| 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: <1411858593.15768.51.camel@edumazet-glaptop2.roam.corp.google.com>
Date: Sat, 27 Sep 2014 15:56:33 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: Or Gerlitz <gerlitz.or@...il.com>
Cc: Alexei Starovoitov <ast@...mgrid.com>,
"David S. Miller" <davem@...emloft.net>,
Jesper Dangaard Brouer <brouer@...hat.com>,
Eric Dumazet <edumazet@...gle.com>,
John Fastabend <john.r.fastabend@...el.com>,
Linux Netdev List <netdev@...r.kernel.org>,
Amir Vadai <amirv@...lanox.com>,
Or Gerlitz <or.gerlitz@...il.com>
Subject: [PATCH net-next] mlx4: optimize xmit path
From: Eric Dumazet <edumazet@...gle.com>
First I implemented skb->xmit_more support, and pktgen throughput
went from ~5Mpps to ~10Mpps.
Then, looking closely at this driver I found false sharing problems that
should be addressed by this patch, as my pktgen now reaches 14.7 Mpps
on a single TX queue, with a burst factor of 8.
So this patch in a whole permits to improve raw performance on a single
TX queue from about 5 Mpps to 14.7 Mpps.
Note that if packets are below the inline_thold threshold (104 bytes),
driver copies packets content into tx descriptor, and throughput
is lowered to ~7 Mpps :
-> We might reconsider inlining strategy in a followup patch.
I could split this patch into multiple components, but I prefer not
spend days on this work.
Lets instead list all changes I did :
1) align struct mlx4_en_tx_info to a cache line
2) add frag0_dma/frag0_byte_count into mlx4_en_tx_info to avoid a cache
line miss in TX completion for frames having one dma element.
(We avoid reading back the tx descriptor)
Note this could be extended to 2/3 dma elements later,
as we have free room in mlx4_en_tx_info
3) reorganize struct mlx4_en_tx_ring to have
3.1 - One cache line containing last_nr_txbb & cons,
used by tx completion.
3.2 - One cache line containing fields dirtied by mlx4_en_xmit()
3.3 - Following part is read mostly and shared by cpus.
4) struct mlx4_bf @offset field reduced to unsigned int to save space
so that the 3.2 part is only 64 bytes, or one cache line on x86.
5) doorbell_qpn is stored in the cpu_to_be32() way to avoid bswap() in
fast path
6) mdev->mr.key stored in ring->mr_key to also avoid bswap() and access
to cold cache line.
7) mlx4_en_free_tx_desc() no longer accesses skb_shinfo(). We use a new
nr_frags fields in mlx4_en_tx_info to avoid 2 or 3 cache misses.
8) mlx4_en_free_tx_desc() uses a prefetchw(&skb->users) to speed up
consume_skb()
9) mlx4_en_process_tx_cq() carefully fetches and writes
ring->last_nr_txbb & ring->cons only one time to avoid false sharing
10) mlx4_en_xmit() reads ring->cons once, and ahead of time to avoid
stalls.
11) prefetchw(&ring->tx_queue->dql) to speed up BQL update
12) properly clears tx_info->ts_requested :
This field was never cleared.
13) Support skb->xmit_more to avoid the expensive doorbell
14) reorganize code to call is_inline() once, so compiler can inline it.
15) rename @i variable to @i_frag to avoid confusion, as the
"goto tx_drop_unmap;" relied on this @i variable.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 312 ++++++++++-------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 89 ++--
include/linux/mlx4/device.h | 2
3 files changed, 241 insertions(+), 162 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c44f4237b9be..fa29d53860a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -191,12 +191,12 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
ring->prod = 0;
ring->cons = 0xffffffff;
ring->last_nr_txbb = 1;
- ring->poll_cnt = 0;
memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info));
memset(ring->buf, 0, ring->buf_size);
ring->qp_state = MLX4_QP_STATE_RST;
- ring->doorbell_qpn = ring->qp.qpn << 8;
+ ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8);
+ ring->mr_key = cpu_to_be32(mdev->mr.key);
mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
ring->cqn, user_prio, &ring->context);
@@ -259,38 +259,45 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring,
int index, u8 owner, u64 timestamp)
{
- struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
struct mlx4_wqe_data_seg *data = (void *) tx_desc + tx_info->data_offset;
- struct sk_buff *skb = tx_info->skb;
- struct skb_frag_struct *frag;
void *end = ring->buf + ring->buf_size;
- int frags = skb_shinfo(skb)->nr_frags;
+ struct sk_buff *skb = tx_info->skb;
+ int nr_frags = tx_info->nr_frags;
int i;
- struct skb_shared_hwtstamps hwts;
- if (timestamp) {
- mlx4_en_fill_hwtstamps(mdev, &hwts, timestamp);
+ /* We do not touch skb here, so prefetch skb->users location
+ * to speedup consume_skb()
+ */
+ prefetchw(&skb->users);
+
+ if (unlikely(timestamp)) {
+ struct skb_shared_hwtstamps hwts;
+
+ mlx4_en_fill_hwtstamps(priv->mdev, &hwts, timestamp);
skb_tstamp_tx(skb, &hwts);
}
/* Optimize the common case when there are no wraparounds */
if (likely((void *) tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) {
if (!tx_info->inl) {
- if (tx_info->linear) {
+ if (tx_info->linear)
dma_unmap_single(priv->ddev,
- (dma_addr_t) be64_to_cpu(data->addr),
- be32_to_cpu(data->byte_count),
- PCI_DMA_TODEVICE);
- ++data;
- }
-
- for (i = 0; i < frags; i++) {
- frag = &skb_shinfo(skb)->frags[i];
+ tx_info->frag0_dma,
+ tx_info->frag0_byte_count,
+ PCI_DMA_TODEVICE);
+ else
+ dma_unmap_page(priv->ddev,
+ tx_info->frag0_dma,
+ tx_info->frag0_byte_count,
+ PCI_DMA_TODEVICE);
+ for (i = 1; i < nr_frags; i++) {
+ data++;
dma_unmap_page(priv->ddev,
- (dma_addr_t) be64_to_cpu(data[i].addr),
- skb_frag_size(frag), PCI_DMA_TODEVICE);
+ (dma_addr_t)be64_to_cpu(data->addr),
+ be32_to_cpu(data->byte_count),
+ PCI_DMA_TODEVICE);
}
}
} else {
@@ -299,22 +306,24 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
data = ring->buf + ((void *)data - end);
}
- if (tx_info->linear) {
+ if (tx_info->linear)
dma_unmap_single(priv->ddev,
- (dma_addr_t) be64_to_cpu(data->addr),
- be32_to_cpu(data->byte_count),
- PCI_DMA_TODEVICE);
- ++data;
- }
-
- for (i = 0; i < frags; i++) {
+ tx_info->frag0_dma,
+ tx_info->frag0_byte_count,
+ PCI_DMA_TODEVICE);
+ else
+ dma_unmap_page(priv->ddev,
+ tx_info->frag0_dma,
+ tx_info->frag0_byte_count,
+ PCI_DMA_TODEVICE);
+ for (i = 1; i < nr_frags; i++) {
/* Check for wraparound before unmapping */
if ((void *) data >= end)
data = ring->buf;
- frag = &skb_shinfo(skb)->frags[i];
dma_unmap_page(priv->ddev,
- (dma_addr_t) be64_to_cpu(data->addr),
- skb_frag_size(frag), PCI_DMA_TODEVICE);
+ (dma_addr_t)be64_to_cpu(data->addr),
+ be32_to_cpu(data->byte_count),
+ PCI_DMA_TODEVICE);
++data;
}
}
@@ -377,13 +386,18 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
u64 timestamp = 0;
