[PATCH net-next v3 5/9] forcedeth: implement ndo_get_stats64() API

From: David Decotigny
Date: Mon Nov 14 2011 - 19:19:36 EST


This commit implements the ndo_get_stats64() API for forcedeth. Since
these stats are being updated from different contexts (process and
timer), this commit adds protection (locking + atomic variables).

Tested:
- 16-way SMP x86_64 ->
RX bytes:7244556582 (7.2 GB) TX bytes:181904254 (181.9 MB)
- pktgen + loopback: identical rx_bytes/tx_bytes and rx_packets/tx_packets



Signed-off-by: David Decotigny <david.decotigny@xxxxxxxxxx>
---
drivers/net/ethernet/nvidia/forcedeth.c | 182 ++++++++++++++++++++++++-------
1 files changed, 141 insertions(+), 41 deletions(-)

diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index ee8cce5..a67c1f4 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -692,6 +692,21 @@ struct nv_ethtool_stats {
#define NV_DEV_STATISTICS_V2_COUNT (NV_DEV_STATISTICS_V3_COUNT - 3)
#define NV_DEV_STATISTICS_V1_COUNT (NV_DEV_STATISTICS_V2_COUNT - 6)

+/* driver statistics */
+struct nv_driver_stat {
+ atomic_t delta; /* increase since last nv_update_stats() */
+ u64 total; /* cumulative, requires netdev_priv(dev)->stats_lock */
+};
+
+#define NV_DRIVER_STAT_ATOMIC_INC(ptr_stat) /* atomic */ \
+ ({ atomic_inc(&(ptr_stat)->delta); })
+#define NV_DRIVER_STAT_ATOMIC_ADD(ptr_stat,increment) /* atomic */ \
+ ({ atomic_add((increment), &(ptr_stat)->delta); })
+#define NV_DRIVER_STAT_UPDATE_TOTAL(ptr_stat) /* requires stats_lock */ \
+ ({ (ptr_stat)->total += atomic_xchg(&(ptr_stat)->delta, 0); })
+#define NV_DRIVER_STAT_GET_TOTAL(ptr_stat) /* requires stats_lock */ \
+ ((ptr_stat)->total)
+
/* diagnostics */
#define NV_TEST_COUNT_BASE 3
#define NV_TEST_COUNT_EXTENDED 4
@@ -736,6 +751,12 @@ struct nv_skb_map {
* - tx setup is lockless: it relies on netif_tx_lock. Actual submission
* needs netdev_priv(dev)->lock :-(
* - set_multicast_list: preparation lockless, relies on netif_tx_lock.
+ *
+ * Stats are protected with stats_lock:
+ * - updated by nv_do_stats_poll (timer). This is meant to avoid
+ * integer wraparound in the NIC stats registers, at low frequency
+ * (0.1 Hz)
+ * - updated by nv_get_ethtool_stats + nv_get_stats64
*/

/* in dev: base, irq */
@@ -745,9 +766,10 @@ struct fe_priv {
struct net_device *dev;
struct napi_struct napi;

- /* General data:
- * Locking: spin_lock(&np->lock); */
+ /* stats are updated in syscall and timer */
+ spinlock_t stats_lock;
struct nv_ethtool_stats estats;
+
int in_shutdown;
u32 linkspeed;
int duplex;
@@ -798,6 +820,11 @@ struct fe_priv {
u32 nic_poll_irq;
int rx_ring_size;

+ /* RX software stats */
+ struct nv_driver_stat stat_rx_packets;
+ struct nv_driver_stat stat_rx_bytes; /* not always available in HW */
+ struct nv_driver_stat stat_rx_missed_errors;
+
/* media detection workaround.
* Locking: Within irq hander or disable_irq+spin_lock(&np->lock);
*/
@@ -820,6 +847,11 @@ struct fe_priv {
struct nv_skb_map *tx_end_flip;
int tx_stop;

+ /* TX software stats */
+ struct nv_driver_stat stat_tx_packets; /* not always available in HW */
+ struct nv_driver_stat stat_tx_bytes;
+ struct nv_driver_stat stat_tx_dropped;
+
/* msi/msi-x fields */
u32 msi_flags;
struct msix_entry msi_x_entry[NV_MSI_X_MAX_VECTORS];
@@ -1635,11 +1667,19 @@ static void nv_mac_reset(struct net_device *dev)
pci_push(base);
}

