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

Documentation/networking/fib_trie.txt

@@ -0,0 +1,145 @@
+			LC-trie implementation notes.
+
+Node types
+----------
+leaf 
+	An end node with data. This has a copy of the relevant key, along
+	with 'hlist' with routing table entries sorted by prefix length.
+	See struct leaf and struct leaf_info.
+
+trie node or tnode
+	An internal node, holding an array of child (leaf or tnode) pointers,
+	indexed	through a subset of the key. See Level Compression.
+
+A few concepts explained
+------------------------
+Bits (tnode) 
+	The number of bits in the key segment used for indexing into the
+	child array - the "child index". See Level Compression.
+
+Pos (tnode)
+	The position (in the key) of the key segment used for indexing into
+	the child array. See Path Compression.
+
+Path Compression / skipped bits
+	Any given tnode is linked to from the child array of its parent, using
+	a segment of the key specified by the parent's "pos" and "bits" 
+	In certain cases, this tnode's own "pos" will not be immediately
+	adjacent to the parent (pos+bits), but there will be some bits
+	in the key skipped over because they represent a single path with no
+	deviations. These "skipped bits" constitute Path Compression.
+	Note that the search algorithm will simply skip over these bits when
+	searching, making it necessary to save the keys in the leaves to
+	verify that they actually do match the key we are searching for.
+
+Level Compression / child arrays
+	the trie is kept level balanced moving, under certain conditions, the
+	children of a full child (see "full_children") up one level, so that
+	instead of a pure binary tree, each internal node ("tnode") may
+	contain an arbitrarily large array of links to several children.
+	Conversely, a tnode with a mostly empty	child array (see empty_children)
+	may be "halved", having some of its children moved downwards one level,
+	in order to avoid ever-increasing child arrays.
+
+empty_children
+	the number of positions in the child array of a given tnode that are
+	NULL.
+
+full_children
+	the number of children of a given tnode that aren't path compressed.
+	(in other words, they aren't NULL or leaves and their "pos" is equal
+	to this	tnode's "pos"+"bits").
+
+	(The word "full" here is used more in the sense of "complete" than
+	as the opposite of "empty", which might be a tad confusing.)
+
+Comments
+---------
+
+We have tried to keep the structure of the code as close to fib_hash as 
+possible to allow verification and help up reviewing. 
+
+fib_find_node()
+	A good start for understanding this code. This function implements a
+	straightforward trie lookup.
+
+fib_insert_node()
+	Inserts a new leaf node in the trie. This is bit more complicated than
+	fib_find_node(). Inserting a new node means we might have to run the
+	level compression algorithm on part of the trie.
+
+trie_leaf_remove()
+	Looks up a key, deletes it and runs the level compression algorithm.
+
+trie_rebalance()
+	The key function for the dynamic trie after any change in the trie
+	it is run to optimize and reorganize. Tt will walk the trie upwards 
+	towards the root from a given tnode, doing a resize() at each step 
+	to implement level compression.
+
+resize()
+	Analyzes a tnode and optimizes the child array size by either inflating
+	or shrinking it repeatedly until it fullfills the criteria for optimal
+	level compression. This part follows the original paper pretty closely
+	and there may be some room for experimentation here.
+
+inflate()
+	Doubles the size of the child array within a tnode. Used by resize().
+
+halve()
+	Halves the size of the child array within a tnode - the inverse of
+	inflate(). Used by resize();
+
+fn_trie_insert(), fn_trie_delete(), fn_trie_select_default()
+	The route manipulation functions. Should conform pretty closely to the
+	corresponding functions in fib_hash.
+
+fn_trie_flush()
+	This walks the full trie (using nextleaf()) and searches for empty
+	leaves which have to be removed.
+
+fn_trie_dump()
+	Dumps the routing table ordered by prefix length. This is somewhat
+	slower than the corresponding fib_hash function, as we have to walk the
+	entire trie for each prefix length. In comparison, fib_hash is organized
+	as one "zone"/hash per prefix length.
+
+Locking
+-------
+
+fib_lock is used for an RW-lock in the same way that this is done in fib_hash.
+However, the functions are somewhat separated for other possible locking
+scenarios. It might conceivably be possible to run trie_rebalance via RCU
+to avoid read_lock in the fn_trie_lookup() function.
+
+Main lookup mechanism
+---------------------
+fn_trie_lookup() is the main lookup function.
+
+The lookup is in its simplest form just like fib_find_node(). We descend the
+trie, key segment by key segment, until we find a leaf. check_leaf() does
+the fib_semantic_match in the leaf's sorted prefix hlist.
+
+If we find a match, we are done.
+
+If we don't find a match, we enter prefix matching mode. The prefix length,
+starting out at the same as the key length, is reduced one step at a time,
+and we backtrack upwards through the trie trying to find a longest matching
+prefix. The goal is always to reach a leaf and get a positive result from the
+fib_semantic_match mechanism.
+
+Inside each tnode, the search for longest matching prefix consists of searching
+through the child array, chopping off (zeroing) the least significant "1" of
+the child index until we find a match or the child index consists of nothing but
+zeros.
+
+At this point we backtrack (t->stats.backtrack++) up the trie, continuing to
+chop off part of the key in order to find the longest matching prefix.
+
+At this point we will repeatedly descend subtries to look for a match, and there
+are some optimizations available that can provide us with "shortcuts" to avoid
+descending into dead ends. Look for "HL_OPTIMIZE" sections in the code.
+
+To alleviate any doubts about the correctness of the route selection process,
+a new netlink operation has been added. Look for NETLINK_FIB_LOOKUP, which
+gives userland access to fib_lookup().