int done = 0;
int budget = priv->tx_work_limit;
+ u32 last_nr_txbb;
+ u32 ring_cons;
if (!priv->port_up)
return true;
+ prefetchw(&ring->tx_queue->dql.limit);
index = cons_index & size_mask;
cqe = mlx4_en_get_cqe(buf, index, priv->cqe_size) + factor;
- ring_index = ring->cons & size_mask;
+ last_nr_txbb = ACCESS_ONCE(ring->last_nr_txbb);
+ ring_cons = ACCESS_ONCE(ring->cons);
+ ring_index = ring_cons & size_mask;
stamp_index = ring_index;
/* Process all completed CQEs */
@@ -408,19 +422,19 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
do {
- txbbs_skipped += ring->last_nr_txbb;
- ring_index = (ring_index + ring->last_nr_txbb) & size_mask;
+ txbbs_skipped += last_nr_txbb;
+ ring_index = (ring_index + last_nr_txbb) & size_mask;
if (ring->tx_info[ring_index].ts_requested)
timestamp = mlx4_en_get_cqe_ts(cqe);
/* free next descriptor */
- ring->last_nr_txbb = mlx4_en_free_tx_desc(
+ last_nr_txbb = mlx4_en_free_tx_desc(
priv, ring, ring_index,
- !!((ring->cons + txbbs_skipped) &
+ !!((ring_cons + txbbs_skipped) &
ring->size), timestamp);
mlx4_en_stamp_wqe(priv, ring, stamp_index,
- !!((ring->cons + txbbs_stamp) &
+ !!((ring_cons + txbbs_stamp) &
ring->size));
stamp_index = ring_index;
txbbs_stamp = txbbs_skipped;
@@ -441,7 +455,11 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
mcq->cons_index = cons_index;
mlx4_cq_set_ci(mcq);
wmb();
- ring->cons += txbbs_skipped;
+
+ /* we want to dirty this cache line once */
+ ACCESS_ONCE(ring->last_nr_txbb) = last_nr_txbb;
+ ACCESS_ONCE(ring->cons) = ring_cons + txbbs_skipped;
+
netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
/*
@@ -512,30 +530,35 @@ static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv,
return ring->buf + index * TXBB_SIZE;
}
-static int is_inline(int inline_thold, struct sk_buff *skb, void **pfrag)
+/* Decide if skb can be inlined in tx descriptor to avoid dma mapping
+ *
+ * It seems strange we do not simply use skb_copy_bits().
+ * This would allow to inline all skbs iff skb->len <= inline_thold
+ *
+ * Note that caller already checked skb was not a gso packet
+ */
+static bool is_inline(int inline_thold, const struct sk_buff *skb,
+ const struct skb_shared_info *shinfo,
+ void **pfrag)
{
void *ptr;
- if (inline_thold && !skb_is_gso(skb) && skb->len <= inline_thold) {
- if (skb_shinfo(skb)->nr_frags == 1) {
- ptr = skb_frag_address_safe(&skb_shinfo(skb)->frags[0]);
- if (unlikely(!ptr))
- return 0;
-
- if (pfrag)
- *pfrag = ptr;
+ if (skb->len > inline_thold || !inline_thold)
+ return false;
- return 1;
- } else if (unlikely(skb_shinfo(skb)->nr_frags))
- return 0;
- else
- return 1;
+ if (shinfo->nr_frags == 1) {
+ ptr = skb_frag_address_safe(&shinfo->frags[0]);
+ if (unlikely(!ptr))
+ return false;
+ *pfrag = ptr;
+ return true;
}
-
- return 0;
+ if (shinfo->nr_frags)
+ return false;
+ return true;
}
-static int inline_size(struct sk_buff *skb)
+static int inline_size(const struct sk_buff *skb)
{
if (skb->len + CTRL_SIZE + sizeof(struct mlx4_wqe_inline_seg)
<= MLX4_INLINE_ALIGN)
@@ -546,18 +569,23 @@ static int inline_size(struct sk_buff *skb)
sizeof(struct mlx4_wqe_inline_seg), 16);
}
-static int get_real_size(struct sk_buff *skb, struct net_device *dev,
- int *lso_header_size)
+static int get_real_size(const struct sk_buff *skb,
+ const struct skb_shared_info *shinfo,
+ struct net_device *dev,
+ int *lso_header_size,
+ bool *inline_ok,
+ void **pfrag)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
int real_size;
- if (skb_is_gso(skb)) {
+ if (shinfo->gso_size) {
+ *inline_ok = false;
if (skb->encapsulation)
*lso_header_size = (skb_inner_transport_header(skb) - skb->data) + inner_tcp_hdrlen(skb);
else
*lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
- real_size = CTRL_SIZE + skb_shinfo(skb)->nr_frags * DS_SIZE +
+ real_size = CTRL_SIZE + shinfo->nr_frags * DS_SIZE +
ALIGN(*lso_header_size + 4, DS_SIZE);
if (unlikely(*lso_header_size != skb_headlen(skb))) {
/* We add a segment for the skb linear buffer only if
@@ -572,17 +600,24 @@ static int get_real_size(struct sk_buff *skb, struct net_device *dev,
}
} else {
*lso_header_size = 0;
- if (!is_inline(priv->prof->inline_thold, skb, NULL))
- real_size = CTRL_SIZE + (skb_shinfo(skb)->nr_frags + 1) * DS_SIZE;
- else
+ *inline_ok = is_inline(priv->prof->inline_thold, skb,
+ shinfo, pfrag);
+
+ if (*inline_ok)
real_size = inline_size(skb);
+ else
+ real_size = CTRL_SIZE +
+ (shinfo->nr_frags + 1) * DS_SIZE;
}
return real_size;
}
-static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *skb,
- int real_size, u16 *vlan_tag, int tx_ind, void *fragptr)
+static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
+ const struct sk_buff *skb,
+ const struct skb_shared_info *shinfo,
+ int real_size, u16 *vlan_tag,
+ int tx_ind, void *fragptr)
{
struct mlx4_wqe_inline_seg *inl = &tx_desc->inl;
int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl;
@@ -596,9 +631,9 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
MIN_PKT_LEN - skb->len);
}
skb_copy_from_linear_data(skb, inl + 1, skb_headlen(skb));
- if (skb_shinfo(skb)->nr_frags)
+ if (shinfo->nr_frags)
memcpy(((void *)(inl + 1)) + skb_headlen(skb), fragptr,
- skb_frag_size(&skb_shinfo(skb)->frags[0]));
+ skb_frag_size(&shinfo->frags[0]));
} else {
inl->byte_count = cpu_to_be32(1 << 31 | spc);
@@ -616,9 +651,10 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
inl = (void *) (inl + 1) + spc;
skb_copy_from_linear_data_offset(skb, spc, inl + 1,
skb_headlen(skb) - spc);
- if (skb_shinfo(skb)->nr_frags)
+ if (shinfo->nr_frags)
memcpy(((void *)(inl + 1)) + skb_headlen(skb) - spc,
- fragptr, skb_frag_size(&skb_shinfo(skb)->frags[0]));
+ fragptr,
+ skb_frag_size(&shinfo->frags[0]));
}
wmb();
@@ -642,7 +678,8 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
return fallback(dev, skb) % rings_p_up + up * rings_p_up;
}
-static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt)
+static void mlx4_bf_copy(void __iomem *dst, const void *src,
+ unsigned int bytecnt)
{
__iowrite64_copy(dst, src, bytecnt / 8);
}
@@ -663,15 +700,26 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
u32 index, bf_index;
__be32 op_own;
u16 vlan_tag = 0;
- int i;
+ int i_frag;
int lso_header_size;
- void *fragptr;
+ void *fragptr = NULL;
bool bounce = false;
+ bool send_doorbell;
+ u32 ring_cons;
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+ bool inline_ok;
if (!priv->port_up)
goto tx_drop;
- real_size = get_real_size(skb, dev, &lso_header_size);
+ tx_ind = skb_get_queue_mapping(skb);
+ ring = priv->tx_ring[tx_ind];
+
+ /* fetch ring->cons far ahead before needing it to avoid stall */
+ ring_cons = ACCESS_ONCE(ring->cons);
+
+ real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
+ &inline_ok, &fragptr);
if (unlikely(!real_size))
goto tx_drop;
@@ -684,13 +732,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_drop;
}
- tx_ind = skb->queue_mapping;
- ring = priv->tx_ring[tx_ind];
if (vlan_tx_tag_present(skb))
vlan_tag = vlan_tx_tag_get(skb);
/* Check available TXBBs And 2K spare for prefetch */
- if (unlikely(((int)(ring->prod - ring->cons)) >
+ if (unlikely(((int)(ring->prod - ring_cons)) >
ring->size - HEADROOM - MAX_DESC_TXBBS)) {
/* every full Tx ring stops queue */
netif_tx_stop_queue(ring->tx_queue);
@@ -704,7 +750,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
*/
wmb();
- if (unlikely(((int)(ring->prod - ring->cons)) <=
