summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx4/en_tx.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/en_tx.c')
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_tx.c121
1 files changed, 75 insertions, 46 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 817f4154b86d..87f35bcbeff8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -42,8 +42,9 @@
#include <linux/tcp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include <linux/moduleparam.h>
#include <linux/indirect_call_wrapper.h>
+#include <net/ipv6.h>
+#include <net/page_pool/helpers.h>
#include "mlx4_en.h"
@@ -65,7 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->size = size;
ring->size_mask = size - 1;
ring->sp_stride = stride;
- ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
+ ring->full_size = ring->size - HEADROOM - MLX4_MAX_DESC_TXBBS;
tmp = size * sizeof(struct mlx4_en_tx_info);
ring->tx_info = kvmalloc_node(tmp, GFP_KERNEL, node);
@@ -77,9 +78,11 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
en_dbg(DRV, priv, "Allocated tx_info ring at addr:%p size:%d\n",
ring->tx_info, tmp);
- ring->bounce_buf = kmalloc_node(MAX_DESC_SIZE, GFP_KERNEL, node);
+ ring->bounce_buf = kmalloc_node(MLX4_TX_BOUNCE_BUFFER_SIZE,
+ GFP_KERNEL, node);
if (!ring->bounce_buf) {
- ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
+ ring->bounce_buf = kmalloc(MLX4_TX_BOUNCE_BUFFER_SIZE,
+ GFP_KERNEL);
if (!ring->bounce_buf) {
err = -ENOMEM;
goto err_info;
@@ -226,7 +229,9 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
{
- return ring->prod - ring->cons > ring->full_size;
+ u32 used = READ_ONCE(ring->prod) - READ_ONCE(ring->cons);
+
+ return used > ring->full_size;
}
static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
@@ -346,16 +351,10 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
int napi_mode)
{
struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
- struct mlx4_en_rx_alloc frame = {
- .page = tx_info->page,
- .dma = tx_info->map0_dma,
- };
-
- if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
- dma_unmap_page(priv->ddev, tx_info->map0_dma,
- PAGE_SIZE, priv->dma_dir);
- put_page(tx_info->page);
- }
+ struct page_pool *pool = ring->recycle_ring->pp;
+
+ /* Note that napi_mode = 0 means ndo_close() path, not budget = 0 */
+ page_pool_put_full_page(pool, tx_info->page, !!napi_mode);
return tx_info->nr_txbb;
}
@@ -446,6 +445,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev,
if (unlikely(!priv->port_up))
return 0;
+ if (unlikely(!napi_budget) && cq->type == TX_XDP)
+ return 0;
netdev_txq_bql_complete_prefetchw(ring->tx_queue);
@@ -635,19 +636,28 @@ static int get_real_size(const struct sk_buff *skb,
struct net_device *dev,
int *lso_header_size,
bool *inline_ok,
- void **pfrag)
+ void **pfrag,
+ int *hopbyhop)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
int real_size;
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);
+ *hopbyhop = 0;
+ if (skb->encapsulation) {
+ *lso_header_size = skb_inner_tcp_all_headers(skb);
+ } else {
+ /* Detects large IPV6 TCP packets and prepares for removal of
+ * HBH header that has been pushed by ip6_xmit(),
+ * mainly so that tcpdump can dissect them.
+ */
+ if (ipv6_has_hopopt_jumbo(skb))
+ *hopbyhop = sizeof(struct hop_jumbo_hdr);
+ *lso_header_size = skb_tcp_all_headers(skb);
+ }
real_size = CTRL_SIZE + shinfo->nr_frags * DS_SIZE +
- ALIGN(*lso_header_size + 4, DS_SIZE);
+ ALIGN(*lso_header_size - *hopbyhop + 4, DS_SIZE);
if (unlikely(*lso_header_size != skb_headlen(skb))) {
/* We add a segment for the skb linear buffer only if
* it contains data */
@@ -688,32 +698,32 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
inl->byte_count = cpu_to_be32(1 << 31 | skb->len);
} else {
inl->byte_count = cpu_to_be32(1 << 31 | MIN_PKT_LEN);
- memset(((void *)(inl + 1)) + skb->len, 0,
+ memset(inl->data + skb->len, 0,
MIN_PKT_LEN - skb->len);
}
- skb_copy_from_linear_data(skb, inl + 1, hlen);
+ skb_copy_from_linear_data(skb, inl->data, hlen);
if (shinfo->nr_frags)
- memcpy(((void *)(inl + 1)) + hlen, fragptr,
+ memcpy(inl->data + hlen, fragptr,
skb_frag_size(&shinfo->frags[0]));
} else {
inl->byte_count = cpu_to_be32(1 << 31 | spc);
if (hlen <= spc) {
- skb_copy_from_linear_data(skb, inl + 1, hlen);
+ skb_copy_from_linear_data(skb, inl->data, hlen);
if (hlen < spc) {
- memcpy(((void *)(inl + 1)) + hlen,
+ memcpy(inl->data + hlen,
fragptr, spc - hlen);
fragptr += spc - hlen;
}
- inl = (void *) (inl + 1) + spc;
- memcpy(((void *)(inl + 1)), fragptr, skb->len - spc);
+ inl = (void *)inl->data + spc;
+ memcpy(inl->data, fragptr, skb->len - spc);
} else {
- skb_copy_from_linear_data(skb, inl + 1, spc);
- inl = (void *) (inl + 1) + spc;
- skb_copy_from_linear_data_offset(skb, spc, inl + 1,
+ skb_copy_from_linear_data(skb, inl->data, spc);
+ inl = (void *)inl->data + spc;
+ skb_copy_from_linear_data_offset(skb, spc, inl->data,
hlen - spc);
if (shinfo->nr_frags)
- memcpy(((void *)(inl + 1)) + hlen - spc,
+ memcpy(inl->data + hlen - spc,
fragptr,
skb_frag_size(&shinfo->frags[0]));
}
@@ -874,6 +884,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
int desc_size;
int real_size;
u32 index, bf_index;
+ struct ipv6hdr *h6;
__be32 op_own;
int lso_header_size;
void *fragptr = NULL;
@@ -882,6 +893,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
bool stop_queue;
bool inline_ok;
u8 data_offset;
+ int hopbyhop;
bool bf_ok;
tx_ind = skb_get_queue_mapping(skb);
@@ -891,18 +903,13 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_drop;
real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
- &inline_ok, &fragptr);
+ &inline_ok, &fragptr, &hopbyhop);
if (unlikely(!real_size))
goto tx_drop_count;
/* Align descriptor to TXBB size */
desc_size = ALIGN(real_size, TXBB_SIZE);
nr_txbb = desc_size >> LOG_TXBB_SIZE;
- if (unlikely(nr_txbb > MAX_DESC_TXBBS)) {
- if (netif_msg_tx_err(priv))
- en_warn(priv, "Oversized header or SG list\n");
- goto tx_drop_count;
- }
bf_ok = ring->bf_enabled;
if (skb_vlan_tag_present(skb)) {
@@ -930,6 +937,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
if (likely(index + nr_txbb <= ring->size))
tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
else {
+ if (unlikely(nr_txbb > MLX4_MAX_DESC_TXBBS)) {
+ if (netif_msg_tx_err(priv))
+ en_warn(priv, "Oversized header or SG list\n");
+ goto tx_drop_count;
+ }
tx_desc = (struct mlx4_en_tx_desc *) ring->bounce_buf;
bounce = true;
bf_ok = false;
@@ -944,7 +956,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
data = &tx_desc->data;
data_offset = offsetof(struct mlx4_en_tx_desc, data);
} else {
- int lso_align = ALIGN(lso_header_size + 4, DS_SIZE);
+ int lso_align = ALIGN(lso_header_size - hopbyhop + 4, DS_SIZE);
data = (void *)&tx_desc->lso + lso_align;
data_offset = offsetof(struct mlx4_en_tx_desc, lso) + lso_align;
@@ -977,7 +989,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
tx_info->ts_requested = 1;
}
- /* Prepare ctrl segement apart opcode+ownership, which depends on
+ /* Prepare ctrl segment apart opcode+ownership, which depends on
* whether LSO is used */
tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
@@ -1009,14 +1021,31 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
((ring->prod & ring->size) ?
cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
+ lso_header_size -= hopbyhop;
/* Fill in the LSO prefix */
tx_desc->lso.mss_hdr_size = cpu_to_be32(
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);
+ if (unlikely(hopbyhop)) {
+ /* remove the HBH header.
+ * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
+ */
+ memcpy(tx_desc->lso.header, skb->data, ETH_HLEN + sizeof(*h6));
+ h6 = (struct ipv6hdr *)((char *)tx_desc->lso.header + ETH_HLEN);
+ h6->nexthdr = IPPROTO_TCP;
+ /* Copy the TCP header after the IPv6 one */
+ memcpy(h6 + 1,
+ skb->data + ETH_HLEN + sizeof(*h6) +
+ sizeof(struct hop_jumbo_hdr),
+ tcp_hdrlen(skb));
+ /* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
+ } else {
+ /* Copy headers;
+ * note that we already verified that it is linear
+ */
+ memcpy(tx_desc->lso.header, skb->data, lso_header_size);
+ }
ring->tso_packets++;
i = shinfo->gso_segs;
@@ -1053,7 +1082,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
op_own |= cpu_to_be32(MLX4_WQE_CTRL_IIP);
}
- ring->prod += nr_txbb;
+ WRITE_ONCE(ring->prod, ring->prod + nr_txbb);
/* If we used a bounce buffer then copy descriptor back into place */
if (unlikely(bounce))
@@ -1162,7 +1191,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
data = &tx_desc->data;
- dma = frame->dma;
+ dma = page_pool_get_dma_addr(frame->page);
tx_info->page = frame->page;
frame->page = NULL;
@@ -1184,7 +1213,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
rx_ring->xdp_tx++;
- ring->prod += MLX4_EN_XDP_TX_NRTXBB;
+ WRITE_ONCE(ring->prod, ring->prod + MLX4_EN_XDP_TX_NRTXBB);
/* Ensure new descriptor hits memory
* before setting ownership of this descriptor to HW
generated by cgit (git 2.34.1) at 2025-12-27 17:40:18 +0000