Introduce AF_XDP PMD
Subsystems (2)
PATCH v5 1/5 net/af_xdp: introduce AF XDP PMD driver
In reply to Xiaolong YeAdd a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 6 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 45 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 931 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1065 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +6 -0
@@ -468,6 +468,12 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/features/af_xdp.rst + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -416,6 +416,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +45 -0
45 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -65,6 +65,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +32 -0
@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpf + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/meson.build new file +21 -0
@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif + +bpf_dep = dependency('libbpf', required: false) +if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false) + if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
drivers/net/af_xdp/rte_eth_af_xdp.c new file +931 -0
931 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v5 1/5] net/af_xdp: introduce AF XDP PMD driver
drivers/net/af_xdp/rte_eth_af_xdp.c line 135
Quoted 4 lines · On Mon, 25 Mar 2019 14:03:56 +0800 Xiaolong Ye <[email protected]> wrote:
drivers/net/af_xdp/rte_eth_af_xdp.c new file +4
-0+ + ret =xsk_ring_prod__reserve (fq, reserve_size, &idx); +if (unlikely (!ret)) { +AF_XDP_LOG (ERR ,"Failed to reserve enough fq descs.\n" );
You defined AF_XDP_LOG to add a newline (similar to other drivers). But all the messages already have a newline.
This will cause log to be double spaced.
Re: [PATCH v5 1/5] net/af_xdp: introduce AF XDP PMD driver
Quoted 11 lines · Stephen Hemminger
drivers/net/af_xdp/rte_eth_af_xdp.c line 135
Quoted 4 lines · On Mon, 25 Mar 2019 14:03:56 +0800 Xiaolong Ye <[email protected]> wrote:
drivers/net/af_xdp/rte_eth_af_xdp.c new file +4
-0+ + ret =xsk_ring_prod__reserve (fq, reserve_size, &idx); +if (unlikely (!ret)) { +AF_XDP_LOG (ERR ,"Failed to reserve enough fq descs.\n" );You defined
AF_XDP_LOGto add a newline (similar to other drivers). But all the messages already have a newline.
This will cause log to be double spaced.
Thanks for the catch, I'll remove the newline in the definition.
PATCH v5 2/5 lib/mbuf: introduce helper to create mempool with flags
In reply to Xiaolong YeThis allows applications to create mbuf mempool with specific flags such as MEMPOOL_F_NO_SPREAD if they want fixed size memory objects.
--- lib/librte_mbuf/rte_mbuf.c | 29 ++++++++++++++---- lib/librte_mbuf/rte_mbuf.h | 45 ++++++++++++++++++++++++++++ lib/librte_mbuf/rte_mbuf_version.map | 1 + 3 files changed, 70 insertions(+), 5 deletions(-)
lib/librte_mbuf/rte_mbuf.c +24 -5
@@ -106,11 +106,10 @@ rte_pktmbuf_init(struct rte_mempool *mp, m->next =NULL ; } -/* Helper to create a mbuf pool with given mempool ops name*/ -struct rte_mempool * -rte_pktmbuf_pool_create_by_ops (const char *name,unsigned int n, +static struct rte_mempool * +rte_pktmbuf_pool_create_by_ops_with_flags (const char *name,unsigned int n,unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, -int socket_id,const char *ops_name) +unsigned int flags,int socket_id,const char *ops_name) {struct rte_mempool *mp;struct rte_pktmbuf_pool_private mbp_priv;
@@ -130,7 +129,7 @@ rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n, mbp_priv.mbuf_priv_size = priv_size; mp =rte_mempool_create_empty (name, n, elt_size, cache_size, -sizeof (struct rte_pktmbuf_pool_private ), socket_id,0 ); +sizeof (struct rte_pktmbuf_pool_private ), socket_id, flags);if (mp ==NULL )return NULL ;
@@ -157,6 +156,16 @@ rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n,return mp; } +/* Helper to create a mbuf pool with given mempool ops name*/ +struct rte_mempool * +rte_pktmbuf_pool_create_by_ops (const char *name,unsigned int n, +unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, +int socket_id,const char *ops_name) +{ +return rte_pktmbuf_pool_create_by_ops_with_flags (name, n, cache_size, + priv_size, data_room_size,0 , socket_id, ops_name); +} +/* helper to create a mbuf pool */ struct rte_mempool * rte_pktmbuf_pool_create(const char *name, unsigned int n,
@@ -167,6 +176,16 @@ rte_pktmbuf_pool_create(const char *name, unsigned int n, data_room_size, socket_id, NULL); } +/* helper to create a mbuf pool with flags (e.g. NO_SPREAD) */ +struct rte_mempool * __rte_experimental +rte_pktmbuf_pool_create_with_flags (const char *name,unsigned int n, +unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, +unsigned int flags,int socket_id) +{ +return rte_pktmbuf_pool_create_by_ops_with_flags (name, n, cache_size, + priv_size, data_room_size, flags, socket_id,NULL ); +} +/* do some sanity checks on a mbuf: panic if it fails */ void rte_mbuf_sanity_check (const struct rte_mbuf *m,int is_header)
lib/librte_mbuf/rte_mbuf.h +45 -0
51 lines not on this page · raw message
lib/librte_mbuf/rte_mbuf_version.map +1 -0
@@ -50,4 +50,5 @@ EXPERIMENTAL { global: rte_mbuf_check; + rte_pktmbuf_pool_create_with_flags; } DPDK_18.08;
Signature · 1 line
2.17.1
PATCH v5 3/5 lib/mempool: allow page size aligned mempool
In reply to Xiaolong YeAllow create a mempool with page size aligned base address.
--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)
lib/librte_mempool/rte_mempool.c +3 -0
@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);
lib/librte_mempool/rte_mempool.h +1 -0
@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */ /** * @internal When debug is enabled, store some statistics.
Signature · 1 line
2.17.1
Re: [PATCH v5 3/5] lib/mempool: allow page size aligned mempool
Quoted 28 lines · Xiaolong Ye
Allow create a mempool with page size aligned base address.
Signed-off-by Qi Zhang <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)lib/librte_mempool/rte_mempool.c +3
-0@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);lib/librte_mempool/rte_mempool.h +0
-0
lib/librte_mempool/rte_mempool.h struct rte_mempool { · line 267
Quoted 4 lines
lib/librte_mempool/rte_mempool.h +1
-0@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */
For me it sounds like mempool objects should be page aligned since MEMPOOL_F_NO_SPREAD, MEMPOOL_F_NO_CACHE_ALIGN and MEMPOOL_F_NO_IOVA_CONTIG say about object properties, not chunk.
Personally I doubt that the final goal is just having chunk page aligned.
Andrew.
Re: [PATCH v5 3/5] lib/mempool: allow page size aligned mempool
Quoted 36 lines · Andrew Rybchenko
Quoted 26 lines · Xiaolong Ye
Allow create a mempool with page size aligned base address.
Signed-off-by Qi Zhang <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)lib/librte_mempool/rte_mempool.c +3
-0@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);lib/librte_mempool/rte_mempool.h +0
-0lib/librte_mempool/rte_mempool.h struct rte_mempool { · line 267
Quoted 4 lines
lib/librte_mempool/rte_mempool.h +1
-0@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */ For me it sounds like mempool objects should be page aligned since
MEMPOOL_F_NO_SPREAD,MEMPOOL_F_NO_CACHE_ALIGNandMEMPOOL_F_NO_IOVA_CONTIGsay about object properties, not chunk.
Quoted 1 line
Personally I doubt that the final goal is just having chunk page aligned.
Hmm, how about naming it MEMPOOL_CHUNK_F_PAGE_ALIGN?
Thanks,
Xiaolong
Quoted 2 lines
Andrew.
PATCH v5 4/5 net/af_xdp: use mbuf mempool for buffer management
In reply to Xiaolong YeNow, af_xdp registered memory buffer is managed by rte_mempool. mbuf allocated from rte_mempool can be converted to xdp_desc's address and vice versa.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 117 +++++++++++++++++----------- 1 file changed, 72 insertions(+), 45 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +72 -45
@@ -48,7 +48,11 @@ static int af_xdp_logtype;#define ETH_AF_XDP_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE#define ETH_AF_XDP_NUM_BUFFERS 4096 -#define ETH_AF_XDP_DATA_HEADROOM 0 +/* mempool hdrobj size (64 bytes) + sizeof(struct rte_mbuf) (128 bytes) */ +#define ETH_AF_XDP_MBUF_OVERHEAD 192 +/* data start from offset 320 (192 + 128) bytes */ +#define ETH_AF_XDP_DATA_HEADROOM \ + (ETH_AF_XDP_MBUF_OVERHEAD + RTE_PKTMBUF_HEADROOM)#define ETH_AF_XDP_DFLT_NUM_DESCS XSK_RING_CONS__DEFAULT_NUM_DESCS#define ETH_AF_XDP_DFLT_QUEUE_IDX 0
@@ -61,7 +65,7 @@ struct xsk_umem_info {struct xsk_ring_prod fq;struct xsk_ring_cons cq;struct xsk_umem *umem; -struct rte_ring *buf_ring; +struct rte_mempool *mb_pool;void *buffer; };
@@ -123,10 +127,30 @@ static struct rte_eth_link pmd_link = { .link_autoneg = ETH_LINK_AUTONEG }; +static inline struct rte_mbuf * +addr_to_mbuf (struct xsk_umem_info *umem,uint64_t addr) +{ +uint64_t offset = (addr /ETH_AF_XDP_FRAME_SIZE * +ETH_AF_XDP_FRAME_SIZE ); +struct rte_mbuf *mbuf = (struct rte_mbuf *)((uint64_t )umem->buffer + + offset +ETH_AF_XDP_MBUF_OVERHEAD - +sizeof (struct rte_mbuf )); + mbuf->data_off = addr - offset -ETH_AF_XDP_MBUF_OVERHEAD ; +return mbuf; +} + +static inline uint64_t +mbuf_to_addr (struct xsk_umem_info *umem,struct rte_mbuf *mbuf) +{ +return (uint64_t )mbuf->buf_addr + mbuf->data_off - + (uint64_t )umem->buffer; +} +static inline int reserve_fill_queue (struct xsk_umem_info *umem,int reserve_size) {struct xsk_ring_prod *fq = &umem->fq; +struct rte_mbuf *mbuf;uint32_t idx;int i, ret;
@@ -138,13 +162,15 @@ reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)for (i =0 ; i < reserve_size; i++) {__u64 *fq_addr; -void *addr =NULL ; -if (rte_ring_dequeue (umem->buf_ring, &addr)) { +uint64_t addr; + mbuf =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf ==NULL )) { i--;break ; } + addr =mbuf_to_addr (umem, mbuf); fq_addr =xsk_ring_prod__fill_addr (fq, idx++); - *fq_addr = (uint64_t )addr; + *fq_addr = addr; }xsk_ring_prod__submit (fq, i);
@@ -196,7 +222,7 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) rx_bytes += len; bufs[count++] = mbufs[i]; -rte_ring_enqueue (umem->buf_ring, (void *)addr); +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); }xsk_ring_cons__release (rx, rcvd);
@@ -219,7 +245,7 @@ static void pull_umem_cq(struct xsk_umem_info *umem, int size)for (i =0 ; i < n; i++) {uint64_t addr; addr = *xsk_ring_cons__comp_addr (cq, idx_cq++); -rte_ring_enqueue (umem->buf_ring, (void *)addr); +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); }xsk_ring_cons__release (cq, n);
@@ -248,7 +274,7 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)struct pkt_tx_queue *txq = queue;struct xsk_umem_info *umem = txq->pair->umem;struct rte_mbuf *mbuf; -void *addrs[ETH_AF_XDP_TX_BATCH_SIZE ]; +struct rte_mbuf *mbuf_to_tx;unsigned long tx_bytes =0 ;int i, valid =0 ;uint32_t idx_tx;
@@ -257,11 +283,6 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)pull_umem_cq (umem, nb_pkts); - nb_pkts =rte_ring_dequeue_bulk (umem->buf_ring, addrs, - nb_pkts,NULL ); -if (nb_pkts ==0 ) -return 0 ; -if (xsk_ring_prod__reserve (&txq->tx, nb_pkts, &idx_tx) != nb_pkts) {kick_tx (txq);return 0 ;
@@ -275,7 +296,12 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) desc =xsk_ring_prod__tx_desc (&txq->tx, idx_tx + i); mbuf = bufs[i];if (mbuf->pkt_len <= buf_len) { - desc->addr = (uint64_t )addrs[valid]; + mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf_to_tx ==NULL )) { +rte_pktmbuf_free (mbuf); +continue ; + } + desc->addr =mbuf_to_addr (umem, mbuf_to_tx); desc->len = mbuf->pkt_len; pkt =xsk_umem__get_data (umem->buffer, desc->addr);
@@ -291,10 +317,6 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)kick_tx (txq); -if (valid < nb_pkts) -rte_ring_enqueue_bulk (umem->buf_ring, &addrs[valid], - nb_pkts - valid,NULL ); - txq->stats.err_pkts += nb_pkts - valid; txq->stats.tx_pkts += valid; txq->stats.tx_bytes += tx_bytes;
@@ -443,16 +465,29 @@ eth_link_update(struct rte_eth_dev *dev __rte_unused,static void xdp_umem_destroy (struct xsk_umem_info *umem) { -free (umem->buffer); - umem->buffer =NULL ; - -rte_ring_free (umem->buf_ring); - umem->buf_ring =NULL ; +rte_mempool_free (umem->mb_pool); + umem->mb_pool =NULL ;rte_free (umem); umem =NULL ; } +static inline uint64_t get_base_addr (struct rte_mempool *mp) +{ +struct rte_mempool_memhdr *memhdr; + + memhdr =STAILQ_FIRST (&mp->mem_list); +return (uint64_t )(memhdr->addr); +} + +static inline uint64_t get_len (struct rte_mempool *mp) +{ +struct rte_mempool_memhdr *memhdr; + + memhdr =STAILQ_FIRST (&mp->mem_list); +return (uint64_t )(memhdr->len); +} +static struct xsk_umem_info *xdp_umem_configure (void ) {struct xsk_umem_info *umem;
@@ -461,9 +496,8 @@ static struct xsk_umem_info *xdp_umem_configure(void) .comp_size = ETH_AF_XDP_DFLT_NUM_DESCS, .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM }; -void *bufs =NULL ; +void *base_addr =NULL ;int ret; -uint64_t i; umem =rte_zmalloc_socket ("umem" ,sizeof (*umem),0 ,rte_socket_id ());if (umem ==NULL ) {
@@ -471,26 +505,20 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->buf_ring =rte_ring_create ("af_xdp_ring" , -ETH_AF_XDP_NUM_BUFFERS , -SOCKET_ID_ANY , -0x0 ); -if (umem->buf_ring ==NULL ) { -AF_XDP_LOG (ERR ,"Failed to create rte_ring\n" ); + umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_F_PAGE_ALIGN , +SOCKET_ID_ANY ); +if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); goto err; } + base_addr = (void *)get_base_addr (umem->mb_pool); -for (i =0 ; i <ETH_AF_XDP_NUM_BUFFERS ; i++) -rte_ring_enqueue (umem->buf_ring, - (void *)(i *ETH_AF_XDP_FRAME_SIZE + -ETH_AF_XDP_DATA_HEADROOM )); - -if (posix_memalign (&bufs,getpagesize (), -ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE )) { -AF_XDP_LOG (ERR ,"Failed to allocate memory pool.\n" ); - goto err; - } - ret =xsk_umem__create (&umem->umem, bufs, + ret =xsk_umem__create (&umem->umem, base_addr,ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE , &umem->fq, &umem->cq, &usr_config);
@@ -499,7 +527,7 @@ static struct xsk_umem_info *xdp_umem_configure(void)AF_XDP_LOG (ERR ,"Failed to create umem" ); goto err; } - umem->buffer = bufs; + umem->buffer = base_addr;return umem;
@@ -903,10 +931,9 @@ rte_pmd_af_xdp_remove(struct rte_vdev_device *dev) internals = eth_dev->data->dev_private; -rte_ring_free (internals->umem->buf_ring); -rte_free (internals->umem->buffer);rte_free (internals->umem); +rte_mempool_free (internals->umem->mb_pool);rte_eth_dev_release_port (eth_dev);
Signature · 1 line
2.17.1
PATCH v5 5/5 net/af_xdp: enable zero copy
In reply to Xiaolong YeTry to check if external mempool (from rx_queue_setup) is fit for af_xdp, if it is, it will be registered to af_xdp socket directly and there will be no packet data copy on Rx and Tx.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 130 ++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 34 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +96 -34
@@ -67,6 +67,7 @@ struct xsk_umem_info {struct xsk_umem *umem;struct rte_mempool *mb_pool;void *buffer; +uint8_t zc; };struct rx_stats {
@@ -85,6 +86,7 @@ struct pkt_rx_queue {struct pkt_tx_queue *pair;uint16_t queue_idx; +uint8_t zc; };struct tx_stats {
@@ -202,7 +204,9 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)if (xsk_prod_nb_free (fq, free_thresh) >= free_thresh) (void )reserve_fill_queue (umem,ETH_AF_XDP_RX_BATCH_SIZE ); -if (unlikely (rte_pktmbuf_alloc_bulk (rxq->mb_pool, mbufs, rcvd) !=0 )) +if (!rxq->zc && +unlikely (rte_pktmbuf_alloc_bulk (rxq->mb_pool, + mbufs, rcvd) !=0 ))return 0 ;for (i =0 ; i < rcvd; i++) {
@@ -216,13 +220,23 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) len = desc->len; pkt =xsk_umem__get_data (rxq->umem->buffer, addr); - rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), pkt, len); -rte_pktmbuf_pkt_len (mbufs[i]) = len; -rte_pktmbuf_data_len (mbufs[i]) = len; - rx_bytes += len; - bufs[count++] = mbufs[i]; - -rte_pktmbuf_free (addr_to_mbuf (umem, addr)); +if (rxq->zc) { +struct rte_mbuf *mbuf; + mbuf =addr_to_mbuf (rxq->umem, addr); +rte_pktmbuf_pkt_len (mbuf) = len; +rte_pktmbuf_data_len (mbuf) = len; + rx_bytes += len; + bufs[count++] = mbuf; + }else { + rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), + pkt, len); +rte_pktmbuf_pkt_len (mbufs[i]) = len; +rte_pktmbuf_data_len (mbufs[i]) = len; + rx_bytes += len; + bufs[count++] = mbufs[i]; + +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); + } }xsk_ring_cons__release (rx, rcvd);
@@ -295,22 +309,29 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) -ETH_AF_XDP_DATA_HEADROOM ; desc =xsk_ring_prod__tx_desc (&txq->tx, idx_tx + i); mbuf = bufs[i]; -if (mbuf->pkt_len <= buf_len) { - mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); -if (unlikely (mbuf_to_tx ==NULL )) { -rte_pktmbuf_free (mbuf); -continue ; - } - desc->addr =mbuf_to_addr (umem, mbuf_to_tx); +if (txq->pair->zc && mbuf->pool == umem->mb_pool) { + desc->addr =mbuf_to_addr (umem, mbuf); desc->len = mbuf->pkt_len; - pkt =xsk_umem__get_data (umem->buffer, - desc->addr); - rte_memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), - desc->len); valid++; tx_bytes += mbuf->pkt_len; + }else { +if (mbuf->pkt_len <= buf_len) { + mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf_to_tx ==NULL )) { +rte_pktmbuf_free (mbuf); +continue ; + } + desc->addr =mbuf_to_addr (umem, mbuf_to_tx); + desc->len = mbuf->pkt_len; + pkt =xsk_umem__get_data (umem->buffer, + desc->addr); + memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), + desc->len); + valid++; + tx_bytes += mbuf->pkt_len; + } +rte_pktmbuf_free (mbuf); } -rte_pktmbuf_free (mbuf); }xsk_ring_prod__submit (&txq->tx, nb_pkts);
@@ -488,7 +509,7 @@ static inline uint64_t get_len(struct rte_mempool *mp)return (uint64_t )(memhdr->len); } -static struct xsk_umem_info *xdp_umem_configure (void ) +static struct xsk_umem_info *xdp_umem_configure (struct rte_mempool *mb_pool) {struct xsk_umem_info *umem;struct xsk_umem_config usr_config = {
@@ -505,16 +526,23 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , -ETH_AF_XDP_NUM_BUFFERS , -250 ,0 , -ETH_AF_XDP_FRAME_SIZE - -ETH_AF_XDP_MBUF_OVERHEAD , -MEMPOOL_F_NO_SPREAD |MEMPOOL_F_PAGE_ALIGN , -SOCKET_ID_ANY ); -if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { -AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); - goto err; +if (!mb_pool) { + umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_F_PAGE_ALIGN , +SOCKET_ID_ANY ); + +if (umem->mb_pool ==NULL || + umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); + goto err; + } + }else { + umem->mb_pool = mb_pool; + umem->zc =1 ; } base_addr = (void *)get_base_addr (umem->mb_pool);
@@ -536,16 +564,43 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } +static uint8_t +check_mempool_zc (struct rte_mempool *mp) +{ +RTE_ASSERT (mp); + +/* must continues */ +if (mp->nb_mem_chunks >1 ) +return 0 ; + +/* check header size */ +if (mp->header_size !=RTE_CACHE_LINE_SIZE ) +return 0 ; + +/* check base address */ +if ((uint64_t )get_base_addr (mp) %getpagesize () !=0 ) +return 0 ; + +/* check chunk size */ +if ((mp->elt_size + mp->header_size + mp->trailer_size) % +ETH_AF_XDP_FRAME_SIZE !=0 ) +return 0 ; + +return 1 ; +} +static int xsk_configure (struct pmd_internals *internals,struct pkt_rx_queue *rxq, -int ring_size) +int ring_size,struct rte_mempool *mb_pool) {struct xsk_socket_config cfg;struct pkt_tx_queue *txq = rxq->pair; +struct rte_mempool *mp;int ret =0 ;int reserve_size; - rxq->umem =xdp_umem_configure (); + mp =check_mempool_zc (mb_pool) ? mb_pool :NULL ; + rxq->umem =xdp_umem_configure (mp);if (rxq->umem ==NULL )return -ENOMEM ;
@@ -622,7 +677,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, rxq->mb_pool = mb_pool; -if (xsk_configure (internals, rxq, nb_rx_desc)) { +if (xsk_configure (internals, rxq, nb_rx_desc, mb_pool)) {AF_XDP_LOG (ERR ,"Failed to configure xdp socket\n" ); ret = -EINVAL ; goto err;
@@ -630,6 +685,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, internals->umem = rxq->umem; +if (mb_pool == internals->umem->mb_pool) + rxq->zc = internals->umem->zc; + +if (rxq->zc) +AF_XDP_LOG (INFO , +"zero copy enabled on rx queue %d\n" , rx_queue_id); + dev->data->rx_queues[rx_queue_id] = rxq;return 0 ;
Signature · 1 line
2.17.1
v6 cover Introduce AF_XDP PMD
In reply to Xiaolong YeOverview
========
This patchset adds a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux, see below links [1] [2] for details of AF_XDP introduction:
AF_XDP roadmap
==============
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.
Change logs
===========
V6:
- remove the newline in AF_XDP_LOG definition to avoid double new lines issue.
- rename MEMPOOL_F_PAGE_ALIGN to MEMPOOL_CHUNK_F_PAGE_ALIGN.
V5:
- disable AF_XDP pmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of Maxime
V4:
- change vdev name to net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by Stephen
V3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.
V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactor rte_mbuf.c to avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.
changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the AP_XDP uapi. After the rework, it helps to reduce 300+ lines of code.
- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls xsk_socket__create. userspace application only needs to handle the cleanup.
How to try
==========
1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support -->
Networking options -->
[ * ] XDP sockets
2. build libbpf in tools/lib/bpf, and copy the libbpf.a and libbpf.so to /usr/lib64
cd tools/lib/bpf
make
3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable AF_XDP pmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
5. start testpmd
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1
in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to af_xdp socket.
Xiaolong Ye (5):
net/af_xdp: introduce AF XDP PMD driver lib/mbuf: introduce helper to create mempool with flags lib/mempool: allow page size aligned mempool net/af_xdp: use mbuf mempool for buffer management net/af_xdp: enable zero copy
MAINTAINERS | 6 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 45 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 1020 +++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + lib/librte_mbuf/rte_mbuf.c | 29 +- lib/librte_mbuf/rte_mbuf.h | 45 + lib/librte_mbuf/rte_mbuf_version.map | 1 + lib/librte_mempool/rte_mempool.c | 3 + lib/librte_mempool/rte_mempool.h | 1 + mk/rte.app.mk | 1 + 18 files changed, 1228 insertions(+), 5 deletions(-) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 1 line
2.17.1
PATCH v6 1/5 net/af_xdp: introduce AF XDP PMD driver
Add a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 6 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 45 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 931 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1065 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +6 -0
@@ -468,6 +468,12 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/features/af_xdp.rst + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -416,6 +416,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +45 -0
45 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -65,6 +65,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +32 -0
@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpf + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/meson.build new file +21 -0
@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif + +bpf_dep = dependency('libbpf', required: false) +if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false) + if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
drivers/net/af_xdp/rte_eth_af_xdp.c new file +931 -0
931 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v6 1/5] net/af_xdp: introduce AF XDP PMD driver
doc/guides/nics/af_xdp.rst line 20
Quoted 6 lines · On Tue, 26 Mar 2019 20:20:25 +0800 Xiaolong Ye <[email protected]> wrote:
doc/guides/nics/af_xdp.rst new file +6
-0+This Linux-specific PMD driver creates the AF_XDP socket and binds it to a +specific netdev queue, it allows a DPDK application to send and receive raw +packets through the socket which would bypass the kernel network stack. +Current implementation only supports single queue, multi-queues feature will +be added later. +
It might be worth mentioning that MTU in XDP is limited because the kernel doesn't allow XDP with segmented packets.
Re: [PATCH v6 1/5] net/af_xdp: introduce AF XDP PMD driver
Quoted 12 lines · Stephen Hemminger
doc/guides/nics/af_xdp.rst line 20
Quoted 6 lines · On Tue, 26 Mar 2019 20:20:25 +0800 Xiaolong Ye <[email protected]> wrote:
doc/guides/nics/af_xdp.rst new file +6
-0+This Linux-specific PMD driver creates the AF_XDP socket and binds it to a +specific netdev queue, it allows a DPDK application to send and receive raw +packets through the socket which would bypass the kernel network stack. +Current implementation only supports single queue, multi-queues feature will +be added later. +It might be worth mentioning that MTU in XDP is limited because the kernel doesn't allow XDP with segmented packets.
Ok, will add it in next version.
Thanks,
Xiaolong
PATCH v6 2/5 lib/mbuf: introduce helper to create mempool with flags
In reply to Xiaolong YeThis allows applications to create mbuf mempool with specific flags such as MEMPOOL_F_NO_SPREAD if they want fixed size memory objects.
--- lib/librte_mbuf/rte_mbuf.c | 29 ++++++++++++++---- lib/librte_mbuf/rte_mbuf.h | 45 ++++++++++++++++++++++++++++ lib/librte_mbuf/rte_mbuf_version.map | 1 + 3 files changed, 70 insertions(+), 5 deletions(-)
lib/librte_mbuf/rte_mbuf.c +24 -5
@@ -106,11 +106,10 @@ rte_pktmbuf_init(struct rte_mempool *mp, m->next =NULL ; } -/* Helper to create a mbuf pool with given mempool ops name*/ -struct rte_mempool * -rte_pktmbuf_pool_create_by_ops (const char *name,unsigned int n, +static struct rte_mempool * +rte_pktmbuf_pool_create_by_ops_with_flags (const char *name,unsigned int n,unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, -int socket_id,const char *ops_name) +unsigned int flags,int socket_id,const char *ops_name) {struct rte_mempool *mp;struct rte_pktmbuf_pool_private mbp_priv;
@@ -130,7 +129,7 @@ rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n, mbp_priv.mbuf_priv_size = priv_size; mp =rte_mempool_create_empty (name, n, elt_size, cache_size, -sizeof (struct rte_pktmbuf_pool_private ), socket_id,0 ); +sizeof (struct rte_pktmbuf_pool_private ), socket_id, flags);if (mp ==NULL )return NULL ;
@@ -157,6 +156,16 @@ rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n,return mp; } +/* Helper to create a mbuf pool with given mempool ops name*/ +struct rte_mempool * +rte_pktmbuf_pool_create_by_ops (const char *name,unsigned int n, +unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, +int socket_id,const char *ops_name) +{ +return rte_pktmbuf_pool_create_by_ops_with_flags (name, n, cache_size, + priv_size, data_room_size,0 , socket_id, ops_name); +} +/* helper to create a mbuf pool */ struct rte_mempool * rte_pktmbuf_pool_create(const char *name, unsigned int n,
@@ -167,6 +176,16 @@ rte_pktmbuf_pool_create(const char *name, unsigned int n, data_room_size, socket_id, NULL); } +/* helper to create a mbuf pool with flags (e.g. NO_SPREAD) */ +struct rte_mempool * __rte_experimental +rte_pktmbuf_pool_create_with_flags (const char *name,unsigned int n, +unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, +unsigned int flags,int socket_id) +{ +return rte_pktmbuf_pool_create_by_ops_with_flags (name, n, cache_size, + priv_size, data_room_size, flags, socket_id,NULL ); +} +/* do some sanity checks on a mbuf: panic if it fails */ void rte_mbuf_sanity_check (const struct rte_mbuf *m,int is_header)
lib/librte_mbuf/rte_mbuf.h +45 -0
51 lines not on this page · raw message
lib/librte_mbuf/rte_mbuf_version.map +1 -0
@@ -50,4 +50,5 @@ EXPERIMENTAL { global: rte_mbuf_check; + rte_pktmbuf_pool_create_with_flags; } DPDK_18.08;
Signature · 1 line
2.17.1
PATCH v6 3/5 lib/mempool: allow page size aligned mempool
In reply to Xiaolong YeAllow create a mempool with page size aligned base address.
--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)
lib/librte_mempool/rte_mempool.c +3 -0
@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_CHUNK_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);
lib/librte_mempool/rte_mempool.h +1 -0
@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_CHUNK_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */ /** * @internal When debug is enabled, store some statistics.
Signature · 1 line
2.17.1
PATCH v6 4/5 net/af_xdp: use mbuf mempool for buffer management
In reply to Xiaolong YeNow, af_xdp registered memory buffer is managed by rte_mempool. mbuf allocated from rte_mempool can be converted to xdp_desc's address and vice versa.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 117 +++++++++++++++++----------- 1 file changed, 72 insertions(+), 45 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +72 -45
@@ -48,7 +48,11 @@ static int af_xdp_logtype;#define ETH_AF_XDP_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE#define ETH_AF_XDP_NUM_BUFFERS 4096 -#define ETH_AF_XDP_DATA_HEADROOM 0 +/* mempool hdrobj size (64 bytes) + sizeof(struct rte_mbuf) (128 bytes) */ +#define ETH_AF_XDP_MBUF_OVERHEAD 192 +/* data start from offset 320 (192 + 128) bytes */ +#define ETH_AF_XDP_DATA_HEADROOM \ + (ETH_AF_XDP_MBUF_OVERHEAD + RTE_PKTMBUF_HEADROOM)#define ETH_AF_XDP_DFLT_NUM_DESCS XSK_RING_CONS__DEFAULT_NUM_DESCS#define ETH_AF_XDP_DFLT_QUEUE_IDX 0
@@ -61,7 +65,7 @@ struct xsk_umem_info {struct xsk_ring_prod fq;struct xsk_ring_cons cq;struct xsk_umem *umem; -struct rte_ring *buf_ring; +struct rte_mempool *mb_pool;void *buffer; };
@@ -123,10 +127,30 @@ static struct rte_eth_link pmd_link = { .link_autoneg = ETH_LINK_AUTONEG }; +static inline struct rte_mbuf * +addr_to_mbuf (struct xsk_umem_info *umem,uint64_t addr) +{ +uint64_t offset = (addr /ETH_AF_XDP_FRAME_SIZE * +ETH_AF_XDP_FRAME_SIZE ); +struct rte_mbuf *mbuf = (struct rte_mbuf *)((uint64_t )umem->buffer + + offset +ETH_AF_XDP_MBUF_OVERHEAD - +sizeof (struct rte_mbuf )); + mbuf->data_off = addr - offset -ETH_AF_XDP_MBUF_OVERHEAD ; +return mbuf; +} + +static inline uint64_t +mbuf_to_addr (struct xsk_umem_info *umem,struct rte_mbuf *mbuf) +{ +return (uint64_t )mbuf->buf_addr + mbuf->data_off - + (uint64_t )umem->buffer; +} +static inline int reserve_fill_queue (struct xsk_umem_info *umem,int reserve_size) {struct xsk_ring_prod *fq = &umem->fq; +struct rte_mbuf *mbuf;uint32_t idx;int i, ret;
@@ -138,13 +162,15 @@ reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)for (i =0 ; i < reserve_size; i++) {__u64 *fq_addr; -void *addr =NULL ; -if (rte_ring_dequeue (umem->buf_ring, &addr)) { +uint64_t addr; + mbuf =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf ==NULL )) { i--;break ; } + addr =mbuf_to_addr (umem, mbuf); fq_addr =xsk_ring_prod__fill_addr (fq, idx++); - *fq_addr = (uint64_t )addr; + *fq_addr = addr; }xsk_ring_prod__submit (fq, i);
@@ -196,7 +222,7 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) rx_bytes += len; bufs[count++] = mbufs[i]; -rte_ring_enqueue (umem->buf_ring, (void *)addr); +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); }xsk_ring_cons__release (rx, rcvd);
@@ -219,7 +245,7 @@ static void pull_umem_cq(struct xsk_umem_info *umem, int size)for (i =0 ; i < n; i++) {uint64_t addr; addr = *xsk_ring_cons__comp_addr (cq, idx_cq++); -rte_ring_enqueue (umem->buf_ring, (void *)addr); +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); }xsk_ring_cons__release (cq, n);
@@ -248,7 +274,7 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)struct pkt_tx_queue *txq = queue;struct xsk_umem_info *umem = txq->pair->umem;struct rte_mbuf *mbuf; -void *addrs[ETH_AF_XDP_TX_BATCH_SIZE ]; +struct rte_mbuf *mbuf_to_tx;unsigned long tx_bytes =0 ;int i, valid =0 ;uint32_t idx_tx;
@@ -257,11 +283,6 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)pull_umem_cq (umem, nb_pkts); - nb_pkts =rte_ring_dequeue_bulk (umem->buf_ring, addrs, - nb_pkts,NULL ); -if (nb_pkts ==0 ) -return 0 ; -if (xsk_ring_prod__reserve (&txq->tx, nb_pkts, &idx_tx) != nb_pkts) {kick_tx (txq);return 0 ;
@@ -275,7 +296,12 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) desc =xsk_ring_prod__tx_desc (&txq->tx, idx_tx + i); mbuf = bufs[i];if (mbuf->pkt_len <= buf_len) { - desc->addr = (uint64_t )addrs[valid]; + mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf_to_tx ==NULL )) { +rte_pktmbuf_free (mbuf); +continue ; + } + desc->addr =mbuf_to_addr (umem, mbuf_to_tx); desc->len = mbuf->pkt_len; pkt =xsk_umem__get_data (umem->buffer, desc->addr);
@@ -291,10 +317,6 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)kick_tx (txq); -if (valid < nb_pkts) -rte_ring_enqueue_bulk (umem->buf_ring, &addrs[valid], - nb_pkts - valid,NULL ); - txq->stats.err_pkts += nb_pkts - valid; txq->stats.tx_pkts += valid; txq->stats.tx_bytes += tx_bytes;
@@ -443,16 +465,29 @@ eth_link_update(struct rte_eth_dev *dev __rte_unused,static void xdp_umem_destroy (struct xsk_umem_info *umem) { -free (umem->buffer); - umem->buffer =NULL ; - -rte_ring_free (umem->buf_ring); - umem->buf_ring =NULL ; +rte_mempool_free (umem->mb_pool); + umem->mb_pool =NULL ;rte_free (umem); umem =NULL ; } +static inline uint64_t get_base_addr (struct rte_mempool *mp) +{ +struct rte_mempool_memhdr *memhdr; + + memhdr =STAILQ_FIRST (&mp->mem_list); +return (uint64_t )(memhdr->addr); +} + +static inline uint64_t get_len (struct rte_mempool *mp) +{ +struct rte_mempool_memhdr *memhdr; + + memhdr =STAILQ_FIRST (&mp->mem_list); +return (uint64_t )(memhdr->len); +} +static struct xsk_umem_info *xdp_umem_configure (void ) {struct xsk_umem_info *umem;
@@ -461,9 +496,8 @@ static struct xsk_umem_info *xdp_umem_configure(void) .comp_size = ETH_AF_XDP_DFLT_NUM_DESCS, .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM }; -void *bufs =NULL ; +void *base_addr =NULL ;int ret; -uint64_t i; umem =rte_zmalloc_socket ("umem" ,sizeof (*umem),0 ,rte_socket_id ());if (umem ==NULL ) {
@@ -471,26 +505,20 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->buf_ring =rte_ring_create ("af_xdp_ring" , -ETH_AF_XDP_NUM_BUFFERS , -SOCKET_ID_ANY , -0x0 ); -if (umem->buf_ring ==NULL ) { -AF_XDP_LOG (ERR ,"Failed to create rte_ring\n" ); + umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , +SOCKET_ID_ANY ); +if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); goto err; } + base_addr = (void *)get_base_addr (umem->mb_pool); -for (i =0 ; i <ETH_AF_XDP_NUM_BUFFERS ; i++) -rte_ring_enqueue (umem->buf_ring, - (void *)(i *ETH_AF_XDP_FRAME_SIZE + -ETH_AF_XDP_DATA_HEADROOM )); - -if (posix_memalign (&bufs,getpagesize (), -ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE )) { -AF_XDP_LOG (ERR ,"Failed to allocate memory pool.\n" ); - goto err; - } - ret =xsk_umem__create (&umem->umem, bufs, + ret =xsk_umem__create (&umem->umem, base_addr,ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE , &umem->fq, &umem->cq, &usr_config);
@@ -499,7 +527,7 @@ static struct xsk_umem_info *xdp_umem_configure(void)AF_XDP_LOG (ERR ,"Failed to create umem" ); goto err; } - umem->buffer = bufs; + umem->buffer = base_addr;return umem;
@@ -903,10 +931,9 @@ rte_pmd_af_xdp_remove(struct rte_vdev_device *dev) internals = eth_dev->data->dev_private; -rte_ring_free (internals->umem->buf_ring); -rte_free (internals->umem->buffer);rte_free (internals->umem); +rte_mempool_free (internals->umem->mb_pool);rte_eth_dev_release_port (eth_dev);
Signature · 1 line
2.17.1
Re: [PATCH v6 4/5] net/af_xdp: use mbuf mempool for buffer management
Hi Xiaolong,
Quoted 14 lines · Xiaolong Ye
Now,
af_xdpregistered memory buffer is managed byrte_mempool. mbuf allocated fromrte_mempoolcan be converted to xdp_desc's address and vice versa.Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 117 +++++++++++++++++----------- 1 file changed, 72 insertions(+), 45 deletions(-)drivers/net/af_xdp/rte_eth_af_xdp.c +0
-0
drivers/net/af_xdp/rte_eth_af_xdp.c static int af_xdp_logtype; · line 55
Quoted 9 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +5
-1@@ -48,7 +48,11 @@ static int af_xdp_logtype;#define ETH_AF_XDP_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE#define ETH_AF_XDP_NUM_BUFFERS 4096 -#define ETH_AF_XDP_DATA_HEADROOM 0 +/* mempool hdrobj size (64 bytes) + sizeof(struct rte_mbuf) (128 bytes) */ +#define ETH_AF_XDP_MBUF_OVERHEAD 192 +/* data start from offset 320 (192 + 128) bytes */ +#define ETH_AF_XDP_DATA_HEADROOM \ + (ETH_AF_XDP_MBUF_OVERHEAD + RTE_PKTMBUF_HEADROOM)
Having these constants looks quite dangerous too me. It imposes the size of the mbuf, and the mempool header size. It would at least require compilation checks.
[...]
drivers/net/af_xdp/rte_eth_af_xdp.c static struct xsk_umem_info *xdp_umem_configure(void) · line 519
Quoted 12 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +10
-0+ umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , +SOCKET_ID_ANY ); +if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); goto err; } + base_addr = (void *)get_base_addr (umem->mb_pool);
Creating a mempool in the pmd like this does not look good to me for several reasons:
- the user application creates its mempool with a specific private area in its mbufs. Here there is no private area, so it will break applications doing this.
- in patch 3 (mempool), you ensure that the chunk starts at a page-aligned address, and you expect that given the other flags and the constants at the top of the file, the data will be aligned. In my opinion it is not ideal.
- the user application may create a large number of mbufs, for instance if the application manages large reassembly queues, or tcp sockets. Here the driver limits the number of mbufs to 4k per rx queue.
- the socket_id is any, so it won't be efficient on numa architectures.
May I suggest another idea?
Allocate the xsk_umem almost like in patch 1, but using rte_memzone allocation instead of posix_memalign() (and it will be faster, because it will use hugepages). And do not allocate any mempool in the driver.
When you receive a packet in the xsk_umem, allocate a new mbuf from the standard pool. Then, use rte_pktmbuf_attach_extbuf() to attach the xsk memory to the mbuf. You will have to register a callback to return the xsk memory when the mbuf is transmitted or freed.
This is, by the way, something I don't understand in your current
implementation: what happens if a mbuf is received in the af_xdp driver, and freed by the application? How does the xsk buffer is returned?
Using rte_pktmbuf_attach_extbuf() would remove changes in mbuf and mempool, at the price of (maybe) decreasing the performance. But I think there are some places where it can be optimized.
I understand my feedback comes late -- as usual :( -- but if you are in a hurry for RC1, maybe we can consider to put the 1st patch only, and add the zero-copy mode in a second patch later. What do you think?
Regards,
Olivier
Re: [PATCH v6 4/5] net/af_xdp: use mbuf mempool for buffer management
Hi, Olivier
Thanks for the comments.
Quoted 51 lines · Olivier Matz
Hi Xiaolong,
Quoted 14 lines · Xiaolong Ye
Now,
af_xdpregistered memory buffer is managed byrte_mempool. mbuf allocated fromrte_mempoolcan be converted to xdp_desc's address and vice versa.Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 117 +++++++++++++++++----------- 1 file changed, 72 insertions(+), 45 deletions(-)drivers/net/af_xdp/rte_eth_af_xdp.c +0
-0drivers/net/af_xdp/rte_eth_af_xdp.c static int af_xdp_logtype; · line 55
Quoted 9 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +5
-1@@ -48,7 +48,11 @@ static int af_xdp_logtype;#define ETH_AF_XDP_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE#define ETH_AF_XDP_NUM_BUFFERS 4096 -#define ETH_AF_XDP_DATA_HEADROOM 0 +/* mempool hdrobj size (64 bytes) + sizeof(struct rte_mbuf) (128 bytes) */ +#define ETH_AF_XDP_MBUF_OVERHEAD 192 +/* data start from offset 320 (192 + 128) bytes */ +#define ETH_AF_XDP_DATA_HEADROOM \ + (ETH_AF_XDP_MBUF_OVERHEAD + RTE_PKTMBUF_HEADROOM)Having these constants looks quite dangerous too me. It imposes the size of the mbuf, and the mempool header size. It would at least require compilation checks.
[...]
drivers/net/af_xdp/rte_eth_af_xdp.c static struct xsk_umem_info *xdp_umem_configure(void) · line 519
Quoted 12 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +10
-0+ umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , +SOCKET_ID_ANY ); +if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); goto err; } + base_addr = (void *)get_base_addr (umem->mb_pool);Creating a mempool in the pmd like this does not look good to me for several reasons:
- the user application creates its mempool with a specific private area in its mbufs. Here there is no private area, so it will break applications doing this.
Quoted 8 lines
- in patch 3 (mempool), you ensure that the chunk starts at a page-aligned address, and you expect that given the other flags and the constants at the top of the file, the data will be aligned. In my opinion it is not ideal.
- the user application may create a large number of mbufs, for instance if the application manages large reassembly queues, or tcp sockets. Here the driver limits the number of mbufs to 4k per rx queue.
- thesocket_idis any, so it won't be efficient on numa architectures.
Our mbuf/mempool change regarding to zero copy does have limitations.
Quoted 7 lines
May I suggest another idea?
Allocate the
xsk_umemalmost like in patch 1, but usingrte_memzoneallocation instead ofposix_memalign()(and it will be faster, because it will use hugepages). And do not allocate any mempool in the driver.
rte_memzone_reserve_aligned is better than posix_memalign, I'll use it in my first patch.
Quoted 4 lines
When you receive a packet in the
xsk_umem, allocate a new mbuf from the standard pool. Then, userte_pktmbuf_attach_extbuf()to attach the xsk memory to the mbuf. You will have to register a callback to return the xsk memory when the mbuf is transmitted or freed.
I'll try to investigate how to implement it.
Quoted 4 lines
This is, by the way, something I don't understand in your current
implementation: what happens if a mbuf is received in theaf_xdpdriver, and freed by the application? How does the xsk buffer is returned?
It is coordinated by the fill ring. The fill ring is used by the application ( user space) to send down addr for the kernel to fill in with Rx packet data. So for the free side, we just return it to the mempool, and each time in rx_pkt_burst, we would allocate new mbufs and submit corresponding addrs to fill ring, that's how we return the xsk buffer to kernel.
Quoted 6 lines
Using
rte_pktmbuf_attach_extbuf()would remove changes in mbuf and mempool, at the price of (maybe) decreasing the performance. But I think there are some places where it can be optimized.I understand my feedback comes late -- as usual :( -- but if you are in
Sorry for not Cc you in my patch set.
Quoted 2 lines
a hurry for RC1, maybe we can consider to put the 1st patch only, and add the zero-copy mode in a second patch later. What do you think?
Sounds a sensible plan, I'll try to exteranl mbuf buffer scheme first.
Thanks,
Xiaolong
Quoted 5 lines
Regards,
Olivier
Re: [PATCH v6 4/5] net/af_xdp: use mbuf mempool for buffer management
Quoted 88 lines
-----Original Message-----
From: Ye, Xiaolong
Sent: Sunday, March 31, 2019 8:38 PM
To: Olivier Matz <[email protected]>
Cc: [email protected]; David Marchand <[email protected]>; Andrew Rybchenko <[email protected]>; Zhang, Qi Z <[email protected]>; Karlsson, Magnus <[email protected]>; Topel, Bjorn <[email protected]>; Maxime Coquelin <[email protected]>; Stephen Hemminger <[email protected]>; Yigit, Ferruh <[email protected]>; Luca Boccassi <[email protected]>; Richardson, Bruce <[email protected]>; Ananyev, Konstantin <[email protected]>
Subject: Re: [dpdk-dev] [PATCH v6 4/5]net/af_xdp: use mbuf mempool for buffer managementHi, Olivier
Thanks for the comments.
Quoted 13 lines · Olivier Matz
Hi Xiaolong,
Quoted 10 lines · Xiaolong Ye
Now,
af_xdpregistered memory buffer is managed byrte_mempool. mbuf allocated fromrte_mempoolcan be converted to xdp_desc's address and vice versa.Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 117 +++++++++++++++++----------- 1 file changed, 72 insertions(+), 45 deletions(-)Quoted 8 lines
drivers/net/af_xdp/rte_eth_af_xdp.c static int af_xdp_logtype; · line 49
Quoted 8 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +0
-0@@ -48,7 +48,11 @@ static int af_xdp_logtype;#define ETH_AF_XDP_FRAME_SIZE
XSK_UMEM__DEFAULT_FRAME_SIZEQuoted 12 lines
drivers/net/af_xdp/rte_eth_af_xdp.c static int af_xdp_logtype; · line 55
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +5
-1#define ETH_AF_XDP_NUM_BUFFERS 4096 -#define ETH_AF_XDP_DATA_HEADROOM 0 +/* mempool hdrobj size (64 bytes) + sizeof(struct rte_mbuf) (128 bytes) */ +#define ETH_AF_XDP_MBUF_OVERHEAD 192 +/* data start from offset 320 (192 + 128) bytes */ +#define ETH_AF_XDP_DATA_HEADROOM \ + (ETH_AF_XDP_MBUF_OVERHEAD + RTE_PKTMBUF_HEADROOM)Having these constants looks quite dangerous too me. It imposes the size of the mbuf, and the mempool header size. It would at least require compilation checks.
Quoted 3 lines
[...]
drivers/net/af_xdp/rte_eth_af_xdp.c
Quoted 1 line
drivers/net/af_xdp/rte_eth_af_xdp.c +1
-0+ umem->mb_pool =rte_pktmbuf_pool_create_with_flags("af_xdp_mempool",
Quoted 5 lines
drivers/net/af_xdp/rte_eth_af_xdp.c static struct xsk_umem_info *xdp_umem_configure(void)
Quoted 5 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +5
-0+ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , + MEMPOOL_F_NO_SPREAD |
MEMPOOL_CHUNK_F_PAGE_ALIGN,Quoted 2 lines
drivers/net/af_xdp/rte_eth_af_xdp.c
Quoted 2 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +2
-0+ SOCKET_ID_ANY); +if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ){
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c static struct xsk_umem_info *xdp_umem_configure(void) · line 519
Quoted 4 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +2
-0+AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); goto err; } + base_addr = (void *)get_base_addr (umem->mb_pool);Creating a mempool in the pmd like this does not look good to me for several reasons:
- the user application creates its mempool with a specific private area in its mbufs. Here there is no private area, so it will break applications doing this.Quoted 8 lines
- in patch 3 (mempool), you ensure that the chunk starts at a page-aligned address, and you expect that given the other flags and the constants at the top of the file, the data will be aligned. In my opinion it is not ideal.
- the user application may create a large number of mbufs, for instance if the application manages large reassembly queues, or tcp sockets. Here the driver limits the number of mbufs to 4k per rx queue.
- thesocket_idis any, so it won't be efficient on numa architectures.
Quoted 1 line
Our mbuf/mempool change regarding to zero copy does have limitations.
Just want to clarify, the above code is only reached for non-zero copy case.
here we create a private memory pool be used to manage AF_XDP umem, it's not the Rx queues' s memory pool itself. so I don't think there is concern on the private area and 4k per rx queue for above code.
Quoted 53 lines
Quoted 8 lines
May I suggest another idea?
Allocate the
xsk_umemalmost like in patch 1, but usingrte_memzoneallocation instead ofposix_memalign()(and it will be faster, because it will use hugepages). And do not allocate any mempool in the driver.
rte_memzone_reserve_alignedis better thanposix_memalign, I'll use it in my first patch.Quoted 4 lines
When you receive a packet in the
xsk_umem, allocate a new mbuf from the standard pool. Then, userte_pktmbuf_attach_extbuf()to attach the xsk memory to the mbuf. You will have to register a callback to return the xsk memory when the mbuf is transmitted or freed.I'll try to investigate how to implement it.
Quoted 4 lines
This is, by the way, something I don't understand in your current
implementation: what happens if a mbuf is received in theaf_xdpdriver, and freed by the application? How does the xsk buffer is returned?It is coordinated by the fill ring. The fill ring is used by the application ( user space) to send down addr for the kernel to fill in with Rx packet data.
So for the free side, we just return it to the mempool, and each time inrx_pkt_burst, we would allocate new mbufs and submit corresponding addrs to fill ring, that's how we return the xsk buffer to kernel.Quoted 6 lines
Using
rte_pktmbuf_attach_extbuf()would remove changes in mbuf and mempool, at the price of (maybe) decreasing the performance. But I think there are some places where it can be optimized.I understand my feedback comes late -- as usual :( -- but if you are in
Sorry for not Cc you in my patch set.
Quoted 2 lines
a hurry for RC1, maybe we can consider to put the 1st patch only, and add the zero-copy mode in a second patch later. What do you think?
Sounds a sensible plan, I'll try to exteranl mbuf buffer scheme first.
Thanks,
XiaolongQuoted 5 lines
Regards,
Olivier
PATCH v6 5/5 net/af_xdp: enable zero copy
In reply to Xiaolong YeTry to check if external mempool (from rx_queue_setup) is fit for af_xdp, if it is, it will be registered to af_xdp socket directly and there will be no packet data copy on Rx and Tx.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 130 ++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 34 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +96 -34
@@ -67,6 +67,7 @@ struct xsk_umem_info {struct xsk_umem *umem;struct rte_mempool *mb_pool;void *buffer; +uint8_t zc; };struct rx_stats {
@@ -85,6 +86,7 @@ struct pkt_rx_queue {struct pkt_tx_queue *pair;uint16_t queue_idx; +uint8_t zc; };struct tx_stats {
@@ -202,7 +204,9 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)if (xsk_prod_nb_free (fq, free_thresh) >= free_thresh) (void )reserve_fill_queue (umem,ETH_AF_XDP_RX_BATCH_SIZE ); -if (unlikely (rte_pktmbuf_alloc_bulk (rxq->mb_pool, mbufs, rcvd) !=0 )) +if (!rxq->zc && +unlikely (rte_pktmbuf_alloc_bulk (rxq->mb_pool, + mbufs, rcvd) !=0 ))return 0 ;for (i =0 ; i < rcvd; i++) {
@@ -216,13 +220,23 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) len = desc->len; pkt =xsk_umem__get_data (rxq->umem->buffer, addr); - rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), pkt, len); -rte_pktmbuf_pkt_len (mbufs[i]) = len; -rte_pktmbuf_data_len (mbufs[i]) = len; - rx_bytes += len; - bufs[count++] = mbufs[i]; - -rte_pktmbuf_free (addr_to_mbuf (umem, addr)); +if (rxq->zc) { +struct rte_mbuf *mbuf; + mbuf =addr_to_mbuf (rxq->umem, addr); +rte_pktmbuf_pkt_len (mbuf) = len; +rte_pktmbuf_data_len (mbuf) = len; + rx_bytes += len; + bufs[count++] = mbuf; + }else { + rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), + pkt, len); +rte_pktmbuf_pkt_len (mbufs[i]) = len; +rte_pktmbuf_data_len (mbufs[i]) = len; + rx_bytes += len; + bufs[count++] = mbufs[i]; + +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); + } }xsk_ring_cons__release (rx, rcvd);
@@ -295,22 +309,29 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) -ETH_AF_XDP_DATA_HEADROOM ; desc =xsk_ring_prod__tx_desc (&txq->tx, idx_tx + i); mbuf = bufs[i]; -if (mbuf->pkt_len <= buf_len) { - mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); -if (unlikely (mbuf_to_tx ==NULL )) { -rte_pktmbuf_free (mbuf); -continue ; - } - desc->addr =mbuf_to_addr (umem, mbuf_to_tx); +if (txq->pair->zc && mbuf->pool == umem->mb_pool) { + desc->addr =mbuf_to_addr (umem, mbuf); desc->len = mbuf->pkt_len; - pkt =xsk_umem__get_data (umem->buffer, - desc->addr); - rte_memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), - desc->len); valid++; tx_bytes += mbuf->pkt_len; + }else { +if (mbuf->pkt_len <= buf_len) { + mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf_to_tx ==NULL )) { +rte_pktmbuf_free (mbuf); +continue ; + } + desc->addr =mbuf_to_addr (umem, mbuf_to_tx); + desc->len = mbuf->pkt_len; + pkt =xsk_umem__get_data (umem->buffer, + desc->addr); + memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), + desc->len); + valid++; + tx_bytes += mbuf->pkt_len; + } +rte_pktmbuf_free (mbuf); } -rte_pktmbuf_free (mbuf); }xsk_ring_prod__submit (&txq->tx, nb_pkts);
@@ -488,7 +509,7 @@ static inline uint64_t get_len(struct rte_mempool *mp)return (uint64_t )(memhdr->len); } -static struct xsk_umem_info *xdp_umem_configure (void ) +static struct xsk_umem_info *xdp_umem_configure (struct rte_mempool *mb_pool) {struct xsk_umem_info *umem;struct xsk_umem_config usr_config = {
@@ -505,16 +526,23 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , -ETH_AF_XDP_NUM_BUFFERS , -250 ,0 , -ETH_AF_XDP_FRAME_SIZE - -ETH_AF_XDP_MBUF_OVERHEAD , -MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , -SOCKET_ID_ANY ); -if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { -AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); - goto err; +if (!mb_pool) { + umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , +SOCKET_ID_ANY ); + +if (umem->mb_pool ==NULL || + umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); + goto err; + } + }else { + umem->mb_pool = mb_pool; + umem->zc =1 ; } base_addr = (void *)get_base_addr (umem->mb_pool);
@@ -536,16 +564,43 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } +static uint8_t +check_mempool_zc (struct rte_mempool *mp) +{ +RTE_ASSERT (mp); + +/* must continues */ +if (mp->nb_mem_chunks >1 ) +return 0 ; + +/* check header size */ +if (mp->header_size !=RTE_CACHE_LINE_SIZE ) +return 0 ; + +/* check base address */ +if ((uint64_t )get_base_addr (mp) %getpagesize () !=0 ) +return 0 ; + +/* check chunk size */ +if ((mp->elt_size + mp->header_size + mp->trailer_size) % +ETH_AF_XDP_FRAME_SIZE !=0 ) +return 0 ; + +return 1 ; +} +static int xsk_configure (struct pmd_internals *internals,struct pkt_rx_queue *rxq, -int ring_size) +int ring_size,struct rte_mempool *mb_pool) {struct xsk_socket_config cfg;struct pkt_tx_queue *txq = rxq->pair; +struct rte_mempool *mp;int ret =0 ;int reserve_size; - rxq->umem =xdp_umem_configure (); + mp =check_mempool_zc (mb_pool) ? mb_pool :NULL ; + rxq->umem =xdp_umem_configure (mp);if (rxq->umem ==NULL )return -ENOMEM ;
@@ -622,7 +677,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, rxq->mb_pool = mb_pool; -if (xsk_configure (internals, rxq, nb_rx_desc)) { +if (xsk_configure (internals, rxq, nb_rx_desc, mb_pool)) {AF_XDP_LOG (ERR ,"Failed to configure xdp socket\n" ); ret = -EINVAL ; goto err;
@@ -630,6 +685,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, internals->umem = rxq->umem; +if (mb_pool == internals->umem->mb_pool) + rxq->zc = internals->umem->zc; + +if (rxq->zc) +AF_XDP_LOG (INFO , +"zero copy enabled on rx queue %d\n" , rx_queue_id); + dev->data->rx_queues[rx_queue_id] = rxq;return 0 ;
Signature · 1 line
2.17.1
v7 cover Introduce AF_XDP PMD
In reply to Xiaolong YeOverview
========
This patchset adds a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux, see below links [1] [2] for details of AF_XDP introduction:
AF_XDP roadmap
==============
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.
Change logs
===========
v7:
- mention mtu limitation in af_xdp.rst
- fix the vdev name in af_xdp.rst
V6:
- remove the newline in AF_XDP_LOG definition to avoid double new lines issue.
- rename MEMPOOL_F_PAGE_ALIGN to MEMPOOL_CHUNK_F_PAGE_ALIGN.
V5:
- disable AF_XDP pmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of Maxime
V4:
- change vdev name to net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by Stephen
V3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.
V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactor rte_mbuf.c to avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.
changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the AP_XDP uapi. After the rework, it helps to reduce 300+ lines of code.
- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls xsk_socket__create. userspace application only needs to handle the cleanup.
How to try
==========
1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support -->
Networking options -->
[ * ] XDP sockets
2. build libbpf in tools/lib/bpf, and copy the libbpf.a and libbpf.so to /usr/lib64
cd tools/lib/bpf
make
3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable AF_XDP pmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
5. start testpmd
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1
in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to af_xdp socket.
Xiaolong Ye (5):
net/af_xdp: introduce AF XDP PMD driver lib/mbuf: introduce helper to create mempool with flags lib/mempool: allow page size aligned mempool net/af_xdp: use mbuf mempool for buffer management net/af_xdp: enable zero copy
MAINTAINERS | 6 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 45 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 1020 +++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + lib/librte_mbuf/rte_mbuf.c | 29 +- lib/librte_mbuf/rte_mbuf.h | 45 + lib/librte_mbuf/rte_mbuf_version.map | 1 + lib/librte_mempool/rte_mempool.c | 3 + lib/librte_mempool/rte_mempool.h | 1 + mk/rte.app.mk | 1 + 18 files changed, 1228 insertions(+), 5 deletions(-) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 1 line
2.17.1
PATCH v7 1/5 net/af_xdp: introduce AF XDP PMD driver
Add a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 6 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 48 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 931 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1068 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +6 -0
@@ -474,6 +474,12 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/features/af_xdp.rst + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -416,6 +416,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +48 -0
48 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -65,6 +65,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +32 -0
@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpf + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/meson.build new file +21 -0
@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2018 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif + +bpf_dep = dependency('libbpf', required: false) +if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false) + if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
drivers/net/af_xdp/rte_eth_af_xdp.c new file +931 -0
931 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v7 1/5] net/af_xdp: introduce AF XDP PMD driver
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]>
Hi Xiaolong,
Mostly looks good, only there are a few comments on minor issues, can you please check them?
<...>
MAINTAINERS M: John W. Linville <[email protected]> · line 481
Quoted 9 lines
MAINTAINERS +5
-0@@ -474,6 +474,12 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/features/af_xdp.rst
Can you please add .ini file too?
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 117
Quoted 5 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +5
-0+static const char *const valid_arguments[] = { +ETH_AF_XDP_IFACE_ARG , +ETH_AF_XDP_QUEUE_IDX_ARG , +NULL +};
Minor issue, but can you please keep close the .*ARG defines and this structure, either move this up or move defines down just above this struct?
drivers/net/af_xdp/rte_eth_af_xdp.c line 124
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +7
-0+ +static struct rte_eth_link pmd_link = { + .link_speed =ETH_SPEED_NUM_10G , + .link_duplex =ETH_LINK_FULL_DUPLEX , + .link_status =ETH_LINK_DOWN , + .link_autoneg =ETH_LINK_AUTONEG +};
Can this variable be const?
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 339
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +10
-0+static void +eth_dev_info (struct rte_eth_dev *dev,struct rte_eth_dev_info *dev_info) +{ +struct pmd_internals *internals = dev->data->dev_private; + + dev_info->if_index = internals->if_index; + dev_info->max_mac_addrs =1 ; + dev_info->max_rx_pktlen =ETH_FRAME_LEN ; + dev_info->max_rx_queues =1 ; + dev_info->max_tx_queues =1 ;
What do you think documenting the only single queue supported limitation?
<...>
Review
Quoted 2 lines
(quoted diff) +2
-0+static void remove_xdp_program(struct pmd_internals *internals) +{
According coding convention it should be:
static voidremove_xdp_program(struct pmd_internals *internals) {
There is a usage of mixture, can you please update them according convention?
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 874
Quoted 4 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +4
-0+if (parse_parameters (kvlist, if_name, &xsk_queue_idx) <0 ) { +AF_XDP_LOG (ERR ,"Invalid kvargs value\n" ); +return -EINVAL ; + }
At this point we don't know if the user provided a "if_name" value, needs a way to confirm mandantory devargs provided before continue.
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 922
Quoted 2 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +2
-0+RTE_PMD_REGISTER_VDEV (net_af_xdp, pmd_af_xdp_drv); +RTE_PMD_REGISTER_PARAM_STRING(eth_af_xdp,
s/eth_af_xdp/net_af_xdp
drivers/net/af_xdp/rte_eth_af_xdp.c line 928
Quoted 6 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +6
-0+"iface=<string> " + "queue=<int> "); + +RTE_INIT (af_xdp_init_log) +{ + af_xdp_logtype =rte_log_register ("pmd.net.xdp" );
why not "pmd.net.af_xdp"?
<...>
mk/rte.app.mk _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 · line 146
Quoted 5 lines
mk/rte.app.mk +1
-0@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpf
Is "-lelf" still required?
Re: [PATCH v7 1/5] net/af_xdp: introduce AF XDP PMD driver
Quoted 10 lines · Ferruh Yigit
Review _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += · line 148
Quoted 8 lines
(quoted diff) +1
-3@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpfIs "-lelf" still required?
This was fixed upstream in the bpf tree by Björn:
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v7 1/5] net/af_xdp: introduce AF XDP PMD driver
Quoted 12 lines · Luca Boccassi
Quoted 10 lines · Ferruh Yigit
Review _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += · line 148
Quoted 8 lines
(quoted diff) +1
-3@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpfIs "-lelf" still required?
Quoted 4 lines
This was fixed upstream in the bpf tree by Björn:
ahh, but this is bpf tree. So it means this change won't be in 5.1 right? Should we add this back for 5.1?
Re: [PATCH v7 1/5] net/af_xdp: introduce AF XDP PMD driver
In reply to Ferruh YigitHi, Ferruh
Thanks for the comments.
Quoted 24 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]>Hi Xiaolong,
Mostly looks good, only there are a few comments on minor issues, can you please check them?
<...>
Quoted 4 lines
MAINTAINERS +0
-0@@ -474,6 +474,12 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini
Quoted 7 lines
MAINTAINERS M: John W. Linville <[email protected]> · line 481
Quoted 5 lines
MAINTAINERS +5
-0+Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/features/af_xdp.rstCan you please add .ini file too?
Will add.
Quoted 11 lines
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 117
Quoted 5 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +5
-0+static const char *const valid_arguments[] = { +ETH_AF_XDP_IFACE_ARG , +ETH_AF_XDP_QUEUE_IDX_ARG , +NULL +};Minor issue, but can you please keep close the .*ARG defines and this structure, either move this up or move defines down just above this struct?
Got it, I'll put them together.
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c line 124
Quoted 8 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +7
-0+ +static struct rte_eth_link pmd_link = { + .link_speed =ETH_SPEED_NUM_10G , + .link_duplex =ETH_LINK_FULL_DUPLEX , + .link_status =ETH_LINK_DOWN , + .link_autoneg =ETH_LINK_AUTONEG +};Can this variable be const?
Will do.
Quoted 15 lines
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 339
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +10
-0+static void +eth_dev_info (struct rte_eth_dev *dev,struct rte_eth_dev_info *dev_info) +{ +struct pmd_internals *internals = dev->data->dev_private; + + dev_info->if_index = internals->if_index; + dev_info->max_mac_addrs =1 ; + dev_info->max_rx_pktlen =ETH_FRAME_LEN ; + dev_info->max_rx_queues =1 ; + dev_info->max_tx_queues =1 ;What do you think documenting the only single queue supported limitation?
I've mentioned the single queue limitation in af_xdp.rst, or you mean we also need to comment it here?
Quoted 8 lines
<...>
Review
Quoted 2 lines
(quoted diff) +2
-0+static void remove_xdp_program(struct pmd_internals *internals) +{According coding convention it should be:
Quoted 7 lines
static void
remove_xdp_program(struct pmd_internals *internals){There is a usage of mixture, can you please update them according convention?
<...>
Will do.
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c line 874
Quoted 5 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +4
-0+if (parse_parameters (kvlist, if_name, &xsk_queue_idx) <0 ) { +AF_XDP_LOG (ERR ,"Invalid kvargs value\n" ); +return -EINVAL ; + }At this point we don't know if the user provided a "
if_name" value, needs a way to confirm mandantory devargs provided before continue.<...>
Got it, will do.
Quoted 5 lines
drivers/net/af_xdp/rte_eth_af_xdp.c line 922
Quoted 3 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +2
-0+RTE_PMD_REGISTER_VDEV (net_af_xdp, pmd_af_xdp_drv); +RTE_PMD_REGISTER_PARAM_STRING(eth_af_xdp,s/eth_af_xdp/net_af_xdp
Got it.
Quoted 9 lines
drivers/net/af_xdp/rte_eth_af_xdp.c line 928
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +6
-0+"iface=<string> " + "queue=<int> "); + +RTE_INIT (af_xdp_init_log) +{ + af_xdp_logtype =rte_log_register ("pmd.net.xdp" );why not "pmd.net.af_xdp"?
Will do.
Quoted 10 lines
<...>
mk/rte.app.mk _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 · line 146
Quoted 5 lines
mk/rte.app.mk +1
-0@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpfIs "-lelf" still required?
Will remove it since Bjorn hasn't sent the fix patch to kernel community.
Thanks,
Xiaolong
Re: [PATCH v7 1/5] net/af_xdp: introduce AF XDP PMD driver
Quoted 13 lines · Ye Xiaolong
Quoted 13 lines
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 339
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +10
-0+static void +eth_dev_info (struct rte_eth_dev *dev,struct rte_eth_dev_info *dev_info) +{ +struct pmd_internals *internals = dev->data->dev_private; + + dev_info->if_index = internals->if_index; + dev_info->max_mac_addrs =1 ; + dev_info->max_rx_pktlen =ETH_FRAME_LEN ; + dev_info->max_rx_queues =1 ; + dev_info->max_tx_queues =1 ;What do you think documenting the only single queue supported limitation?
Quoted 3 lines
I've mentioned the single queue limitation in
af_xdp.rst, or you mean we also need to comment it here?
I missed it in af_xdp.rst, if documented there I think it is OK.
PATCH v7 2/5 lib/mbuf: introduce helper to create mempool with flags
In reply to Xiaolong YeThis allows applications to create mbuf mempool with specific flags such as MEMPOOL_F_NO_SPREAD if they want fixed size memory objects.
--- lib/librte_mbuf/rte_mbuf.c | 29 ++++++++++++++---- lib/librte_mbuf/rte_mbuf.h | 45 ++++++++++++++++++++++++++++ lib/librte_mbuf/rte_mbuf_version.map | 1 + 3 files changed, 70 insertions(+), 5 deletions(-)
lib/librte_mbuf/rte_mbuf.c +24 -5
@@ -106,11 +106,10 @@ rte_pktmbuf_init(struct rte_mempool *mp, m->next =NULL ; } -/* Helper to create a mbuf pool with given mempool ops name*/ -struct rte_mempool * -rte_pktmbuf_pool_create_by_ops (const char *name,unsigned int n, +static struct rte_mempool * +rte_pktmbuf_pool_create_by_ops_with_flags (const char *name,unsigned int n,unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, -int socket_id,const char *ops_name) +unsigned int flags,int socket_id,const char *ops_name) {struct rte_mempool *mp;struct rte_pktmbuf_pool_private mbp_priv;
@@ -130,7 +129,7 @@ rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n, mbp_priv.mbuf_priv_size = priv_size; mp =rte_mempool_create_empty (name, n, elt_size, cache_size, -sizeof (struct rte_pktmbuf_pool_private ), socket_id,0 ); +sizeof (struct rte_pktmbuf_pool_private ), socket_id, flags);if (mp ==NULL )return NULL ;
@@ -157,6 +156,16 @@ rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n,return mp; } +/* Helper to create a mbuf pool with given mempool ops name*/ +struct rte_mempool * +rte_pktmbuf_pool_create_by_ops (const char *name,unsigned int n, +unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, +int socket_id,const char *ops_name) +{ +return rte_pktmbuf_pool_create_by_ops_with_flags (name, n, cache_size, + priv_size, data_room_size,0 , socket_id, ops_name); +} +/* helper to create a mbuf pool */ struct rte_mempool * rte_pktmbuf_pool_create(const char *name, unsigned int n,
@@ -167,6 +176,16 @@ rte_pktmbuf_pool_create(const char *name, unsigned int n, data_room_size, socket_id, NULL); } +/* helper to create a mbuf pool with flags (e.g. NO_SPREAD) */ +struct rte_mempool * __rte_experimental +rte_pktmbuf_pool_create_with_flags (const char *name,unsigned int n, +unsigned int cache_size,uint16_t priv_size,uint16_t data_room_size, +unsigned int flags,int socket_id) +{ +return rte_pktmbuf_pool_create_by_ops_with_flags (name, n, cache_size, + priv_size, data_room_size, flags, socket_id,NULL ); +} +/* do some sanity checks on a mbuf: panic if it fails */ void rte_mbuf_sanity_check (const struct rte_mbuf *m,int is_header)
lib/librte_mbuf/rte_mbuf.h +45 -0
51 lines not on this page · raw message
lib/librte_mbuf/rte_mbuf_version.map +1 -0
@@ -50,4 +50,5 @@ EXPERIMENTAL { global: rte_mbuf_check; + rte_pktmbuf_pool_create_with_flags; } DPDK_18.08;
Signature · 1 line
2.17.1
Re: [PATCH v7 2/5] lib/mbuf: introduce helper to create mempool with flags
Quoted 5 lines · Xiaolong Ye
This allows applications to create mbuf mempool with specific flags such as
MEMPOOL_F_NO_SPREADif they want fixed size memory objects.Signed-off-by Qi Zhang <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>
Hi Olivier,
Can you please check this patch?
I would like to get the PMD for rc1 but it has a dependency to this mbuf change.
Thanks,
ferruh
PATCH v7 3/5 lib/mempool: allow page size aligned mempool
In reply to Xiaolong YeAllow create a mempool with page size aligned base address.
--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)
lib/librte_mempool/rte_mempool.c +3 -0
@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_CHUNK_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);
lib/librte_mempool/rte_mempool.h +1 -0
@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_CHUNK_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */ /** * @internal When debug is enabled, store some statistics.
Signature · 1 line
2.17.1
Re: [PATCH v7 3/5] lib/mempool: allow page size aligned mempool
Quoted 4 lines · Xiaolong Ye
Allow create a mempool with page size aligned base address.
Signed-off-by Qi Zhang <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>
Hi Andrew, Olivier,
Can you please check this patch,
It is adding a new mempool flag which is dependency for the pmd.
Thanks,
ferruh
Re: [PATCH v7 3/5] lib/mempool: allow page size aligned mempool
In reply to Xiaolong YeQuoted 28 lines · Xiaolong Ye
Allow create a mempool with page size aligned base address.
Signed-off-by Qi Zhang <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)lib/librte_mempool/rte_mempool.c +3
-0@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_CHUNK_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);lib/librte_mempool/rte_mempool.h +0
-0
lib/librte_mempool/rte_mempool.h struct rte_mempool { · line 267
Quoted 4 lines
lib/librte_mempool/rte_mempool.h +1
-0@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_CHUNK_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */
Now the define name better explains what happens. I would name it MEMPOOL_F_CHUNK_PAGE_ALIGN to have MEMPOOL_F_ prefix for all flags, but it is minor. More important is what is behind and I have doubts that it is a right way to go.
I have already asked what is the final goal (but agree that question is unclear). Personally I doubt that the final goal is just having chunk page aligned.
It looks like the patch makes an assumption on how chunk is sliced into objects/elements and the property of chunk address allows to achieve some goal with elements start address. It looks very fragile and easily breakable with other flags (or no flags).
Also prefix should be just "mempool:", not "lib/mempool".
Andrew.
Re: [PATCH v7 3/5] lib/mempool: allow page size aligned mempool
Hi,
Quoted 42 lines · Andrew Rybchenko
Quoted 26 lines · Xiaolong Ye
Allow create a mempool with page size aligned base address.
Signed-off-by Qi Zhang <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- lib/librte_mempool/rte_mempool.c | 3 +++ lib/librte_mempool/rte_mempool.h | 1 + 2 files changed, 4 insertions(+)lib/librte_mempool/rte_mempool.c +3
-0@@ -543,6 +543,9 @@ rte_mempool_populate_default(struct rte_mempool *mp)if (try_contig) flags |=RTE_MEMZONE_IOVA_CONTIG ; +if (mp->flags &MEMPOOL_CHUNK_F_PAGE_ALIGN ) + align =RTE_MAX (align, (size_t )getpagesize ()); + mz =rte_memzone_reserve_aligned (mz_name, mem_size, mp->socket_id, flags, align);lib/librte_mempool/rte_mempool.h +0
-0lib/librte_mempool/rte_mempool.h struct rte_mempool { · line 267
Quoted 4 lines
lib/librte_mempool/rte_mempool.h +1
-0@@ -264,6 +264,7 @@ struct rte_mempool {#define MEMPOOL_F_POOL_CREATED 0x0010/**< Internal: pool is created. */ #define MEMPOOL_F_NO_IOVA_CONTIG 0x0020/**< Don't need IOVA contiguous objs. */ #define MEMPOOL_F_NO_PHYS_CONTIG MEMPOOL_F_NO_IOVA_CONTIG/* deprecated */ +#define MEMPOOL_CHUNK_F_PAGE_ALIGN 0x0040/**< Chunk's base address is page aligned */ Now the define name better explains what happens. I would name it
MEMPOOL_F_CHUNK_PAGE_ALIGNto haveMEMPOOL_F_prefix for all flags, but it is minor. More important is what is behind and I have doubts that it is
a right way to go.I have already asked what is the final goal (but agree that question is unclear).
Personally I doubt that the final goal is just having chunk page aligned.
Quoted 6 lines
It looks like the patch makes an assumption on how chunk is sliced into objects/elements and the property of chunk address allows to achieve some goal with elements start address. It looks very fragile and easily breakable with other flags (or no flags).
Also prefix should be just "mempool:", not "lib/mempool".
+1
I agree with Andrew. Please see my comment in patch 4.
Regards,
Olivier
PATCH v7 4/5 net/af_xdp: use mbuf mempool for buffer management
In reply to Xiaolong YeNow, af_xdp registered memory buffer is managed by rte_mempool. mbuf allocated from rte_mempool can be converted to xdp_desc's address and vice versa.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 117 +++++++++++++++++----------- 1 file changed, 72 insertions(+), 45 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +72 -45
@@ -48,7 +48,11 @@ static int af_xdp_logtype;#define ETH_AF_XDP_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE#define ETH_AF_XDP_NUM_BUFFERS 4096 -#define ETH_AF_XDP_DATA_HEADROOM 0 +/* mempool hdrobj size (64 bytes) + sizeof(struct rte_mbuf) (128 bytes) */ +#define ETH_AF_XDP_MBUF_OVERHEAD 192 +/* data start from offset 320 (192 + 128) bytes */ +#define ETH_AF_XDP_DATA_HEADROOM \ + (ETH_AF_XDP_MBUF_OVERHEAD + RTE_PKTMBUF_HEADROOM)#define ETH_AF_XDP_DFLT_NUM_DESCS XSK_RING_CONS__DEFAULT_NUM_DESCS#define ETH_AF_XDP_DFLT_QUEUE_IDX 0
@@ -61,7 +65,7 @@ struct xsk_umem_info {struct xsk_ring_prod fq;struct xsk_ring_cons cq;struct xsk_umem *umem; -struct rte_ring *buf_ring; +struct rte_mempool *mb_pool;void *buffer; };
@@ -123,10 +127,30 @@ static struct rte_eth_link pmd_link = { .link_autoneg = ETH_LINK_AUTONEG }; +static inline struct rte_mbuf * +addr_to_mbuf (struct xsk_umem_info *umem,uint64_t addr) +{ +uint64_t offset = (addr /ETH_AF_XDP_FRAME_SIZE * +ETH_AF_XDP_FRAME_SIZE ); +struct rte_mbuf *mbuf = (struct rte_mbuf *)((uint64_t )umem->buffer + + offset +ETH_AF_XDP_MBUF_OVERHEAD - +sizeof (struct rte_mbuf )); + mbuf->data_off = addr - offset -ETH_AF_XDP_MBUF_OVERHEAD ; +return mbuf; +} + +static inline uint64_t +mbuf_to_addr (struct xsk_umem_info *umem,struct rte_mbuf *mbuf) +{ +return (uint64_t )mbuf->buf_addr + mbuf->data_off - + (uint64_t )umem->buffer; +} +static inline int reserve_fill_queue (struct xsk_umem_info *umem,int reserve_size) {struct xsk_ring_prod *fq = &umem->fq; +struct rte_mbuf *mbuf;uint32_t idx;int i, ret;
@@ -138,13 +162,15 @@ reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)for (i =0 ; i < reserve_size; i++) {__u64 *fq_addr; -void *addr =NULL ; -if (rte_ring_dequeue (umem->buf_ring, &addr)) { +uint64_t addr; + mbuf =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf ==NULL )) { i--;break ; } + addr =mbuf_to_addr (umem, mbuf); fq_addr =xsk_ring_prod__fill_addr (fq, idx++); - *fq_addr = (uint64_t )addr; + *fq_addr = addr; }xsk_ring_prod__submit (fq, i);
@@ -196,7 +222,7 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) rx_bytes += len; bufs[count++] = mbufs[i]; -rte_ring_enqueue (umem->buf_ring, (void *)addr); +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); }xsk_ring_cons__release (rx, rcvd);
@@ -219,7 +245,7 @@ static void pull_umem_cq(struct xsk_umem_info *umem, int size)for (i =0 ; i < n; i++) {uint64_t addr; addr = *xsk_ring_cons__comp_addr (cq, idx_cq++); -rte_ring_enqueue (umem->buf_ring, (void *)addr); +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); }xsk_ring_cons__release (cq, n);
@@ -248,7 +274,7 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)struct pkt_tx_queue *txq = queue;struct xsk_umem_info *umem = txq->pair->umem;struct rte_mbuf *mbuf; -void *addrs[ETH_AF_XDP_TX_BATCH_SIZE ]; +struct rte_mbuf *mbuf_to_tx;unsigned long tx_bytes =0 ;int i, valid =0 ;uint32_t idx_tx;
@@ -257,11 +283,6 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)pull_umem_cq (umem, nb_pkts); - nb_pkts =rte_ring_dequeue_bulk (umem->buf_ring, addrs, - nb_pkts,NULL ); -if (nb_pkts ==0 ) -return 0 ; -if (xsk_ring_prod__reserve (&txq->tx, nb_pkts, &idx_tx) != nb_pkts) {kick_tx (txq);return 0 ;
@@ -275,7 +296,12 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) desc =xsk_ring_prod__tx_desc (&txq->tx, idx_tx + i); mbuf = bufs[i];if (mbuf->pkt_len <= buf_len) { - desc->addr = (uint64_t )addrs[valid]; + mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf_to_tx ==NULL )) { +rte_pktmbuf_free (mbuf); +continue ; + } + desc->addr =mbuf_to_addr (umem, mbuf_to_tx); desc->len = mbuf->pkt_len; pkt =xsk_umem__get_data (umem->buffer, desc->addr);
@@ -291,10 +317,6 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)kick_tx (txq); -if (valid < nb_pkts) -rte_ring_enqueue_bulk (umem->buf_ring, &addrs[valid], - nb_pkts - valid,NULL ); - txq->stats.err_pkts += nb_pkts - valid; txq->stats.tx_pkts += valid; txq->stats.tx_bytes += tx_bytes;
@@ -443,16 +465,29 @@ eth_link_update(struct rte_eth_dev *dev __rte_unused,static void xdp_umem_destroy (struct xsk_umem_info *umem) { -free (umem->buffer); - umem->buffer =NULL ; - -rte_ring_free (umem->buf_ring); - umem->buf_ring =NULL ; +rte_mempool_free (umem->mb_pool); + umem->mb_pool =NULL ;rte_free (umem); umem =NULL ; } +static inline uint64_t get_base_addr (struct rte_mempool *mp) +{ +struct rte_mempool_memhdr *memhdr; + + memhdr =STAILQ_FIRST (&mp->mem_list); +return (uint64_t )(memhdr->addr); +} + +static inline uint64_t get_len (struct rte_mempool *mp) +{ +struct rte_mempool_memhdr *memhdr; + + memhdr =STAILQ_FIRST (&mp->mem_list); +return (uint64_t )(memhdr->len); +} +static struct xsk_umem_info *xdp_umem_configure (void ) {struct xsk_umem_info *umem;
@@ -461,9 +496,8 @@ static struct xsk_umem_info *xdp_umem_configure(void) .comp_size = ETH_AF_XDP_DFLT_NUM_DESCS, .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM }; -void *bufs =NULL ; +void *base_addr =NULL ;int ret; -uint64_t i; umem =rte_zmalloc_socket ("umem" ,sizeof (*umem),0 ,rte_socket_id ());if (umem ==NULL ) {
@@ -471,26 +505,20 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->buf_ring =rte_ring_create ("af_xdp_ring" , -ETH_AF_XDP_NUM_BUFFERS , -SOCKET_ID_ANY , -0x0 ); -if (umem->buf_ring ==NULL ) { -AF_XDP_LOG (ERR ,"Failed to create rte_ring\n" ); + umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , +SOCKET_ID_ANY ); +if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); goto err; } + base_addr = (void *)get_base_addr (umem->mb_pool); -for (i =0 ; i <ETH_AF_XDP_NUM_BUFFERS ; i++) -rte_ring_enqueue (umem->buf_ring, - (void *)(i *ETH_AF_XDP_FRAME_SIZE + -ETH_AF_XDP_DATA_HEADROOM )); - -if (posix_memalign (&bufs,getpagesize (), -ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE )) { -AF_XDP_LOG (ERR ,"Failed to allocate memory pool.\n" ); - goto err; - } - ret =xsk_umem__create (&umem->umem, bufs, + ret =xsk_umem__create (&umem->umem, base_addr,ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE , &umem->fq, &umem->cq, &usr_config);
@@ -499,7 +527,7 @@ static struct xsk_umem_info *xdp_umem_configure(void)AF_XDP_LOG (ERR ,"Failed to create umem" ); goto err; } - umem->buffer = bufs; + umem->buffer = base_addr;return umem;
@@ -903,10 +931,9 @@ rte_pmd_af_xdp_remove(struct rte_vdev_device *dev) internals = eth_dev->data->dev_private; -rte_ring_free (internals->umem->buf_ring); -rte_free (internals->umem->buffer);rte_free (internals->umem); +rte_mempool_free (internals->umem->mb_pool);rte_eth_dev_release_port (eth_dev);
Signature · 1 line
2.17.1
PATCH v7 5/5 net/af_xdp: enable zero copy
In reply to Xiaolong YeTry to check if external mempool (from rx_queue_setup) is fit for af_xdp, if it is, it will be registered to af_xdp socket directly and there will be no packet data copy on Rx and Tx.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 130 ++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 34 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +96 -34
@@ -67,6 +67,7 @@ struct xsk_umem_info {struct xsk_umem *umem;struct rte_mempool *mb_pool;void *buffer; +uint8_t zc; };struct rx_stats {
@@ -85,6 +86,7 @@ struct pkt_rx_queue {struct pkt_tx_queue *pair;uint16_t queue_idx; +uint8_t zc; };struct tx_stats {
@@ -202,7 +204,9 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)if (xsk_prod_nb_free (fq, free_thresh) >= free_thresh) (void )reserve_fill_queue (umem,ETH_AF_XDP_RX_BATCH_SIZE ); -if (unlikely (rte_pktmbuf_alloc_bulk (rxq->mb_pool, mbufs, rcvd) !=0 )) +if (!rxq->zc && +unlikely (rte_pktmbuf_alloc_bulk (rxq->mb_pool, + mbufs, rcvd) !=0 ))return 0 ;for (i =0 ; i < rcvd; i++) {
@@ -216,13 +220,23 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) len = desc->len; pkt =xsk_umem__get_data (rxq->umem->buffer, addr); - rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), pkt, len); -rte_pktmbuf_pkt_len (mbufs[i]) = len; -rte_pktmbuf_data_len (mbufs[i]) = len; - rx_bytes += len; - bufs[count++] = mbufs[i]; - -rte_pktmbuf_free (addr_to_mbuf (umem, addr)); +if (rxq->zc) { +struct rte_mbuf *mbuf; + mbuf =addr_to_mbuf (rxq->umem, addr); +rte_pktmbuf_pkt_len (mbuf) = len; +rte_pktmbuf_data_len (mbuf) = len; + rx_bytes += len; + bufs[count++] = mbuf; + }else { + rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), + pkt, len); +rte_pktmbuf_pkt_len (mbufs[i]) = len; +rte_pktmbuf_data_len (mbufs[i]) = len; + rx_bytes += len; + bufs[count++] = mbufs[i]; + +rte_pktmbuf_free (addr_to_mbuf (umem, addr)); + } }xsk_ring_cons__release (rx, rcvd);
@@ -295,22 +309,29 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) -ETH_AF_XDP_DATA_HEADROOM ; desc =xsk_ring_prod__tx_desc (&txq->tx, idx_tx + i); mbuf = bufs[i]; -if (mbuf->pkt_len <= buf_len) { - mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); -if (unlikely (mbuf_to_tx ==NULL )) { -rte_pktmbuf_free (mbuf); -continue ; - } - desc->addr =mbuf_to_addr (umem, mbuf_to_tx); +if (txq->pair->zc && mbuf->pool == umem->mb_pool) { + desc->addr =mbuf_to_addr (umem, mbuf); desc->len = mbuf->pkt_len; - pkt =xsk_umem__get_data (umem->buffer, - desc->addr); - rte_memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), - desc->len); valid++; tx_bytes += mbuf->pkt_len; + }else { +if (mbuf->pkt_len <= buf_len) { + mbuf_to_tx =rte_pktmbuf_alloc (umem->mb_pool); +if (unlikely (mbuf_to_tx ==NULL )) { +rte_pktmbuf_free (mbuf); +continue ; + } + desc->addr =mbuf_to_addr (umem, mbuf_to_tx); + desc->len = mbuf->pkt_len; + pkt =xsk_umem__get_data (umem->buffer, + desc->addr); + memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), + desc->len); + valid++; + tx_bytes += mbuf->pkt_len; + } +rte_pktmbuf_free (mbuf); } -rte_pktmbuf_free (mbuf); }xsk_ring_prod__submit (&txq->tx, nb_pkts);
@@ -488,7 +509,7 @@ static inline uint64_t get_len(struct rte_mempool *mp)return (uint64_t )(memhdr->len); } -static struct xsk_umem_info *xdp_umem_configure (void ) +static struct xsk_umem_info *xdp_umem_configure (struct rte_mempool *mb_pool) {struct xsk_umem_info *umem;struct xsk_umem_config usr_config = {
@@ -505,16 +526,23 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , -ETH_AF_XDP_NUM_BUFFERS , -250 ,0 , -ETH_AF_XDP_FRAME_SIZE - -ETH_AF_XDP_MBUF_OVERHEAD , -MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , -SOCKET_ID_ANY ); -if (umem->mb_pool ==NULL || umem->mb_pool->nb_mem_chunks !=1 ) { -AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); - goto err; +if (!mb_pool) { + umem->mb_pool =rte_pktmbuf_pool_create_with_flags ("af_xdp_mempool" , +ETH_AF_XDP_NUM_BUFFERS , +250 ,0 , +ETH_AF_XDP_FRAME_SIZE - +ETH_AF_XDP_MBUF_OVERHEAD , +MEMPOOL_F_NO_SPREAD |MEMPOOL_CHUNK_F_PAGE_ALIGN , +SOCKET_ID_ANY ); + +if (umem->mb_pool ==NULL || + umem->mb_pool->nb_mem_chunks !=1 ) { +AF_XDP_LOG (ERR ,"Failed to create mempool\n" ); + goto err; + } + }else { + umem->mb_pool = mb_pool; + umem->zc =1 ; } base_addr = (void *)get_base_addr (umem->mb_pool);
@@ -536,16 +564,43 @@ static struct xsk_umem_info *xdp_umem_configure(void)return NULL ; } +static uint8_t +check_mempool_zc (struct rte_mempool *mp) +{ +RTE_ASSERT (mp); + +/* must continues */ +if (mp->nb_mem_chunks >1 ) +return 0 ; + +/* check header size */ +if (mp->header_size !=RTE_CACHE_LINE_SIZE ) +return 0 ; + +/* check base address */ +if ((uint64_t )get_base_addr (mp) %getpagesize () !=0 ) +return 0 ; + +/* check chunk size */ +if ((mp->elt_size + mp->header_size + mp->trailer_size) % +ETH_AF_XDP_FRAME_SIZE !=0 ) +return 0 ; + +return 1 ; +} +static int xsk_configure (struct pmd_internals *internals,struct pkt_rx_queue *rxq, -int ring_size) +int ring_size,struct rte_mempool *mb_pool) {struct xsk_socket_config cfg;struct pkt_tx_queue *txq = rxq->pair; +struct rte_mempool *mp;int ret =0 ;int reserve_size; - rxq->umem =xdp_umem_configure (); + mp =check_mempool_zc (mb_pool) ? mb_pool :NULL ; + rxq->umem =xdp_umem_configure (mp);if (rxq->umem ==NULL )return -ENOMEM ;
@@ -622,7 +677,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, rxq->mb_pool = mb_pool; -if (xsk_configure (internals, rxq, nb_rx_desc)) { +if (xsk_configure (internals, rxq, nb_rx_desc, mb_pool)) {AF_XDP_LOG (ERR ,"Failed to configure xdp socket\n" ); ret = -EINVAL ; goto err;
@@ -630,6 +685,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, internals->umem = rxq->umem; +if (mb_pool == internals->umem->mb_pool) + rxq->zc = internals->umem->zc; + +if (rxq->zc) +AF_XDP_LOG (INFO , +"zero copy enabled on rx queue %d\n" , rx_queue_id); + dev->data->rx_queues[rx_queue_id] = rxq;return 0 ;
Signature · 1 line
2.17.1
Re: [PATCH v7 5/5] net/af_xdp: enable zero copy
Quoted 29 lines · Xiaolong Ye
Try to check if external mempool (from
rx_queue_setup) is fit foraf_xdp, if it is, it will be registered toaf_xdpsocket directly and there will be no packet data copy on Rx and Tx.Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 130 ++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 34 deletions(-)drivers/net/af_xdp/rte_eth_af_xdp.c +2
-0@@ -67,6 +67,7 @@ struct xsk_umem_info {struct xsk_umem *umem;struct rte_mempool *mb_pool;void *buffer; +uint8_t zc; };struct rx_stats {@@ -85,6 +86,7 @@ struct pkt_rx_queue {struct pkt_tx_queue *pair;uint16_t queue_idx; +uint8_t zc; };struct tx_stats {
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c eth_rx_queue_setup(struct rte_eth_dev *dev, · line 694
Quoted 11 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +7
-0@@ -630,6 +685,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, internals->umem = rxq->umem; +if (mb_pool == internals->umem->mb_pool) + rxq->zc = internals->umem->zc; + +if (rxq->zc) +AF_XDP_LOG (INFO , +"zero copy enabled on rx queue %d\n" , rx_queue_id); +
The "zero copy" implemented in this patch, also the variable 'zc', is from 'af_xdp' umem to mbuf data via versa copy, right?
There is also another "zero copy" support in af_xdp, device to buffers... Do you think can these be confused with each other, should we have another log message and variable name for this one?
Indeed I can't think of a good name, but something like, "pmd/driver zero copy" & 'pmd_zc' ??
Re: [PATCH v7 5/5] net/af_xdp: enable zero copy
Quoted 37 lines · Ferruh Yigit
Quoted 29 lines · Xiaolong Ye
Try to check if external mempool (from
rx_queue_setup) is fit foraf_xdp, if it is, it will be registered toaf_xdpsocket directly and there will be no packet data copy on Rx and Tx.Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 130 ++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 34 deletions(-)drivers/net/af_xdp/rte_eth_af_xdp.c +2
-0@@ -67,6 +67,7 @@ struct xsk_umem_info {struct xsk_umem *umem;struct rte_mempool *mb_pool;void *buffer; +uint8_t zc; };struct rx_stats {@@ -85,6 +86,7 @@ struct pkt_rx_queue {struct pkt_tx_queue *pair;uint16_t queue_idx; +uint8_t zc; };struct tx_stats {<...>
Quoted 4 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +0
-0@@ -630,6 +685,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, internals->umem = rxq->umem;
Quoted 15 lines
drivers/net/af_xdp/rte_eth_af_xdp.c eth_rx_queue_setup(struct rte_eth_dev *dev, · line 694
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +7
-0+if (mb_pool == internals->umem->mb_pool) + rxq->zc = internals->umem->zc; + +if (rxq->zc) +AF_XDP_LOG (INFO , +"zero copy enabled on rx queue %d\n" , rx_queue_id); +The "zero copy" implemented in this patch, also the variable 'zc', is from '
af_xdp' umem to mbuf data via versa copy, right?
There is also another "zero copy" support inaf_xdp, device to buffers... Do you think can these be confused with each other, should we have another log message and variable name for this one?
Indeed I can't think of a good name, but something like, "pmd/driver zero copy" & 'pmd_zc' ??
That's a good suggestion, will adopt it.
Thanks,
Xiaolong
v8 cover AF_XDP PMD
In reply to Xiaolong YeHi, all
Overview
========
This patchset adds a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux, see below links [1] [2] for details of AF_XDP introduction:
AF_XDP roadmap
==============
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.
Change logs
===========
v8:
- address Ferruh's comments on V7
- replace posix_memalign with rte_memzone_reserve_aligned to get better performance
- keep the first patch only as Oliver suggested as zero copy part implementation is still in suspense, we may provide the related patch later.
v7:
- mention mtu limitation in af_xdp.rst
- fix the vdev name in af_xdp.rst
V6:
- remove the newline in AF_XDP_LOG definition to avoid double new lines issue.
- rename MEMPOOL_F_PAGE_ALIGN to MEMPOOL_CHUNK_F_PAGE_ALIGN.
V5:
- disable AF_XDP pmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of Maxime
V4:
- change vdev name to net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by Stephen
V3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.
V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactor rte_mbuf.c to avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.
changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the AP_XDP uapi. After the rework, it helps to reduce 300+ lines of code.
- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls xsk_socket__create. userspace application only needs to handle the cleanup.
How to try
==========
1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support -->
Networking options -->
[ * ] XDP sockets
2. build libbpf in tools/lib/bpf, and copy the libbpf.a and libbpf.so to /usr/lib64
cd tools/lib/bpf
make
3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable AF_XDP pmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
5. start testpmd
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1
in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to af_xdp socket.
Xiaolong Ye (1):
net/af_xdp: introduce AF XDP PMD driver
MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 48 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 945 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1083 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 1 line
2.17.1
PATCH v8 1/1 net/af_xdp: introduce AF XDP PMD driver
Add a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 48 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 945 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1083 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +7 -0
@@ -479,6 +479,13 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/af_xdp.rst +F: doc/guides/nics/features/af_xdp.ini + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -430,6 +430,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +48 -0
48 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -65,6 +65,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +32 -0
@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpf + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/meson.build new file +21 -0
@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif + +bpf_dep = dependency('libbpf', required: false) +if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false) + if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
drivers/net/af_xdp/rte_eth_af_xdp.c new file +945 -0
945 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v8 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 13 lines · On Tue, 2 Apr 2019 18:45:54 +0800 Xiaolong Ye <[email protected]> wrote:
drivers/net/af_xdp/rte_eth_af_xdp.c new file +13
-0+ +#include <rte_mbuf.h> +#include <rte_ethdev_driver.h> +#include <rte_ethdev_vdev.h> +#include <rte_malloc.h> +#include <rte_kvargs.h> +#include <rte_bus_vdev.h> +#include <rte_string_fns.h> + +#include <linux/if_ether.h> +#include <linux/if_xdp.h> +#include <linux/if_link.h> +#include <asm/barrier.h>
drivers/net/af_xdp/rte_eth_af_xdp.c line 26
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +10
-0+#include <arpa/inet.h> +#include <net/if.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <unistd.h> +#include <poll.h> +#include <bpf/bpf.h> +#include <xsk.h>
The ordering here seems surprising. The usual ordering is:
Libc includes:
#include <stdio.h>
...
Sys includes:
#include <sys/types.h>
Linux includes:
#include <linux/if_xdp.h>
DPDK includes:
#include <rte_mbuf.h>
If I run "Include what you use" it has different suggestions. Some of which you should ignore but overall there are several good ones.
rte_eth_af_xdp.c should add these lines:
#include <asm/int-ll64.h> // for __u64 #include <bits/stdint-uintn.h> // for uint16_t, uint64_t, uint32_t #include <errno.h> // for EINVAL, errno, EAGAIN, ENOMEM, EBUSY #include <netinet/in.h> // for IPPROTO_IP #include <rte_ethdev.h> // for rte_eth_dev, rte_eth_dev_data #include <stdlib.h> // for strtol #include <string.h> // for NULL, memset, strlen #include "rte_branch_prediction.h" // for unlikely #include "rte_common.h" // for __rte_unused, RTE_MIN, RTE_PRIORI... #include "rte_config.h" // for RTE_PKTMBUF_HEADROOM #include "rte_dev.h" // for rte_device, RTE_PMD_REGISTER_PARA... #include "rte_eal.h" // for rte_eal_process_type, rte_proc_ty... #include "rte_ethdev.h" // for rte_eth_stats, rte_eth_dev_info #include "rte_ether.h" // for ETHER_ADDR_LEN, ether_addr #include "rte_lcore.h" // for rte_socket_id #include "rte_log.h" // for rte_log, RTE_LOG_ERR, RTE_LOG_INFO #include "rte_memory.h" // for SOCKET_ID_ANY #include "rte_memzone.h" // for rte_memzone_free, RTE_MEMZONE_IOV... #include "rte_ring.h" // for rte_ring_free, rte_ring_create
struct rte_mempool;
rte_eth_af_xdp.c should remove these lines:
- #include <arpa/inet.h> // lines 17-17
- #include <poll.h> // lines 24-24
- #include <rte_ethdev_vdev.h> // lines 7-7
- #include <sys/mman.h> // lines 22-22
- #include <sys/types.h> // lines 19-19
Re: [PATCH v8 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 66 lines · Stephen Hemminger
Quoted 13 lines · On Tue, 2 Apr 2019 18:45:54 +0800 Xiaolong Ye <[email protected]> wrote:
drivers/net/af_xdp/rte_eth_af_xdp.c new file +13
-0+ +#include <rte_mbuf.h> +#include <rte_ethdev_driver.h> +#include <rte_ethdev_vdev.h> +#include <rte_malloc.h> +#include <rte_kvargs.h> +#include <rte_bus_vdev.h> +#include <rte_string_fns.h> + +#include <linux/if_ether.h> +#include <linux/if_xdp.h> +#include <linux/if_link.h> +#include <asm/barrier.h> drivers/net/af_xdp/rte_eth_af_xdp.c line 26
Quoted 10 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +10
-0+#include <arpa/inet.h> +#include <net/if.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <unistd.h> +#include <poll.h> +#include <bpf/bpf.h> +#include <xsk.h> The ordering here seems surprising. The usual ordering is:
Libc includes:
#include <stdio.h>
...
Sys includes:
#include <sys/types.h>Linux includes:
#include <linux/if_xdp.h>DPDK includes:
#include <rte_mbuf.h>If I run "Include what you use" it has different suggestions. Some of which you should ignore but overall there are several good ones.
rte_eth_af_xdp.cshould add these lines:#include <asm/int-ll64.h> // for __u64 #include <bits/stdint-uintn.h> // for uint16_t, uint64_t, uint32_t #include <errno.h> // for EINVAL, errno, EAGAIN, ENOMEM, EBUSY #include <netinet/in.h> // for IPPROTO_IP #include <rte_ethdev.h> // for rte_eth_dev, rte_eth_dev_data #include <stdlib.h> // for strtol #include <string.h> // for NULL, memset, strlen #include "rte_branch_prediction.h" // for unlikely #include "rte_common.h" // for __rte_unused, RTE_MIN, RTE_PRIORI... #include "rte_config.h" // for RTE_PKTMBUF_HEADROOM #include "rte_dev.h" // for rte_device, RTE_PMD_REGISTER_PARA... #include "rte_eal.h" // for rte_eal_process_type, rte_proc_ty... #include "rte_ethdev.h" // for rte_eth_stats, rte_eth_dev_info #include "rte_ether.h" // for ETHER_ADDR_LEN, ether_addr #include "rte_lcore.h" // for rte_socket_id #include "rte_log.h" // for rte_log, RTE_LOG_ERR, RTE_LOG_INFO #include "rte_memory.h" // for SOCKET_ID_ANY #include "rte_memzone.h" // for rte_memzone_free, RTE_MEMZONE_IOV... #include "rte_ring.h" // for rte_ring_free, rte_ring_create
Quoted 9 lines
struct
rte_mempool;
rte_eth_af_xdp.cshould remove these lines:
- #include <arpa/inet.h> // lines 17-17
- #include <poll.h> // lines 24-24
- #include <rte_ethdev_vdev.h> // lines 7-7
- #include <sys/mman.h> // lines 22-22
- #include <sys/types.h> // lines 19-19
Thanks for pointing out, I'll adjust the headers.
Thanks,
Xiaolong
Quoted 3 lines
v9 cover Introduce AF_XDP PMD
In reply to Xiaolong YeOverview
========
This patchset adds a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux, see below links [1] [2] for details of AF_XDP introduction:
AF_XDP roadmap
==============
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.
Change logs
===========
V9:
- adjust header files order according to Stephen's suggestion
v8:
- address Ferruh's comments on V7
- replace posix_memalign with rte_memzone_reserve_aligned to get better performance
- keep the first patch only as Oliver suggested as zero copy part implementation is still in suspense, we may provide the related patch later.
v7:
- mention mtu limitation in af_xdp.rst
- fix the vdev name in af_xdp.rst
V6:
- remove the newline in AF_XDP_LOG definition to avoid double new lines issue.
- rename MEMPOOL_F_PAGE_ALIGN to MEMPOOL_CHUNK_F_PAGE_ALIGN.
V5:
- disable AF_XDP pmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of Maxime
V4:
- change vdev name to net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by Stephen
V3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.
V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactor rte_mbuf.c to avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.
changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the AP_XDP uapi. After the rework, it helps to reduce 300+ lines of code.
- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls xsk_socket__create. userspace application only needs to handle the cleanup.
How to try
==========
1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support -->
Networking options -->
[ * ] XDP sockets
2. build libbpf in tools/lib/bpf, and copy the libbpf.a and libbpf.so to /usr/lib64
cd tools/lib/bpf
make
3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable AF_XDP pmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
5. start testpmd
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1
in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to af_xdp socket.
Xiaolong Ye (1):
net/af_xdp: introduce AF XDP PMD driver
MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 48 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 956 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1094 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 1 line
2.17.1
PATCH v9 1/1 net/af_xdp: introduce AF XDP PMD driver
Add a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 48 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 32 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 956 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 13 files changed, 1094 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +7 -0
@@ -479,6 +479,13 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/af_xdp.rst +F: doc/guides/nics/features/af_xdp.ini + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -430,6 +430,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +48 -0
48 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -74,6 +74,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +32 -0
@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpf + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/meson.build new file +21 -0
@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif + +bpf_dep = dependency('libbpf', required: false) +if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false) + if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
drivers/net/af_xdp/rte_eth_af_xdp.c new file +956 -0
956 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
drivers/net/af_xdp/rte_eth_af_xdp.c line 251
Quoted 1 line · On Tue, 2 Apr 2019 23:46:53 +0800 Xiaolong Ye <[email protected]> wrote:
drivers/net/af_xdp/rte_eth_af_xdp.c new file +1
-0+/* pull from complete qeueu to leave more space */
Overall looks good, one last spelling error
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 6 lines · Stephen Hemminger
drivers/net/af_xdp/rte_eth_af_xdp.c line 251
Quoted 1 line · On Tue, 2 Apr 2019 23:46:53 +0800 Xiaolong Ye <[email protected]> wrote:
drivers/net/af_xdp/rte_eth_af_xdp.c new file +1
-0+/* pull from complete qeueu to leave more space */ Overall looks good, one last spelling error
Sorry for the typo, will fix in in next version.
Thanks,
Xiaolong
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Xiaolong YeQuoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a
drivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf
Sorry for not noticing this before, but doesn't this require the full kernel tree rather than just the typical headers package? Requiring the full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHEL and SUSE. At least on Debian and Ubuntu, the kernel headers packages distributed do not include the full kernel tree, only the headers, so there's no tools/lib or tools/include.
Like other dependencies, this should assume they are installed as regular libraries, eg:
CFLAGS += $(shell command -v pkg-config > /dev/null 2>&1 && pkg-config --cflags libbpf || echo "-I/usr/include/bpf")
drivers/net/af_xdp/Makefile line 25
Quoted 5 lines
drivers/net/af_xdp/Makefile new file +5
-0+CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpf
LDLIBS += $(shell command -v pkg-config > /dev/null 2>&1 && pkg-config --libs libbpf || echo "-lbpf")
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Hi, Luca
Quoted 28 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf
Quoted 7 lines
Sorry for not noticing this before, but doesn't this require the full kernel tree rather than just the typical headers package? Requiring the full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHEL and SUSE. At least on Debian and Ubuntu, the kernel headers packages distributed do not include the full kernel tree, only the headers, so there's no
tools/libortools/include.
Currently we do have dependencies on the kernel src tree, as xsk.h and asm/barrier wouldn't be installed by libbpf, so before libbpf handles these properly, can we keep the current RTE_KERNELDIR in Makefile for now, and mention the dependencies in document, also suggest users to config RTE_KERNELDIR to correct kernel src tree if they want to use af_xdp pmd?
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and install
Thanks,
Xiaolong
Quoted 17 lines
Like other dependencies, this should assume they are installed as regular libraries, eg:
CFLAGS += $(shell command -v pkg-config >
/dev/null2>&1 && pkg-config --cflags libbpf || echo "-I/usr/include/bpf")drivers/net/af_xdp/Makefile line 25
Quoted 5 lines
drivers/net/af_xdp/Makefile new file +5
-0+CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += -lbpfLDLIBS += $(shell command -v pkg-config >
/dev/null2>&1 && pkg-config --libs libbpf || echo "-lbpf")Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 53 lines · Ye Xiaolong
Hi, Luca
Quoted 31 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require the full
kernel tree rather than just the typical headers package? RequiringQuoted 8 lines
the
full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHEL and SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.hand
asm/barrier wouldn't be installed by libbpf, so before libbpf handles these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor now, and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?
Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.h is installed by the kernel headers packages so it would be fine (although not ideal) and not need the full source tree. xsk.h is a bit more worrying, as it looks like an internal header from here.
Is it really necessary for external applications to use an internal- only header and a kernel header to be able to use libbpf?
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 67 lines · Luca Boccassi
Quoted 57 lines · Ye Xiaolong
Hi, Luca
Quoted 33 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require the full
kernel tree rather than just the typical headers package? Requiring
theQuoted 8 lines
full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHEL and SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.hand
asm/barrier wouldn't be installed by libbpf, so before libbpf handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
Quoted 8 lines
asm/barrier.his installed by the kernel headers packages so it would be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header from
here.Is it really necessary for external applications to use an internal- only header and a kernel header to be able to use libbpf?
Actually, xsk.h is now installed by the library makefile:
https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/commit/?id=379e2014c95b
So the full kernel source tree is no longer required.
Is asm/barrier.h really required? Isn't there an userspace alternative?
Also, the license in asm/barrier.h is GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which means at the very least the af_xdp PMD shared object is also licensed under GPL-2.0 only, isn't it?
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 74 lines · Luca Boccassi
Quoted 73 lines · Luca Boccassi
Quoted 57 lines · Ye Xiaolong
Hi, Luca
Quoted 33 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require the full
kernel tree rather than just the typical headers package? Requiring
theQuoted 8 lines
full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHEL and SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.hand
asm/barrier wouldn't be installed by libbpf, so before libbpf handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.his installed by the kernel headers packages so it would be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header from
here.
Quoted 6 lines
Quoted 2 lines
Is it really necessary for external applications to use an internal- only header and a kernel header to be able to use libbpf?
Actually,
xsk.his now installed by the library makefile:https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/commit/?id=379e2014c95b
Good to have this one. But again it is in BPF tree and it won't be in 5.1.
I suggested changing code as following for now, it would help to keep changes small when above patch merged into kernel:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib [in makefile]
#include <bpf/xsk.h> [in .c file]
Quoted 4 lines
So the full kernel source tree is no longer required.
Is
asm/barrier.hreally required? Isn't there an userspace alternative?
The 'asm/barrier.h' in the kernel headers and the 'tools/include/asm/barrier.h' looks different, the one in the kernel source has dependency to other kernel headers.
I wonder same thing, what is used from 'tools/include/asm/barrier.h' and if it can be avoided.
Anyway, as Xiaolong mentioned, following is working, can it work from a distro point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk with af_xdp enabled
Quoted 6 lines
Also, the license in
asm/barrier.his GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which means at the very least theaf_xdpPMD shared object is also licensed under GPL-2.0 only, isn't it?
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 84 lines · Ferruh Yigit
Quoted 83 lines · Luca Boccassi
Quoted 81 lines · Luca Boccassi
Quoted 61 lines · Ye Xiaolong
Hi, Luca
Quoted 36 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require the
full
kernel tree rather than just the typical headers package? Requiring
the
full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHELQuoted 8 lines
and
SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.h
and
asm/barrier wouldn't be installed by libbpf, so before libbpf handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.his installed by the kernel headers packages so it would
be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header from
here.Is it really necessary for external applications to use an internal-
only header and a kernel header to be able to use libbpf?
Quoted 7 lines
Quoted 4 lines
Actually,
xsk.his now installed by the library makefile:https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/commit/?id=379e2014c95b
Good to have this one. But again it is in BPF tree and it won't be in 5.1.
It looks like a small and required bug fix to me, and 5.1 is still in RC state, so perhaps there's still time.
Bjorn and Magnus, any chance the above makefile install fix could be sent for inclusion in 5.1-rc4?
Quoted 17 lines
I suggested changing code as following for now, it would help to keep changes
small when above patch merged into kernel:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib [in makefile]
#include <bpf/xsk.h> [in .c file]Quoted 4 lines
So the full kernel source tree is no longer required.
Is
asm/barrier.hreally required? Isn't there an userspace alternative?The '
asm/barrier.h' in the kernel headers and the 'tools/include/asm/barrier.h'
looks different, the one in the kernel source has dependency to other kernel
headers.
Quoted 3 lines
I wonder same thing, what is used from '
tools/include/asm/barrier.h' and if it
can be avoided.
The one in tools/include also is GPL-2.0 only so it cannot be included from the PMD, which is BSD-3-clause only (and it recursively includes the other arch-specific kernel headers)
Quoted 7 lines
Anyway, as Xiaolong mentioned, following is working, can it work from a distro
point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk withaf_xdpenabled
As long as the full kernel tree is required, we cannot enable it in Debian and Ubuntu - we can't have it at build time on the build workers, and also there's the licensing problem.
Quoted 9 lines
Quoted 7 lines
Also, the license in
asm/barrier.his GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which
means at the very least theaf_xdpPMD shared object is also licensed
under GPL-2.0 only, isn't it?
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 99 lines · Luca Boccassi
Quoted 90 lines · Ferruh Yigit
Quoted 89 lines · Luca Boccassi
Quoted 82 lines · Luca Boccassi
Quoted 64 lines · Ye Xiaolong
Hi, Luca
Quoted 38 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require
the
full
kernel tree rather than just the typical headers package? Requiring
the
full kernel tree to be available at build time will make this
unbuildable on distros that still use makefiles, like RHELQuoted 8 lines
and
SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.h
and
asm/barrier wouldn't be installed by libbpf, so before libbpf handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor
now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.his installed by the kernel headers packages so it would
be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header
from
here.Quoted 3 lines
Is it really necessary for external applications to use an internal-
only header and a kernel header to be able to use libbpf?Actually,
xsk.his now installed by the library makefile:Quoted 7 lines
Good to have this one. But again it is in BPF tree and it won't be in
5.1.
Quoted 5 lines
It looks like a small and required bug fix to me, and 5.1 is still in RC state, so perhaps there's still time.
Bjorn and Magnus, any chance the above makefile install fix could be sent for inclusion in 5.1-rc4?
Actually the bpf tree was already merged in the net tree a couple of days ago. As far as I understand from the process, this should mean that this fix should be set for inclusion in Linus' tree in time for 5.1-rc4:
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 106 lines · Luca Boccassi
Quoted 99 lines · Luca Boccassi
Quoted 90 lines · Ferruh Yigit
Quoted 89 lines · Luca Boccassi
Quoted 82 lines · Luca Boccassi
Quoted 64 lines · Ye Xiaolong
Hi, Luca
Quoted 38 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require
the
full
kernel tree rather than just the typical headers package? Requiring
the
full kernel tree to be available at build time will make this
unbuildable on distros that still use makefiles, like RHELQuoted 8 lines
and
SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.h
and
asm/barrier wouldn't be installed by libbpf, so before libbpf handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor
now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.his installed by the kernel headers packages so it would
be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header
from
here.Quoted 3 lines
Is it really necessary for external applications to use an internal-
only header and a kernel header to be able to use libbpf?Actually,
xsk.his now installed by the library makefile:Quoted 7 lines
Good to have this one. But again it is in BPF tree and it won't be in
5.1.Quoted 5 lines
It looks like a small and required bug fix to me, and 5.1 is still in RC state, so perhaps there's still time.
Bjorn and Magnus, any chance the above makefile install fix could be sent for inclusion in 5.1-rc4?
Quoted 7 lines
Actually the bpf tree was already merged in the net tree a couple of days ago. As far as I understand from the process, this should mean that this fix should be set for inclusion in Linus' tree in time for 5.1-rc4:
My bad, it seems 'bpf' tree can be merged into 'net' tree, but also there is another 'bpf-next' for further releases.
So I believe it is OK to expect the fixes you pointed in 'bpf' tree to be in 5.1
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Luca BoccassiQuoted 90 lines · Luca Boccassi
Quoted 89 lines · Ferruh Yigit
Quoted 87 lines · Luca Boccassi
Quoted 78 lines · Luca Boccassi
Quoted 61 lines · Ye Xiaolong
Hi, Luca
Quoted 36 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require the
full
kernel tree rather than just the typical headers package? Requiring
the
full kernel tree to be available at build time will make this unbuildable on distros that still use makefiles, like RHELQuoted 8 lines
and
SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.h
and
asm/barrier wouldn't be installed by libbpf, so before libbpf handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.his installed by the kernel headers packages so it would
be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header from
here.Quoted 3 lines
Is it really necessary for external applications to use an internal-
only header and a kernel header to be able to use libbpf?Actually,
xsk.his now installed by the library makefile:https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/commit/?id=379e2014c95b
Quoted 29 lines
Quoted 2 lines
Good to have this one. But again it is in BPF tree and it won't be in 5.1.
It looks like a small and required bug fix to me, and 5.1 is still in RC state, so perhaps there's still time.
Bjorn and Magnus, any chance the above makefile install fix could be sent for inclusion in 5.1-rc4?
Quoted 20 lines
I suggested changing code as following for now, it would help to keep changes
small when above patch merged into kernel:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib [in makefile]
#include <bpf/xsk.h> [in .c file]Quoted 4 lines
So the full kernel source tree is no longer required.
Is
asm/barrier.hreally required? Isn't there an userspace alternative?The '
asm/barrier.h' in the kernel headers and the 'tools/include/asm/barrier.h'
looks different, the one in the kernel source has dependency to other kernel
headers.I wonder same thing, what is used from '
tools/include/asm/barrier.h' and if it
can be avoided.
It seems, 'tools/include/asm/barrier.h' is required for 'smp_wmb()' & 'smp_rmb()' in 'xsk.h'.
We have equivalents of these in DPDK [1], and perhaps it can be possible to use them and not include this header at all.
in 'rte_eth_af_xdp.c', before including 'xsk.h', we can include an local compatibility header which does following should work:
#define smp_rmb() rte_rmb()
#define smp_wmb() rte_wmb()
@Xiaolong, what do you think?
[1]
https://git.dpdk.org/dpdk/tree/lib/librte_eal/common/include/arch/x86/rte_atomic.h?h=v19.02#n30
Quoted 13 lines
The one in
tools/includealso is GPL-2.0 only so it cannot be included from the PMD, which is BSD-3-clause only (and it recursively includes the other arch-specific kernel headers)Quoted 7 lines
Anyway, as Xiaolong mentioned, following is working, can it work from a distro
point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk withaf_xdpenabled
Quoted 3 lines
As long as the full kernel tree is required, we cannot enable it in Debian and Ubuntu - we can't have it at build time on the build workers, and also there's the licensing problem.
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it be problem in you builds to not have it build from source?
If not, taking into account that xsk.h also will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like it can be solved, please check above.
Quoted 10 lines
Quoted 10 lines
Quoted 8 lines
Also, the license in
asm/barrier.his GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which
means at the very least theaf_xdpPMD shared object is also licensed
under GPL-2.0 only, isn't it?
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 149 lines · Ferruh Yigit
Quoted 104 lines · Luca Boccassi
Quoted 95 lines · Ferruh Yigit
Quoted 94 lines · Luca Boccassi
Quoted 87 lines · Luca Boccassi
Quoted 67 lines · Ye Xiaolong
Hi, Luca
Quoted 39 lines · Luca Boccassi
Quoted 16 lines · Xiaolong Ye
drivers/net/af_xdp/Makefile new file +9
-0@@ -0,0 +1,32 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.adrivers/net/af_xdp/Makefile line 19
Quoted 10 lines
drivers/net/af_xdp/Makefile new file +10
-0+ +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +# require kernel version >= v5.1-rc1 +CFLAGS += -I$(RTE_KERNELDIR)/tools/include +CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpfSorry for not noticing this before, but doesn't this require
the
full
kernel tree rather than just the typical headers package? Requiring
the
full kernel tree to be available at build time will make this
unbuildable on distros that still use makefiles, like RHELQuoted 8 lines
and
SUSE. At
least on Debian and Ubuntu, the kernel headers packages distributed
do
not include the full kernel tree, only the headers, so there's notools/libortools/include.Currently we do have dependencies on the kernel src tree, as
xsk.h
and
asm/barrier wouldn't be installed by libbpf, so before libbpf
handles
these
properly, can we keep the currentRTE_KERNELDIRinMakefilefor
now,
and mention
the dependencies in document, also suggest users to configRTE_KERNELDIRto correct
kernel src tree if they want to useaf_xdppmd?Quoted 8 lines
Something like:
dependencies:
- kernel source code (>= v5.1-rc1)
- build libbfp and installThanks,
Xiaolong
asm/barrier.his installed by the kernel headers packages so it
would
be fine (although not ideal) and not need the full source tree.xsk.his a bit more worrying, as it looks like an internal header
from
here.Quoted 3 lines
Is it really necessary for external applications to use an internal-
only header and a kernel header to be able to use libbpf?Actually,
xsk.his now installed by the library makefile:Quoted 7 lines
Good to have this one. But again it is in BPF tree and it won't be in
5.1.Quoted 31 lines
It looks like a small and required bug fix to me, and 5.1 is still in
RC state, so perhaps there's still time.Bjorn and Magnus, any chance the above makefile install fix could be
sent for inclusion in 5.1-rc4?Quoted 23 lines
I suggested changing code as following for now, it would help to keep
changes
small when above patch merged into kernel:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib [in makefile]
#include <bpf/xsk.h> [in .c file]Quoted 4 lines
So the full kernel source tree is no longer required.
Is
asm/barrier.hreally required? Isn't there an userspace alternative?The '
asm/barrier.h' in the kernel headers and the 'tools/include/asm/barrier.h'
looks different, the one in the kernel source has dependency to other
kernel
headers.I wonder same thing, what is used from
'tools/include/asm/barrier.h'
and if it
can be avoided.It seems, '
tools/include/asm/barrier.h' is required for 'smp_wmb()' & 'smp_rmb()' in 'xsk.h'.
We have equivalents of these in DPDK [1], and perhaps it can be possible to use
them and not include this header at all.in '
rte_eth_af_xdp.c', before including 'xsk.h', we can include an local
compatibility header which does following should work:
#definesmp_rmb()rte_rmb()
#definesmp_wmb()rte_wmb()
Quoted 4 lines
@Xiaolong, what do you think?
[1]
https://git.dpdk.org/dpdk/tree/lib/librte_eal/common/include/arch/x86/rte_atomic.h?h=v19.02#n30
Perfect, that looks like a great solution for the PMD.
For the broader picture, now that xsk.h is a public userspace header, it should at some point in the future be fixed to avoid depending on an internal kernel definition for the barriers, and either ship their own or depend on another public header that provides them. Otherwise every application that wants to use bpf with xdp needs to provide their own implementation - but this is not relanted to this patchset and we can live without for the moment in DPDK.
Quoted 21 lines
Quoted 15 lines
The one in
tools/includealso is GPL-2.0 only so it cannot be included
from the PMD, which is BSD-3-clause only (and it recursively includes
the other arch-specific kernel headers)Quoted 8 lines
Anyway, as Xiaolong mentioned, following is working, can it work from
a distro
point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk withaf_xdpenabledQuoted 3 lines
As long as the full kernel tree is required, we cannot enable it in Debian and Ubuntu - we can't have it at build time on the build workers, and also there's the licensing problem.
Got it.
Quoted 8 lines
In above steps, 'libbpf' also build from kernel source tree, will it be problem
in you builds to not have it build from source?If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like it can be
solved, please check above.
libbpf is already packaged separately in Debian and I think other distros will follow soon, so it's all good for me once the barrier issue is solved.
https://packages.debian.org/buster/libbpf-dev
Quoted 1 line
From the makefile's perspective it should not matter where it comes
from - the headers should be expected to be in /usr/include and the library in /usr/lib* - and pkg-config can help with that if available. And if a user wants to use a custom path, then it's no different than any of the other dependencies on other external libraries
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
On 04/03, Luca Boccassi wrote:
[snip]
Quoted 18 lines
Quoted 11 lines
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it be problem
in you builds to not have it build from source?If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like it can be
solved, please check above.libbpf is already packaged separately in Debian and I think other distros will follow soon, so it's all good for me once the barrier issue is solved.
Quoted 7 lines
From the makefile's perspective it should not matter where it comes from - the headers should be expected to be in
/usr/includeand the library in/usr/lib*- and pkg-config can help with that if available. And if a user wants to use a custom path, then it's no different than any of the other dependencies on other external librariesFrom
tools/lib/bpf/Makefile, after makeinstall_liband makeinstall_headers,
the headers and library would be put in /usr/local/include/bpf and /usr/local/lib*, Is it ok?
Thanks,
Xiaolong
Quoted 4 lines
Signature · 3 lines
-- Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 30 lines · Ye Xiaolong
On 04/03, Luca Boccassi wrote:
[snip]Quoted 20 lines
Quoted 7 lines
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it
be problem
in you builds to not have it build from source?Quoted 5 lines
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like
it can be
solved, please check above.libbpf is already packaged separately in Debian and I think other distros will follow soon, so it's all good for me once the barrier issue is solved.
Quoted 7 lines
From the makefile's perspective it should not matter where it comes from - the headers should be expected to be in
/usr/includeand the library in/usr/lib*- and pkg-config can help with that if available.
And if a user wants to use a custom path, then it's no different than
any of the other dependencies on other external libraries
Quoted 5 lines
From
tools/lib/bpf/Makefile, after makeinstall_liband makeinstall_headers,
the headers and library would be put in/usr/local/include/bpfand/usr/local/lib*,
Is it ok?
Yes certainly that's fine, that's expected for local installations, and users can specify a prefix with the upstream's makefile if they want to install somewhere else.
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 37 lines · Luca Boccassi
Quoted 30 lines · Ye Xiaolong
On 04/03, Luca Boccassi wrote:
[snip]Quoted 20 lines
Quoted 7 lines
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it
be problem
in you builds to not have it build from source?Quoted 5 lines
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like
it can be
solved, please check above.libbpf is already packaged separately in Debian and I think other distros will follow soon, so it's all good for me once the barrier issue is solved.
Quoted 7 lines
From the makefile's perspective it should not matter where it comes from - the headers should be expected to be in
/usr/includeand the library in/usr/lib*- and pkg-config can help with that if available.
And if a user wants to use a custom path, then it's no different than
any of the other dependencies on other external librariesQuoted 5 lines
From
tools/lib/bpf/Makefile, after makeinstall_liband makeinstall_headers,
the headers and library would be put in/usr/local/include/bpfand/usr/local/lib*,
Is it ok?
Quoted 3 lines
Yes certainly that's fine, that's expected for local installations, and users can specify a prefix with the upstream's makefile if they want to install somewhere else.
In my local test, if I run make install_lib to install the libbpf.so to /usr/local/lib64, -lbpf specified in af_xdp pmd still fails to find the library, the build would end up with a lot of undefined references which are defined in libbpf. It means during dpdk compilation, it won't search libraries in /usr/local/lib*, right?
Install the libbpf to /usr/lib64 via make install_lib prefix=/usr doesn't have this issue, so shall I just document it in af_xdp.rst or there is other proper way to do it?
Thanks,
Xiaolong
Quoted 4 lines
Signature · 3 lines
-- Kind regards, Luca Boccassi
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 42 lines · Ye Xiaolong
Quoted 37 lines · Luca Boccassi
Quoted 30 lines · Ye Xiaolong
On 04/03, Luca Boccassi wrote:
[snip]Quoted 20 lines
Quoted 7 lines
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it
be problem
in you builds to not have it build from source?Quoted 5 lines
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like
it can be
solved, please check above.libbpf is already packaged separately in Debian and I think other distros will follow soon, so it's all good for me once the barrier issue is solved.
Quoted 7 lines
From the makefile's perspective it should not matter where it comes from - the headers should be expected to be in
/usr/includeand the library in/usr/lib*- and pkg-config can help with that if available.
And if a user wants to use a custom path, then it's no different than
any of the other dependencies on other external librariesQuoted 5 lines
From
tools/lib/bpf/Makefile, after makeinstall_liband makeinstall_headers,
the headers and library would be put in/usr/local/include/bpfand/usr/local/lib*,
Is it ok?Quoted 3 lines
Yes certainly that's fine, that's expected for local installations, and users can specify a prefix with the upstream's makefile if they want to install somewhere else.
Quoted 9 lines
In my local test, if I run
make install_libto install the libbpf.so to/usr/local/lib64,-lbpfspecified inaf_xdppmd still fails to find the library, the build would end up with a lot of undefined references which are defined in libbpf. It means during dpdk compilation, it won't search libraries in/usr/local/lib*, right?Install the libbpf to
/usr/lib64viamake install_lib prefix=/usrdoesn't have this issue, so shall I just document it inaf_xdp.rstor there is other proper way to do it?
At a guess I'd say you are using Fedora Linux, right? Fedora is unusual in that it doesn't by default add /usr/local to the library and header search paths so you need to explicitly add them to your environment. Other distros should work fine for this.
/Bruce
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 48 lines · Bruce Richardson
Quoted 47 lines · Ye Xiaolong
Quoted 37 lines · Luca Boccassi
Quoted 30 lines · Ye Xiaolong
On 04/03, Luca Boccassi wrote:
[snip]Quoted 20 lines
Quoted 7 lines
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it
be problem
in you builds to not have it build from source?Quoted 5 lines
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like
it can be
solved, please check above.libbpf is already packaged separately in Debian and I think other distros will follow soon, so it's all good for me once the barrier issue is solved.
Quoted 7 lines
From the makefile's perspective it should not matter where it comes from - the headers should be expected to be in
/usr/includeand the library in/usr/lib*- and pkg-config can help with that if available.
And if a user wants to use a custom path, then it's no different than
any of the other dependencies on other external librariesQuoted 5 lines
From
tools/lib/bpf/Makefile, after makeinstall_liband makeinstall_headers,
the headers and library would be put in/usr/local/include/bpfand/usr/local/lib*,
Is it ok?Quoted 3 lines
Yes certainly that's fine, that's expected for local installations, and users can specify a prefix with the upstream's makefile if they want to install somewhere else.
In my local test, if I run
make install_libto install the libbpf.so to/usr/local/lib64,-lbpfspecified inaf_xdppmd still fails to find the library, the build would end up with a lot of undefined references which are defined in libbpf. It means during dpdk compilation, it won't search libraries in/usr/local/lib*, right?
Quoted 8 lines
Quoted 4 lines
Install the libbpf to
/usr/lib64viamake install_lib prefix=/usrdoesn't have this issue, so shall I just document it inaf_xdp.rstor there is other proper way to do it?At a guess I'd say you are using Fedora Linux, right? Fedora is unusual in that it doesn't by default add
/usr/localto the library and header search paths so you need to explicitly add them to your environment. Other distros should work fine for this.
I am using centos 7.4, I guess it has the same issue as Fedora you mentioned above.
Thanks,
Xiaolong
Quoted 2 lines
/Bruce
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Ferruh YigitOn 04/03, Ferruh Yigit wrote:
[snip]
Quoted 6 lines
It seems, '
tools/include/asm/barrier.h' is required for 'smp_wmb()' & 'smp_rmb()' in 'xsk.h'.
We have equivalents of these in DPDK [1], and perhaps it can be possible to use them and not include this header at all.
Quoted 6 lines
in '
rte_eth_af_xdp.c', before including 'xsk.h', we can include an local compatibility header which does following should work:
#definesmp_rmb()rte_rmb()
#definesmp_wmb()rte_wmb()@Xiaolong, what do you think?
It sounds perfect to me, I'll take it in my next version.
Something to confirm, So we can now assume af_xdp pmd user would use kernel (say v5.1-rc4) that contains fixes regarding to xsk.h and libelf, I still need to do following changes.
1. I shall use <bpf/xsk.h> as xsk.h should be installed in system folders.
2. -lelf is not needed in rte.app.mk
3. I need to document the libbpf build and install steps in af_xdp.rst
4. add the above two defines before including xsk.h
Thanks,
Xiaolong
Quoted 42 lines
[1]
https://git.dpdk.org/dpdk/tree/lib/librte_eal/common/include/arch/x86/rte_atomic.h?h=v19.02#n30Quoted 13 lines
The one in
tools/includealso is GPL-2.0 only so it cannot be included from the PMD, which is BSD-3-clause only (and it recursively includes the other arch-specific kernel headers)Quoted 7 lines
Anyway, as Xiaolong mentioned, following is working, can it work from a distro
point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk withaf_xdpenabledQuoted 3 lines
As long as the full kernel tree is required, we cannot enable it in Debian and Ubuntu - we can't have it at build time on the build workers, and also there's the licensing problem.
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it be problem in you builds to not have it build from source?
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like it can be solved, please check above.Quoted 10 lines
Quoted 10 lines
Quoted 8 lines
Also, the license in
asm/barrier.his GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which
means at the very least theaf_xdpPMD shared object is also licensed
under GPL-2.0 only, isn't it?
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 20 lines · Ye Xiaolong
On 04/03, Ferruh Yigit wrote:
[snip]Quoted 6 lines
It seems, '
tools/include/asm/barrier.h' is required for 'smp_wmb()' & 'smp_rmb()' in 'xsk.h'.
We have equivalents of these in DPDK [1], and perhaps it can be possible to use them and not include this header at all.Quoted 6 lines
in '
rte_eth_af_xdp.c', before including 'xsk.h', we can include an local compatibility header which does following should work:
#definesmp_rmb()rte_rmb()
#definesmp_wmb()rte_wmb()@Xiaolong, what do you think?
It sounds perfect to me, I'll take it in my next version.
Something to confirm, So we can now assumeaf_xdppmd user would use kernel (say v5.1-rc4) that contains fixes regarding toxsk.hand libelf, I still need to do following changes.
Quoted 4 lines
1. I shall use <
bpf/xsk.h> asxsk.hshould be installed in system folders.
2.-lelfis not needed in rte.app.mk
3. I need to document the libbpf build and install steps inaf_xdp.rst
4. add the above two defines before includingxsk.h
Looks good to me,
only for item 4) instead of putting those defines into .c file directly, can create a private header in driver folder, put those lines and I assume will need a few includes for rte_rmb as well, and include that header before xsk.h.
Quoted 47 lines
Thanks,
XiaolongQuoted 42 lines
[1]
https://git.dpdk.org/dpdk/tree/lib/librte_eal/common/include/arch/x86/rte_atomic.h?h=v19.02#n30Quoted 13 lines
The one in
tools/includealso is GPL-2.0 only so it cannot be included from the PMD, which is BSD-3-clause only (and it recursively includes the other arch-specific kernel headers)Quoted 7 lines
Anyway, as Xiaolong mentioned, following is working, can it work from a distro
point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk withaf_xdpenabledQuoted 3 lines
As long as the full kernel tree is required, we cannot enable it in Debian and Ubuntu - we can't have it at build time on the build workers, and also there's the licensing problem.
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it be problem in you builds to not have it build from source?
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like it can be solved, please check above.Quoted 10 lines
Quoted 10 lines
Quoted 8 lines
Also, the license in
asm/barrier.his GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which
means at the very least theaf_xdpPMD shared object is also licensed
under GPL-2.0 only, isn't it?
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 26 lines · Ferruh Yigit
Quoted 20 lines · Ye Xiaolong
On 04/03, Ferruh Yigit wrote:
[snip]Quoted 6 lines
It seems, '
tools/include/asm/barrier.h' is required for 'smp_wmb()' & 'smp_rmb()' in 'xsk.h'.
We have equivalents of these in DPDK [1], and perhaps it can be possible to use them and not include this header at all.Quoted 6 lines
in '
rte_eth_af_xdp.c', before including 'xsk.h', we can include an local compatibility header which does following should work:
#definesmp_rmb()rte_rmb()
#definesmp_wmb()rte_wmb()@Xiaolong, what do you think?
It sounds perfect to me, I'll take it in my next version.
Something to confirm, So we can now assumeaf_xdppmd user would use kernel (say v5.1-rc4) that contains fixes regarding toxsk.hand libelf, I still need to do following changes.Quoted 4 lines
1. I shall use <
bpf/xsk.h> asxsk.hshould be installed in system folders.
2.-lelfis not needed in rte.app.mk
3. I need to document the libbpf build and install steps inaf_xdp.rst
4. add the above two defines before includingxsk.h
Quoted 4 lines
Looks good to me,
only for item 4) instead of putting those defines into .c file directly, can create a private header in driver folder, put those lines and I assume will need a few includes forrte_rmbas well, and include that header beforexsk.h.
Sounds better, will do.
Thanks,
Xiaolong
Quoted 49 lines
Quoted 48 lines
Thanks,
XiaolongQuoted 42 lines
[1]
https://git.dpdk.org/dpdk/tree/lib/librte_eal/common/include/arch/x86/rte_atomic.h?h=v19.02#n30Quoted 13 lines
The one in
tools/includealso is GPL-2.0 only so it cannot be included from the PMD, which is BSD-3-clause only (and it recursively includes the other arch-specific kernel headers)Quoted 7 lines
Anyway, as Xiaolong mentioned, following is working, can it work from a distro
point of view:
- get kernel source code (>= v5.1-rc1)
- build libbfp and install
- set 'RTE_KERNELDIR' to point kernel source path
- build dpdk withaf_xdpenabledQuoted 3 lines
As long as the full kernel tree is required, we cannot enable it in Debian and Ubuntu - we can't have it at build time on the build workers, and also there's the licensing problem.
Got it.
In above steps, 'libbpf' also build from kernel source tree, will it be problem in you builds to not have it build from source?
If not, taking into account that
xsk.halso will be fixed, only 'tools/include/asm/barrier.h' remains the problem, and it looks like it can be solved, please check above.Quoted 10 lines
Quoted 10 lines
Quoted 8 lines
Also, the license in
asm/barrier.his GPL-2.0 only. It is not a userspace header so it is not covered by the userspace exception, which
means at the very least theaf_xdpPMD shared object is also licensed
under GPL-2.0 only, isn't it?
[dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
I tested the new af_xdp based device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a single af_xdp vdev. If a second vdev of the same type gets created, the mempool allocation fails.
Best regards,
Markus Theil
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.
Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
Xiaolong
Quoted 3 lines
Best regards,
Markus Theil
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
Hi Xiaolong,
I tested your commit "net/af_xdp: fix creating multiple instance" on the current master branch. It does not work for me in the following minimal test setting:
1) allocate 2x 1GB huge pages for DPDK
2) ip link add p1 type veth peer name p2
3) ./dpdk-testpmd --vdev=net_af_xdp0,iface=p1 --vdev=net_af_xdp1,iface=p2 (I also tested this with two igb devices, with the same errors)
I'm using Linux 5.1-rc6 and an up to date libbpf. The setup works for the first device and fails for the second device when creating bpf maps in libbpf ("qidconf_map" or "xsks_map"). It seems, that these maps also need unique names and cannot exist twice under the same name. Furthermore if running step 3 again after it failed for the first time, xdp vdev allocation already fails for the first xdp vdev and does not reach the second one. Please let me know if you need some program output or more information from me.
Best regards,
Markus
Quoted 15 lines · Ye Xiaolong
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
XiaolongQuoted 2 lines
Best regards,
Markus Theil
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
Hi, Markus
Quoted 6 lines · Markus Theil
Hi Xiaolong,
I tested your commit "
net/af_xdp: fix creating multiple instance" on the current master branch. It does not work for me in the following minimal test setting:
Quoted 7 lines
1) allocate 2x 1GB huge pages for DPDK
2) ip link add p1 type veth peer name p2
3) ./dpdk-testpmd --vdev=net_af_xdp0,iface=p1 --vdev=net_af_xdp1,iface=p2 (I also tested this with two igb devices, with the same errors)
I've tested 19.05-rc2, started testpmd with 2 af_xdp vdev (with two i40e devices), and it works for me.
$ ./x86_64-native-linuxapp-gcc/app/testpmd -l 5,6 -n 4 --log-level=pmd.net.af_xdp:info -b 82:00.1 --no-pci --vdev net_af_xdp0,iface=ens786f1 --vdev net_af_xdp1,iface=ens786f0 EAL: Detected 88 lcore(s) EAL: Detected 2 NUMA nodes EAL: Multi-process socket /var/run/dpdk/rte/mp_socket EAL: Probing VFIO support... rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1 testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=155456, size=2176, socket=0 testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0) Port 0: 3C:FD:FE:C5:E2:41 Configuring Port 1 (socket 0) Port 1: 3C:FD:FE:C5:E2:40 Checking link statuses... Done No commandline core given, start packet forwarding io packet forwarding - ports=2 - cores=1 - streams=2 - NUMA support enabled, MP allocation mode: native Logical Core 6 (socket 0) forwards packets on 2 streams: RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
io packet forwarding packets/burst=32
nb forwarding cores=1 - nb forwarding ports=2 port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
port 1: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
Press enter to exit
Could you paste your whole failure log here?
Quoted 5 lines
I'm using Linux 5.1-rc6 and an up to date libbpf. The setup works for the first device and fails for the second device when creating bpf maps in libbpf ("
qidconf_map" or "xsks_map"). It seems, that these maps also need unique names and cannot exist twice under the same name.
So far as I know, there should not be such contraint, the bpf maps creations are wrapped in libbpf.
Quoted 8 lines
Furthermore if running step 3 again after it failed for the first time, xdp vdev allocation already fails for the first xdp vdev and does not reach the second one. Please let me know if you need some program output or more information from me.
Best regards,
Markus
Thanks,
Xiaolong
Quoted 18 lines · Ye Xiaolong
Quoted 15 lines
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
XiaolongQuoted 2 lines
Best regards,
Markus Theil
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
Hi Xiaolong,
I also tested with i40e devices, with the same result.
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0)
Port 0: 3C:FD:FE:A3:E7:30
Configuring Port 1 (socket 0)xsk_configure(): Failed to create xsk socket. (-1) eth_rx_queue_setup(): Failed to configure xdp socket
Fail to configure port 1 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failed
If I execute the same call again, I get error -16 already on the first port:
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0)xsk_configure(): Failed to create xsk socket. (-16) eth_rx_queue_setup(): Failed to configure xdp socket
Fail to configure port 0 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failed
Software versions/commits/infos:
- Linux 5.1-rc6
- DPDK 7f251bcf22c5729792f9243480af1b3c072876a5 (19.05-rc2)
- libbpf from https://github.com/libbpf/libbpf
(910c475f09e5c269f441d7496c27dace30dc2335)
- DPDK and libbpf build with meson
Best regards,
Markus
Quoted 99 lines · Ye Xiaolong
Hi, Markus
Quoted 6 lines · Markus Theil
Hi Xiaolong,
I tested your commit "
net/af_xdp: fix creating multiple instance" on the current master branch. It does not work for me in the following minimal test setting:Quoted 7 lines
1) allocate 2x 1GB huge pages for DPDK
2) ip link add p1 type veth peer name p2
3) ./dpdk-testpmd --vdev=net_af_xdp0,iface=p1 --vdev=net_af_xdp1,iface=p2 (I also tested this with two igb devices, with the same errors)
I've tested 19.05-rc2, started testpmd with 2
af_xdpvdev (with two i40e devices), and it works for me.$ ./x86_64-native-linuxapp-gcc/app/testpmd -l 5,6 -n 4 --log-level=pmd.net.af_xdp:info -b 82:00.1 --no-pci --vdev net_af_xdp0,iface=ens786f1 --vdev net_af_xdp1,iface=ens786f0 EAL: Detected 88 lcore(s) EAL: Detected 2 NUMA nodes EAL: Multi-process socket /var/run/dpdk/rte/mp_socket EAL: Probing VFIO support... rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1 testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=155456, size=2176, socket=0 testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0) Port 0: 3C:FD:FE:C5:E2:41 Configuring Port 1 (socket 0) Port 1: 3C:FD:FE:C5:E2:40 Checking link statuses... Done No commandline core given, start packet forwarding io packet forwarding - ports=2 - cores=1 - streams=2 - NUMA support enabled, MP allocation mode: native Logical Core 6 (socket 0) forwards packets on 2 streams: RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00io packet forwarding packets/burst=32
nb forwarding cores=1 - nb forwarding ports=2 port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
port 1: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
Press enter to exitCould you paste your whole failure log here?
Quoted 4 lines
I'm using Linux 5.1-rc6 and an up to date libbpf. The setup works for the first device and fails for the second device when creating bpf maps in libbpf ("
qidconf_map" or "xsks_map"). It seems, that these maps also need unique names and cannot exist twice under the same name.So far as I know, there should not be such contraint, the bpf maps creations are wrapped in libbpf.
Quoted 8 lines
Furthermore if running step 3 again after it failed for the first time, xdp vdev allocation already fails for the first xdp vdev and does not reach the second one. Please let me know if you need some program output or more information from me.
Best regards,
MarkusThanks,
XiaolongQuoted 16 lines · Ye Xiaolong
Quoted 15 lines
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
XiaolongQuoted 2 lines
Best regards,
Markus Theil
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
Hi, Markus
Quoted 17 lines · Markus Theil
Hi Xiaolong,
I also tested with i40e devices, with the same result.
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket/var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp0rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected:ring_mp_mc
Quoted 9 lines
Configuring Port 0 (socket 0)
Port 0: 3C:FD:FE:A3:E7:30
Configuring Port 1 (socket 0)xsk_configure(): Failed to create xsk socket. (-1)eth_rx_queue_setup(): Failed to configure xdp socket Fail to configure port 1 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failed
What about one vdev instance on your side? And have you brought up the interface? xsk_configure requires the interface to be up state.
dsd
Thanks,
Xiaolong
Quoted 133 lines
If I execute the same call again, I get error -16 already on the first port:
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket/var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp0rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected:ring_mp_mcConfiguring Port 0 (socket 0)xsk_configure(): Failed to create xsk socket. (-16)eth_rx_queue_setup(): Failed to configure xdp socket
Fail to configure port 0 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failedSoftware versions/commits/infos:
- Linux 5.1-rc6
- DPDK7f251bcf22c5729792f9243480af1b3c072876a5(19.05-rc2)
- libbpf from https://github.com/libbpf/libbpf
(910c475f09e5c269f441d7496c27dace30dc2335)
- DPDK and libbpf build with mesonBest regards,
MarkusQuoted 99 lines · Ye Xiaolong
Hi, Markus
Quoted 6 lines · Markus Theil
Hi Xiaolong,
I tested your commit "
net/af_xdp: fix creating multiple instance" on the current master branch. It does not work for me in the following minimal test setting:Quoted 7 lines
1) allocate 2x 1GB huge pages for DPDK
2) ip link add p1 type veth peer name p2
3) ./dpdk-testpmd --vdev=net_af_xdp0,iface=p1 --vdev=net_af_xdp1,iface=p2 (I also tested this with two igb devices, with the same errors)
I've tested 19.05-rc2, started testpmd with 2
af_xdpvdev (with two i40e devices), and it works for me.$ ./x86_64-native-linuxapp-gcc/app/testpmd -l 5,6 -n 4 --log-level=pmd.net.af_xdp:info -b 82:00.1 --no-pci --vdev net_af_xdp0,iface=ens786f1 --vdev net_af_xdp1,iface=ens786f0 EAL: Detected 88 lcore(s) EAL: Detected 2 NUMA nodes EAL: Multi-process socket /var/run/dpdk/rte/mp_socket EAL: Probing VFIO support... rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1 testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=155456, size=2176, socket=0 testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0) Port 0: 3C:FD:FE:C5:E2:41 Configuring Port 1 (socket 0) Port 1: 3C:FD:FE:C5:E2:40 Checking link statuses... Done No commandline core given, start packet forwarding io packet forwarding - ports=2 - cores=1 - streams=2 - NUMA support enabled, MP allocation mode: native Logical Core 6 (socket 0) forwards packets on 2 streams: RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00io packet forwarding packets/burst=32
nb forwarding cores=1 - nb forwarding ports=2 port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
port 1: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
Press enter to exitCould you paste your whole failure log here?
Quoted 4 lines
I'm using Linux 5.1-rc6 and an up to date libbpf. The setup works for the first device and fails for the second device when creating bpf maps in libbpf ("
qidconf_map" or "xsks_map"). It seems, that these maps also need unique names and cannot exist twice under the same name.So far as I know, there should not be such contraint, the bpf maps creations are wrapped in libbpf.
Quoted 8 lines
Furthermore if running step 3 again after it failed for the first time, xdp vdev allocation already fails for the first xdp vdev and does not reach the second one. Please let me know if you need some program output or more information from me.
Best regards,
MarkusThanks,
XiaolongQuoted 16 lines · Ye Xiaolong
Quoted 15 lines
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
XiaolongQuoted 2 lines
Best regards,
Markus Theil
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
Hi Xiaolong,
with only one vdev everything works. It stops working if I use two vdevs. Both interfaces were brought up before testing.
Best regards,
Markus
Quoted 170 lines · Ye Xiaolong
Hi, Markus
Quoted 17 lines · Markus Theil
Hi Xiaolong,
I also tested with i40e devices, with the same result.
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket/var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp0rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected:ring_mp_mcQuoted 9 lines
Configuring Port 0 (socket 0)
Port 0: 3C:FD:FE:A3:E7:30
Configuring Port 1 (socket 0)xsk_configure(): Failed to create xsk socket. (-1)eth_rx_queue_setup(): Failed to configure xdp socket Fail to configure port 1 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failedWhat about one vdev instance on your side? And have you brought up the interface?
xsk_configurerequires the interface to be up state.dsd
Thanks,
XiaolongQuoted 133 lines
If I execute the same call again, I get error -16 already on the first port:
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket/var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp0rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected:ring_mp_mcConfiguring Port 0 (socket 0)xsk_configure(): Failed to create xsk socket. (-16)eth_rx_queue_setup(): Failed to configure xdp socket
Fail to configure port 0 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failedSoftware versions/commits/infos:
- Linux 5.1-rc6
- DPDK7f251bcf22c5729792f9243480af1b3c072876a5(19.05-rc2)
- libbpf from https://github.com/libbpf/libbpf
(910c475f09e5c269f441d7496c27dace30dc2335)
- DPDK and libbpf build with mesonBest regards,
MarkusQuoted 99 lines · Ye Xiaolong
Hi, Markus
Quoted 6 lines · Markus Theil
Hi Xiaolong,
I tested your commit "
net/af_xdp: fix creating multiple instance" on the current master branch. It does not work for me in the following minimal test setting:Quoted 7 lines
1) allocate 2x 1GB huge pages for DPDK
2) ip link add p1 type veth peer name p2
3) ./dpdk-testpmd --vdev=net_af_xdp0,iface=p1 --vdev=net_af_xdp1,iface=p2 (I also tested this with two igb devices, with the same errors)
I've tested 19.05-rc2, started testpmd with 2
af_xdpvdev (with two i40e devices), and it works for me.$ ./x86_64-native-linuxapp-gcc/app/testpmd -l 5,6 -n 4 --log-level=pmd.net.af_xdp:info -b 82:00.1 --no-pci --vdev net_af_xdp0,iface=ens786f1 --vdev net_af_xdp1,iface=ens786f0 EAL: Detected 88 lcore(s) EAL: Detected 2 NUMA nodes EAL: Multi-process socket /var/run/dpdk/rte/mp_socket EAL: Probing VFIO support... rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1 testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=155456, size=2176, socket=0 testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0) Port 0: 3C:FD:FE:C5:E2:41 Configuring Port 1 (socket 0) Port 1: 3C:FD:FE:C5:E2:40 Checking link statuses... Done No commandline core given, start packet forwarding io packet forwarding - ports=2 - cores=1 - streams=2 - NUMA support enabled, MP allocation mode: native Logical Core 6 (socket 0) forwards packets on 2 streams: RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00io packet forwarding packets/burst=32
nb forwarding cores=1 - nb forwarding ports=2 port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
port 1: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
Press enter to exitCould you paste your whole failure log here?
Quoted 4 lines
I'm using Linux 5.1-rc6 and an up to date libbpf. The setup works for the first device and fails for the second device when creating bpf maps in libbpf ("
qidconf_map" or "xsks_map"). It seems, that these maps also need unique names and cannot exist twice under the same name.So far as I know, there should not be such contraint, the bpf maps creations are wrapped in libbpf.
Quoted 8 lines
Furthermore if running step 3 again after it failed for the first time, xdp vdev allocation already fails for the first xdp vdev and does not reach the second one. Please let me know if you need some program output or more information from me.
Best regards,
MarkusThanks,
XiaolongQuoted 16 lines · Ye Xiaolong
Quoted 15 lines
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
XiaolongQuoted 2 lines
Best regards,
Markus Theil
Signature · 9 lines
Markus Theil Technische Universität Ilmenau, Fachgebiet Telematik/Rechnernetze Postfach 100565 98684 Ilmenau, Germany Phone: +49 3677 69-4582 Email: markus[dot]theil[at]tu-ilmenau[dot]de Web: http://www.tu-ilmenau.de/telematik
Re: [dpdk-dev] [BUG] net/af_xdp: Current code can only create one af_xdp device
In reply to Markus TheilHi, Markus
Quoted 17 lines · Markus Theil
Hi Xiaolong,
I also tested with i40e devices, with the same result.
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket/var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp0rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected:ring_mp_mc
Quoted 8 lines
Configuring Port 0 (socket 0)
Port 0: 3C:FD:FE:A3:E7:30
Configuring Port 1 (socket 0)xsk_configure(): Failed to create xsk socket. (-1)eth_rx_queue_setup(): Failed to configure xdp socket Fail to configure port 1 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failed
(-1) error should typically refer to "Operation not permitted", any special configuration for you interfaces and were you running it with root privilege? and out of curiosity, why you got (-1) in your log, do you add some private patch to print the errno?
Thanks,
Xiaolong
Quoted 134 lines
If I execute the same call again, I get error -16 already on the first port:
./dpdk-testpmd -n 4 --log-level=pmd.net.af_xdp:debug --no-pci --vdev net_af_xdp0,iface=enp36s0f0 --vdev net_af_xdp1,iface=enp36s0f1
EAL: Detected 16 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket/var/run/dpdk/rte/mp_socket
EAL: No free hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-2048kB
EAL: Probing VFIO support...rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp0rte_pmd_af_xdp_probe(): Initializingpmd_af_xdpfornet_af_xdp1
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=267456, size=2176, socket=0
testpmd: preferred mempool ops selected:ring_mp_mcConfiguring Port 0 (socket 0)xsk_configure(): Failed to create xsk socket. (-16)eth_rx_queue_setup(): Failed to configure xdp socket
Fail to configure port 0 rx queues
EAL: Error - exiting with code: 1
Cause: Start ports failedSoftware versions/commits/infos:
- Linux 5.1-rc6
- DPDK7f251bcf22c5729792f9243480af1b3c072876a5(19.05-rc2)
- libbpf from https://github.com/libbpf/libbpf
(910c475f09e5c269f441d7496c27dace30dc2335)
- DPDK and libbpf build with mesonBest regards,
MarkusQuoted 99 lines · Ye Xiaolong
Hi, Markus
Quoted 6 lines · Markus Theil
Hi Xiaolong,
I tested your commit "
net/af_xdp: fix creating multiple instance" on the current master branch. It does not work for me in the following minimal test setting:Quoted 7 lines
1) allocate 2x 1GB huge pages for DPDK
2) ip link add p1 type veth peer name p2
3) ./dpdk-testpmd --vdev=net_af_xdp0,iface=p1 --vdev=net_af_xdp1,iface=p2 (I also tested this with two igb devices, with the same errors)
I've tested 19.05-rc2, started testpmd with 2
af_xdpvdev (with two i40e devices), and it works for me.$ ./x86_64-native-linuxapp-gcc/app/testpmd -l 5,6 -n 4 --log-level=pmd.net.af_xdp:info -b 82:00.1 --no-pci --vdev net_af_xdp0,iface=ens786f1 --vdev net_af_xdp1,iface=ens786f0 EAL: Detected 88 lcore(s) EAL: Detected 2 NUMA nodes EAL: Multi-process socket /var/run/dpdk/rte/mp_socket EAL: Probing VFIO support... rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp0 rte_pmd_af_xdp_probe(): Initializing pmd_af_xdp for net_af_xdp1 testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=155456, size=2176, socket=0 testpmd: preferred mempool ops selected: ring_mp_mc Configuring Port 0 (socket 0) Port 0: 3C:FD:FE:C5:E2:41 Configuring Port 1 (socket 0) Port 1: 3C:FD:FE:C5:E2:40 Checking link statuses... Done No commandline core given, start packet forwarding io packet forwarding - ports=2 - cores=1 - streams=2 - NUMA support enabled, MP allocation mode: native Logical Core 6 (socket 0) forwards packets on 2 streams: RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00io packet forwarding packets/burst=32
nb forwarding cores=1 - nb forwarding ports=2 port 0: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
port 1: RX queue number: 1 Tx queue number: 1
Rx offloads=0x0 Tx offloads=0x0
RX queue: 0
RX desc=0 - RX free threshold=0
RX threshold registers: pthresh=0 hthresh=0 wthresh=0 RX Offloads=0x0
TX queue: 0
TX desc=0 - TX free threshold=0
TX threshold registers: pthresh=0 hthresh=0 wthresh=0 TX offloads=0x0 - TX RS bit threshold=0
Press enter to exitCould you paste your whole failure log here?
Quoted 4 lines
I'm using Linux 5.1-rc6 and an up to date libbpf. The setup works for the first device and fails for the second device when creating bpf maps in libbpf ("
qidconf_map" or "xsks_map"). It seems, that these maps also need unique names and cannot exist twice under the same name.So far as I know, there should not be such contraint, the bpf maps creations are wrapped in libbpf.
Quoted 8 lines
Furthermore if running step 3 again after it failed for the first time, xdp vdev allocation already fails for the first xdp vdev and does not reach the second one. Please let me know if you need some program output or more information from me.
Best regards,
MarkusThanks,
XiaolongQuoted 16 lines · Ye Xiaolong
Quoted 15 lines
Hi, Markus
Quoted 4 lines · Markus Theil
I tested the new
af_xdpbased device on the current master branch and noticed, that the usage of static mempool names allows only for the creation of a singleaf_xdpvdev. If a second vdev of the same type gets created, the mempool allocation fails.Thanks for reporting, could you paste the cmdline you used and the error log? Are you referring to ring creation or mempool creation?
Thanks,
XiaolongQuoted 2 lines
Best regards,
Markus Theil
PATCH 1/2 net/af_xdp: name the buf ring dynamically
In reply to Markus TheilNaming the buf_ring dynamically allows to create multiple af_xdp vdevs.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +6 -3
@@ -473,7 +473,7 @@ xdp_umem_destroy(struct xsk_umem_info *umem) }static struct -xsk_umem_info *xdp_umem_configure (void ) +xsk_umem_info *xdp_umem_configure (struct pmd_internals *internals) {struct xsk_umem_info *umem;const struct rte_memzone *mz;
@@ -482,6 +482,7 @@ xsk_umem_info *xdp_umem_configure(void) .comp_size = ETH_AF_XDP_DFLT_NUM_DESCS, .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM }; +char ring_name[RTE_RING_NAMESIZE ];int ret;uint64_t i;
@@ -491,7 +492,9 @@ xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->buf_ring =rte_ring_create ("af_xdp_ring" , + ret =snprintf (ring_name,sizeof (ring_name),"af_xdp_ring_%s_%d" , + internals->if_name, internals->queue_idx); + umem->buf_ring =rte_ring_create (ring_name,ETH_AF_XDP_NUM_BUFFERS ,rte_socket_id (),0x0 );
@@ -541,7 +544,7 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,int ret =0 ;int reserve_size; - rxq->umem =xdp_umem_configure (); + rxq->umem =xdp_umem_configure (internals);if (rxq->umem ==NULL )return -ENOMEM ;
Signature · 1 line
2.17.1
PATCH 2/2 net/af_xdp: name the umem memzone dynamically
Naming the umem memzone dynamically allows to create multiple af_xdp vdevs.
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +4 -1
@@ -483,6 +483,7 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM };char ring_name[RTE_RING_NAMESIZE ]; +char mz_name[RTE_MEMZONE_NAMESIZE ];int ret;uint64_t i;
@@ -508,7 +509,9 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) (void *)(i *ETH_AF_XDP_FRAME_SIZE + ETH_AF_XDP_DATA_HEADROOM)); - mz =rte_memzone_reserve_aligned ("af_xdp uemem" , + ret =snprintf (mz_name,sizeof (mz_name),"af_xdp_umem_%s_%d" , + internals->if_name, internals->queue_idx); + mz =rte_memzone_reserve_aligned (mz_name,ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE ,rte_socket_id (),RTE_MEMZONE_IOVA_CONTIG ,getpagesize ());
Signature · 1 line
2.17.1
Re: [dpdk-dev] [PATCH v1 2/2] net/af_xdp: name the umem memzone dynamically
Quoted 25 lines · Xiaolong Ye
Naming the umem memzone dynamically allows to create multiple
af_xdpvdevs.Fixes f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")Reported-by Markus Theil <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)drivers/net/af_xdp/rte_eth_af_xdp.c +1
-0@@ -483,6 +483,7 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM };char ring_name[RTE_RING_NAMESIZE ]; +char mz_name[RTE_MEMZONE_NAMESIZE ];int ret;uint64_t i;
drivers/net/af_xdp/rte_eth_af_xdp.c xsk_umem_info *xdp_umem_configure(struct pmd_internals · line 515
Quoted 8 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +2
-1@@ -508,7 +509,9 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) (void *)(i * ETH_AF_XDP_FRAME_SIZE + ETH_AF_XDP_DATA_HEADROOM)); - mz = rte_memzone_reserve_aligned("af_xdp uemem", + ret =snprintf (mz_name,sizeof (mz_name),"af_xdp_umem_%s_%d" , + internals->if_name, internals->queue_idx);
Idem previous patch.
+ mz = rte_memzone_reserve_aligned(mz_name,
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +0
-1ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE ,rte_socket_id (),RTE_MEMZONE_IOVA_CONTIG , getpagesize()); --2.17.1
How about squashing those two patches as a single one ?
The issue is that you can't create multiple devices. Having the first one still leaves the issue.
Signature · 1 line
David Marchand
Re: [dpdk-dev] [PATCH v1 2/2] net/af_xdp: name the umem memzone dynamically
Quoted 46 lines · David Marchand
Quoted 25 lines · Xiaolong Ye
Naming the umem memzone dynamically allows to create multiple
af_xdpvdevs.Fixes f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")Reported-by Markus Theil <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)drivers/net/af_xdp/rte_eth_af_xdp.c +1
-0@@ -483,6 +483,7 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM };char ring_name[RTE_RING_NAMESIZE ]; +char mz_name[RTE_MEMZONE_NAMESIZE ];int ret;uint64_t i;drivers/net/af_xdp/rte_eth_af_xdp.c xsk_umem_info *xdp_umem_configure(struct pmd_internals · line 515
Quoted 8 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +2
-1@@ -508,7 +509,9 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) (void *)(i * ETH_AF_XDP_FRAME_SIZE + ETH_AF_XDP_DATA_HEADROOM)); - mz = rte_memzone_reserve_aligned("af_xdp uemem", + ret =snprintf (mz_name,sizeof (mz_name),"af_xdp_umem_%s_%d" , + internals->if_name, internals->queue_idx);Idem previous patch.
+ mz = rte_memzone_reserve_aligned(mz_name,
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +0
-1ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE ,rte_socket_id (),RTE_MEMZONE_IOVA_CONTIG , getpagesize()); --2.17.1
Quoted 4 lines
How about squashing those two patches as a single one ?
The issue is that you can't create multiple devices. Having the first one still leaves the issue.
+1 to squash. let me make a new version applying minor issues you pointed in other patch, squashing both and keeping your review tag.
Quoted 3 lines
Reviewed-by David Marchand <[email protected]>
Re: [dpdk-dev] [PATCH v1 2/2] net/af_xdp: name the umem memzone dynamically
Quoted 47 lines · Ferruh Yigit
Quoted 46 lines · David Marchand
Quoted 25 lines · Xiaolong Ye
Naming the umem memzone dynamically allows to create multiple
af_xdpvdevs.Fixes f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")Reported-by Markus Theil <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)drivers/net/af_xdp/rte_eth_af_xdp.c +1
-0@@ -483,6 +483,7 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM };char ring_name[RTE_RING_NAMESIZE ]; +char mz_name[RTE_MEMZONE_NAMESIZE ];int ret;uint64_t i;drivers/net/af_xdp/rte_eth_af_xdp.c xsk_umem_info *xdp_umem_configure(struct pmd_internals · line 515
Quoted 8 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +2
-1@@ -508,7 +509,9 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals) (void *)(i * ETH_AF_XDP_FRAME_SIZE + ETH_AF_XDP_DATA_HEADROOM)); - mz = rte_memzone_reserve_aligned("af_xdp uemem", + ret =snprintf (mz_name,sizeof (mz_name),"af_xdp_umem_%s_%d" , + internals->if_name, internals->queue_idx);Idem previous patch.
+ mz = rte_memzone_reserve_aligned(mz_name,
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +0
-1ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE ,rte_socket_id (),RTE_MEMZONE_IOVA_CONTIG , getpagesize()); --2.17.1
Quoted 7 lines
Quoted 4 lines
How about squashing those two patches as a single one ?
The issue is that you can't create multiple devices. Having the first one still leaves the issue.+1 to squash. let me make a new version applying minor issues you pointed in other patch, squashing both and keeping your review tag.
Thanks for doing the new patch.
Quoted 5 lines
Quoted 4 lines
Reviewed-by David Marchand <[email protected]>
Re: [dpdk-dev] [PATCH v1 1/2] net/af_xdp: name the buf ring dynamically
In reply to Xiaolong YeQuoted 33 lines · Xiaolong Ye
Naming the
buf_ringdynamically allows to create multipleaf_xdpvdevs.Fixes f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")Reported-by Markus Theil <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>--- drivers/net/af_xdp/rte_eth_af_xdp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)drivers/net/af_xdp/rte_eth_af_xdp.c +2
-1@@ -473,7 +473,7 @@ xdp_umem_destroy(struct xsk_umem_info *umem) }static struct -xsk_umem_info *xdp_umem_configure (void ) +xsk_umem_info *xdp_umem_configure (struct pmd_internals *internals) {struct xsk_umem_info *umem;const struct rte_memzone *mz;@@ -482,6 +482,7 @@ xsk_umem_info *xdp_umem_configure(void) .comp_size = ETH_AF_XDP_DFLT_NUM_DESCS, .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM }; +char ring_name[RTE_RING_NAMESIZE ];int ret;uint64_t i;
drivers/net/af_xdp/rte_eth_af_xdp.c xsk_umem_info *xdp_umem_configure(void) · line 497
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +2
-1@@ -491,7 +492,9 @@ xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->buf_ring = rte_ring_create("af_xdp_ring", + ret =snprintf (ring_name,sizeof (ring_name),"af_xdp_ring_%s_%d" , + internals->if_name, internals->queue_idx);
You can drop the ret assignment, you won't check it anyway. queue_idx is unsigned %d -> %u ?
+ umem->buf_ring = rte_ring_create(ring_name,
Quoted 14 lines
drivers/net/af_xdp/rte_eth_af_xdp.c +1
-2ETH_AF_XDP_NUM_BUFFERS ,rte_socket_id (), 0x0);@@ -541,7 +544,7 @@ xsk_configure(struct pmd_internals *internals, structpkt_rx_queue *rxq, int ret = 0;int reserve_size; - rxq->umem =xdp_umem_configure (); + rxq->umem =xdp_umem_configure (internals);if (rxq->umem ==NULL )return -ENOMEM ; --
Quoted 3 lines
2.17.1
Signature · 1 line
David Marchand
PATCH v2 1/1 net/af_xdp: fix creating multiple instance
In reply to Xiaolong YeFrom: Xiaolong Ye <[email protected]>
Naming the buf_ring and umem memzone dynamically allows to create multiple af_xdp vdevs.
---
v2:
* squashed buf_ring & memzone patches
* removed unused return value
* changed format specifier to unsigned
--- drivers/net/af_xdp/rte_eth_af_xdp.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
drivers/net/af_xdp/rte_eth_af_xdp.c +10 -4
@@ -473,7 +473,7 @@ xdp_umem_destroy(struct xsk_umem_info *umem) }static struct -xsk_umem_info *xdp_umem_configure (void ) +xsk_umem_info *xdp_umem_configure (struct pmd_internals *internals) {struct xsk_umem_info *umem;const struct rte_memzone *mz;
@@ -482,6 +482,8 @@ xsk_umem_info *xdp_umem_configure(void) .comp_size = ETH_AF_XDP_DFLT_NUM_DESCS, .frame_size = ETH_AF_XDP_FRAME_SIZE, .frame_headroom = ETH_AF_XDP_DATA_HEADROOM }; +char ring_name[RTE_RING_NAMESIZE ]; +char mz_name[RTE_MEMZONE_NAMESIZE ];int ret;uint64_t i;
@@ -491,7 +493,9 @@ xsk_umem_info *xdp_umem_configure(void)return NULL ; } - umem->buf_ring =rte_ring_create ("af_xdp_ring" , +snprintf (ring_name,sizeof (ring_name),"af_xdp_ring_%s_%u" , + internals->if_name, internals->queue_idx); + umem->buf_ring =rte_ring_create (ring_name,ETH_AF_XDP_NUM_BUFFERS ,rte_socket_id (),0x0 );
@@ -505,7 +509,9 @@ xsk_umem_info *xdp_umem_configure(void) (void *)(i *ETH_AF_XDP_FRAME_SIZE + ETH_AF_XDP_DATA_HEADROOM)); - mz =rte_memzone_reserve_aligned ("af_xdp uemem" , +snprintf (mz_name,sizeof (mz_name),"af_xdp_umem_%s_%u" , + internals->if_name, internals->queue_idx); + mz =rte_memzone_reserve_aligned (mz_name,ETH_AF_XDP_NUM_BUFFERS *ETH_AF_XDP_FRAME_SIZE ,rte_socket_id (),RTE_MEMZONE_IOVA_CONTIG ,getpagesize ());
@@ -541,7 +547,7 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,int ret =0 ;int reserve_size; - rxq->umem =xdp_umem_configure (); + rxq->umem =xdp_umem_configure (internals);if (rxq->umem ==NULL )return -ENOMEM ;
Signature · 1 line
2.20.1
Ferruh Yigit
AppliedRe: [dpdk-dev] [PATCH v2] net/af_xdp: fix creating multiple instance
Quoted 10 lines · Ferruh Yigit
From: Xiaolong Ye <[email protected]>
Naming the
buf_ringand umem memzone dynamically allows to create multipleaf_xdpvdevs.Fixes f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")Reported-by Markus Theil <[email protected]>Signed-off-by Xiaolong Ye <[email protected]>Reviewed-by David Marchand <[email protected]>
Applied to dpdk-next-net/master, thanks.
