#include "gve.h"
#include "gve_adminq.h"
#include "gve_utils.h"
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/vmalloc.h>
#include <linux/skbuff.h>
#include <net/xdp_sock_drv.h>
static inline void gve_tx_put_doorbell(struct gve_priv *priv,
struct gve_queue_resources *q_resources,
u32 val)
{
iowrite32be(val, &priv->db_bar2[be32_to_cpu(q_resources->db_index)]);
}
void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid)
{
u32 tx_qid = gve_xdp_tx_queue_id(priv, xdp_qid);
struct gve_tx_ring *tx = &priv->tx[tx_qid];
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
}
static int gve_tx_fifo_init(struct gve_priv *priv, struct gve_tx_fifo *fifo)
{
fifo->base = vmap(fifo->qpl->pages, fifo->qpl->num_entries, VM_MAP,
PAGE_KERNEL);
if (unlikely(!fifo->base)) {
netif_err(priv, drv, priv->dev, "Failed to vmap fifo, qpl_id = %d\n",
fifo->qpl->id);
return -ENOMEM;
}
fifo->size = fifo->qpl->num_entries * PAGE_SIZE;
atomic_set(&fifo->available, fifo->size);
fifo->head = 0;
return 0;
}
static void gve_tx_fifo_release(struct gve_priv *priv, struct gve_tx_fifo *fifo)
{
WARN(atomic_read(&fifo->available) != fifo->size,
"Releasing non-empty fifo");
vunmap(fifo->base);
}
static int gve_tx_fifo_pad_alloc_one_frag(struct gve_tx_fifo *fifo,
size_t bytes)
{
return (fifo->head + bytes < fifo->size) ? 0 : fifo->size - fifo->head;
}
static bool gve_tx_fifo_can_alloc(struct gve_tx_fifo *fifo, size_t bytes)
{
return (atomic_read(&fifo->available) <= bytes) ? false : true;
}
static int gve_tx_alloc_fifo(struct gve_tx_fifo *fifo, size_t bytes,
struct gve_tx_iovec iov[2])
{
size_t overflow, padding;
u32 aligned_head;
int nfrags = 0;
if (!bytes)
return 0;
WARN(!gve_tx_fifo_can_alloc(fifo, bytes),
"Reached %s when there's not enough space in the fifo", __func__);
nfrags++;
iov[0].iov_offset = fifo->head;
iov[0].iov_len = bytes;
fifo->head += bytes;
if (fifo->head > fifo->size) {
nfrags++;
overflow = fifo->head - fifo->size;
iov[0].iov_len -= overflow;
iov[1].iov_offset = 0;
iov[1].iov_len = overflow;
fifo->head = overflow;
}
aligned_head = L1_CACHE_ALIGN(fifo->head);
padding = aligned_head - fifo->head;
iov[nfrags - 1].iov_padding = padding;
atomic_sub(bytes + padding, &fifo->available);
fifo->head = aligned_head;
if (fifo->head == fifo->size)
fifo->head = 0;
return nfrags;
}
static void gve_tx_free_fifo(struct gve_tx_fifo *fifo, size_t bytes)
{
atomic_add(bytes, &fifo->available);
}
static size_t gve_tx_clear_buffer_state(struct gve_tx_buffer_state *info)
{
size_t space_freed = 0;
int i;
for (i = 0; i < ARRAY_SIZE(info->iov); i++) {
space_freed += info->iov[i].iov_len + info->iov[i].iov_padding;
info->iov[i].iov_len = 0;
info->iov[i].iov_padding = 0;
}
return space_freed;
}
static int gve_clean_xdp_done(struct gve_priv *priv, struct gve_tx_ring *tx,
u32 to_do)
{
struct gve_tx_buffer_state *info;
u32 clean_end = tx->done + to_do;
u64 pkts = 0, bytes = 0;
size_t space_freed = 0;
u32 xsk_complete = 0;
u32 idx;
for (; tx->done < clean_end; tx->done++) {
idx = tx->done & tx->mask;
info = &tx->info[idx];
if (unlikely(!info->xdp.size))
continue;
bytes += info->xdp.size;
pkts++;
xsk_complete += info->xdp.is_xsk;
info->xdp.size = 0;
if (info->xdp_frame) {
xdp_return_frame(info->xdp_frame);
info->xdp_frame = NULL;
}
space_freed += gve_tx_clear_buffer_state(info);
}
gve_tx_free_fifo(&tx->tx_fifo, space_freed);
if (xsk_complete > 0 && tx->xsk_pool)
xsk_tx_completed(tx->xsk_pool, xsk_complete);
u64_stats_update_begin(&tx->statss);
tx->bytes_done += bytes;
tx->pkt_done += pkts;
u64_stats_update_end(&tx->statss);
return pkts;
}
static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
u32 to_do, bool try_to_wake);
static void gve_tx_free_ring(struct gve_priv *priv, int idx)
{
struct gve_tx_ring *tx = &priv->tx[idx];
struct device *hdev = &priv->pdev->dev;
size_t bytes;
u32 slots;
gve_tx_remove_from_block(priv, idx);
slots = tx->mask + 1;
if (tx->q_num < priv->tx_cfg.num_queues) {
gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
netdev_tx_reset_queue(tx->netdev_txq);
} else {
gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt);
}
dma_free_coherent(hdev, sizeof(*tx->q_resources),
tx->q_resources, tx->q_resources_bus);
tx->q_resources = NULL;
if (!tx->raw_addressing) {
gve_tx_fifo_release(priv, &tx->tx_fifo);
gve_unassign_qpl(priv, tx->tx_fifo.qpl->id);
tx->tx_fifo.qpl = NULL;
}
bytes = sizeof(*tx->desc) * slots;
dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
tx->desc = NULL;
vfree(tx->info);
tx->info = NULL;
netif_dbg(priv, drv, priv->dev, "freed tx queue %d\n", idx);
}
static int gve_tx_alloc_ring(struct gve_priv *priv, int idx)
{
struct gve_tx_ring *tx = &priv->tx[idx];
struct device *hdev = &priv->pdev->dev;
u32 slots = priv->tx_desc_cnt;
size_t bytes;
memset(tx, 0, sizeof(*tx));
spin_lock_init(&tx->clean_lock);
spin_lock_init(&tx->xdp_lock);
tx->q_num = idx;
tx->mask = slots - 1;
tx->info = vcalloc(slots, sizeof(*tx->info));
if (!tx->info)
return -ENOMEM;
bytes = sizeof(*tx->desc) * slots;
tx->desc = dma_alloc_coherent(hdev, bytes, &tx->bus, GFP_KERNEL);
if (!tx->desc)
goto abort_with_info;
tx->raw_addressing = priv->queue_format == GVE_GQI_RDA_FORMAT;
tx->dev = &priv->pdev->dev;
if (!tx->raw_addressing) {
tx->tx_fifo.qpl = gve_assign_tx_qpl(priv, idx);
if (!tx->tx_fifo.qpl)
goto abort_with_desc;
if (gve_tx_fifo_init(priv, &tx->tx_fifo))
goto abort_with_qpl;
}
tx->q_resources =
dma_alloc_coherent(hdev,
sizeof(*tx->q_resources),
&tx->q_resources_bus,
GFP_KERNEL);
if (!tx->q_resources)
goto abort_with_fifo;
netif_dbg(priv, drv, priv->dev, "tx[%d]->bus=%lx\n", idx,
(unsigned long)tx->bus);
if (idx < priv->tx_cfg.num_queues)
tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx);
gve_tx_add_to_block(priv, idx);
return 0;
abort_with_fifo:
if (!tx->raw_addressing)
gve_tx_fifo_release(priv, &tx->tx_fifo);
abort_with_qpl:
if (!tx->raw_addressing)
gve_unassign_qpl(priv, tx->tx_fifo.qpl->id);
abort_with_desc:
dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
tx->desc = NULL;
abort_with_info:
vfree(tx->info);
tx->info = NULL;
return -ENOMEM;
}
