forcedeth: stats & debug enhancements
Subsystems (3)
PATCH v2 1/10 forcedeth: fix ifconfig stats on hardware without extended stats support
In reply to David DecotignyThis change makes sure that tx_packets/rx_bytes ifconfig counters are updated even on NICs that don't provide hardware support for these stats. In that case, they are updated in software.
Related commit: "forcedeth: Improve stats counters" (0bdfea8ba8)
--- drivers/net/ethernet/nvidia/forcedeth.c | 34 ++++++++++++++++++++++++++---- 1 files changed, 29 insertions(+), 5 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +29 -5
@@ -90,6 +90,7 @@#define DEV_HAS_STATISTICS_V2 0x0000400/* device supports hw statistics version 2 */ #define DEV_HAS_STATISTICS_V3 0x0000800/* device supports hw statistics version 3 */ #define DEV_HAS_STATISTICS_V12 0x0000600/* device supports hw statistics version 1 and 2 */ +#define DEV_HAS_STATISTICS_V23 0x0000c00/* device supports hw statistics version 2 and 3 */ #define DEV_HAS_STATISTICS_V123 0x0000e00/* device supports hw statistics version 1, 2, and 3 */ #define DEV_HAS_TEST_EXTENDED 0x0001000/* device supports extended diagnostic test */ #define DEV_HAS_MGMT_UNIT 0x0002000/* device supports management unit */
@@ -1703,12 +1704,19 @@ static struct net_device_stats *nv_get_stats(struct net_device *dev)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 )) { +if (np->driver_data &DEV_HAS_STATISTICS_V123 ) { +/* query hardware */ nv_get_hw_stats (dev);/* copy to net_device stats */ - dev->stats.tx_packets = np->estats.tx_packets; - dev->stats.rx_bytes = np->estats.rx_bytes; + +if (np->driver_data &DEV_HAS_STATISTICS_V23 ) { +/* When HW stats are available for following +* stats, we use them. Otherwise they are +* updated by software. */ + dev->stats.tx_packets = np->estats.tx_packets; + dev->stats.rx_bytes = np->estats.rx_bytes; + } dev->stats.tx_bytes = np->estats.tx_bytes; dev->stats.tx_fifo_errors = np->estats.tx_fifo_errors; dev->stats.tx_carrier_errors = np->estats.tx_carrier_errors;
@@ -2378,8 +2386,12 @@ 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 if (unlikely (!(np->driver_data + &DEV_HAS_STATISTICS_V23 ))) { + dev->stats.tx_packets++; }dev_kfree_skb_any (np->get_tx_ctx->skb); np->get_tx_ctx->skb =NULL ;
@@ -2388,8 +2400,12 @@ 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 if (unlikely (!(np->driver_data + &DEV_HAS_STATISTICS_V23 ))) { + dev->stats.tx_packets++; }dev_kfree_skb_any (np->get_tx_ctx->skb); np->get_tx_ctx->skb =NULL ;
@@ -2429,6 +2445,9 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit)else nv_legacybackoff_reseed (dev); } + }else if (unlikely (!(np->driver_data + &DEV_HAS_STATISTICS_V23 ))) { + dev->stats.tx_packets++; }dev_kfree_skb_any (np->get_tx_ctx->skb);
@@ -2678,6 +2697,8 @@ static int nv_rx_process(struct net_device *dev, int limit) skb->protocol =eth_type_trans (skb, dev);napi_gro_receive (&np->napi, skb); dev->stats.rx_packets++; +if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) + dev->stats.rx_bytes += len; next_pkt:if (unlikely (np->get_rx.orig++ == np->last_rx.orig)) np->get_rx.orig = np->first_rx.orig;
@@ -2761,6 +2782,9 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit) }napi_gro_receive (&np->napi, skb); dev->stats.rx_packets++; +if (unlikely (!(np->driver_data + &DEV_HAS_STATISTICS_V23 ))) + dev->stats.rx_bytes += len; }else {dev_kfree_skb (skb); }
Signature · 1 line
1.7.3.1
PATCH v2 2/10 forcedeth: Add messages to indicate using MSI or MSI-X
In reply to David DecotignyFrom: Mike Ditto <[email protected]>
This adds a few debug messages to indicate whether PCIe interrupts are signaled with MSI or MSI-X.