drivers/net/shaper.c

@@ -135,10 +135,8 @@ static int shaper_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct shaper *shaper = dev->priv;
  	struct sk_buff *ptr;
-
-	if (down_trylock(&shaper->sem))
-		return -1;
-
+
+	spin_lock(&shaper->lock);
  	ptr=shaper->sendq.prev;
 
  	/*
@@ -232,7 +230,7 @@ static int shaper_start_xmit(struct sk_buff *skb, struct net_device *dev)
                 shaper->stats.collisions++;
  	}
 	shaper_kick(shaper);
-	up(&shaper->sem);
+	spin_unlock(&shaper->lock);
  	return 0;
 }
 
@@ -271,11 +269,9 @@ static void shaper_timer(unsigned long data)
 {
 	struct shaper *shaper = (struct shaper *)data;
 
-	if (!down_trylock(&shaper->sem)) {
-		shaper_kick(shaper);
-		up(&shaper->sem);
-	} else
-		mod_timer(&shaper->timer, jiffies);
+	spin_lock(&shaper->lock);
+	shaper_kick(shaper);
+	spin_unlock(&shaper->lock);
 }
 
 /*
@@ -331,21 +327,6 @@ static void shaper_kick(struct shaper *shaper)
 }
 
 
-/*
- *	Flush the shaper queues on a closedown
- */
-
-static void shaper_flush(struct shaper *shaper)
-{
-	struct sk_buff *skb;
-
-	down(&shaper->sem);
-	while((skb=skb_dequeue(&shaper->sendq))!=NULL)
-		dev_kfree_skb(skb);
-	shaper_kick(shaper);
-	up(&shaper->sem);
-}
-
 /*
  *	Bring the interface up. We just disallow this until a 
  *	bind.
@@ -375,7 +356,15 @@ static int shaper_open(struct net_device *dev)
 static int shaper_close(struct net_device *dev)
 {
 	struct shaper *shaper=dev->priv;
-	shaper_flush(shaper);
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&shaper->sendq)) != NULL)
+		dev_kfree_skb(skb);
+
+	spin_lock_bh(&shaper->lock);
+	shaper_kick(shaper);
+	spin_unlock_bh(&shaper->lock);
+
 	del_timer_sync(&shaper->timer);
 	return 0;
 }
@@ -576,6 +565,7 @@ static void shaper_init_priv(struct net_device *dev)
 	init_timer(&sh->timer);
 	sh->timer.function=shaper_timer;
 	sh->timer.data=(unsigned long)sh;
+	spin_lock_init(&sh->lock);
 }
 
 /*

drivers/net/skge.h

@@ -7,6 +7,7 @@
 /* PCI config registers */
 #define PCI_DEV_REG1	0x40
 #define PCI_DEV_REG2	0x44
+#define  PCI_REV_DESC	 0x4
 
 #define PCI_STATUS_ERROR_BITS (PCI_STATUS_DETECTED_PARITY | \
 			       PCI_STATUS_SIG_SYSTEM_ERROR | \

drivers/net/tg3.c

@@ -66,8 +66,8 @@
 
 #define DRV_MODULE_NAME		"tg3"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"3.32"
-#define DRV_MODULE_RELDATE	"June 24, 2005"
+#define DRV_MODULE_VERSION	"3.33"
+#define DRV_MODULE_RELDATE	"July 5, 2005"
 
 #define TG3_DEF_MAC_MODE	0
 #define TG3_DEF_RX_MODE		0
@@ -5117,7 +5117,7 @@ static void tg3_set_bdinfo(struct tg3 *tp, u32 bdinfo_addr,
 }
 
 static void __tg3_set_rx_mode(struct net_device *);
-static void tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec)
+static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec)
 {
 	tw32(HOSTCC_RXCOL_TICKS, ec->rx_coalesce_usecs);
 	tw32(HOSTCC_TXCOL_TICKS, ec->tx_coalesce_usecs);
@@ -5460,7 +5460,7 @@ static int tg3_reset_hw(struct tg3 *tp)
 		udelay(10);
 	}
 
-	tg3_set_coalesce(tp, &tp->coal);
+	__tg3_set_coalesce(tp, &tp->coal);
 
 	/* set status block DMA address */
 	tw32(HOSTCC_STATUS_BLK_HOST_ADDR + TG3_64BIT_REG_HIGH,
@@ -7821,6 +7821,60 @@ static int tg3_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
+static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+{
+	struct tg3 *tp = netdev_priv(dev);
+	u32 max_rxcoal_tick_int = 0, max_txcoal_tick_int = 0;
+	u32 max_stat_coal_ticks = 0, min_stat_coal_ticks = 0;
+
+	if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) {
+		max_rxcoal_tick_int = MAX_RXCOAL_TICK_INT;
+		max_txcoal_tick_int = MAX_TXCOAL_TICK_INT;
+		max_stat_coal_ticks = MAX_STAT_COAL_TICKS;
+		min_stat_coal_ticks = MIN_STAT_COAL_TICKS;
+	}
+
+	if ((ec->rx_coalesce_usecs > MAX_RXCOL_TICKS) ||
+	    (ec->tx_coalesce_usecs > MAX_TXCOL_TICKS) ||
+	    (ec->rx_max_coalesced_frames > MAX_RXMAX_FRAMES) ||
+	    (ec->tx_max_coalesced_frames > MAX_TXMAX_FRAMES) ||
+	    (ec->rx_coalesce_usecs_irq > max_rxcoal_tick_int) ||
+	    (ec->tx_coalesce_usecs_irq > max_txcoal_tick_int) ||
+	    (ec->rx_max_coalesced_frames_irq > MAX_RXCOAL_MAXF_INT) ||
+	    (ec->tx_max_coalesced_frames_irq > MAX_TXCOAL_MAXF_INT) ||
+	    (ec->stats_block_coalesce_usecs > max_stat_coal_ticks) ||
+	    (ec->stats_block_coalesce_usecs < min_stat_coal_ticks))
+		return -EINVAL;
+
+	/* No rx interrupts will be generated if both are zero */
+	if ((ec->rx_coalesce_usecs == 0) &&
+	    (ec->rx_max_coalesced_frames == 0))
+		return -EINVAL;
+
+	/* No tx interrupts will be generated if both are zero */
+	if ((ec->tx_coalesce_usecs == 0) &&
+	    (ec->tx_max_coalesced_frames == 0))
+		return -EINVAL;
+
+	/* Only copy relevant parameters, ignore all others. */
+	tp->coal.rx_coalesce_usecs = ec->rx_coalesce_usecs;
+	tp->coal.tx_coalesce_usecs = ec->tx_coalesce_usecs;
+	tp->coal.rx_max_coalesced_frames = ec->rx_max_coalesced_frames;
+	tp->coal.tx_max_coalesced_frames = ec->tx_max_coalesced_frames;
+	tp->coal.rx_coalesce_usecs_irq = ec->rx_coalesce_usecs_irq;
+	tp->coal.tx_coalesce_usecs_irq = ec->tx_coalesce_usecs_irq;
+	tp->coal.rx_max_coalesced_frames_irq = ec->rx_max_coalesced_frames_irq;
+	tp->coal.tx_max_coalesced_frames_irq = ec->tx_max_coalesced_frames_irq;
+	tp->coal.stats_block_coalesce_usecs = ec->stats_block_coalesce_usecs;
+
+	if (netif_running(dev)) {
+		tg3_full_lock(tp, 0);
+		__tg3_set_coalesce(tp, &tp->coal);
+		tg3_full_unlock(tp);
+	}
+	return 0;
+}
+
 static struct ethtool_ops tg3_ethtool_ops = {
 	.get_settings		= tg3_get_settings,
 	.set_settings		= tg3_set_settings,
@@ -7856,6 +7910,7 @@ static struct ethtool_ops tg3_ethtool_ops = {
 	.get_stats_count	= tg3_get_stats_count,
 	.get_ethtool_stats	= tg3_get_ethtool_stats,
 	.get_coalesce		= tg3_get_coalesce,
+	.set_coalesce		= tg3_set_coalesce,
 };
 
 static void __devinit tg3_get_eeprom_size(struct tg3 *tp)
@@ -9800,6 +9855,12 @@ static void __devinit tg3_init_coal(struct tg3 *tp)
 		ec->tx_coalesce_usecs = LOW_TXCOL_TICKS_CLRTCKS;
 		ec->tx_coalesce_usecs_irq = DEFAULT_TXCOAL_TICK_INT_CLRTCKS;
 	}
+
+	if (tp->tg3_flags2 & TG3_FLG2_5705_PLUS) {
+		ec->rx_coalesce_usecs_irq = 0;
+		ec->tx_coalesce_usecs_irq = 0;
+		ec->stats_block_coalesce_usecs = 0;
+	}
 }
 
 static int __devinit tg3_init_one(struct pci_dev *pdev,

drivers/net/tg3.h

@@ -879,31 +879,41 @@
 #define  LOW_RXCOL_TICKS_CLRTCKS	 0x00000014
 #define  DEFAULT_RXCOL_TICKS		 0x00000048
 #define  HIGH_RXCOL_TICKS		 0x00000096
+#define  MAX_RXCOL_TICKS		 0x000003ff
 #define HOSTCC_TXCOL_TICKS		0x00003c0c
 #define  LOW_TXCOL_TICKS		 0x00000096
 #define  LOW_TXCOL_TICKS_CLRTCKS	 0x00000048
 #define  DEFAULT_TXCOL_TICKS		 0x0000012c
 #define  HIGH_TXCOL_TICKS		 0x00000145
+#define  MAX_TXCOL_TICKS		 0x000003ff
 #define HOSTCC_RXMAX_FRAMES		0x00003c10
 #define  LOW_RXMAX_FRAMES		 0x00000005
 #define  DEFAULT_RXMAX_FRAMES		 0x00000008
 #define  HIGH_RXMAX_FRAMES		 0x00000012
+#define  MAX_RXMAX_FRAMES		 0x000000ff
 #define HOSTCC_TXMAX_FRAMES		0x00003c14
 #define  LOW_TXMAX_FRAMES		 0x00000035
 #define  DEFAULT_TXMAX_FRAMES		 0x0000004b
 #define  HIGH_TXMAX_FRAMES		 0x00000052
+#define  MAX_TXMAX_FRAMES		 0x000000ff
 #define HOSTCC_RXCOAL_TICK_INT		0x00003c18
 #define  DEFAULT_RXCOAL_TICK_INT	 0x00000019
 #define  DEFAULT_RXCOAL_TICK_INT_CLRTCKS 0x00000014
+#define  MAX_RXCOAL_TICK_INT		 0x000003ff
 #define HOSTCC_TXCOAL_TICK_INT		0x00003c1c
 #define  DEFAULT_TXCOAL_TICK_INT	 0x00000019
 #define  DEFAULT_TXCOAL_TICK_INT_CLRTCKS 0x00000014
+#define  MAX_TXCOAL_TICK_INT		 0x000003ff
 #define HOSTCC_RXCOAL_MAXF_INT		0x00003c20
 #define  DEFAULT_RXCOAL_MAXF_INT	 0x00000005
+#define  MAX_RXCOAL_MAXF_INT		 0x000000ff
 #define HOSTCC_TXCOAL_MAXF_INT		0x00003c24
 #define  DEFAULT_TXCOAL_MAXF_INT	 0x00000005
+#define  MAX_TXCOAL_MAXF_INT		 0x000000ff
 #define HOSTCC_STAT_COAL_TICKS		0x00003c28
 #define  DEFAULT_STAT_COAL_TICKS	 0x000f4240
+#define  MAX_STAT_COAL_TICKS		 0xd693d400
+#define  MIN_STAT_COAL_TICKS		 0x00000064
 /* 0x3c2c --> 0x3c30 unused */
 #define HOSTCC_STATS_BLK_HOST_ADDR	0x00003c30 /* 64-bit */
 #define HOSTCC_STATUS_BLK_HOST_ADDR	0x00003c38 /* 64-bit */

include/linux/if_shaper.h

@@ -23,7 +23,7 @@ struct shaper
 	__u32 shapeclock;
 	unsigned long recovery;	/* Time we can next clock a packet out on
 				   an empty queue */
-	struct semaphore sem;
+	spinlock_t lock;
         struct net_device_stats stats;
 	struct net_device *dev;
 	int  (*hard_start_xmit) (struct sk_buff *skb,