[dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[Xiaolong Ye]

This patch adds a new devarg to support the need_wakeup flag for Tx and
fill rings, when this flag is set by the driver, it means that the
userspace application has to explicitly wake up the kernel Rx or kernel Tx
processing by issuing a syscall. Poll() can wake up both and sendto() or
its alternatives will wake up Tx processing only.

This feature is to provide efficient support for case that application and
driver are executing on the same core.

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
---

Original busy poll feature has morphed into need_wakeup flag in
kernel side, the main purpose is the same, that is to support both
application and driver executing on the same core efficiently.

kernel side patchset can be found at netdev mailing list.
https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t

It is targeted for v5.3

 drivers/net/af_xdp/rte_eth_af_xdp.c | 51 ++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 15 deletions(-)

diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index c638d9227..198b00147 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -5,6 +5,7 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <string.h>
+#include <poll.h>
 #include <netinet/in.h>
 #include <net/if.h>
 #include <sys/socket.h>
@@ -90,6 +91,7 @@ struct pkt_rx_queue {
 	struct rx_stats stats;
 
 	struct pkt_tx_queue *pair;
+	struct pollfd fds[1];
 	int xsk_queue_idx;
 };
 
@@ -117,6 +119,7 @@ struct pmd_internals {
 	int combined_queue_cnt;
 
 	int pmd_zc;
+	int need_wakeup;
 	struct rte_ether_addr eth_addr;
 
 	struct pkt_rx_queue *rx_queues;
@@ -127,12 +130,14 @@ struct pmd_internals {
 #define ETH_AF_XDP_START_QUEUE_ARG		"start_queue"
 #define ETH_AF_XDP_QUEUE_COUNT_ARG		"queue_count"
 #define ETH_AF_XDP_PMD_ZC_ARG			"pmd_zero_copy"
+#define ETH_AF_XDP_NEED_WAKEUP_ARG		"need_wakeup"
 
 static const char * const valid_arguments[] = {
 	ETH_AF_XDP_IFACE_ARG,
 	ETH_AF_XDP_START_QUEUE_ARG,
 	ETH_AF_XDP_QUEUE_COUNT_ARG,
 	ETH_AF_XDP_PMD_ZC_ARG,
+	ETH_AF_XDP_NEED_WAKEUP_ARG,
 	NULL
 };
 
@@ -206,8 +211,12 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		return 0;
 
 	rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
-	if (rcvd == 0)
+	if (rcvd == 0) {
+		if (xsk_ring_prod__needs_wakeup(fq))
+			(void)poll(rxq->fds, 1, 1000);
+
 		goto out;
+	}
 
 	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
 		(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
@@ -279,16 +288,17 @@ kick_tx(struct pkt_tx_queue *txq)
 {
 	struct xsk_umem_info *umem = txq->pair->umem;
 
-	while (send(xsk_socket__fd(txq->pair->xsk), NULL,
-		      0, MSG_DONTWAIT) < 0) {
-		/* some thing unexpected */
-		if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
-			break;
+	if (xsk_ring_prod__needs_wakeup(&txq->tx))
+		while (send(xsk_socket__fd(txq->pair->xsk), NULL,
+			    0, MSG_DONTWAIT) < 0) {
+			/* some thing unexpected */
+			if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
+				break;
 
-		/* pull from completion queue to leave more space */
-		if (errno == EAGAIN)
-			pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
-	}
+			/* pull from completion queue to leave more space */
+			if (errno == EAGAIN)
+				pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+		}
 	pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
 }
 
@@ -621,7 +631,7 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
 	cfg.tx_size = ring_size;
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-	cfg.bind_flags = 0;
+	cfg.bind_flags = internals->need_wakeup ? XDP_USE_NEED_WAKEUP : 0;
 	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
 			rxq->xsk_queue_idx, rxq->umem->umem, &rxq->rx,
 			&txq->tx, &cfg);
@@ -683,6 +693,9 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		goto err;
 	}
 
+	rxq->fds[0].fd = xsk_socket__fd(rxq->xsk);
+	rxq->fds[0].events = POLLIN;
+
 	rxq->umem->pmd_zc = internals->pmd_zc;
 
 	dev->data->rx_queues[rx_queue_id] = rxq;
@@ -856,7 +869,7 @@ xdp_get_channels_info(const char *if_name, int *max_queues,
 
 static int
 parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *start_queue,
-			int *queue_cnt, int *pmd_zc)
+		 int *queue_cnt, int *pmd_zc, int *need_wakeup)
 {
 	int ret;
 
@@ -882,6 +895,9 @@ parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *start_queue,
 	if (ret < 0)
 		goto free_kvlist;
 
+	ret = rte_kvargs_process(kvlist, ETH_AF_XDP_NEED_WAKEUP_ARG,
+				 &parse_integer_arg, need_wakeup);
+
 free_kvlist:
 	rte_kvargs_free(kvlist);
 	return ret;
@@ -919,7 +935,7 @@ get_iface_info(const char *if_name,
 
 static struct rte_eth_dev *
 init_internals(struct rte_vdev_device *dev, const char *if_name,
-			int start_queue_idx, int queue_cnt, int pmd_zc)
+	       int start_queue_idx, int queue_cnt, int pmd_zc, int need_wakeup)
 {
 	const char *name = rte_vdev_device_name(dev);
 	const unsigned int numa_node = dev->device.numa_node;
@@ -935,6 +951,7 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	internals->start_queue_idx = start_queue_idx;
 	internals->queue_cnt = queue_cnt;
 	internals->pmd_zc = pmd_zc;
+	internals->need_wakeup = !!need_wakeup;
 	strlcpy(internals->if_name, if_name, IFNAMSIZ);
 
 	if (xdp_get_channels_info(if_name, &internals->max_queue_cnt,
@@ -993,6 +1010,9 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	if (internals->pmd_zc)
 		AF_XDP_LOG(INFO, "Zero copy between umem and mbuf enabled.\n");
 
+	if (internals->need_wakeup)
+		AF_XDP_LOG(INFO, "need_wakeup feature is explicitly turned on.\n");
+
 	return eth_dev;
 
 err_free_tx:
@@ -1014,6 +1034,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 	struct rte_eth_dev *eth_dev = NULL;
 	const char *name;
 	int pmd_zc = 0;
+	int need_wakeup = 0;
 
 	AF_XDP_LOG(INFO, "Initializing pmd_af_xdp for %s\n",
 		rte_vdev_device_name(dev));
@@ -1041,7 +1062,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 		dev->device.numa_node = rte_socket_id();
 
 	if (parse_parameters(kvlist, if_name, &xsk_start_queue_idx,
-			     &xsk_queue_cnt, &pmd_zc) < 0) {
+			     &xsk_queue_cnt, &pmd_zc, &need_wakeup) < 0) {
 		AF_XDP_LOG(ERR, "Invalid kvargs value\n");
 		return -EINVAL;
 	}
@@ -1052,7 +1073,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 	}
 
 	eth_dev = init_internals(dev, if_name, xsk_start_queue_idx,
-					xsk_queue_cnt, pmd_zc);
+				 xsk_queue_cnt, pmd_zc, need_wakeup);
 	if (eth_dev == NULL) {
 		AF_XDP_LOG(ERR, "Failed to init internals\n");
 		return -1;
-- 
2.17.1

Re: [dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[David Marchand]

On Mon, Jun 17, 2019 at 9:42 AM Xiaolong Ye <xiaolong.ye@intel.com> wrote:

> This patch adds a new devarg to support the need_wakeup flag for Tx and
> fill rings, when this flag is set by the driver, it means that the
> userspace application has to explicitly wake up the kernel Rx or kernel Tx
> processing by issuing a syscall. Poll() can wake up both and sendto() or
> its alternatives will wake up Tx processing only.
>
> This feature is to provide efficient support for case that application and
> driver are executing on the same core.
>
> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
> ---
>
> Original busy poll feature has morphed into need_wakeup flag in
> kernel side, the main purpose is the same, that is to support both
> application and driver executing on the same core efficiently.
>
> kernel side patchset can be found at netdev mailing list.
>
> https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t
>
> It is targeted for v5.3
>

- Is this really optional? Adding too many options is just a nightmare
later...

- I suppose this will break compilation with kernels that have af_xdp but
are < 5.3.


-- 
David Marchand

Re: [dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[Ye Xiaolong]

On 06/17, David Marchand wrote:
>On Mon, Jun 17, 2019 at 9:42 AM Xiaolong Ye <xiaolong.ye@intel.com> wrote:
>
>> This patch adds a new devarg to support the need_wakeup flag for Tx and
>> fill rings, when this flag is set by the driver, it means that the
>> userspace application has to explicitly wake up the kernel Rx or kernel Tx
>> processing by issuing a syscall. Poll() can wake up both and sendto() or
>> its alternatives will wake up Tx processing only.
>>
>> This feature is to provide efficient support for case that application and
>> driver are executing on the same core.
>>
>> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
>> ---
>>
>> Original busy poll feature has morphed into need_wakeup flag in
>> kernel side, the main purpose is the same, that is to support both
>> application and driver executing on the same core efficiently.
>>
>> kernel side patchset can be found at netdev mailing list.
>>
>> https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t
>>
>> It is targeted for v5.3
>>
>
>- Is this really optional? Adding too many options is just a nightmare
>later...

Hmm, I think we can remove this option and alway turn the need_wakeup flag on
since it provides better performance for 1 core case and doesn't downgrage the
2 core case performance.

>
>- I suppose this will break compilation with kernels that have af_xdp but
>are < 5.3.

Yes, that is true. It will break the compilation with early kernel, I feel it's 
sort of common issue, we enable some features in dpdk that's based on kernel
features, then kernel side features keep evolving, we need to keep the pace,
but it will hurt the compatiblity with the old kernel.

What's dpdk's convention for handling this kind of case? Add some notes in doc
to reminder the prerequisite or use the KERNEL_VERSION macro in code?

Thanks,
Xiaolong

>
>
>-- 
>David Marchand

Re: [dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[David Marchand]

On Mon, Jun 17, 2019 at 10:45 AM Ye Xiaolong <xiaolong.ye@intel.com> wrote:

> On 06/17, David Marchand wrote:
> >On Mon, Jun 17, 2019 at 9:42 AM Xiaolong Ye <xiaolong.ye@intel.com>
> wrote:
> >
> >> This patch adds a new devarg to support the need_wakeup flag for Tx and
> >> fill rings, when this flag is set by the driver, it means that the
> >> userspace application has to explicitly wake up the kernel Rx or kernel
> Tx
> >> processing by issuing a syscall. Poll() can wake up both and sendto() or
> >> its alternatives will wake up Tx processing only.
> >>
> >> This feature is to provide efficient support for case that application
> and
> >> driver are executing on the same core.
> >>
> >> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
> >> ---
> >>
> >> Original busy poll feature has morphed into need_wakeup flag in
> >> kernel side, the main purpose is the same, that is to support both
> >> application and driver executing on the same core efficiently.
> >>
> >> kernel side patchset can be found at netdev mailing list.
> >>
> >>
> https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t
> >>
> >> It is targeted for v5.3
> >>
> >
> >- Is this really optional? Adding too many options is just a nightmare
> >later...
>
> Hmm, I think we can remove this option and alway turn the need_wakeup flag
> on
> since it provides better performance for 1 core case and doesn't downgrage
> the
> 2 core case performance.
>
> >
> >- I suppose this will break compilation with kernels that have af_xdp but
> >are < 5.3.
>
> Yes, that is true. It will break the compilation with early kernel, I feel
> it's
> sort of common issue, we enable some features in dpdk that's based on
> kernel
> features, then kernel side features keep evolving, we need to keep the
> pace,
> but it will hurt the compatiblity with the old kernel.
>
> What's dpdk's convention for handling this kind of case? Add some notes in
> doc
> to reminder the prerequisite or use the KERNEL_VERSION macro in code?
>

Rather than a kernel version, you can check that XDP_USE_NEED_WAKEUP is
defined (present in the uapi kernel header).


-- 
David Marchand

Re: [dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[Bruce Richardson]

On Mon, Jun 17, 2019 at 10:51:52AM +0200, David Marchand wrote:
> On Mon, Jun 17, 2019 at 10:45 AM Ye Xiaolong <xiaolong.ye@intel.com> wrote:
> 
> > On 06/17, David Marchand wrote:
> > >On Mon, Jun 17, 2019 at 9:42 AM Xiaolong Ye <xiaolong.ye@intel.com>
> > wrote:
> > >
> > >> This patch adds a new devarg to support the need_wakeup flag for Tx and
> > >> fill rings, when this flag is set by the driver, it means that the
> > >> userspace application has to explicitly wake up the kernel Rx or kernel
> > Tx
> > >> processing by issuing a syscall. Poll() can wake up both and sendto() or
> > >> its alternatives will wake up Tx processing only.
> > >>
> > >> This feature is to provide efficient support for case that application
> > and
> > >> driver are executing on the same core.
> > >>
> > >> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
> > >> ---
> > >>
> > >> Original busy poll feature has morphed into need_wakeup flag in
> > >> kernel side, the main purpose is the same, that is to support both
> > >> application and driver executing on the same core efficiently.
> > >>
> > >> kernel side patchset can be found at netdev mailing list.
> > >>
> > >>
> > https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t
> > >>
> > >> It is targeted for v5.3
> > >>
> > >
> > >- Is this really optional? Adding too many options is just a nightmare
> > >later...
> >
> > Hmm, I think we can remove this option and alway turn the need_wakeup flag
> > on
> > since it provides better performance for 1 core case and doesn't downgrage
> > the
> > 2 core case performance.
> >
> > >
> > >- I suppose this will break compilation with kernels that have af_xdp but
> > >are < 5.3.
> >
> > Yes, that is true. It will break the compilation with early kernel, I feel
> > it's
> > sort of common issue, we enable some features in dpdk that's based on
> > kernel
> > features, then kernel side features keep evolving, we need to keep the
> > pace,
> > but it will hurt the compatiblity with the old kernel.
> >
> > What's dpdk's convention for handling this kind of case? Add some notes in
> > doc
> > to reminder the prerequisite or use the KERNEL_VERSION macro in code?
> >
> 
> Rather than a kernel version, you can check that XDP_USE_NEED_WAKEUP is
> defined (present in the uapi kernel header).
> 
+1 for this.

Also, since AF_XDP is still fairly new with ongoing development on the
kernel side, I think it is reasonable to limit out PMD to only working with
sufficiently updated kernels. Hopefully in 6 months or so, the feature set
we need should be locked down and we can specify a fixed baseline
requirement.

/Bruce

Re: [dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature

[Ye Xiaolong]

On 06/17, David Marchand wrote:
>On Mon, Jun 17, 2019 at 10:45 AM Ye Xiaolong <xiaolong.ye@intel.com> wrote:
>
>> On 06/17, David Marchand wrote:
>> >On Mon, Jun 17, 2019 at 9:42 AM Xiaolong Ye <xiaolong.ye@intel.com>
>> wrote:
>> >
>> >> This patch adds a new devarg to support the need_wakeup flag for Tx and
>> >> fill rings, when this flag is set by the driver, it means that the
>> >> userspace application has to explicitly wake up the kernel Rx or kernel
>> Tx
>> >> processing by issuing a syscall. Poll() can wake up both and sendto() or
>> >> its alternatives will wake up Tx processing only.
>> >>
>> >> This feature is to provide efficient support for case that application
>> and
>> >> driver are executing on the same core.
>> >>
>> >> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
>> >> ---
>> >>
>> >> Original busy poll feature has morphed into need_wakeup flag in
>> >> kernel side, the main purpose is the same, that is to support both
>> >> application and driver executing on the same core efficiently.
>> >>
>> >> kernel side patchset can be found at netdev mailing list.
>> >>
>> >>
>> https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t
>> >>
>> >> It is targeted for v5.3
>> >>
>> >
>> >- Is this really optional? Adding too many options is just a nightmare
>> >later...
>>
>> Hmm, I think we can remove this option and alway turn the need_wakeup flag
>> on
>> since it provides better performance for 1 core case and doesn't downgrage
>> the
>> 2 core case performance.
>>
>> >
>> >- I suppose this will break compilation with kernels that have af_xdp but
>> >are < 5.3.
>>
>> Yes, that is true. It will break the compilation with early kernel, I feel
>> it's
>> sort of common issue, we enable some features in dpdk that's based on
>> kernel
>> features, then kernel side features keep evolving, we need to keep the
>> pace,
>> but it will hurt the compatiblity with the old kernel.
>>
>> What's dpdk's convention for handling this kind of case? Add some notes in
>> doc
>> to reminder the prerequisite or use the KERNEL_VERSION macro in code?
>>
>
>Rather than a kernel version, you can check that XDP_USE_NEED_WAKEUP is
>defined (present in the uapi kernel header).

Sounds better, will try.

Thanks,
Xiaolong
>
>
>-- 
>David Marchand

[dpdk-dev] [PATCH v2] net/af_xdp: support need wakeup feature

[Xiaolong Ye]

This patch enables need_wakeup flag for Tx and fill rings, when this flag
is set by the driver, it means that the userspace application has to
explicitly wake up the kernel Rx or kernel Tx processing by issuing a
syscall. Poll() can wake up both and sendto() or its alternatives will wake
up Tx processing only.

This feature is to provide efficient support for case that application and
driver are executing on the same core.

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
---

v2 changes:

1. remove need_wakeup devarg to make need_wakeup feature enabled
   unconditionally.
2. add conditional compilation directive to avoid breaking build with
   kernel which doesn't support need_wakeup feature yet.

Note:

Original busy poll feature has morphed into need_wakeup flag in
kernel side, the main purpose is the same, that is to support both
application and driver executing on the same core efficiently.

kernel side patchset can be found at netdev mailing list.
https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t

It is targeted for v5.3

Cc: David Marchand <david.marchand@redhat.com>
Cc: Bruce Richardson <bruce.richardson@intel.com>

 drivers/net/af_xdp/rte_eth_af_xdp.c | 41 +++++++++++++++++++++--------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index c638d9227..5ce90a760 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -5,6 +5,7 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <string.h>
+#include <poll.h>
 #include <netinet/in.h>
 #include <net/if.h>
 #include <sys/socket.h>
@@ -90,6 +91,7 @@ struct pkt_rx_queue {
 	struct rx_stats stats;
 
 	struct pkt_tx_queue *pair;
+	struct pollfd fds[1];
 	int xsk_queue_idx;
 };
 
@@ -206,8 +208,14 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		return 0;
 
 	rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
-	if (rcvd == 0)
+	if (rcvd == 0) {
+#if defined(XDP_USE_NEED_WAKEUP)
+		if (xsk_ring_prod__needs_wakeup(fq))
+			(void)poll(rxq->fds, 1, 1000);
+#endif
+
 		goto out;
+	}
 
 	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
 		(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
@@ -279,16 +287,19 @@ kick_tx(struct pkt_tx_queue *txq)
 {
 	struct xsk_umem_info *umem = txq->pair->umem;
 
-	while (send(xsk_socket__fd(txq->pair->xsk), NULL,
-		      0, MSG_DONTWAIT) < 0) {
-		/* some thing unexpected */
-		if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
-			break;
-
-		/* pull from completion queue to leave more space */
-		if (errno == EAGAIN)
-			pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
-	}
+#if defined(XDP_USE_NEED_WAKEUP)
+	if (xsk_ring_prod__needs_wakeup(&txq->tx))
+#endif
+		while (send(xsk_socket__fd(txq->pair->xsk), NULL,
+			    0, MSG_DONTWAIT) < 0) {
+			/* some thing unexpected */
+			if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
+				break;
+
+			/* pull from completion queue to leave more space */
+			if (errno == EAGAIN)
+				pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+		}
 	pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
 }
 
@@ -622,6 +633,11 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	cfg.bind_flags = 0;
+
+#if defined(XDP_USE_NEED_WAKEUP)
+	cfg.bind_flags |= XDP_USE_NEED_WAKEUP;
+#endif
+
 	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
 			rxq->xsk_queue_idx, rxq->umem->umem, &rxq->rx,
 			&txq->tx, &cfg);
@@ -683,6 +699,9 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		goto err;
 	}
 
+	rxq->fds[0].fd = xsk_socket__fd(rxq->xsk);
+	rxq->fds[0].events = POLLIN;
+
 	rxq->umem->pmd_zc = internals->pmd_zc;
 
 	dev->data->rx_queues[rx_queue_id] = rxq;
-- 
2.17.1

[dpdk-dev] [PATCH v3] net/af_xdp: support need wakeup feature

[Xiaolong Ye]

This patch enables need_wakeup flag for Tx and fill rings, when this flag
is set by the driver, it means that the userspace application has to
explicitly wake up the kernel Rx or kernel Tx processing by issuing a
syscall. Poll() can wake up both and sendto() or its alternatives will wake
up Tx processing only.

This feature is to provide efficient support for case that application and
driver executing on the same core.

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
---
v3 changes:

1. add introduction in 19.08 release note

v2 changes:

1. remove need_wakeup devarg to make need_wakeup feature enabled
   unconditionally.
2. add conditional compilation directive to avoid breaking build with
   kernel which doesn't support need_wakeup feature yet.

Note:

Original busy poll feature has morphed into need_wakeup flag in
kernel side, the main purpose is the same, that is to support both
application and driver executing on the same core efficiently.
 doc/guides/rel_notes/release_19_08.rst |  2 ++
 drivers/net/af_xdp/rte_eth_af_xdp.c    | 41 +++++++++++++++++++-------
 2 files changed, 32 insertions(+), 11 deletions(-)

diff --git a/doc/guides/rel_notes/release_19_08.rst b/doc/guides/rel_notes/release_19_08.rst
index 8c3932d06..49656c3cc 100644
--- a/doc/guides/rel_notes/release_19_08.rst
+++ b/doc/guides/rel_notes/release_19_08.rst
@@ -87,6 +87,8 @@ New Features
     high performance
   * Added multi-queue support to allow one af_xdp vdev with multiple netdev
     queues
+  * Enabled need_wakeup feature which can provide efficient support for case
+    that application and driver executing on the same core.
 
 
 Removed Items
diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index c638d9227..5ce90a760 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -5,6 +5,7 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <string.h>
+#include <poll.h>
 #include <netinet/in.h>
 #include <net/if.h>
 #include <sys/socket.h>
@@ -90,6 +91,7 @@ struct pkt_rx_queue {
 	struct rx_stats stats;
 
 	struct pkt_tx_queue *pair;
+	struct pollfd fds[1];
 	int xsk_queue_idx;
 };
 
@@ -206,8 +208,14 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		return 0;
 
 	rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
-	if (rcvd == 0)
+	if (rcvd == 0) {
+#if defined(XDP_USE_NEED_WAKEUP)
+		if (xsk_ring_prod__needs_wakeup(fq))
+			(void)poll(rxq->fds, 1, 1000);
+#endif
+
 		goto out;
+	}
 
 	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
 		(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
@@ -279,16 +287,19 @@ kick_tx(struct pkt_tx_queue *txq)
 {
 	struct xsk_umem_info *umem = txq->pair->umem;
 
-	while (send(xsk_socket__fd(txq->pair->xsk), NULL,
-		      0, MSG_DONTWAIT) < 0) {
-		/* some thing unexpected */
-		if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
-			break;
-
-		/* pull from completion queue to leave more space */
-		if (errno == EAGAIN)
-			pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
-	}
+#if defined(XDP_USE_NEED_WAKEUP)
+	if (xsk_ring_prod__needs_wakeup(&txq->tx))
+#endif
+		while (send(xsk_socket__fd(txq->pair->xsk), NULL,
+			    0, MSG_DONTWAIT) < 0) {
+			/* some thing unexpected */
+			if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
+				break;
+
+			/* pull from completion queue to leave more space */
+			if (errno == EAGAIN)
+				pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+		}
 	pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
 }
 
@@ -622,6 +633,11 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	cfg.bind_flags = 0;
+
+#if defined(XDP_USE_NEED_WAKEUP)
+	cfg.bind_flags |= XDP_USE_NEED_WAKEUP;
+#endif
+
 	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
 			rxq->xsk_queue_idx, rxq->umem->umem, &rxq->rx,
 			&txq->tx, &cfg);
@@ -683,6 +699,9 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		goto err;
 	}
 
+	rxq->fds[0].fd = xsk_socket__fd(rxq->xsk);
+	rxq->fds[0].events = POLLIN;
+
 	rxq->umem->pmd_zc = internals->pmd_zc;
 
 	dev->data->rx_queues[rx_queue_id] = rxq;
-- 
2.17.1

Re: [dpdk-dev] [PATCH v3] net/af_xdp: support need wakeup feature

[Ferruh Yigit]

On 6/21/2019 2:19 PM, Xiaolong Ye wrote:
> This patch enables need_wakeup flag for Tx and fill rings, when this flag
> is set by the driver, it means that the userspace application has to
> explicitly wake up the kernel Rx or kernel Tx processing by issuing a
> syscall. Poll() can wake up both and sendto() or its alternatives will wake
> up Tx processing only.
> 
> This feature is to provide efficient support for case that application and
> driver executing on the same core.
> 
> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
> ---
> v3 changes:
> 
> 1. add introduction in 19.08 release note
> 
> v2 changes:
> 
> 1. remove need_wakeup devarg to make need_wakeup feature enabled
>    unconditionally.
> 2. add conditional compilation directive to avoid breaking build with
>    kernel which doesn't support need_wakeup feature yet.
> 
> Note:
> 
> Original busy poll feature has morphed into need_wakeup flag in
> kernel side, the main purpose is the same, that is to support both
> application and driver executing on the same core efficiently.
>  doc/guides/rel_notes/release_19_08.rst |  2 ++
>  drivers/net/af_xdp/rte_eth_af_xdp.c    | 41 +++++++++++++++++++-------

Hi Xiaolong,

Can you please document this feature in af_xdp documentation? And if there
specific kernel version requirement for this, can you please add this
information too?

Re: [dpdk-dev] [PATCH v3] net/af_xdp: support need wakeup feature

[Ye Xiaolong]

Hi, Ferruh

On 06/27, Ferruh Yigit wrote:
>On 6/21/2019 2:19 PM, Xiaolong Ye wrote:
>> This patch enables need_wakeup flag for Tx and fill rings, when this flag
>> is set by the driver, it means that the userspace application has to
>> explicitly wake up the kernel Rx or kernel Tx processing by issuing a
>> syscall. Poll() can wake up both and sendto() or its alternatives will wake
>> up Tx processing only.
>> 
>> This feature is to provide efficient support for case that application and
>> driver executing on the same core.
>> 
>> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
>> ---
>> v3 changes:
>> 
>> 1. add introduction in 19.08 release note
>> 
>> v2 changes:
>> 
>> 1. remove need_wakeup devarg to make need_wakeup feature enabled
>>    unconditionally.
>> 2. add conditional compilation directive to avoid breaking build with
>>    kernel which doesn't support need_wakeup feature yet.
>> 
>> Note:
>> 
>> Original busy poll feature has morphed into need_wakeup flag in
>> kernel side, the main purpose is the same, that is to support both
>> application and driver executing on the same core efficiently.
>>  doc/guides/rel_notes/release_19_08.rst |  2 ++
>>  drivers/net/af_xdp/rte_eth_af_xdp.c    | 41 +++++++++++++++++++-------
>
>Hi Xiaolong,
>
>Can you please document this feature in af_xdp documentation? And if there
>specific kernel version requirement for this, can you please add this
>information too?

Got it, will do in next version.

Thanks,
Xiaolong
>

[dpdk-dev] [PATCH v4] net/af_xdp: support need wakeup feature

[Xiaolong Ye]

This patch enables need_wakeup flag for Tx and fill rings, when this flag
is set by the driver, it means that the userspace application has to
explicitly wake up the kernel Rx or kernel Tx processing by issuing a
syscall. Poll() can wake up both and sendto() or its alternatives will wake
up Tx processing only.

This feature is to provide efficient support for case that application and
driver executing on the same core.

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
---

v4 changes:

1. document need_wakeup feature in the af_xdp.rst

v3 changes:

1. add introduction in 19.08 release note

v2 changes:

1. remove need_wakeup devarg to make need_wakeup feature enabled
   unconditionally.
2. add conditional compilation directive to avoid breaking build with
   kernel which doesn't support need_wakeup feature yet.

Note:

Original busy poll feature has morphed into need_wakeup flag in
kernel side, the main purpose is the same, that is to support both
application and driver executing on the same core efficiently.

 doc/guides/nics/af_xdp.rst             |  7 +++++
 doc/guides/rel_notes/release_19_08.rst |  2 ++
 drivers/net/af_xdp/rte_eth_af_xdp.c    | 41 +++++++++++++++++++-------
 3 files changed, 39 insertions(+), 11 deletions(-)

diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
index 18defcda3..c99c4c715 100644
--- a/doc/guides/nics/af_xdp.rst
+++ b/doc/guides/nics/af_xdp.rst
@@ -21,6 +21,12 @@ be added later.
 Note that MTU of AF_XDP PMD is limited due to XDP lacks support for
 fragmentation.
 
+AF_XDP PMD enables need_wakeup flag by default if it is supported. This
+need_wakeup feature is used to support executing application and driver on the
+same core efficiently. This feature not only has a large positive performance
+impact for the one core case, but also does not degrade 2 core performance and
+actually improves it for Tx heavy workloads.
+
 Options
 -------
 
@@ -41,6 +47,7 @@ This is a Linux-specific PMD, thus the following prerequisites apply:
    User can install libbpf via `make install_lib` && `make install_headers` in
    <kernel src tree>/tools/lib/bpf;
 *  A Kernel bound interface to attach to;
+*  For need_wakeup feature, it requires kernel version later than v5.3-rc1;
 
 Set up an af_xdp interface
 -----------------------------
diff --git a/doc/guides/rel_notes/release_19_08.rst b/doc/guides/rel_notes/release_19_08.rst
index 3da266705..1c9efcbe7 100644
--- a/doc/guides/rel_notes/release_19_08.rst
+++ b/doc/guides/rel_notes/release_19_08.rst
@@ -93,6 +93,8 @@ New Features
     high performance
   * Added multi-queue support to allow one af_xdp vdev with multiple netdev
     queues
+  * Enabled need_wakeup feature which can provide efficient support for case
+    that application and driver executing on the same core.
 
 * **Updated telemetry library for global metrics support.**
 
diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index c638d9227..5ce90a760 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -5,6 +5,7 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <string.h>
+#include <poll.h>
 #include <netinet/in.h>
 #include <net/if.h>
 #include <sys/socket.h>
@@ -90,6 +91,7 @@ struct pkt_rx_queue {
 	struct rx_stats stats;
 
 	struct pkt_tx_queue *pair;
+	struct pollfd fds[1];
 	int xsk_queue_idx;
 };
 
@@ -206,8 +208,14 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		return 0;
 
 	rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
-	if (rcvd == 0)
+	if (rcvd == 0) {
+#if defined(XDP_USE_NEED_WAKEUP)
+		if (xsk_ring_prod__needs_wakeup(fq))
+			(void)poll(rxq->fds, 1, 1000);
+#endif
+
 		goto out;
+	}
 
 	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
 		(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
@@ -279,16 +287,19 @@ kick_tx(struct pkt_tx_queue *txq)
 {
 	struct xsk_umem_info *umem = txq->pair->umem;
 
-	while (send(xsk_socket__fd(txq->pair->xsk), NULL,
-		      0, MSG_DONTWAIT) < 0) {
-		/* some thing unexpected */
-		if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
-			break;
-
-		/* pull from completion queue to leave more space */
-		if (errno == EAGAIN)
-			pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
-	}
+#if defined(XDP_USE_NEED_WAKEUP)
+	if (xsk_ring_prod__needs_wakeup(&txq->tx))
+#endif
+		while (send(xsk_socket__fd(txq->pair->xsk), NULL,
+			    0, MSG_DONTWAIT) < 0) {
+			/* some thing unexpected */
+			if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
+				break;
+
+			/* pull from completion queue to leave more space */
+			if (errno == EAGAIN)
+				pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+		}
 	pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
 }
 
@@ -622,6 +633,11 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	cfg.bind_flags = 0;
+
+#if defined(XDP_USE_NEED_WAKEUP)
+	cfg.bind_flags |= XDP_USE_NEED_WAKEUP;
+#endif
+
 	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
 			rxq->xsk_queue_idx, rxq->umem->umem, &rxq->rx,
 			&txq->tx, &cfg);
@@ -683,6 +699,9 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		goto err;
 	}
 
+	rxq->fds[0].fd = xsk_socket__fd(rxq->xsk);
+	rxq->fds[0].events = POLLIN;
+
 	rxq->umem->pmd_zc = internals->pmd_zc;
 
 	dev->data->rx_queues[rx_queue_id] = rxq;
-- 
2.17.1

Re: [dpdk-dev] [PATCH v4] net/af_xdp: support need wakeup feature

[Ferruh Yigit]

On 6/28/2019 11:07 AM, Xiaolong Ye wrote:
> This patch enables need_wakeup flag for Tx and fill rings, when this flag
> is set by the driver, it means that the userspace application has to
> explicitly wake up the kernel Rx or kernel Tx processing by issuing a
> syscall. Poll() can wake up both and sendto() or its alternatives will wake
> up Tx processing only.
> 
> This feature is to provide efficient support for case that application and
> driver executing on the same core.
> 
> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>

Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

Applied to dpdk-next-net/master, thanks.