Merge branch 'ocelot-stats'

Colin Foster says:

====================
use bulk reads for ocelot statistics

Ocelot loops over memory regions to gather stats on different ports.
These regions are mostly continuous, and are ordered. This patch set
uses that information to break the stats reads into regions that can get
read in bulk.

The motiviation is for general cleanup, but also for SPI. Performing two
back-to-back reads on a SPI bus require toggling the CS line, holding,
re-toggling the CS line, sending 3 address bytes, sending N padding
bytes, then actually performing the read. Bulk reads could reduce almost
all of that overhead, but require that the reads are performed via
regmap_bulk_read.

Verified with eth0 hooked up to the CPU port:
NIC statistics:
     Good Rx Frames: 905
     Rx Octets: 78848
     Good Tx Frames: 691
     Tx Octets: 52516
     Rx + Tx 65-127 Octet Frames: 1574
     Rx + Tx 128-255 Octet Frames: 22
     Net Octets: 131364
     Rx DMA chan 0: head_enqueue: 1
     Rx DMA chan 0: tail_enqueue: 1032
     Rx DMA chan 0: busy_dequeue: 628
     Rx DMA chan 0: good_dequeue: 905
     Tx DMA chan 0: head_enqueue: 346
     Tx DMA chan 0: tail_enqueue: 345
     Tx DMA chan 0: misqueued: 345
     Tx DMA chan 0: empty_dequeue: 346
     Tx DMA chan 0: good_dequeue: 691
     p00_rx_octets: 52516
     p00_rx_unicast: 691
     p00_rx_frames_65_to_127_octets: 691
     p00_tx_octets: 78848
     p00_tx_unicast: 905
     p00_tx_frames_65_to_127_octets: 883
     p00_tx_frames_128_255_octets: 22
     p00_tx_green_prio_0: 905

And with swp2 connected to swp3 with STP enabled:
NIC statistics:
     tx_packets: 379
     tx_bytes: 19708
     rx_packets: 1
     rx_bytes: 46
     rx_octets: 64
     rx_multicast: 1
     rx_frames_below_65_octets: 1
     rx_classified_drops: 1
     tx_octets: 44630
     tx_multicast: 387
     tx_broadcast: 290
     tx_frames_below_65_octets: 379
     tx_frames_65_to_127_octets: 294
     tx_frames_128_255_octets: 4
     tx_green_prio_0: 298
     tx_green_prio_7: 379
NIC statistics:
     tx_packets: 1
     tx_bytes: 52
     rx_packets: 713
     rx_bytes: 34148
     rx_octets: 46982
     rx_multicast: 407
     rx_broadcast: 306
     rx_frames_below_65_octets: 399
     rx_frames_65_to_127_octets: 310
     rx_frames_128_to_255_octets: 4
     rx_classified_drops: 399
     rx_green_prio_0: 314
     tx_octets: 64
     tx_multicast: 1
     tx_frames_below_65_octets: 1
     tx_green_prio_7: 1

v1 > v2: reword commit messages
v2 > v3: correctly mark this for net-next when sending
v3 > v4: calloc array instead of zalloc per review
v4 > v5:
    Apply CR suggestions for whitespace
    Fix calloc / zalloc mixup
    Properly destroy workqueues
    Add third commit to split long macros
v5 > v6:
    Fix functionality - v5 was improperly tested
    Add bugfix for ethtool mutex lock
    Remove unnecessary ethtool stats reads
v6 > v7:
    Remove mutex bug patch that was applied via net
    Rename function based on CR
    Add missed error check
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mscc/ocelot.c

@@ -1746,28 +1746,36 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data)
 EXPORT_SYMBOL(ocelot_get_strings);
 
 /* Caller must hold &ocelot->stats_lock */
-static void ocelot_update_stats(struct ocelot *ocelot)
+static int ocelot_port_update_stats(struct ocelot *ocelot, int port)
 {
-	int i, j;
+	unsigned int idx = port * ocelot->num_stats;
+	struct ocelot_stats_region *region;
+	int err, j;
 
-	for (i = 0; i < ocelot->num_phys_ports; i++) {
 	/* Configure the port to read the stats from */
-		ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG);
+	ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port), SYS_STAT_CFG);
 
-		for (j = 0; j < ocelot->num_stats; j++) {
-			u32 val;
-			unsigned int idx = i * ocelot->num_stats + j;
+	list_for_each_entry(region, &ocelot->stats_regions, node) {
+		err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
+					   region->offset, region->buf,
+					   region->count);
+		if (err)
+			return err;
 
-			val = ocelot_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
-					      ocelot->stats_layout[j].offset);
+		for (j = 0; j < region->count; j++) {
+			u64 *stat = &ocelot->stats[idx + j];
+			u64 val = region->buf[j];
 
-			if (val < (ocelot->stats[idx] & U32_MAX))
-				ocelot->stats[idx] += (u64)1 << 32;
+			if (val < (*stat & U32_MAX))
+				*stat += (u64)1 << 32;
 
-			ocelot->stats[idx] = (ocelot->stats[idx] &
-					      ~(u64)U32_MAX) + val;
+			*stat = (*stat & ~(u64)U32_MAX) + val;
 		}
+
+		idx += region->count;
 	}
+
+	return err;
 }
 
 static void ocelot_check_stats_work(struct work_struct *work)
@@ -1775,29 +1783,40 @@ static void ocelot_check_stats_work(struct work_struct *work)
 	struct delayed_work *del_work = to_delayed_work(work);
 	struct ocelot *ocelot = container_of(del_work, struct ocelot,
 					     stats_work);
+	int i, err;
 
 	mutex_lock(&ocelot->stats_lock);
-	ocelot_update_stats(ocelot);
+	for (i = 0; i < ocelot->num_phys_ports; i++) {
+		err = ocelot_port_update_stats(ocelot, i);
+		if (err)
+			break;
+	}
 	mutex_unlock(&ocelot->stats_lock);
 
+	if (err)
+		dev_err(ocelot->dev, "Error %d updating ethtool stats\n",  err);
+
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
 }
 
 void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data)
 {
-	int i;
+	int i, err;
 
 	mutex_lock(&ocelot->stats_lock);
 
 	/* check and update now */
-	ocelot_update_stats(ocelot);
+	err = ocelot_port_update_stats(ocelot, port);
 
 	/* Copy all counters */
 	for (i = 0; i < ocelot->num_stats; i++)
 		*data++ = ocelot->stats[port * ocelot->num_stats + i];
 
 	mutex_unlock(&ocelot->stats_lock);
+
+	if (err)
+		dev_err(ocelot->dev, "Error %d updating ethtool stats\n", err);
 }
 EXPORT_SYMBOL(ocelot_get_ethtool_stats);
 
@@ -1810,6 +1829,41 @@ int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset)
 }
 EXPORT_SYMBOL(ocelot_get_sset_count);
 
+static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
+{
+	struct ocelot_stats_region *region = NULL;
+	unsigned int last;
+	int i;
+
+	INIT_LIST_HEAD(&ocelot->stats_regions);
+
+	for (i = 0; i < ocelot->num_stats; i++) {
+		if (region && ocelot->stats_layout[i].offset == last + 1) {
+			region->count++;
+		} else {
+			region = devm_kzalloc(ocelot->dev, sizeof(*region),
+					      GFP_KERNEL);
+			if (!region)
+				return -ENOMEM;
+
+			region->offset = ocelot->stats_layout[i].offset;
+			region->count = 1;
+			list_add_tail(&region->node, &ocelot->stats_regions);
+		}
+
+		last = ocelot->stats_layout[i].offset;
+	}
+
+	list_for_each_entry(region, &ocelot->stats_regions, node) {
+		region->buf = devm_kcalloc(ocelot->dev, region->count,
+					   sizeof(*region->buf), GFP_KERNEL);
+		if (!region->buf)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 		       struct ethtool_ts_info *info)
 {
@@ -2810,6 +2864,13 @@ int ocelot_init(struct ocelot *ocelot)
 				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
 				 ANA_CPUQ_8021_CFG, i);
 
+	ret = ocelot_prepare_stats_regions(ocelot);
+	if (ret) {
+		destroy_workqueue(ocelot->stats_queue);
+		destroy_workqueue(ocelot->owq);
+		return ret;
+	}
+
 	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);

drivers/net/ethernet/mscc/ocelot_io.c

@@ -10,6 +10,19 @@
 
 #include "ocelot.h"
 
+int __ocelot_bulk_read_ix(struct ocelot *ocelot, u32 reg, u32 offset, void *buf,
+			  int count)
+{
+	u16 target = reg >> TARGET_OFFSET;
+
+	WARN_ON(!target);
+
+	return regmap_bulk_read(ocelot->targets[target],
+				ocelot->map[target][reg & REG_MASK] + offset,
+				buf, count);
+}
+EXPORT_SYMBOL_GPL(__ocelot_bulk_read_ix);
+
 u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset)
 {
 	u16 target = reg >> TARGET_OFFSET;

include/soc/mscc/ocelot.h

@@ -540,6 +540,13 @@ struct ocelot_stat_layout {
 	char name[ETH_GSTRING_LEN];
 };
 
+struct ocelot_stats_region {
+	struct list_head node;
+	u32 offset;
+	int count;
+	u32 *buf;
+};
+
 enum ocelot_tag_prefix {
 	OCELOT_TAG_PREFIX_DISABLED	= 0,
 	OCELOT_TAG_PREFIX_NONE,
@@ -671,6 +678,7 @@ struct ocelot {
 	struct regmap_field		*regfields[REGFIELD_MAX];
 	const u32 *const		*map;
 	const struct ocelot_stat_layout	*stats_layout;
+	struct list_head		stats_regions;
 	unsigned int			num_stats;
 
 	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
@@ -742,25 +750,42 @@ struct ocelot_policer {
 	u32 burst; /* bytes */
 };
 
-#define ocelot_read_ix(ocelot, reg, gi, ri) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
-#define ocelot_read_gix(ocelot, reg, gi) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi))
-#define ocelot_read_rix(ocelot, reg, ri) __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri))
-#define ocelot_read(ocelot, reg) __ocelot_read_ix(ocelot, reg, 0)
-
-#define ocelot_write_ix(ocelot, val, reg, gi, ri) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
-#define ocelot_write_gix(ocelot, val, reg, gi) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi))
-#define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri))
+#define ocelot_bulk_read_rix(ocelot, reg, ri, buf, count) \
+	__ocelot_bulk_read_ix(ocelot, reg, reg##_RSZ * (ri), buf, count)
+
+#define ocelot_read_ix(ocelot, reg, gi, ri) \
+	__ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_read_gix(ocelot, reg, gi) \
+	__ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi))
+#define ocelot_read_rix(ocelot, reg, ri) \
+	__ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri))
+#define ocelot_read(ocelot, reg) \
+	__ocelot_read_ix(ocelot, reg, 0)
+
+#define ocelot_write_ix(ocelot, val, reg, gi, ri) \
+	__ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_write_gix(ocelot, val, reg, gi) \
+	__ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi))
+#define ocelot_write_rix(ocelot, val, reg, ri) \
+	__ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri))
 #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0)
 
-#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
-#define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi))
-#define ocelot_rmw_rix(ocelot, val, m, reg, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri))
+#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) \
+	__ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_rmw_gix(ocelot, val, m, reg, gi) \
+	__ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi))
+#define ocelot_rmw_rix(ocelot, val, m, reg, ri) \
+	__ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri))
 #define ocelot_rmw(ocelot, val, m, reg) __ocelot_rmw_ix(ocelot, val, m, reg, 0)
 
-#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val))
-#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val))
-#define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val))
-#define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val))
+#define ocelot_field_write(ocelot, reg, val) \
+	regmap_field_write((ocelot)->regfields[(reg)], (val))
+#define ocelot_field_read(ocelot, reg, val) \
+	regmap_field_read((ocelot)->regfields[(reg)], (val))
+#define ocelot_fields_write(ocelot, id, reg, val) \
+	regmap_fields_write((ocelot)->regfields[(reg)], (id), (val))
+#define ocelot_fields_read(ocelot, id, reg, val) \
+	regmap_fields_read((ocelot)->regfields[(reg)], (id), (val))
 
 #define ocelot_target_read_ix(ocelot, target, reg, gi, ri) \
 	__ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
@@ -784,6 +809,8 @@ struct ocelot_policer {
 u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
 void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
 void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg);
+int __ocelot_bulk_read_ix(struct ocelot *ocelot, u32 reg, u32 offset, void *buf,
+			  int count);
 u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset);
 void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset);
 void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,