Re: [dpdk-dev] [PATCH v3 0/6] PMD driver for AF_XDP

["Zhang, Qi Z" <qi.z.zhang@intel.com>]

Sorry, the patch for kernel sample code is not complete. It should be as below

~~~~~~~~~~~~~~~~~~~~~~~PATCH START ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index d69c8d78d3fd..44a6318043e7 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -76,6 +76,8 @@ static int opt_poll;
 static int opt_shared_packet_buffer;
 static int opt_interval = 1;
 static u32 opt_xdp_bind_flags;
+static int opt_bind;
+static int opt_unbind;
 
 struct xdp_umem_uqueue {
 	u32 cached_prod;
@@ -662,6 +664,8 @@ static void usage(const char *prog)
 		"  -S, --xdp-skb=n	Use XDP skb-mod\n"
 		"  -N, --xdp-native=n	Enfore XDP native mode\n"
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
+		"  -b, --bind		Bind only.\n"
+		"  -u, --unbind		Unbind only.\n"
 		"\n";
 	fprintf(stderr, str, prog);
 	exit(EXIT_FAILURE);
@@ -674,7 +678,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options,
+		c = getopt_long(argc, argv, "rtli:q:psSNn:bu", long_options,
 				&option_index);
 		if (c == -1)
 			break;
@@ -711,6 +715,12 @@ static void parse_command_line(int argc, char **argv)
 		case 'n':
 			opt_interval = atoi(optarg);
 			break;
+		case 'b':
+			opt_bind = 1;
+			break;
+		case 'u':
+			opt_unbind = 1;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -898,6 +908,12 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	if (opt_unbind) {
+		bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
+		printf("unbind.\n");
+		return 0;
+	}
+
 	snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
 
 	if (load_bpf_file(xdp_filename)) {
@@ -922,6 +938,11 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	if (opt_bind) {
+		printf("bind.\n");
+		return 0;
+	}
+
 	/* Create sockets... */
 	xsks[num_socks++] = xsk_configure(NULL);

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~PATCH END~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

BTW, there is bug in kernel bpftool on 4.18, it will cause segment fault when you try to dump bpf map with
#./tools/bpf/bpftool/bpftool map -p

So, please also apply below patch 

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~PATCH START ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 097b1a5e046b..0c661de58976 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -67,6 +67,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
 	[BPF_MAP_TYPE_CPUMAP]		= "cpumap",
 	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
+	[BPF_MAP_TYPE_XSKMAP]		= "xskmap"
 };

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~PATCH END~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

> -----Original Message-----
> From: Zhang, Qi Z
> Sent: Thursday, August 16, 2018 10:43 PM
> To: dev@dpdk.org
> Cc: Karlsson, Magnus <magnus.karlsson@intel.com>; Topel, Bjorn
> <bjorn.topel@intel.com>; Wu, Jingjing <jingjing.wu@intel.com>; Li, Xiaoyun
> <xiaoyun.li@intel.com>; Yigit, Ferruh <ferruh.yigit@intel.com>; Zhang, Qi Z
> <qi.z.zhang@intel.com>
> Subject: [PATCH v3 0/6] PMD driver for AF_XDP
> 
> Overview
> ========
> 
> The patch set add a new PMD driver for AF_XDP which is a proposed faster
> version of AF_PACKET interface in Linux, see below link for detail AF_XDP
> introduction:
> https://lwn.net/Articles/750845/
> https://fosdem.org/2018/schedule/event/af_xdp/
> 
> AF_XDP roadmap
> ==============
> - The kernel 4.18 is out and af_xdp is included.
>   https://kernelnewbies.org/Linux_4.18
> - So far there is no zero copy supported driver be merged, but some are
>   on the way.
> 
> Change logs
> ===========
> 
> v3:
> - Re-work base on AF_XDP's interface changes.
> - Support multi-queues, each dpdk queue has its own xdp socket.
>   An xdp socket is always bound to a netdev queue.
>   We assume all xdp socket from the same ethdev are bound to the
>   same netdev queue, though a netdev queue still can be bound by
>   xdp sockets from different ethdev instances.
>   Below is an example of the mapping.
>   ------------------------------------------------------
>   | dpdk q0 | dpdk q1 | dpdk q0    | dpdk q0 | dpdk q1 |
>   ------------------------------------------------------
>   | xsk A   | xsk B   | xsk C      | xsk D   | xsk E   |<---|
>   ------------------------------------------------------    |
>   |  ETHDEV 0         | ETHDEV 1   |  ETHDEV 2         |    |
> DPDK
>   ------------------------------------------------------------------
>   |  netdev queue 0                |   netdev queue 1  |    |
> KERNEL
>   ------------------------------------------------------    |
>   |                  NETDEV eth0                       |    |
>   ------------------------------------------------------    |
>   |                    key   xsk                       |    |
>   |  ----------       --------------                   |    |
>   |  |         |      | 0  | xsk A |                   |    |
>   |  |         |      --------------                   |    |
>   |  |         |      | 2  | xsk B |                   |    |
>   |  | ebpf    |      ---------------------------------------
>   |  |         |      | 3  | xsk C |                   |
>   |  |     redirect ->|--------------                  |
>   |  |         |      | 4  | xsk D |                   |
>   |  |         |      --------------                   |
>   |  |---------|      | 5  | xsk E |                   |
>   |                   --------------                   |
>   |-----------------------------------------------------
> 
> - It is an open question that how to load ebpf to kernel and link to
>   specific netdev in DPDK, should it be part of PMD, or it should be handled
> by
>   an independent tool? In this patchset, it takes the second option, there will
>   be a "bind" stage before we start AF_XDP PMD, this includes below steps:
>   a) load ebpf program to the kernel, (the ebpf program must contain the
>      logic to redirect packet to a xdp socket base on a redirect map).
>   b) link ebpf program to specific network interface.
>   c) expose the xdp socket redirect map id and entries number to user,
>      so this will be parsed to PMD, and PMD will create xdp socket
>      for each queue and update the redirect map correctly.
>      (example:
> --vdev,iface=eth0,xsk_map_id=53,xsk_map_key_base=0,xsk_map_key_count
> =4)
> 
> v2:
> - fix lisence header
> - clean up bpf dependency, bpf program is embedded,  no
> "xdpsock_kern.o"
>   required
> - clean up make file, only linux_header is required
> - fix all the compile warning.
> - fix packet number return in Tx.
> 
> How to try
> ==========
> 
> 1. Take the kernel v4.18.
>    make sure you turn on XDP sockets when compiling
>    Networking support -->
>         Networking options -->
>                 [ * ] XDP sockets
> 2. in the kernel source code, apply below patch and compile the bpf sample
> code.
>    #make samples/bpf/
>    so the sample xdpsock can be used as a bind/unbind tool for af_xdp
>    PMD, sorry for this ugly, but in future, there could be a dedicated
>    tool in DPDK, if we agree with the idea that bpf configure in the kernel
>    should be separated from PMD.