--- drivers/net/ethernet/nvidia/forcedeth.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +2 -0
@@ -3735,6 +3735,7 @@ static int nv_request_irq(struct net_device *dev, int intr_test)writel (0 , base + NvRegMSIXMap0);writel (0 , base + NvRegMSIXMap1); } +netdev_info (dev,"MSI-X enabled\n" ); } }if (ret !=0 && np->msi_flags &NV_MSI_CAPABLE ) {
@@ -3756,6 +3757,7 @@ static int nv_request_irq(struct net_device *dev, int intr_test)writel (0 , base + NvRegMSIMap1);/* enable msi vector 0 */ writel (NVREG_MSI_VECTOR_0_ENABLED , base + NvRegMSIIrqMask); +netdev_info (dev,"MSI enabled\n" ); } }if (ret !=0 ) {
Signature · 1 line
1.7.3.1
PATCH v2 3/10 forcedeth: allow to silence "TX timeout" debug messages
In reply to David DecotignyFrom: Sameer Nanda <[email protected]>
This adds a new module parameter "debug_tx_timeout" to silence most debug messages in case of TX timeout. These messages don't provide a signal/noise ratio high enough for production systems and, with ~30kB logged each time, they tend to add to a cascade effect if the system is already under stress (memory pressure, disk, etc.).
By default, the parameter is clear, meaning that only a single warning will be reported.
--- drivers/net/ethernet/nvidia/forcedeth.c | 98 ++++++++++++++++++------------- 1 files changed, 57 insertions(+), 41 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +57 -41
@@ -893,6 +893,11 @@ enum {static int dma_64bit =NV_DMA_64BIT_ENABLED ;/* +* Debug output control for tx_timeout +*/ +static bool debug_tx_timeout = false; + +/* * Crossover Detection * Realtek 8201 phy + some OEM boards do not work properly. */
@@ -2480,56 +2485,64 @@ static void nv_tx_timeout(struct net_device *dev)u32 status;union ring_type put_tx;int saved_tx_limit; -int i;if (np->msi_flags &NV_MSI_X_ENABLED ) status =readl (base + NvRegMSIXIrqStatus) &NVREG_IRQSTAT_MASK ;else status =readl (base + NvRegIrqStatus) &NVREG_IRQSTAT_MASK ; -netdev_info (dev,"Got tx_timeout. irq: %08x\n" , status); +netdev_warn (dev,"Got tx_timeout. irq status: %08x\n" , status); -netdev_info (dev,"Ring at %lx\n" , (unsigned long )np->ring_addr); -netdev_info (dev,"Dumping tx registers\n" ); -for (i =0 ; i <= np->register_size; i +=32 ) { -netdev_info (dev, -"%3x: %08x %08x %08x %08x %08x %08x %08x %08x\n" , - i, -readl (base + i +0 ),readl (base + i +4 ), -readl (base + i +8 ),readl (base + i +12 ), -readl (base + i +16 ),readl (base + i +20 ), -readl (base + i +24 ),readl (base + i +28 )); - } -netdev_info (dev,"Dumping tx ring\n" ); -for (i =0 ; i < np->tx_ring_size; i +=4 ) { -if (!nv_optimized (np)) { -netdev_info (dev, -"%03x: %08x %08x // %08x %08x // %08x %08x // %08x %08x\n" , - i, -le32_to_cpu (np->tx_ring.orig[i].buf), -le32_to_cpu (np->tx_ring.orig[i].flaglen), -le32_to_cpu (np->tx_ring.orig[i+1 ].buf), -le32_to_cpu (np->tx_ring.orig[i+1 ].flaglen), -le32_to_cpu (np->tx_ring.orig[i+2 ].buf), -le32_to_cpu (np->tx_ring.orig[i+2 ].flaglen), -le32_to_cpu (np->tx_ring.orig[i+3 ].buf), -le32_to_cpu (np->tx_ring.orig[i+3 ].flaglen)); - }else { +if (unlikely (debug_tx_timeout)) { +int i; + +netdev_info (dev,"Ring at %lx\n" , (unsigned long )np->ring_addr); +netdev_info (dev,"Dumping tx registers\n" ); +for (i =0 ; i <= np->register_size; i +=32 ) {netdev_info (dev, -"%03x: %08x %08x %08x // %08x %08x %08x // %08x %08x %08x // %08x %08x %08x\n" , +"%3x: %08x %08x %08x %08x " +"%08x %08x %08x %08x\n" , i, -le32_to_cpu (np->tx_ring.ex[i].bufhigh), -le32_to_cpu (np->tx_ring.ex[i].buflow), -le32_to_cpu (np->tx_ring.ex[i].flaglen), -le32_to_cpu (np->tx_ring.ex[i+1 ].bufhigh), -le32_to_cpu (np->tx_ring.ex[i+1 ].buflow), -le32_to_cpu (np->tx_ring.ex[i+1 ].flaglen), -le32_to_cpu (np->tx_ring.ex[i+2 ].bufhigh), -le32_to_cpu (np->tx_ring.ex[i+2 ].buflow), -le32_to_cpu (np->tx_ring.ex[i+2 ].flaglen), -le32_to_cpu (np->tx_ring.ex[i+3 ].bufhigh), -le32_to_cpu (np->tx_ring.ex[i+3 ].buflow), -le32_to_cpu (np->tx_ring.ex[i+3 ].flaglen)); +readl (base + i +0 ),readl (base + i +4 ), +readl (base + i +8 ),readl (base + i +12 ), +readl (base + i +16 ),readl (base + i +20 ), +readl (base + i +24 ),readl (base + i +28 )); + } +netdev_info (dev,"Dumping tx ring\n" ); +for (i =0 ; i < np->tx_ring_size; i +=4 ) { +if (!nv_optimized (np)) { +netdev_info (dev, +"%03x: %08x %08x // %08x %08x " +"// %08x %08x // %08x %08x\n" , + i, +le32_to_cpu (np->tx_ring.orig[i].buf), +le32_to_cpu (np->tx_ring.orig[i].flaglen), +le32_to_cpu (np->tx_ring.orig[i+1 ].buf), +le32_to_cpu (np->tx_ring.orig[i+1 ].flaglen), +le32_to_cpu (np->tx_ring.orig[i+2 ].buf), +le32_to_cpu (np->tx_ring.orig[i+2 ].flaglen), +le32_to_cpu (np->tx_ring.orig[i+3 ].buf), +le32_to_cpu (np->tx_ring.orig[i+3 ].flaglen)); + }else { +netdev_info (dev, +"%03x: %08x %08x %08x " +"// %08x %08x %08x " +"// %08x %08x %08x " +"// %08x %08x %08x\n" , + i, +le32_to_cpu (np->tx_ring.ex[i].bufhigh), +le32_to_cpu (np->tx_ring.ex[i].buflow), +le32_to_cpu (np->tx_ring.ex[i].flaglen), +le32_to_cpu (np->tx_ring.ex[i+1 ].bufhigh), +le32_to_cpu (np->tx_ring.ex[i+1 ].buflow), +le32_to_cpu (np->tx_ring.ex[i+1 ].flaglen), +le32_to_cpu (np->tx_ring.ex[i+2 ].bufhigh), +le32_to_cpu (np->tx_ring.ex[i+2 ].buflow), +le32_to_cpu (np->tx_ring.ex[i+2 ].flaglen), +le32_to_cpu (np->tx_ring.ex[i+3 ].bufhigh), +le32_to_cpu (np->tx_ring.ex[i+3 ].buflow), +le32_to_cpu (np->tx_ring.ex[i+3 ].flaglen)); + } } }
@@ -6008,6 +6021,9 @@ module_param(phy_cross, int, 0);MODULE_PARM_DESC (phy_cross,"Phy crossover detection for Realtek 8201 phy is enabled by setting to 1 and disabled by setting to 0." );module_param (phy_power_down, int,0 );MODULE_PARM_DESC (phy_power_down,"Power down phy and disable link when interface is down (1), or leave phy powered up (0)." ); +module_param (debug_tx_timeout, bool,0 ); +MODULE_PARM_DESC (debug_tx_timeout, +"Dump tx related registers and ring when tx_timeout happens" );MODULE_AUTHOR ("Manfred Spraul <[email protected]>" );MODULE_DESCRIPTION ("Reverse Engineered nForce ethernet driver" );
Signature · 1 line
1.7.3.1
PATCH v2 4/10 forcedeth: expose module parameters in /sys/module
In reply to David DecotignyIn particular, debug_tx_timeout can be updated at runtime.
--- drivers/net/ethernet/nvidia/forcedeth.c | 18 +++++++++--------- 1 files changed, 9 insertions(+), 9 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +9 -9
@@ -6005,23 +6005,23 @@ static void __exit exit_nic(void)pci_unregister_driver (&driver); } -module_param (max_interrupt_work, int,0 ); +module_param (max_interrupt_work, int,S_IRUGO );MODULE_PARM_DESC (max_interrupt_work,"forcedeth maximum events handled per interrupt" ); -module_param (optimization_mode, int,0 ); +module_param (optimization_mode, int,S_IRUGO );MODULE_PARM_DESC (optimization_mode,"In throughput mode (0), every tx & rx packet will generate an interrupt. In CPU mode (1), interrupts are controlled by a timer. In dynamic mode (2), the mode toggles between throughput and CPU mode based on network load." ); -module_param (poll_interval, int,0 ); +module_param (poll_interval, int,S_IRUGO );MODULE_PARM_DESC (poll_interval,"Interval determines how frequent timer interrupt is generated by [(time_in_micro_secs * 100) / (2^10)]. Min is 0 and Max is 65535." ); -module_param (msi, int,0 ); +module_param (msi, int,S_IRUGO );MODULE_PARM_DESC (msi,"MSI interrupts are enabled by setting to 1 and disabled by setting to 0." ); -module_param (msix, int,0 ); +module_param (msix, int,S_IRUGO );MODULE_PARM_DESC (msix,"MSIX interrupts are enabled by setting to 1 and disabled by setting to 0." ); -module_param (dma_64bit, int,0 ); +module_param (dma_64bit, int,S_IRUGO );MODULE_PARM_DESC (dma_64bit,"High DMA is enabled by setting to 1 and disabled by setting to 0." ); -module_param (phy_cross, int,0 ); +module_param (phy_cross, int,S_IRUGO );MODULE_PARM_DESC (phy_cross,"Phy crossover detection for Realtek 8201 phy is enabled by setting to 1 and disabled by setting to 0." ); -module_param (phy_power_down, int,0 ); +module_param (phy_power_down, int,S_IRUGO );MODULE_PARM_DESC (phy_power_down,"Power down phy and disable link when interface is down (1), or leave phy powered up (0)." ); -module_param (debug_tx_timeout, bool,0 ); +module_param (debug_tx_timeout, bool,S_IRUGO |S_IWUSR );MODULE_PARM_DESC (debug_tx_timeout,"Dump tx related registers and ring when tx_timeout happens" );
Signature · 1 line
1.7.3.1
PATCH v2 5/10 forcedeth: stats for rx_packets based on hardware registers
In reply to David DecotignyUse the hardware registers instead of a software implementation to account for the number of RX packets.
--- drivers/net/ethernet/nvidia/forcedeth.c | 3 +-- 1 files changed, 1 insertions(+), 2 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +1 -2
@@ -1722,6 +1722,7 @@ static struct net_device_stats *nv_get_stats(struct net_device *dev) dev->stats.tx_packets = np->estats.tx_packets; dev->stats.rx_bytes = np->estats.rx_bytes; } + dev->stats.rx_packets = np->estats.rx_packets; dev->stats.tx_bytes = np->estats.tx_bytes; dev->stats.tx_fifo_errors = np->estats.tx_fifo_errors; dev->stats.tx_carrier_errors = np->estats.tx_carrier_errors;
@@ -2709,7 +2710,6 @@ 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++;if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) dev->stats.rx_bytes += len; next_pkt:
@@ -2794,7 +2794,6 @@ 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++;if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) dev->stats.rx_bytes += len;
Signature · 1 line
1.7.3.1
PATCH v2 6/10 forcedeth: implement ndo_get_stats64() API
In reply to David DecotignyThis 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)
--- drivers/net/ethernet/nvidia/forcedeth.c | 155 +++++++++++++++++++++++-------- 1 files changed, 118 insertions(+), 37 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +118 -37
@@ -693,6 +693,21 @@ 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
@@ -737,6 +752,12 @@ 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 */
@@ -746,9 +767,10 @@ 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;
@@ -799,6 +821,10 @@ struct fe_priv {u32 nic_poll_irq;int rx_ring_size; +/* RX software stats */ +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); */
@@ -821,6 +847,10 @@ 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_dropped; +/* msi/msi-x fields */ u32 msi_flags;struct msix_entry msi_x_entry[NV_MSI_X_MAX_VECTORS ];
@@ -1636,11 +1666,19 @@ 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);
@@ -1696,44 +1734,75 @@ 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_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_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_V123 ) { -/* query hardware */ -nv_get_hw_stats (dev); +spin_lock_bh (&np->stats_lock); -/* copy to net_device stats */ +nv_update_stats (dev); + +/* generic stats */ if (np->driver_data &DEV_HAS_STATISTICS_V23 ) {/* When HW stats are available for following * stats, we use them. Otherwise they are * updated by software. */ - dev->stats.tx_packets = np->estats.tx_packets; - dev->stats.rx_bytes = np->estats.rx_bytes; + storage->tx_packets = np->estats.tx_packets; + storage->rx_bytes = np->estats.rx_bytes; + }else { + storage->tx_packets =NV_DRIVER_STAT_GET_TOTAL ( + &np->stat_tx_packets); + storage->rx_bytes =NV_DRIVER_STAT_GET_TOTAL ( + &np->stat_rx_bytes); } - dev->stats.rx_packets = np->estats.rx_packets; - dev->stats.tx_bytes = np->estats.tx_bytes; - 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; + storage->rx_packets = np->estats.rx_packets; + storage->tx_bytes = np->estats.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; }/*
@@ -1935,7 +2004,7 @@ 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 ;
@@ -2397,7 +2466,7 @@ static int nv_tx_done(struct net_device *dev, int limit)nv_legacybackoff_reseed (dev); }else if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) { - dev->stats.tx_packets++; +NV_DRIVER_STAT_ATOMIC_INC (&np->stat_tx_packets); }dev_kfree_skb_any (np->get_tx_ctx->skb); np->get_tx_ctx->skb =NULL ;
@@ -2411,7 +2480,7 @@ static int nv_tx_done(struct net_device *dev, int limit)nv_legacybackoff_reseed (dev); }else if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) { - dev->stats.tx_packets++; +NV_DRIVER_STAT_ATOMIC_INC (&np->stat_tx_packets); }dev_kfree_skb_any (np->get_tx_ctx->skb); np->get_tx_ctx->skb =NULL ;
@@ -2453,7 +2522,7 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit) } }else if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) { - dev->stats.tx_packets++; +NV_DRIVER_STAT_ATOMIC_INC (&np->stat_tx_packets); }dev_kfree_skb_any (np->get_tx_ctx->skb);
@@ -2667,7 +2736,7 @@ 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; }
@@ -2711,7 +2780,7 @@ static int nv_rx_process(struct net_device *dev, int limit) skb->protocol =eth_type_trans (skb, dev);napi_gro_receive (&np->napi, skb);if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) - dev->stats.rx_bytes += len; +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;
@@ -2796,7 +2865,7 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit)napi_gro_receive (&np->napi, skb);if (unlikely (!(np->driver_data &DEV_HAS_STATISTICS_V23 ))) - dev->stats.rx_bytes += len; +NV_DRIVER_STAT_ATOMIC_ADD (&np->stat_rx_bytes, len); }else {dev_kfree_skb (skb); }
@@ -3924,11 +3993,18 @@ 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,
@@ -4573,14 +4649,18 @@ 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)
@@ -5218,7 +5298,7 @@ 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,
@@ -5235,7 +5315,7 @@ 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,
@@ -5274,6 +5354,7 @@ 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);
Signature · 1 line
1.7.3.1
PATCH v2 8/10 forcedeth: new ethtool stat counter for TX timeouts
In reply to David DecotignyThis change publishes a new ethtool stats: tx_timeout that counts the number of times the tx_timeout callback was triggered.
--- drivers/net/ethernet/nvidia/forcedeth.c | 6 ++++++ 1 files changed, 6 insertions(+), 0 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +6 -0
@@ -634,6 +634,7 @@ static const struct nv_ethtool_str nv_estats_str[] = { { "rx_packets" }, { "rx_errors_total" }, { "tx_errors_total" }, + { "tx_timeout" },/* version 2 stats */ { "tx_deferral" },
@@ -674,6 +675,7 @@ struct nv_ethtool_stats {u64 rx_packets;u64 rx_errors_total;u64 tx_errors_total; +u64 tx_timeout;/* version 2 stats */ u64 tx_deferral;
@@ -851,6 +853,7 @@ struct fe_priv {/* TX software stats */ struct nv_driver_stat stat_tx_packets;/* not always available in HW */ struct nv_driver_stat stat_tx_dropped; +atomic_t stat_tx_timeout;/* TX timeouts since last nv_update_stats */ /* msi/msi-x fields */ u32 msi_flags;
@@ -1743,6 +1746,7 @@ static void nv_update_stats(struct net_device *dev)NV_DRIVER_STAT_UPDATE_TOTAL (&np->stat_tx_packets);NV_DRIVER_STAT_UPDATE_TOTAL (&np->stat_tx_dropped); + np->estats.tx_timeout +=atomic_xchg (&np->stat_tx_timeout,0 ); }/*
@@ -2624,6 +2628,8 @@ static void nv_tx_timeout(struct net_device *dev) } } +atomic_inc (&np->stat_tx_timeout); +spin_lock_irq (&np->lock);/* 1) stop tx engine */
Signature · 1 line
1.7.3.1
PATCH v2 9/10 forcedeth: stats updated with a deferrable timer
In reply to David DecotignyMark stats timer as deferrable: punctuality in waking the stats timer callback doesn't matter much, as it is responsible only to avoid integer wraparound.
We need at least 1 other timer to fire within 17s (fully loaded 1Gbps) to avoid wrap-arounds. Desired period is still 10s.
--- drivers/net/ethernet/nvidia/forcedeth.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +1 -1
@@ -5377,7 +5377,7 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_iinit_timer (&np->nic_poll); np->nic_poll.data = (unsigned long ) dev; np->nic_poll.function = nv_do_nic_poll;/* timer handler */ -init_timer (&np->stats_poll); +init_timer_deferrable (&np->stats_poll); np->stats_poll.data = (unsigned long ) dev; np->stats_poll.function = nv_do_stats_poll;/* timer handler */
Signature · 1 line
1.7.3.1
PATCH v2 10/10 forcedeth: whitespace/indentation fixes
In reply to David Decotigny--- drivers/net/ethernet/nvidia/forcedeth.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +1 -1
@@ -65,7 +65,7 @@#include <linux/slab.h> #include <linux/uaccess.h> #include <linux/prefetch.h> -#include <linux/io.h> +#include <linux/io.h> #include <asm/irq.h> #include <asm/system.h>
Signature · 1 line
1.7.3.1
PATCH v2 7/10 forcedeth: account for dropped RX frames
In reply to David DecotignyThis adds the stats counter for dropped RX frames.
--- drivers/net/ethernet/nvidia/forcedeth.c | 12 ++++++++++-- 1 files changed, 10 insertions(+), 2 deletions(-)
drivers/net/ethernet/nvidia/forcedeth.c +10 -2
@@ -824,6 +824,7 @@ struct fe_priv {/* RX software stats */ struct nv_driver_stat stat_rx_bytes;/* not always available in HW */ struct nv_driver_stat stat_rx_missed_errors; +struct nv_driver_stat stat_rx_dropped;/* media detection workaround. * Locking: Within irq hander or disable_irq+spin_lock(&np->lock);
@@ -1738,6 +1739,7 @@ static void nv_update_stats(struct net_device *dev)/* update software stats */ 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_rx_dropped);NV_DRIVER_STAT_UPDATE_TOTAL (&np->stat_tx_packets);NV_DRIVER_STAT_UPDATE_TOTAL (&np->stat_tx_dropped);
@@ -1780,6 +1782,8 @@ nv_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *storage) storage->tx_bytes = np->estats.tx_bytes; storage->rx_errors = np->estats.rx_errors_total; storage->tx_errors = np->estats.tx_errors_total; + storage->rx_dropped =NV_DRIVER_STAT_GET_TOTAL ( + &np->stat_rx_dropped); storage->tx_dropped =NV_DRIVER_STAT_GET_TOTAL ( &np->stat_tx_dropped);
@@ -1835,8 +1839,10 @@ static int nv_alloc_rx(struct net_device *dev) np->put_rx.orig = np->first_rx.orig;if (unlikely (np->put_rx_ctx++ == np->last_rx_ctx)) np->put_rx_ctx = np->first_rx_ctx; - }else + }else { +NV_DRIVER_STAT_ATOMIC_INC (&np->stat_rx_dropped);return 1 ; + } }return 0 ; }
@@ -1867,8 +1873,10 @@ static int nv_alloc_rx_optimized(struct net_device *dev) np->put_rx.ex = np->first_rx.ex;if (unlikely (np->put_rx_ctx++ == np->last_rx_ctx)) np->put_rx_ctx = np->first_rx_ctx; - }else + }else { +NV_DRIVER_STAT_ATOMIC_INC (&np->stat_rx_dropped);return 1 ; + } }return 0 ; }
Signature · 1 line
1.7.3.1
v2 cover forcedeth: stats & debug enhancements
These changes implement the ndo_get_stats64 API and add a few more stats and debugging features for forcedeth. They also ensure that stats updates are correct in SMP systems, 32 or 64-bits.
Changes since v1:
- patch 1/10 is the same as
http://patchwork.ozlabs.org/patch/125017/ (targetting net)
- other patches updated to take patch 1/10 into account
- various commit message updates
Tested:
~150Mbps incoming TCP, ethtool -S in a loop, x86_64 16-way:
tx_bytes: 1413863329
rx_packets: 38918872
tx_packets: 19828148
rx_bytes: 57818685991############################################
# Patch Set Summary:
David Decotigny (8):
forcedeth: fix ifconfig stats on hardware without extended stats
support
forcedeth: expose module parameters in /sys/module
forcedeth: stats for rx_packets based on hardware registers
forcedeth: implement ndo_get_stats64() API
forcedeth: account for dropped RX frames
forcedeth: new ethtool stat counter for TX timeouts
forcedeth: stats updated with a deferrable timer
forcedeth: whitespace/indentation fixes
Mike Ditto (1):
forcedeth: Add messages to indicate using MSI or MSI-X
Sameer Nanda (1):
forcedeth: allow to silence "TX timeout" debug messages
drivers/net/ethernet/nvidia/forcedeth.c | 314 ++++++++++++++++++++++--------- 1 files changed, 225 insertions(+), 89 deletions(-)
Signature · 1 line
1.7.3.1