netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Maxim Mikityanskiy <maximmi@mellanox.com>
To: "Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>
Cc: "bpf@vger.kernel.org" <bpf@vger.kernel.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"David S. Miller" <davem@davemloft.net>,
	Saeed Mahameed <saeedm@mellanox.com>, Jonathan Lemon <bsd@fb.com>,
	Tariq Toukan <tariqt@mellanox.com>,
	Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
	Yonghong Song <yhs@fb.com>,
	Jakub Kicinski <jakub.kicinski@netronome.com>,
	Maciej Fijalkowski <maciejromanfijalkowski@gmail.com>,
	Maxim Mikityanskiy <maximmi@mellanox.com>
Subject: [PATCH bpf-next v5 05/16] xsk: Change the default frame size to 4096 and allow controlling it
Date: Tue, 18 Jun 2019 12:00:49 +0000	[thread overview]
Message-ID: <20190618120024.16788-6-maximmi@mellanox.com> (raw)
In-Reply-To: <20190618120024.16788-1-maximmi@mellanox.com>

The typical XDP memory scheme is one packet per page. Change the AF_XDP
frame size in libbpf to 4096, which is the page size on x86, to allow
libbpf to be used with the drivers with the packet-per-page scheme.

Add a command line option -f to xdpsock to allow to specify a custom
frame size.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
---
 samples/bpf/xdpsock_user.c | 44 ++++++++++++++++++++++++--------------
 tools/lib/bpf/xsk.h        |  2 +-
 2 files changed, 29 insertions(+), 17 deletions(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 0f5eb0d7f2df..93eaaf7239b2 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -68,6 +68,7 @@ static int opt_queue;
 static int opt_poll;
 static int opt_interval = 1;
 static u32 opt_xdp_bind_flags;
+static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 static __u32 prog_id;
 
 struct xsk_umem_info {
@@ -276,6 +277,12 @@ static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
 static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 {
 	struct xsk_umem_info *umem;
+	struct xsk_umem_config cfg = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = opt_xsk_frame_size,
+		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
+	};
 	int ret;
 
 	umem = calloc(1, sizeof(*umem));
@@ -283,7 +290,7 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 		exit_with_error(errno);
 
 	ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
-			       NULL);
+			       &cfg);
 	if (ret)
 		exit_with_error(-ret);
 
@@ -323,11 +330,9 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 				     &idx);
 	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
 		exit_with_error(-ret);
-	for (i = 0;
-	     i < XSK_RING_PROD__DEFAULT_NUM_DESCS *
-		     XSK_UMEM__DEFAULT_FRAME_SIZE;
-	     i += XSK_UMEM__DEFAULT_FRAME_SIZE)
-		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = i;
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) =
+			i * opt_xsk_frame_size;
 	xsk_ring_prod__submit(&xsk->umem->fq,
 			      XSK_RING_PROD__DEFAULT_NUM_DESCS);
 
@@ -346,6 +351,7 @@ static struct option long_options[] = {
 	{"interval", required_argument, 0, 'n'},
 	{"zero-copy", no_argument, 0, 'z'},
 	{"copy", no_argument, 0, 'c'},
+	{"frame-size", required_argument, 0, 'f'},
 	{0, 0, 0, 0}
 };
 
@@ -365,8 +371,9 @@ static void usage(const char *prog)
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
 		"  -z, --zero-copy      Force zero-copy mode.\n"
 		"  -c, --copy           Force copy mode.\n"
+		"  -f, --frame-size=n   Set the frame size (must be a power of two, default is %d).\n"
 		"\n";
-	fprintf(stderr, str, prog);
+	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
 	exit(EXIT_FAILURE);
 }
 
@@ -377,7 +384,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:psSNn:cz", long_options,
+		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:", long_options,
 				&option_index);
 		if (c == -1)
 			break;
@@ -420,6 +427,9 @@ static void parse_command_line(int argc, char **argv)
 		case 'F':
 			opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
 			break;
+		case 'f':
+			opt_xsk_frame_size = atoi(optarg);
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -432,6 +442,11 @@ static void parse_command_line(int argc, char **argv)
 		usage(basename(argv[0]));
 	}
 