int gve_tx_alloc_rings(struct gve_priv *priv, int start_id, int num_rings)
{
int err = 0;
int i;
for (i = start_id; i < start_id + num_rings; i++) {
err = gve_tx_alloc_ring(priv, i);
if (err) {
netif_err(priv, drv, priv->dev,
"Failed to alloc tx ring=%d: err=%d\n",
i, err);
break;
}
}
if (err) {
int j;
for (j = start_id; j < i; j++)
gve_tx_free_ring(priv, j);
}
return err;
}
void gve_tx_free_rings_gqi(struct gve_priv *priv, int start_id, int num_rings)
{
int i;
for (i = start_id; i < start_id + num_rings; i++)
gve_tx_free_ring(priv, i);
}
static inline u32 gve_tx_avail(struct gve_tx_ring *tx)
{
return tx->mask + 1 - (tx->req - tx->done);
}
static inline int gve_skb_fifo_bytes_required(struct gve_tx_ring *tx,
struct sk_buff *skb)
{
int pad_bytes, align_hdr_pad;
int bytes;
int hlen;
hlen = skb_is_gso(skb) ? skb_checksum_start_offset(skb) + tcp_hdrlen(skb) :
min_t(int, GVE_GQ_TX_MIN_PKT_DESC_BYTES, skb->len);
pad_bytes = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo,
hlen);
align_hdr_pad = L1_CACHE_ALIGN(hlen) - hlen;
bytes = align_hdr_pad + pad_bytes + skb->len;
return bytes;
}
#define MAX_TX_DESC_NEEDED (MAX_SKB_FRAGS + 4)
static void gve_tx_unmap_buf(struct device *dev, struct gve_tx_buffer_state *info)
{
if (info->skb) {
dma_unmap_single(dev, dma_unmap_addr(info, dma),
dma_unmap_len(info, len),
DMA_TO_DEVICE);
dma_unmap_len_set(info, len, 0);
} else {
dma_unmap_page(dev, dma_unmap_addr(info, dma),
dma_unmap_len(info, len),
DMA_TO_DEVICE);
dma_unmap_len_set(info, len, 0);
}
}
static inline bool gve_can_tx(struct gve_tx_ring *tx, int bytes_required)
{
bool can_alloc = true;
if (!tx->raw_addressing)
can_alloc = gve_tx_fifo_can_alloc(&tx->tx_fifo, bytes_required);
return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED && can_alloc);
}
static_assert(NAPI_POLL_WEIGHT >= MAX_TX_DESC_NEEDED);
static int gve_maybe_stop_tx(struct gve_priv *priv, struct gve_tx_ring *tx,
struct sk_buff *skb)
{
int bytes_required = 0;
u32 nic_done;
u32 to_do;
int ret;
if (!tx->raw_addressing)
bytes_required = gve_skb_fifo_bytes_required(tx, skb);
if (likely(gve_can_tx(tx, bytes_required)))
return 0;
ret = -EBUSY;
spin_lock(&tx->clean_lock);
nic_done = gve_tx_load_event_counter(priv, tx);
to_do = nic_done - tx->done;
if (to_do + gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED) {
if (to_do > 0) {
to_do = min_t(u32, to_do, NAPI_POLL_WEIGHT);
gve_clean_tx_done(priv, tx, to_do, false);
}
if (likely(gve_can_tx(tx, bytes_required)))
ret = 0;
}
if (ret) {
tx->stop_queue++;
netif_tx_stop_queue(tx->netdev_txq);
}
spin_unlock(&tx->clean_lock);
return ret;
}
static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc,
u16 csum_offset, u8 ip_summed, bool is_gso,
int l4_hdr_offset, u32 desc_cnt,
u16 hlen, u64 addr, u16 pkt_len)
{
if (is_gso) {
pkt_desc->pkt.type_flags = GVE_TXD_TSO | GVE_TXF_L4CSUM;
pkt_desc->pkt.l4_csum_offset = csum_offset >> 1;
pkt_desc->pkt.l4_hdr_offset = l4_hdr_offset >> 1;
} else if (likely(ip_summed == CHECKSUM_PARTIAL)) {
pkt_desc->pkt.type_flags = GVE_TXD_STD | GVE_TXF_L4CSUM;
pkt_desc->pkt.l4_csum_offset = csum_offset >> 1;
pkt_desc->pkt.l4_hdr_offset = l4_hdr_offset >> 1;
} else {
pkt_desc->pkt.type_flags = GVE_TXD_STD;
pkt_desc->pkt.l4_csum_offset = 0;
pkt_desc->pkt.l4_hdr_offset = 0;
}
pkt_desc->pkt.desc_cnt = desc_cnt;
pkt_desc->pkt.len = cpu_to_be16(pkt_len);
pkt_desc->pkt.seg_len = cpu_to_be16(hlen);
pkt_desc->pkt.seg_addr = cpu_to_be64(addr);
}
static void gve_tx_fill_mtd_desc(union gve_tx_desc *mtd_desc,
struct sk_buff *skb)
{
BUILD_BUG_ON(sizeof(mtd_desc->mtd) != sizeof(mtd_desc->pkt));
mtd_desc->mtd.type_flags = GVE_TXD_MTD | GVE_MTD_SUBTYPE_PATH;
mtd_desc->mtd.path_state = GVE_MTD_PATH_STATE_DEFAULT |
GVE_MTD_PATH_HASH_L4;
mtd_desc->mtd.path_hash = cpu_to_be32(skb->hash);
mtd_desc->mtd.reserved0 = 0;
mtd_desc->mtd.reserved1 = 0;
}
static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc,
u16 l3_offset, u16 gso_size,
bool is_gso_v6, bool is_gso,
u16 len, u64 addr)
{
seg_desc->seg.type_flags = GVE_TXD_SEG;
if (is_gso) {
if (is_gso_v6)
seg_desc->seg.type_flags |= GVE_TXSF_IPV6;
seg_desc->seg.l3_offset = l3_offset >> 1;
seg_desc->seg.mss = cpu_to_be16(gso_size);
}
seg_desc->seg.seg_len = cpu_to_be16(len);
seg_desc->seg.seg_addr = cpu_to_be64(addr);
}
static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses,
u64 iov_offset, u64 iov_len)
{
u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE;
u64 first_page = iov_offset / PAGE_SIZE;
u64 page;
for (page = first_page; page <= last_page; page++)
dma_sync_single_for_device(dev, page_buses[page], PAGE_SIZE, DMA_TO_DEVICE);
}
static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, struct sk_buff *skb)
{
int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset;
union gve_tx_desc *pkt_desc, *seg_desc;
struct gve_tx_buffer_state *info;
int mtd_desc_nr = !!skb->l4_hash;
bool is_gso = skb_is_gso(skb);
u32 idx = tx->req & tx->mask;
int payload_iov = 2;
int copy_offset;
u32 next_idx;
int i;
info = &tx->info[idx];
pkt_desc = &tx->desc[idx];
l4_hdr_offset = skb_checksum_start_offset(skb);
hlen = is_gso ? l4_hdr_offset + tcp_hdrlen(skb) :
min_t(int, GVE_GQ_TX_MIN_PKT_DESC_BYTES, skb->len);
info->skb = skb;
pad_bytes = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo, hlen);
hdr_nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, hlen + pad_bytes,
&info->iov[0]);
WARN(!hdr_nfrags, "hdr_nfrags should never be 0!");
payload_nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, skb->len - hlen,
&info->iov[payload_iov]);
gve_tx_fill_pkt_desc(pkt_desc, skb->csum_offset, skb->ip_summed,
is_gso, l4_hdr_offset,
1 + mtd_desc_nr + payload_nfrags, hlen,
info->iov[hdr_nfrags - 1].iov_offset, skb->len);
skb_copy_bits(skb, 0,
tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset,
hlen);
gve_dma_sync_for_device(&priv->pdev->dev, tx->tx_fifo.qpl->page_buses,
info->iov[hdr_nfrags - 1].iov_offset,
info->iov[hdr_nfrags - 1].iov_len);
copy_offset = hlen;
if (mtd_desc_nr) {
next_idx = (tx->req + 1) & tx->mask;
gve_tx_fill_mtd_desc(&tx->desc[next_idx], skb);
}
for (i = payload_iov; i < payload_nfrags + payload_iov; i++) {
next_idx = (tx->req + 1 + mtd_desc_nr + i - payload_iov) & tx->mask;
seg_desc = &tx->desc[next_idx];
gve_tx_fill_seg_desc(seg_desc, skb_network_offset(skb),
skb_shinfo(skb)->gso_size,
skb_is_gso_v6(skb), is_gso,
info->iov[i].iov_len,
info->iov[i].iov_offset);
skb_copy_bits(skb, copy_offset,
tx->tx_fifo.base + info->iov[i].iov_offset,
info->iov[i].iov_len);
gve_dma_sync_for_device(&priv->pdev->dev, tx->tx_fifo.qpl->page_buses,
info->iov[i].iov_offset,
info->iov[i].iov_len);
copy_offset += info->iov[i].iov_len;
}
return 1 + mtd_desc_nr + payload_nfrags;
}
static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx,
struct sk_buff *skb)
{
const struct skb_shared_info *shinfo = skb_shinfo(skb);
int hlen, num_descriptors, l4_hdr_offset;
union gve_tx_desc *pkt_desc, *mtd_desc, *seg_desc;
struct gve_tx_buffer_state *info;
int mtd_desc_nr = !!skb->l4_hash;
bool is_gso = skb_is_gso(skb);
u32 idx = tx->req & tx->mask;
u64 addr;
u32 len;
int i;
info = &tx->info[idx];
pkt_desc = &tx->desc[idx];
l4_hdr_offset = skb_checksum_start_offset(skb);
hlen = is_gso ? l4_hdr_offset + tcp_hdrlen(skb) : skb_headlen(skb);
len = skb_headlen(skb);
info->skb = skb;
addr = dma_map_single(tx->dev, skb->data, len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(tx->dev, addr))) {
tx->dma_mapping_error++;
goto drop;
}
dma_unmap_len_set(info, len, len);
dma_unmap_addr_set(info, dma, addr);
num_descriptors = 1 + shinfo->nr_frags;
if (hlen < len)
num_descriptors++;
if (mtd_desc_nr)
num_descriptors++;
gve_tx_fill_pkt_desc(pkt_desc, skb->csum_offset, skb->ip_summed,
is_gso, l4_hdr_offset,
num_descriptors, hlen, addr, skb->len);
if (mtd_desc_nr) {
idx = (idx + 1) & tx->mask;
mtd_desc = &tx->desc[idx];
gve_tx_fill_mtd_desc(mtd_desc, skb);
}
if (hlen < len) {
len -= hlen;
addr += hlen;
idx = (idx + 1) & tx->mask;
seg_desc = &tx->desc[idx];
gve_tx_fill_seg_desc(seg_desc, skb_network_offset(skb),
skb_shinfo(skb)->gso_size,
skb_is_gso_v6(skb), is_gso, len, addr);
}
for (i = 0; i < shinfo->nr_frags; i++) {
const skb_frag_t *frag = &shinfo->frags[i];
idx = (idx + 1) & tx->mask;
seg_desc = &tx->desc[idx];
len = skb_frag_size(frag);
addr = skb_frag_dma_map(tx->dev, frag, 0, len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(tx->dev, addr))) {
tx->dma_mapping_error++;
goto unmap_drop;
}
tx->info[idx].skb = NULL;
dma_unmap_len_set(&tx->info[idx], len, len);
dma_unmap_addr_set(&tx->info[idx], dma, addr);
gve_tx_fill_seg_desc(seg_desc, skb_network_offset(skb),
skb_shinfo(skb)->gso_size,
skb_is_gso_v6(skb), is_gso, len, addr);
}
return num_descriptors;
unmap_drop:
i += num_descriptors - shinfo->nr_frags;
while (i--) {
if (i == 1 && mtd_desc_nr == 1)
continue;
idx--;
gve_tx_unmap_buf(tx->dev, &tx->info[idx & tx->mask]);
}
drop:
tx->dropped_pkt++;
return 0;
}
netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
{
struct gve_priv *priv = netdev_priv(dev);
struct gve_tx_ring *tx;
int nsegs;
WARN(skb_get_queue_mapping(skb) >= priv->tx_cfg.num_queues,
"skb queue index out of range");
tx = &priv->tx[skb_get_queue_mapping(skb)];
if (unlikely(gve_maybe_stop_tx(priv, tx, skb))) {
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
return NETDEV_TX_BUSY;
}
if (tx->raw_addressing)
nsegs = gve_tx_add_skb_no_copy(priv, tx, skb);
else
nsegs = gve_tx_add_skb_copy(priv, tx, skb);
if (nsegs) {
netdev_tx_sent_queue(tx->netdev_txq, skb->len);
skb_tx_timestamp(skb);
tx->req += nsegs;
} else {
dev_kfree_skb_any(skb);
}
if (!netif_xmit_stopped(tx->netdev_txq) && netdev_xmit_more())
return NETDEV_TX_OK;
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
return NETDEV_TX_OK;
}
static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx,
void *data, int len, void *frame_p, bool is_xsk)
{
int pad, nfrags, ndescs, iovi, offset;
struct gve_tx_buffer_state *info;
u32 reqi = tx->req;
pad = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo, len);
if (pad >= GVE_GQ_TX_MIN_PKT_DESC_BYTES)
pad = 0;
info = &tx->info[reqi & tx->mask];
info->xdp_frame = frame_p;
info->xdp.size = len;
info->xdp.is_xsk = is_xsk;
nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, pad + len,
&info->iov[0]);
iovi = pad > 0;
ndescs = nfrags - iovi;
offset = 0;
while (iovi < nfrags) {
if (!offset)
gve_tx_fill_pkt_desc(&tx->desc[reqi & tx->mask], 0,
CHECKSUM_NONE, false, 0, ndescs,
info->iov[iovi].iov_len,
info->iov[iovi].iov_offset, len);
else
gve_tx_fill_seg_desc(&tx->desc[reqi & tx->mask],
0, 0, false, false,
info->iov[iovi].iov_len,
info->iov[iovi].iov_offset);
memcpy(tx->tx_fifo.base + info->iov[iovi].iov_offset,
data + offset, info->iov[iovi].iov_len);
gve_dma_sync_for_device(&priv->pdev->dev,
tx->tx_fifo.qpl->page_buses,
info->iov[iovi].iov_offset,
info->iov[iovi].iov_len);
offset += info->iov[iovi].iov_len;
iovi++;
reqi++;
}
return ndescs;
}
int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
u32 flags)
{
struct gve_priv *priv = netdev_priv(dev);
struct gve_tx_ring *tx;
int i, err = 0, qid;
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
return -EINVAL;
qid = gve_xdp_tx_queue_id(priv,
smp_processor_id() % priv->num_xdp_queues);
tx = &priv->tx[qid];
spin_lock(&tx->xdp_lock);
for (i = 0; i < n; i++) {
err = gve_xdp_xmit_one(priv, tx, frames[i]->data,
frames[i]->len, frames[i]);
if (err)
break;
}
if (flags & XDP_XMIT_FLUSH)
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
spin_unlock(&tx->xdp_lock);
u64_stats_update_begin(&tx->statss);
tx->xdp_xmit += n;
tx->xdp_xmit_errors += n - i;
u64_stats_update_end(&tx->statss);
return i ? i : err;
}
int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
void *data, int len, void *frame_p)
{
int nsegs;
if (!gve_can_tx(tx, len + GVE_GQ_TX_MIN_PKT_DESC_BYTES - 1))
return -EBUSY;
nsegs = gve_tx_fill_xdp(priv, tx, data, len, frame_p, false);
tx->req += nsegs;
return 0;
}
#define GVE_TX_START_THRESH PAGE_SIZE
static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
u32 to_do, bool try_to_wake)
{
struct gve_tx_buffer_state *info;
u64 pkts = 0, bytes = 0;
size_t space_freed = 0;
struct sk_buff *skb;
u32 idx;
int j;
for (j = 0; j < to_do; j++) {
idx = tx->done & tx->mask;
netif_info(priv, tx_done, priv->dev,
"[%d] %s: idx=%d (req=%u done=%u)\n",
tx->q_num, __func__, idx, tx->req, tx->done);
info = &tx->info[idx];
skb = info->skb;
if (tx->raw_addressing)
gve_tx_unmap_buf(tx->dev, info);
tx->done++;
if (skb) {
info->skb = NULL;
bytes += skb->len;
pkts++;
dev_consume_skb_any(skb);
if (tx->raw_addressing)
continue;
space_freed += gve_tx_clear_buffer_state(info);
}
}
if (!tx->raw_addressing)
gve_tx_free_fifo(&tx->tx_fifo, space_freed);
u64_stats_update_begin(&tx->statss);
tx->bytes_done += bytes;
tx->pkt_done += pkts;
u64_stats_update_end(&tx->statss);
netdev_tx_completed_queue(tx->netdev_txq, pkts, bytes);
#ifndef CONFIG_BQL
smp_mb();
#endif
if (try_to_wake && netif_tx_queue_stopped(tx->netdev_txq) &&
likely(gve_can_tx(tx, GVE_TX_START_THRESH))) {
tx->wake_queue++;
netif_tx_wake_queue(tx->netdev_txq);
}
return pkts;
}
u32 gve_tx_load_event_counter(struct gve_priv *priv,
struct gve_tx_ring *tx)
{
u32 counter_index = be32_to_cpu(tx->q_resources->counter_index);
__be32 counter = READ_ONCE(priv->counter_array[counter_index]);
return be32_to_cpu(counter);
}
static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx,
int budget)
{
struct xdp_desc desc;
int sent = 0, nsegs;
void *data;
spin_lock(&tx->xdp_lock);
while (sent < budget) {
if (!gve_can_tx(tx, GVE_TX_START_THRESH))
goto out;
if (!xsk_tx_peek_desc(tx->xsk_pool, &desc)) {
tx->xdp_xsk_done = tx->xdp_xsk_wakeup;
goto out;
}
data = xsk_buff_raw_get_data(tx->xsk_pool, desc.addr);
nsegs = gve_tx_fill_xdp(priv, tx, data, desc.len, NULL, true);
tx->req += nsegs;
sent++;
}
out:
if (sent > 0) {
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
xsk_tx_release(tx->xsk_pool);
}
spin_unlock(&tx->xdp_lock);
return sent;
}
bool gve_xdp_poll(struct gve_notify_block *block, int budget)
{
struct gve_priv *priv = block->priv;
struct gve_tx_ring *tx = block->tx;
u32 nic_done;
bool repoll;
u32 to_do;
if (budget == 0)
budget = INT_MAX;
nic_done = gve_tx_load_event_counter(priv, tx);
to_do = min_t(u32, (nic_done - tx->done), budget);
gve_clean_xdp_done(priv, tx, to_do);
repoll = nic_done != tx->done;
if (tx->xsk_pool) {
int sent = gve_xsk_tx(priv, tx, budget);
u64_stats_update_begin(&tx->statss);
tx->xdp_xsk_sent += sent;
u64_stats_update_end(&tx->statss);
repoll |= (sent == budget);
if (xsk_uses_need_wakeup(tx->xsk_pool))
xsk_set_tx_need_wakeup(tx->xsk_pool);
}
return repoll;
}
bool gve_tx_poll(struct gve_notify_block *block, int budget)
{
struct gve_priv *priv = block->priv;
struct gve_tx_ring *tx = block->tx;
u32 nic_done;
u32 to_do;
if (budget == 0)
budget = INT_MAX;
spin_lock(&tx->clean_lock);
nic_done = gve_tx_load_event_counter(priv, tx);
to_do = min_t(u32, (nic_done - tx->done), budget);
gve_clean_tx_done(priv, tx, to_do, true);
spin_unlock(&tx->clean_lock);
return nic_done != tx->done;
}
bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx)
{
u32 nic_done = gve_tx_load_event_counter(priv, tx);
return nic_done != tx->done;
}