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

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1958 commits)
  net: pack skb_shared_info more efficiently
  net_sched: red: split red_parms into parms and vars
  net_sched: sfq: extend limits
  cnic: Improve error recovery on bnx2x devices
  cnic: Re-init dev->stats_addr after chip reset
  net_sched: Bug in netem reordering
  bna: fix sparse warnings/errors
  bna: make ethtool_ops and strings const
  xgmac: cleanups
  net: make ethtool_ops const
  vmxnet3" make ethtool ops const
  xen-netback: make ops structs const
  virtio_net: Pass gfp flags when allocating rx buffers.
  ixgbe: FCoE: Add support for ndo_get_fcoe_hbainfo() call
  netdev: FCoE: Add new ndo_get_fcoe_hbainfo() call
  igb: reset PHY after recovering from PHY power down
  igb: add basic runtime PM support
  igb: Add support for byte queue limits.
  e1000: cleanup CE4100 MDIO registers access
  e1000: unmap ce4100_gbe_mdio_base_virt in e1000_remove
  ...

lib/Kconfig

@@ -244,6 +244,9 @@ config CPU_RMAP
 	bool
 	depends on SMP
 
+config DQL
+	bool
+
 #
 # Netlink attribute parsing support is select'ed if needed
 #

lib/Makefile

@@ -115,6 +115,8 @@ obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
 obj-$(CONFIG_CORDIC) += cordic.o
 
+obj-$(CONFIG_DQL) += dynamic_queue_limits.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 

lib/dynamic_queue_limits.c

@@ -0,0 +1,133 @@
+/*
+ * Dynamic byte queue limits.  See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/dynamic_queue_limits.h>
+
+#define POSDIFF(A, B) ((A) > (B) ? (A) - (B) : 0)
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+	unsigned int inprogress, prev_inprogress, limit;
+	unsigned int ovlimit, all_prev_completed, completed;
+
+	/* Can't complete more than what's in queue */
+	BUG_ON(count > dql->num_queued - dql->num_completed);
+
+	completed = dql->num_completed + count;
+	limit = dql->limit;
+	ovlimit = POSDIFF(dql->num_queued - dql->num_completed, limit);
+	inprogress = dql->num_queued - completed;
+	prev_inprogress = dql->prev_num_queued - dql->num_completed;
+	all_prev_completed = POSDIFF(completed, dql->prev_num_queued);
+
+	if ((ovlimit && !inprogress) ||
+	    (dql->prev_ovlimit && all_prev_completed)) {
+		/*
+		 * Queue considered starved if:
+		 *   - The queue was over-limit in the last interval,
+		 *     and there is no more data in the queue.
+		 *  OR
+		 *   - The queue was over-limit in the previous interval and
+		 *     when enqueuing it was possible that all queued data
+		 *     had been consumed.  This covers the case when queue
+		 *     may have becomes starved between completion processing
+		 *     running and next time enqueue was scheduled.
+		 *
+		 *     When queue is starved increase the limit by the amount
+		 *     of bytes both sent and completed in the last interval,
+		 *     plus any previous over-limit.
+		 */
+		limit += POSDIFF(completed, dql->prev_num_queued) +
+		     dql->prev_ovlimit;
+		dql->slack_start_time = jiffies;
+		dql->lowest_slack = UINT_MAX;
+	} else if (inprogress && prev_inprogress && !all_prev_completed) {
+		/*
+		 * Queue was not starved, check if the limit can be decreased.
+		 * A decrease is only considered if the queue has been busy in
+		 * the whole interval (the check above).
+		 *
+		 * If there is slack, the amount of execess data queued above
+		 * the the amount needed to prevent starvation, the queue limit
+		 * can be decreased.  To avoid hysteresis we consider the
+		 * minimum amount of slack found over several iterations of the
+		 * completion routine.
+		 */
+		unsigned int slack, slack_last_objs;
+
+		/*
+		 * Slack is the maximum of
+		 *   - The queue limit plus previous over-limit minus twice
+		 *     the number of objects completed.  Note that two times
+		 *     number of completed bytes is a basis for an upper bound
+		 *     of the limit.
+		 *   - Portion of objects in the last queuing operation that
+		 *     was not part of non-zero previous over-limit.  That is
+		 *     "round down" by non-overlimit portion of the last
+		 *     queueing operation.
+		 */
+		slack = POSDIFF(limit + dql->prev_ovlimit,
+		    2 * (completed - dql->num_completed));
+		slack_last_objs = dql->prev_ovlimit ?
+		    POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+		slack = max(slack, slack_last_objs);
+
+		if (slack < dql->lowest_slack)
+			dql->lowest_slack = slack;
+
+		if (time_after(jiffies,
+			       dql->slack_start_time + dql->slack_hold_time)) {
+			limit = POSDIFF(limit, dql->lowest_slack);
+			dql->slack_start_time = jiffies;
+			dql->lowest_slack = UINT_MAX;
+		}
+	}
+
+	/* Enforce bounds on limit */
+	limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+	if (limit != dql->limit) {
+		dql->limit = limit;
+		ovlimit = 0;
+	}
+
+	dql->adj_limit = limit + completed;
+	dql->prev_ovlimit = ovlimit;
+	dql->prev_last_obj_cnt = dql->last_obj_cnt;
+	dql->num_completed = completed;
+	dql->prev_num_queued = dql->num_queued;
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+	/* Reset all dynamic values */
+	dql->limit = 0;
+	dql->num_queued = 0;
+	dql->num_completed = 0;
+	dql->last_obj_cnt = 0;
+	dql->prev_num_queued = 0;
+	dql->prev_last_obj_cnt = 0;
+	dql->prev_ovlimit = 0;
+	dql->lowest_slack = UINT_MAX;
+	dql->slack_start_time = jiffies;
+}
+EXPORT_SYMBOL(dql_reset);
+
+int dql_init(struct dql *dql, unsigned hold_time)
+{
+	dql->max_limit = DQL_MAX_LIMIT;
+	dql->min_limit = 0;
+	dql->slack_hold_time = hold_time;
+	dql_reset(dql);
+	return 0;
+}
+EXPORT_SYMBOL(dql_init);

lib/reciprocal_div.c

@@ -1,5 +1,6 @@
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
+#include <linux/export.h>
 
 u32 reciprocal_value(u32 k)
 {
@@ -7,3 +8,4 @@ u32 reciprocal_value(u32 k)
 	do_div(val, k);
 	return (u32)val;
 }
+EXPORT_SYMBOL(reciprocal_value);

lib/vsprintf.c

@@ -777,6 +777,18 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 	return string(buf, end, uuid, spec);
 }
 
+static
+char *netdev_feature_string(char *buf, char *end, const u8 *addr,
+		      struct printf_spec spec)
+{
+	spec.flags |= SPECIAL | SMALL | ZEROPAD;
+	if (spec.field_width == -1)
+		spec.field_width = 2 + 2 * sizeof(netdev_features_t);
+	spec.base = 16;
+
+	return number(buf, end, *(const netdev_features_t *)addr, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -824,6 +836,7 @@ int kptr_restrict __read_mostly;
  *       Do not use this feature without some mechanism to verify the
  *       correctness of the format string and va_list arguments.
  * - 'K' For a kernel pointer that should be hidden from unprivileged users
+ * - 'NF' For a netdev_features_t
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -896,6 +909,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		       has_capability_noaudit(current, CAP_SYSLOG))))
 			ptr = NULL;
 		break;
+	case 'N':
+		switch (fmt[1]) {
+		case 'F':
+			return netdev_feature_string(buf, end, ptr, spec);
+		}
+		break;
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {