| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250226211003.2790916-8-kuba@kernel.org>
Date: Wed, 26 Feb 2025 13:10:01 -0800
From: Jakub Kicinski <kuba@...nel.org>
To: davem@...emloft.net
Cc: netdev@...r.kernel.org,
edumazet@...gle.com,
pabeni@...hat.com,
andrew+netdev@...n.ch,
horms@...nel.org,
michael.chan@...adcom.com,
pavan.chebbi@...adcom.com,
Jakub Kicinski <kuba@...nel.org>
Subject: [PATCH net-next 7/9] eth: bnxt: maintain rx pkt/byte stats in SW
Some workloads want to be able to track bandwidth utilization on
the scale of 10s of msecs. Updating all HW stats at this rate is
both hard and wasteful of PCIe bandwidth.
Maintain basic Rx pkt/byte counters in software. ethtool -S will still
show the HW stats, but qstats and rtnl stats will show SW statistics.
We need to take care of HW-GRO, XDP and VF representors. Per netdev
qstat definition Rx stats should reflect packets passed to XDP (if
active, otherwise to the stack). XDP and GRO do not interoperate
in bnxt, so we need to count the packets in a few places.
Add a helper and call it where needed.
Do not count VF representor traffic as traffic for the main netdev.
The stats are added towards the end of the struct since ethtool
code expects existing members to be first.
Signed-off-by: Jakub Kicinski <kuba@...nel.org>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.h | 7 ++
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 96 +++++++++++++++--------
2 files changed, 72 insertions(+), 31 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 34f23ddd4d71..1607a4a28bf0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1118,8 +1118,12 @@ struct bnxt_rx_sw_stats {
u64 rx_l4_csum_errors;
u64 rx_resets;
u64 rx_buf_errors;
+ /* non-ethtool stats follow */
u64 rx_oom_discards;
u64 rx_netpoll_discards;
+ u64 rx_packets;
+ u64 rx_bytes;
+ struct u64_stats_sync syncp;
};
struct bnxt_tx_sw_stats {
@@ -1146,6 +1150,9 @@ struct bnxt_total_ring_drv_stats {
u64 tx_total_resets;
u64 tx_total_ring_discards;
u64 total_missed_irqs;
+ /* non-ethtool stats follow */
+ u64 rx_total_packets;
+ u64 rx_total_bytes;
};
struct bnxt_stats_mem {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 113989b9b8cb..b74495e0e5d5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -886,6 +886,24 @@ static bool bnxt_separate_head_pool(void)
return PAGE_SIZE > BNXT_RX_PAGE_SIZE;
}
+static void bnxt_rx_pkt_cnt(struct bnxt *bp, struct bnxt_napi *bnapi,
+ struct net_device *dev,
+ int segs, int len, int payload_off)
+{
+ struct bnxt_sw_stats *sw_stats = bnapi->cp_ring.sw_stats;
+
+ /* Packet is for a representor */
+ if (bp->dev != dev)
+ return;
+
+ u64_stats_update_begin(&sw_stats->rx.syncp);
+ sw_stats->rx.rx_packets += segs;
+ sw_stats->rx.rx_bytes += len;
+ if (segs > 1)
+ sw_stats->rx.rx_bytes += (segs - 1) * payload_off;
+ u64_stats_update_end(&sw_stats->rx.syncp);
+}
+
static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
struct bnxt_rx_ring_info *rxr,
unsigned int *offset,
@@ -1735,6 +1753,7 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
}
static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