-static void nv_get_hw_stats(struct net_device *dev)
+/* Caller must appropriately lock netdev_priv(dev)->stats_lock */
+static void nv_update_stats(struct net_device *dev)
{
struct fe_priv *np = netdev_priv(dev);
u8 __iomem *base = get_hwbase(dev);

+ /* If it happens that this is run in top-half context, then
+ * replace the spin_lock of stats_lock with
+ * spin_lock_irqsave() in calling functions. */
+ WARN_ONCE(in_irq(), "forcedeth: estats spin_lock(_bh) from top-half");
+ assert_spin_locked(&np->stats_lock);
+
+ /* query hardware */
np->estats.tx_bytes += readl(base + NvRegTxCnt);
np->estats.tx_zero_rexmt += readl(base + NvRegTxZeroReXmt);
np->estats.tx_one_rexmt += readl(base + NvRegTxOneReXmt);
@@ -1695,21 +1735,35 @@ static void nv_get_hw_stats(struct net_device *dev)
np->estats.tx_multicast += readl(base + NvRegTxMulticast);
np->estats.tx_broadcast += readl(base + NvRegTxBroadcast);
}
+
+ /* update software stats */
+ NV_DRIVER_STAT_UPDATE_TOTAL(&np->stat_rx_packets);
+ NV_DRIVER_STAT_UPDATE_TOTAL(&np->stat_rx_bytes);
+ NV_DRIVER_STAT_UPDATE_TOTAL(&np->stat_rx_missed_errors);
+
+ NV_DRIVER_STAT_UPDATE_TOTAL(&np->stat_tx_packets);
+ NV_DRIVER_STAT_UPDATE_TOTAL(&np->stat_tx_bytes);
+ NV_DRIVER_STAT_UPDATE_TOTAL(&np->stat_tx_dropped);
}

/*
- * nv_get_stats: dev->get_stats function
+ * nv_get_stats64: dev->ndo_get_stats64 function
* Get latest stats value from the nic.
* Called with read_lock(&dev_base_lock) held for read -
* only synchronized against unregister_netdevice.
*/
-static struct net_device_stats *nv_get_stats(struct net_device *dev)
+static struct rtnl_link_stats64*
+nv_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *storage)
+ __acquires(&netdev_priv(dev)->stats_lock)
+ __releases(&netdev_priv(dev)->stats_lock)
{
struct fe_priv *np = netdev_priv(dev);

/* If the nic supports hw counters then retrieve latest values */
- if (np->driver_data & (DEV_HAS_STATISTICS_V1|DEV_HAS_STATISTICS_V2|DEV_HAS_STATISTICS_V3)) {
- nv_get_hw_stats(dev);
+ if (np->driver_data & DEV_HAS_STATISTICS_V123) {
+ spin_lock_bh(&np->stats_lock);
+
+ nv_update_stats(dev);

/*
* Note: because HW stats are not always available and
@@ -1721,17 +1775,40 @@ static struct net_device_stats *nv_get_stats(struct net_device *dev)
* packet (Ethernet FCS CRC).
*/

- /* copy to net_device stats */
- dev->stats.tx_fifo_errors = np->estats.tx_fifo_errors;
- dev->stats.tx_carrier_errors = np->estats.tx_carrier_errors;
- dev->stats.rx_crc_errors = np->estats.rx_crc_errors;
- dev->stats.rx_over_errors = np->estats.rx_over_errors;
- dev->stats.rx_fifo_errors = np->estats.rx_drop_frame;
- dev->stats.rx_errors = np->estats.rx_errors_total;
- dev->stats.tx_errors = np->estats.tx_errors_total;
- }
-
- return &dev->stats;
+ /* generic stats */
+ storage->rx_packets = NV_DRIVER_STAT_GET_TOTAL(
+ &np->stat_rx_packets);
+ storage->tx_packets = NV_DRIVER_STAT_GET_TOTAL(
+ &np->stat_tx_packets);
+ storage->rx_bytes = NV_DRIVER_STAT_GET_TOTAL(
+ &np->stat_rx_bytes);
+ storage->tx_bytes = NV_DRIVER_STAT_GET_TOTAL(
+ &np->stat_tx_bytes);
+ storage->rx_errors = np->estats.rx_errors_total;
+ storage->tx_errors = np->estats.tx_errors_total;
+ storage->tx_dropped = NV_DRIVER_STAT_GET_TOTAL(
+ &np->stat_tx_dropped);
+
+ /* meaningful only when NIC supports stats v3 */
+ storage->multicast = np->estats.rx_multicast;
+
+ /* detailed rx_errors */
+ storage->rx_length_errors = np->estats.rx_length_error;
+ storage->rx_over_errors = np->estats.rx_over_errors;
+ storage->rx_crc_errors = np->estats.rx_crc_errors;
+ storage->rx_frame_errors = np->estats.rx_frame_align_error;
+ storage->rx_fifo_errors = np->estats.rx_drop_frame;
+ storage->rx_missed_errors = NV_DRIVER_STAT_GET_TOTAL(
+ &np->stat_rx_missed_errors);
+
+ /* detailed tx_errors */
+ storage->tx_carrier_errors = np->estats.tx_carrier_errors;
+ storage->tx_fifo_errors = np->estats.tx_fifo_errors;
+
+ spin_unlock_bh(&np->stats_lock);
+ }
+
+ return storage;
}

/*
@@ -1933,7 +2010,7 @@ static void nv_drain_tx(struct net_device *dev)
np->tx_ring.ex[i].buflow = 0;
}
if (nv_release_txskb(np, &np->tx_skb[i]))
- dev->stats.tx_dropped++;
+ NV_DRIVER_STAT_ATOMIC_INC(&np->stat_tx_dropped);
np->tx_skb[i].dma = 0;
np->tx_skb[i].dma_len = 0;
np->tx_skb[i].dma_single = 0;
@@ -2390,11 +2467,15 @@ static int nv_tx_done(struct net_device *dev, int limit)
if (np->desc_ver == DESC_VER_1) {
if (flags & NV_TX_LASTPACKET) {
if (flags & NV_TX_ERROR) {
- if ((flags & NV_TX_RETRYERROR) && !(flags & NV_TX_RETRYCOUNT_MASK))
+ if ((flags & NV_TX_RETRYERROR)
+ && !(flags & NV_TX_RETRYCOUNT_MASK))
nv_legacybackoff_reseed(dev);
} else {
- dev->stats.tx_packets++;
- dev->stats.tx_bytes += np->get_tx_ctx->skb->len;
+ NV_DRIVER_STAT_ATOMIC_INC(
+ &np->stat_tx_packets);
+ NV_DRIVER_STAT_ATOMIC_ADD(
+ &np->stat_tx_bytes,
+ np->get_tx_ctx->skb->len);
}
dev_kfree_skb_any(np->get_tx_ctx->skb);
np->get_tx_ctx->skb = NULL;
@@ -2403,11 +2484,15 @@ static int nv_tx_done(struct net_device *dev, int limit)
} else {
if (flags & NV_TX2_LASTPACKET) {
if (flags & NV_TX2_ERROR) {
- if ((flags & NV_TX2_RETRYERROR) && !(flags & NV_TX2_RETRYCOUNT_MASK))
+ if ((flags & NV_TX2_RETRYERROR)
+ && !(flags & NV_TX2_RETRYCOUNT_MASK))
nv_legacybackoff_reseed(dev);
} else {
- dev->stats.tx_packets++;
- dev->stats.tx_bytes += np->get_tx_ctx->skb->len;
+ NV_DRIVER_STAT_ATOMIC_INC(
+ &np->stat_tx_packets);
+ NV_DRIVER_STAT_ATOMIC_ADD(
+ &np->stat_tx_bytes,
+ np->get_tx_ctx->skb->len);
}
dev_kfree_skb_any(np->get_tx_ctx->skb);
np->get_tx_ctx->skb = NULL;
@@ -2441,15 +2526,18 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit)

if (flags & NV_TX2_LASTPACKET) {
if (flags & NV_TX2_ERROR) {
- if ((flags & NV_TX2_RETRYERROR) && !(flags & NV_TX2_RETRYCOUNT_MASK)) {
+ if ((flags & NV_TX2_RETRYERROR)
+ && !(flags & NV_TX2_RETRYCOUNT_MASK)) {
if (np->driver_data & DEV_HAS_GEAR_MODE)
nv_gear_backoff_reseed(dev);
else
nv_legacybackoff_reseed(dev);
}
} else {
- dev->stats.tx_packets++;
- dev->stats.tx_bytes += np->get_tx_ctx->skb->len;
+ NV_DRIVER_STAT_ATOMIC_INC(&np->stat_tx_packets);
+ NV_DRIVER_STAT_ATOMIC_ADD(
+ &np->stat_tx_bytes,
+ np->get_tx_ctx->skb->len);
}

dev_kfree_skb_any(np->get_tx_ctx->skb);
@@ -2663,7 +2751,7 @@ static int nv_rx_process(struct net_device *dev, int limit)
/* the rest are hard errors */
else {
if (flags & NV_RX_MISSEDFRAME)
- dev->stats.rx_missed_errors++;
+ NV_DRIVER_STAT_ATOMIC_INC(&np->stat_rx_missed_errors);
dev_kfree_skb(skb);
goto next_pkt;
}
@@ -2706,8 +2794,8 @@ static int nv_rx_process(struct net_device *dev, int limit)
skb_put(skb, len);
skb->protocol = eth_type_trans(skb, dev);
napi_gro_receive(&np->napi, skb);
- dev->stats.rx_packets++;
- dev->stats.rx_bytes += len;
+ NV_DRIVER_STAT_ATOMIC_INC(&np->stat_rx_packets);
+ NV_DRIVER_STAT_ATOMIC_ADD(&np->stat_rx_bytes, len);
next_pkt:
if (unlikely(np->get_rx.orig++ == np->last_rx.orig))
np->get_rx.orig = np->first_rx.orig;
@@ -2790,8 +2878,8 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit)
__vlan_hwaccel_put_tag(skb, vid);
}
napi_gro_receive(&np->napi, skb);
- dev->stats.rx_packets++;
- dev->stats.rx_bytes += len;
+ NV_DRIVER_STAT_ATOMIC_INC(&np->stat_rx_packets);
+ NV_DRIVER_STAT_ATOMIC_ADD(&np->stat_rx_bytes, len);
} else {
dev_kfree_skb(skb);
}
@@ -4000,11 +4088,18 @@ static void nv_poll_controller(struct net_device *dev)
#endif

static void nv_do_stats_poll(unsigned long data)
+ __acquires(&netdev_priv(dev)->stats_lock)
+ __releases(&netdev_priv(dev)->stats_lock)
{
struct net_device *dev = (struct net_device *) data;
struct fe_priv *np = netdev_priv(dev);

- nv_get_hw_stats(dev);
+ /* If lock is currently taken, the stats are being refreshed
+ * and hence fresh enough */
+ if (spin_trylock(&np->stats_lock)) {
+ nv_update_stats(dev);
+ spin_unlock(&np->stats_lock);
+ }

if (!np->in_shutdown)
mod_timer(&np->stats_poll,
@@ -4711,14 +4806,18 @@ static int nv_get_sset_count(struct net_device *dev, int sset)
}
}

-static void nv_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *estats, u64 *buffer)
+static void nv_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *estats, u64 *buffer)
+ __acquires(&netdev_priv(dev)->stats_lock)
+ __releases(&netdev_priv(dev)->stats_lock)
{
struct fe_priv *np = netdev_priv(dev);

- /* update stats */
- nv_get_hw_stats(dev);
-
- memcpy(buffer, &np->estats, nv_get_sset_count(dev, ETH_SS_STATS)*sizeof(u64));
+ spin_lock_bh(&np->stats_lock);
+ nv_update_stats(dev);
+ memcpy(buffer, &np->estats,
+ nv_get_sset_count(dev, ETH_SS_STATS)*sizeof(u64));
+ spin_unlock_bh(&np->stats_lock);
}

static int nv_link_test(struct net_device *dev)
@@ -5362,7 +5461,7 @@ static int nv_close(struct net_device *dev)
static const struct net_device_ops nv_netdev_ops = {
.ndo_open = nv_open,
.ndo_stop = nv_close,
- .ndo_get_stats = nv_get_stats,
+ .ndo_get_stats64 = nv_get_stats64,
.ndo_start_xmit = nv_start_xmit,
.ndo_tx_timeout = nv_tx_timeout,
.ndo_change_mtu = nv_change_mtu,
@@ -5379,7 +5478,7 @@ static const struct net_device_ops nv_netdev_ops = {
static const struct net_device_ops nv_netdev_ops_optimized = {
.ndo_open = nv_open,
.ndo_stop = nv_close,
- .ndo_get_stats = nv_get_stats,
+ .ndo_get_stats64 = nv_get_stats64,
.ndo_start_xmit = nv_start_xmit_optimized,
.ndo_tx_timeout = nv_tx_timeout,
.ndo_change_mtu = nv_change_mtu,
@@ -5418,6 +5517,7 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
np->dev = dev;
np->pci_dev = pci_dev;
spin_lock_init(&np->lock);
+ spin_lock_init(&np->stats_lock);
SET_NETDEV_DEV(dev, &pci_dev->dev);

init_timer(&np->oom_kick);
--
1.7.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/