+	if (opt_xsk_frame_size & (opt_xsk_frame_size - 1)) {
+		fprintf(stderr, "--frame-size=%d is not a power of two\n",
+			opt_xsk_frame_size);
+		usage(basename(argv[0]));
+	}
 }
 
 static void kick_tx(struct xsk_socket_info *xsk)
@@ -583,8 +598,7 @@ static void tx_only(struct xsk_socket_info *xsk)
 
 			for (i = 0; i < BATCH_SIZE; i++) {
 				xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr
-					= (frame_nb + i) <<
-					XSK_UMEM__DEFAULT_FRAME_SHIFT;
+					= (frame_nb + i) * opt_xsk_frame_size;
 				xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len =
 					sizeof(pkt_data) - 1;
 			}
@@ -661,21 +675,19 @@ int main(int argc, char **argv)
 	}
 
 	ret = posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */
-			     NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE);
+			     NUM_FRAMES * opt_xsk_frame_size);
 	if (ret)
 		exit_with_error(ret);
 
        /* Create sockets... */
-	umem = xsk_configure_umem(bufs,
-				  NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE);
+	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
 	xsks[num_socks++] = xsk_configure_socket(umem);
 
 	if (opt_bench == BENCH_TXONLY) {
 		int i;
 
-		for (i = 0; i < NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE;
-		     i += XSK_UMEM__DEFAULT_FRAME_SIZE)
-			(void)gen_eth_frame(umem, i);
+		for (i = 0; i < NUM_FRAMES; i++)
+			(void)gen_eth_frame(umem, i * opt_xsk_frame_size);
 	}
 
 	signal(SIGINT, int_exit);
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index 82ea71a0f3ec..833a6e60d065 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -167,7 +167,7 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
 
 #define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
 #define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
-#define XSK_UMEM__DEFAULT_FRAME_SHIFT    11 /* 2048 bytes */
+#define XSK_UMEM__DEFAULT_FRAME_SHIFT    12 /* 4096 bytes */
 #define XSK_UMEM__DEFAULT_FRAME_SIZE     (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
 #define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0
 
-- 
2.19.1


  parent reply	other threads:[~2019-06-18 12:00 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-18 12:00 [PATCH bpf-next v5 00/16] AF_XDP infrastructure improvements and mlx5e support Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 01/16] net/mlx5e: Attach/detach XDP program safely Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 02/16] xsk: Add API to check for available entries in FQ Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 03/16] xsk: Add getsockopt XDP_OPTIONS Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 04/16] libbpf: Support " Maxim Mikityanskiy
2019-06-18 12:00 ` Maxim Mikityanskiy [this message]
2019-06-18 12:00 ` [PATCH bpf-next v5 06/16] xsk: Return the whole xdp_desc from xsk_umem_consume_tx Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 07/16] net/mlx5e: Replace deprecated PCI_DMA_TODEVICE Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 08/16] net/mlx5e: Calculate linear RX frag size considering XSK Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 09/16] net/mlx5e: Allow ICO SQ to be used by multiple RQs Maxim Mikityanskiy
2019-06-18 12:00 ` [PATCH bpf-next v5 10/16] net/mlx5e: Refactor struct mlx5e_xdp_info Maxim Mikityanskiy
2019-06-18 12:01 ` [PATCH bpf-next v5 11/16] net/mlx5e: Share the XDP SQ for XDP_TX between RQs Maxim Mikityanskiy
2019-06-18 12:01 ` [PATCH bpf-next v5 12/16] net/mlx5e: XDP_TX from UMEM support Maxim Mikityanskiy
2019-06-18 12:01 ` [PATCH bpf-next v5 13/16] net/mlx5e: Consider XSK in XDP MTU limit calculation Maxim Mikityanskiy
2019-06-18 12:01 ` [PATCH bpf-next v5 14/16] net/mlx5e: Encapsulate open/close queues into a function Maxim Mikityanskiy
2019-06-18 12:01 ` [PATCH bpf-next v5 15/16] net/mlx5e: Move queue param structs to en/params.h Maxim Mikityanskiy
2019-06-18 12:01 ` [PATCH bpf-next v5 16/16] net/mlx5e: Add XSK zero-copy support Maxim Mikityanskiy
2019-06-20  9:13 ` [PATCH bpf-next v5 00/16] AF_XDP infrastructure improvements and mlx5e support Björn Töpel
2019-06-21 19:52   ` Saeed Mahameed
2019-06-23 11:53     ` Tariq Toukan
2019-06-24 14:48   ` Daniel Borkmann

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190618120024.16788-6-maximmi@mellanox.com \
    --to=maximmi@mellanox.com \
    --cc=ast@kernel.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=bsd@fb.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=jakub.kicinski@netronome.com \
    --cc=kafai@fb.com \
    --cc=maciejromanfijalkowski@gmail.com \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=songliubraving@fb.com \
    --cc=tariqt@mellanox.com \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).