| 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: <1497526540-30028-4-git-send-email-tariqt@mellanox.com>
Date: Thu, 15 Jun 2017 14:35:33 +0300
From: Tariq Toukan <tariqt@...lanox.com>
To: "David S. Miller" <davem@...emloft.net>
Cc: netdev@...r.kernel.org, Eran Ben Elisha <eranbe@...lanox.com>,
Saeed Mahameed <saeedm@...lanox.com>, kernel-team@...com,
Tariq Toukan <tariqt@...lanox.com>,
Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 03/10] net/mlx4_en: Improve receive data-path
Several small performance improvements in RX datapath,
including:
- Compiler branch predictor hints.
- Replace a multiplication with a shift operation.
- Minimize variables scope.
- Write-prefetch for packet header.
- Avoid trinary-operator ("?") when value can be preset in a matching
branch.
- Save a branch by updating RX ring doorbell within
mlx4_en_refill_rx_buffers(), which now returns void.
Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON
(enable by ethtool -L <interface> rx 1).
XDP_DROP packet rate:
Same (28.1 Mpps), lower CPU utilization (from ~100% to ~92%).
Drop packets in TC:
-------------------------------------
| Before | After | Gain |
IPv4 | 4.14 Mpps | 4.18 Mpps | 1% |
-------------------------------------
XDP_TX packet rate:
-------------------------------------
| Before | After | Gain |
IPv4 | 10.1 Mpps | 10.3 Mpps | 2% |
IPv6 | 10.1 Mpps | 10.3 Mpps | 2% |
-------------------------------------
Signed-off-by: Tariq Toukan <tariqt@...lanox.com>
Reviewed-by: Saeed Mahameed <saeedm@...lanox.com>
Cc: kernel-team@...com
Cc: Eric Dumazet <edumazet@...gle.com>
---
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 73 ++++++++++++++++--------------
1 file changed, 39 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index c4edae854f1b..507c48ef2674 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -134,10 +134,11 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring, int index,
gfp_t gfp)
{
- struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride);
+ struct mlx4_en_rx_desc *rx_desc = ring->buf +
+ (index << ring->log_stride);
struct mlx4_en_rx_alloc *frags = ring->rx_info +
(index << priv->log_rx_info);
- if (ring->page_cache.index > 0) {
+ if (likely(ring->page_cache.index > 0)) {
/* XDP uses a single page per frame */
if (!frags->page) {
ring->page_cache.index--;
@@ -178,6 +179,7 @@ static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
}
}
+/* Function not in fast-path */
static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
{
struct mlx4_en_rx_ring *ring;
@@ -539,14 +541,14 @@ static void validate_loopback(struct mlx4_en_priv *priv, void *va)
priv->loopback_ok = 1;
}
-static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
+static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring)
{
u32 missing = ring->actual_size - (ring->prod - ring->cons);
/* Try to batch allocations, but not too much. */
if (missing < 8)
- return false;
+ return;
do {
if (mlx4_en_prepare_rx_desc(priv, ring,
ring->prod & ring->size_mask,
@@ -554,9 +556,9 @@ static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
__GFP_MEMALLOC))
break;
ring->prod++;
- } while (--missing);
+ } while (likely(--missing));
- return true;
+ mlx4_en_update_rx_prod_db(ring);
}
/* When hardware doesn't strip the vlan, we need to calculate the checksum
@@ -637,21 +639,14 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_dev *mdev = priv->mdev;
- struct mlx4_cqe *cqe;
- struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
- struct mlx4_en_rx_alloc *frags;
+ int factor = priv->cqe_factor;
+ struct mlx4_en_rx_ring *ring;
struct bpf_prog *xdp_prog;
+ int cq_ring = cq->ring;
int doorbell_pending;
- struct sk_buff *skb;
- int index;
- int nr;
- unsigned int length;
+ struct mlx4_cqe *cqe;
int polled = 0;
- int ip_summed;
- int factor = priv->cqe_factor;
- u64 timestamp;
- bool l2_tunnel;
+ int index;
if (unlikely(!priv->port_up))
return 0;
@@ -659,6 +654,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
if (unlikely(budget <= 0))
return polled;
+ ring = priv->rx_ring[cq_ring];
+
/* Protect accesses to: ring->xdp_prog, priv->mac_hash list */
rcu_read_lock();
xdp_prog = rcu_dereference(ring->xdp_prog);
@@ -673,10 +670,17 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
/* Process all completed CQEs */
while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
cq->mcq.cons_index & cq->size)) {
+ struct mlx4_en_rx_alloc *frags;
+ enum pkt_hash_types hash_type;
+ struct sk_buff *skb;
+ unsigned int length;
+ int ip_summed;
void *va;
+ int nr;
frags = ring->rx_info + (index << priv->log_rx_info);
va = page_address(frags[0].page) + frags[0].page_offset;
+ prefetchw(va);
/*
* make sure we read the CQE after we read the ownership bit
*/
@@ -768,7 +772,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
break;
case XDP_TX:
if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
- length, cq->ring,
+ length, cq_ring,
&doorbell_pending))) {
frags[0].page = NULL;
goto next;
@@ -790,24 +794,27 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
ring->packets++;
skb = napi_get_frags(&cq->napi);
- if (!skb)
+ if (unlikely(!skb))
goto next;
if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
- timestamp = mlx4_en_get_cqe_ts(cqe);
- mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
+ u64 timestamp = mlx4_en_get_cqe_ts(cqe);
+
+ mlx4_en_fill_hwtstamps(priv->mdev, skb_hwtstamps(skb),
timestamp);
}
- skb_record_rx_queue(skb, cq->ring);
+ skb_record_rx_queue(skb, cq_ring);
if (likely(dev->features & NETIF_F_RXCSUM)) {
if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
MLX4_CQE_STATUS_UDP)) {
if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
cqe->checksum == cpu_to_be16(0xffff)) {
- ip_summed = CHECKSUM_UNNECESSARY;
- l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
+ bool l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
+
+ ip_summed = CHECKSUM_UNNECESSARY;
+ hash_type = PKT_HASH_TYPE_L4;
if (l2_tunnel)
skb->csum_level = 1;
ring->csum_ok++;
@@ -822,6 +829,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
goto csum_none;
} else {
ip_summed = CHECKSUM_COMPLETE;
+ hash_type = PKT_HASH_TYPE_L3;
ring->csum_complete++;
}
} else {
@@ -831,16 +839,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
} else {
csum_none:
ip_summed = CHECKSUM_NONE;
+ hash_type = PKT_HASH_TYPE_L3;
ring->csum_none++;
}
skb->ip_summed = ip_summed;
if (dev->features & NETIF_F_RXHASH)
skb_set_hash(skb,
be32_to_cpu(cqe->immed_rss_invalid),
- (ip_summed == CHECKSUM_UNNECESSARY) ?
- PKT_HASH_TYPE_L4 :
- PKT_HASH_TYPE_L3);
-
+ hash_type);
if ((cqe->vlan_my_qpn &
cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
@@ -867,13 +873,13 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
++cq->mcq.cons_index;
index = (cq->mcq.cons_index) & ring->size_mask;
cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor;
- if (++polled == budget)
+ if (unlikely(++polled == budget))
break;
}
rcu_read_unlock();
- if (polled) {
+ if (likely(polled)) {
if (doorbell_pending)
mlx4_en_xmit_doorbell(priv->tx_ring[TX_XDP][cq->ring]);
@@ -883,8 +889,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
}
AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled);
- if (mlx4_en_refill_rx_buffers(priv, ring))
- mlx4_en_update_rx_prod_db(ring);
+ mlx4_en_refill_rx_buffers(priv, ring);
return polled;
}
@@ -936,7 +941,7 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
done--;
}
/* Done for now */
- if (napi_complete_done(napi, done))
+ if (likely(napi_complete_done(napi, done)))
mlx4_en_arm_cq(priv, cq);
return done;
}
--
1.8.3.1
Powered by blists - more mailing lists