+ struct bnxt_napi *bnapi,
bool gro,
struct bnxt_tpa_info *tpa_info,
struct rx_tpa_end_cmp *tpa_end,
@@ -1742,11 +1761,15 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
struct sk_buff *skb)
{
int payload_off;
+ int full_len;
u16 segs;
+ full_len = skb->len - skb_mac_offset(skb);
segs = TPA_END_TPA_SEGS(tpa_end);
- if (!gro || segs == 1 || !IS_ENABLED(CONFIG_INET))
+ if (!gro || segs == 1 || !IS_ENABLED(CONFIG_INET)) {
+ bnxt_rx_pkt_cnt(bp, bnapi, skb->dev, 1, full_len, 0);
return skb;
+ }
NAPI_GRO_CB(skb)->count = segs;
skb_shinfo(skb)->gso_size =
@@ -1757,8 +1780,11 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
else
payload_off = TPA_END_PAYLOAD_OFF(tpa_end);
skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb);
- if (likely(skb))
+ if (likely(skb)) {
tcp_gro_complete(skb);
+ bnxt_rx_pkt_cnt(bp, bnapi, skb->dev,
+ segs, full_len, payload_off);
+ }
return skb;
}
@@ -1918,7 +1944,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
(tpa_info->flags2 & RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3;
}
- return bnxt_gro_skb(bp, gro, tpa_info, tpa_end, tpa_end1, skb);
+ return bnxt_gro_skb(bp, bnapi, gro, tpa_info, tpa_end, tpa_end1, skb);
}
static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
@@ -2045,6 +2071,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
struct sk_buff *skb;
struct xdp_buff xdp;
u32 flags, misc;
+ u32 frag_len;
u32 cmpl_ts;
void *data;
int rc = 0;
@@ -2162,16 +2189,19 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
if (bnxt_xdp_attached(bp, rxr)) {
bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
if (agg_bufs) {
- u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
- cp_cons, agg_bufs,
- false);
+ frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
+ cp_cons, agg_bufs,
+ false);
if (!frag_len)
goto oom_next_rx;
+ } else {
+ frag_len = 0;
}
xdp_active = true;
}
if (xdp_active && dev == bp->dev) {
+ bnxt_rx_pkt_cnt(bp, bnapi, dev, 1, len + frag_len, 0);
if (bnxt_rx_xdp(bp, rxr, cons, &xdp, data, &data_ptr, &len, event)) {
rc = 1;
goto next_rx;
@@ -2274,6 +2304,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
}
}
}
+
+ if (!xdp_active) /* XDP packets counted before calling XDP */
+ bnxt_rx_pkt_cnt(bp, bnapi, dev,
+ 1, skb->len - skb_mac_offset(skb), 0);
bnxt_deliver_skb(bp, bnapi, skb);
rc = 1;
@@ -5114,6 +5148,8 @@ static int bnxt_alloc_stats(struct bnxt *bp)
if (!cpr->sw_stats)
return -ENOMEM;
+ u64_stats_init(&cpr->sw_stats->rx.syncp);
+
cpr->stats.len = size;
rc = bnxt_alloc_stats_mem(bp, &cpr->stats, !i);
if (rc)
@@ -13091,7 +13127,14 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
static void bnxt_drv_stat_snapshot(const struct bnxt_sw_stats *sw_stats,
struct bnxt_sw_stats *snapshot)
{
- memcpy(snapshot, sw_stats, sizeof(*snapshot));
+ unsigned int seq_rx;
+
+ do {
+ seq_rx = u64_stats_fetch_begin(&sw_stats->rx.syncp);
+
+ memcpy(snapshot, sw_stats, sizeof(*snapshot));
+
+ } while (u64_stats_fetch_retry(&sw_stats->rx.syncp, seq_rx));
}
static void bnxt_get_ring_stats(struct bnxt *bp,
@@ -13107,18 +13150,13 @@ static void bnxt_get_ring_stats(struct bnxt *bp,
bnxt_drv_stat_snapshot(cpr->sw_stats, &sw_stats);
- stats->rx_packets += BNXT_GET_RING_STATS64(sw, rx_ucast_pkts);
- stats->rx_packets += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts);
- stats->rx_packets += BNXT_GET_RING_STATS64(sw, rx_bcast_pkts);
+ stats->rx_packets += sw_stats.rx.rx_packets;
+ stats->rx_bytes += sw_stats.rx.rx_bytes;
stats->tx_packets += BNXT_GET_RING_STATS64(sw, tx_ucast_pkts);
stats->tx_packets += BNXT_GET_RING_STATS64(sw, tx_mcast_pkts);
stats->tx_packets += BNXT_GET_RING_STATS64(sw, tx_bcast_pkts);
- stats->rx_bytes += BNXT_GET_RING_STATS64(sw, rx_ucast_bytes);
- stats->rx_bytes += BNXT_GET_RING_STATS64(sw, rx_mcast_bytes);
- stats->rx_bytes += BNXT_GET_RING_STATS64(sw, rx_bcast_bytes);
-
stats->tx_bytes += BNXT_GET_RING_STATS64(sw, tx_ucast_bytes);
stats->tx_bytes += BNXT_GET_RING_STATS64(sw, tx_mcast_bytes);
stats->tx_bytes += BNXT_GET_RING_STATS64(sw, tx_bcast_bytes);
@@ -13209,6 +13247,8 @@ static void bnxt_get_one_ring_drv_stats(struct bnxt *bp,
stats->rx_total_buf_errors += sw_stats.rx.rx_buf_errors;
stats->rx_total_oom_discards += sw_stats.rx.rx_oom_discards;
stats->rx_total_netpoll_discards += sw_stats.rx.rx_netpoll_discards;
+ stats->rx_total_packets += sw_stats.rx.rx_packets;
+ stats->rx_total_bytes += sw_stats.rx.rx_bytes;
stats->rx_total_ring_discards +=
BNXT_GET_RING_STATS64(hw_stats, rx_discard_pkts);
stats->tx_total_resets += sw_stats.tx.tx_resets;
@@ -15601,23 +15641,17 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
struct netdev_queue_stats_rx *stats)
{
struct bnxt *bp = netdev_priv(dev);
- struct bnxt_cp_ring_info *cpr;
- u64 *sw;
+ struct bnxt_sw_stats *sw_stats;
+ unsigned int seq;
- cpr = &bp->bnapi[i]->cp_ring;
- sw = cpr->stats.sw_stats;
+ sw_stats = bp->bnapi[i]->cp_ring.sw_stats;
- stats->packets = 0;
- stats->packets += BNXT_GET_RING_STATS64(sw, rx_ucast_pkts);
- stats->packets += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts);
- stats->packets += BNXT_GET_RING_STATS64(sw, rx_bcast_pkts);
-
- stats->bytes = 0;
- stats->bytes += BNXT_GET_RING_STATS64(sw, rx_ucast_bytes);
- stats->bytes += BNXT_GET_RING_STATS64(sw, rx_mcast_bytes);
- stats->bytes += BNXT_GET_RING_STATS64(sw, rx_bcast_bytes);
-
- stats->alloc_fail = cpr->sw_stats->rx.rx_oom_discards;
+ do {
+ seq = u64_stats_fetch_begin(&sw_stats->rx.syncp);
+ stats->packets = sw_stats->rx.rx_packets;
+ stats->bytes = sw_stats->rx.rx_bytes;
+ stats->alloc_fail = sw_stats->rx.rx_oom_discards;
+ } while (u64_stats_fetch_retry(&sw_stats->rx.syncp, seq));
}
static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
@@ -15647,8 +15681,8 @@ static void bnxt_get_base_stats(struct net_device *dev,
{
struct bnxt *bp = netdev_priv(dev);
- rx->packets = bp->net_stats_prev.rx_packets;
- rx->bytes = bp->net_stats_prev.rx_bytes;
+ rx->packets = bp->ring_drv_stats_prev.rx_total_packets;
+ rx->bytes = bp->ring_drv_stats_prev.rx_total_bytes;
rx->alloc_fail = bp->ring_drv_stats_prev.rx_total_oom_discards;
tx->packets = bp->net_stats_prev.tx_packets;
--
2.48.1
Powered by blists - more mailing lists