> 
> ~~~~~~~~~~~~~~~~~~~~~~~PATCH
> START~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> 
> diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index
> d69c8d78d3fd..44a6318043e7 100644
> --- a/samples/bpf/xdpsock_user.c
> +++ b/samples/bpf/xdpsock_user.c
> @@ -76,6 +76,8 @@ static int opt_poll;
>  static int opt_shared_packet_buffer;
>  static int opt_interval = 1;
>  static u32 opt_xdp_bind_flags;
> +static int opt_bind;
> +static int opt_unbind;
> 
>  struct xdp_umem_uqueue {
>  	u32 cached_prod;
> @@ -662,6 +664,8 @@ static void usage(const char *prog)
>  		"  -S, --xdp-skb=n	Use XDP skb-mod\n"
>  		"  -N, --xdp-native=n	Enfore XDP native mode\n"
>  		"  -n, --interval=n	Specify statistics update interval (default 1
> sec).\n"
> +		"  -b, --bind		Bind only.\n"
> +		"  -u, --unbind		Unbind only.\n"
>  		"\n";
>  	fprintf(stderr, str, prog);
>  	exit(EXIT_FAILURE);
> @@ -674,7 +678,7 @@ static void parse_command_line(int argc, char
> **argv)
>  	opterr = 0;
> 
>  	for (;;) {
> -		c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options,
> +		c = getopt_long(argc, argv, "rtli:q:psSNn:bu", long_options,
>  				&option_index);
>  		if (c == -1)
>  			break;
> @@ -711,6 +715,12 @@ static void parse_command_line(int argc, char
> **argv)
>  		case 'n':
>  			opt_interval = atoi(optarg);
>  			break;
> +		case 'b':
> +			opt_bind = 1;
> +			break;
> +		case 'u':
> +			opt_unbind = 1;
> +			break;
>  		default:
>  			usage(basename(argv[0]));
>  		}
> @@ -898,6 +908,12 @@ int main(int argc, char **argv)
>  		exit(EXIT_FAILURE);
>  	}
> 
> +	if (opt_unbind) {
> +		bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
> 
> ~~~~~~~~~~~~~~~~~~~~~~~PATCH
> END~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> 
> 3. bind
>   #./samples/bpf/xdpsock -i eth0 -b
> 
>   in this step, an ebpf binary xdpsock_kern.o is be loaded into the kernel
>   and linked to eth0, the ebpf source code is /samples/bpf/xdpsock_kern.c
>   you can modify it and re-compile for a different test.
> 
> 4. dump xdp socket map information.
>   #./tools/bpf/bpftool/bpftool map -p, you will see something like below.
> 
>   },{
>        "id": 56,
>        "type": "xskmap",
>        "name": "xsks_map",
>        "flags": 0,
>        "bytes_key": 4,
>        "bytes_value": 4,
>        "max_entries": 4,
>        "bytes_memlock": 4096
>    }
> 
>    in this case 56 is the map id and it has 4 entries
> 
> 5. start testpmd
> 
>    ./build/app/testpmd -c 0xc -n 4 --vdev
> eth_af_xdp,iface=enp59s0f0,xsk_map_id=56,xsk_map_key_start=2xsk_map_
> key_count=2 -- -i --rxq=2 --txq=2
> 
>     in this case, we reserved 2 entries (2,3) in the map, and they will be
> mapped to queue 0 and queue 1.
> 
> 6. unbind after test
>    ./sample/bpf/xdpsock -i eth0 -u.
> 
> Performance
> ===========
> Since no zero copy driver is ready yet.
> So far only tested with DRV and SKB mode on i40e 25G the result show
> identical with kernel sample "xdpsock"
> 
> Qi Zhang (6):
>   net/af_xdp: new PMD driver
>   lib/mbuf: enable parse flags when create mempool
>   lib/mempool: allow page size aligned mempool
>   net/af_xdp: use mbuf mempool for buffer management
>   net/af_xdp: enable zero copy
>   app/testpmd: add mempool flags parameter
> 
>  app/test-pmd/parameters.c                     |   12 +
>  app/test-pmd/testpmd.c                        |   15 +-
>  app/test-pmd/testpmd.h                        |    1 +
>  config/common_base                            |    5 +
>  config/common_linuxapp                        |    1 +
>  drivers/net/Makefile                          |    1 +
>  drivers/net/af_xdp/Makefile                   |   30 +
>  drivers/net/af_xdp/meson.build                |    7 +
>  drivers/net/af_xdp/rte_eth_af_xdp.c           | 1345
> +++++++++++++++++++++++++
>  drivers/net/af_xdp/rte_pmd_af_xdp_version.map |    4 +
>  lib/librte_mbuf/rte_mbuf.c                    |   15 +-
>  lib/librte_mbuf/rte_mbuf.h                    |    8 +-
>  lib/librte_mempool/rte_mempool.c              |    3 +
>  lib/librte_mempool/rte_mempool.h              |    1 +
>  mk/rte.app.mk                                 |    1 +
>  15 files changed, 1439 insertions(+), 10 deletions(-)  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
> 
> --
> 2.13.6