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Xiaolong YeQuoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]>
<...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 17
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +5
-0@@ -0,0 +1,956 @@ +/* SPDX-License-Identifier: BSD-3-Clause +* Copyright(c) 2019 Intel Corporation. +*/ +#include <bpf/bpf.h> +#include <xsk.h>
Under linux, both headers are in same 'bpf' folder, why one included as 'bpf/bpf.h' but other 'xsk.h'?
Perhaps this is not problem when headers are installed into system folders, but I am compiling using RTE_KERNELDIR, which used in Makefile as:
-I$(RTE_KERNELDIR)/tools/lib/bpf
This fails to find 'bpf/bpf.h'
Also for '-lbpf', shouldn't need to add '-L$(RTE_KERNELDIR)/tools/lib/bpf', to new added line in 'rte.app.mk', so that it can find the library?
I assume you are building in a system with new kernel, I think you need this for functionality, where 'xsk.h' is located in that case? Because I was thinking building and installing libbpf can solve the issue but it is not installing 'xsk.h', not sure why, so not exactly solving.
if you still need "CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf" for your case, does it make sense update as following:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib
#include <bpf/xsk.h>
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 26 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 17
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +5
-0@@ -0,0 +1,956 @@ +/* SPDX-License-Identifier: BSD-3-Clause +* Copyright(c) 2019 Intel Corporation. +*/ +#include <bpf/bpf.h> +#include <xsk.h> Under linux, both headers are in same 'bpf' folder, why one included as '
bpf/bpf.h' but other 'xsk.h'?
Quoted 3 lines
Perhaps this is not problem when headers are installed into system folders, but I am compiling using
RTE_KERNELDIR, which used inMakefileas:
-I$(RTE_KERNELDIR)/tools/lib/bpf
When installed in system folders they will still need the "bpf" prefix. On my system after running "make headers_install" in libbpf folder, the headers are placed in "/usr/local/include/bpf/"
Quoted 11 lines
This fails to find '
bpf/bpf.h'Also for '-lbpf', shouldn't need to add '-L$(RTE_KERNELDIR)/tools/lib/bpf', to new added line in 'rte.app.mk', so that it can find the library?
I assume you are building in a system with new kernel, I think you need this for functionality, where '
xsk.h' is located in that case? Because I was thinking building and installing libbpf can solve the issue but it is not installing 'xsk.h', not sure why, so not exactly solving.
Quoted 4 lines
if you still need "CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf" for your case, does it make sense update as following:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib
#include <bpf/xsk.h>
We should not include in any driver a cflag or ldflag that points to the kernel dir. We should expect the headers for libbpf in a regular include folder and the library itself in /usr/lib or /usr/local/lib.
/Bruce
Re: [PATCH v9 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 27 lines · Bruce Richardson
Quoted 26 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
drivers/net/af_xdp/rte_eth_af_xdp.c line 17
Quoted 7 lines
drivers/net/af_xdp/rte_eth_af_xdp.c new file +5
-0@@ -0,0 +1,956 @@ +/* SPDX-License-Identifier: BSD-3-Clause +* Copyright(c) 2019 Intel Corporation. +*/ +#include <bpf/bpf.h> +#include <xsk.h> Under linux, both headers are in same 'bpf' folder, why one included as '
bpf/bpf.h' but other 'xsk.h'?
Quoted 7 lines
Quoted 3 lines
Perhaps this is not problem when headers are installed into system folders, but I am compiling using
RTE_KERNELDIR, which used inMakefileas:
-I$(RTE_KERNELDIR)/tools/lib/bpfWhen installed in system folders they will still need the "bpf" prefix. On my system after running "make
headers_install" in libbpf folder, the headers are placed in "/usr/local/include/bpf/"
This is for 'xsk.h' which was not installed via "make headers_install", but as Luca pointed out there is a patch to install 'xsk.h' too, so it should be OK to remove that line.
Quoted 12 lines
Quoted 12 lines
This fails to find '
bpf/bpf.h'Also for '-lbpf', shouldn't need to add '-L$(RTE_KERNELDIR)/tools/lib/bpf', to new added line in 'rte.app.mk', so that it can find the library?
I assume you are building in a system with new kernel, I think you need this for functionality, where '
xsk.h' is located in that case? Because I was thinking building and installing libbpf can solve the issue but it is not installing 'xsk.h', not sure why, so not exactly solving.
Quoted 8 lines
Quoted 4 lines
if you still need "CFLAGS += -I$(RTE_KERNELDIR)/tools/lib/bpf" for your case, does it make sense update as following:
CFLAGS += -I$(RTE_KERNELDIR)/tools/lib
#include <bpf/xsk.h>We should not include in any driver a cflag or ldflag that points to the kernel dir. We should expect the headers for libbpf in a regular include folder and the library itself in
/usr/libor/usr/local/lib.
Overall agree, but there is a dependency from 'xsk.h' to 'tools/include/asm/barrier.h', and this header file is not installed into system folders, it can be found only in kernel source code.
Hopefully it looks like there is a way to get rid of 'tools/include/asm/barrier.h' dependency for DPDK, so we can remove that cflags too.
v10 cover Introduce AF_XDP PMD
In reply to Xiaolong YeOverview
========
This patchset adds a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux, see below links [1] [2] for details of AF_XDP introduction:
AF_XDP roadmap
==============
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.
Change logs
===========
v10:
- refine the Makefile, remove RTE_KERNELDIR related CFLAGS
- add a new internal file af_xdp_deps.h to handle the dependency for asm/barrier.h
- fix a typo observed by Stephen
- rename xsk.h to bpf/xsk.h as xsk.h is assumed to be installed in /usr/local/include/bpf
- add libbpf build steps in af_xdp.rst
v9:
- adjust header files order according to Stephen's suggestion
v8:
- address Ferruh's comments on V7
- replace posix_memalign with rte_memzone_reserve_aligned to get better performance
- keep the first patch only as Oliver suggested as zero copy part implementation is still in suspense, we may provide the related patch later.
v7:
- mention mtu limitation in af_xdp.rst
- fix the vdev name in af_xdp.rst
V6:
- remove the newline in AF_XDP_LOG definition to avoid double new lines issue.
- rename MEMPOOL_F_PAGE_ALIGN to MEMPOOL_CHUNK_F_PAGE_ALIGN.
V5:
- disable AF_XDP pmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of Maxime
V4:
- change vdev name to net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by Stephen
V3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.
V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactor rte_mbuf.c to avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.
changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the AP_XDP uapi. After the rework, it helps to reduce 300+ lines of code.
- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls xsk_socket__create. userspace application only needs to handle the cleanup.
How to try
==========
1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support -->
Networking options -->
[ * ] XDP sockets
2. build & install libbpf in tools/lib/bpf
cd tools/lib/bpf
make install_lib
make install_headers
3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable AF_XDP pmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
5. start testpmd
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1
in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to af_xdp socket.
Xiaolong Ye (1):
net/af_xdp: introduce AF XDP PMD driver
MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 50 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 28 + drivers/net/af_xdp/af_xdp_deps.h | 14 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 955 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 14 files changed, 1105 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/af_xdp_deps.h create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 1 line
2.17.1
PATCH v10 1/1 net/af_xdp: introduce AF XDP PMD driver
Add a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 50 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 28 + drivers/net/af_xdp/af_xdp_deps.h | 14 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 955 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 14 files changed, 1105 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/af_xdp_deps.h create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +7 -0
@@ -489,6 +489,13 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/af_xdp.rst +F: doc/guides/nics/features/af_xdp.ini + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -430,6 +430,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +50 -0
50 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -74,6 +74,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +28 -0
@@ -0,0 +1,28 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += $(shell command -v pkg-config > /dev/null 2>&1 && pkg-config --libs libbpf || echo "-lbpf") + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/af_xdp_deps.h new file +14 -0
@@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: BSD-3-Clause +* Copyright(c) 2019 Intel Corporation. +*/ + +#ifndef AF_XDP_DEPS_H_ +#define AF_XDP_DEPS_H_ + +#include <rte_atomic.h> +#include <rte_branch_prediction.h> + +#define smp_rmb () rte_rmb() +#define smp_wmb () rte_wmb() + +#endif /* AF_XDP_DEPS_H_ */
drivers/net/af_xdp/meson.build new file +21 -0
@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif + +bpf_dep = dependency('libbpf', required: false) +if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false) + if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
drivers/net/af_xdp/rte_eth_af_xdp.c new file +955 -0
955 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 35 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to
[1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.[1]
https://fosdem.org/2018/schedule/event/af_xdp/[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Quoted 1 line
--- MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 50 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 28 + drivers/net/af_xdp/af_xdp_deps.h | 14 + drivers/net/af_xdp/meson.build | 21 + drivers/net/af_xdp/rte_eth_af_xdp.c | 955 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 +
Quoted 8 lines
14 files changed, 1105 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/af_xdp_deps.h create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Xiaolong YeQuoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]>
I am not able to test functionality but code looks good to me, I can compile via Makefile (with suggested steps in doc) but not able to build with meson, can you please check below comments?
<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endif
After this point, if build is false it shouldn't continue to below checks I think.
Review line 8
Quoted 2 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)
My library is in '/usr/local/lib64/libbpf.so' but this line can't find it. Where does 'dependency()' checks for libraries?
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)
Also this line can't find it, in log it says "(tried pkgconfig and cmake)" and yes there is no pkgconfig for it, any idea how 'cmake' used?
drivers/net/af_xdp/meson.build line 13
Quoted 1 line
drivers/net/af_xdp/meson.build new file +1
-0+ if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h')
Should this be 'lib/xsk.h' now?
Quoted 8 lines
drivers/net/af_xdp/meson.build new file +8
-0+ build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 41 lines · Ferruh Yigit
Quoted 13 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.Quoted 7 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Quoted 1 line
I am not able to test functionality but code looks good to me, I can compile via
Makefile(with suggested steps in doc) but not able to build with meson, can you
please check below comments?<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endifAfter this point, if build is false it shouldn't continue to below checks I think.
Quoted 6 lines
Review line 8
Quoted 2 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)My library is in '
/usr/local/lib64/libbpf.so' but this line can't find it. Where
does 'dependency()' checks for libraries?
dependency() uses only pkg-config (or cmake or embedded specific tools, neither of which applies to bpf), so if you haven't built from bpf-next you won't have the pkg-config file installed, and it will fall back to the next block.
Side note, there's an issue open upstream in Meson to merge dependency() and find_library(), with some traction but it's not done yet.
For me building from bpf-next it works fine:
$ PKG_CONFIG_PATH=/tmp/bpf/lib64/pkgconfig/ ninja -C build-gcc-shared
...
Dependency libbpf found: YES 0.0.2
...
$ lddtree build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1
librte_pmd_af_xdp.so.1.1 => build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 (interpreter => none)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2
libnuma.so.1 => /lib/x86_64-linux-gnu/libnuma.so.1
librte_ethdev.so.12 => build-gcc-shared/drivers/../lib/librte_ethdev.so.12
librte_eal.so.10 => build-gcc-shared/drivers/../lib/librte_eal.so.10
librte_kvargs.so.1 => build-gcc-shared/drivers/../lib/librte_kvargs.so.1
librte_net.so.1 => build-gcc-shared/drivers/../lib/librte_net.so.1
librte_mbuf.so.5 => build-gcc-shared/drivers/../lib/librte_mbuf.so.5
librte_mempool.so.5 => build-gcc-shared/drivers/../lib/librte_mempool.so.5
librte_ring.so.2 => build-gcc-shared/drivers/../lib/librte_ring.so.2
librte_cmdline.so.2 => build-gcc-shared/drivers/../lib/librte_cmdline.so.2
librte_meter.so.2 => build-gcc-shared/drivers/../lib/librte_meter.so.2
librte_bus_pci.so.2 => not found
librte_pci.so.1 => build-gcc-shared/drivers/../lib/librte_pci.so.1
librte_bus_vdev.so.2 => not found
libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1
libbpf.so.0 => /tmp/bpf/lib64/libbpf.so.0
libelf.so.1 => /lib/x86_64-linux-gnu/libelf.so.1
libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6
ld-linux-x86-64.so.2 => /lib/x86_64-linux-gnu/ld-linux-x86-64.so.2Quoted 8 lines
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)Also this line can't find it, in log it says "(tried pkgconfig and cmake)" and
yes there is no pkgconfig for it, any idea how 'cmake' used?
The issue here is that it should be cc.find_library('bpf' - not 'libbpf'. I missed this when reviewing, good catch.
That's because find_library just does a compilation test passing the value to the compiler as a linker flag - so right now it's passing -llibbpf. Fixing this line and the header line below makes it work without pkg-config:
$ CPPFLAGS=-I/tmp/bpf/include LDFLAGS=-L/tmp/bpf/lib64 meson testt ... Dependency libbpf found: NO (tried pkgconfig and cmake) Library bpf found: YES
Quoted 4 lines
Quoted 2 lines
(quoted diff) +1
-0+ if bpf_dep.found() and cc.has_header('xsk.h', dependencies:
bpf_dep) andcc.has_header('linux/if_xdp.h')Should this be '
lib/xsk.h' now?
Yes, this should be 'bpf/xsk.h'
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 107 lines · Luca Boccassi
Quoted 41 lines · Ferruh Yigit
Quoted 13 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.Quoted 7 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Quoted 1 line
I am not able to test functionality but code looks good to me, I can compile via
Makefile(with suggested steps in doc) but not able to build with meson, can you
please check below comments?<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endifAfter this point, if build is false it shouldn't continue to below checks I think.
Quoted 6 lines
Review line 8
Quoted 2 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)My library is in '
/usr/local/lib64/libbpf.so' but this line can't find it. Where
does 'dependency()' checks for libraries?
dependency()uses only pkg-config (or cmake or embedded specific tools, neither of which applies to bpf), so if you haven't built from bpf-next you won't have the pkg-config file installed, and it will fall back to the next block.Side note, there's an issue open upstream in Meson to merge
dependency()andfind_library(), with some traction but it's not done yet.For me building from bpf-next it works fine:
$ PKG_CONFIG_PATH=/tmp/bpf/lib64/pkgconfig/ ninja -C build-gcc-shared ... Dependency libbpf found: YES 0.0.2 ... $ lddtree build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 librte_pmd_af_xdp.so.1.1 => build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 (interpreter => none) libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 libnuma.so.1 => /lib/x86_64-linux-gnu/libnuma.so.1 librte_ethdev.so.12 => build-gcc-shared/drivers/../lib/librte_ethdev.so.12 librte_eal.so.10 => build-gcc-shared/drivers/../lib/librte_eal.so.10 librte_kvargs.so.1 => build-gcc-shared/drivers/../lib/librte_kvargs.so.1 librte_net.so.1 => build-gcc-shared/drivers/../lib/librte_net.so.1 librte_mbuf.so.5 => build-gcc-shared/drivers/../lib/librte_mbuf.so.5 librte_mempool.so.5 => build-gcc-shared/drivers/../lib/librte_mempool.so.5 librte_ring.so.2 => build-gcc-shared/drivers/../lib/librte_ring.so.2 librte_cmdline.so.2 => build-gcc-shared/drivers/../lib/librte_cmdline.so.2 librte_meter.so.2 => build-gcc-shared/drivers/../lib/librte_meter.so.2 librte_bus_pci.so.2 => not found librte_pci.so.1 => build-gcc-shared/drivers/../lib/librte_pci.so.1 librte_bus_vdev.so.2 => not found libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 libbpf.so.0 => /tmp/bpf/lib64/libbpf.so.0 libelf.so.1 => /lib/x86_64-linux-gnu/libelf.so.1 libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 ld-linux-x86-64.so.2 => /lib/x86_64-linux-gnu/ld-linux-x86-64.so.2Quoted 8 lines
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)Also this line can't find it, in log it says "(tried pkgconfig and cmake)" and
yes there is no pkgconfig for it, any idea how 'cmake' used?The issue here is that it should be cc.find_library('bpf' - not 'libbpf'. I missed this when reviewing, good catch.
That's because
find_libraryjust does a compilation test passing the value to the compiler as a linker flag - so right now it's passing -llibbpf. Fixing this line and the header line below makes it work without pkg-config:
Quoted 4 lines
$ CPPFLAGS=-I/tmp/bpf/include LDFLAGS=-L/tmp/bpf/lib64 meson testt ... Dependency libbpf found: NO (tried pkgconfig and cmake) Library bpf found: YES
Thanks for pointing out, will adopt it.
Quoted 7 lines
Quoted 5 lines
Quoted 3 lines
(quoted diff) +1
-0+ if bpf_dep.found() and cc.has_header('xsk.h', dependencies:
bpf_dep) andcc.has_header('linux/if_xdp.h')Should this be '
lib/xsk.h' now?Yes, this should be '
bpf/xsk.h'
Will change it in next version.
Thanks,
Xiaolong
Quoted 4 lines
Signature · 3 lines
-- Kind regards, Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Luca BoccassiHi, Luca
Quoted 107 lines · Luca Boccassi
Quoted 41 lines · Ferruh Yigit
Quoted 13 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.Quoted 7 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Quoted 1 line
I am not able to test functionality but code looks good to me, I can compile via
Makefile(with suggested steps in doc) but not able to build with meson, can you
please check below comments?<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endifAfter this point, if build is false it shouldn't continue to below checks I think.
Quoted 6 lines
Review line 8
Quoted 2 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)My library is in '
/usr/local/lib64/libbpf.so' but this line can't find it. Where
does 'dependency()' checks for libraries?
dependency()uses only pkg-config (or cmake or embedded specific tools, neither of which applies to bpf), so if you haven't built from bpf-next you won't have the pkg-config file installed, and it will fall back to the next block.Side note, there's an issue open upstream in Meson to merge
dependency()andfind_library(), with some traction but it's not done yet.For me building from bpf-next it works fine:
$ PKG_CONFIG_PATH=/tmp/bpf/lib64/pkgconfig/ ninja -C build-gcc-shared ... Dependency libbpf found: YES 0.0.2 ... $ lddtree build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 librte_pmd_af_xdp.so.1.1 => build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 (interpreter => none) libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 libnuma.so.1 => /lib/x86_64-linux-gnu/libnuma.so.1 librte_ethdev.so.12 => build-gcc-shared/drivers/../lib/librte_ethdev.so.12 librte_eal.so.10 => build-gcc-shared/drivers/../lib/librte_eal.so.10 librte_kvargs.so.1 => build-gcc-shared/drivers/../lib/librte_kvargs.so.1 librte_net.so.1 => build-gcc-shared/drivers/../lib/librte_net.so.1 librte_mbuf.so.5 => build-gcc-shared/drivers/../lib/librte_mbuf.so.5 librte_mempool.so.5 => build-gcc-shared/drivers/../lib/librte_mempool.so.5 librte_ring.so.2 => build-gcc-shared/drivers/../lib/librte_ring.so.2 librte_cmdline.so.2 => build-gcc-shared/drivers/../lib/librte_cmdline.so.2 librte_meter.so.2 => build-gcc-shared/drivers/../lib/librte_meter.so.2 librte_bus_pci.so.2 => not found librte_pci.so.1 => build-gcc-shared/drivers/../lib/librte_pci.so.1 librte_bus_vdev.so.2 => not found libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 libbpf.so.0 => /tmp/bpf/lib64/libbpf.so.0 libelf.so.1 => /lib/x86_64-linux-gnu/libelf.so.1 libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 ld-linux-x86-64.so.2 => /lib/x86_64-linux-gnu/ld-linux-x86-64.so.2Quoted 8 lines
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)Also this line can't find it, in log it says "(tried pkgconfig and cmake)" and
yes there is no pkgconfig for it, any idea how 'cmake' used?The issue here is that it should be cc.find_library('bpf' - not 'libbpf'. I missed this when reviewing, good catch.
That's because
find_libraryjust does a compilation test passing the value to the compiler as a linker flag - so right now it's passing -llibbpf. Fixing this line and the header line below makes it work without pkg-config:
Quoted 4 lines
$ CPPFLAGS=-I/tmp/bpf/include LDFLAGS=-L/tmp/bpf/lib64 meson testt ... Dependency libbpf found: NO (tried pkgconfig and cmake) Library bpf found: YES
After apply the fix in af_xdp pmd's meson.build, now I was able to build library for af_xdp pmd.
$ ls drivers/ |grep xdp a715181@@rte_pmd_af_xdp@sha a715181@@rte_pmd_af_xdp@sta a715181@@tmp_rte_pmd_af_xdp@sta librte_pmd_af_xdp.a librte_pmd_af_xdp.so librte_pmd_af_xdp.so.1 librte_pmd_af_xdp.so.1.1 libtmp_rte_pmd_af_xdp.a rte_pmd_af_xdp.pmd.c
But I found that if I install libbpf to /usr/local/lib64 by default, application built by meson build will fail to run:
$ ./dpdk-testpmd ./dpdk-testpmd: error while loading shared libraries: libbpf.so.0: cannot open shared object file: No such file or directory
While install libbpf to /usr/lib doesn't have this issue (I was testing on ubuntu system). Is it a expected behavior? Do we need any fix for it?
Thanks,
Xiaolong
Quoted 11 lines
Quoted 5 lines
Quoted 3 lines
(quoted diff) +1
-0+ if bpf_dep.found() and cc.has_header('xsk.h', dependencies:
bpf_dep) andcc.has_header('linux/if_xdp.h')Should this be '
lib/xsk.h' now?Yes, this should be '
bpf/xsk.h'Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 143 lines
-----Original Message-----
From: dev <[email protected]> On Behalf Of Ye Xiaolong
Sent: Thursday, April 4, 2019 1:55 PM
To: Ferruh Yigit <[email protected]>; Luca Boccassi <[email protected]>
Cc: [email protected]; Stephen Hemminger <[email protected]>; Qi Zhang <[email protected]>; Karlsson Magnus <[email protected]>; Topel Bjorn <[email protected]>; Maxime Coquelin <[email protected]>; Bruce Richardson <[email protected]>; Ananyev Konstantin <[email protected]>; David Marchand <[email protected]>; Andrew Rybchenko <[email protected]>; Olivier Matz <[email protected]>
Subject: Re: [dpdk-dev] [PATCH v10 1/1]net/af_xdp: introduce AF XDP PMD driverHi, Luca
Quoted 52 lines · Luca Boccassi
Quoted 36 lines · Ferruh Yigit
Quoted 10 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
Quoted 7 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Quoted 1 line
I am not able to test functionality but code looks good to me, I can compile via
Makefile(with suggested steps in doc) but not able to build with meson, can you please check below comments?<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause # Copyright(c) 2019 Intel +Corporation + +if host_machine.system() != 'linux' + build = false +endifAfter this point, if build is false it shouldn't continue to below checks I think.
Quoted 5 lines
Review line 8
Quoted 2 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)My library is in '
/usr/local/lib64/libbpf.so' but this line can't find it. Where does 'dependency()' checks for libraries?
dependency()uses only pkg-config (or cmake or embedded specific tools, neither of which applies to bpf), so if you haven't built from bpf-next you won't have the pkg-config file installed, and it will fall back to the next block.Side note, there's an issue open upstream in Meson to merge
dependency()andfind_library(), with some traction but it's not done yet.Quoted 8 lines
For me building from bpf-next it works fine:
$ PKG_CONFIG_PATH=/tmp/bpf/lib64/pkgconfig/ ninja -C build-gcc-shared ... Dependency libbpf found: YES 0.0.2 ... $ lddtree build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 librte_pmd_af_xdp.so.1.1 => build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 (interpreter => none)
Quoted 4 lines
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 libnuma.so.1 => /lib/x86_64-linux-gnu/libnuma.so.1 librte_ethdev.so.12 => build-gcc-shared/drivers/../lib/librte_ethdev.so.12
Quoted 5 lines
librte_eal.so.10 => build-gcc-shared/drivers/../lib/librte_eal.so.10 librte_kvargs.so.1 => build-gcc-shared/drivers/../lib/librte_kvargs.so.1 librte_net.so.1 => build-gcc-shared/drivers/../lib/librte_net.so.1 librte_mbuf.so.5 => build-gcc-shared/drivers/../lib/librte_mbuf.so.5 librte_mempool.so.5 => build-gcc-shared/drivers/../lib/librte_mempool.so.5
Quoted 27 lines
librte_ring.so.2 => build-gcc-shared/drivers/../lib/librte_ring.so.2 librte_cmdline.so.2 => build-gcc-shared/drivers/../lib/librte_cmdline.so.2 librte_meter.so.2 => build-gcc-shared/drivers/../lib/librte_meter.so.2 librte_bus_pci.so.2 => not found librte_pci.so.1 => build-gcc-shared/drivers/../lib/librte_pci.so.1 librte_bus_vdev.so.2 => not found libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 libbpf.so.0 => /tmp/bpf/lib64/libbpf.so.0 libelf.so.1 => /lib/x86_64-linux-gnu/libelf.so.1 libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 ld-linux-x86-64.so.2 => /lib/x86_64-linux-gnu/ld-linux-x86-64.so.2Quoted 8 lines
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)Also this line can't find it, in log it says "(tried pkgconfig and cmake)" and yes there is no pkgconfig for it, any idea how 'cmake' used?
The issue here is that it should be cc.find_library('bpf' - not 'libbpf'. I missed this when reviewing, good catch.
Quoted 8 lines
That's because
find_libraryjust does a compilation test passing the value to the compiler as a linker flag - so right now it's passing -llibbpf. Fixing this line and the header line below makes it work without pkg-config:$ CPPFLAGS=-I/tmp/bpf/include LDFLAGS=-L/tmp/bpf/lib64 meson testt ... Dependency libbpf found: NO (tried pkgconfig and cmake) Library bpf found: YESAfter apply the fix in
af_xdppmd's meson.build, now I was able to build library foraf_xdppmd.$ ls drivers/ |grep xdp a715181@@rte_pmd_af_xdp@sha a715181@@rte_pmd_af_xdp@sta a715181@@tmp_rte_pmd_af_xdp@sta librte_pmd_af_xdp.a librte_pmd_af_xdp.so librte_pmd_af_xdp.so.1 librte_pmd_af_xdp.so.1.1 libtmp_rte_pmd_af_xdp.a rte_pmd_af_xdp.pmd.cBut I found that if I install libbpf to
/usr/local/lib64by default, application built by meson build will fail to run:
Quoted 7 lines
$ ./dpdk-testpmd ./dpdk-testpmd: error while loading shared libraries: libbpf.so.0: cannot open shared object file: No such file or directoryWhile install libbpf to
/usr/libdoesn't have this issue (I was testing on ubuntu system).
Is it a expected behavior? Do we need any fix for it?
Hi, Xiaolong
I have encountered the same issue on ubuntu-arm64-server with Kernel v5.1.0-rc3+. If I read correctly, I think Luca's patch can solve this issue.
https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=dd399ac9e343c7573c47d6820e4a23013c54749d
So, will this patch in v5.1-rc4 ?
Thanks,
Phil
Quoted 14 lines
Thanks,
XiaolongQuoted 11 lines
Quoted 5 lines
Quoted 3 lines
(quoted diff) +1
-0+ if bpf_dep.found() and cc.has_header('xsk.h', dependencies:
bpf_dep) andcc.has_header('linux/if_xdp.h')Should this be '
lib/xsk.h' now?Yes, this should be '
bpf/xsk.h'--
Kind regards,
Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Ye XiaolongQuoted 159 lines · Ye Xiaolong
Hi, Luca
Quoted 132 lines · Luca Boccassi
Quoted 47 lines · Ferruh Yigit
Quoted 16 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version
ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer
to [1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.Quoted 8 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]I am not able to test functionality but code looks good to me, I can
compile viaMakefile(with suggested steps in doc) but not able to build with meson, can you
please check below comments?<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endifAfter this point, if build is false it shouldn't continue to below
checks I think.Quoted 6 lines
Review line 8
Quoted 2 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)My library is in '
/usr/local/lib64/libbpf.so' but this line can't find it. Where
does 'dependency()' checks for libraries?
dependency()uses only pkg-config (or cmake or embedded specific tools,
neither of which applies to bpf), so if you haven't built from bpf- next
you won't have the pkg-config file installed, and it will fall back to
the next block.Side note, there's an issue open upstream in Meson to merge
dependency()andfind_library(), with some traction but it's not done
yet.For me building from bpf-next it works fine:
$ PKG_CONFIG_PATH=/tmp/bpf/lib64/pkgconfig/ ninja -C build-gcc- shared ... Dependency libbpf found: YES 0.0.2 ... $ lddtree build-gcc-shared/drivers/librte_pmd_af_xdp.so.1.1 librte_pmd_af_xdp.so.1.1 => build-gcc- shared/drivers/librte_pmd_af_xdp.so.1.1 (interpreter => none) libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 libnuma.so.1 => /lib/x86_64-linux-gnu/libnuma.so.1 librte_ethdev.so.12 => build-gcc- shared/drivers/../lib/librte_ethdev.so.12 librte_eal.so.10 => build-gcc- shared/drivers/../lib/librte_eal.so.10 librte_kvargs.so.1 => build-gcc- shared/drivers/../lib/librte_kvargs.so.1 librte_net.so.1 => build-gcc- shared/drivers/../lib/librte_net.so.1 librte_mbuf.so.5 => build-gcc- shared/drivers/../lib/librte_mbuf.so.5 librte_mempool.so.5 => build-gcc- shared/drivers/../lib/librte_mempool.so.5 librte_ring.so.2 => build-gcc- shared/drivers/../lib/librte_ring.so.2 librte_cmdline.so.2 => build-gcc- shared/drivers/../lib/librte_cmdline.so.2 librte_meter.so.2 => build-gcc- shared/drivers/../lib/librte_meter.so.2 librte_bus_pci.so.2 => not found librte_pci.so.1 => build-gcc- shared/drivers/../lib/librte_pci.so.1 librte_bus_vdev.so.2 => not found libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 libbpf.so.0 => /tmp/bpf/lib64/libbpf.so.0 libelf.so.1 => /lib/x86_64-linux-gnu/libelf.so.1 libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 ld-linux-x86-64.so.2 => /lib/x86_64-linux-gnu/ld-linux-x86- 64.so.2Quoted 9 lines
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)Also this line can't find it, in log it says "(tried pkgconfig and
cmake)" and
yes there is no pkgconfig for it, any idea how 'cmake' used?The issue here is that it should be cc.find_library('bpf' - not 'libbpf'. I missed this when reviewing, good catch.
That's because
find_libraryjust does a compilation test passing the
value to the compiler as a linker flag - so right now it's passing -llibbpf. Fixing this line and the header line below makes it work without pkg-config:Quoted 4 lines
$ CPPFLAGS=-I/tmp/bpf/include LDFLAGS=-L/tmp/bpf/lib64 meson testt ... Dependency libbpf found: NO (tried pkgconfig and cmake) Library bpf found: YESAfter apply the fix in
af_xdppmd's meson.build, now I was able to build
library foraf_xdppmd.$ ls drivers/ |grep xdp a715181@@rte_pmd_af_xdp@sha a715181@@rte_pmd_af_xdp@sta a715181@@tmp_rte_pmd_af_xdp@sta librte_pmd_af_xdp.a librte_pmd_af_xdp.so librte_pmd_af_xdp.so.1 librte_pmd_af_xdp.so.1.1 libtmp_rte_pmd_af_xdp.a rte_pmd_af_xdp.pmd.cBut I found that if I install libbpf to
/usr/local/lib64by default, application
built by meson build will fail to run:
Quoted 7 lines
$ ./dpdk-testpmd ./dpdk-testpmd: error while loading shared libraries: libbpf.so.0: cannot open shared object file: No such file or directoryWhile install libbpf to
/usr/libdoesn't have this issue (I was testing on ubuntu system).
Is it a expected behavior? Do we need any fix for it?
Hi,
That is expected and distro specific: if your distro doesn't add /usr/local/lib* to the compiler path, it also won't be in the LD_LIBRARY_PATH.
So if you do:
LD_LIBRARY_PATH=/usr/local/lib64 ./dpdk-testpmd
It should then work. It's not related to the build system, but just to what the default paths are in the distro.
Signature · 2 lines
Kind regards, Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 30 lines · Luca Boccassi
Quoted 20 lines
After apply the fix in
af_xdppmd's meson.build, now I was able to build
library foraf_xdppmd.$ ls drivers/ |grep xdp a715181@@rte_pmd_af_xdp@sha a715181@@rte_pmd_af_xdp@sta a715181@@tmp_rte_pmd_af_xdp@sta librte_pmd_af_xdp.a librte_pmd_af_xdp.so librte_pmd_af_xdp.so.1 librte_pmd_af_xdp.so.1.1 libtmp_rte_pmd_af_xdp.a rte_pmd_af_xdp.pmd.cBut I found that if I install libbpf to
/usr/local/lib64by default, application
built by meson build will fail to run:Quoted 7 lines
$ ./dpdk-testpmd ./dpdk-testpmd: error while loading shared libraries: libbpf.so.0: cannot open shared object file: No such file or directoryWhile install libbpf to
/usr/libdoesn't have this issue (I was testing on ubuntu system).
Is it a expected behavior? Do we need any fix for it?Hi,
Quoted 7 lines
That is expected and distro specific: if your distro doesn't add
/usr/local/lib*to the compiler path, it also won't be in theLD_LIBRARY_PATH.So if you do:
LD_LIBRARY_PATH=/usr/local/lib64 ./dpdk-testpmd
Yes, it does work for me.
Quoted 3 lines
It should then work. It's not related to the build system, but just to what the default paths are in the distro.
Thanks for confirmation, then I can send my v11 out :)
Thanks,
Xiaolong
Quoted 4 lines
Signature · 3 lines
-- Kind regards, Luca Boccassi
Re: [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Ferruh YigitHi, Ferruh
Quoted 8 lines · Ferruh Yigit
Quoted 7 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
Quoted 9 lines
Quoted 4 lines
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]>I am not able to test functionality but code looks good to me, I can compile via
Makefile(with suggested steps in doc) but not able to build with meson, can you please check below comments?
My bad, sorry for not testing out meson build.
Quoted 11 lines
<...>
drivers/net/af_xdp/meson.build line 6
Quoted 7 lines
drivers/net/af_xdp/meson.build new file +6
-0@@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() != 'linux' + build = false +endifAfter this point, if build is false it shouldn't continue to below checks I think.
Make sense, will do.
Quoted 7 lines
Review line 8
Quoted 3 lines
(quoted diff) +2
-0+ +bpf_dep = dependency('libbpf', required: false)My library is in '
/usr/local/lib64/libbpf.so' but this line can't find it. Where does 'dependency()' checks for libraries?
Quoted 7 lines
drivers/net/af_xdp/meson.build line 12
Quoted 4 lines
drivers/net/af_xdp/meson.build new file +4
-0+if bpf_dep.found() + build = true +else + bpf_dep = cc.find_library('libbpf', required: false)Also this line can't find it, in log it says "(tried pkgconfig and cmake)" and yes there is no pkgconfig for it, any idea how 'cmake' used?
As Luca said, it should be cc.find_library('bpf', required: false), will correct it in next version.
Quoted 4 lines
drivers/net/af_xdp/meson.build line 13
Quoted 2 lines
drivers/net/af_xdp/meson.build new file +1
-0+ if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h')Should this be '
lib/xsk.h' now?
Will change to bpf/xsk.h in next version.
Thanks,
Xiaolong
Quoted 10 lines
Quoted 9 lines
drivers/net/af_xdp/meson.build new file +8
-0+ build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif +endif +sources = files('rte_eth_af_xdp.c') +ext_deps += bpf_dep
v11 cover Introduce AF_XDP PMD
In reply to Xiaolong YeOverview
========
This patchset adds a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux, see below links [1] [2] for details of AF_XDP introduction:
AF_XDP roadmap
==============
- AF_XDP is included in upstream kernel since 4.18, and AF_XDP support in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.
Change logs
===========
v11:
- fix the meson build issue
v10:
- refine the Makefile, remove RTE_KERNELDIR related CFLAGS
- add a new internal file af_xdp_deps.h to handle the dependency for asm/barrier.h
- fix a typo observed by Stephen
- rename xsk.h to bpf/xsk.h as xsk.h is assumed to be installed in /usr/local/include/bpf
- add libbpf build steps in af_xdp.rst
v9:
- adjust header files order according to Stephen's suggestion
v8:
- address Ferruh's comments on V7
- replace posix_memalign with rte_memzone_reserve_aligned to get better performance
- keep the first patch only as Oliver suggested as zero copy part implementation is still in suspense, we may provide the related patch later.
v7:
- mention mtu limitation in af_xdp.rst
- fix the vdev name in af_xdp.rst
V6:
- remove the newline in AF_XDP_LOG definition to avoid double new lines issue.
- rename MEMPOOL_F_PAGE_ALIGN to MEMPOOL_CHUNK_F_PAGE_ALIGN.
V5:
- disable AF_XDP pmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of Maxime
V4:
- change vdev name to net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by Stephen
V3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.
V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactor rte_mbuf.c to avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.
changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the AP_XDP uapi. After the rework, it helps to reduce 300+ lines of code.
- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls xsk_socket__create. userspace application only needs to handle the cleanup.
How to try
==========
1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support -->
Networking options -->
[ * ] XDP sockets
2. build & install libbpf in tools/lib/bpf
cd tools/lib/bpf
make install_lib
make install_headers
3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable AF_XDP pmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
5. start testpmd
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1
in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to af_xdp socket.
Xiaolong Ye (1):
net/af_xdp: introduce AF XDP PMD driver
MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 50 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 28 + drivers/net/af_xdp/af_xdp_deps.h | 15 + drivers/net/af_xdp/meson.build | 19 + drivers/net/af_xdp/rte_eth_af_xdp.c | 955 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 14 files changed, 1104 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/af_xdp_deps.h create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 1 line
2.17.1
PATCH v11 1/1 net/af_xdp: introduce AF XDP PMD driver
Add a new PMD driver for AF_XDP which is a proposed faster version of AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1] [2].
This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/
--- MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 50 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 28 + drivers/net/af_xdp/af_xdp_deps.h | 15 + drivers/net/af_xdp/meson.build | 19 + drivers/net/af_xdp/rte_eth_af_xdp.c | 955 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 + 14 files changed, 1104 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/af_xdp_deps.h create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
MAINTAINERS +7 -0
@@ -489,6 +489,13 @@ M: John W. Linville <[email protected]> F: drivers/net/af_packet/ F: doc/guides/nics/features/afpacket.ini +Linux AF_XDP +M: Xiaolong Ye <[email protected]> +M: Qi Zhang <[email protected]> +F: drivers/net/af_xdp/ +F: doc/guides/nics/af_xdp.rst +F: doc/guides/nics/features/af_xdp.ini + Amazon ENA M: Marcin Wojtas <[email protected]> M: Michal Krawczyk <[email protected]>
config/common_base +5 -0
@@ -430,6 +430,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n # CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n +# +# Compile software PMD backed by AF_XDP sockets (Linux only) +# +CONFIG_RTE_LIBRTE_PMD_AF_XDP=n + # # Compile link bonding PMD library #
doc/guides/nics/af_xdp.rst new file +50 -0
50 lines not on this page · raw message
doc/guides/nics/features/af_xdp.ini new file +11 -0
@@ -0,0 +1,11 @@ +; +; Supported features of the 'af_xdp' network poll mode driver. +; +; Refer to default.ini for the full list of available PMD features. +; +[Features] +Link status = Y +MTU update = Y +Promiscuous mode = Y +Stats per queue = Y +x86-64 = Y
doc/guides/nics/index.rst +1 -0
@@ -12,6 +12,7 @@ Network Interface Controller Drivers features build_and_test af_packet + af_xdp ark atlantic avp
doc/guides/rel_notes/release_19_05.rst +7 -0
@@ -74,6 +74,13 @@ New Features process. * Added support for Rx packet types list in a secondary process. +* **Added the AF_XDP PMD.** + + Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket + and bind it to a specific netdev queue, it allows a DPDK application to send + and receive raw packets through the socket which would bypass the kernel + network stack to achieve high performance packet processing. + * **Updated Mellanox drivers.** New features and improvements were done in mlx4 and mlx5 PMDs:
drivers/net/Makefile +1 -0
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d) endif DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet +DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
drivers/net/af_xdp/Makefile new file +28 -0
@@ -0,0 +1,28 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +include $(RTE_SDK)/mk/rte.vars.mk + +# +# library name +# +LIB = librte_pmd_af_xdp.a + +EXPORT_MAP := rte_pmd_af_xdp_version.map + +LIBABIVER := 1 + +CFLAGS += -O3 + +CFLAGS += $(WERROR_FLAGS) +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs +LDLIBS += -lrte_bus_vdev +LDLIBS += $(shell command -v pkg-config > /dev/null 2>&1 && pkg-config --libs libbpf || echo "-lbpf") + +# +# all source are stored in SRCS-y +# +SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c + +include $(RTE_SDK)/mk/rte.lib.mk
drivers/net/af_xdp/af_xdp_deps.h new file +15 -0
@@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: BSD-3-Clause +* Copyright(c) 2019 Intel Corporation. +*/ + +#ifndef AF_XDP_DEPS_H_ +#define AF_XDP_DEPS_H_ + +#include <rte_atomic.h> +#include <rte_branch_prediction.h> + +/* This is to fix the xsk.h's dependency on asm/barrier.h */ +#define smp_rmb () rte_rmb() +#define smp_wmb () rte_wmb() + +#endif /* AF_XDP_DEPS_H_ */
drivers/net/af_xdp/meson.build new file +19 -0
@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endif + ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')
drivers/net/af_xdp/rte_eth_af_xdp.c new file +955 -0
955 lines not on this page · raw message
drivers/net/af_xdp/rte_pmd_af_xdp_version.map new file +3 -0
@@ -0,0 +1,3 @@ +DPDK_19.05 { + local: *; +};
drivers/net/meson.build +1 -0
@@ -2,6 +2,7 @@ # Copyright(c) 2017 Intel Corporation drivers = ['af_packet', + 'af_xdp', 'ark', 'atlantic', 'avp',
mk/rte.app.mk +1 -0
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL) += -lrte_mempool_dpaa2 endif _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet +_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lbpf _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += -lrte_pmd_atlantic _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
Signature · 1 line
2.17.1
Re: [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 35 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to
[1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.[1]
https://fosdem.org/2018/schedule/event/af_xdp/[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Quoted 1 line
--- MAINTAINERS | 7 + config/common_base | 5 + doc/guides/nics/af_xdp.rst | 50 + doc/guides/nics/features/af_xdp.ini | 11 + doc/guides/nics/index.rst | 1 + doc/guides/rel_notes/release_19_05.rst | 7 + drivers/net/Makefile | 1 + drivers/net/af_xdp/Makefile | 28 + drivers/net/af_xdp/af_xdp_deps.h | 15 + drivers/net/af_xdp/meson.build | 19 + drivers/net/af_xdp/rte_eth_af_xdp.c | 955 ++++++++++++++++++ drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 + drivers/net/meson.build | 1 + mk/rte.app.mk | 1 +
Quoted 8 lines
14 files changed, 1104 insertions(+) create mode 100644 doc/guides/nics/af_xdp.rst create mode 100644 doc/guides/nics/features/af_xdp.ini create mode 100644 drivers/net/af_xdp/Makefile create mode 100644 drivers/net/af_xdp/af_xdp_deps.h create mode 100644 drivers/net/af_xdp/meson.build create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map
Signature · 2 lines
Kind regards, Luca Boccassi
Stephen Hemminger
Reviewed-byRe: [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 13 lines · On Thu, 04 Apr 2019 17:20:43 +0100 Luca Boccassi <[email protected]> wrote:
Quoted 12 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to
[1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.
Quoted 6 lines
Quoted 6 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]
Re: [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 16 lines · Stephen Hemminger
Quoted 13 lines · On Thu, 04 Apr 2019 17:20:43 +0100 Luca Boccassi <[email protected]> wrote:
Quoted 12 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to
[1]
[2].This is the vanilla version PMD which just uses a raw buffer registered as
the umem.
Quoted 9 lines
Quoted 6 lines
Quoted 6 lines
[2]
https://lwn.net/Articles/745934/Signed-off-by: Xiaolong Ye <
[email protected]Reviewed-by Stephen Hemminger <[email protected]>
Applied to dpdk-next-net/master, thanks.
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Xiaolong YeQuoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]>
<...>
Quoted 15 lines
drivers/net/af_xdp/meson.build new file +9
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false)
drivers/net/af_xdp/meson.build line 19
Quoted 10 lines
drivers/net/af_xdp/meson.build new file +10
-0+ if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endif + ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')
if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found? And can 'ext_deps' go out of if block?
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Hi, Ferruh
Quoted 37 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
Quoted 22 lines
drivers/net/af_xdp/meson.build new file +16
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endif
Quoted 8 lines
drivers/net/af_xdp/meson.build line 19
Quoted 3 lines
drivers/net/af_xdp/meson.build new file +3
-0+ ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found?
This is a good catch, we do need to initialize build = false first, otherwise meson/ninja would just try to build af_xdp pmd if system is not linux, which is undesired. Do I need to send a separate patch for this so you can squash it into af_xdp pmd patch?
Quoted 1 line
And can '
ext_deps' go out of if block?
If we move ext_deps += bpf_dep out of if block and build system is not linux, there would be error "ERROR: Unknown variable "bpf_dep".", so we need either initialize bpf_dep (to value like NULL?) first or keep ext_deps += bpf_dep inside the if block, I'd prefer keep it as it is, what's you opinion?
Thanks,
Xiaolong
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 49 lines · Ye Xiaolong
Hi, Ferruh
Quoted 37 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
Quoted 22 lines
drivers/net/af_xdp/meson.build new file +16
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endifQuoted 8 lines
drivers/net/af_xdp/meson.build line 19
Quoted 3 lines
drivers/net/af_xdp/meson.build new file +3
-0+ ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found?
Quoted 4 lines
This is a good catch, we do need to initialize build = false first, otherwise meson/ninja would just try to build
af_xdppmd if system is not linux, which is undesired. Do I need to send a separate patch for this so you can squash it intoaf_xdppmd patch?
If you are agree with the change, I can send the patch and squash it into the original af_xdp commit:
diff --git a/drivers/net/af_xdp/meson.build b/drivers/net/af_xdp/meson.build index 840c93728..e3d86c39a 100644 --- a/drivers/net/af_xdp/meson.build +++ b/drivers/net/af_xdp/meson.build @@ -1,6 +1,7 @@ # SPDX-License-Identifier: BSD-3-Clause # Copyright(c) 2019 Intel Corporation
+build = false
if host_machine.system() == 'linux'
bpf_dep = dependency('libbpf', required: false) if bpf_dep.found()
@@ -10,8 +11,6 @@ if host_machine.system() == 'linux'
if bpf_dep.found() and cc.has_header('bpf/xsk.h',
dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h')
build = true pkgconfig_extra_libs += '-lbpf'
- else
- build = false
endif
endif
ext_deps += bpf_depQuoted 7 lines
Quoted 2 lines
And can '
ext_deps' go out of if block?If we move
ext_deps += bpf_depout of if block and build system is not linux, there would be error "ERROR: Unknown variable "bpf_dep".", so we need either initializebpf_dep(to value like NULL?) first or keepext_deps += bpf_depinside the if block, I'd prefer keep it as it is, what's you opinion?
OK to keep as it is.
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 77 lines · Ferruh Yigit
Quoted 49 lines · Ye Xiaolong
Hi, Ferruh
Quoted 37 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
Quoted 22 lines
drivers/net/af_xdp/meson.build new file +16
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endifQuoted 8 lines
drivers/net/af_xdp/meson.build line 19
Quoted 3 lines
drivers/net/af_xdp/meson.build new file +3
-0+ ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found?Quoted 4 lines
This is a good catch, we do need to initialize build = false first, otherwise meson/ninja would just try to build
af_xdppmd if system is not linux, which is undesired. Do I need to send a separate patch for this so you can squash it intoaf_xdppmd patch?If you are agree with the change, I can send the patch and squash it into the original
af_xdpcommit:diff --git a/drivers/net/af_xdp/meson.build b/drivers/net/af_xdp/meson.build index
840c93728..e3d86c39a100644
--- a/drivers/net/af_xdp/meson.build
+++ b/drivers/net/af_xdp/meson.build
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: BSD-3-Clause
# Copyright(c) 2019 Intel Corporation+build = false
ifhost_machine.system()== 'linux'
bpf_dep=dependency('libbpf', required: false)ifbpf_dep.found()
@@ -10,8 +11,6 @@ ifhost_machine.system()== 'linux'
ifbpf_dep.found()and cc.has_header('bpf/xsk.h',
dependencies:bpf_dep) andcc.has_header('linux/if_xdp.h')
build = truepkgconfig_extra_libs+= '-lbpf'
- else
- build = false
Quoted 4 lines
endif
endif
ext_deps += bpf_depLooks good to me, thanks for the fix.
Thanks,
Xiaolong
Quoted 9 lines
Quoted 7 lines
Quoted 2 lines
And can '
ext_deps' go out of if block?If we move
ext_deps += bpf_depout of if block and build system is not linux, there would be error "ERROR: Unknown variable "bpf_dep".", so we need either initializebpf_dep(to value like NULL?) first or keepext_deps += bpf_depinside the if block, I'd prefer keep it as it is, what's you opinion?OK to keep as it is.
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
In reply to Ye XiaolongQuoted 54 lines · Ye Xiaolong
Hi, Ferruh
Quoted 37 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
Quoted 22 lines
drivers/net/af_xdp/meson.build new file +16
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endifQuoted 8 lines
drivers/net/af_xdp/meson.build line 19
Quoted 3 lines
drivers/net/af_xdp/meson.build new file +3
-0+ ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found?This is a good catch, we do need to initialize build = false first, otherwise meson/ninja would just try to build
af_xdppmd if system is not linux, which is undesired. Do I need to send a separate patch for this so you can squash it intoaf_xdppmd patch?
Quoted 6 lines
Quoted 1 line
And can '
ext_deps' go out of if block?If we move
ext_deps += bpf_depout of if block and build system is not linux, there would be error "ERROR: Unknown variable "bpf_dep".", so we need either initializebpf_dep(to value like NULL?) first or keepext_deps += bpf_depinside the if block, I'd prefer keep it as it is, what's you opinion?
Actually, a suggestion - rather than limiting the build to linux, why not just limit the build to the presence of libbpf, and not bother checking the OS?
/Bruce
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 57 lines · Bruce Richardson
Quoted 56 lines · Ye Xiaolong
Hi, Ferruh
Quoted 37 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
Quoted 22 lines
drivers/net/af_xdp/meson.build new file +16
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endifQuoted 8 lines
drivers/net/af_xdp/meson.build line 19
Quoted 3 lines
drivers/net/af_xdp/meson.build new file +3
-0+ ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found?This is a good catch, we do need to initialize build = false first, otherwise meson/ninja would just try to build
af_xdppmd if system is not linux, which is undesired. Do I need to send a separate patch for this so you can squash it intoaf_xdppmd patch?Quoted 1 line
And can '
ext_deps' go out of if block?
Quoted 8 lines
Quoted 4 lines
If we move
ext_deps += bpf_depout of if block and build system is not linux, there would be error "ERROR: Unknown variable "bpf_dep".", so we need either initializebpf_dep(to value like NULL?) first or keepext_deps += bpf_depinside the if block, I'd prefer keep it as it is, what's you opinion?Actually, a suggestion - rather than limiting the build to linux, why not just limit the build to the presence of libbpf, and not bother checking the OS?
If this won't cause a problem for other OS in case they have the library, I have no objection.
Re: [dpdk-dev] [PATCH v11 1/1] net/af_xdp: introduce AF XDP PMD driver
Quoted 63 lines · Ferruh Yigit
Quoted 62 lines · Bruce Richardson
Quoted 60 lines · Ye Xiaolong
Hi, Ferruh
Quoted 37 lines · Ferruh Yigit
Quoted 11 lines · Xiaolong Ye
Add a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux. More info aboutAF_XDP, please refer to [1] [2].This is the vanilla version PMD which just uses a raw buffer registered as the umem.
[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/Signed-off-by Xiaolong Ye <[email protected]><...>
Quoted 22 lines
drivers/net/af_xdp/meson.build new file +16
-0@@ -0,0 +1,19 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2019 Intel Corporation + +if host_machine.system() == 'linux' + bpf_dep = dependency('libbpf', required: false) + if bpf_dep.found() + build = true + else + bpf_dep = cc.find_library('bpf', required: false) + if bpf_dep.found() and cc.has_header('bpf/xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h') + build = true + pkgconfig_extra_libs += '-lbpf' + else + build = false + endif + endifQuoted 8 lines
drivers/net/af_xdp/meson.build line 19
Quoted 3 lines
drivers/net/af_xdp/meson.build new file +3
-0+ ext_deps += bpf_dep +endif +sources = files('rte_eth_af_xdp.c')if system is not 'linux', by default build will be 'true', right, so will it try to build the driver in that case?
What about setting "build = false" before the linux check, so won't need to set it false again in the if block, only set it true if dependencies found?This is a good catch, we do need to initialize build = false first, otherwise meson/ninja would just try to build
af_xdppmd if system is not linux, which is undesired. Do I need to send a separate patch for this so you can squash it intoaf_xdppmd patch?Quoted 1 line
And can '
ext_deps' go out of if block?If we move
ext_deps += bpf_depout of if block and build system is not linux, there would be error "ERROR: Unknown variable "bpf_dep".", so we need either initializebpf_dep(to value like NULL?) first or keepext_deps += bpf_depinside the if block, I'd prefer keep it as it is, what's you opinion?
Quoted 7 lines
Quoted 3 lines
Actually, a suggestion - rather than limiting the build to linux, why not just limit the build to the presence of libbpf, and not bother checking the OS?
If this won't cause a problem for other OS in case they have the library, I have no objection.
Well, they shouldn't have, and we also check for the header file "linux/if_xdp.h", so I don't think an additional check for linux itself is required. Generally, I think it's better to check for the requirements of a driver directly, rather than assuming that only certain environments would ever have them.
Just sent my suggested patch: http://patches.dpdk.org/patch/52357/
/Bruce
Quoted 117 lines · Xiaolong Ye
Overview
========This patchset adds a new PMD driver for
AF_XDPwhich is a proposed faster version ofAF_PACKETinterface in Linux, see below links [1] [2] for details ofAF_XDPintroduction:
AF_XDProadmap
==============
-AF_XDPis included in upstream kernel since 4.18, andAF_XDPsupport in libbpf has been merged in v5.1-rc1.
- Now i40e and ixgbe drivers have supported zero copy mode.Change logs
===========
v11:- fix the meson build issue
v10:
- refine the
Makefile, removeRTE_KERNELDIRrelated CFLAGS
- add a new internal fileaf_xdp_deps.hto handle the dependency forasm/barrier.h
- fix a typo observed by Stephen
- renamexsk.htobpf/xsk.hasxsk.his assumed to be installed in/usr/local/include/bpf
- add libbpf build steps inaf_xdp.rstv9:
- adjust header files order according to Stephen's suggestionv8:
- address Ferruh's comments on V7
- replaceposix_memalignwithrte_memzone_reserve_alignedto get better performance
- keep the first patch only as Oliver suggested as zero copy part implementation is still in suspense, we may provide the related patch later.v7:
- mention mtu limitation inaf_xdp.rst
- fix the vdev name inaf_xdp.rstV6:
- remove the newline in
AF_XDP_LOGdefinition to avoid double new lines issue.
- renameMEMPOOL_F_PAGE_ALIGNtoMEMPOOL_CHUNK_F_PAGE_ALIGN.V5:
- disable
AF_XDPpmd by default due to it requires kernel more recent than minimum kernel version supported by DPDK
- address other review comments of MaximeV4:
- change vdev name to
net_af_xdp
- adopt dynamic log type for all logging
- Fix other style issues raised by StephenV3:
- Fix all style issues pointed by Stephen, Mattias, David.
- Drop the testpmd change as we'll adopt Jerin's suggestion to add a new mempool driver to handle the application use of AF_XDP's zero copy feature.V2:
- Fix a NULL pointer reference crash issue
- Fix txonly stop sending traffic in zc mode
- Refactorrte_mbuf.cto avoid ABI breakage.
- Fix multiple style issues pointed by Ferruh, David, Stephen, Luca.changes vs RFC sent by Qi last Aug:
- Re-work base on AF_XDP's interface changes since the new libbpf has provided higher-level APIs that hide many of the details of the
AP_XDPuapi. After the rework, it helps to reduce 300+ lines of code.- multi-queues is not supported due to current libbpf doesn't support multi-sockets on a single umem.
- No extra steps to load xdp program manually, since the current behavior of libbpf would load a default xdp program when user calls
xsk_socket__create. userspace application only needs to handle the cleanup.How to try
==========1. take the kernel >= v5.1-rc1, build kernel and replace your host kernel with it.
make sure you turn on XDP sockets when compiling
Networking support --> Networking options --> [ * ] XDP sockets2. build & install libbpf in
tools/lib/bpfcd
tools/lib/bpf
makeinstall_lib
makeinstall_headers3. ethtool -L enp59s0f0 combined 1
4. extra step to build dpdk
explicitly enable
AF_XDPpmd by adding below line to config/common_linux
CONFIG_RTE_LIBRTE_PMD_AF_XDP=y5. start testpmd
Quoted 7 lines
./build/app/testpmd -c 0xc -n 4 --vdev net_af_xdp,iface=enp59s0f0,queue=0 -- -i --rxq=1 --txq=1in this case, default xdp program will be loaded and linked to queue 0 of enp59s0f0, network traffics travel to queue 0 will be redirected to
af_xdpsocket.Xiaolong Ye (1):
net/af_xdp: introduce AF XDP PMD driver