* [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 05/14] i40e: refactor rx_bi accesses
[not found] <20200506132746.526188-1-bjorn.topel@gmail.com>
@ 2020-05-06 13:27 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:30 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 06/14] i40e: separate kernel allocated rx_bi rings from AF_XDP rings =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
` (3 subsequent siblings)
4 siblings, 1 reply; 6+ messages in thread
From: =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= @ 2020-05-06 13:27 UTC (permalink / raw)
To: intel-wired-lan
From: Bj?rn T?pel <bjorn.topel@intel.com>
As a first step to migrate i40e to the new MEM_TYPE_XSK_BUFF_POOL
APIs, code that accesses the rx_bi (SW/shadow ring) is refactored to
use an accessor function.
Cc: intel-wired-lan at lists.osuosl.org
Signed-off-by: Bj?rn T?pel <bjorn.topel@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 17 +++++++++++------
drivers/net/ethernet/intel/i40e/i40e_xsk.c | 18 ++++++++++++------
2 files changed, 23 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b8496037ef7f..58daba8fabc8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1195,6 +1195,11 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector,
rc->total_packets = 0;
}
+static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+{
+ return &rx_ring->rx_bi[idx];
+}
+
/**
* i40e_reuse_rx_page - page flip buffer and store it back on the ring
* @rx_ring: rx descriptor ring to store buffers on
@@ -1208,7 +1213,7 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
struct i40e_rx_buffer *new_buff;
u16 nta = rx_ring->next_to_alloc;
- new_buff = &rx_ring->rx_bi[nta];
+ new_buff = i40e_rx_bi(rx_ring, nta);
/* update, and store next to alloc */
nta++;
@@ -1272,7 +1277,7 @@ struct i40e_rx_buffer *i40e_clean_programming_status(
ntc = rx_ring->next_to_clean;
/* fetch, update, and store next to clean */
- rx_buffer = &rx_ring->rx_bi[ntc++];
+ rx_buffer = i40e_rx_bi(rx_ring, ntc++);
ntc = (ntc < rx_ring->count) ? ntc : 0;
rx_ring->next_to_clean = ntc;
@@ -1361,7 +1366,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
/* Free all the Rx ring sk_buffs */
for (i = 0; i < rx_ring->count; i++) {
- struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+ struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i);
if (!rx_bi->page)
continue;
@@ -1576,7 +1581,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
return false;
rx_desc = I40E_RX_DESC(rx_ring, ntu);
- bi = &rx_ring->rx_bi[ntu];
+ bi = i40e_rx_bi(rx_ring, ntu);
do {
if (!i40e_alloc_mapped_page(rx_ring, bi))
@@ -1598,7 +1603,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
ntu++;
if (unlikely(ntu == rx_ring->count)) {
rx_desc = I40E_RX_DESC(rx_ring, 0);
- bi = rx_ring->rx_bi;
+ bi = i40e_rx_bi(rx_ring, 0);
ntu = 0;
}
@@ -1965,7 +1970,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
{
struct i40e_rx_buffer *rx_buffer;
- rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+ rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
prefetchw(rx_buffer->page);
/* we are reusing so sync this buffer for CPU use */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 452bba7bc4ff..8d29477bb0b6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -9,6 +9,11 @@
#include "i40e_txrx_common.h"
#include "i40e_xsk.h"
+static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+{
+ return &rx_ring->rx_bi[idx];
+}
+
/**
* i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
* @vsi: Current VSI
@@ -321,7 +326,7 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
bool ok = true;
rx_desc = I40E_RX_DESC(rx_ring, ntu);
- bi = &rx_ring->rx_bi[ntu];
+ bi = i40e_rx_bi(rx_ring, ntu);
do {
if (!alloc(rx_ring, bi)) {
ok = false;
@@ -340,7 +345,7 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
if (unlikely(ntu == rx_ring->count)) {
rx_desc = I40E_RX_DESC(rx_ring, 0);
- bi = rx_ring->rx_bi;
+ bi = i40e_rx_bi(rx_ring, 0);
ntu = 0;
}
@@ -402,7 +407,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
{
struct i40e_rx_buffer *bi;
- bi = &rx_ring->rx_bi[rx_ring->next_to_clean];
+ 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,
@@ -424,7 +429,8 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
struct i40e_rx_buffer *old_bi)
{
- struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc];
+ struct i40e_rx_buffer *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 */
@@ -456,7 +462,7 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
mask = rx_ring->xsk_umem->chunk_mask;
nta = rx_ring->next_to_alloc;
- bi = &rx_ring->rx_bi[nta];
+ bi = i40e_rx_bi(rx_ring, nta);
nta++;
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
@@ -824,7 +830,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
u16 i;
for (i = 0; i < rx_ring->count; i++) {
- struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+ struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i);
if (!rx_bi->addr)
continue;
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 06/14] i40e: separate kernel allocated rx_bi rings from AF_XDP rings
[not found] <20200506132746.526188-1-bjorn.topel@gmail.com>
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 05/14] i40e: refactor rx_bi accesses =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
@ 2020-05-06 13:27 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 07/14] i40e, xsk: migrate to new MEM_TYPE_XSK_BUFF_POOL =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= @ 2020-05-06 13:27 UTC (permalink / raw)
To: intel-wired-lan
From: Bj?rn T?pel <bjorn.topel@intel.com>
Continuing the path to support MEM_TYPE_XSK_BUFF_POOL, the AF_XDP
zero-copy/sk_buff rx_bi rings are now separate. Functions to properly
allocate the different rings are added as well.
Cc: intel-wired-lan at lists.osuosl.org
Signed-off-by: Bj?rn T?pel <bjorn.topel@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 7 ++
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 119 +++++++-----------
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 22 ++--
.../ethernet/intel/i40e/i40e_txrx_common.h | 40 +++++-
drivers/net/ethernet/intel/i40e/i40e_type.h | 5 +-
drivers/net/ethernet/intel/i40e/i40e_xsk.c | 74 ++++++-----
drivers/net/ethernet/intel/i40e/i40e_xsk.h | 2 +
7 files changed, 142 insertions(+), 127 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d6b2db4f2c65..3e1695bb8262 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3260,8 +3260,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
if (ring->vsi->type == I40E_VSI_MAIN)
xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+ kfree(ring->rx_bi);
ring->xsk_umem = i40e_xsk_umem(ring);
if (ring->xsk_umem) {
+ ret = i40e_alloc_rx_bi_zc(ring);
+ if (ret)
+ return ret;
ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
XDP_PACKET_HEADROOM;
/* For AF_XDP ZC, we disallow packets to span on
@@ -3280,6 +3284,9 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
ring->queue_index);
} else {
+ ret = i40e_alloc_rx_bi(ring);
+ if (ret)
+ return ret;
ring->rx_buf_len = vsi->rx_buf_len;
if (ring->vsi->type == I40E_VSI_MAIN) {
ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 58daba8fabc8..f063df623443 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -521,28 +521,29 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
/**
* i40e_fd_handle_status - check the Programming Status for FD
* @rx_ring: the Rx ring for this descriptor
- * @rx_desc: the Rx descriptor for programming Status, not a packet descriptor.
+ * @qword0_raw: qword0
+ * @qword1: qword1 after le_to_cpu
* @prog_id: the id originally used for programming
*
* This is used to verify if the FD programming or invalidation
* requested by SW to the HW is successful or not and take actions accordingly.
**/
-void i40e_fd_handle_status(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc, u8 prog_id)
+void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+ u64 qword1, u8 prog_id)
{
struct i40e_pf *pf = rx_ring->vsi->back;
struct pci_dev *pdev = pf->pdev;
+ struct i40e_32b_rx_wb_qw0 *qw0;
u32 fcnt_prog, fcnt_avail;
u32 error;
- u64 qw;
- qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- error = (qw & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
+ qw0 = (struct i40e_32b_rx_wb_qw0 *)&qword0_raw;
+ error = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT;
if (error == BIT(I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) {
- pf->fd_inv = le32_to_cpu(rx_desc->wb.qword0.hi_dword.fd_id);
- if ((rx_desc->wb.qword0.hi_dword.fd_id != 0) ||
+ pf->fd_inv = le32_to_cpu(qw0->hi_dword.fd_id);
+ if (qw0->hi_dword.fd_id != 0 ||
(I40E_DEBUG_FD & pf->hw.debug_mask))
dev_warn(&pdev->dev, "ntuple filter loc = %d, could not be added\n",
pf->fd_inv);
@@ -560,7 +561,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring,
/* store the current atr filter count */
pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
- if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
+ if (qw0->hi_dword.fd_id == 0 &&
test_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state)) {
/* These set_bit() calls aren't atomic with the
* test_bit() here, but worse case we potentially
@@ -589,7 +590,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring,
} else if (error == BIT(I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) {
if (I40E_DEBUG_FD & pf->hw.debug_mask)
dev_info(&pdev->dev, "ntuple filter fd_id = %d, could not be removed\n",
- rx_desc->wb.qword0.hi_dword.fd_id);
+ qw0->hi_dword.fd_id);
}
}
@@ -1232,29 +1233,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
}
/**
- * i40e_rx_is_programming_status - check for programming status descriptor
- * @qw: qword representing status_error_len in CPU ordering
- *
- * The value of in the descriptor length field indicate if this
- * is a programming status descriptor for flow director or FCoE
- * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
- * it is a packet descriptor.
- **/
-static inline bool i40e_rx_is_programming_status(u64 qw)
-{
- /* The Rx filter programming status and SPH bit occupy the same
- * spot in the descriptor. Since we don't support packet split we
- * can just reuse the bit as an indication that this is a
- * programming status descriptor.
- */
- return qw & I40E_RXD_QW1_LENGTH_SPH_MASK;
-}
-
-/**
- * i40e_clean_programming_status - try clean the programming status descriptor
+ * i40e_clean_programming_status - clean the programming status descriptor
* @rx_ring: the rx ring that has this descriptor
- * @rx_desc: the rx descriptor written back by HW
- * @qw: qword representing status_error_len in CPU ordering
+ * @qword0: qword0
+ * @qword1: qword1 representing status_error_len in CPU ordering
*
* Flow director should handle FD_FILTER_STATUS to check its filter programming
* status being successful or not and take actions accordingly. FCoE should
@@ -1262,34 +1244,16 @@ static inline bool i40e_rx_is_programming_status(u64 qw)
*
* Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL.
**/
-struct i40e_rx_buffer *i40e_clean_programming_status(
- struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
- u64 qw)
+void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+ u64 qword1)
{
- struct i40e_rx_buffer *rx_buffer;
- u32 ntc;
u8 id;
- if (!i40e_rx_is_programming_status(qw))
- return NULL;
-
- ntc = rx_ring->next_to_clean;
-
- /* fetch, update, and store next to clean */
- rx_buffer = i40e_rx_bi(rx_ring, ntc++);
- ntc = (ntc < rx_ring->count) ? ntc : 0;
- rx_ring->next_to_clean = ntc;
-
- prefetch(I40E_RX_DESC(rx_ring, ntc));
-
- id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
+ id = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
- i40e_fd_handle_status(rx_ring, rx_desc, id);
-
- return rx_buffer;
+ i40e_fd_handle_status(rx_ring, qword0_raw, qword1, id);
}
/**
@@ -1341,13 +1305,25 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
return -ENOMEM;
}
+int i40e_alloc_rx_bi(struct i40e_ring *rx_ring)
+{
+ unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count;
+
+ rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL);
+ return rx_ring->rx_bi ? 0 : -ENOMEM;
+}
+
+static void i40e_clear_rx_bi(struct i40e_ring *rx_ring)
+{
+ memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count);
+}
+
/**
* i40e_clean_rx_ring - Free Rx buffers
* @rx_ring: ring to be cleaned
**/
void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
{
- unsigned long bi_size;
u16 i;
/* ring already cleared, nothing to do */
@@ -1393,8 +1369,10 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
}
skip_free:
- bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
- memset(rx_ring->rx_bi, 0, bi_size);
+ if (rx_ring->xsk_umem)
+ i40e_clear_rx_bi_zc(rx_ring);
+ else
+ i40e_clear_rx_bi(rx_ring);
/* Zero out the descriptor ring */
memset(rx_ring->desc, 0, rx_ring->size);
@@ -1435,15 +1413,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring)
int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
{
struct device *dev = rx_ring->dev;
- int err = -ENOMEM;
- int bi_size;
-
- /* warn if we are about to overwrite the pointer */
- WARN_ON(rx_ring->rx_bi);
- bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
- rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
- if (!rx_ring->rx_bi)
- goto err;
+ int err;
u64_stats_init(&rx_ring->syncp);
@@ -1456,7 +1426,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
if (!rx_ring->desc) {
dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
rx_ring->size);
- goto err;
+ return -ENOMEM;
}
rx_ring->next_to_alloc = 0;
@@ -1468,16 +1438,12 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
rx_ring->queue_index);
if (err < 0)
- goto err;
+ return err;
}
rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
return 0;
-err:
- kfree(rx_ring->rx_bi);
- rx_ring->rx_bi = NULL;
- return err;
}
/**
@@ -2370,9 +2336,12 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
*/
dma_rmb();
- rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc,
- qword);
- if (unlikely(rx_buffer)) {
+ if (i40e_rx_is_programming_status(qword)) {
+ i40e_clean_programming_status(rx_ring,
+ rx_desc->raw.qword[0],
+ qword);
+ rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+ i40e_inc_ntc(rx_ring);
i40e_reuse_rx_page(rx_ring, rx_buffer);
cleaned_count++;
continue;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 36d37f31a287..d343498e8de5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -296,17 +296,15 @@ struct i40e_tx_buffer {
struct i40e_rx_buffer {
dma_addr_t dma;
- union {
- struct {
- struct page *page;
- __u32 page_offset;
- __u16 pagecnt_bias;
- };
- struct {
- void *addr;
- u64 handle;
- };
- };
+ struct page *page;
+ __u32 page_offset;
+ __u16 pagecnt_bias;
+};
+
+struct i40e_rx_buffer_zc {
+ dma_addr_t dma;
+ void *addr;
+ u64 handle;
};
struct i40e_queue_stats {
@@ -358,6 +356,7 @@ struct i40e_ring {
union {
struct i40e_tx_buffer *tx_bi;
struct i40e_rx_buffer *rx_bi;
+ struct i40e_rx_buffer_zc *rx_bi_zc;
};
DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
u16 queue_index; /* Queue number of ring */
@@ -495,6 +494,7 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
bool __i40e_chk_linearize(struct sk_buff *skb);
int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
u32 flags);
+int i40e_alloc_rx_bi(struct i40e_ring *rx_ring);
/**
* i40e_get_head - Retrieve head from head writeback
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
index 8af0e99c6c0d..667c4dc4b39f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -4,13 +4,9 @@
#ifndef I40E_TXRX_COMMON_
#define I40E_TXRX_COMMON_
-void i40e_fd_handle_status(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc, u8 prog_id);
int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring);
-struct i40e_rx_buffer *i40e_clean_programming_status(
- struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
- u64 qw);
+void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+ u64 qword1);
void i40e_process_skb_fields(struct i40e_ring *rx_ring,
union i40e_rx_desc *rx_desc, struct sk_buff *skb);
void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring);
@@ -84,6 +80,38 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
}
}
+/**
+ * i40e_rx_is_programming_status - check for programming status descriptor
+ * @qword1: qword1 representing status_error_len in CPU ordering
+ *
+ * The value of in the descriptor length field indicate if this
+ * is a programming status descriptor for flow director or FCoE
+ * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
+ * it is a packet descriptor.
+ **/
+static inline bool i40e_rx_is_programming_status(u64 qword1)
+{
+ /* The Rx filter programming status and SPH bit occupy the same
+ * spot in the descriptor. Since we don't support packet split we
+ * can just reuse the bit as an indication that this is a
+ * programming status descriptor.
+ */
+ return qword1 & I40E_RXD_QW1_LENGTH_SPH_MASK;
+}
+
+/**
+ * i40e_inc_ntc: Advance the next_to_clean index
+ * @rx_ring: Rx ring
+ **/
+static inline void i40e_inc_ntc(struct i40e_ring *rx_ring)
+{
+ u32 ntc = rx_ring->next_to_clean + 1;
+
+ ntc = (ntc < rx_ring->count) ? ntc : 0;
+ rx_ring->next_to_clean = ntc;
+ prefetch(I40E_RX_DESC(rx_ring, ntc));
+}
+
void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring);
void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 6ea2867ff60f..63e098f7cb63 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -689,7 +689,7 @@ union i40e_32byte_rx_desc {
__le64 rsvd2;
} read;
struct {
- struct {
+ struct i40e_32b_rx_wb_qw0 {
struct {
union {
__le16 mirroring_status;
@@ -727,6 +727,9 @@ union i40e_32byte_rx_desc {
} hi_dword;
} qword3;
} wb; /* writeback */
+ struct {
+ u64 qword[4];
+ } raw;
};
enum i40e_rx_desc_status_bits {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 8d29477bb0b6..4fce057f1eec 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -9,9 +9,23 @@
#include "i40e_txrx_common.h"
#include "i40e_xsk.h"
-static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring)
{
- return &rx_ring->rx_bi[idx];
+ unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count;
+
+ rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL);
+ return rx_ring->rx_bi_zc ? 0 : -ENOMEM;
+}
+
+void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
+{
+ memset(rx_ring->rx_bi_zc, 0,
+ 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)
+{
+ return &rx_ring->rx_bi_zc[idx];
}
/**
@@ -238,7 +252,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
}
/**
- * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer
+ * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer_zc
* @rx_ring: Rx ring
* @bi: Rx buffer to populate
*
@@ -248,7 +262,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
* Returns true for a successful allocation, false otherwise
**/
static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *bi)
+ struct i40e_rx_buffer_zc *bi)
{
struct xdp_umem *umem = rx_ring->xsk_umem;
void *addr = bi->addr;
@@ -279,7 +293,7 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
}
/**
- * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer
+ * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer_zc
* @rx_ring: Rx ring
* @bi: Rx buffer to populate
*
@@ -289,7 +303,7 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
* Returns true for a successful allocation, false otherwise
**/
static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *bi)
+ struct i40e_rx_buffer_zc *bi)
{
struct xdp_umem *umem = rx_ring->xsk_umem;
u64 handle, hr;
@@ -318,11 +332,11 @@ static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
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 *bi))
+ struct i40e_rx_buffer_zc *bi))
{
u16 ntu = rx_ring->next_to_use;
union i40e_rx_desc *rx_desc;
- struct i40e_rx_buffer *bi;
+ struct i40e_rx_buffer_zc *bi;
bool ok = true;
rx_desc = I40E_RX_DESC(rx_ring, ntu);
@@ -402,10 +416,11 @@ static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
*
* Returns the received Rx buffer
**/
-static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
- const unsigned int size)
+static struct i40e_rx_buffer_zc *i40e_get_rx_buffer_zc(
+ struct i40e_ring *rx_ring,
+ const unsigned int size)
{
- struct i40e_rx_buffer *bi;
+ struct i40e_rx_buffer_zc *bi;
bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
@@ -427,10 +442,10 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
* recycle queue (next_to_alloc).
**/
static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *old_bi)
+ struct i40e_rx_buffer_zc *old_bi)
{
- struct i40e_rx_buffer *new_bi = i40e_rx_bi(rx_ring,
- rx_ring->next_to_alloc);
+ 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 */
@@ -452,7 +467,7 @@ static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
**/
void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
{
- struct i40e_rx_buffer *bi;
+ struct i40e_rx_buffer_zc *bi;
struct i40e_ring *rx_ring;
u64 hr, mask;
u16 nta;
@@ -490,7 +505,7 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
* Returns the skb, or NULL on failure.
**/
static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *bi,
+ struct i40e_rx_buffer_zc *bi,
struct xdp_buff *xdp)
{
unsigned int metasize = xdp->data - xdp->data_meta;
@@ -513,19 +528,6 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
return skb;
}
-/**
- * i40e_inc_ntc: Advance the next_to_clean index
- * @rx_ring: Rx ring
- **/
-static void i40e_inc_ntc(struct i40e_ring *rx_ring)
-{
- u32 ntc = rx_ring->next_to_clean + 1;
-
- ntc = (ntc < rx_ring->count) ? ntc : 0;
- rx_ring->next_to_clean = ntc;
- prefetch(I40E_RX_DESC(rx_ring, ntc));
-}
-
/**
* i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
* @rx_ring: Rx ring
@@ -545,7 +547,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
xdp.rxq = &rx_ring->xdp_rxq;
while (likely(total_rx_packets < (unsigned int)budget)) {
- struct i40e_rx_buffer *bi;
+ struct i40e_rx_buffer_zc *bi;
union i40e_rx_desc *rx_desc;
unsigned int size;
u64 qword;
@@ -566,14 +568,18 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
*/
dma_rmb();
- bi = i40e_clean_programming_status(rx_ring, rx_desc,
- qword);
- if (unlikely(bi)) {
+ if (i40e_rx_is_programming_status(qword)) {
+ i40e_clean_programming_status(rx_ring,
+ rx_desc->raw.qword[0],
+ qword);
+ bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+ i40e_inc_ntc(rx_ring);
i40e_reuse_rx_buffer_zc(rx_ring, bi);
cleaned_count++;
continue;
}
+ bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
if (!size)
@@ -830,7 +836,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
u16 i;
for (i = 0; i < rx_ring->count; i++) {
- struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i);
+ struct i40e_rx_buffer_zc *rx_bi = i40e_rx_bi(rx_ring, i);
if (!rx_bi->addr)
continue;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index 9ed59c14eb55..f5e292c218ee 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -19,5 +19,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
struct i40e_ring *tx_ring, int napi_budget);
int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring);
+void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring);
#endif /* _I40E_XSK_H_ */
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 07/14] i40e, xsk: migrate to new MEM_TYPE_XSK_BUFF_POOL
[not found] <20200506132746.526188-1-bjorn.topel@gmail.com>
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 05/14] i40e: refactor rx_bi accesses =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 06/14] i40e: separate kernel allocated rx_bi rings from AF_XDP rings =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
@ 2020-05-06 13:27 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 08/14] ice, " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 09/14] ixgbe, " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
4 siblings, 0 replies; 6+ messages in thread
From: =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= @ 2020-05-06 13:27 UTC (permalink / raw)
To: intel-wired-lan
From: Bj?rn T?pel <bjorn.topel@intel.com>
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.
Cc: intel-wired-lan at lists.osuosl.org
Signed-off-by: Bj?rn T?pel <bjorn.topel@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 19 +-
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 9 +-
drivers/net/ethernet/intel/i40e/i40e_xsk.c | 350 ++------------------
drivers/net/ethernet/intel/i40e/i40e_xsk.h | 1 -
4 files changed, 47 insertions(+), 332 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 3e1695bb8262..ea7395b391e5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3266,21 +3266,19 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
ret = i40e_alloc_rx_bi_zc(ring);
if (ret)
return ret;
- ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
- XDP_PACKET_HEADROOM;
+ ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
/* For AF_XDP ZC, we disallow packets to span on
* multiple buffers, thus letting us skip that
* handling in the fast-path.
*/
chain_len = 1;
- ring->zca.free = i40e_zca_free;
ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
- MEM_TYPE_ZERO_COPY,
- &ring->zca);
+ MEM_TYPE_XSK_BUFF_POOL,
+ NULL);
if (ret)
return ret;
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);
} 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);
writel(0, ring->tail);
- ok = ring->xsk_umem ?
- i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
- !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+ if (ring->xsk_umem) {
+ xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
+ ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring));
+ } else {
+ ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+ }
if (!ok) {
/* Log this in case the user has forgotten to give the kernel
* any buffers, even later in the application.
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index d343498e8de5..5c255977fd58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -301,12 +301,6 @@ struct i40e_rx_buffer {
__u16 pagecnt_bias;
};
-struct i40e_rx_buffer_zc {
- dma_addr_t dma;
- void *addr;
- u64 handle;
-};
-
struct i40e_queue_stats {
u64 packets;
u64 bytes;
@@ -356,7 +350,7 @@ struct i40e_ring {
union {
struct i40e_tx_buffer *tx_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);
u16 queue_index; /* Queue number of ring */
@@ -418,7 +412,6 @@ struct i40e_ring {
struct i40e_channel *ch;
struct xdp_rxq_info xdp_rxq;
struct xdp_umem *xsk_umem;
- struct zero_copy_allocator zca; /* ZC allocator anchor */
} ____cacheline_internodealigned_in_smp;
static inline bool ring_uses_build_skb(struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 4fce057f1eec..460f5052e1db 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -23,68 +23,11 @@ void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
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];
}
-/**
- * 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
* @vsi: Current VSI
@@ -97,7 +40,6 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
u16 qid)
{
struct net_device *netdev = vsi->netdev;
- struct xdp_umem_fq_reuse *reuseq;
bool if_running;
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)
return -EINVAL;
- reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
- if (!reuseq)
- return -ENOMEM;
-
- xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
- err = i40e_xsk_umem_dma_map(vsi, umem);
+ err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
if (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);
- i40e_xsk_umem_dma_unmap(vsi, umem);
+ xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR);
if (if_running) {
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)
{
- struct xdp_umem *umem = rx_ring->xsk_umem;
int err, result = I40E_XDP_PASS;
struct i40e_ring *xdp_ring;
struct bpf_prog *xdp_prog;
- u64 offset;
u32 act;
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);
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) {
case XDP_PASS:
@@ -251,107 +182,26 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
return result;
}
-/**
- * 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))
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
{
u16 ntu = rx_ring->next_to_use;
union i40e_rx_desc *rx_desc;
- struct i40e_rx_buffer_zc *bi;
+ struct xdp_buff **bi, *xdp;
+ dma_addr_t dma;
bool ok = true;
rx_desc = I40E_RX_DESC(rx_ring, ntu);
bi = i40e_rx_bi(rx_ring, ntu);
do {
- if (!alloc(rx_ring, bi)) {
+ xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+ if (!xdp) {
ok = false;
goto no_buffers;
}
-
- dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0,
- rx_ring->rx_buf_len,
- DMA_BIDIRECTIONAL);
-
- rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+ *bi = xdp;
+ dma = xsk_buff_xdp_get_dma(xdp);
+ rx_desc->read.pkt_addr = cpu_to_le64(dma);
+ rx_desc->read.hdr_addr = 0;
rx_desc++;
bi++;
@@ -363,7 +213,6 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
ntu = 0;
}
- rx_desc->wb.qword1.status_error_len = 0;
count--;
} while (count);
@@ -374,126 +223,6 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
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
* @rx_ring: Rx ring
@@ -505,7 +234,6 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
* Returns the skb, or NULL on failure.
**/
static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer_zc *bi,
struct xdp_buff *xdp)
{
unsigned int metasize = xdp->data - xdp->data_meta;
@@ -524,7 +252,7 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
if (metasize)
skb_metadata_set(skb, metasize);
- i40e_reuse_rx_buffer_zc(rx_ring, bi);
+ xsk_buff_free(xdp);
return skb;
}
@@ -542,20 +270,17 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
unsigned int xdp_res, xdp_xmit = 0;
bool failure = false;
struct sk_buff *skb;
- struct xdp_buff xdp;
-
- xdp.rxq = &rx_ring->xdp_rxq;
while (likely(total_rx_packets < (unsigned int)budget)) {
- struct i40e_rx_buffer_zc *bi;
union i40e_rx_desc *rx_desc;
+ struct xdp_buff **bi;
unsigned int size;
u64 qword;
if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
failure = failure ||
- !i40e_alloc_rx_buffers_fast_zc(rx_ring,
- cleaned_count);
+ !i40e_alloc_rx_buffers_zc(rx_ring,
+ cleaned_count);
cleaned_count = 0;
}
@@ -573,9 +298,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
rx_desc->raw.qword[0],
qword);
bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
- i40e_inc_ntc(rx_ring);
- i40e_reuse_rx_buffer_zc(rx_ring, bi);
+ xsk_buff_free(*bi);
+ *bi = NULL;
cleaned_count++;
+ i40e_inc_ntc(rx_ring);
continue;
}
@@ -585,22 +311,18 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
if (!size)
break;
- bi = i40e_get_rx_buffer_zc(rx_ring, size);
- xdp.data = bi->addr;
- xdp.data_meta = xdp.data;
- xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
- xdp.data_end = xdp.data + size;
- xdp.handle = bi->handle;
+ bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+ (*bi)->data_end = (*bi)->data + size;
+ xsk_buff_dma_sync_for_cpu(*bi);
- xdp_res = i40e_run_xdp_zc(rx_ring, &xdp);
+ xdp_res = i40e_run_xdp_zc(rx_ring, *bi);
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;
- bi->addr = NULL;
- } else {
- i40e_reuse_rx_buffer_zc(rx_ring, bi);
- }
+ else
+ xsk_buff_free(*bi);
+ *bi = NULL;
total_rx_bytes += size;
total_rx_packets++;
@@ -616,7 +338,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
* BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
* 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) {
rx_ring->rx_stats.alloc_buff_failed++;
break;
@@ -674,10 +397,9 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
break;
- dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
-
- dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
- DMA_BIDIRECTIONAL);
+ dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
+ xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+ desc.len);
tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
tx_bi->bytecount = desc.len;
@@ -836,13 +558,13 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
u16 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;
- xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle);
- rx_bi->addr = NULL;
+ xsk_buff_free(rx_bi);
+ rx_bi = NULL;
}
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index f5e292c218ee..ea919a7d60ec 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -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_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
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);
int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 08/14] ice, xsk: migrate to new MEM_TYPE_XSK_BUFF_POOL
[not found] <20200506132746.526188-1-bjorn.topel@gmail.com>
` (2 preceding siblings ...)
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 07/14] i40e, xsk: migrate to new MEM_TYPE_XSK_BUFF_POOL =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
@ 2020-05-06 13:27 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 09/14] ixgbe, " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
4 siblings, 0 replies; 6+ messages in thread
From: =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= @ 2020-05-06 13:27 UTC (permalink / raw)
To: intel-wired-lan
From: Bj?rn T?pel <bjorn.topel@intel.com>
Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL
APIs.
Cc: intel-wired-lan at lists.osuosl.org
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Bj?rn T?pel <bjorn.topel@intel.com>
---
drivers/net/ethernet/intel/ice/ice_base.c | 16 +-
drivers/net/ethernet/intel/ice/ice_txrx.h | 8 +-
drivers/net/ethernet/intel/ice/ice_xsk.c | 372 +++-------------------
drivers/net/ethernet/intel/ice/ice_xsk.h | 13 +-
4 files changed, 54 insertions(+), 355 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index a19cd6f5436b..433eb72b1c85 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019, Intel Corporation. */
+#include <net/xdp_sock_drv.h>
#include "ice_base.h"
#include "ice_dcb_lib.h"
@@ -308,24 +309,23 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
if (ring->xsk_umem) {
xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
- ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
- XDP_PACKET_HEADROOM;
+ ring->rx_buf_len =
+ xsk_umem_get_rx_frame_size(ring->xsk_umem);
/* For AF_XDP ZC, we disallow packets to span on
* multiple buffers, thus letting us skip that
* handling in the fast-path.
*/
chain_len = 1;
- ring->zca.free = ice_zca_free;
err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
- MEM_TYPE_ZERO_COPY,
- &ring->zca);
+ MEM_TYPE_XSK_BUFF_POOL,
+ NULL);
if (err)
return err;
+ xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
- dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
+ dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
ring->q_index);
} else {
- ring->zca.free = NULL;
if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
/* coverity[check_return] */
xdp_rxq_info_reg(&ring->xdp_rxq,
@@ -426,7 +426,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
writel(0, ring->tail);
err = ring->xsk_umem ?
- ice_alloc_rx_bufs_slow_zc(ring, ICE_DESC_UNUSED(ring)) :
+ ice_alloc_rx_bufs_zc(ring, ICE_DESC_UNUSED(ring)) :
ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
if (err)
dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 7ee00a128663..d0fd2173854f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -155,17 +155,16 @@ struct ice_tx_offload_params {
};
struct ice_rx_buf {
- struct sk_buff *skb;
- dma_addr_t dma;
union {
struct {
+ struct sk_buff *skb;
+ dma_addr_t dma;
struct page *page;
unsigned int page_offset;
u16 pagecnt_bias;
};
struct {
- void *addr;
- u64 handle;
+ struct xdp_buff *xdp;
};
};
};
@@ -289,7 +288,6 @@ struct ice_ring {
struct rcu_head rcu; /* to avoid race on free */
struct bpf_prog *xdp_prog;
struct xdp_umem *xsk_umem;
- struct zero_copy_allocator zca;
/* CL3 - 3rd cacheline starts here */
struct xdp_rxq_info xdp_rxq;
/* CLX - the below items are only accessed infrequently and should be
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 955b0fbb7c9a..da89589c3137 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -279,28 +279,6 @@ static int ice_xsk_alloc_umems(struct ice_vsi *vsi)
return 0;
}
-/**
- * ice_xsk_add_umem - add a UMEM region for XDP sockets
- * @vsi: VSI to which the UMEM will be added
- * @umem: pointer to a requested UMEM region
- * @qid: queue ID
- *
- * Returns 0 on success, negative on error
- */
-static int ice_xsk_add_umem(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
-{
- int err;
-
- err = ice_xsk_alloc_umems(vsi);
- if (err)
- return err;
-
- vsi->xsk_umems[qid] = umem;
- vsi->num_xsk_umems_used++;
-
- return 0;
-}
-
/**
* ice_xsk_remove_umem - Remove an UMEM for a certain ring/qid
* @vsi: VSI from which the VSI will be removed
@@ -318,65 +296,6 @@ static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid)
}
}
-/**
- * ice_xsk_umem_dma_map - DMA map UMEM region for XDP sockets
- * @vsi: VSI to map the UMEM region
- * @umem: UMEM to map
- *
- * Returns 0 on success, negative on error
- */
-static int ice_xsk_umem_dma_map(struct ice_vsi *vsi, struct xdp_umem *umem)
-{
- struct ice_pf *pf = vsi->back;
- struct device *dev;
- unsigned int i;
-
- dev = ice_pf_to_dev(pf);
- for (i = 0; i < umem->npgs; i++) {
- dma_addr_t dma = dma_map_page_attrs(dev, umem->pgs[i], 0,
- PAGE_SIZE,
- DMA_BIDIRECTIONAL,
- ICE_RX_DMA_ATTR);
- if (dma_mapping_error(dev, dma)) {
- dev_dbg(dev, "XSK UMEM DMA mapping error on page num %d\n",
- i);
- goto out_unmap;
- }
-
- umem->pages[i].dma = dma;
- }
-
- return 0;
-
-out_unmap:
- for (; i > 0; i--) {
- dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
- DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR);
- umem->pages[i].dma = 0;
- }
-
- return -EFAULT;
-}
-
-/**
- * ice_xsk_umem_dma_unmap - DMA unmap UMEM region for XDP sockets
- * @vsi: VSI from which the UMEM will be unmapped
- * @umem: UMEM to unmap
- */
-static void ice_xsk_umem_dma_unmap(struct ice_vsi *vsi, struct xdp_umem *umem)
-{
- struct ice_pf *pf = vsi->back;
- struct device *dev;
- unsigned int i;
-
- dev = ice_pf_to_dev(pf);
- for (i = 0; i < umem->npgs; i++) {
- dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
- DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR);
-
- umem->pages[i].dma = 0;
- }
-}
/**
* ice_xsk_umem_disable - disable a UMEM region
@@ -391,7 +310,7 @@ static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid)
!vsi->xsk_umems[qid])
return -EINVAL;
- ice_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]);
+ xsk_buff_dma_unmap(vsi->xsk_umems[qid], ICE_RX_DMA_ATTR);
ice_xsk_remove_umem(vsi, qid);
return 0;
@@ -408,7 +327,6 @@ static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid)
static int
ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
{
- struct xdp_umem_fq_reuse *reuseq;
int err;
if (vsi->type != ICE_VSI_PF)
@@ -419,20 +337,18 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
if (qid >= vsi->num_xsk_umems)
return -EINVAL;
+ err = ice_xsk_alloc_umems(vsi);
+ if (err)
+ return err;
+
if (vsi->xsk_umems && vsi->xsk_umems[qid])
return -EBUSY;
- reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
- if (!reuseq)
- return -ENOMEM;
-
- xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
- err = ice_xsk_umem_dma_map(vsi, umem);
- if (err)
- return err;
+ vsi->xsk_umems[qid] = umem;
+ vsi->num_xsk_umems_used++;
- err = ice_xsk_add_umem(vsi, umem, qid);
+ err = xsk_buff_dma_map(vsi->xsk_umems[qid], ice_pf_to_dev(vsi->back),
+ ICE_RX_DMA_ATTR);
if (err)
return err;
@@ -483,119 +399,6 @@ int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
return ret;
}
-/**
- * ice_zca_free - Callback for MEM_TYPE_ZERO_COPY allocations
- * @zca: zero-cpoy allocator
- * @handle: Buffer handle
- */
-void ice_zca_free(struct zero_copy_allocator *zca, unsigned long handle)
-{
- struct ice_rx_buf *rx_buf;
- struct ice_ring *rx_ring;
- struct xdp_umem *umem;
- u64 hr, mask;
- u16 nta;
-
- rx_ring = container_of(zca, struct ice_ring, zca);
- umem = rx_ring->xsk_umem;
- hr = umem->headroom + XDP_PACKET_HEADROOM;
-
- mask = umem->chunk_mask;
-
- nta = rx_ring->next_to_alloc;
- rx_buf = &rx_ring->rx_buf[nta];
-
- nta++;
- rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
- handle &= mask;
-
- rx_buf->dma = xdp_umem_get_dma(umem, handle);
- rx_buf->dma += hr;
-
- rx_buf->addr = xdp_umem_get_data(umem, handle);
- rx_buf->addr += hr;
-
- rx_buf->handle = (u64)handle + umem->headroom;
-}
-
-/**
- * ice_alloc_buf_fast_zc - Retrieve buffer address from XDP umem
- * @rx_ring: ring with an xdp_umem bound to it
- * @rx_buf: buffer to which xsk page address will be assigned
- *
- * This function allocates an Rx buffer in the hot path.
- * The buffer can come from fill queue or recycle queue.
- *
- * Returns true if an assignment was successful, false if not.
- */
-static __always_inline bool
-ice_alloc_buf_fast_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
-{
- struct xdp_umem *umem = rx_ring->xsk_umem;
- void *addr = rx_buf->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;
-
- rx_buf->dma = xdp_umem_get_dma(umem, handle);
- rx_buf->dma += hr;
-
- rx_buf->addr = xdp_umem_get_data(umem, handle);
- rx_buf->addr += hr;
-
- rx_buf->handle = handle + umem->headroom;
-
- xsk_umem_release_addr(umem);
- return true;
-}
-
-/**
- * ice_alloc_buf_slow_zc - Retrieve buffer address from XDP umem
- * @rx_ring: ring with an xdp_umem bound to it
- * @rx_buf: buffer to which xsk page address will be assigned
- *
- * This function allocates an Rx buffer in the slow path.
- * The buffer can come from fill queue or recycle queue.
- *
- * Returns true if an assignment was successful, false if not.
- */
-static __always_inline bool
-ice_alloc_buf_slow_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
-{
- struct xdp_umem *umem = rx_ring->xsk_umem;
- u64 handle, headroom;
-
- if (!xsk_umem_peek_addr_rq(umem, &handle)) {
- rx_ring->rx_stats.alloc_page_failed++;
- return false;
- }
-
- handle &= umem->chunk_mask;
- headroom = umem->headroom + XDP_PACKET_HEADROOM;
-
- rx_buf->dma = xdp_umem_get_dma(umem, handle);
- rx_buf->dma += headroom;
-
- rx_buf->addr = xdp_umem_get_data(umem, handle);
- rx_buf->addr += headroom;
-
- rx_buf->handle = handle + umem->headroom;
-
- xsk_umem_release_addr_rq(umem);
- return true;
-}
-
/**
* ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
* @rx_ring: Rx ring
@@ -607,14 +410,13 @@ ice_alloc_buf_slow_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
*
* Returns false if all allocations were successful, true if any fail.
*/
-static bool
-ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count,
- bool (*alloc)(struct ice_ring *, struct ice_rx_buf *))
+bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
{
union ice_32b_rx_flex_desc *rx_desc;
u16 ntu = rx_ring->next_to_use;
struct ice_rx_buf *rx_buf;
bool ret = false;
+ dma_addr_t dma;
if (!count)
return false;
@@ -623,16 +425,14 @@ ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count,
rx_buf = &rx_ring->rx_buf[ntu];
do {
- if (!alloc(rx_ring, rx_buf)) {
+ rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+ if (!rx_buf->xdp) {
ret = true;
break;
}
- dma_sync_single_range_for_device(rx_ring->dev, rx_buf->dma, 0,
- rx_ring->rx_buf_len,
- DMA_BIDIRECTIONAL);
-
- rx_desc->read.pkt_addr = cpu_to_le64(rx_buf->dma);
+ dma = xsk_buff_xdp_get_dma(rx_buf->xdp);
+ rx_desc->read.pkt_addr = cpu_to_le64(dma);
rx_desc->wb.status_error0 = 0;
rx_desc++;
@@ -652,32 +452,6 @@ ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count,
return ret;
}
-/**
- * ice_alloc_rx_bufs_fast_zc - allocate zero copy bufs in the hot path
- * @rx_ring: Rx ring
- * @count: number of bufs to allocate
- *
- * Returns false on success, true on failure.
- */
-static bool ice_alloc_rx_bufs_fast_zc(struct ice_ring *rx_ring, u16 count)
-{
- return ice_alloc_rx_bufs_zc(rx_ring, count,
- ice_alloc_buf_fast_zc);
-}
-
-/**
- * ice_alloc_rx_bufs_slow_zc - allocate zero copy bufs in the slow path
- * @rx_ring: Rx ring
- * @count: number of bufs to allocate
- *
- * Returns false on success, true on failure.
- */
-bool ice_alloc_rx_bufs_slow_zc(struct ice_ring *rx_ring, u16 count)
-{
- return ice_alloc_rx_bufs_zc(rx_ring, count,
- ice_alloc_buf_slow_zc);
-}
-
/**
* ice_bump_ntc - Bump the next_to_clean counter of an Rx ring
* @rx_ring: Rx ring
@@ -691,59 +465,6 @@ static void ice_bump_ntc(struct ice_ring *rx_ring)
prefetch(ICE_RX_DESC(rx_ring, ntc));
}
-/**
- * ice_get_rx_buf_zc - Fetch the current Rx buffer
- * @rx_ring: Rx ring
- * @size: size of a buffer
- *
- * This function returns the current, received Rx buffer and does
- * DMA synchronization.
- *
- * Returns a pointer to the received Rx buffer.
- */
-static struct ice_rx_buf *ice_get_rx_buf_zc(struct ice_ring *rx_ring, int size)
-{
- struct ice_rx_buf *rx_buf;
-
- rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
-
- dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma, 0,
- size, DMA_BIDIRECTIONAL);
-
- return rx_buf;
-}
-
-/**
- * ice_reuse_rx_buf_zc - reuse an Rx buffer
- * @rx_ring: Rx ring
- * @old_buf: The buffer to recycle
- *
- * This function recycles a finished Rx buffer, and places it on the recycle
- * queue (next_to_alloc).
- */
-static void
-ice_reuse_rx_buf_zc(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
-{
- unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask;
- u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
- u16 nta = rx_ring->next_to_alloc;
- struct ice_rx_buf *new_buf;
-
- new_buf = &rx_ring->rx_buf[nta++];
- rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
- new_buf->dma = old_buf->dma & mask;
- new_buf->dma += hr;
-
- new_buf->addr = (void *)((unsigned long)old_buf->addr & mask);
- new_buf->addr += hr;
-
- new_buf->handle = old_buf->handle & mask;
- new_buf->handle += rx_ring->xsk_umem->headroom;
-
- old_buf->addr = NULL;
-}
-
/**
* ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
* @rx_ring: Rx ring
@@ -755,13 +476,12 @@ ice_reuse_rx_buf_zc(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
* Returns the skb on success, NULL on failure.
*/
static struct sk_buff *
-ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
- struct xdp_buff *xdp)
+ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
{
- unsigned int metasize = xdp->data - xdp->data_meta;
- unsigned int datasize = xdp->data_end - xdp->data;
- unsigned int datasize_hard = xdp->data_end -
- xdp->data_hard_start;
+ unsigned int metasize = rx_buf->xdp->data - rx_buf->xdp->data_meta;
+ unsigned int datasize = rx_buf->xdp->data_end - rx_buf->xdp->data;
+ unsigned int datasize_hard = rx_buf->xdp->data_end -
+ rx_buf->xdp->data_hard_start;
struct sk_buff *skb;
skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
@@ -769,13 +489,13 @@ ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
if (unlikely(!skb))
return NULL;
- skb_reserve(skb, xdp->data - xdp->data_hard_start);
- memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+ skb_reserve(skb, rx_buf->xdp->data - rx_buf->xdp->data_hard_start);
+ memcpy(__skb_put(skb, datasize), rx_buf->xdp->data, datasize);
if (metasize)
skb_metadata_set(skb, metasize);
- ice_reuse_rx_buf_zc(rx_ring, rx_buf);
-
+ xsk_buff_free(rx_buf->xdp);
+ rx_buf->xdp = NULL;
return skb;
}
@@ -802,7 +522,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
}
act = bpf_prog_run_xdp(xdp_prog, xdp);
- xdp->handle += xdp->data - xdp->data_hard_start;
switch (act) {
case XDP_PASS:
break;
@@ -842,9 +561,6 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
unsigned int xdp_xmit = 0;
bool failure = false;
- struct xdp_buff xdp;
-
- xdp.rxq = &rx_ring->xdp_rxq;
while (likely(total_rx_packets < (unsigned int)budget)) {
union ice_32b_rx_flex_desc *rx_desc;
@@ -856,8 +572,8 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
u8 rx_ptype;
if (cleaned_count >= ICE_RX_BUF_WRITE) {
- failure |= ice_alloc_rx_bufs_fast_zc(rx_ring,
- cleaned_count);
+ failure |= ice_alloc_rx_bufs_zc(rx_ring,
+ cleaned_count);
cleaned_count = 0;
}
@@ -878,25 +594,19 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
if (!size)
break;
- rx_buf = ice_get_rx_buf_zc(rx_ring, size);
- if (!rx_buf->addr)
- break;
- xdp.data = rx_buf->addr;
- xdp.data_meta = xdp.data;
- xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
- xdp.data_end = xdp.data + size;
- xdp.handle = rx_buf->handle;
+ rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
+ rx_buf->xdp->data_end = rx_buf->xdp->data + size;
+ xsk_buff_dma_sync_for_cpu(rx_buf->xdp);
- xdp_res = ice_run_xdp_zc(rx_ring, &xdp);
+ xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp);
if (xdp_res) {
- if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+ if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
xdp_xmit |= xdp_res;
- rx_buf->addr = NULL;
- } else {
- ice_reuse_rx_buf_zc(rx_ring, rx_buf);
- }
+ else
+ xsk_buff_free(rx_buf->xdp);
+ rx_buf->xdp = NULL;
total_rx_bytes += size;
total_rx_packets++;
cleaned_count++;
@@ -906,7 +616,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
}
/* XDP_PASS path */
- skb = ice_construct_skb_zc(rx_ring, rx_buf, &xdp);
+ skb = ice_construct_skb_zc(rx_ring, rx_buf);
if (!skb) {
rx_ring->rx_stats.alloc_buf_failed++;
break;
@@ -977,10 +687,9 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
break;
- dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
-
- dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
- DMA_BIDIRECTIONAL);
+ dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
+ xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+ desc.len);
tx_buf->bytecount = desc.len;
@@ -1163,11 +872,10 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring)
for (i = 0; i < rx_ring->count; i++) {
struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];
- if (!rx_buf->addr)
+ if (!rx_buf->xdp)
continue;
- xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_buf->handle);
- rx_buf->addr = NULL;
+ rx_buf->xdp = NULL;
}
}
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 8a4ba7c6d549..fc1a06b4df36 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -10,11 +10,10 @@ struct ice_vsi;
#ifdef CONFIG_XDP_SOCKETS
int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid);
-void ice_zca_free(struct zero_copy_allocator *zca, unsigned long handle);
int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget);
bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget);
int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_slow_zc(struct ice_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count);
bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring);
void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring);
@@ -27,12 +26,6 @@ ice_xsk_umem_setup(struct ice_vsi __always_unused *vsi,
return -EOPNOTSUPP;
}
-static inline void
-ice_zca_free(struct zero_copy_allocator __always_unused *zca,
- unsigned long __always_unused handle)
-{
-}
-
static inline int
ice_clean_rx_irq_zc(struct ice_ring __always_unused *rx_ring,
int __always_unused budget)
@@ -48,8 +41,8 @@ ice_clean_tx_irq_zc(struct ice_ring __always_unused *xdp_ring,
}
static inline bool
-ice_alloc_rx_bufs_slow_zc(struct ice_ring __always_unused *rx_ring,
- u16 __always_unused count)
+ice_alloc_rx_bufs_zc(struct ice_ring __always_unused *rx_ring,
+ u16 __always_unused count)
{
return false;
}
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 09/14] ixgbe, xsk: migrate to new MEM_TYPE_XSK_BUFF_POOL
[not found] <20200506132746.526188-1-bjorn.topel@gmail.com>
` (3 preceding siblings ...)
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 08/14] ice, " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
@ 2020-05-06 13:27 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
4 siblings, 0 replies; 6+ messages in thread
From: =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= @ 2020-05-06 13:27 UTC (permalink / raw)
To: intel-wired-lan
From: Bj?rn T?pel <bjorn.topel@intel.com>
Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL
APIs.
Cc: intel-wired-lan at lists.osuosl.org
Signed-off-by: Bj?rn T?pel <bjorn.topel@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 9 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 15 +-
.../ethernet/intel/ixgbe/ixgbe_txrx_common.h | 2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 305 +++---------------
4 files changed, 62 insertions(+), 269 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 2833e4f041ce..5ddfc83a1e46 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -224,17 +224,17 @@ struct ixgbe_tx_buffer {
};
struct ixgbe_rx_buffer {
- struct sk_buff *skb;
- dma_addr_t dma;
union {
struct {
+ struct sk_buff *skb;
+ dma_addr_t dma;
struct page *page;
__u32 page_offset;
__u16 pagecnt_bias;
};
struct {
- void *addr;
- u64 handle;
+ bool discard;
+ struct xdp_buff *xdp;
};
};
};
@@ -351,7 +351,6 @@ struct ixgbe_ring {
};
struct xdp_rxq_info xdp_rxq;
struct xdp_umem *xsk_umem;
- struct zero_copy_allocator zca; /* ZC allocator anchor */
u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */
u16 rx_buf_len;
} ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 718931d951bc..da7b8042901f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -35,7 +35,7 @@
#include <net/tc_act/tc_mirred.h>
#include <net/vxlan.h>
#include <net/mpls.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
#include <net/xfrm.h>
#include "ixgbe.h"
@@ -3726,8 +3726,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
/* configure the packet buffer length */
if (rx_ring->xsk_umem) {
- u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr -
- XDP_PACKET_HEADROOM;
+ u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_umem);
/* If the MAC support setting RXDCTL.RLPML, the
* SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
@@ -4074,11 +4073,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
if (ring->xsk_umem) {
- ring->zca.free = ixgbe_zca_free;
WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
- MEM_TYPE_ZERO_COPY,
- &ring->zca));
-
+ MEM_TYPE_XSK_BUFF_POOL,
+ NULL));
+ xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
} else {
WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
MEM_TYPE_PAGE_SHARED, NULL));
@@ -4134,8 +4132,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
}
if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) {
- u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr -
- XDP_PACKET_HEADROOM;
+ u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
IXGBE_RXDCTL_RLPML_EN);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index 6d01700b46bc..7887ae4aaf4f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -35,7 +35,7 @@ int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
-void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
+bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *rx_ring,
const int budget);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 5b6edbd8a4ed..12f5dc3fe76e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -20,54 +20,11 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
return xdp_get_umem_from_qid(adapter->netdev, qid);
}
-static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter,
- struct xdp_umem *umem)
-{
- struct device *dev = &adapter->pdev->dev;
- unsigned int i, j;
- dma_addr_t dma;
-
- for (i = 0; i < umem->npgs; i++) {
- dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
- DMA_BIDIRECTIONAL, IXGBE_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, IXGBE_RX_DMA_ATTR);
- umem->pages[i].dma = 0;
- }
-
- return -1;
-}
-
-static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter,
- struct xdp_umem *umem)
-{
- struct device *dev = &adapter->pdev->dev;
- unsigned int i;
-
- for (i = 0; i < umem->npgs; i++) {
- dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
- DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
-
- umem->pages[i].dma = 0;
- }
-}
-
static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
struct xdp_umem *umem,
u16 qid)
{
struct net_device *netdev = adapter->netdev;
- struct xdp_umem_fq_reuse *reuseq;
bool if_running;
int err;
@@ -78,13 +35,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
qid >= netdev->real_num_tx_queues)
return -EINVAL;
- reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count);
- if (!reuseq)
- return -ENOMEM;
-
- xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
- err = ixgbe_xsk_umem_dma_map(adapter, umem);
+ err = xsk_buff_dma_map(umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
if (err)
return err;
@@ -124,7 +75,7 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
ixgbe_txrx_ring_disable(adapter, qid);
clear_bit(qid, adapter->af_xdp_zc_qps);
- ixgbe_xsk_umem_dma_unmap(adapter, umem);
+ xsk_buff_dma_unmap(umem, IXGBE_RX_DMA_ATTR);
if (if_running)
ixgbe_txrx_ring_enable(adapter, qid);
@@ -143,19 +94,14 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring,
struct xdp_buff *xdp)
{
- struct xdp_umem *umem = rx_ring->xsk_umem;
int err, result = IXGBE_XDP_PASS;
struct bpf_prog *xdp_prog;
struct xdp_frame *xdpf;
- u64 offset;
u32 act;
rcu_read_lock();
xdp_prog = READ_ONCE(rx_ring->xdp_prog);
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) {
case XDP_PASS:
@@ -186,140 +132,16 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
return result;
}
-static struct
-ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring,
- unsigned int size)
-{
- struct ixgbe_rx_buffer *bi;
-
- bi = &rx_ring->rx_buffer_info[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;
-}
-
-static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring,
- struct ixgbe_rx_buffer *obi)
-{
- u16 nta = rx_ring->next_to_alloc;
- struct ixgbe_rx_buffer *nbi;
-
- nbi = &rx_ring->rx_buffer_info[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 */
- nbi->dma = obi->dma;
- nbi->addr = obi->addr;
- nbi->handle = obi->handle;
-
- obi->addr = NULL;
- obi->skb = NULL;
-}
-
-void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
-{
- struct ixgbe_rx_buffer *bi;
- struct ixgbe_ring *rx_ring;
- u64 hr, mask;
- u16 nta;
-
- rx_ring = container_of(alloc, struct ixgbe_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 = rx_ring->rx_buffer_info;
-
- 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);
-}
-
-static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring,
- struct ixgbe_rx_buffer *bi)
-{
- struct xdp_umem *umem = rx_ring->xsk_umem;
- void *addr = bi->addr;
- u64 handle, hr;
-
- if (addr)
- return true;
-
- if (!xsk_umem_peek_addr(umem, &handle)) {
- rx_ring->rx_stats.alloc_rx_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;
-}
-
-static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring,
- struct ixgbe_rx_buffer *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_rx_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
-__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
- bool alloc(struct ixgbe_ring *rx_ring,
- struct ixgbe_rx_buffer *bi))
+bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
{
union ixgbe_adv_rx_desc *rx_desc;
struct ixgbe_rx_buffer *bi;
u16 i = rx_ring->next_to_use;
+ dma_addr_t dma;
bool ok = true;
/* nothing to do */
- if (!cleaned_count)
+ if (!count)
return true;
rx_desc = IXGBE_RX_DESC(rx_ring, i);
@@ -327,21 +149,18 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
i -= rx_ring->count;
do {
- if (!alloc(rx_ring, bi)) {
+ bi->xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+ if (!bi->xdp) {
ok = false;
break;
}
- /* sync the buffer for use by the device */
- dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
- bi->page_offset,
- rx_ring->rx_buf_len,
- DMA_BIDIRECTIONAL);
+ dma = xsk_buff_xdp_get_dma(bi->xdp);
/* Refresh the desc even if buffer_addrs didn't change
* because each write-back erases this info.
*/
- rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+ rx_desc->read.pkt_addr = cpu_to_le64(dma);
rx_desc++;
bi++;
@@ -355,17 +174,14 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
/* clear the length for the next_to_use descriptor */
rx_desc->wb.upper.length = 0;
- cleaned_count--;
- } while (cleaned_count);
+ count--;
+ } while (count);
i += rx_ring->count;
if (rx_ring->next_to_use != i) {
rx_ring->next_to_use = i;
- /* update next to alloc since we have filled the ring */
- rx_ring->next_to_alloc = i;
-
/* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch. (Only
* applicable for weak-ordered memory model archs,
@@ -378,40 +194,27 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
return ok;
}
-void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
-{
- __ixgbe_alloc_rx_buffers_zc(rx_ring, count,
- ixgbe_alloc_buffer_slow_zc);
-}
-
-static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring,
- u16 count)
-{
- return __ixgbe_alloc_rx_buffers_zc(rx_ring, count,
- ixgbe_alloc_buffer_zc);
-}
-
static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
- struct ixgbe_rx_buffer *bi,
- struct xdp_buff *xdp)
+ struct ixgbe_rx_buffer *bi)
{
- unsigned int metasize = xdp->data - xdp->data_meta;
- unsigned int datasize = xdp->data_end - xdp->data;
+ unsigned int metasize = bi->xdp->data - bi->xdp->data_meta;
+ unsigned int datasize = bi->xdp->data_end - bi->xdp->data;
struct sk_buff *skb;
/* allocate a skb to store the frags */
skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- xdp->data_end - xdp->data_hard_start,
+ bi->xdp->data_end - bi->xdp->data_hard_start,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
- skb_reserve(skb, xdp->data - xdp->data_hard_start);
- memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+ skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start);
+ memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize);
if (metasize)
skb_metadata_set(skb, metasize);
- ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ xsk_buff_free(bi->xdp);
+ bi->xdp = NULL;
return skb;
}
@@ -434,9 +237,6 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
unsigned int xdp_res, xdp_xmit = 0;
bool failure = false;
struct sk_buff *skb;
- struct xdp_buff xdp;
-
- xdp.rxq = &rx_ring->xdp_rxq;
while (likely(total_rx_packets < budget)) {
union ixgbe_adv_rx_desc *rx_desc;
@@ -446,8 +246,8 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
/* return some buffers to hardware, one@a time is too slow */
if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
failure = failure ||
- !ixgbe_alloc_rx_buffers_fast_zc(rx_ring,
- cleaned_count);
+ !ixgbe_alloc_rx_buffers_zc(rx_ring,
+ cleaned_count);
cleaned_count = 0;
}
@@ -462,42 +262,40 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
*/
dma_rmb();
- bi = ixgbe_get_rx_buffer_zc(rx_ring, size);
+ bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
if (unlikely(!ixgbe_test_staterr(rx_desc,
IXGBE_RXD_STAT_EOP))) {
struct ixgbe_rx_buffer *next_bi;
- ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ xsk_buff_free(bi->xdp);
+ bi->xdp = NULL;
ixgbe_inc_ntc(rx_ring);
next_bi =
&rx_ring->rx_buffer_info[rx_ring->next_to_clean];
- next_bi->skb = ERR_PTR(-EINVAL);
+ next_bi->discard = true;
continue;
}
- if (unlikely(bi->skb)) {
- ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ if (unlikely(bi->discard)) {
+ xsk_buff_free(bi->xdp);
+ bi->xdp = NULL;
+ bi->discard = false;
ixgbe_inc_ntc(rx_ring);
continue;
}
- xdp.data = bi->addr;
- xdp.data_meta = xdp.data;
- xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
- xdp.data_end = xdp.data + size;
- xdp.handle = bi->handle;
-
- xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp);
+ bi->xdp->data_end = bi->xdp->data_end + size;
+ xsk_buff_dma_sync_for_cpu(bi->xdp);
+ xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp);
if (xdp_res) {
- if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+ if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))
xdp_xmit |= xdp_res;
- bi->addr = NULL;
- bi->skb = NULL;
- } else {
- ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
- }
+ else
+ xsk_buff_free(bi->xdp);
+
+ bi->xdp = NULL;
total_rx_packets++;
total_rx_bytes += size;
@@ -507,7 +305,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
}
/* XDP_PASS path */
- skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp);
+ skb = ixgbe_construct_skb_zc(rx_ring, bi);
if (!skb) {
rx_ring->rx_stats.alloc_rx_buff_failed++;
break;
@@ -559,17 +357,17 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring)
{
- u16 i = rx_ring->next_to_clean;
- struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i];
+ struct ixgbe_rx_buffer *bi;
+ u16 i;
- while (i != rx_ring->next_to_alloc) {
- xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle);
- i++;
- bi++;
- if (i == rx_ring->count) {
- i = 0;
- bi = rx_ring->rx_buffer_info;
- }
+ for (i = 0; i < rx_ring->count; i++) {
+ bi = &rx_ring->rx_buffer_info[i];
+
+ if (!bi->xdp)
+ continue;
+
+ xsk_buff_free(bi->xdp);
+ bi->xdp = NULL;
}
}
@@ -592,10 +390,9 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
break;
- dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
-
- dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
- DMA_BIDIRECTIONAL);
+ dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
+ xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+ desc.len);
tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
tx_bi->bytecount = desc.len;
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 05/14] i40e: refactor rx_bi accesses
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 05/14] i40e: refactor rx_bi accesses =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
@ 2020-05-06 13:30 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
0 siblings, 0 replies; 6+ messages in thread
From: =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= @ 2020-05-06 13:30 UTC (permalink / raw)
To: intel-wired-lan
On Wed, 6 May 2020 at 15:28, Bj?rn T?pel <bjorn.topel@gmail.com> wrote:
>
> From: Bj?rn T?pel <bjorn.topel@intel.com>
>
> As a first step to migrate i40e to the new MEM_TYPE_XSK_BUFF_POOL
> APIs, code that accesses the rx_bi (SW/shadow ring) is refactored to
> use an accessor function.
>
And c**p. So much for "no Cc". Sorry for the noise intel-wired-lan.
Bj?rn
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2020-05-06 13:30 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <20200506132746.526188-1-bjorn.topel@gmail.com>
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 05/14] i40e: refactor rx_bi accesses =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:30 ` =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 06/14] i40e: separate kernel allocated rx_bi rings from AF_XDP rings =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 07/14] i40e, xsk: migrate to new MEM_TYPE_XSK_BUFF_POOL =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 08/14] ice, " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
2020-05-06 13:27 ` [Intel-wired-lan] [PATCH bpf-next pre-v1 MAXONLY 09/14] ixgbe, " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?=
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.