PCI_DMA_FROMDEVICE);
+		pci_unmap_addr_set(&q->pg_chunk, mapping, mapping);
 	}
 	sd->pg_chunk = q->pg_chunk;
 
+	prefetch(sd->pg_chunk.p_cnt);
+
 	q->pg_chunk.offset += q->buf_size;
 	if (q->pg_chunk.offset == (PAGE_SIZE << order))
 		q->pg_chunk.page = NULL;
@@ -436,6 +467,12 @@ static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp,
 		q->pg_chunk.va += q->buf_size;
 		get_page(q->pg_chunk.page);
 	}
+
+	if (sd->pg_chunk.offset == 0)
+		*sd->pg_chunk.p_cnt = 1;
+	else
+		*sd->pg_chunk.p_cnt += 1;
+
 	return 0;
 }
 
@@ -460,35 +497,43 @@ static inline void ring_fl_db(struct adapter *adap, struct sge_fl *q)
  */
 static int refill_fl(struct adapter *adap, struct sge_fl *q, int n, gfp_t gfp)
 {
-	void *buf_start;
 	struct rx_sw_desc *sd = &q->sdesc[q->pidx];
 	struct rx_desc *d = &q->desc[q->pidx];
 	unsigned int count = 0;
 
 	while (n--) {
+		dma_addr_t mapping;
 		int err;
 
 		if (q->use_pages) {
-			if (unlikely(alloc_pg_chunk(q, sd, gfp, q->order))) {
+			if (unlikely(alloc_pg_chunk(adap, q, sd, gfp,
+						    q->order))) {
 nomem:				q->alloc_failed++;
 				break;
 			}
-			buf_start = sd->pg_chunk.va;
+			mapping = pci_unmap_addr(&sd->pg_chunk, mapping) +
+						 sd->pg_chunk.offset;
+			pci_unmap_addr_set(sd, dma_addr, mapping);
+
+			add_one_rx_chunk(mapping, d, q->gen);
+			pci_dma_sync_single_for_device(adap->pdev, mapping,
+						q->buf_size - SGE_PG_RSVD,
+						PCI_DMA_FROMDEVICE);
 		} else {
-			struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
+			void *buf_start;
 
+			struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
 			if (!skb)
 				goto nomem;
 
 			sd->skb = skb;
 			buf_start = skb->data;
-		}
-
-		err = add_one_rx_buf(buf_start, q->buf_size, d, sd, q->gen,
-				     adap->pdev);
-		if (unlikely(err)) {
-			clear_rx_desc(q, sd);
-			break;
+			err = add_one_rx_buf(buf_start, q->buf_size, d, sd,
+					     q->gen, adap->pdev);
+			if (unlikely(err)) {
+				clear_rx_desc(adap->pdev, q, sd);
+				break;
+			}
 		}
 
 		d++;
@@ -795,19 +840,19 @@ static struct sk_buff *get_packet_pg(struct adapter *adap, struct sge_fl *fl,
 	struct sk_buff *newskb, *skb;
 	struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
 
-	newskb = skb = q->pg_skb;
+	dma_addr_t dma_addr = pci_unmap_addr(sd, dma_addr);
 
+	newskb = skb = q->pg_skb;
 	if (!skb && (len <= SGE_RX_COPY_THRES)) {
 		newskb = alloc_skb(len, GFP_ATOMIC);
 		if (likely(newskb != NULL)) {
 			__skb_put(newskb, len);
-			pci_dma_sync_single_for_cpu(adap->pdev,
-					    pci_unmap_addr(sd, dma_addr), len,
+			pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len,
 					    PCI_DMA_FROMDEVICE);
 			memcpy(newskb->data, sd->pg_chunk.va, len);
-			pci_dma_sync_single_for_device(adap->pdev,
-					    pci_unmap_addr(sd, dma_addr), len,
-					    PCI_DMA_FROMDEVICE);
+			pci_dma_sync_single_for_device(adap->pdev, dma_addr,
+						       len,
+						       PCI_DMA_FROMDEVICE);
 		} else if (!drop_thres)
 			return NULL;
 recycle:
@@ -820,16 +865,25 @@ recycle:
 	if (unlikely(q->rx_recycle_buf || (!skb && fl->credits <= drop_thres)))
 		goto recycle;
 
+	prefetch(sd->pg_chunk.p_cnt);
+
 	if (!skb)
 		newskb = alloc_skb(SGE_RX_PULL_LEN, GFP_ATOMIC);
+
 	if (unlikely(!newskb)) {
 		if (!drop_thres)
 			return NULL;
 		goto recycle;
 	}
 
-	pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
-			 fl->buf_size, PCI_DMA_FROMDEVICE);
+	pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len,
+				    PCI_DMA_FROMDEVICE);
+	(*sd->pg_chunk.p_cnt)--;
+	if (!*sd->pg_chunk.p_cnt)
+		pci_unmap_page(adap->pdev,
+			       pci_unmap_addr(&sd->pg_chunk, mapping),
+			       fl->alloc_size,
+			       PCI_DMA_FROMDEVICE);
 	if (!skb) {
 		__skb_put(newskb, SGE_RX_PULL_LEN);
 		memcpy(newskb->data, sd->pg_chunk.va, SGE_RX_PULL_LEN);
@@ -1089,7 +1143,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 	struct tx_desc *d = &q->desc[pidx];
 	struct cpl_tx_pkt *cpl = (struct cpl_tx_pkt *)d;
 
-	cpl->len = htonl(skb->len | 0x80000000);
+	cpl->len = htonl(skb->len);
 	cntrl = V_TXPKT_INTF(pi->port_id);
 
 	if (vlan_tx_tag_present(skb) && pi->vlan_grp)
@@ -1958,8 +2012,8 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
 	skb_pull(skb, sizeof(*p) + pad);
 	skb->protocol = eth_type_trans(skb, adap->port[p->iff]);
 	pi = netdev_priv(skb->dev);
-	if ((pi->rx_offload & T3_RX_CSUM) && p->csum_valid && p->csum == htons(0xffff) &&
-	    !p->fragment) {
+	if ((pi->rx_offload & T3_RX_CSUM) && p->csum_valid &&
+	    p->csum == htons(0xffff) && !p->fragment) {
 		qs->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++;
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	} else
@@ -2034,10 +2088,19 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 	fl->credits--;
 
 	len -= offset;
-	pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
-			 fl->buf_size, PCI_DMA_FROMDEVICE);
+	pci_dma_sync_single_for_cpu(adap->pdev,
+				    pci_unmap_addr(sd, dma_addr),
+				    fl->buf_size - SGE_PG_RSVD,
+				    PCI_DMA_FROMDEVICE);
 
-	prefetch(&qs->lro_frag_tbl);
+	(*sd->pg_chunk.p_cnt)--;
+	if (!*sd->pg_chunk.p_cnt)
+		pci_unmap_page(adap->pdev,
+			       pci_unmap_addr(&sd->pg_chunk, mapping),
+			       fl->alloc_size,
+			       PCI_DMA_FROMDEVICE);
+
+	prefetch(qs->lro_va);
 
 	rx_frag += nr_frags;
 	rx_frag->page = sd->pg_chunk.page;
@@ -2047,6 +2110,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 	qs->lro_frag_tbl.nr_frags++;
 	qs->lro_frag_tbl.len = frag_len;
 
+
 	if (!complete)
 		return;
 
@@ -2236,6 +2300,8 @@ no_mem:
 			if (fl->use_pages) {
 				void *addr = fl->sdesc[fl->cidx].pg_chunk.va;
 
+				prefetch(&qs->lro_frag_tbl);
+
 				prefetch(addr);
 #if L1_CACHE_BYTES < 128
 				prefetch(addr + L1_CACHE_BYTES);
@@ -2972,21 +3038,23 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	q->fl[1].use_pages = FL1_PG_CHUNK_SIZE > 0;
 	q->fl[0].order = FL0_PG_ORDER;
 	q->fl[1].order = FL1_PG_ORDER;
+	q->fl[0].alloc_size = FL0_PG_ALLOC_SIZE;
+	q->fl[1].alloc_size = FL1_PG_ALLOC_SIZE;
 
 	spin_lock_irq(&adapter->sge.reg_lock);
 
 	/* FL threshold comparison uses < */
 	ret = t3_sge_init_rspcntxt(adapter, q->rspq.cntxt_id, irq_vec_idx,
 				   q->rspq.phys_addr, q->rspq.size,
-				   q->fl[0].buf_size, 1, 0);
+				   q->fl[0].buf_size - SGE_PG_RSVD, 1, 0);
 	if (ret)
 		goto err_unlock;
 
 	for (i = 0; i < SGE_RXQ_PER_SET; ++i) {
 		ret = t3_sge_init_flcntxt(adapter, q->fl[i].cntxt_id, 0,
 					  q->fl[i].phys_addr, q->fl[i].size,
-					  q->fl[i].buf_size, p->cong_thres, 1,
-					  0);
+					  q->fl[i].buf_size - SGE_PG_RSVD,
+					  p->cong_thres, 1, 0);
 		if (ret)
 			goto err_unlock;
 	}
@@ -3044,9 +3112,6 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	t3_write_reg(adapter, A_SG_GTS, V_RSPQ(q->rspq.cntxt_id) |
 		     V_NEWTIMER(q->rspq.holdoff_tmr));
 
-	mod_timer(&q->tx_reclaim_timer, jiffies + TX_RECLAIM_PERIOD);
-	mod_timer(&q->rx_reclaim_timer, jiffies + RX_RECLAIM_PERIOD);
-
 	return 0;
 
 err_unlock:
@@ -3057,6 +3122,27 @@ err:
 }
 
 /**
+ *      t3_start_sge_timers - start SGE timer call backs
+ *      @adap: the adapter
+ *
+ *      Starts each SGE queue set's timer call back
+ */
+void t3_start_sge_timers(struct adapter *adap)
+{
+	int i;
+
+	for (i = 0; i < SGE_QSETS; ++i) {
+		struct sge_qset *q = &adap->sge.qs[i];
+
+	if (q->tx_reclaim_timer.function)
+		mod_timer(&q->tx_reclaim_timer, jiffies + TX_RECLAIM_PERIOD);
+
+	if (q->rx_reclaim_timer.function)
+		mod_timer(&q->rx_reclaim_timer, jiffies + RX_RECLAIM_PERIOD);
+	}
+}
+
+/**
  *	t3_stop_sge_timers - stop SGE timer call backs
  *	@adap: the adapter
  *