+ ring_cons = ACCESS_ONCE(ring->cons);
+ if (unlikely(((int)(ring->prod - ring_cons)) <=
ring->size - HEADROOM - MAX_DESC_TXBBS)) {
netif_tx_wake_queue(ring->tx_queue);
ring->wake_queue++;
@@ -713,9 +760,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
}
}
+ prefetchw(&ring->tx_queue->dql);
+
/* Track current inflight packets for performance analysis */
AVG_PERF_COUNTER(priv->pstats.inflight_avg,
- (u32) (ring->prod - ring->cons - 1));
+ (u32)(ring->prod - ring_cons - 1));
/* Packet is good - grab an index and transmit it */
index = ring->prod & ring->size_mask;
@@ -735,31 +784,34 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
tx_info->skb = skb;
tx_info->nr_txbb = nr_txbb;
+ data = &tx_desc->data;
if (lso_header_size)
data = ((void *)&tx_desc->lso + ALIGN(lso_header_size + 4,
DS_SIZE));
- else
- data = &tx_desc->data;
/* valid only for none inline segments */
tx_info->data_offset = (void *)data - (void *)tx_desc;
+ tx_info->inl = inline_ok;
+
tx_info->linear = (lso_header_size < skb_headlen(skb) &&
- !is_inline(ring->inline_thold, skb, NULL)) ? 1 : 0;
+ !inline_ok) ? 1 : 0;
- data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1;
+ tx_info->nr_frags = shinfo->nr_frags + tx_info->linear;
+ data += tx_info->nr_frags - 1;
- if (is_inline(ring->inline_thold, skb, &fragptr)) {
- tx_info->inl = 1;
- } else {
- /* Map fragments */
- for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+ if (!tx_info->inl) {
+ dma_addr_t dma = 0;
+ u32 byte_count = 0;
+
+ /* Map fragments if any */
+ for (i_frag = shinfo->nr_frags - 1; i_frag >= 0; i_frag--) {
struct skb_frag_struct *frag;
- dma_addr_t dma;
- frag = &skb_shinfo(skb)->frags[i];
+ frag = &shinfo->frags[i_frag];
+ byte_count = skb_frag_size(frag);
dma = skb_frag_dma_map(ddev, frag,
- 0, skb_frag_size(frag),
+ 0, byte_count,
DMA_TO_DEVICE);
if (dma_mapping_error(ddev, dma))
goto tx_drop_unmap;
@@ -767,14 +819,13 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
data->addr = cpu_to_be64(dma);
data->lkey = cpu_to_be32(mdev->mr.key);
wmb();
- data->byte_count = cpu_to_be32(skb_frag_size(frag));
+ data->byte_count = cpu_to_be32(byte_count);
--data;
}
- /* Map linear part */
+ /* Map linear part if needed */
if (tx_info->linear) {
- u32 byte_count = skb_headlen(skb) - lso_header_size;
- dma_addr_t dma;
+ byte_count = skb_headlen(skb) - lso_header_size;
dma = dma_map_single(ddev, skb->data +
lso_header_size, byte_count,
@@ -787,25 +838,24 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
wmb();
data->byte_count = cpu_to_be32(byte_count);
}
- tx_info->inl = 0;
+ /* tx completion can avoid cache line miss for common cases */
+ tx_info->frag0_dma = dma;
+ tx_info->frag0_byte_count = byte_count;
}
/*
* For timestamping add flag to skb_shinfo and
* set flag for further reference
*/
- if (ring->hwtstamp_tx_type == HWTSTAMP_TX_ON &&
- skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
- skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+ tx_info->ts_requested = 0;
+ if (unlikely(ring->hwtstamp_tx_type == HWTSTAMP_TX_ON &&
+ shinfo->tx_flags & SKBTX_HW_TSTAMP)) {
+ shinfo->tx_flags |= SKBTX_IN_PROGRESS;
tx_info->ts_requested = 1;
}
/* Prepare ctrl segement apart opcode+ownership, which depends on
* whether LSO is used */
- tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
- tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
- !!vlan_tx_tag_present(skb);
- tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
@@ -826,6 +876,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
/* Handle LSO (TSO) packets */
if (lso_header_size) {
+ int i;
+
/* Mark opcode as LSO */
op_own = cpu_to_be32(MLX4_OPCODE_LSO | (1 << 6)) |
((ring->prod & ring->size) ?
@@ -833,15 +885,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
/* Fill in the LSO prefix */
tx_desc->lso.mss_hdr_size = cpu_to_be32(
- skb_shinfo(skb)->gso_size << 16 | lso_header_size);
+ shinfo->gso_size << 16 | lso_header_size);
/* Copy headers;
* note that we already verified that it is linear */
memcpy(tx_desc->lso.header, skb->data, lso_header_size);
priv->port_stats.tso_packets++;
- i = ((skb->len - lso_header_size) / skb_shinfo(skb)->gso_size) +
- !!((skb->len - lso_header_size) % skb_shinfo(skb)->gso_size);
+ i = ((skb->len - lso_header_size) / shinfo->gso_size) +
+ !!((skb->len - lso_header_size) % shinfo->gso_size);
tx_info->nr_bytes = skb->len + (i - 1) * lso_header_size;
ring->packets += i;
} else {
@@ -851,16 +903,14 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
tx_info->nr_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
ring->packets++;
-
}
ring->bytes += tx_info->nr_bytes;
netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes);
AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len);
- if (tx_info->inl) {
- build_inline_wqe(tx_desc, skb, real_size, &vlan_tag, tx_ind, fragptr);
- tx_info->inl = 1;
- }
+ if (tx_info->inl)
+ build_inline_wqe(tx_desc, skb, shinfo, real_size,
+ &vlan_tag, tx_ind, fragptr);
if (skb->encapsulation) {
struct iphdr *ipv4 = (struct iphdr *)skb_inner_network_header(skb);
@@ -873,35 +923,53 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
ring->prod += nr_txbb;
/* If we used a bounce buffer then copy descriptor back into place */
- if (bounce)
+ if (unlikely(bounce))
tx_desc = mlx4_en_bounce_to_desc(priv, ring, index, desc_size);
skb_tx_timestamp(skb);
- if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tx_tag_present(skb)) {
- tx_desc->ctrl.bf_qpn |= cpu_to_be32(ring->doorbell_qpn);
+ real_size = (real_size / 16) & 0x3f;
+
+ send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue);
+
+ if (ring->bf_enabled && desc_size <= MAX_BF && !bounce &&
+ !vlan_tx_tag_present(skb) && send_doorbell) {
+ tx_desc->ctrl.bf_qpn = ring->doorbell_qpn |
+ cpu_to_be32(real_size);
op_own |= htonl((bf_index & 0xffff) << 8);
- /* Ensure new descirptor hits memory
- * before setting ownership of this descriptor to HW */
+ /* Ensure new descriptor hits memory
+ * before setting ownership of this descriptor to HW
+ */
wmb();
tx_desc->ctrl.owner_opcode = op_own;
wmb();
- mlx4_bf_copy(ring->bf.reg + ring->bf.offset, (unsigned long *) &tx_desc->ctrl,
- desc_size);
+ mlx4_bf_copy(ring->bf.reg + ring->bf.offset,
+ &tx_desc->ctrl,
+ desc_size);
wmb();
ring->bf.offset ^= ring->bf.buf_size;
} else {
- /* Ensure new descirptor hits memory
- * before setting ownership of this descriptor to HW */
+ tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
+ tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
+ !!vlan_tx_tag_present(skb);
+ tx_desc->ctrl.fence_size = real_size;
+
+ /* Ensure new descriptor hits memory
+ * before setting ownership of this descriptor to HW
+ */
wmb();
tx_desc->ctrl.owner_opcode = op_own;
- wmb();
- iowrite32be(ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL);
+
+ if (send_doorbell) {
+ wmb(); /* ensure owner_opcode is written */
+ iowrite32(ring->doorbell_qpn,
+ ring->bf.uar->map + MLX4_SEND_DOORBELL);
+ }
}
return NETDEV_TX_OK;
@@ -909,8 +977,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
tx_drop_unmap:
en_err(priv, "DMA mapping error\n");
- for (i++; i < skb_shinfo(skb)->nr_frags; i++) {
- data++;
+ while (++i_frag < shinfo->nr_frags) {
+ ++data;
dma_unmap_page(ddev, (dma_addr_t) be64_to_cpu(data->addr),
be32_to_cpu(data->byte_count),
PCI_DMA_TODEVICE);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 6a4fc2394cf2..8025e3c0b14e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -216,13 +216,16 @@ enum cq_type {
struct mlx4_en_tx_info {
struct sk_buff *skb;
- u32 nr_txbb;
- u32 nr_bytes;
- u8 linear;
- u8 data_offset;
- u8 inl;
- u8 ts_requested;
-};
+ dma_addr_t frag0_dma;
+ u32 frag0_byte_count;
+ u32 nr_txbb;
+ u32 nr_bytes;
+ u8 linear;
+ u8 data_offset;
+ u8 inl;
+ u8 ts_requested;
+ u8 nr_frags;
+} ____cacheline_aligned_in_smp;
#define MLX4_EN_BIT_DESC_OWN 0x80000000
@@ -253,39 +256,47 @@ struct mlx4_en_rx_alloc {
};
struct mlx4_en_tx_ring {
+ /* cache line used and dirtied in tx completion
+ * (mlx4_en_free_tx_buf())
+ */
+ u32 last_nr_txbb;
+ u32 cons;
+
+ /* cache line used and dirtied in mlx4_en_xmit()
+ */
+ u32 prod ____cacheline_aligned_in_smp;
+ unsigned long bytes;
+ unsigned long packets;
+ unsigned long tx_csum;
+ struct mlx4_bf bf;
+ unsigned long queue_stopped;
+ unsigned long wake_queue;
+
+ /* Following part should be mostly read
+ */
+ cpumask_t affinity_mask;
+ struct mlx4_qp qp;
struct mlx4_hwq_resources wqres;
- u32 size ; /* number of TXBBs */
- u32 size_mask;
- u16 stride;
- u16 cqn; /* index of port CQ associated with this ring */
- u32 prod;
- u32 cons;
- u32 buf_size;
- u32 doorbell_qpn;
- void *buf;
- u16 poll_cnt;
- struct mlx4_en_tx_info *tx_info;
- u8 *bounce_buf;
- u8 queue_index;
- cpumask_t affinity_mask;
- u32 last_nr_txbb;
- struct mlx4_qp qp;
- struct mlx4_qp_context context;
- int qpn;
- enum mlx4_qp_state qp_state;
- struct mlx4_srq dummy;
- unsigned long bytes;
- unsigned long packets;
- unsigned long tx_csum;
- unsigned long queue_stopped;
- unsigned long wake_queue;
- struct mlx4_bf bf;
- bool bf_enabled;
- bool bf_alloced;
- struct netdev_queue *tx_queue;
- int hwtstamp_tx_type;
- int inline_thold;
-};
+ u32 size ; /* number of TXBBs */
+ u32 size_mask;
+ u16 stride;
+ u16 cqn; /* index of port CQ associated with this ring */
+ u32 buf_size;
+ __be32 doorbell_qpn;
+ __be32 mr_key;
+ void *buf;
+ struct mlx4_en_tx_info *tx_info;
+ u8 *bounce_buf;
+ struct mlx4_qp_context context;
+ int qpn;
+ enum mlx4_qp_state qp_state;
+ u8 queue_index;
+ bool bf_enabled;
+ bool bf_alloced;
+ struct netdev_queue *tx_queue;
+ int hwtstamp_tx_type;
+ int inline_thold;
+} ____cacheline_aligned_in_smp;
struct mlx4_en_rx_desc {
/* actual number of entries depends on rx ring stride */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 03b5608a4329..5e5ad07548b8 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -583,7 +583,7 @@ struct mlx4_uar {
};
struct mlx4_bf {
- unsigned long offset;
+ unsigned int offset;
int buf_size;
struct mlx4_uar *uar;
void __iomem *reg;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists