i40e, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL
Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL APIs. The AF_XDP zero-copy rx_bi ring is now simply a struct xdp_buff pointer. v4->v5: Fixed "warning: Excess function parameter 'bi' description in 'i40e_construct_skb_zc'". (Jakub) Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: intel-wired-lan@lists.osuosl.org Link: https://lore.kernel.org/bpf/20200520192103.355233-9-bjorn.topel@gmail.com
This commit is contained in:
Родитель
be1222b585
Коммит
3b4f0b66c2
|
@ -3266,21 +3266,19 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
|
||||||
ret = i40e_alloc_rx_bi_zc(ring);
|
ret = i40e_alloc_rx_bi_zc(ring);
|
||||||
if (ret)
|
if (ret)
|
||||||
return ret;
|
return ret;
|
||||||
ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
|
ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
|
||||||
XDP_PACKET_HEADROOM;
|
|
||||||
/* For AF_XDP ZC, we disallow packets to span on
|
/* For AF_XDP ZC, we disallow packets to span on
|
||||||
* multiple buffers, thus letting us skip that
|
* multiple buffers, thus letting us skip that
|
||||||
* handling in the fast-path.
|
* handling in the fast-path.
|
||||||
*/
|
*/
|
||||||
chain_len = 1;
|
chain_len = 1;
|
||||||
ring->zca.free = i40e_zca_free;
|
|
||||||
ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
|
ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
|
||||||
MEM_TYPE_ZERO_COPY,
|
MEM_TYPE_XSK_BUFF_POOL,
|
||||||
&ring->zca);
|
NULL);
|
||||||
if (ret)
|
if (ret)
|
||||||
return ret;
|
return ret;
|
||||||
dev_info(&vsi->back->pdev->dev,
|
dev_info(&vsi->back->pdev->dev,
|
||||||
"Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
|
"Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
|
||||||
ring->queue_index);
|
ring->queue_index);
|
||||||
|
|
||||||
} else {
|
} else {
|
||||||
|
@ -3351,9 +3349,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
|
||||||
ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
|
ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
|
||||||
writel(0, ring->tail);
|
writel(0, ring->tail);
|
||||||
|
|
||||||
ok = ring->xsk_umem ?
|
if (ring->xsk_umem) {
|
||||||
i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
|
xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
|
||||||
!i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
|
ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring));
|
||||||
|
} else {
|
||||||
|
ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
|
||||||
|
}
|
||||||
if (!ok) {
|
if (!ok) {
|
||||||
/* Log this in case the user has forgotten to give the kernel
|
/* Log this in case the user has forgotten to give the kernel
|
||||||
* any buffers, even later in the application.
|
* any buffers, even later in the application.
|
||||||
|
|
|
@ -301,12 +301,6 @@ struct i40e_rx_buffer {
|
||||||
__u16 pagecnt_bias;
|
__u16 pagecnt_bias;
|
||||||
};
|
};
|
||||||
|
|
||||||
struct i40e_rx_buffer_zc {
|
|
||||||
dma_addr_t dma;
|
|
||||||
void *addr;
|
|
||||||
u64 handle;
|
|
||||||
};
|
|
||||||
|
|
||||||
struct i40e_queue_stats {
|
struct i40e_queue_stats {
|
||||||
u64 packets;
|
u64 packets;
|
||||||
u64 bytes;
|
u64 bytes;
|
||||||
|
@ -356,7 +350,7 @@ struct i40e_ring {
|
||||||
union {
|
union {
|
||||||
struct i40e_tx_buffer *tx_bi;
|
struct i40e_tx_buffer *tx_bi;
|
||||||
struct i40e_rx_buffer *rx_bi;
|
struct i40e_rx_buffer *rx_bi;
|
||||||
struct i40e_rx_buffer_zc *rx_bi_zc;
|
struct xdp_buff **rx_bi_zc;
|
||||||
};
|
};
|
||||||
DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
|
DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
|
||||||
u16 queue_index; /* Queue number of ring */
|
u16 queue_index; /* Queue number of ring */
|
||||||
|
@ -418,7 +412,6 @@ struct i40e_ring {
|
||||||
struct i40e_channel *ch;
|
struct i40e_channel *ch;
|
||||||
struct xdp_rxq_info xdp_rxq;
|
struct xdp_rxq_info xdp_rxq;
|
||||||
struct xdp_umem *xsk_umem;
|
struct xdp_umem *xsk_umem;
|
||||||
struct zero_copy_allocator zca; /* ZC allocator anchor */
|
|
||||||
} ____cacheline_internodealigned_in_smp;
|
} ____cacheline_internodealigned_in_smp;
|
||||||
|
|
||||||
static inline bool ring_uses_build_skb(struct i40e_ring *ring)
|
static inline bool ring_uses_build_skb(struct i40e_ring *ring)
|
||||||
|
|
|
@ -23,68 +23,11 @@ void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
|
||||||
sizeof(*rx_ring->rx_bi_zc) * rx_ring->count);
|
sizeof(*rx_ring->rx_bi_zc) * rx_ring->count);
|
||||||
}
|
}
|
||||||
|
|
||||||
static struct i40e_rx_buffer_zc *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
|
static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
|
||||||
{
|
{
|
||||||
return &rx_ring->rx_bi_zc[idx];
|
return &rx_ring->rx_bi_zc[idx];
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
|
|
||||||
* @vsi: Current VSI
|
|
||||||
* @umem: UMEM to DMA map
|
|
||||||
*
|
|
||||||
* Returns 0 on success, <0 on failure
|
|
||||||
**/
|
|
||||||
static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem)
|
|
||||||
{
|
|
||||||
struct i40e_pf *pf = vsi->back;
|
|
||||||
struct device *dev;
|
|
||||||
unsigned int i, j;
|
|
||||||
dma_addr_t dma;
|
|
||||||
|
|
||||||
dev = &pf->pdev->dev;
|
|
||||||
for (i = 0; i < umem->npgs; i++) {
|
|
||||||
dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
|
|
||||||
DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
|
|
||||||
if (dma_mapping_error(dev, dma))
|
|
||||||
goto out_unmap;
|
|
||||||
|
|
||||||
umem->pages[i].dma = dma;
|
|
||||||
}
|
|
||||||
|
|
||||||
return 0;
|
|
||||||
|
|
||||||
out_unmap:
|
|
||||||
for (j = 0; j < i; j++) {
|
|
||||||
dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
|
|
||||||
DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
|
|
||||||
umem->pages[i].dma = 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
return -1;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev
|
|
||||||
* @vsi: Current VSI
|
|
||||||
* @umem: UMEM to DMA map
|
|
||||||
**/
|
|
||||||
static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
|
|
||||||
{
|
|
||||||
struct i40e_pf *pf = vsi->back;
|
|
||||||
struct device *dev;
|
|
||||||
unsigned int i;
|
|
||||||
|
|
||||||
dev = &pf->pdev->dev;
|
|
||||||
|
|
||||||
for (i = 0; i < umem->npgs; i++) {
|
|
||||||
dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
|
|
||||||
DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
|
|
||||||
|
|
||||||
umem->pages[i].dma = 0;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
|
* i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
|
||||||
* @vsi: Current VSI
|
* @vsi: Current VSI
|
||||||
|
@ -97,7 +40,6 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
|
||||||
u16 qid)
|
u16 qid)
|
||||||
{
|
{
|
||||||
struct net_device *netdev = vsi->netdev;
|
struct net_device *netdev = vsi->netdev;
|
||||||
struct xdp_umem_fq_reuse *reuseq;
|
|
||||||
bool if_running;
|
bool if_running;
|
||||||
int err;
|
int err;
|
||||||
|
|
||||||
|
@ -111,13 +53,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
|
||||||
qid >= netdev->real_num_tx_queues)
|
qid >= netdev->real_num_tx_queues)
|
||||||
return -EINVAL;
|
return -EINVAL;
|
||||||
|
|
||||||
reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
|
err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
|
||||||
if (!reuseq)
|
|
||||||
return -ENOMEM;
|
|
||||||
|
|
||||||
xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
|
|
||||||
|
|
||||||
err = i40e_xsk_umem_dma_map(vsi, umem);
|
|
||||||
if (err)
|
if (err)
|
||||||
return err;
|
return err;
|
||||||
|
|
||||||
|
@ -170,7 +106,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
|
||||||
}
|
}
|
||||||
|
|
||||||
clear_bit(qid, vsi->af_xdp_zc_qps);
|
clear_bit(qid, vsi->af_xdp_zc_qps);
|
||||||
i40e_xsk_umem_dma_unmap(vsi, umem);
|
xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR);
|
||||||
|
|
||||||
if (if_running) {
|
if (if_running) {
|
||||||
err = i40e_queue_pair_enable(vsi, qid);
|
err = i40e_queue_pair_enable(vsi, qid);
|
||||||
|
@ -209,11 +145,9 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
|
||||||
**/
|
**/
|
||||||
static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
|
static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
|
||||||
{
|
{
|
||||||
struct xdp_umem *umem = rx_ring->xsk_umem;
|
|
||||||
int err, result = I40E_XDP_PASS;
|
int err, result = I40E_XDP_PASS;
|
||||||
struct i40e_ring *xdp_ring;
|
struct i40e_ring *xdp_ring;
|
||||||
struct bpf_prog *xdp_prog;
|
struct bpf_prog *xdp_prog;
|
||||||
u64 offset;
|
|
||||||
u32 act;
|
u32 act;
|
||||||
|
|
||||||
rcu_read_lock();
|
rcu_read_lock();
|
||||||
|
@ -222,9 +156,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
|
||||||
*/
|
*/
|
||||||
xdp_prog = READ_ONCE(rx_ring->xdp_prog);
|
xdp_prog = READ_ONCE(rx_ring->xdp_prog);
|
||||||
act = bpf_prog_run_xdp(xdp_prog, xdp);
|
act = bpf_prog_run_xdp(xdp_prog, xdp);
|
||||||
offset = xdp->data - xdp->data_hard_start;
|
|
||||||
|
|
||||||
xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
|
|
||||||
|
|
||||||
switch (act) {
|
switch (act) {
|
||||||
case XDP_PASS:
|
case XDP_PASS:
|
||||||
|
@ -251,107 +182,26 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
|
||||||
* i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer_zc
|
|
||||||
* @rx_ring: Rx ring
|
|
||||||
* @bi: Rx buffer to populate
|
|
||||||
*
|
|
||||||
* This function allocates an Rx buffer. The buffer can come from fill
|
|
||||||
* queue, or via the recycle queue (next_to_alloc).
|
|
||||||
*
|
|
||||||
* Returns true for a successful allocation, false otherwise
|
|
||||||
**/
|
|
||||||
static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
|
|
||||||
struct i40e_rx_buffer_zc *bi)
|
|
||||||
{
|
|
||||||
struct xdp_umem *umem = rx_ring->xsk_umem;
|
|
||||||
void *addr = bi->addr;
|
|
||||||
u64 handle, hr;
|
|
||||||
|
|
||||||
if (addr) {
|
|
||||||
rx_ring->rx_stats.page_reuse_count++;
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!xsk_umem_peek_addr(umem, &handle)) {
|
|
||||||
rx_ring->rx_stats.alloc_page_failed++;
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
|
|
||||||
hr = umem->headroom + XDP_PACKET_HEADROOM;
|
|
||||||
|
|
||||||
bi->dma = xdp_umem_get_dma(umem, handle);
|
|
||||||
bi->dma += hr;
|
|
||||||
|
|
||||||
bi->addr = xdp_umem_get_data(umem, handle);
|
|
||||||
bi->addr += hr;
|
|
||||||
|
|
||||||
bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
|
|
||||||
|
|
||||||
xsk_umem_release_addr(umem);
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer_zc
|
|
||||||
* @rx_ring: Rx ring
|
|
||||||
* @bi: Rx buffer to populate
|
|
||||||
*
|
|
||||||
* This function allocates an Rx buffer. The buffer can come from fill
|
|
||||||
* queue, or via the reuse queue.
|
|
||||||
*
|
|
||||||
* Returns true for a successful allocation, false otherwise
|
|
||||||
**/
|
|
||||||
static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
|
|
||||||
struct i40e_rx_buffer_zc *bi)
|
|
||||||
{
|
|
||||||
struct xdp_umem *umem = rx_ring->xsk_umem;
|
|
||||||
u64 handle, hr;
|
|
||||||
|
|
||||||
if (!xsk_umem_peek_addr_rq(umem, &handle)) {
|
|
||||||
rx_ring->rx_stats.alloc_page_failed++;
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
|
|
||||||
handle &= rx_ring->xsk_umem->chunk_mask;
|
|
||||||
|
|
||||||
hr = umem->headroom + XDP_PACKET_HEADROOM;
|
|
||||||
|
|
||||||
bi->dma = xdp_umem_get_dma(umem, handle);
|
|
||||||
bi->dma += hr;
|
|
||||||
|
|
||||||
bi->addr = xdp_umem_get_data(umem, handle);
|
|
||||||
bi->addr += hr;
|
|
||||||
|
|
||||||
bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
|
|
||||||
|
|
||||||
xsk_umem_release_addr_rq(umem);
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
static __always_inline bool
|
|
||||||
__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
|
|
||||||
bool alloc(struct i40e_ring *rx_ring,
|
|
||||||
struct i40e_rx_buffer_zc *bi))
|
|
||||||
{
|
{
|
||||||
u16 ntu = rx_ring->next_to_use;
|
u16 ntu = rx_ring->next_to_use;
|
||||||
union i40e_rx_desc *rx_desc;
|
union i40e_rx_desc *rx_desc;
|
||||||
struct i40e_rx_buffer_zc *bi;
|
struct xdp_buff **bi, *xdp;
|
||||||
|
dma_addr_t dma;
|
||||||
bool ok = true;
|
bool ok = true;
|
||||||
|
|
||||||
rx_desc = I40E_RX_DESC(rx_ring, ntu);
|
rx_desc = I40E_RX_DESC(rx_ring, ntu);
|
||||||
bi = i40e_rx_bi(rx_ring, ntu);
|
bi = i40e_rx_bi(rx_ring, ntu);
|
||||||
do {
|
do {
|
||||||
if (!alloc(rx_ring, bi)) {
|
xdp = xsk_buff_alloc(rx_ring->xsk_umem);
|
||||||
|
if (!xdp) {
|
||||||
ok = false;
|
ok = false;
|
||||||
goto no_buffers;
|
goto no_buffers;
|
||||||
}
|
}
|
||||||
|
*bi = xdp;
|
||||||
dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0,
|
dma = xsk_buff_xdp_get_dma(xdp);
|
||||||
rx_ring->rx_buf_len,
|
rx_desc->read.pkt_addr = cpu_to_le64(dma);
|
||||||
DMA_BIDIRECTIONAL);
|
rx_desc->read.hdr_addr = 0;
|
||||||
|
|
||||||
rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
|
|
||||||
|
|
||||||
rx_desc++;
|
rx_desc++;
|
||||||
bi++;
|
bi++;
|
||||||
|
@ -363,7 +213,6 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
|
||||||
ntu = 0;
|
ntu = 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
rx_desc->wb.qword1.status_error_len = 0;
|
|
||||||
count--;
|
count--;
|
||||||
} while (count);
|
} while (count);
|
||||||
|
|
||||||
|
@ -374,130 +223,9 @@ no_buffers:
|
||||||
return ok;
|
return ok;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers
|
|
||||||
* @rx_ring: Rx ring
|
|
||||||
* @count: The number of buffers to allocate
|
|
||||||
*
|
|
||||||
* This function allocates a number of Rx buffers from the reuse queue
|
|
||||||
* or fill ring and places them on the Rx ring.
|
|
||||||
*
|
|
||||||
* Returns true for a successful allocation, false otherwise
|
|
||||||
**/
|
|
||||||
bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
|
|
||||||
{
|
|
||||||
return __i40e_alloc_rx_buffers_zc(rx_ring, count,
|
|
||||||
i40e_alloc_buffer_slow_zc);
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers
|
|
||||||
* @rx_ring: Rx ring
|
|
||||||
* @count: The number of buffers to allocate
|
|
||||||
*
|
|
||||||
* This function allocates a number of Rx buffers from the fill ring
|
|
||||||
* or the internal recycle mechanism and places them on the Rx ring.
|
|
||||||
*
|
|
||||||
* Returns true for a successful allocation, false otherwise
|
|
||||||
**/
|
|
||||||
static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
|
|
||||||
{
|
|
||||||
return __i40e_alloc_rx_buffers_zc(rx_ring, count,
|
|
||||||
i40e_alloc_buffer_zc);
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_get_rx_buffer_zc - Return the current Rx buffer
|
|
||||||
* @rx_ring: Rx ring
|
|
||||||
* @size: The size of the rx buffer (read from descriptor)
|
|
||||||
*
|
|
||||||
* This function returns the current, received Rx buffer, and also
|
|
||||||
* does DMA synchronization. the Rx ring.
|
|
||||||
*
|
|
||||||
* Returns the received Rx buffer
|
|
||||||
**/
|
|
||||||
static struct i40e_rx_buffer_zc *i40e_get_rx_buffer_zc(
|
|
||||||
struct i40e_ring *rx_ring,
|
|
||||||
const unsigned int size)
|
|
||||||
{
|
|
||||||
struct i40e_rx_buffer_zc *bi;
|
|
||||||
|
|
||||||
bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
|
|
||||||
|
|
||||||
/* we are reusing so sync this buffer for CPU use */
|
|
||||||
dma_sync_single_range_for_cpu(rx_ring->dev,
|
|
||||||
bi->dma, 0,
|
|
||||||
size,
|
|
||||||
DMA_BIDIRECTIONAL);
|
|
||||||
|
|
||||||
return bi;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_reuse_rx_buffer_zc - Recycle an Rx buffer
|
|
||||||
* @rx_ring: Rx ring
|
|
||||||
* @old_bi: The Rx buffer to recycle
|
|
||||||
*
|
|
||||||
* This function recycles a finished Rx buffer, and places it on the
|
|
||||||
* recycle queue (next_to_alloc).
|
|
||||||
**/
|
|
||||||
static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
|
|
||||||
struct i40e_rx_buffer_zc *old_bi)
|
|
||||||
{
|
|
||||||
struct i40e_rx_buffer_zc *new_bi = i40e_rx_bi(rx_ring,
|
|
||||||
rx_ring->next_to_alloc);
|
|
||||||
u16 nta = rx_ring->next_to_alloc;
|
|
||||||
|
|
||||||
/* update, and store next to alloc */
|
|
||||||
nta++;
|
|
||||||
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
|
|
||||||
|
|
||||||
/* transfer page from old buffer to new buffer */
|
|
||||||
new_bi->dma = old_bi->dma;
|
|
||||||
new_bi->addr = old_bi->addr;
|
|
||||||
new_bi->handle = old_bi->handle;
|
|
||||||
|
|
||||||
old_bi->addr = NULL;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations
|
|
||||||
* @alloc: Zero-copy allocator
|
|
||||||
* @handle: Buffer handle
|
|
||||||
**/
|
|
||||||
void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
|
|
||||||
{
|
|
||||||
struct i40e_rx_buffer_zc *bi;
|
|
||||||
struct i40e_ring *rx_ring;
|
|
||||||
u64 hr, mask;
|
|
||||||
u16 nta;
|
|
||||||
|
|
||||||
rx_ring = container_of(alloc, struct i40e_ring, zca);
|
|
||||||
hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
|
|
||||||
mask = rx_ring->xsk_umem->chunk_mask;
|
|
||||||
|
|
||||||
nta = rx_ring->next_to_alloc;
|
|
||||||
bi = i40e_rx_bi(rx_ring, nta);
|
|
||||||
|
|
||||||
nta++;
|
|
||||||
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
|
|
||||||
|
|
||||||
handle &= mask;
|
|
||||||
|
|
||||||
bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
|
|
||||||
bi->dma += hr;
|
|
||||||
|
|
||||||
bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
|
|
||||||
bi->addr += hr;
|
|
||||||
|
|
||||||
bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
|
|
||||||
rx_ring->xsk_umem->headroom);
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer
|
* i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer
|
||||||
* @rx_ring: Rx ring
|
* @rx_ring: Rx ring
|
||||||
* @bi: Rx buffer
|
|
||||||
* @xdp: xdp_buff
|
* @xdp: xdp_buff
|
||||||
*
|
*
|
||||||
* This functions allocates a new skb from a zero-copy Rx buffer.
|
* This functions allocates a new skb from a zero-copy Rx buffer.
|
||||||
|
@ -505,7 +233,6 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
|
||||||
* Returns the skb, or NULL on failure.
|
* Returns the skb, or NULL on failure.
|
||||||
**/
|
**/
|
||||||
static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
|
static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
|
||||||
struct i40e_rx_buffer_zc *bi,
|
|
||||||
struct xdp_buff *xdp)
|
struct xdp_buff *xdp)
|
||||||
{
|
{
|
||||||
unsigned int metasize = xdp->data - xdp->data_meta;
|
unsigned int metasize = xdp->data - xdp->data_meta;
|
||||||
|
@ -524,7 +251,7 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
|
||||||
if (metasize)
|
if (metasize)
|
||||||
skb_metadata_set(skb, metasize);
|
skb_metadata_set(skb, metasize);
|
||||||
|
|
||||||
i40e_reuse_rx_buffer_zc(rx_ring, bi);
|
xsk_buff_free(xdp);
|
||||||
return skb;
|
return skb;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -539,25 +266,20 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
|
||||||
{
|
{
|
||||||
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
|
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
|
||||||
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
|
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
|
||||||
struct xdp_umem *umem = rx_ring->xsk_umem;
|
|
||||||
unsigned int xdp_res, xdp_xmit = 0;
|
unsigned int xdp_res, xdp_xmit = 0;
|
||||||
bool failure = false;
|
bool failure = false;
|
||||||
struct sk_buff *skb;
|
struct sk_buff *skb;
|
||||||
struct xdp_buff xdp;
|
|
||||||
|
|
||||||
xdp.rxq = &rx_ring->xdp_rxq;
|
|
||||||
xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
|
|
||||||
|
|
||||||
while (likely(total_rx_packets < (unsigned int)budget)) {
|
while (likely(total_rx_packets < (unsigned int)budget)) {
|
||||||
struct i40e_rx_buffer_zc *bi;
|
|
||||||
union i40e_rx_desc *rx_desc;
|
union i40e_rx_desc *rx_desc;
|
||||||
|
struct xdp_buff **bi;
|
||||||
unsigned int size;
|
unsigned int size;
|
||||||
u64 qword;
|
u64 qword;
|
||||||
|
|
||||||
if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
|
if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
|
||||||
failure = failure ||
|
failure = failure ||
|
||||||
!i40e_alloc_rx_buffers_fast_zc(rx_ring,
|
!i40e_alloc_rx_buffers_zc(rx_ring,
|
||||||
cleaned_count);
|
cleaned_count);
|
||||||
cleaned_count = 0;
|
cleaned_count = 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -575,9 +297,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
|
||||||
rx_desc->raw.qword[0],
|
rx_desc->raw.qword[0],
|
||||||
qword);
|
qword);
|
||||||
bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
|
bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
|
||||||
i40e_inc_ntc(rx_ring);
|
xsk_buff_free(*bi);
|
||||||
i40e_reuse_rx_buffer_zc(rx_ring, bi);
|
*bi = NULL;
|
||||||
cleaned_count++;
|
cleaned_count++;
|
||||||
|
i40e_inc_ntc(rx_ring);
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -587,22 +310,18 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
|
||||||
if (!size)
|
if (!size)
|
||||||
break;
|
break;
|
||||||
|
|
||||||
bi = i40e_get_rx_buffer_zc(rx_ring, size);
|
bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
|
||||||
xdp.data = bi->addr;
|
(*bi)->data_end = (*bi)->data + size;
|
||||||
xdp.data_meta = xdp.data;
|
xsk_buff_dma_sync_for_cpu(*bi);
|
||||||
xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
|
|
||||||
xdp.data_end = xdp.data + size;
|
|
||||||
xdp.handle = bi->handle;
|
|
||||||
|
|
||||||
xdp_res = i40e_run_xdp_zc(rx_ring, &xdp);
|
xdp_res = i40e_run_xdp_zc(rx_ring, *bi);
|
||||||
if (xdp_res) {
|
if (xdp_res) {
|
||||||
if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
|
if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR))
|
||||||
xdp_xmit |= xdp_res;
|
xdp_xmit |= xdp_res;
|
||||||
bi->addr = NULL;
|
else
|
||||||
} else {
|
xsk_buff_free(*bi);
|
||||||
i40e_reuse_rx_buffer_zc(rx_ring, bi);
|
|
||||||
}
|
|
||||||
|
|
||||||
|
*bi = NULL;
|
||||||
total_rx_bytes += size;
|
total_rx_bytes += size;
|
||||||
total_rx_packets++;
|
total_rx_packets++;
|
||||||
|
|
||||||
|
@ -618,7 +337,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
|
||||||
* BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
|
* BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
|
||||||
* SBP is *not* set in PRT_SBPVSI (default not set).
|
* SBP is *not* set in PRT_SBPVSI (default not set).
|
||||||
*/
|
*/
|
||||||
skb = i40e_construct_skb_zc(rx_ring, bi, &xdp);
|
skb = i40e_construct_skb_zc(rx_ring, *bi);
|
||||||
|
*bi = NULL;
|
||||||
if (!skb) {
|
if (!skb) {
|
||||||
rx_ring->rx_stats.alloc_buff_failed++;
|
rx_ring->rx_stats.alloc_buff_failed++;
|
||||||
break;
|
break;
|
||||||
|
@ -676,10 +396,9 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
|
||||||
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
|
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
|
||||||
break;
|
break;
|
||||||
|
|
||||||
dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
|
dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
|
||||||
|
xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
|
||||||
dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
|
desc.len);
|
||||||
DMA_BIDIRECTIONAL);
|
|
||||||
|
|
||||||
tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
|
tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
|
||||||
tx_bi->bytecount = desc.len;
|
tx_bi->bytecount = desc.len;
|
||||||
|
@ -838,13 +557,13 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
|
||||||
u16 i;
|
u16 i;
|
||||||
|
|
||||||
for (i = 0; i < rx_ring->count; i++) {
|
for (i = 0; i < rx_ring->count; i++) {
|
||||||
struct i40e_rx_buffer_zc *rx_bi = i40e_rx_bi(rx_ring, i);
|
struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, i);
|
||||||
|
|
||||||
if (!rx_bi->addr)
|
if (!rx_bi)
|
||||||
continue;
|
continue;
|
||||||
|
|
||||||
xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle);
|
xsk_buff_free(rx_bi);
|
||||||
rx_bi->addr = NULL;
|
rx_bi = NULL;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -12,7 +12,6 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
|
||||||
int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
|
int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
|
||||||
int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
|
int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
|
||||||
u16 qid);
|
u16 qid);
|
||||||
void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
|
|
||||||
bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
|
bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
|
||||||
int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
|
int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
|
||||||
|
|
||||||
|
|
Загрузка…
Ссылка в новой задаче