From 46738f73ea4f94906491cb8399bdeafa5b9cc5ec Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 14 Aug 2019 09:27:21 +0200 Subject: samples/bpf: add use of need_wakeup flag in xdpsock This commit adds using the need_wakeup flag to the xdpsock sample application. It is turned on by default as we think it is a feature that seems to always produce a performance benefit, if the application has been written taking advantage of it. It can be turned off in the sample app by using the '-m' command line option. The txpush and l2fwd sub applications have also been updated to support poll() with multiple sockets. Signed-off-by: Magnus Karlsson Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- samples/bpf/xdpsock_user.c | 192 ++++++++++++++++++++++++++++----------------- 1 file changed, 120 insertions(+), 72 deletions(-) (limited to 'samples') diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 93eaaf7239b2..da84c760c094 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -67,8 +67,10 @@ static int opt_ifindex; static int opt_queue; static int opt_poll; static int opt_interval = 1; -static u32 opt_xdp_bind_flags; +static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; +static int opt_timeout = 1000; +static bool opt_need_wakeup = true; static __u32 prog_id; struct xsk_umem_info { @@ -352,6 +354,7 @@ static struct option long_options[] = { {"zero-copy", no_argument, 0, 'z'}, {"copy", no_argument, 0, 'c'}, {"frame-size", required_argument, 0, 'f'}, + {"no-need-wakeup", no_argument, 0, 'm'}, {0, 0, 0, 0} }; @@ -372,6 +375,7 @@ static void usage(const char *prog) " -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" + " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n" "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE); exit(EXIT_FAILURE); @@ -384,8 +388,9 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:", long_options, - &option_index); + + c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:m", + long_options, &option_index); if (c == -1) break; @@ -429,6 +434,9 @@ static void parse_command_line(int argc, char **argv) break; case 'f': opt_xsk_frame_size = atoi(optarg); + case 'm': + opt_need_wakeup = false; + opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP; break; default: usage(basename(argv[0])); @@ -459,7 +467,8 @@ static void kick_tx(struct xsk_socket_info *xsk) exit_with_error(errno); } -static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) +static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, + struct pollfd *fds) { u32 idx_cq = 0, idx_fq = 0; unsigned int rcvd; @@ -468,7 +477,9 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) if (!xsk->outstanding_tx) return; - kick_tx(xsk); + if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) + kick_tx(xsk); + ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE : xsk->outstanding_tx; @@ -482,6 +493,8 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + ret = poll(fds, num_socks, opt_timeout); ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); } @@ -505,7 +518,8 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk) if (!xsk->outstanding_tx) return; - kick_tx(xsk); + if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) + kick_tx(xsk); rcvd = xsk_ring_cons__peek(&xsk->umem->cq, BATCH_SIZE, &idx); if (rcvd > 0) { @@ -515,20 +529,25 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk) } } -static void rx_drop(struct xsk_socket_info *xsk) +static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) { unsigned int rcvd, i; u32 idx_rx = 0, idx_fq = 0; int ret; rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); - if (!rcvd) + if (!rcvd) { + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + ret = poll(fds, num_socks, opt_timeout); return; + } ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + ret = poll(fds, num_socks, opt_timeout); ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); } @@ -549,42 +568,65 @@ static void rx_drop(struct xsk_socket_info *xsk) static void rx_drop_all(void) { struct pollfd fds[MAX_SOCKS + 1]; - int i, ret, timeout, nfds = 1; + int i, ret; memset(fds, 0, sizeof(fds)); for (i = 0; i < num_socks; i++) { fds[i].fd = xsk_socket__fd(xsks[i]->xsk); fds[i].events = POLLIN; - timeout = 1000; /* 1sn */ } for (;;) { if (opt_poll) { - ret = poll(fds, nfds, timeout); + ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; } for (i = 0; i < num_socks; i++) - rx_drop(xsks[i]); + rx_drop(xsks[i], fds); + } +} + +static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb) +{ + u32 idx; + + if (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) == BATCH_SIZE) { + unsigned int i; + + 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; + xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len = + sizeof(pkt_data) - 1; + } + + xsk_ring_prod__submit(&xsk->tx, BATCH_SIZE); + xsk->outstanding_tx += BATCH_SIZE; + frame_nb += BATCH_SIZE; + frame_nb %= NUM_FRAMES; } + + complete_tx_only(xsk); } -static void tx_only(struct xsk_socket_info *xsk) +static void tx_only_all(void) { - int timeout, ret, nfds = 1; - struct pollfd fds[nfds + 1]; - u32 idx, frame_nb = 0; + struct pollfd fds[MAX_SOCKS]; + u32 frame_nb[MAX_SOCKS] = {}; + int i, ret; memset(fds, 0, sizeof(fds)); - fds[0].fd = xsk_socket__fd(xsk->xsk); - fds[0].events = POLLOUT; - timeout = 1000; /* 1sn */ + for (i = 0; i < num_socks; i++) { + fds[0].fd = xsk_socket__fd(xsks[i]->xsk); + fds[0].events = POLLOUT; + } for (;;) { if (opt_poll) { - ret = poll(fds, nfds, timeout); + ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; @@ -592,69 +634,75 @@ static void tx_only(struct xsk_socket_info *xsk) continue; } - if (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) == - BATCH_SIZE) { - unsigned int i; - - for (i = 0; i < BATCH_SIZE; i++) { - xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr - = (frame_nb + i) * opt_xsk_frame_size; - xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len = - sizeof(pkt_data) - 1; - } - - xsk_ring_prod__submit(&xsk->tx, BATCH_SIZE); - xsk->outstanding_tx += BATCH_SIZE; - frame_nb += BATCH_SIZE; - frame_nb %= NUM_FRAMES; - } - - complete_tx_only(xsk); + for (i = 0; i < num_socks; i++) + tx_only(xsks[i], frame_nb[i]); } } -static void l2fwd(struct xsk_socket_info *xsk) +static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) { - for (;;) { - unsigned int rcvd, i; - u32 idx_rx = 0, idx_tx = 0; - int ret; + unsigned int rcvd, i; + u32 idx_rx = 0, idx_tx = 0; + int ret; - for (;;) { - complete_tx_l2fwd(xsk); + complete_tx_l2fwd(xsk, fds); - rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, - &idx_rx); - if (rcvd > 0) - break; - } + rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); + if (!rcvd) { + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + ret = poll(fds, num_socks, opt_timeout); + return; + } + ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + if (xsk_ring_prod__needs_wakeup(&xsk->tx)) + kick_tx(xsk); ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); - while (ret != rcvd) { - if (ret < 0) - exit_with_error(-ret); - ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); - } + } + + for (i = 0; i < rcvd; i++) { + u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr; + u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len; + char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); + + swap_mac_addresses(pkt); - for (i = 0; i < rcvd; i++) { - u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, - idx_rx)->addr; - u32 len = xsk_ring_cons__rx_desc(&xsk->rx, - idx_rx++)->len; - char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); + hex_dump(pkt, len, addr); + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = addr; + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len; + } - swap_mac_addresses(pkt); + xsk_ring_prod__submit(&xsk->tx, rcvd); + xsk_ring_cons__release(&xsk->rx, rcvd); - hex_dump(pkt, len, addr); - xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = addr; - xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len; - } + xsk->rx_npkts += rcvd; + xsk->outstanding_tx += rcvd; +} + +static void l2fwd_all(void) +{ + struct pollfd fds[MAX_SOCKS]; + int i, ret; + + memset(fds, 0, sizeof(fds)); + + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); + fds[i].events = POLLOUT | POLLIN; + } - xsk_ring_prod__submit(&xsk->tx, rcvd); - xsk_ring_cons__release(&xsk->rx, rcvd); + for (;;) { + if (opt_poll) { + ret = poll(fds, num_socks, opt_timeout); + if (ret <= 0) + continue; + } - xsk->rx_npkts += rcvd; - xsk->outstanding_tx += rcvd; + for (i = 0; i < num_socks; i++) + l2fwd(xsks[i], fds); } } @@ -705,9 +753,9 @@ int main(int argc, char **argv) if (opt_bench == BENCH_RXDROP) rx_drop_all(); else if (opt_bench == BENCH_TXONLY) - tx_only(xsks[0]); + tx_only_all(); else - l2fwd(xsks[0]); + l2fwd_all(); return 0; } -- cgit v1.2.3 From bb4b5c08a8e0f854a313184498b22fa37dd087db Mon Sep 17 00:00:00 2001 From: Ivan Khoronzhuk Date: Thu, 15 Aug 2019 15:13:56 +0300 Subject: samples: bpf: syscall_nrs: use mmap2 if defined For arm32 xdp sockets mmap2 is preferred, so use it if it's defined. Declaration of __NR_mmap can be skipped and it breaks build. Signed-off-by: Ivan Khoronzhuk Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- samples/bpf/syscall_nrs.c | 6 ++++++ samples/bpf/tracex5_kern.c | 13 +++++++++++++ 2 files changed, 19 insertions(+) (limited to 'samples') diff --git a/samples/bpf/syscall_nrs.c b/samples/bpf/syscall_nrs.c index 516e255cbe8f..88f940052450 100644 --- a/samples/bpf/syscall_nrs.c +++ b/samples/bpf/syscall_nrs.c @@ -9,5 +9,11 @@ void syscall_defines(void) COMMENT("Linux system call numbers."); SYSNR(__NR_write); SYSNR(__NR_read); +#ifdef __NR_mmap2 + SYSNR(__NR_mmap2); +#endif +#ifdef __NR_mmap SYSNR(__NR_mmap); +#endif + } diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c index f57f4e1ea1ec..35cb0eed3be5 100644 --- a/samples/bpf/tracex5_kern.c +++ b/samples/bpf/tracex5_kern.c @@ -68,12 +68,25 @@ PROG(SYS__NR_read)(struct pt_regs *ctx) return 0; } +#ifdef __NR_mmap2 +PROG(SYS__NR_mmap2)(struct pt_regs *ctx) +{ + char fmt[] = "mmap2\n"; + + bpf_trace_printk(fmt, sizeof(fmt)); + return 0; +} +#endif + +#ifdef __NR_mmap PROG(SYS__NR_mmap)(struct pt_regs *ctx) { char fmt[] = "mmap\n"; + bpf_trace_printk(fmt, sizeof(fmt)); return 0; } +#endif char _license[] SEC("license") = "GPL"; u32 _version SEC("version") = LINUX_VERSION_CODE; -- cgit v1.2.3 From c543f54698229b50078b72760b9e8a4731cffa03 Mon Sep 17 00:00:00 2001 From: Kevin Laatz Date: Tue, 27 Aug 2019 02:25:28 +0000 Subject: samples/bpf: add unaligned chunks mode support to xdpsock This patch adds support for the unaligned chunks mode. The addition of the unaligned chunks option will allow users to run the application with more relaxed chunk placement in the XDP umem. Unaligned chunks mode can be used with the '-u' or '--unaligned' command line options. Signed-off-by: Kevin Laatz Signed-off-by: Ciara Loftus Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- samples/bpf/xdpsock_user.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'samples') diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index da84c760c094..7312eab4d201 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -68,6 +68,9 @@ static int opt_queue; static int opt_poll; static int opt_interval = 1; static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; +static u32 opt_umem_flags; +static int opt_unaligned_chunks; +static u32 opt_xdp_bind_flags; static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static int opt_timeout = 1000; static bool opt_need_wakeup = true; @@ -284,7 +287,9 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, .frame_size = opt_xsk_frame_size, .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, + .flags = opt_umem_flags }; + int ret; umem = calloc(1, sizeof(*umem)); @@ -293,6 +298,7 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, &cfg); + if (ret) exit_with_error(-ret); @@ -355,6 +361,7 @@ static struct option long_options[] = { {"copy", no_argument, 0, 'c'}, {"frame-size", required_argument, 0, 'f'}, {"no-need-wakeup", no_argument, 0, 'm'}, + {"unaligned", no_argument, 0, 'u'}, {0, 0, 0, 0} }; @@ -376,6 +383,8 @@ static void usage(const char *prog) " -c, --copy Force copy mode.\n" " -f, --frame-size=n Set the frame size (must be a power of two, default is %d).\n" " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n" + " -f, --frame-size=n Set the frame size (must be a power of two in aligned mode, default is %d).\n" + " -u, --unaligned Enable unaligned chunk placement\n" "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE); exit(EXIT_FAILURE); @@ -388,8 +397,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - - c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:m", + c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:mu", long_options, &option_index); if (c == -1) break; @@ -429,6 +437,10 @@ static void parse_command_line(int argc, char **argv) case 'c': opt_xdp_bind_flags |= XDP_COPY; break; + case 'u': + opt_umem_flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; + opt_unaligned_chunks = 1; + break; case 'F': opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; break; @@ -438,6 +450,7 @@ static void parse_command_line(int argc, char **argv) opt_need_wakeup = false; opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP; break; + default: usage(basename(argv[0])); } @@ -450,7 +463,8 @@ static void parse_command_line(int argc, char **argv) usage(basename(argv[0])); } - if (opt_xsk_frame_size & (opt_xsk_frame_size - 1)) { + if ((opt_xsk_frame_size & (opt_xsk_frame_size - 1)) && + !opt_unaligned_chunks) { fprintf(stderr, "--frame-size=%d is not a power of two\n", opt_xsk_frame_size); usage(basename(argv[0])); -- cgit v1.2.3 From 03895e63ff97447e5eab1b71ed46e3662a45bfe8 Mon Sep 17 00:00:00 2001 From: Kevin Laatz Date: Tue, 27 Aug 2019 02:25:29 +0000 Subject: samples/bpf: add buffer recycling for unaligned chunks to xdpsock This patch adds buffer recycling support for unaligned buffers. Since we don't mask the addr to 2k at umem_reg in unaligned mode, we need to make sure we give back the correct (original) addr to the fill queue. We achieve this using the new descriptor format and associated masks. The new format uses the upper 16-bits for the offset and the lower 48-bits for the addr. Since we have a field for the offset, we no longer need to modify the actual address. As such, all we have to do to get back the original address is mask for the lower 48 bits (i.e. strip the offset and we get the address on it's own). Signed-off-by: Kevin Laatz Signed-off-by: Bruce Richardson Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- samples/bpf/xdpsock_user.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'samples') diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 7312eab4d201..dc3d50f8ed86 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -484,6 +484,7 @@ static void kick_tx(struct xsk_socket_info *xsk) static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) { + struct xsk_umem_info *umem = xsk->umem; u32 idx_cq = 0, idx_fq = 0; unsigned int rcvd; size_t ndescs; @@ -498,24 +499,23 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, xsk->outstanding_tx; /* re-add completed Tx buffers */ - rcvd = xsk_ring_cons__peek(&xsk->umem->cq, ndescs, &idx_cq); + rcvd = xsk_ring_cons__peek(&umem->cq, ndescs, &idx_cq); if (rcvd > 0) { unsigned int i; int ret; - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + if (xsk_ring_prod__needs_wakeup(&umem->fq)) ret = poll(fds, num_socks, opt_timeout); - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, - &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } + for (i = 0; i < rcvd; i++) - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = - *xsk_ring_cons__comp_addr(&xsk->umem->cq, - idx_cq++); + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = + *xsk_ring_cons__comp_addr(&umem->cq, idx_cq++); xsk_ring_prod__submit(&xsk->umem->fq, rcvd); xsk_ring_cons__release(&xsk->umem->cq, rcvd); @@ -568,10 +568,13 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) for (i = 0; i < rcvd; i++) { u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr; u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len; + u64 orig = xsk_umem__extract_addr(addr); + + addr = xsk_umem__add_offset_to_addr(addr); char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); hex_dump(pkt, len, addr); - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = addr; + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; } xsk_ring_prod__submit(&xsk->umem->fq, rcvd); @@ -680,12 +683,15 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) for (i = 0; i < rcvd; i++) { u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr; u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len; + u64 orig = xsk_umem__extract_addr(addr); + + addr = xsk_umem__add_offset_to_addr(addr); char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); swap_mac_addresses(pkt); hex_dump(pkt, len, addr); - xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = addr; + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = orig; xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len; } -- cgit v1.2.3 From 3945b37a975d22bed33b525f2933bac82424793d Mon Sep 17 00:00:00 2001 From: Kevin Laatz Date: Tue, 27 Aug 2019 02:25:30 +0000 Subject: samples/bpf: use hugepages in xdpsock app This patch modifies xdpsock to use mmap instead of posix_memalign. With this change, we can use hugepages when running the application in unaligned chunks mode. Using hugepages makes it more likely that we have physically contiguous memory, which supports the unaligned chunk mode better. Signed-off-by: Kevin Laatz Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- samples/bpf/xdpsock_user.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'samples') diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index dc3d50f8ed86..102eace22956 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -70,6 +70,7 @@ static int opt_interval = 1; static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; static u32 opt_umem_flags; static int opt_unaligned_chunks; +static int opt_mmap_flags; static u32 opt_xdp_bind_flags; static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static int opt_timeout = 1000; @@ -440,6 +441,7 @@ static void parse_command_line(int argc, char **argv) case 'u': opt_umem_flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; opt_unaligned_chunks = 1; + opt_mmap_flags = MAP_HUGETLB; break; case 'F': opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -742,11 +744,14 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } - ret = posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */ - NUM_FRAMES * opt_xsk_frame_size); - if (ret) - exit_with_error(ret); - + /* Reserve memory for the umem. Use hugepages if unaligned chunk mode */ + bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | opt_mmap_flags, -1, 0); + if (bufs == MAP_FAILED) { + printf("ERROR: mmap failed\n"); + exit(EXIT_FAILURE); + } /* Create sockets... */ umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size); xsks[num_socks++] = xsk_configure_socket(umem); -- cgit v1.2.3