If HW supports multiqueues, there are frequent cacheline ping pongs
on some driver statistic vars, for example, normal_irq_n, tx_pkt_n
and so on. What's more, frequent cacheline ping pongs on normal_irq_n
happens in ISR, this make the situation worse.
Use pcpu statistics where necessary to remove cacheline ping pongs
as much as possible to make multiqueue operations faster. Those stats
vars which are not frequently updated are kept as is.
Signed-off-by: Jisheng Zhang <[email protected]>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 45 ++---
.../net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 9 +-
.../net/ethernet/stmicro/stmmac/dwmac4_lib.c | 19 +-
.../net/ethernet/stmicro/stmmac/dwmac_lib.c | 11 +-
.../ethernet/stmicro/stmmac/dwxgmac2_dma.c | 11 +-
.../ethernet/stmicro/stmmac/stmmac_ethtool.c | 87 +++++----
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 166 ++++++++++--------
7 files changed, 193 insertions(+), 155 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 1cb8be45330d..ec212528b9df 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -59,20 +59,42 @@
/* #define FRAME_FILTER_DEBUG */
struct stmmac_txq_stats {
- struct u64_stats_sync syncp;
u64 tx_pkt_n;
u64 tx_normal_irq_n;
};
struct stmmac_rxq_stats {
+ u64 rx_pkt_n;
+ u64 rx_normal_irq_n;
+};
+
+struct stmmac_pcpu_stats {
struct u64_stats_sync syncp;
+ /* per queue statistics */
+ struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
+ struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
+ /* device stats */
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
+ /* Tx/Rx IRQ Events */
+ u64 tx_pkt_n;
u64 rx_pkt_n;
+ u64 normal_irq_n;
u64 rx_normal_irq_n;
+ u64 napi_poll;
+ u64 tx_normal_irq_n;
+ u64 tx_clean;
+ u64 tx_set_ic_bit;
+ /* TSO */
+ u64 tx_tso_frames;
+ u64 tx_tso_nfrags;
};
/* Extra statistic and debug information exposed by ethtool */
struct stmmac_extra_stats {
- struct u64_stats_sync syncp ____cacheline_aligned;
+ struct stmmac_pcpu_stats __percpu *pstats;
/* Transmit errors */
unsigned long tx_underflow;
unsigned long tx_carrier;
@@ -117,14 +139,6 @@ struct stmmac_extra_stats {
/* Tx/Rx IRQ Events */
unsigned long rx_early_irq;
unsigned long threshold;
- u64 tx_pkt_n;
- u64 rx_pkt_n;
- u64 normal_irq_n;
- u64 rx_normal_irq_n;
- u64 napi_poll;
- u64 tx_normal_irq_n;
- u64 tx_clean;
- u64 tx_set_ic_bit;
unsigned long irq_receive_pmt_irq_n;
/* MMC info */
unsigned long mmc_tx_irq_n;
@@ -194,23 +208,12 @@ struct stmmac_extra_stats {
unsigned long mtl_rx_fifo_ctrl_active;
unsigned long mac_rx_frame_ctrl_fifo;
unsigned long mac_gmii_rx_proto_engine;
- /* TSO */
- u64 tx_tso_frames;
- u64 tx_tso_nfrags;
/* EST */
unsigned long mtl_est_cgce;
unsigned long mtl_est_hlbs;
unsigned long mtl_est_hlbf;
unsigned long mtl_est_btre;
unsigned long mtl_est_btrlm;
- /* per queue statistics */
- struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
- struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
- /* device stats */
- u64 rx_packets;
- u64 rx_bytes;
- u64 tx_packets;
- u64 tx_bytes;
unsigned long rx_dropped;
unsigned long rx_errors;
unsigned long tx_dropped;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 1571ca0c6616..c0a689529883 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -440,6 +440,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
struct stmmac_extra_stats *x, u32 chan,
u32 dir)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
u32 v;
int ret = 0;
@@ -450,17 +451,17 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
else if (dir == DMA_DIR_TX)
v &= EMAC_INT_MSK_TX;
- u64_stats_update_begin(&priv->xstats.syncp);
+ u64_stats_update_begin(&stats->syncp);
if (v & EMAC_TX_INT) {
ret |= handle_tx;
- x->tx_normal_irq_n++;
+ stats->tx_normal_irq_n++;
}
if (v & EMAC_RX_INT) {
ret |= handle_rx;
- x->rx_normal_irq_n++;
+ stats->rx_normal_irq_n++;
}
- u64_stats_update_end(&priv->xstats.syncp);
+ u64_stats_update_end(&stats->syncp);
if (v & EMAC_TX_DMA_STOP_INT)
x->tx_process_stopped_irq++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index eda4859fa468..bd5fecb101af 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -168,6 +168,7 @@ void dwmac410_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
struct stmmac_extra_stats *x, u32 chan, u32 dir)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs;
u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan));
u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan));
@@ -198,27 +199,23 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
}
}
/* TX/RX NORMAL interrupts */
- u64_stats_update_begin(&priv->xstats.syncp);
+ u64_stats_update_begin(&stats->syncp);
if (likely(intr_status & DMA_CHAN_STATUS_NIS))
- x->normal_irq_n++;
+ stats->normal_irq_n++;
if (likely(intr_status & DMA_CHAN_STATUS_RI))
- x->rx_normal_irq_n++;
+ stats->rx_normal_irq_n++;
if (likely(intr_status & DMA_CHAN_STATUS_TI))
- x->tx_normal_irq_n++;
- u64_stats_update_end(&priv->xstats.syncp);
+ stats->tx_normal_irq_n++;
if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
- u64_stats_update_begin(&priv->xstats.rxq_stats[chan].syncp);
- x->rxq_stats[chan].rx_normal_irq_n++;
- u64_stats_update_end(&priv->xstats.rxq_stats[chan].syncp);
+ stats->rxq_stats[chan].rx_normal_irq_n++;
ret |= handle_rx;
}
if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
- u64_stats_update_begin(&priv->xstats.txq_stats[chan].syncp);
- x->txq_stats[chan].tx_normal_irq_n++;
- u64_stats_update_end(&priv->xstats.txq_stats[chan].syncp);
+ stats->txq_stats[chan].tx_normal_irq_n++;
ret |= handle_tx;
}
+ u64_stats_update_end(&stats->syncp);
if (unlikely(intr_status & DMA_CHAN_STATUS_TBU))
ret |= handle_tx;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 4cef67571d5a..bb938b334313 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -162,6 +162,7 @@ static void show_rx_process_state(unsigned int status)
int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
struct stmmac_extra_stats *x, u32 chan, u32 dir)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
int ret = 0;
/* read the status register (CSR5) */
u32 intr_status = readl(ioaddr + DMA_STATUS);
@@ -209,21 +210,21 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
}
/* TX/RX NORMAL interrupts */
if (likely(intr_status & DMA_STATUS_NIS)) {
- u64_stats_update_begin(&priv->xstats.syncp);
- x->normal_irq_n++;
+ u64_stats_update_begin(&stats->syncp);
+ stats->normal_irq_n++;
if (likely(intr_status & DMA_STATUS_RI)) {
u32 value = readl(ioaddr + DMA_INTR_ENA);
/* to schedule NAPI on real RIE event. */
if (likely(value & DMA_INTR_ENA_RIE)) {
- x->rx_normal_irq_n++;
+ stats->rx_normal_irq_n++;
ret |= handle_rx;
}
}
if (likely(intr_status & DMA_STATUS_TI)) {
- x->tx_normal_irq_n++;
+ stats->tx_normal_irq_n++;
ret |= handle_tx;
}
- u64_stats_update_end(&priv->xstats.syncp);
+ u64_stats_update_end(&stats->syncp);
if (unlikely(intr_status & DMA_STATUS_ERI))
x->rx_early_irq++;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 5997aa0c9b55..052852aeb12d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -337,6 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
struct stmmac_extra_stats *x, u32 chan,
u32 dir)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
int ret = 0;
@@ -364,18 +365,18 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
/* TX/RX NORMAL interrupts */
if (likely(intr_status & XGMAC_NIS)) {
- u64_stats_update_begin(&priv->xstats.syncp);
- x->normal_irq_n++;
+ u64_stats_update_begin(&stats->syncp);
+ stats->normal_irq_n++;
if (likely(intr_status & XGMAC_RI)) {
- x->rx_normal_irq_n++;
+ stats->rx_normal_irq_n++;
ret |= handle_rx;
}
if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
- x->tx_normal_irq_n++;
+ stats->tx_normal_irq_n++;
ret |= handle_tx;
}
- u64_stats_update_end(&priv->xstats.syncp);
+ u64_stats_update_end(&stats->syncp);
}
/* Clear interrupts */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index f9cca2562d60..2f56d0ab3d27 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -164,21 +164,29 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
};
#define STMMAC_STATS_LEN ARRAY_SIZE(stmmac_gstrings_stats)
-static const struct stmmac_stats stmmac_gstrings_stats64[] = {
+struct stmmac_ethtool_pcpu_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int stat_offset;
+};
+
+#define STMMAC_ETHTOOL_PCPU_STAT(m) \
+ { #m, offsetof(struct stmmac_pcpu_stats, m) }
+
+static const struct stmmac_ethtool_pcpu_stats stmmac_gstrings_pcpu_stats[] = {
/* Tx/Rx IRQ Events */
- STMMAC_STAT(tx_pkt_n),
- STMMAC_STAT(rx_pkt_n),
- STMMAC_STAT(normal_irq_n),
- STMMAC_STAT(rx_normal_irq_n),
- STMMAC_STAT(napi_poll),
- STMMAC_STAT(tx_normal_irq_n),
- STMMAC_STAT(tx_clean),
- STMMAC_STAT(tx_set_ic_bit),
+ STMMAC_ETHTOOL_PCPU_STAT(tx_pkt_n),
+ STMMAC_ETHTOOL_PCPU_STAT(rx_pkt_n),
+ STMMAC_ETHTOOL_PCPU_STAT(normal_irq_n),
+ STMMAC_ETHTOOL_PCPU_STAT(rx_normal_irq_n),
+ STMMAC_ETHTOOL_PCPU_STAT(napi_poll),
+ STMMAC_ETHTOOL_PCPU_STAT(tx_normal_irq_n),
+ STMMAC_ETHTOOL_PCPU_STAT(tx_clean),
+ STMMAC_ETHTOOL_PCPU_STAT(tx_set_ic_bit),
/* TSO */
- STMMAC_STAT(tx_tso_frames),
- STMMAC_STAT(tx_tso_nfrags),
+ STMMAC_ETHTOOL_PCPU_STAT(tx_tso_frames),
+ STMMAC_ETHTOOL_PCPU_STAT(tx_tso_nfrags),
};
-#define STMMAC_STATS64_LEN ARRAY_SIZE(stmmac_gstrings_stats64)
+#define STMMAC_PCPU_STATS_LEN ARRAY_SIZE(stmmac_gstrings_pcpu_stats)
/* HW MAC Management counters (if supported) */
#define STMMAC_MMC_STAT(m) \
@@ -541,30 +549,36 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
u32 tx_cnt = priv->plat->tx_queues_to_use;
u32 rx_cnt = priv->plat->rx_queues_to_use;
unsigned int start;
- int q, stat;
+ int q, stat, cpu;
char *p;
+ u64 *pos;
- for (q = 0; q < tx_cnt; q++) {
+ pos = data;
+ for_each_possible_cpu(cpu) {
+ struct stmmac_pcpu_stats *stats, snapshot;
+
+ data = pos;
+ stats = per_cpu_ptr(priv->xstats.pstats, cpu);
do {
- start = u64_stats_fetch_begin(&priv->xstats.txq_stats[q].syncp);
- p = (char *)priv + offsetof(struct stmmac_priv,
- xstats.txq_stats[q].tx_pkt_n);
+ snapshot = *stats;
+ } while (u64_stats_fetch_retry(&stats->syncp, start));
+
+ for (q = 0; q < tx_cnt; q++) {
+ p = (char *)&snapshot + offsetof(struct stmmac_pcpu_stats,
+ txq_stats[q].tx_pkt_n);
for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
*data++ = (*(u64 *)p);
p += sizeof(u64);
}
- } while (u64_stats_fetch_retry(&priv->xstats.txq_stats[q].syncp, start));
- }
- for (q = 0; q < rx_cnt; q++) {
- do {
- start = u64_stats_fetch_begin(&priv->xstats.rxq_stats[q].syncp);
- p = (char *)priv + offsetof(struct stmmac_priv,
- xstats.rxq_stats[q].rx_pkt_n);
+ }
+ for (q = 0; q < rx_cnt; q++) {
+ p = (char *)&snapshot + offsetof(struct stmmac_pcpu_stats,
+ rxq_stats[q].rx_pkt_n);
for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
*data++ = (*(u64 *)p);
p += sizeof(u64);
}
- } while (u64_stats_fetch_retry(&priv->xstats.rxq_stats[q].syncp, start));
+ }
}
}
@@ -576,7 +590,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
u32 tx_queues_count = priv->plat->tx_queues_to_use;
unsigned long count;
unsigned int start;
- int i, j = 0, ret;
+ int i, j = 0, pos, ret, cpu;
if (priv->dma_cap.asp) {
for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) {
@@ -618,13 +632,22 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
data[j++] = (stmmac_gstrings_stats[i].sizeof_stat ==
sizeof(u64)) ? (*(u64 *)p) : (*(u32 *)p);
}
- do {
- start = u64_stats_fetch_begin(&priv->xstats.syncp);
- for (i = 0; i < STMMAC_STATS64_LEN; i++) {
- char *p = (char *)priv + stmmac_gstrings_stats64[i].stat_offset;
- data[j++] = *(u64 *)p;
+ pos = j;
+ for_each_possible_cpu(cpu) {
+ struct stmmac_pcpu_stats *stats, snapshot;
+
+ stats = per_cpu_ptr(priv->xstats.pstats, cpu);
+ j = pos;
+ do {
+ start = u64_stats_fetch_begin(&stats->syncp);
+ snapshot = *stats;
+ } while (u64_stats_fetch_retry(&stats->syncp, start));
+
+ for (i = 0; i < STMMAC_PCPU_STATS_LEN; i++) {
+ char *p = (char *)&snapshot + stmmac_gstrings_pcpu_stats[i].stat_offset;
+ data[j++] += *(u64 *)p;
}
- } while (u64_stats_fetch_retry(&priv->xstats.syncp, start));
+ }
stmmac_get_per_qstats(priv, &data[j]);
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 69cb2835fa82..4056ea859963 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2422,6 +2422,7 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
struct netdev_queue *nq = netdev_get_tx_queue(priv->dev, queue);
struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
struct xsk_buff_pool *pool = tx_q->xsk_pool;
@@ -2502,9 +2503,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
entry = tx_q->cur_tx;
}
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.tx_set_ic_bit += tx_set_ic_bit;
- u64_stats_update_end(&priv->xstats.syncp);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_set_ic_bit += tx_set_ic_bit;
+ u64_stats_update_end(&stats->syncp);
if (tx_desc) {
stmmac_flush_tx_descriptors(priv, queue);
@@ -2543,6 +2544,7 @@ static void stmmac_bump_dma_threshold(struct stmmac_priv *priv, u32 chan)
*/
static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
unsigned int bytes_compl = 0, pkts_compl = 0;
unsigned int entry, xmits = 0, count = 0;
@@ -2704,15 +2706,12 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
HRTIMER_MODE_REL);
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.tx_packets += tx_packets;
- priv->xstats.tx_pkt_n += tx_packets;
- priv->xstats.tx_clean++;
- u64_stats_update_end(&priv->xstats.syncp);
-
- u64_stats_update_begin(&priv->xstats.txq_stats[queue].syncp);
- priv->xstats.txq_stats[queue].tx_pkt_n += tx_packets;
- u64_stats_update_end(&priv->xstats.txq_stats[queue].syncp);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_packets += tx_packets;
+ stats->tx_pkt_n += tx_packets;
+ stats->tx_clean++;
+ stats->txq_stats[queue].tx_pkt_n += tx_packets;
+ u64_stats_update_end(&stats->syncp);
priv->xstats.tx_errors += tx_errors;
@@ -4108,6 +4107,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
int nfrags = skb_shinfo(skb)->nr_frags;
u32 queue = skb_get_queue_mapping(skb);
unsigned int first_entry, tx_packets;
+ struct stmmac_pcpu_stats *stats;
int tmp_pay_len = 0, first_tx;
struct stmmac_tx_queue *tx_q;
bool has_vlan, set_ic;
@@ -4275,13 +4275,14 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
}
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.tx_bytes += skb->len;
- priv->xstats.tx_tso_frames++;
- priv->xstats.tx_tso_nfrags += nfrags;
+ stats = this_cpu_ptr(priv->xstats.pstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_bytes += skb->len;
+ stats->tx_tso_frames++;
+ stats->tx_tso_nfrags += nfrags;
if (set_ic)
- priv->xstats.tx_set_ic_bit++;
- u64_stats_update_end(&priv->xstats.syncp);
+ stats->tx_set_ic_bit++;
+ u64_stats_update_end(&stats->syncp);
if (priv->sarc_type)
stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4353,6 +4354,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
int nfrags = skb_shinfo(skb)->nr_frags;
int gso = skb_shinfo(skb)->gso_type;
struct dma_edesc *tbs_desc = NULL;
+ struct stmmac_pcpu_stats *stats;
struct dma_desc *desc, *first;
struct stmmac_tx_queue *tx_q;
bool has_vlan, set_ic;
@@ -4511,11 +4513,12 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
}
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.tx_bytes += skb->len;
+ stats = this_cpu_ptr(priv->xstats.pstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_bytes += skb->len;
if (set_ic)
- priv->xstats.tx_set_ic_bit++;
- u64_stats_update_end(&priv->xstats.syncp);
+ stats->tx_set_ic_bit++;
+ u64_stats_update_end(&stats->syncp);
if (priv->sarc_type)
stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4722,6 +4725,7 @@ static unsigned int stmmac_rx_buf2_len(struct stmmac_priv *priv,
static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
struct xdp_frame *xdpf, bool dma_map)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
unsigned int entry = tx_q->cur_tx;
struct dma_desc *tx_desc;
@@ -4780,9 +4784,9 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
if (set_ic) {
tx_q->tx_count_frames = 0;
stmmac_set_tx_ic(priv, tx_desc);
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.tx_set_ic_bit++;
- u64_stats_update_end(&priv->xstats.syncp);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_set_ic_bit++;
+ u64_stats_update_end(&stats->syncp);
}
stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -4927,6 +4931,7 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
struct dma_desc *p, struct dma_desc *np,
struct xdp_buff *xdp)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
struct stmmac_channel *ch = &priv->channel[queue];
unsigned int len = xdp->data_end - xdp->data;
enum pkt_hash_types hash_type;
@@ -4955,10 +4960,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
skb_record_rx_queue(skb, queue);
napi_gro_receive(&ch->rxtx_napi, skb);
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.rx_packets++;
- priv->xstats.rx_bytes += len;
- u64_stats_update_end(&priv->xstats.syncp);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets++;
+ stats->rx_bytes += len;
+ u64_stats_update_end(&stats->syncp);
}
static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -5031,6 +5036,7 @@ static struct stmmac_xdp_buff *xsk_buff_to_stmmac_ctx(struct xdp_buff *xdp)
static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue];
unsigned int count = 0, error = 0, len = 0;
u32 rx_errors = 0, rx_dropped = 0;
@@ -5193,13 +5199,10 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
stmmac_finalize_xdp_rx(priv, xdp_status);
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.rx_pkt_n += count;
- u64_stats_update_end(&priv->xstats.syncp);
-
- u64_stats_update_begin(&priv->xstats.rxq_stats[queue].syncp);
- priv->xstats.rxq_stats[queue].rx_pkt_n += count;
- u64_stats_update_end(&priv->xstats.rxq_stats[queue].syncp);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_pkt_n += count;
+ stats->rxq_stats[queue].rx_pkt_n += count;
+ u64_stats_update_end(&stats->syncp);
priv->xstats.rx_dropped += rx_dropped;
priv->xstats.rx_errors += rx_errors;
@@ -5226,6 +5229,7 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
*/
static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
{
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pstats);
u32 rx_errors = 0, rx_dropped = 0, rx_bytes = 0, rx_packets = 0;
struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue];
struct stmmac_channel *ch = &priv->channel[queue];
@@ -5487,15 +5491,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
stmmac_rx_refill(priv, queue);
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.rx_packets += rx_packets;
- priv->xstats.rx_bytes += rx_bytes;
- priv->xstats.rx_pkt_n += count;
- u64_stats_update_end(&priv->xstats.syncp);
-
- u64_stats_update_begin(&priv->xstats.rxq_stats[queue].syncp);
- priv->xstats.rxq_stats[queue].rx_pkt_n += count;
- u64_stats_update_end(&priv->xstats.rxq_stats[queue].syncp);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets += rx_packets;
+ stats->rx_bytes += rx_bytes;
+ stats->rx_pkt_n += count;
+ stats->rxq_stats[queue].rx_pkt_n += count;
+ u64_stats_update_end(&stats->syncp);
priv->xstats.rx_dropped += rx_dropped;
priv->xstats.rx_errors += rx_errors;
@@ -5508,12 +5509,14 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
struct stmmac_channel *ch =
container_of(napi, struct stmmac_channel, rx_napi);
struct stmmac_priv *priv = ch->priv_data;
+ struct stmmac_pcpu_stats *stats;
u32 chan = ch->index;
int work_done;
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.napi_poll++;
- u64_stats_update_end(&priv->xstats.syncp);
+ stats = this_cpu_ptr(priv->xstats.pstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->napi_poll++;
+ u64_stats_update_end(&stats->syncp);
work_done = stmmac_rx(priv, budget, chan);
if (work_done < budget && napi_complete_done(napi, work_done)) {
@@ -5532,12 +5535,14 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
struct stmmac_channel *ch =
container_of(napi, struct stmmac_channel, tx_napi);
struct stmmac_priv *priv = ch->priv_data;
+ struct stmmac_pcpu_stats *stats;
u32 chan = ch->index;
int work_done;
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.napi_poll++;
- u64_stats_update_end(&priv->xstats.syncp);
+ stats = this_cpu_ptr(priv->xstats.pstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->napi_poll++;
+ u64_stats_update_end(&stats->syncp);
work_done = stmmac_tx_clean(priv, budget, chan);
work_done = min(work_done, budget);
@@ -5558,12 +5563,14 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget)
struct stmmac_channel *ch =
container_of(napi, struct stmmac_channel, rxtx_napi);
struct stmmac_priv *priv = ch->priv_data;
+ struct stmmac_pcpu_stats *stats;
int rx_done, tx_done, rxtx_done;
u32 chan = ch->index;
- u64_stats_update_begin(&priv->xstats.syncp);
- priv->xstats.napi_poll++;
- u64_stats_update_end(&priv->xstats.syncp);
+ stats = this_cpu_ptr(priv->xstats.pstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->napi_poll++;
+ u64_stats_update_end(&stats->syncp);
tx_done = stmmac_tx_clean(priv, budget, chan);
tx_done = min(tx_done, budget);
@@ -6823,23 +6830,30 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
{
struct stmmac_priv *priv = netdev_priv(dev);
unsigned int start;
- u64 rx_packets;
- u64 rx_bytes;
- u64 tx_packets;
- u64 tx_bytes;
-
- do {
- start = u64_stats_fetch_begin(&priv->xstats.syncp);
- rx_packets = priv->xstats.rx_packets;
- rx_bytes = priv->xstats.rx_bytes;
- tx_packets = priv->xstats.tx_packets;
- tx_bytes = priv->xstats.tx_bytes;
- } while (u64_stats_fetch_retry(&priv->xstats.syncp, start));
-
- stats->rx_packets = rx_packets;
- stats->rx_bytes = rx_bytes;
- stats->tx_packets = tx_packets;
- stats->tx_bytes = tx_bytes;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct stmmac_pcpu_stats *stats;
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
+
+ stats = per_cpu_ptr(priv->xstats.pstats, cpu);
+ do {
+ start = u64_stats_fetch_begin(&stats->syncp);
+ rx_packets = stats->rx_packets;
+ rx_bytes = stats->rx_bytes;
+ tx_packets = stats->tx_packets;
+ tx_bytes = stats->tx_bytes;
+ } while (u64_stats_fetch_retry(&stats->syncp, start));
+
+ stats->rx_packets += rx_packets;
+ stats->rx_bytes += rx_bytes;
+ stats->tx_packets += tx_packets;
+ stats->tx_bytes += tx_bytes;
+ }
+
stats->rx_dropped = priv->xstats.rx_dropped;
stats->rx_errors = priv->xstats.rx_errors;
stats->tx_dropped = priv->xstats.tx_dropped;
@@ -7225,6 +7239,10 @@ int stmmac_dvr_probe(struct device *device,
priv->device = device;
priv->dev = ndev;
+ priv->xstats.pstats = devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
+ if (!priv->xstas.pstats)
+ return -ENOMEM;
+
stmmac_set_ethtool_ops(ndev);
priv->pause = pause;
priv->plat = plat_dat;
@@ -7383,12 +7401,6 @@ int stmmac_dvr_probe(struct device *device,
priv->xstats.threshold = tc;
- u64_stats_init(&priv->xstats.syncp);
- for (i = 0; i < priv->plat->rx_queues_to_use; i++)
- u64_stats_init(&priv->xstats.rxq_stats[i].syncp);
- for (i = 0; i < priv->plat->tx_queues_to_use; i++)
- u64_stats_init(&priv->xstats.txq_stats[i].syncp);
-
/* Initialize RSS */
rxq = priv->plat->rx_queues_to_use;
netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key));
--
2.40.1
Hi Jisheng,
kernel test robot noticed the following build warnings:
[auto build test WARNING on sunxi/sunxi/for-next]
[also build test WARNING on linus/master v6.4-rc6]
[cannot apply to next-20230614]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Jisheng-Zhang/net-stmmac-don-t-clear-network-statistics-in-ndo_open/20230615-003137
base: https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git sunxi/for-next
patch link: https://lore.kernel.org/r/20230614161847.4071-4-jszhang%40kernel.org
patch subject: [PATCH 3/3] net: stmmac: use pcpu statistics where necessary
config: m68k-allyesconfig (https://download.01.org/0day-ci/archive/20230615/[email protected]/config)
compiler: m68k-linux-gcc (GCC) 12.3.0
reproduce (this is a W=1 build):
mkdir -p ~/bin
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
git remote add sunxi https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
git fetch sunxi sunxi/for-next
git checkout sunxi/sunxi/for-next
b4 shazam https://lore.kernel.org/r/[email protected]
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.3.0 ~/bin/make.cross W=1 O=build_dir ARCH=m68k olddefconfig
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.3.0 ~/bin/make.cross W=1 O=build_dir ARCH=m68k SHELL=/bin/bash drivers/net/
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All warnings (new ones prefixed by >>):
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c: In function 'stmmac_get_per_qstats':
>> drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:564:26: warning: 'start' is used uninitialized [-Wuninitialized]
564 | } while (u64_stats_fetch_retry(&stats->syncp, start));
| ^~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:551:22: note: 'start' was declared here
551 | unsigned int start;
| ^~~~~
vim +/start +564 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
546
547 static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
548 {
549 u32 tx_cnt = priv->plat->tx_queues_to_use;
550 u32 rx_cnt = priv->plat->rx_queues_to_use;
551 unsigned int start;
552 int q, stat, cpu;
553 char *p;
554 u64 *pos;
555
556 pos = data;
557 for_each_possible_cpu(cpu) {
558 struct stmmac_pcpu_stats *stats, snapshot;
559
560 data = pos;
561 stats = per_cpu_ptr(priv->xstats.pstats, cpu);
562 do {
563 snapshot = *stats;
> 564 } while (u64_stats_fetch_retry(&stats->syncp, start));
565
566 for (q = 0; q < tx_cnt; q++) {
567 p = (char *)&snapshot + offsetof(struct stmmac_pcpu_stats,
568 txq_stats[q].tx_pkt_n);
569 for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
570 *data++ = (*(u64 *)p);
571 p += sizeof(u64);
572 }
573 }
574 for (q = 0; q < rx_cnt; q++) {
575 p = (char *)&snapshot + offsetof(struct stmmac_pcpu_stats,
576 rxq_stats[q].rx_pkt_n);
577 for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
578 *data++ = (*(u64 *)p);
579 p += sizeof(u64);
580 }
581 }
582 }
583 }
584
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Jisheng,
kernel test robot noticed the following build errors:
[auto build test ERROR on sunxi/sunxi/for-next]
[also build test ERROR on linus/master v6.4-rc6]
[cannot apply to next-20230614]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Jisheng-Zhang/net-stmmac-don-t-clear-network-statistics-in-ndo_open/20230615-003137
base: https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git sunxi/for-next
patch link: https://lore.kernel.org/r/20230614161847.4071-4-jszhang%40kernel.org
patch subject: [PATCH 3/3] net: stmmac: use pcpu statistics where necessary
config: riscv-randconfig-r006-20230612 (https://download.01.org/0day-ci/archive/20230615/[email protected]/config)
compiler: clang version 17.0.0 (https://github.com/llvm/llvm-project.git 4a5ac14ee968ff0ad5d2cc1ffa0299048db4c88a)
reproduce (this is a W=1 build):
mkdir -p ~/bin
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install riscv cross compiling tool for clang build
# apt-get install binutils-riscv64-linux-gnu
git remote add sunxi https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
git fetch sunxi sunxi/for-next
git checkout sunxi/sunxi/for-next
b4 shazam https://lore.kernel.org/r/[email protected]
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang ~/bin/make.cross W=1 O=build_dir ARCH=riscv olddefconfig
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang ~/bin/make.cross W=1 O=build_dir ARCH=riscv SHELL=/bin/bash drivers/net/ethernet/stmicro/stmmac/
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All error/warnings (new ones prefixed by >>):
>> drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:564:49: warning: variable 'start' is uninitialized when used here [-Wuninitialized]
564 | } while (u64_stats_fetch_retry(&stats->syncp, start));
| ^~~~~
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:551:20: note: initialize the variable 'start' to silence this warning
551 | unsigned int start;
| ^
| = 0
1 warning generated.
--
>> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:7243:13: error: no member named 'xstas' in 'struct stmmac_priv'; did you mean 'xstats'?
7243 | if (!priv->xstas.pstats)
| ^~~~~
| xstats
drivers/net/ethernet/stmicro/stmmac/stmmac.h:247:28: note: 'xstats' declared here
247 | struct stmmac_extra_stats xstats ____cacheline_aligned_in_smp;
| ^
1 error generated.
vim +7243 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
7211
7212 /**
7213 * stmmac_dvr_probe
7214 * @device: device pointer
7215 * @plat_dat: platform data pointer
7216 * @res: stmmac resource pointer
7217 * Description: this is the main probe function used to
7218 * call the alloc_etherdev, allocate the priv structure.
7219 * Return:
7220 * returns 0 on success, otherwise errno.
7221 */
7222 int stmmac_dvr_probe(struct device *device,
7223 struct plat_stmmacenet_data *plat_dat,
7224 struct stmmac_resources *res)
7225 {
7226 struct net_device *ndev = NULL;
7227 struct stmmac_priv *priv;
7228 u32 rxq;
7229 int i, ret = 0;
7230
7231 ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv),
7232 MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES);
7233 if (!ndev)
7234 return -ENOMEM;
7235
7236 SET_NETDEV_DEV(ndev, device);
7237
7238 priv = netdev_priv(ndev);
7239 priv->device = device;
7240 priv->dev = ndev;
7241
7242 priv->xstats.pstats = devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
> 7243 if (!priv->xstas.pstats)
7244 return -ENOMEM;
7245
7246 stmmac_set_ethtool_ops(ndev);
7247 priv->pause = pause;
7248 priv->plat = plat_dat;
7249 priv->ioaddr = res->addr;
7250 priv->dev->base_addr = (unsigned long)res->addr;
7251 priv->plat->dma_cfg->multi_msi_en = priv->plat->multi_msi_en;
7252
7253 priv->dev->irq = res->irq;
7254 priv->wol_irq = res->wol_irq;
7255 priv->lpi_irq = res->lpi_irq;
7256 priv->sfty_ce_irq = res->sfty_ce_irq;
7257 priv->sfty_ue_irq = res->sfty_ue_irq;
7258 for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
7259 priv->rx_irq[i] = res->rx_irq[i];
7260 for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
7261 priv->tx_irq[i] = res->tx_irq[i];
7262
7263 if (!is_zero_ether_addr(res->mac))
7264 eth_hw_addr_set(priv->dev, res->mac);
7265
7266 dev_set_drvdata(device, priv->dev);
7267
7268 /* Verify driver arguments */
7269 stmmac_verify_args();
7270
7271 priv->af_xdp_zc_qps = bitmap_zalloc(MTL_MAX_TX_QUEUES, GFP_KERNEL);
7272 if (!priv->af_xdp_zc_qps)
7273 return -ENOMEM;
7274
7275 /* Allocate workqueue */
7276 priv->wq = create_singlethread_workqueue("stmmac_wq");
7277 if (!priv->wq) {
7278 dev_err(priv->device, "failed to create workqueue\n");
7279 ret = -ENOMEM;
7280 goto error_wq_init;
7281 }
7282
7283 INIT_WORK(&priv->service_task, stmmac_service_task);
7284
7285 /* Initialize Link Partner FPE workqueue */
7286 INIT_WORK(&priv->fpe_task, stmmac_fpe_lp_task);
7287
7288 /* Override with kernel parameters if supplied XXX CRS XXX
7289 * this needs to have multiple instances
7290 */
7291 if ((phyaddr >= 0) && (phyaddr <= 31))
7292 priv->plat->phy_addr = phyaddr;
7293
7294 if (priv->plat->stmmac_rst) {
7295 ret = reset_control_assert(priv->plat->stmmac_rst);
7296 reset_control_deassert(priv->plat->stmmac_rst);
7297 /* Some reset controllers have only reset callback instead of
7298 * assert + deassert callbacks pair.
7299 */
7300 if (ret == -ENOTSUPP)
7301 reset_control_reset(priv->plat->stmmac_rst);
7302 }
7303
7304 ret = reset_control_deassert(priv->plat->stmmac_ahb_rst);
7305 if (ret == -ENOTSUPP)
7306 dev_err(priv->device, "unable to bring out of ahb reset: %pe\n",
7307 ERR_PTR(ret));
7308
7309 /* Init MAC and get the capabilities */
7310 ret = stmmac_hw_init(priv);
7311 if (ret)
7312 goto error_hw_init;
7313
7314 /* Only DWMAC core version 5.20 onwards supports HW descriptor prefetch.
7315 */
7316 if (priv->synopsys_id < DWMAC_CORE_5_20)
7317 priv->plat->dma_cfg->dche = false;
7318
7319 stmmac_check_ether_addr(priv);
7320
7321 ndev->netdev_ops = &stmmac_netdev_ops;
7322
7323 ndev->xdp_metadata_ops = &stmmac_xdp_metadata_ops;
7324
7325 ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
7326 NETIF_F_RXCSUM;
7327 ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
7328 NETDEV_XDP_ACT_XSK_ZEROCOPY |
7329 NETDEV_XDP_ACT_NDO_XMIT;
7330
7331 ret = stmmac_tc_init(priv, priv);
7332 if (!ret) {
7333 ndev->hw_features |= NETIF_F_HW_TC;
7334 }
7335
7336 if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
7337 ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
7338 if (priv->plat->has_gmac4)
7339 ndev->hw_features |= NETIF_F_GSO_UDP_L4;
7340 priv->tso = true;
7341 dev_info(priv->device, "TSO feature enabled\n");
7342 }
7343
7344 if (priv->dma_cap.sphen && !priv->plat->sph_disable) {
7345 ndev->hw_features |= NETIF_F_GRO;
7346 priv->sph_cap = true;
7347 priv->sph = priv->sph_cap;
7348 dev_info(priv->device, "SPH feature enabled\n");
7349 }
7350
7351 /* Ideally our host DMA address width is the same as for the
7352 * device. However, it may differ and then we have to use our
7353 * host DMA width for allocation and the device DMA width for
7354 * register handling.
7355 */
7356 if (priv->plat->host_dma_width)
7357 priv->dma_cap.host_dma_width = priv->plat->host_dma_width;
7358 else
7359 priv->dma_cap.host_dma_width = priv->dma_cap.addr64;
7360
7361 if (priv->dma_cap.host_dma_width) {
7362 ret = dma_set_mask_and_coherent(device,
7363 DMA_BIT_MASK(priv->dma_cap.host_dma_width));
7364 if (!ret) {
7365 dev_info(priv->device, "Using %d/%d bits DMA host/device width\n",
7366 priv->dma_cap.host_dma_width, priv->dma_cap.addr64);
7367
7368 /*
7369 * If more than 32 bits can be addressed, make sure to
7370 * enable enhanced addressing mode.
7371 */
7372 if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT))
7373 priv->plat->dma_cfg->eame = true;
7374 } else {
7375 ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(32));
7376 if (ret) {
7377 dev_err(priv->device, "Failed to set DMA Mask\n");
7378 goto error_hw_init;
7379 }
7380
7381 priv->dma_cap.host_dma_width = 32;
7382 }
7383 }
7384
7385 ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
7386 ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
7387 #ifdef STMMAC_VLAN_TAG_USED
7388 /* Both mac100 and gmac support receive VLAN tag detection */
7389 ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX;
7390 if (priv->dma_cap.vlhash) {
7391 ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
7392 ndev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
7393 }
7394 if (priv->dma_cap.vlins) {
7395 ndev->features |= NETIF_F_HW_VLAN_CTAG_TX;
7396 if (priv->dma_cap.dvlan)
7397 ndev->features |= NETIF_F_HW_VLAN_STAG_TX;
7398 }
7399 #endif
7400 priv->msg_enable = netif_msg_init(debug, default_msg_level);
7401
7402 priv->xstats.threshold = tc;
7403
7404 /* Initialize RSS */
7405 rxq = priv->plat->rx_queues_to_use;
7406 netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key));
7407 for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++)
7408 priv->rss.table[i] = ethtool_rxfh_indir_default(i, rxq);
7409
7410 if (priv->dma_cap.rssen && priv->plat->rss_en)
7411 ndev->features |= NETIF_F_RXHASH;
7412
7413 ndev->vlan_features |= ndev->features;
7414 /* TSO doesn't work on VLANs yet */
7415 ndev->vlan_features &= ~NETIF_F_TSO;
7416
7417 /* MTU range: 46 - hw-specific max */
7418 ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
7419 if (priv->plat->has_xgmac)
7420 ndev->max_mtu = XGMAC_JUMBO_LEN;
7421 else if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00))
7422 ndev->max_mtu = JUMBO_LEN;
7423 else
7424 ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN);
7425 /* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu
7426 * as well as plat->maxmtu < ndev->min_mtu which is a invalid range.
7427 */
7428 if ((priv->plat->maxmtu < ndev->max_mtu) &&
7429 (priv->plat->maxmtu >= ndev->min_mtu))
7430 ndev->max_mtu = priv->plat->maxmtu;
7431 else if (priv->plat->maxmtu < ndev->min_mtu)
7432 dev_warn(priv->device,
7433 "%s: warning: maxmtu having invalid value (%d)\n",
7434 __func__, priv->plat->maxmtu);
7435
7436 if (flow_ctrl)
7437 priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */
7438
7439 ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
7440
7441 /* Setup channels NAPI */
7442 stmmac_napi_add(ndev);
7443
7444 mutex_init(&priv->lock);
7445
7446 /* If a specific clk_csr value is passed from the platform
7447 * this means that the CSR Clock Range selection cannot be
7448 * changed at run-time and it is fixed. Viceversa the driver'll try to
7449 * set the MDC clock dynamically according to the csr actual
7450 * clock input.
7451 */
7452 if (priv->plat->clk_csr >= 0)
7453 priv->clk_csr = priv->plat->clk_csr;
7454 else
7455 stmmac_clk_csr_set(priv);
7456
7457 stmmac_check_pcs_mode(priv);
7458
7459 pm_runtime_get_noresume(device);
7460 pm_runtime_set_active(device);
7461 if (!pm_runtime_enabled(device))
7462 pm_runtime_enable(device);
7463
7464 if (priv->hw->pcs != STMMAC_PCS_TBI &&
7465 priv->hw->pcs != STMMAC_PCS_RTBI) {
7466 /* MDIO bus Registration */
7467 ret = stmmac_mdio_register(ndev);
7468 if (ret < 0) {
7469 dev_err_probe(priv->device, ret,
7470 "%s: MDIO bus (id: %d) registration failed\n",
7471 __func__, priv->plat->bus_id);
7472 goto error_mdio_register;
7473 }
7474 }
7475
7476 if (priv->plat->speed_mode_2500)
7477 priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv);
7478
7479 if (priv->plat->mdio_bus_data && priv->plat->mdio_bus_data->has_xpcs) {
7480 ret = stmmac_xpcs_setup(priv->mii);
7481 if (ret)
7482 goto error_xpcs_setup;
7483 }
7484
7485 ret = stmmac_phy_setup(priv);
7486 if (ret) {
7487 netdev_err(ndev, "failed to setup phy (%d)\n", ret);
7488 goto error_phy_setup;
7489 }
7490
7491 ret = register_netdev(ndev);
7492 if (ret) {
7493 dev_err(priv->device, "%s: ERROR %i registering the device\n",
7494 __func__, ret);
7495 goto error_netdev_register;
7496 }
7497
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Jisheng,
kernel test robot noticed the following build errors:
[auto build test ERROR on sunxi/sunxi/for-next]
[also build test ERROR on linus/master v6.4-rc6]
[cannot apply to next-20230614]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Jisheng-Zhang/net-stmmac-don-t-clear-network-statistics-in-ndo_open/20230615-003137
base: https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git sunxi/for-next
patch link: https://lore.kernel.org/r/20230614161847.4071-4-jszhang%40kernel.org
patch subject: [PATCH 3/3] net: stmmac: use pcpu statistics where necessary
config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20230615/[email protected]/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build):
git remote add sunxi https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
git fetch sunxi sunxi/for-next
git checkout sunxi/sunxi/for-next
b4 shazam https://lore.kernel.org/r/[email protected]
# save the config file
mkdir build_dir && cp config build_dir/.config
make W=1 O=build_dir ARCH=x86_64 olddefconfig
make W=1 O=build_dir ARCH=x86_64 SHELL=/bin/bash
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c: In function 'stmmac_dvr_probe':
>> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:7243:20: error: 'struct stmmac_priv' has no member named 'xstas'; did you mean 'xstats'?
7243 | if (!priv->xstas.pstats)
| ^~~~~
| xstats
vim +7243 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
7211
7212 /**
7213 * stmmac_dvr_probe
7214 * @device: device pointer
7215 * @plat_dat: platform data pointer
7216 * @res: stmmac resource pointer
7217 * Description: this is the main probe function used to
7218 * call the alloc_etherdev, allocate the priv structure.
7219 * Return:
7220 * returns 0 on success, otherwise errno.
7221 */
7222 int stmmac_dvr_probe(struct device *device,
7223 struct plat_stmmacenet_data *plat_dat,
7224 struct stmmac_resources *res)
7225 {
7226 struct net_device *ndev = NULL;
7227 struct stmmac_priv *priv;
7228 u32 rxq;
7229 int i, ret = 0;
7230
7231 ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv),
7232 MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES);
7233 if (!ndev)
7234 return -ENOMEM;
7235
7236 SET_NETDEV_DEV(ndev, device);
7237
7238 priv = netdev_priv(ndev);
7239 priv->device = device;
7240 priv->dev = ndev;
7241
7242 priv->xstats.pstats = devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
> 7243 if (!priv->xstas.pstats)
7244 return -ENOMEM;
7245
7246 stmmac_set_ethtool_ops(ndev);
7247 priv->pause = pause;
7248 priv->plat = plat_dat;
7249 priv->ioaddr = res->addr;
7250 priv->dev->base_addr = (unsigned long)res->addr;
7251 priv->plat->dma_cfg->multi_msi_en = priv->plat->multi_msi_en;
7252
7253 priv->dev->irq = res->irq;
7254 priv->wol_irq = res->wol_irq;
7255 priv->lpi_irq = res->lpi_irq;
7256 priv->sfty_ce_irq = res->sfty_ce_irq;
7257 priv->sfty_ue_irq = res->sfty_ue_irq;
7258 for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
7259 priv->rx_irq[i] = res->rx_irq[i];
7260 for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
7261 priv->tx_irq[i] = res->tx_irq[i];
7262
7263 if (!is_zero_ether_addr(res->mac))
7264 eth_hw_addr_set(priv->dev, res->mac);
7265
7266 dev_set_drvdata(device, priv->dev);
7267
7268 /* Verify driver arguments */
7269 stmmac_verify_args();
7270
7271 priv->af_xdp_zc_qps = bitmap_zalloc(MTL_MAX_TX_QUEUES, GFP_KERNEL);
7272 if (!priv->af_xdp_zc_qps)
7273 return -ENOMEM;
7274
7275 /* Allocate workqueue */
7276 priv->wq = create_singlethread_workqueue("stmmac_wq");
7277 if (!priv->wq) {
7278 dev_err(priv->device, "failed to create workqueue\n");
7279 ret = -ENOMEM;
7280 goto error_wq_init;
7281 }
7282
7283 INIT_WORK(&priv->service_task, stmmac_service_task);
7284
7285 /* Initialize Link Partner FPE workqueue */
7286 INIT_WORK(&priv->fpe_task, stmmac_fpe_lp_task);
7287
7288 /* Override with kernel parameters if supplied XXX CRS XXX
7289 * this needs to have multiple instances
7290 */
7291 if ((phyaddr >= 0) && (phyaddr <= 31))
7292 priv->plat->phy_addr = phyaddr;
7293
7294 if (priv->plat->stmmac_rst) {
7295 ret = reset_control_assert(priv->plat->stmmac_rst);
7296 reset_control_deassert(priv->plat->stmmac_rst);
7297 /* Some reset controllers have only reset callback instead of
7298 * assert + deassert callbacks pair.
7299 */
7300 if (ret == -ENOTSUPP)
7301 reset_control_reset(priv->plat->stmmac_rst);
7302 }
7303
7304 ret = reset_control_deassert(priv->plat->stmmac_ahb_rst);
7305 if (ret == -ENOTSUPP)
7306 dev_err(priv->device, "unable to bring out of ahb reset: %pe\n",
7307 ERR_PTR(ret));
7308
7309 /* Init MAC and get the capabilities */
7310 ret = stmmac_hw_init(priv);
7311 if (ret)
7312 goto error_hw_init;
7313
7314 /* Only DWMAC core version 5.20 onwards supports HW descriptor prefetch.
7315 */
7316 if (priv->synopsys_id < DWMAC_CORE_5_20)
7317 priv->plat->dma_cfg->dche = false;
7318
7319 stmmac_check_ether_addr(priv);
7320
7321 ndev->netdev_ops = &stmmac_netdev_ops;
7322
7323 ndev->xdp_metadata_ops = &stmmac_xdp_metadata_ops;
7324
7325 ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
7326 NETIF_F_RXCSUM;
7327 ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
7328 NETDEV_XDP_ACT_XSK_ZEROCOPY |
7329 NETDEV_XDP_ACT_NDO_XMIT;
7330
7331 ret = stmmac_tc_init(priv, priv);
7332 if (!ret) {
7333 ndev->hw_features |= NETIF_F_HW_TC;
7334 }
7335
7336 if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
7337 ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
7338 if (priv->plat->has_gmac4)
7339 ndev->hw_features |= NETIF_F_GSO_UDP_L4;
7340 priv->tso = true;
7341 dev_info(priv->device, "TSO feature enabled\n");
7342 }
7343
7344 if (priv->dma_cap.sphen && !priv->plat->sph_disable) {
7345 ndev->hw_features |= NETIF_F_GRO;
7346 priv->sph_cap = true;
7347 priv->sph = priv->sph_cap;
7348 dev_info(priv->device, "SPH feature enabled\n");
7349 }
7350
7351 /* Ideally our host DMA address width is the same as for the
7352 * device. However, it may differ and then we have to use our
7353 * host DMA width for allocation and the device DMA width for
7354 * register handling.
7355 */
7356 if (priv->plat->host_dma_width)
7357 priv->dma_cap.host_dma_width = priv->plat->host_dma_width;
7358 else
7359 priv->dma_cap.host_dma_width = priv->dma_cap.addr64;
7360
7361 if (priv->dma_cap.host_dma_width) {
7362 ret = dma_set_mask_and_coherent(device,
7363 DMA_BIT_MASK(priv->dma_cap.host_dma_width));
7364 if (!ret) {
7365 dev_info(priv->device, "Using %d/%d bits DMA host/device width\n",
7366 priv->dma_cap.host_dma_width, priv->dma_cap.addr64);
7367
7368 /*
7369 * If more than 32 bits can be addressed, make sure to
7370 * enable enhanced addressing mode.
7371 */
7372 if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT))
7373 priv->plat->dma_cfg->eame = true;
7374 } else {
7375 ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(32));
7376 if (ret) {
7377 dev_err(priv->device, "Failed to set DMA Mask\n");
7378 goto error_hw_init;
7379 }
7380
7381 priv->dma_cap.host_dma_width = 32;
7382 }
7383 }
7384
7385 ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
7386 ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
7387 #ifdef STMMAC_VLAN_TAG_USED
7388 /* Both mac100 and gmac support receive VLAN tag detection */
7389 ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX;
7390 if (priv->dma_cap.vlhash) {
7391 ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
7392 ndev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
7393 }
7394 if (priv->dma_cap.vlins) {
7395 ndev->features |= NETIF_F_HW_VLAN_CTAG_TX;
7396 if (priv->dma_cap.dvlan)
7397 ndev->features |= NETIF_F_HW_VLAN_STAG_TX;
7398 }
7399 #endif
7400 priv->msg_enable = netif_msg_init(debug, default_msg_level);
7401
7402 priv->xstats.threshold = tc;
7403
7404 /* Initialize RSS */
7405 rxq = priv->plat->rx_queues_to_use;
7406 netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key));
7407 for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++)
7408 priv->rss.table[i] = ethtool_rxfh_indir_default(i, rxq);
7409
7410 if (priv->dma_cap.rssen && priv->plat->rss_en)
7411 ndev->features |= NETIF_F_RXHASH;
7412
7413 ndev->vlan_features |= ndev->features;
7414 /* TSO doesn't work on VLANs yet */
7415 ndev->vlan_features &= ~NETIF_F_TSO;
7416
7417 /* MTU range: 46 - hw-specific max */
7418 ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
7419 if (priv->plat->has_xgmac)
7420 ndev->max_mtu = XGMAC_JUMBO_LEN;
7421 else if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00))
7422 ndev->max_mtu = JUMBO_LEN;
7423 else
7424 ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN);
7425 /* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu
7426 * as well as plat->maxmtu < ndev->min_mtu which is a invalid range.
7427 */
7428 if ((priv->plat->maxmtu < ndev->max_mtu) &&
7429 (priv->plat->maxmtu >= ndev->min_mtu))
7430 ndev->max_mtu = priv->plat->maxmtu;
7431 else if (priv->plat->maxmtu < ndev->min_mtu)
7432 dev_warn(priv->device,
7433 "%s: warning: maxmtu having invalid value (%d)\n",
7434 __func__, priv->plat->maxmtu);
7435
7436 if (flow_ctrl)
7437 priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */
7438
7439 ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
7440
7441 /* Setup channels NAPI */
7442 stmmac_napi_add(ndev);
7443
7444 mutex_init(&priv->lock);
7445
7446 /* If a specific clk_csr value is passed from the platform
7447 * this means that the CSR Clock Range selection cannot be
7448 * changed at run-time and it is fixed. Viceversa the driver'll try to
7449 * set the MDC clock dynamically according to the csr actual
7450 * clock input.
7451 */
7452 if (priv->plat->clk_csr >= 0)
7453 priv->clk_csr = priv->plat->clk_csr;
7454 else
7455 stmmac_clk_csr_set(priv);
7456
7457 stmmac_check_pcs_mode(priv);
7458
7459 pm_runtime_get_noresume(device);
7460 pm_runtime_set_active(device);
7461 if (!pm_runtime_enabled(device))
7462 pm_runtime_enable(device);
7463
7464 if (priv->hw->pcs != STMMAC_PCS_TBI &&
7465 priv->hw->pcs != STMMAC_PCS_RTBI) {
7466 /* MDIO bus Registration */
7467 ret = stmmac_mdio_register(ndev);
7468 if (ret < 0) {
7469 dev_err_probe(priv->device, ret,
7470 "%s: MDIO bus (id: %d) registration failed\n",
7471 __func__, priv->plat->bus_id);
7472 goto error_mdio_register;
7473 }
7474 }
7475
7476 if (priv->plat->speed_mode_2500)
7477 priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv);
7478
7479 if (priv->plat->mdio_bus_data && priv->plat->mdio_bus_data->has_xpcs) {
7480 ret = stmmac_xpcs_setup(priv->mii);
7481 if (ret)
7482 goto error_xpcs_setup;
7483 }
7484
7485 ret = stmmac_phy_setup(priv);
7486 if (ret) {
7487 netdev_err(ndev, "failed to setup phy (%d)\n", ret);
7488 goto error_phy_setup;
7489 }
7490
7491 ret = register_netdev(ndev);
7492 if (ret) {
7493 dev_err(priv->device, "%s: ERROR %i registering the device\n",
7494 __func__, ret);
7495 goto error_netdev_register;
7496 }
7497
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki