* [net-next V7 PATCH 5/5] samples/bpf: add cpumap sample program xdp_redirect_cpu
From: Jesper Dangaard Brouer @ 2017-10-12 12:27 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, ast, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
In-Reply-To: <150781116384.9409.2491501775270038284.stgit@firesoul>
This sample program show how to use cpumap and the associated
tracepoints.
It provides command line stats, which shows how the XDP-RX process,
cpumap-enqueue and cpumap kthread dequeue is cooperating on a per CPU
basis. It also utilize the xdp_exception and xdp_redirect_err
transpoints to allow users quickly to identify setup issues.
One issue with ixgbe driver is that the driver reset the link when
loading XDP. This reset the procfs smp_affinity settings. Thus,
after loading the program, these must be reconfigured. The easiest
workaround it to reduce the RX-queue to e.g. two via:
# ethtool --set-channels ixgbe1 combined 2
And then add CPUs above 0 and 1, like:
# xdp_redirect_cpu --dev ixgbe1 --prog 2 --cpu 2 --cpu 3 --cpu 4
Another issue with ixgbe is that the page recycle mechanism is tied to
the RX-ring size. And the default setting of 512 elements is too
small. This is the same issue with regular devmap XDP_REDIRECT.
To overcome this I've been using 1024 rx-ring size:
# ethtool -G ixgbe1 rx 1024 tx 1024
V3:
- whitespace cleanups
- bpf tracepoint cannot access top part of struct
V4:
- report on kthread sched events, according to tracepoint change
- report average bulk enqueue size
V5:
- bpf_map_lookup_elem on cpumap not allowed from bpf_prog
use separate map to mark CPUs not available
V6:
- correct kthread sched summary output
V7:
- Added a --stress-mode for concurrently changing underlying cpumap
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
samples/bpf/Makefile | 4
samples/bpf/xdp_redirect_cpu_kern.c | 609 +++++++++++++++++++++++++++++++
samples/bpf/xdp_redirect_cpu_user.c | 697 +++++++++++++++++++++++++++++++++++
3 files changed, 1310 insertions(+)
create mode 100644 samples/bpf/xdp_redirect_cpu_kern.c
create mode 100644 samples/bpf/xdp_redirect_cpu_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index ebc2ad69b62c..52c4dab2c153 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -39,6 +39,7 @@ hostprogs-y += per_socket_stats_example
hostprogs-y += load_sock_ops
hostprogs-y += xdp_redirect
hostprogs-y += xdp_redirect_map
+hostprogs-y += xdp_redirect_cpu
hostprogs-y += xdp_monitor
hostprogs-y += syscall_tp
@@ -84,6 +85,7 @@ test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
+xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
@@ -129,6 +131,7 @@ always += tcp_iw_kern.o
always += tcp_clamp_kern.o
always += xdp_redirect_kern.o
always += xdp_redirect_map_kern.o
+always += xdp_redirect_cpu_kern.o
always += xdp_monitor_kern.o
always += syscall_tp_kern.o
@@ -169,6 +172,7 @@ HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
HOSTLOADLIBES_test_map_in_map += -lelf
HOSTLOADLIBES_xdp_redirect += -lelf
HOSTLOADLIBES_xdp_redirect_map += -lelf
+HOSTLOADLIBES_xdp_redirect_cpu += -lelf
HOSTLOADLIBES_xdp_monitor += -lelf
HOSTLOADLIBES_syscall_tp += -lelf
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
new file mode 100644
index 000000000000..303e9e7161f3
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -0,0 +1,609 @@
+/* XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP)
+ *
+ * GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+ */
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/if_vlan.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
+
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define MAX_CPUS 12 /* WARNING - sync with _user.c */
+
+/* Special map type that can XDP_REDIRECT frames to another CPU */
+struct bpf_map_def SEC("maps") cpu_map = {
+ .type = BPF_MAP_TYPE_CPUMAP,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = MAX_CPUS,
+};
+
+/* Common stats data record to keep userspace more simple */
+struct datarec {
+ __u64 processed;
+ __u64 dropped;
+ __u64 issue;
+};
+
+/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
+ * feedback. Redirect TX errors can be caught via a tracepoint.
+ */
+struct bpf_map_def SEC("maps") rx_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 1,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") redirect_err_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 2,
+ /* TODO: have entries for all possible errno's */
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = MAX_CPUS,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") cpumap_kthread_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 1,
+};
+
+/* Set of maps controlling available CPU, and for iterating through
+ * selectable redirect CPUs.
+ */
+struct bpf_map_def SEC("maps") cpus_available = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = MAX_CPUS,
+};
+struct bpf_map_def SEC("maps") cpus_count = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = 1,
+};
+struct bpf_map_def SEC("maps") cpus_iterator = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = 1,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") exception_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 1,
+};
+
+/* Helper parse functions */
+
+/* Parse Ethernet layer 2, extract network layer 3 offset and protocol
+ *
+ * Returns false on error and non-supported ether-type
+ */
+struct vlan_hdr {
+ __be16 h_vlan_TCI;
+ __be16 h_vlan_encapsulated_proto;
+};
+
+static __always_inline
+bool parse_eth(struct ethhdr *eth, void *data_end,
+ u16 *eth_proto, u64 *l3_offset)
+{
+ u16 eth_type;
+ u64 offset;
+
+ offset = sizeof(*eth);
+ if ((void *)eth + offset > data_end)
+ return false;
+
+ eth_type = eth->h_proto;
+
+ /* Skip non 802.3 Ethertypes */
+ if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN))
+ return false;
+
+ /* Handle VLAN tagged packet */
+ if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+ struct vlan_hdr *vlan_hdr;
+
+ vlan_hdr = (void *)eth + offset;
+ offset += sizeof(*vlan_hdr);
+ if ((void *)eth + offset > data_end)
+ return false;
+ eth_type = vlan_hdr->h_vlan_encapsulated_proto;
+ }
+ /* TODO: Handle double VLAN tagged packet */
+
+ *eth_proto = ntohs(eth_type);
+ *l3_offset = offset;
+ return true;
+}
+
+static __always_inline
+u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct iphdr *iph = data + nh_off;
+ struct udphdr *udph;
+ u16 dport;
+
+ if (iph + 1 > data_end)
+ return 0;
+ if (!(iph->protocol == IPPROTO_UDP))
+ return 0;
+
+ udph = (void *)(iph + 1);
+ if (udph + 1 > data_end)
+ return 0;
+
+ dport = ntohs(udph->dest);
+ return dport;
+}
+
+static __always_inline
+int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct iphdr *iph = data + nh_off;
+
+ if (iph + 1 > data_end)
+ return 0;
+ return iph->protocol;
+}
+
+static __always_inline
+int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ipv6hdr *ip6h = data + nh_off;
+
+ if (ip6h + 1 > data_end)
+ return 0;
+ return ip6h->nexthdr;
+}
+
+SEC("xdp_cpu_map0")
+int xdp_prognum0_no_touch(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct datarec *rec;
+ u32 *cpu_selected;
+ u32 cpu_dest;
+ u32 key = 0;
+
+ /* Only use first entry in cpus_available */
+ cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+ if (!cpu_selected)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_selected;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map1_touch_data")
+int xdp_prognum1_touch_data(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ struct datarec *rec;
+ u32 *cpu_selected;
+ u32 cpu_dest;
+ u16 eth_type;
+ u32 key = 0;
+
+ /* Only use first entry in cpus_available */
+ cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+ if (!cpu_selected)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_selected;
+
+ /* Validate packet length is minimum Eth header size */
+ if (eth + 1 > data_end)
+ return XDP_ABORTED;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ /* Read packet data, and use it (drop non 802.3 Ethertypes) */
+ eth_type = eth->h_proto;
+ if (ntohs(eth_type) < ETH_P_802_3_MIN) {
+ rec->dropped++;
+ return XDP_DROP;
+ }
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map2_round_robin")
+int xdp_prognum2_round_robin(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ struct datarec *rec;
+ u32 cpu_dest;
+ u32 *cpu_lookup;
+ u32 key0 = 0;
+
+ u32 *cpu_selected;
+ u32 *cpu_iterator;
+ u32 *cpu_max;
+ u32 cpu_idx;
+
+ cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
+ if (!cpu_max)
+ return XDP_ABORTED;
+
+ cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0);
+ if (!cpu_iterator)
+ return XDP_ABORTED;
+ cpu_idx = *cpu_iterator;
+
+ *cpu_iterator += 1;
+ if (*cpu_iterator == *cpu_max)
+ *cpu_iterator = 0;
+
+ cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+ if (!cpu_selected)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_selected;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key0);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map3_proto_separate")
+int xdp_prognum3_proto_separate(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ u8 ip_proto = IPPROTO_UDP;
+ struct datarec *rec;
+ u16 eth_proto = 0;
+ u64 l3_offset = 0;
+ u32 cpu_dest = 0;
+ u32 cpu_idx = 0;
+ u32 *cpu_lookup;
+ u32 key = 0;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (!(parse_eth(eth, data_end, ð_proto, &l3_offset)))
+ return XDP_PASS; /* Just skip */
+
+ /* Extract L4 protocol */
+ switch (eth_proto) {
+ case ETH_P_IP:
+ ip_proto = get_proto_ipv4(ctx, l3_offset);
+ break;
+ case ETH_P_IPV6:
+ ip_proto = get_proto_ipv6(ctx, l3_offset);
+ break;
+ case ETH_P_ARP:
+ cpu_idx = 0; /* ARP packet handled on separate CPU */
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ /* Choose CPU based on L4 protocol */
+ switch (ip_proto) {
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ cpu_idx = 2;
+ break;
+ case IPPROTO_TCP:
+ cpu_idx = 0;
+ break;
+ case IPPROTO_UDP:
+ cpu_idx = 1;
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+ if (!cpu_lookup)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_lookup;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map4_ddos_filter_pktgen")
+int xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ u8 ip_proto = IPPROTO_UDP;
+ struct datarec *rec;
+ u16 eth_proto = 0;
+ u64 l3_offset = 0;
+ u32 cpu_dest = 0;
+ u32 cpu_idx = 0;
+ u16 dest_port;
+ u32 *cpu_lookup;
+ u32 key = 0;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (!(parse_eth(eth, data_end, ð_proto, &l3_offset)))
+ return XDP_PASS; /* Just skip */
+
+ /* Extract L4 protocol */
+ switch (eth_proto) {
+ case ETH_P_IP:
+ ip_proto = get_proto_ipv4(ctx, l3_offset);
+ break;
+ case ETH_P_IPV6:
+ ip_proto = get_proto_ipv6(ctx, l3_offset);
+ break;
+ case ETH_P_ARP:
+ cpu_idx = 0; /* ARP packet handled on separate CPU */
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ /* Choose CPU based on L4 protocol */
+ switch (ip_proto) {
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ cpu_idx = 2;
+ break;
+ case IPPROTO_TCP:
+ cpu_idx = 0;
+ break;
+ case IPPROTO_UDP:
+ cpu_idx = 1;
+ /* DDoS filter UDP port 9 (pktgen) */
+ dest_port = get_dest_port_ipv4_udp(ctx, l3_offset);
+ if (dest_port == 9) {
+ if (rec)
+ rec->dropped++;
+ return XDP_DROP;
+ }
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+ if (!cpu_lookup)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_lookup;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+
+char _license[] SEC("license") = "GPL";
+
+/*** Trace point code ***/
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct xdp_redirect_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int prog_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12 size:4; signed:0;
+ int ifindex; // offset:16 size:4; signed:1;
+ int err; // offset:20 size:4; signed:1;
+ int to_ifindex; // offset:24 size:4; signed:1;
+ u32 map_id; // offset:28 size:4; signed:0;
+ int map_index; // offset:32 size:4; signed:1;
+}; // offset:36
+
+enum {
+ XDP_REDIRECT_SUCCESS = 0,
+ XDP_REDIRECT_ERROR = 1
+};
+
+static __always_inline
+int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx)
+{
+ u32 key = XDP_REDIRECT_ERROR;
+ struct datarec *rec;
+ int err = ctx->err;
+
+ if (!err)
+ key = XDP_REDIRECT_SUCCESS;
+
+ rec = bpf_map_lookup_elem(&redirect_err_cnt, &key);
+ if (!rec)
+ return 0;
+ rec->dropped += 1;
+
+ return 0; /* Indicate event was filtered (no further processing)*/
+ /*
+ * Returning 1 here would allow e.g. a perf-record tracepoint
+ * to see and record these events, but it doesn't work well
+ * in-practice as stopping perf-record also unload this
+ * bpf_prog. Plus, there is additional overhead of doing so.
+ */
+}
+
+SEC("tracepoint/xdp/xdp_redirect_err")
+int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx)
+{
+ return xdp_redirect_collect_stat(ctx);
+}
+
+SEC("tracepoint/xdp/xdp_redirect_map_err")
+int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx)
+{
+ return xdp_redirect_collect_stat(ctx);
+}
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct xdp_exception_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int prog_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12; size:4; signed:0;
+ int ifindex; // offset:16; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_exception")
+int trace_xdp_exception(struct xdp_exception_ctx *ctx)
+{
+ struct datarec *rec;
+ u32 key = 0;
+
+ rec = bpf_map_lookup_elem(&exception_cnt, &key);
+ if (!rec)
+ return 1;
+ rec->dropped += 1;
+
+ return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct cpumap_enqueue_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int map_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12; size:4; signed:0;
+ int cpu; // offset:16; size:4; signed:1;
+ unsigned int drops; // offset:20; size:4; signed:0;
+ unsigned int processed; // offset:24; size:4; signed:0;
+ int to_cpu; // offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_enqueue")
+int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
+{
+ u32 to_cpu = ctx->to_cpu;
+ struct datarec *rec;
+
+ if (to_cpu >= MAX_CPUS)
+ return 1;
+
+ rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu);
+ if (!rec)
+ return 0;
+ rec->processed += ctx->processed;
+ rec->dropped += ctx->drops;
+
+ /* Record bulk events, then userspace can calc average bulk size */
+ if (ctx->processed > 0)
+ rec->issue += 1;
+
+ /* Inception: It's possible to detect overload situations, via
+ * this tracepoint. This can be used for creating a feedback
+ * loop to XDP, which can take appropriate actions to mitigate
+ * this overload situation.
+ */
+ return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct cpumap_kthread_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int map_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12; size:4; signed:0;
+ int cpu; // offset:16; size:4; signed:1;
+ unsigned int drops; // offset:20; size:4; signed:0;
+ unsigned int processed; // offset:24; size:4; signed:0;
+ int sched; // offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_kthread")
+int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
+{
+ struct datarec *rec;
+ u32 key = 0;
+
+ rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key);
+ if (!rec)
+ return 0;
+ rec->processed += ctx->processed;
+ rec->dropped += ctx->drops;
+
+ /* Count times kthread yielded CPU via schedule call */
+ if (ctx->sched)
+ rec->issue++;
+
+ return 0;
+}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
new file mode 100644
index 000000000000..35fec9fecb57
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -0,0 +1,697 @@
+/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+ */
+static const char *__doc__ =
+ " XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\"";
+
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <locale.h>
+#include <sys/resource.h>
+#include <getopt.h>
+#include <net/if.h>
+#include <time.h>
+
+#include <arpa/inet.h>
+#include <linux/if_link.h>
+
+#define MAX_CPUS 12 /* WARNING - sync with _kern.c */
+
+/* How many xdp_progs are defined in _kern.c */
+#define MAX_PROG 5
+
+/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
+ * use bpf/libbpf.h), but cannot as (currently) needed for XDP
+ * attaching to a device via set_link_xdp_fd()
+ */
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#include "bpf_util.h"
+
+static int ifindex = -1;
+static char ifname_buf[IF_NAMESIZE];
+static char *ifname;
+
+static __u32 xdp_flags;
+
+/* Exit return codes */
+#define EXIT_OK 0
+#define EXIT_FAIL 1
+#define EXIT_FAIL_OPTION 2
+#define EXIT_FAIL_XDP 3
+#define EXIT_FAIL_BPF 4
+#define EXIT_FAIL_MEM 5
+
+static const struct option long_options[] = {
+ {"help", no_argument, NULL, 'h' },
+ {"dev", required_argument, NULL, 'd' },
+ {"skb-mode", no_argument, NULL, 'S' },
+ {"debug", no_argument, NULL, 'D' },
+ {"sec", required_argument, NULL, 's' },
+ {"prognum", required_argument, NULL, 'p' },
+ {"qsize", required_argument, NULL, 'q' },
+ {"cpu", required_argument, NULL, 'c' },
+ {"stress-mode", no_argument, NULL, 'x' },
+ {"no-separators", no_argument, NULL, 'z' },
+ {0, 0, NULL, 0 }
+};
+
+static void int_exit(int sig)
+{
+ fprintf(stderr,
+ "Interrupted: Removing XDP program on ifindex:%d device:%s\n",
+ ifindex, ifname);
+ if (ifindex > -1)
+ set_link_xdp_fd(ifindex, -1, xdp_flags);
+ exit(EXIT_OK);
+}
+
+static void usage(char *argv[])
+{
+ int i;
+
+ printf("\nDOCUMENTATION:\n%s\n", __doc__);
+ printf("\n");
+ printf(" Usage: %s (options-see-below)\n", argv[0]);
+ printf(" Listing options:\n");
+ for (i = 0; long_options[i].name != 0; i++) {
+ printf(" --%-12s", long_options[i].name);
+ if (long_options[i].flag != NULL)
+ printf(" flag (internal value:%d)",
+ *long_options[i].flag);
+ else
+ printf(" short-option: -%c",
+ long_options[i].val);
+ printf("\n");
+ }
+ printf("\n");
+}
+
+/* gettime returns the current time of day in nanoseconds.
+ * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC)
+ * clock_gettime (ns) => 9ns (CLOCK_MONOTONIC_COARSE)
+ */
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+static __u64 gettime(void)
+{
+ struct timespec t;
+ int res;
+
+ res = clock_gettime(CLOCK_MONOTONIC, &t);
+ if (res < 0) {
+ fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
+ exit(EXIT_FAIL);
+ }
+ return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
+}
+
+/* Common stats data record shared with _kern.c */
+struct datarec {
+ __u64 processed;
+ __u64 dropped;
+ __u64 issue;
+};
+struct record {
+ __u64 timestamp;
+ struct datarec total;
+ struct datarec *cpu;
+};
+struct stats_record {
+ struct record rx_cnt;
+ struct record redir_err;
+ struct record kthread;
+ struct record exception;
+ struct record enq[MAX_CPUS];
+};
+
+static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
+{
+ /* For percpu maps, userspace gets a value per possible CPU */
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ struct datarec values[nr_cpus];
+ __u64 sum_processed = 0;
+ __u64 sum_dropped = 0;
+ __u64 sum_issue = 0;
+ int i;
+
+ if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
+ fprintf(stderr,
+ "ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
+ return false;
+ }
+ /* Get time as close as possible to reading map contents */
+ rec->timestamp = gettime();
+
+ /* Record and sum values from each CPU */
+ for (i = 0; i < nr_cpus; i++) {
+ rec->cpu[i].processed = values[i].processed;
+ sum_processed += values[i].processed;
+ rec->cpu[i].dropped = values[i].dropped;
+ sum_dropped += values[i].dropped;
+ rec->cpu[i].issue = values[i].issue;
+ sum_issue += values[i].issue;
+ }
+ rec->total.processed = sum_processed;
+ rec->total.dropped = sum_dropped;
+ rec->total.issue = sum_issue;
+ return true;
+}
+
+static struct datarec *alloc_record_per_cpu(void)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ struct datarec *array;
+ size_t size;
+
+ size = sizeof(struct datarec) * nr_cpus;
+ array = malloc(size);
+ memset(array, 0, size);
+ if (!array) {
+ fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
+ exit(EXIT_FAIL_MEM);
+ }
+ return array;
+}
+
+static struct stats_record *alloc_stats_record(void)
+{
+ struct stats_record *rec;
+ int i;
+
+ rec = malloc(sizeof(*rec));
+ memset(rec, 0, sizeof(*rec));
+ if (!rec) {
+ fprintf(stderr, "Mem alloc error\n");
+ exit(EXIT_FAIL_MEM);
+ }
+ rec->rx_cnt.cpu = alloc_record_per_cpu();
+ rec->redir_err.cpu = alloc_record_per_cpu();
+ rec->kthread.cpu = alloc_record_per_cpu();
+ rec->exception.cpu = alloc_record_per_cpu();
+ for (i = 0; i < MAX_CPUS; i++)
+ rec->enq[i].cpu = alloc_record_per_cpu();
+
+ return rec;
+}
+
+static void free_stats_record(struct stats_record *r)
+{
+ int i;
+
+ for (i = 0; i < MAX_CPUS; i++)
+ free(r->enq[i].cpu);
+ free(r->exception.cpu);
+ free(r->kthread.cpu);
+ free(r->redir_err.cpu);
+ free(r->rx_cnt.cpu);
+ free(r);
+}
+
+static double calc_period(struct record *r, struct record *p)
+{
+ double period_ = 0;
+ __u64 period = 0;
+
+ period = r->timestamp - p->timestamp;
+ if (period > 0)
+ period_ = ((double) period / NANOSEC_PER_SEC);
+
+ return period_;
+}
+
+static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
+{
+ __u64 packets = 0;
+ __u64 pps = 0;
+
+ if (period_ > 0) {
+ packets = r->processed - p->processed;
+ pps = packets / period_;
+ }
+ return pps;
+}
+
+static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_)
+{
+ __u64 packets = 0;
+ __u64 pps = 0;
+
+ if (period_ > 0) {
+ packets = r->dropped - p->dropped;
+ pps = packets / period_;
+ }
+ return pps;
+}
+
+static __u64 calc_errs_pps(struct datarec *r,
+ struct datarec *p, double period_)
+{
+ __u64 packets = 0;
+ __u64 pps = 0;
+
+ if (period_ > 0) {
+ packets = r->issue - p->issue;
+ pps = packets / period_;
+ }
+ return pps;
+}
+
+static void stats_print(struct stats_record *stats_rec,
+ struct stats_record *stats_prev,
+ int prog_num)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ double pps = 0, drop = 0, err = 0;
+ struct record *rec, *prev;
+ int to_cpu;
+ double t;
+ int i;
+
+ /* Header */
+ printf("Running XDP/eBPF prog_num:%d\n", prog_num);
+ printf("%-15s %-7s %-14s %-11s %-9s\n",
+ "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info");
+
+ /* XDP rx_cnt */
+ {
+ char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
+ char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n";
+ char *errstr = "";
+
+ rec = &stats_rec->rx_cnt;
+ prev = &stats_prev->rx_cnt;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ err = calc_errs_pps(r, p, t);
+ if (err > 0)
+ errstr = "cpu-dest/err";
+ if (pps > 0)
+ printf(fmt_rx, "XDP-RX",
+ i, pps, drop, err, errstr);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ err = calc_errs_pps(&rec->total, &prev->total, t);
+ printf(fm2_rx, "XDP-RX", "total", pps, drop);
+ }
+
+ /* cpumap enqueue stats */
+ for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) {
+ char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
+ char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
+ char *errstr = "";
+
+ rec = &stats_rec->enq[to_cpu];
+ prev = &stats_prev->enq[to_cpu];
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ err = calc_errs_pps(r, p, t);
+ if (err > 0) {
+ errstr = "bulk-average";
+ err = pps / err; /* calc average bulk size */
+ }
+ if (pps > 0)
+ printf(fmt, "cpumap-enqueue",
+ i, to_cpu, pps, drop, err, errstr);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ if (pps > 0) {
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ err = calc_errs_pps(&rec->total, &prev->total, t);
+ if (err > 0) {
+ errstr = "bulk-average";
+ err = pps / err; /* calc average bulk size */
+ }
+ printf(fm2, "cpumap-enqueue",
+ "sum", to_cpu, pps, drop, err, errstr);
+ }
+ }
+
+ /* cpumap kthread stats */
+ {
+ char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
+ char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n";
+ char *e_str = "";
+
+ rec = &stats_rec->kthread;
+ prev = &stats_prev->kthread;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ err = calc_errs_pps(r, p, t);
+ if (err > 0)
+ e_str = "sched";
+ if (pps > 0)
+ printf(fmt_k, "cpumap_kthread",
+ i, pps, drop, err, e_str);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ err = calc_errs_pps(&rec->total, &prev->total, t);
+ if (err > 0)
+ e_str = "sched-sum";
+ printf(fm2_k, "cpumap_kthread", "total", pps, drop, err, e_str);
+ }
+
+ /* XDP redirect err tracepoints (very unlikely) */
+ {
+ char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
+ char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
+
+ rec = &stats_rec->redir_err;
+ prev = &stats_prev->redir_err;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ if (pps > 0)
+ printf(fmt_err, "redirect_err", i, pps, drop);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ printf(fm2_err, "redirect_err", "total", pps, drop);
+ }
+
+ /* XDP general exception tracepoints */
+ {
+ char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
+ char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
+
+ rec = &stats_rec->exception;
+ prev = &stats_prev->exception;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ if (pps > 0)
+ printf(fmt_err, "xdp_exception", i, pps, drop);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ printf(fm2_err, "xdp_exception", "total", pps, drop);
+ }
+
+ printf("\n");
+ fflush(stdout);
+}
+
+static void stats_collect(struct stats_record *rec)
+{
+ int fd, i;
+
+ fd = map_fd[1]; /* map: rx_cnt */
+ map_collect_percpu(fd, 0, &rec->rx_cnt);
+
+ fd = map_fd[2]; /* map: redirect_err_cnt */
+ map_collect_percpu(fd, 1, &rec->redir_err);
+
+ fd = map_fd[3]; /* map: cpumap_enqueue_cnt */
+ for (i = 0; i < MAX_CPUS; i++)
+ map_collect_percpu(fd, i, &rec->enq[i]);
+
+ fd = map_fd[4]; /* map: cpumap_kthread_cnt */
+ map_collect_percpu(fd, 0, &rec->kthread);
+
+ fd = map_fd[8]; /* map: exception_cnt */
+ map_collect_percpu(fd, 0, &rec->exception);
+}
+
+
+/* Pointer swap trick */
+static inline void swap(struct stats_record **a, struct stats_record **b)
+{
+ struct stats_record *tmp;
+
+ tmp = *a;
+ *a = *b;
+ *b = tmp;
+}
+
+static int create_cpu_entry(__u32 cpu, __u32 queue_size,
+ __u32 avail_idx, bool new)
+{
+ __u32 curr_cpus_count = 0;
+ __u32 key = 0;
+ int ret;
+
+ /* Add a CPU entry to cpumap, as this allocate a cpu entry in
+ * the kernel for the cpu.
+ */
+ ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0);
+ if (ret) {
+ fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret);
+ exit(EXIT_FAIL_BPF);
+ }
+
+ /* Inform bpf_prog's that a new CPU is available to select
+ * from via some control maps.
+ */
+ /* map_fd[5] = cpus_available */
+ ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0);
+ if (ret) {
+ fprintf(stderr, "Add to avail CPUs failed\n");
+ exit(EXIT_FAIL_BPF);
+ }
+
+ /* When not replacing/updating existing entry, bump the count */
+ /* map_fd[6] = cpus_count */
+ ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count);
+ if (ret) {
+ fprintf(stderr, "Failed reading curr cpus_count\n");
+ exit(EXIT_FAIL_BPF);
+ }
+ if (new) {
+ curr_cpus_count++;
+ ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0);
+ if (ret) {
+ fprintf(stderr, "Failed write curr cpus_count\n");
+ exit(EXIT_FAIL_BPF);
+ }
+ }
+ /* map_fd[7] = cpus_iterator */
+ printf("%s CPU:%u as idx:%u queue_size:%d (total cpus_count:%u)\n",
+ new ? "Add-new":"Replace", cpu, avail_idx,
+ queue_size, curr_cpus_count);
+
+ return 0;
+}
+
+/* CPUs are zero-indexed. Thus, add a special sentinel default value
+ * in map cpus_available to mark CPU index'es not configured
+ */
+static void mark_cpus_unavailable(void)
+{
+ __u32 invalid_cpu = MAX_CPUS;
+ int ret, i;
+
+ for (i = 0; i < MAX_CPUS; i++) {
+ /* map_fd[5] = cpus_available */
+ ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0);
+ if (ret) {
+ fprintf(stderr, "Failed marking CPU unavailable\n");
+ exit(EXIT_FAIL_BPF);
+ }
+ }
+}
+
+/* Stress cpumap management code by concurrently changing underlying cpumap */
+static void stress_cpumap(void)
+{
+ /* Changing qsize will cause kernel to free and alloc a new
+ * bpf_cpu_map_entry, with an associated/complicated tear-down
+ * procedure.
+ */
+ create_cpu_entry(1, 1024, 0, false);
+ create_cpu_entry(1, 128, 0, false);
+ create_cpu_entry(1, 16000, 0, false);
+}
+
+static void stats_poll(int interval, bool use_separators, int prog_num,
+ bool stress_mode)
+{
+ struct stats_record *record, *prev;
+
+ record = alloc_stats_record();
+ prev = alloc_stats_record();
+ stats_collect(record);
+
+ /* Trick to pretty printf with thousands separators use %' */
+ if (use_separators)
+ setlocale(LC_NUMERIC, "en_US");
+
+ while (1) {
+ swap(&prev, &record);
+ stats_collect(record);
+ stats_print(record, prev, prog_num);
+ sleep(interval);
+ if (stress_mode)
+ stress_cpumap();
+ }
+
+ free_stats_record(record);
+ free_stats_record(prev);
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ bool use_separators = true;
+ bool stress_mode = false;
+ char filename[256];
+ bool debug = false;
+ int added_cpus = 0;
+ int longindex = 0;
+ int interval = 2;
+ int prog_num = 0;
+ int add_cpu = -1;
+ __u32 qsize;
+ int opt;
+
+ /* Notice: choosing he queue size is very important with the
+ * ixgbe driver, because it's driver page recycling trick is
+ * dependend on pages being returned quickly. The number of
+ * out-standing packets in the system must be less-than 2x
+ * RX-ring size.
+ */
+ qsize = 128+64;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
+
+ if (load_bpf_file(filename)) {
+ fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf);
+ return EXIT_FAIL;
+ }
+
+ if (!prog_fd[0]) {
+ fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
+ return EXIT_FAIL;
+ }
+
+ mark_cpus_unavailable();
+
+ /* Parse commands line args */
+ while ((opt = getopt_long(argc, argv, "hSd:",
+ long_options, &longindex)) != -1) {
+ switch (opt) {
+ case 'd':
+ if (strlen(optarg) >= IF_NAMESIZE) {
+ fprintf(stderr, "ERR: --dev name too long\n");
+ goto error;
+ }
+ ifname = (char *)&ifname_buf;
+ strncpy(ifname, optarg, IF_NAMESIZE);
+ ifindex = if_nametoindex(ifname);
+ if (ifindex == 0) {
+ fprintf(stderr,
+ "ERR: --dev name unknown err(%d):%s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ break;
+ case 's':
+ interval = atoi(optarg);
+ break;
+ case 'S':
+ xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'D':
+ debug = true;
+ break;
+ case 'x':
+ stress_mode = true;
+ break;
+ case 'z':
+ use_separators = false;
+ break;
+ case 'p':
+ /* Selecting eBPF prog to load */
+ prog_num = atoi(optarg);
+ if (prog_num < 0 || prog_num >= MAX_PROG) {
+ fprintf(stderr,
+ "--prognum too large err(%d):%s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ break;
+ case 'c':
+ /* Add multiple CPUs */
+ add_cpu = strtoul(optarg, NULL, 0);
+ if (add_cpu >= MAX_CPUS) {
+ fprintf(stderr,
+ "--cpu nr too large for cpumap err(%d):%s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ create_cpu_entry(add_cpu, qsize, added_cpus, true);
+ added_cpus++;
+ break;
+ case 'q':
+ qsize = atoi(optarg);
+ break;
+ case 'h':
+ error:
+ default:
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+ }
+ /* Required option */
+ if (ifindex == -1) {
+ fprintf(stderr, "ERR: required option --dev missing\n");
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+ /* Required option */
+ if (add_cpu == -1) {
+ fprintf(stderr, "ERR: required option --cpu missing\n");
+ fprintf(stderr, " Specify multiple --cpu option to add more\n");
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+
+ /* Remove XDP program when program is interrupted */
+ signal(SIGINT, int_exit);
+
+ if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+ fprintf(stderr, "link set xdp fd failed\n");
+ return EXIT_FAIL_XDP;
+ }
+
+ if (debug) {
+ printf("Debug-mode reading trace pipe (fix #define DEBUG)\n");
+ read_trace_pipe();
+ }
+
+ stats_poll(interval, use_separators, prog_num, stress_mode);
+ return EXIT_OK;
+}
^ permalink raw reply related
* [PATCH] netconsole: make config_item_type const
From: Bhumika Goyal @ 2017-10-12 12:29 UTC (permalink / raw)
To: julia.lawall, davem, akpm, nab, linux-kernel, netdev; +Cc: Bhumika Goyal
This is a followup patch for: https://lkml.org/lkml/2017/10/11/375 and
https://patchwork.kernel.org/patch/9999649/
Make these structures const as they are either passed to the functions
having the argument as const or stored as a reference in the "ci_type"
const field of a config_item structure.
Done using Coccienlle.
Signed-off-by: Bhumika Goyal <bhumirks@gmail.com>
---
drivers/net/netconsole.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 0e27920..be9aa36 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -616,7 +616,7 @@ static void netconsole_target_release(struct config_item *item)
.release = netconsole_target_release,
};
-static struct config_item_type netconsole_target_type = {
+static const struct config_item_type netconsole_target_type = {
.ct_attrs = netconsole_target_attrs,
.ct_item_ops = &netconsole_target_item_ops,
.ct_owner = THIS_MODULE,
@@ -682,7 +682,7 @@ static void drop_netconsole_target(struct config_group *group,
.drop_item = drop_netconsole_target,
};
-static struct config_item_type netconsole_subsys_type = {
+static const struct config_item_type netconsole_subsys_type = {
.ct_group_ops = &netconsole_subsys_group_ops,
.ct_owner = THIS_MODULE,
};
--
1.9.1
^ permalink raw reply related
* Re: [PATCH] [net-next] ip_tunnel: fix building with NET_IP_TUNNEL=m
From: Amine Kherbouche @ 2017-10-12 13:16 UTC (permalink / raw)
To: Arnd Bergmann, David S. Miller; +Cc: Networking, Linux Kernel Mailing List
In-Reply-To: <CAK8P3a0GDGs-iJegS2RZFtiBKU7miOuK0aujGDdBLVsvyh0Ngg@mail.gmail.com>
Hi Arnd,
On 10/11/2017 03:57 PM, Arnd Bergmann wrote:
> I forgot to Cc Amine, sorry.
>
> On Wed, Oct 11, 2017 at 3:55 PM, Arnd Bergmann <arnd@arndb.de> wrote:
>> When af_mpls is built-in but the tunnel support is a module,
>> we get a link failure:
>>
>> net/mpls/af_mpls.o: In function `mpls_init':
>> af_mpls.c:(.init.text+0xdc): undefined reference to `ip_tunnel_encap_add_ops'
>>
>> This adds a Kconfig statement to prevent the broken
>> configuration and force mpls to be a module as well in
>> this case.
>>
>> Fixes: bdc476413dcd ("ip_tunnel: add mpls over gre support")
>> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
>> ---
>> net/mpls/Kconfig | 1 +
>> 1 file changed, 1 insertion(+)
>>
>> diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig
>> index 5c467ef97311..801ea9098387 100644
>> --- a/net/mpls/Kconfig
>> +++ b/net/mpls/Kconfig
>> @@ -24,6 +24,7 @@ config NET_MPLS_GSO
>>
>> config MPLS_ROUTING
>> tristate "MPLS: routing support"
>> + depends on NET_IP_TUNNEL || NET_IP_TUNNEL=n
>> ---help---
>> Add support for forwarding of mpls packets.
>>
>> --
>> 2.9.0
>>
Acked-by: Amine Kherbouche <amine.kherbouche@6wind.com>
^ permalink raw reply
* [RFC 3/3] bnxt: Add devlink support for config get/set
From: Steve Lin @ 2017-10-12 13:34 UTC (permalink / raw)
To: netdev; +Cc: jiri, davem, michael.chan, linux-pci, linville, gospo,
steven.lin1
In-Reply-To: <1507815262-33294-1-git-send-email-steven.lin1@broadcom.com>
Implements get and set of configuration parameters using new devlink
config get/set API.
Signed-off-by: Steve Lin <steven.lin1@broadcom.com>
Acked-by: Andy Gospodarek <gospo@broadcom.com>
---
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 306 +++++++++++++++++++++-
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h | 17 ++
drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 100 +++++++
3 files changed, 417 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index d159cce..32319d5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -14,6 +14,83 @@
#include "bnxt_vfr.h"
#include "bnxt_devlink.h"
+struct bnxt_drv_cfgparam bnxt_drv_cfgparam_list[] = {
+ {DEVLINK_ATTR_MAX_NUM_PF_MSIX_VECT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 10, 108},
+ {DEVLINK_ATTR_IGNORE_ARI_CAPABILITY, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 164},
+ {DEVLINK_ATTR_PME_CAPABILITY_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 166},
+ {DEVLINK_ATTR_LLDP_NEAREST_BRIDGE_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 269},
+ {DEVLINK_ATTR_LLDP_NEAREST_NONTPMR_BRIDGE_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 270},
+ {DEVLINK_ATTR_SECURE_NIC_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 162},
+ {DEVLINK_ATTR_PHY_SELECT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 329},
+ {DEVLINK_ATTR_SRIOV_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_SHARED, 1, 401},
+
+ {DEVLINK_ATTR_MBA_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 351},
+ {DEVLINK_ATTR_MBA_BOOT_TYPE, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 2, 352},
+ {DEVLINK_ATTR_MBA_DELAY_TIME, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 4, 353},
+ {DEVLINK_ATTR_MBA_SETUP_HOT_KEY, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 354},
+ {DEVLINK_ATTR_MBA_HIDE_SETUP_PROMPT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 355},
+ {DEVLINK_ATTR_MBA_VLAN_TAG, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 16, 357},
+ {DEVLINK_ATTR_MBA_VLAN_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 358},
+ {DEVLINK_ATTR_MBA_LINK_SPEED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 4, 359},
+ {DEVLINK_ATTR_MBA_BOOT_RETRY_COUNT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 3, 360},
+ {DEVLINK_ATTR_MBA_BOOT_PROTOCOL, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 3, 361},
+ {DEVLINK_ATTR_NUM_VF_PER_PF, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 8, 404},
+ {DEVLINK_ATTR_MSIX_VECTORS_PER_VF, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 10, 406},
+ {DEVLINK_ATTR_NPAR_BW_RESERVATION, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 10, 501},
+ {DEVLINK_ATTR_NPAR_BW_LIMIT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 10, 502},
+ {DEVLINK_ATTR_RDMA_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 506},
+ {DEVLINK_ATTR_NPAR_BW_IN_PERCENT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 507},
+ {DEVLINK_ATTR_NPAR_BW_RESERVATION_VALID, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 508},
+ {DEVLINK_ATTR_NPAR_BW_LIMIT_VALID, BNXT_DRV_PF,
+ BNXT_DRV_APPL_FUNCTION, 1, 509},
+
+ {DEVLINK_ATTR_MAGIC_PACKET_WOL_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 1, 152},
+ {DEVLINK_ATTR_DCBX_MODE, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 4, 155},
+ {DEVLINK_ATTR_MULTIFUNC_MODE, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 5, 157},
+ {DEVLINK_ATTR_PRE_OS_LINK_SPEED_D0, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 4, 205},
+ {DEVLINK_ATTR_EEE_PWR_SAVE_ENABLED, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 1, 208},
+ {DEVLINK_ATTR_PRE_OS_LINK_SPEED_D3, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 4, 210},
+ {DEVLINK_ATTR_MEDIA_AUTO_DETECT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 1, 213},
+ {DEVLINK_ATTR_AUTONEG_PROTOCOL, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 8, 312},
+ {DEVLINK_ATTR_NPAR_NUM_PARTITIONS_PER_PORT, BNXT_DRV_PF,
+ BNXT_DRV_APPL_PORT, 8, 503},
+};
+
+#define BNXT_NUM_DRV_CFGPARAM ARRAY_SIZE(bnxt_drv_cfgparam_list)
+
static int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
{
struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
@@ -60,9 +137,226 @@ static int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
return rc;
}
-static const struct devlink_ops bnxt_dl_ops = {
+static int bnxt_nvm_read(struct bnxt *bp, int nvm_param, int idx,
+ void *buf, int size)
+{
+ struct hwrm_nvm_get_variable_input req = {0};
+ void *dest_data_addr = NULL;
+ dma_addr_t dest_data_dma_addr;
+ int rc;
+ int bytesize;
+
+ bytesize = (size + 7) / 8;
+ dest_data_addr = dma_alloc_coherent(&bp->pdev->dev, bytesize,
+ &dest_data_dma_addr, GFP_KERNEL);
+ if (!dest_data_addr) {
+ netdev_err(bp->dev, "dma_alloc_coherent failure\n");
+ return -ENOMEM;
+ }
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1);
+ req.dest_data_addr = cpu_to_le64(dest_data_dma_addr);
+ req.data_len = cpu_to_le16(size);
+ req.option_num = cpu_to_le16(nvm_param);
+ req.index_0 = cpu_to_le16(idx);
+ if (idx != 0)
+ req.dimensions = cpu_to_le16(1);
+
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+ memcpy(buf, dest_data_addr, size);
+
+ dma_free_coherent(&bp->pdev->dev, bytesize, dest_data_addr,
+ dest_data_dma_addr);
+
+ return rc;
+}
+
+static int bnxt_nvm_write(struct bnxt *bp, int nvm_param, int idx,
+ const void *buf, int size)
+{
+ struct hwrm_nvm_set_variable_input req = {0};
+ void *src_data_addr = NULL;
+ dma_addr_t src_data_dma_addr;
+ int rc;
+ int bytesize;
+
+ bytesize = (size + 7) / 8;
+
+ src_data_addr = dma_alloc_coherent(&bp->pdev->dev, bytesize,
+ &src_data_dma_addr, GFP_KERNEL);
+ if (!src_data_addr) {
+ netdev_err(bp->dev, "dma_alloc_coherent failure\n");
+ return -ENOMEM;
+ }
+
+ memcpy(src_data_addr, buf, bytesize);
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1);
+ req.src_data_addr = cpu_to_le64(src_data_dma_addr);
+ req.data_len = cpu_to_le16(size);
+ req.option_num = cpu_to_le16(nvm_param);
+ req.index_0 = cpu_to_le16(idx);
+ if (idx != 0)
+ req.dimensions = cpu_to_le16(1);
+
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+ dma_free_coherent(&bp->pdev->dev, bytesize, src_data_addr,
+ src_data_dma_addr);
+
+ return 0;
+}
+
+static int bnxt_dl_config_set(struct devlink *devlink,
+ enum devlink_attr attr, u32 value,
+ u8 *restart_reqd)
+{
+ struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
+ int i;
+ int idx = 0;
+ void *data;
+ int ret = 0;
+ u32 bytesize;
+ struct bnxt_drv_cfgparam *entry;
+
+ *restart_reqd = 0;
+
+ /* Find parameter in table */
+ for (i = 0; i < BNXT_NUM_DRV_CFGPARAM; i++) {
+ if (attr == bnxt_drv_cfgparam_list[i].attr) {
+ entry = &bnxt_drv_cfgparam_list[i];
+ break;
+ }
+ }
+
+ /* Not found */
+ if (i == BNXT_NUM_DRV_CFGPARAM)
+ return -EINVAL;
+
+ /* Check to see if this func type can access variable */
+ if (BNXT_PF(bp) && !(entry->func & BNXT_DRV_PF))
+ return -EOPNOTSUPP;
+ if (BNXT_VF(bp) && !(entry->func & BNXT_DRV_VF))
+ return -EOPNOTSUPP;
+
+ /* If parameter is per port or function, compute index */
+ if (entry->appl == BNXT_DRV_APPL_PORT) {
+ idx = bp->pf.port_id;
+ } else if (entry->appl == BNXT_DRV_APPL_FUNCTION) {
+ if (BNXT_PF(bp))
+ idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
+ else
+ idx = bp->vf.fw_fid - BNXT_FIRST_VF_FID;
+ }
+
+ bytesize = (entry->bitlength + 7) / 8;
+ data = kmalloc(bytesize, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ if (bytesize == 1) {
+ u8 val8 = (value & 0xff);
+
+ memcpy(data, &val8, sizeof(u8));
+ } else if (bytesize == 2) {
+ u16 val16 = (value & 0xffff);
+
+ memcpy(data, &val16, sizeof(u16));
+ } else {
+ memcpy(data, &value, sizeof(u32));
+ }
+
+ ret = bnxt_nvm_write(bp, entry->nvm_param, idx, data,
+ entry->bitlength);
+
+ /* Restart required for all nvm parameter writes */
+ *restart_reqd = 1;
+
+ kfree(data);
+
+ return ret;
+}
+
+static int bnxt_dl_config_get(struct devlink *devlink,
+ enum devlink_attr attr, u32 *value)
+{
+ struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
+
+ int i;
+ int idx = 0;
+ void *data;
+ int ret = 0;
+ u32 bytesize;
+ struct bnxt_drv_cfgparam *entry;
+
+ /* Find parameter in table */
+ for (i = 0; i < BNXT_NUM_DRV_CFGPARAM; i++) {
+ if (attr == bnxt_drv_cfgparam_list[i].attr) {
+ entry = &bnxt_drv_cfgparam_list[i];
+ break;
+ }
+ }
+
+ /* Not found */
+ if (i == BNXT_NUM_DRV_CFGPARAM)
+ return -EINVAL;
+
+ /* Check to see if this func type can access variable */
+ if (BNXT_PF(bp) && !(entry->func & BNXT_DRV_PF))
+ return -EOPNOTSUPP;
+ if (BNXT_VF(bp) && !(entry->func & BNXT_DRV_VF))
+ return -EOPNOTSUPP;
+
+ /* If parameter is per port or function, compute index */
+ if (entry->appl == BNXT_DRV_APPL_PORT) {
+ idx = bp->pf.port_id;
+ } else if (entry->appl == BNXT_DRV_APPL_FUNCTION) {
+ if (BNXT_PF(bp))
+ idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
+ else
+ idx = bp->vf.fw_fid - BNXT_FIRST_VF_FID;
+ }
+
+ /* Allocate space, retrieve value, and copy to result */
+ bytesize = (entry->bitlength + 7) / 8;
+ data = kmalloc(bytesize, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+ ret = bnxt_nvm_read(bp, entry->nvm_param, idx, data, entry->bitlength);
+
+ if (ret) {
+ kfree(data);
+ return ret;
+ }
+
+ if (bytesize == 1) {
+ u8 val;
+
+ memcpy(&val, data, sizeof(u8));
+ *value = val;
+ } else if (bytesize == 2) {
+ u16 val;
+
+ memcpy(&val, data, sizeof(u16));
+ *value = val;
+ } else {
+ u32 val;
+
+ memcpy(&val, data, sizeof(u32));
+ *value = val;
+ }
+
+ kfree(data);
+
+ return 0;
+}
+
+static struct devlink_ops bnxt_dl_ops = {
.eswitch_mode_set = bnxt_dl_eswitch_mode_set,
.eswitch_mode_get = bnxt_dl_eswitch_mode_get,
+ .config_get = bnxt_dl_config_get,
+ .config_set = bnxt_dl_config_set,
};
int bnxt_dl_register(struct bnxt *bp)
@@ -70,12 +364,12 @@ int bnxt_dl_register(struct bnxt *bp)
struct devlink *dl;
int rc;
- if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
- return 0;
-
- if (bp->hwrm_spec_code < 0x10800) {
+ if ((!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV)) ||
+ bp->hwrm_spec_code < 0x10800) {
+ /* eswitch switchdev mode not supported */
+ bnxt_dl_ops.eswitch_mode_set = NULL;
+ bnxt_dl_ops.eswitch_mode_get = NULL;
netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
- return -ENOTSUPP;
}
dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index e92a35d..ee28890 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -10,6 +10,23 @@
#ifndef BNXT_DEVLINK_H
#define BNXT_DEVLINK_H
+#define BNXT_DRV_PF 1
+#define BNXT_DRV_VF 2
+
+enum bnxt_drv_appl {
+ BNXT_DRV_APPL_SHARED,
+ BNXT_DRV_APPL_PORT,
+ BNXT_DRV_APPL_FUNCTION
+};
+
+struct bnxt_drv_cfgparam {
+ enum devlink_attr attr;
+ u8 func; /* BNXT_DRV_PF | BNXT_DRV_VF */
+ enum bnxt_drv_appl appl; /* applicability (shared, func, port) */
+ u32 bitlength; /* length, in bits */
+ u32 nvm_param;
+};
+
/* Struct to hold housekeeping info needed by devlink interface */
struct bnxt_dl {
struct bnxt *bp; /* back ptr to the controlling dev */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index cb04cc7..8c25731 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -5676,6 +5676,106 @@ struct hwrm_nvm_install_update_cmd_err {
u8 unused_0[7];
};
+/* hwrm_nvm_get_variable */
+/* Input (40 bytes) */
+struct hwrm_nvm_get_variable_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le64 dest_data_addr;
+ __le16 data_len;
+ __le16 option_num;
+ #define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0 0x0UL
+ #define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
+ __le16 dimensions;
+ __le16 index_0;
+ __le16 index_1;
+ __le16 index_2;
+ __le16 index_3;
+ u8 flags;
+ #define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT 0x1UL
+ u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_nvm_get_variable_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le16 data_len;
+ __le16 option_num;
+ #define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0 0x0UL
+ #define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF 0xffffUL
+ u8 unused_0;
+ u8 unused_1;
+ u8 unused_2;
+ u8 valid;
+};
+
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_get_variable_cmd_err {
+ u8 code;
+ #define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN 0x0UL
+ #define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
+ #define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR 0x2UL
+ #define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL
+ u8 unused_0[7];
+};
+
+/* hwrm_nvm_set_variable */
+/* Input (40 bytes) */
+struct hwrm_nvm_set_variable_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le64 src_data_addr;
+ __le16 data_len;
+ __le16 option_num;
+ #define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0 0x0UL
+ #define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
+ __le16 dimensions;
+ __le16 index_0;
+ __le16 index_1;
+ __le16 index_2;
+ __le16 index_3;
+ u8 flags;
+ #define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH 0x1UL
+ #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK 0xeUL
+ #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT 1
+ #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE (0x0UL << 1)
+ #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1 (0x1UL << 1)
+ #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST \
+ NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1
+ u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_nvm_set_variable_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le32 unused_0;
+ u8 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 valid;
+};
+
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_set_variable_cmd_err {
+ u8 code;
+ #define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN 0x0UL
+ #define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
+ #define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR 0x2UL
+ u8 unused_0[7];
+};
+
/* hwrm_selftest_qlist */
/* Input (16 bytes) */
struct hwrm_selftest_qlist_input {
--
2.7.4
^ permalink raw reply related
* [RFC 0/3] Adding config get/set to devlink
From: Steve Lin @ 2017-10-12 13:34 UTC (permalink / raw)
To: netdev; +Cc: jiri, davem, michael.chan, linux-pci, linville, gospo,
steven.lin1
Adds a devlink command for getting & setting device configuration
parameters, and enumerates a bunch of those parameters as devlink
attributes. Also introduces an attribute that can be set by a
driver to indicate that the config change doesn't take effect
until the next restart (as in the case of the bnxt driver changes
in this patchset, for which all the configuration changes affect NVM
only, and aren't loaded until the next restart.)
bnxt driver patches make use of these new devlink cmds/attributes.
Steve Lin (3):
devlink: Add config parameter get/set operations
bnxt: Move generic devlink code to new file
bnxt: Add devlink support for config get/set
drivers/net/ethernet/broadcom/bnxt/Makefile | 2 +-
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 +
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 403 ++++++++++++++++++++++
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h | 56 +++
drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 100 ++++++
drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 97 +-----
drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h | 35 +-
include/net/devlink.h | 4 +
include/uapi/linux/devlink.h | 108 ++++++
net/core/devlink.c | 207 +++++++++++
10 files changed, 882 insertions(+), 131 deletions(-)
create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
--
2.7.4
^ permalink raw reply
* [RFC 1/3] devlink: Add config parameter get/set operations
From: Steve Lin @ 2017-10-12 13:34 UTC (permalink / raw)
To: netdev; +Cc: jiri, davem, michael.chan, linux-pci, linville, gospo,
steven.lin1
In-Reply-To: <1507815262-33294-1-git-send-email-steven.lin1@broadcom.com>
Add support for config parameter get/set commands. Initially used by
bnxt driver, but other drivers can use the same, or new, attributes.
The config_get() and config_set() operations operate as expected, but
note that the driver implementation of the config_set() operation can
indicate whether a restart is necessary for the setting to take
effect.
Signed-off-by: Steve Lin <steven.lin1@broadcom.com>
Acked-by: Andy Gospodarek <gospo@broadcom.com>
---
include/net/devlink.h | 4 +
include/uapi/linux/devlink.h | 108 ++++++++++++++++++++++
net/core/devlink.c | 207 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 319 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b9654e1..952966c 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -270,6 +270,10 @@ struct devlink_ops {
int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode);
int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode);
int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode);
+ int (*config_get)(struct devlink *devlink, enum devlink_attr attr,
+ u32 *value);
+ int (*config_set)(struct devlink *devlink, enum devlink_attr attr,
+ u32 value, u8 *restart_reqd);
};
static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 0cbca96..e959716 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -70,6 +70,9 @@ enum devlink_command {
DEVLINK_CMD_DPIPE_HEADERS_GET,
DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+ DEVLINK_CMD_CONFIG_GET,
+ DEVLINK_CMD_CONFIG_SET,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -124,6 +127,68 @@ enum devlink_eswitch_encap_mode {
DEVLINK_ESWITCH_ENCAP_MODE_BASIC,
};
+enum devlink_dcbx_mode {
+ DEVLINK_DCBX_MODE_DISABLED,
+ DEVLINK_DCBX_MODE_IEEE,
+ DEVLINK_DCBX_MODE_CEE,
+ DEVLINK_DCBX_MODE_IEEE_CEE,
+};
+
+enum devlink_multifunc_mode {
+ DEVLINK_MULTIFUNC_MODE_ALLOWED, /* Ext switch activates MF */
+ DEVLINK_MULTIFUNC_MODE_FORCE_SINGFUNC,
+ DEVLINK_MULTIFUNC_MODE_NPAR10, /* NPAR 1.0 */
+ DEVLINK_MULTIFUNC_MODE_NPAR15, /* NPAR 1.5 */
+ DEVLINK_MULTIFUNC_MODE_NPAR20, /* NPAR 2.0 */
+};
+
+enum devlink_autoneg_protocol {
+ DEVLINK_AUTONEG_PROTOCOL_IEEE8023BY_BAM,
+ DEVLINK_AUTONEG_PROTOCOL_IEEE8023BY_CONSORTIUM,
+ DEVLINK_AUTONEG_PROTOCOL_IEEE8023BY,
+ DEVLINK_AUTONEG_PROTOCOL_BAM, /* Broadcom Autoneg Mode */
+ DEVLINK_AUTONEG_PROTOCOL_CONSORTIUM, /* Consortium Autoneg Mode */
+};
+
+enum devlink_pre_os_link_speed {
+ DEVLINK_PRE_OS_LINK_SPEED_AUTONEG,
+ DEVLINK_PRE_OS_LINK_SPEED_1G,
+ DEVLINK_PRE_OS_LINK_SPEED_10G,
+ DEVLINK_PRE_OS_LINK_SPEED_25G,
+ DEVLINK_PRE_OS_LINK_SPEED_40G,
+ DEVLINK_PRE_OS_LINK_SPEED_50G,
+ DEVLINK_PRE_OS_LINK_SPEED_100G,
+ DEVLINK_PRE_OS_LINK_SPEED_5G = 0xe,
+ DEVLINK_PRE_OS_LINK_SPEED_100M = 0xf,
+};
+
+enum devlink_mba_boot_type {
+ DEVLINK_MBA_BOOT_TYPE_AUTO_DETECT,
+ DEVLINK_MBA_BOOT_TYPE_BBS, /* BIOS Boot Specification */
+ DEVLINK_MBA_BOOT_TYPE_INTR18, /* Hook interrupt 0x18 */
+ DEVLINK_MBA_BOOT_TYPE_INTR19, /* Hook interrupt 0x19 */
+};
+
+enum devlink_mba_setup_hot_key {
+ DEVLINK_MBA_SETUP_HOT_KEY_CTRL_S,
+ DEVLINK_MBA_SETUP_HOT_KEY_CTRL_B,
+};
+
+enum devlink_mba_boot_protocol {
+ DEVLINK_MBA_BOOT_PROTOCOL_PXE,
+ DEVLINK_MBA_BOOT_PROTOCOL_ISCSI,
+ DEVLINK_MBA_BOOT_PROTOCOL_NONE = 0x7,
+};
+
+enum devlink_mba_link_speed {
+ DEVLINK_MBA_LINK_SPEED_AUTONEG,
+ DEVLINK_MBA_LINK_SPEED_1G,
+ DEVLINK_MBA_LINK_SPEED_10G,
+ DEVLINK_MBA_LINK_SPEED_25G,
+ DEVLINK_MBA_LINK_SPEED_40G,
+ DEVLINK_MBA_LINK_SPEED_50G,
+};
+
enum devlink_attr {
/* don't change the order or add anything between, this is ABI! */
DEVLINK_ATTR_UNSPEC,
@@ -202,6 +267,49 @@ enum devlink_attr {
DEVLINK_ATTR_ESWITCH_ENCAP_MODE, /* u8 */
+ /* Configuration Parameters */
+ DEVLINK_ATTR_SRIOV_ENABLED, /* u8 */
+ DEVLINK_ATTR_NUM_VF_PER_PF, /* u32 */
+ DEVLINK_ATTR_MAX_NUM_PF_MSIX_VECT, /* u32 */
+ DEVLINK_ATTR_MSIX_VECTORS_PER_VF, /* u32 */
+ DEVLINK_ATTR_NPAR_NUM_PARTITIONS_PER_PORT, /* u32 */
+ DEVLINK_ATTR_NPAR_BW_IN_PERCENT, /* u8 */
+ DEVLINK_ATTR_NPAR_BW_RESERVATION, /* u8 */
+ DEVLINK_ATTR_NPAR_BW_RESERVATION_VALID, /* u8 */
+ DEVLINK_ATTR_NPAR_BW_LIMIT, /* u8 */
+ DEVLINK_ATTR_NPAR_BW_LIMIT_VALID, /* u8 */
+ DEVLINK_ATTR_DCBX_MODE, /* u8 */
+ DEVLINK_ATTR_RDMA_ENABLED, /* u8 */
+ DEVLINK_ATTR_MULTIFUNC_MODE, /* u8 */
+ DEVLINK_ATTR_SECURE_NIC_ENABLED, /* u8 */
+ DEVLINK_ATTR_IGNORE_ARI_CAPABILITY, /* u8 */
+ DEVLINK_ATTR_LLDP_NEAREST_BRIDGE_ENABLED, /* u8 */
+ DEVLINK_ATTR_LLDP_NEAREST_NONTPMR_BRIDGE_ENABLED, /* u8 */
+ DEVLINK_ATTR_PME_CAPABILITY_ENABLED, /* u8 */
+ DEVLINK_ATTR_MAGIC_PACKET_WOL_ENABLED, /* u8 */
+ DEVLINK_ATTR_EEE_PWR_SAVE_ENABLED, /* u8 */
+ DEVLINK_ATTR_AUTONEG_PROTOCOL, /* u8 */
+ DEVLINK_ATTR_MEDIA_AUTO_DETECT, /* u8 */
+ DEVLINK_ATTR_PHY_SELECT, /* u8 */
+ DEVLINK_ATTR_PRE_OS_LINK_SPEED_D0, /* u8 */
+ DEVLINK_ATTR_PRE_OS_LINK_SPEED_D3, /* u8 */
+ DEVLINK_ATTR_MBA_ENABLED, /* u8 */
+ DEVLINK_ATTR_MBA_BOOT_TYPE, /* u8 */
+ DEVLINK_ATTR_MBA_DELAY_TIME, /* u32 */
+ DEVLINK_ATTR_MBA_SETUP_HOT_KEY, /* u8 */
+ DEVLINK_ATTR_MBA_HIDE_SETUP_PROMPT, /* u8 */
+ DEVLINK_ATTR_MBA_BOOT_RETRY_COUNT, /* u32 */
+ DEVLINK_ATTR_MBA_VLAN_ENABLED, /* u8 */
+ DEVLINK_ATTR_MBA_VLAN_TAG, /* u16 */
+ DEVLINK_ATTR_MBA_BOOT_PROTOCOL, /* u8 */
+ DEVLINK_ATTR_MBA_LINK_SPEED, /* u8 */
+
+ /* When config doesn't take effect until next reboot (config
+ * just changed NVM which isn't read until boot, for example),
+ * this attribute should be set by the driver.
+ */
+ DEVLINK_ATTR_RESTART_REQUIRED, /* u8 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7d430c1..701c84b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1566,6 +1566,164 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
return 0;
}
+static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1];
+
+static int devlink_nl_config_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ enum devlink_command cmd,
+ struct genl_info *info)
+{
+ const struct devlink_ops *ops = devlink->ops;
+ void *hdr;
+ int err;
+ enum devlink_attr attr = -1;
+ u32 value;
+ int i;
+ struct nla_policy policy;
+ u8 restart_reqd;
+
+ if (!ops->config_get)
+ return -EOPNOTSUPP;
+
+ hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+ &devlink_nl_family, 0, cmd);
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto nla_msg_failure;
+ }
+
+ err = devlink_nl_put_handle(msg, devlink);
+ if (err)
+ goto nla_put_failure;
+
+ for (i = 0; i < DEVLINK_ATTR_MAX; i++)
+ if (info->attrs[i])
+ attr = i;
+
+ if (attr == -1) {
+ /* Not found - invalid/unknown attribute? */
+ err = -EINVAL;
+ goto nla_put_failure;
+ }
+
+ policy = devlink_nl_policy[attr];
+
+ if (cmd == DEVLINK_CMD_CONFIG_GET) {
+ err = ops->config_get(devlink, attr, &value);
+
+ if (err)
+ goto nla_put_failure;
+
+ switch (policy.type) {
+ case NLA_U8:
+ err = nla_put_u8(msg, attr, value);
+ break;
+ case NLA_U16:
+ err = nla_put_u16(msg, attr, value);
+ break;
+ case NLA_U32:
+ err = nla_put_u32(msg, attr, value);
+ break;
+ default:
+ goto nla_put_failure;
+ }
+
+ if (err)
+ goto nla_put_failure;
+ } else {
+ /* Must be config_set command */
+ u8 *val8;
+ u16 *val16;
+ u32 *val32;
+
+ switch (policy.type) {
+ case NLA_U8:
+ val8 = nla_data(info->attrs[attr]);
+ value = *val8;
+ break;
+ case NLA_U16:
+ val16 = nla_data(info->attrs[attr]);
+ value = *val16;
+ break;
+ case NLA_U32:
+ val32 = nla_data(info->attrs[attr]);
+ value = *val32;
+ break;
+ default:
+ goto nla_put_failure;
+ }
+
+ err = ops->config_set(devlink, attr, value, &restart_reqd);
+ if (err)
+ goto nla_put_failure;
+
+ if (restart_reqd) {
+ err = nla_put_u8(msg, DEVLINK_ATTR_RESTART_REQUIRED,
+ restart_reqd);
+ if (err)
+ goto nla_put_failure;
+ }
+ }
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+nla_msg_failure:
+ return err;
+}
+
+static int devlink_nl_cmd_config_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct sk_buff *msg;
+ int err;
+
+ if (!devlink->ops)
+ return -EOPNOTSUPP;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_config_fill(msg, devlink, DEVLINK_CMD_CONFIG_GET,
+ info);
+
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_config_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct sk_buff *msg;
+ int err;
+
+ if (!devlink->ops)
+ return -EOPNOTSUPP;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_config_fill(msg, devlink, DEVLINK_CMD_CONFIG_SET,
+ info);
+
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
int devlink_dpipe_match_put(struct sk_buff *skb,
struct devlink_dpipe_match *match)
{
@@ -2291,6 +2449,41 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_SRIOV_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_NUM_VF_PER_PF] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MAX_NUM_PF_MSIX_VECT] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MSIX_VECTORS_PER_VF] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NPAR_NUM_PARTITIONS_PER_PORT] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NPAR_BW_IN_PERCENT] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NPAR_BW_RESERVATION] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NPAR_BW_RESERVATION_VALID] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_NPAR_BW_LIMIT] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NPAR_BW_LIMIT_VALID] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_DCBX_MODE] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_RDMA_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_MULTIFUNC_MODE] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_SECURE_NIC_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_IGNORE_ARI_CAPABILITY] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_LLDP_NEAREST_BRIDGE_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_LLDP_NEAREST_NONTPMR_BRIDGE_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_PME_CAPABILITY_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_MAGIC_PACKET_WOL_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_EEE_PWR_SAVE_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_AUTONEG_PROTOCOL] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MEDIA_AUTO_DETECT] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_PHY_SELECT] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_PRE_OS_LINK_SPEED_D0] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_PRE_OS_LINK_SPEED_D3] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MBA_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_MBA_BOOT_TYPE] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MBA_DELAY_TIME] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MBA_SETUP_HOT_KEY] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MBA_HIDE_SETUP_PROMPT] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_MBA_BOOT_RETRY_COUNT] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MBA_VLAN_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_MBA_VLAN_TAG] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_MBA_BOOT_PROTOCOL] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_MBA_LINK_SPEED] = { .type = NLA_U32 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -2451,6 +2644,20 @@ static const struct genl_ops devlink_nl_ops[] = {
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_CONFIG_GET,
+ .doit = devlink_nl_cmd_config_get_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_CONFIG_SET,
+ .doit = devlink_nl_cmd_config_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
--
2.7.4
^ permalink raw reply related
* [RFC 2/3] bnxt: Move generic devlink code to new file
From: Steve Lin @ 2017-10-12 13:34 UTC (permalink / raw)
To: netdev; +Cc: jiri, davem, michael.chan, linux-pci, linville, gospo,
steven.lin1
In-Reply-To: <1507815262-33294-1-git-send-email-steven.lin1@broadcom.com>
Moving generic devlink code (registration, etc.) out of VF-R code
into new bnxt_devlink file.
Signed-off-by: Steve Lin <steven.lin1@broadcom.com>
Acked-by: Andy Gospodarek <gospo@broadcom.com>
---
drivers/net/ethernet/broadcom/bnxt/Makefile | 2 +-
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 +
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 109 ++++++++++++++++++++++
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h | 39 ++++++++
drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 97 +------------------
drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h | 35 +------
6 files changed, 152 insertions(+), 131 deletions(-)
create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index 457201f..59c8ec9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,4 +1,4 @@
obj-$(CONFIG_BNXT) += bnxt_en.o
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o
+bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o
bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5ba4993..52cc38d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -61,6 +61,7 @@
#include "bnxt_xdp.h"
#include "bnxt_vfr.h"
#include "bnxt_tc.h"
+#include "bnxt_devlink.h"
#define BNXT_TX_TIMEOUT (5 * HZ)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
new file mode 100644
index 0000000..d159cce
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -0,0 +1,109 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_vfr.h"
+#include "bnxt_devlink.h"
+
+static int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+ struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
+
+ *mode = bp->eswitch_mode;
+ return 0;
+}
+
+static int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+ struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
+ int rc = 0;
+
+ mutex_lock(&bp->sriov_lock);
+ if (bp->eswitch_mode == mode) {
+ netdev_info(bp->dev, "already in %s eswitch mode",
+ mode == DEVLINK_ESWITCH_MODE_LEGACY ?
+ "legacy" : "switchdev");
+ rc = -EINVAL;
+ goto done;
+ }
+
+ switch (mode) {
+ case DEVLINK_ESWITCH_MODE_LEGACY:
+ bnxt_vf_reps_destroy(bp);
+ break;
+
+ case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+ if (pci_num_vf(bp->pdev) == 0) {
+ netdev_info(bp->dev,
+ "Enable VFs before setting switchdev mode");
+ rc = -EPERM;
+ goto done;
+ }
+ rc = bnxt_vf_reps_create(bp);
+ break;
+
+ default:
+ rc = -EINVAL;
+ goto done;
+ }
+done:
+ mutex_unlock(&bp->sriov_lock);
+ return rc;
+}
+
+static const struct devlink_ops bnxt_dl_ops = {
+ .eswitch_mode_set = bnxt_dl_eswitch_mode_set,
+ .eswitch_mode_get = bnxt_dl_eswitch_mode_get,
+};
+
+int bnxt_dl_register(struct bnxt *bp)
+{
+ struct devlink *dl;
+ int rc;
+
+ if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
+ return 0;
+
+ if (bp->hwrm_spec_code < 0x10800) {
+ netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
+ return -ENOTSUPP;
+ }
+
+ dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+ if (!dl) {
+ netdev_warn(bp->dev, "devlink_alloc failed");
+ return -ENOMEM;
+ }
+
+ bnxt_link_bp_to_dl(bp, dl);
+ bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+ rc = devlink_register(dl, &bp->pdev->dev);
+ if (rc) {
+ bnxt_link_bp_to_dl(bp, NULL);
+ devlink_free(dl);
+ netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
+ return rc;
+ }
+
+ return 0;
+}
+
+void bnxt_dl_unregister(struct bnxt *bp)
+{
+ struct devlink *dl = bp->dl;
+
+ if (!dl)
+ return;
+
+ devlink_unregister(dl);
+ devlink_free(dl);
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
new file mode 100644
index 0000000..e92a35d
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -0,0 +1,39 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_DEVLINK_H
+#define BNXT_DEVLINK_H
+
+/* Struct to hold housekeeping info needed by devlink interface */
+struct bnxt_dl {
+ struct bnxt *bp; /* back ptr to the controlling dev */
+};
+
+static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl)
+{
+ return ((struct bnxt_dl *)devlink_priv(dl))->bp;
+}
+
+/* To clear devlink pointer from bp, pass NULL dl */
+static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
+{
+ bp->dl = dl;
+
+ /* add a back pointer in dl to bp */
+ if (dl) {
+ struct bnxt_dl *bp_dl = devlink_priv(dl);
+
+ bp_dl->bp = bp;
+ }
+}
+
+int bnxt_dl_register(struct bnxt *bp);
+void bnxt_dl_unregister(struct bnxt *bp);
+
+#endif /* BNXT_DEVLINK_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index e75db04..1ed2bcf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -338,7 +338,7 @@ static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
ether_addr_copy(dev->dev_addr, dev->perm_addr);
}
-static int bnxt_vf_reps_create(struct bnxt *bp)
+int bnxt_vf_reps_create(struct bnxt *bp)
{
u16 *cfa_code_map = NULL, num_vfs = pci_num_vf(bp->pdev);
struct bnxt_vf_rep *vf_rep;
@@ -415,99 +415,4 @@ static int bnxt_vf_reps_create(struct bnxt *bp)
return rc;
}
-/* Devlink related routines */
-static int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
-{
- struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
-
- *mode = bp->eswitch_mode;
- return 0;
-}
-
-static int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
-{
- struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
- int rc = 0;
-
- mutex_lock(&bp->sriov_lock);
- if (bp->eswitch_mode == mode) {
- netdev_info(bp->dev, "already in %s eswitch mode",
- mode == DEVLINK_ESWITCH_MODE_LEGACY ?
- "legacy" : "switchdev");
- rc = -EINVAL;
- goto done;
- }
-
- switch (mode) {
- case DEVLINK_ESWITCH_MODE_LEGACY:
- bnxt_vf_reps_destroy(bp);
- break;
-
- case DEVLINK_ESWITCH_MODE_SWITCHDEV:
- if (pci_num_vf(bp->pdev) == 0) {
- netdev_info(bp->dev,
- "Enable VFs before setting switchdev mode");
- rc = -EPERM;
- goto done;
- }
- rc = bnxt_vf_reps_create(bp);
- break;
-
- default:
- rc = -EINVAL;
- goto done;
- }
-done:
- mutex_unlock(&bp->sriov_lock);
- return rc;
-}
-
-static const struct devlink_ops bnxt_dl_ops = {
- .eswitch_mode_set = bnxt_dl_eswitch_mode_set,
- .eswitch_mode_get = bnxt_dl_eswitch_mode_get
-};
-
-int bnxt_dl_register(struct bnxt *bp)
-{
- struct devlink *dl;
- int rc;
-
- if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
- return 0;
-
- if (bp->hwrm_spec_code < 0x10800) {
- netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
- return -ENOTSUPP;
- }
-
- dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
- if (!dl) {
- netdev_warn(bp->dev, "devlink_alloc failed");
- return -ENOMEM;
- }
-
- bnxt_link_bp_to_dl(bp, dl);
- bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
- rc = devlink_register(dl, &bp->pdev->dev);
- if (rc) {
- bnxt_link_bp_to_dl(bp, NULL);
- devlink_free(dl);
- netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
- return rc;
- }
-
- return 0;
-}
-
-void bnxt_dl_unregister(struct bnxt *bp)
-{
- struct devlink *dl = bp->dl;
-
- if (!dl)
- return;
-
- devlink_unregister(dl);
- devlink_free(dl);
-}
-
#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
index 7787cd24..1b67ce1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
@@ -14,36 +14,12 @@
#define MAX_CFA_CODE 65536
-/* Struct to hold housekeeping info needed by devlink interface */
-struct bnxt_dl {
- struct bnxt *bp; /* back ptr to the controlling dev */
-};
-
-static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl)
-{
- return ((struct bnxt_dl *)devlink_priv(dl))->bp;
-}
-
-/* To clear devlink pointer from bp, pass NULL dl */
-static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
-{
- bp->dl = dl;
-
- /* add a back pointer in dl to bp */
- if (dl) {
- struct bnxt_dl *bp_dl = devlink_priv(dl);
-
- bp_dl->bp = bp;
- }
-}
-
-int bnxt_dl_register(struct bnxt *bp);
-void bnxt_dl_unregister(struct bnxt *bp);
void bnxt_vf_reps_destroy(struct bnxt *bp);
void bnxt_vf_reps_close(struct bnxt *bp);
void bnxt_vf_reps_open(struct bnxt *bp);
void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb);
struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code);
+int bnxt_vf_reps_create(struct bnxt *bp);
static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
{
@@ -55,15 +31,6 @@ static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
#else
-static inline int bnxt_dl_register(struct bnxt *bp)
-{
- return 0;
-}
-
-static inline void bnxt_dl_unregister(struct bnxt *bp)
-{
-}
-
static inline void bnxt_vf_reps_close(struct bnxt *bp)
{
}
--
2.7.4
^ permalink raw reply related
* Re: BUG:af_packet fails to TX TSO frames
From: Willem de Bruijn @ 2017-10-12 13:39 UTC (permalink / raw)
To: Anton Ivanov; +Cc: Anton Ivanov, Network Development, David Miller
In-Reply-To: <529ff560-8230-c799-2948-fae711de382e@kot-begemot.co.uk>
> If I produce a real vnet frame out of a live kernel frame using
> virtio_net_hdr_from_skb() and try to send it it fails on the check in
> af_packet, while succeeding for tap. If I remove the af_packet check the
> frame is accepted by the hardware too.
>
> If I produce it a synthetic frame + vnet header using the test program - it
> works. Go figure.
Besides looking at the raw frame bytes, also compare the setup
of virtio_net_header, as well as the tcp checksum field. The stack
expects the pseudo header to have already been calculated.
> I am going to continue digging into it.
>
> At the very least I now have a positive test case which uses the same
> semantics as my code so I have something to compare to.
Glad to hear that the test is helpful. I wrote it because I
have run into these exact same issues in the past.
^ permalink raw reply
* Re: staging/irda/net: Adjustments for several function implementations
From: SF Markus Elfring @ 2017-10-12 13:45 UTC (permalink / raw)
To: Bjørn Mork, devel, netdev
Cc: Georgiana Chelu, Samuel Ortiz, Johannes Berg, Greg Kroah-Hartman,
kernel-janitors, LKML, Yuan Linyu, David Howells, Julia Lawall,
Srishti Sharma, Corentin Labbe, Al Viro, David S. Miller
In-Reply-To: <878tggwr70.fsf@miraculix.mork.no>
> Did you read drivers/staging/irda/TODO ?
Yes.
How do recent contributions (by other software developers) fit to information
that is provided in this file?
Regards,
Markus
^ permalink raw reply
* Re: [PATCH] ravb: Consolidate clock handling
From: Niklas Söderlund @ 2017-10-12 13:46 UTC (permalink / raw)
To: Geert Uytterhoeven
Cc: David S . Miller, Sergei Shtylyov, Simon Horman, netdev,
linux-renesas-soc
In-Reply-To: <1507796693-14268-1-git-send-email-geert+renesas@glider.be>
Hi Geert,
Grate patch!
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
On 2017-10-12 10:24:53 +0200, Geert Uytterhoeven wrote:
> The module clock is used for two purposes:
> - Wake-on-LAN (WoL), which is optional,
> - gPTP Timer Increment (GTI) configuration, which is mandatory.
>
> As the clock is needed for GTI configuration anyway, WoL is always
> available. Hence remove duplication and repeated obtaining of the clock
> by making GTI use the stored clock for WoL use.
>
> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
> ---
> drivers/net/ethernet/renesas/ravb_main.c | 35 +++++++++-----------------------
> 1 file changed, 10 insertions(+), 25 deletions(-)
>
> diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
> index fdf30bfa403bf416..8fad62f08e85e3ac 100644
> --- a/drivers/net/ethernet/renesas/ravb_main.c
> +++ b/drivers/net/ethernet/renesas/ravb_main.c
> @@ -1337,20 +1337,15 @@ static void ravb_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
> {
> struct ravb_private *priv = netdev_priv(ndev);
>
> - wol->supported = 0;
> - wol->wolopts = 0;
> -
> - if (priv->clk) {
> - wol->supported = WAKE_MAGIC;
> - wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0;
> - }
> + wol->supported = WAKE_MAGIC;
> + wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0;
> }
>
> static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
> {
> struct ravb_private *priv = netdev_priv(ndev);
>
> - if (!priv->clk || wol->wolopts & ~WAKE_MAGIC)
> + if (wol->wolopts & ~WAKE_MAGIC)
> return -EOPNOTSUPP;
>
> priv->wol_enabled = !!(wol->wolopts & WAKE_MAGIC);
> @@ -1912,22 +1907,12 @@ MODULE_DEVICE_TABLE(of, ravb_match_table);
>
> static int ravb_set_gti(struct net_device *ndev)
> {
> -
> + struct ravb_private *priv = netdev_priv(ndev);
> struct device *dev = ndev->dev.parent;
> - struct device_node *np = dev->of_node;
> unsigned long rate;
> - struct clk *clk;
> uint64_t inc;
>
> - clk = of_clk_get(np, 0);
> - if (IS_ERR(clk)) {
> - dev_err(dev, "could not get clock\n");
> - return PTR_ERR(clk);
> - }
> -
> - rate = clk_get_rate(clk);
> - clk_put(clk);
> -
> + rate = clk_get_rate(priv->clk);
> if (!rate)
> return -EINVAL;
>
> @@ -2073,10 +2058,11 @@ static int ravb_probe(struct platform_device *pdev)
>
> priv->chip_id = chip_id;
>
> - /* Get clock, if not found that's OK but Wake-On-Lan is unavailable */
> priv->clk = devm_clk_get(&pdev->dev, NULL);
> - if (IS_ERR(priv->clk))
> - priv->clk = NULL;
> + if (IS_ERR(priv->clk)) {
> + error = PTR_ERR(priv->clk);
> + goto out_release;
> + }
>
> /* Set function */
> ndev->netdev_ops = &ravb_netdev_ops;
> @@ -2144,8 +2130,7 @@ static int ravb_probe(struct platform_device *pdev)
> if (error)
> goto out_napi_del;
>
> - if (priv->clk)
> - device_set_wakeup_capable(&pdev->dev, 1);
> + device_set_wakeup_capable(&pdev->dev, 1);
>
> /* Print device information */
> netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n",
> --
> 2.7.4
>
--
Regards,
Niklas Söderlund
^ permalink raw reply
* [PATCH net-next v2 1/1] bridge: return error code when deleting Vlan
From: Roman Mashak @ 2017-10-12 13:51 UTC (permalink / raw)
To: davem; +Cc: stephen, dsahern, netdev, Roman Mashak
v2:
Return err immediately if nbp_vlan_delete() fails (pointed by David Ahern)
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
---
net/bridge/br_netlink.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index f0e8268..1efdd48 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -527,11 +527,13 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
case RTM_DELLINK:
if (p) {
- nbp_vlan_delete(p, vinfo->vid);
+ err = nbp_vlan_delete(p, vinfo->vid);
+ if (err)
+ break;
if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
- br_vlan_delete(p->br, vinfo->vid);
+ err = br_vlan_delete(p->br, vinfo->vid);
} else {
- br_vlan_delete(br, vinfo->vid);
+ err = br_vlan_delete(br, vinfo->vid);
}
break;
}
--
1.9.1
^ permalink raw reply related
* [net-next 00/18] tipc: Introduce Communcation Group feature
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
With this commit series we introduce a 'Group Communication' feature in
order to resolve the datagram and multicast flow control problem. This
new feature makes it possible to instantiate multiple virtual brokerless
message buses by just creating member sockets.
The main features are as follows:
---------------------------------
- Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN.
If it is the first socket of the group this implies creation of the
group. This call takes four parameters: 'type' serves as group
identifier, 'instance' serves as member identifier, and 'scope'
indicates the visibility of the group (node/cluster/zone). Finally,
'flags' indicates different options for the socket joining the group.
For the time being, there are only two such flags: 1) 'LOOPBACK'
indicates if the creator of the socket wants to receive a copy of
broadcast or multicast messages it sends to the group, 2) EVENTS
indicates if it wants to receive membership (JOINED/LEFT) events for
the other members of the group.
- Groups are closed, i.e., sockets which have not joined a group will
not be able to send messages to or receive messages from members of
the group, and vice versa. A socket can only be member of one group
at a time.
- There are four transmission modes.
1: Unicast. The sender transmits a message using the port identity
(node:port tuple) of the receiving socket.
2: Anycast. The sender transmits a message using a port name (type:
instance:scope) of one of the receiving sockets. If more than
one member socket matches the given address a destination is
selected according to a round-robin algorithm, but also considering
the destination load (advertised window size) as an additional
criteria.
3: Multicast. The sender transmits a message using a port name
(type:instance:scope) of one or more of the receiving sockets.
All sockets in the group matching the given address will receive
a copy of the message.
4: Broadcast. The sender transmits a message using the primtive
send(). All members of the group, irrespective of their member
identity (instance) number receive a copy of the message.
- TIPC broadcast is used for carrying messages in mode 3 or 4 when
this is deemed more efficient, i.e., depending on number of actual
destinations.
- All transmission modes are flow controlled, so that messages never
are dropped or rejected, just like we are used to from connection
oriented communication. A special algorithm guarantees that this is
true even for multipoint-to-point communication, i.e., at occasions
where many source sockets may decide to send simultaneously towards
the same destination socket.
- Sequence order is always guaranteed, even between the different
transmission modes.
- Member join/leave events are received in all other member sockets
in guaranteed order. I.e., a 'JOINED' (an empty message with the OOB
bit set) will always be received before the first data message from
a new member, and a 'LEAVE' (like 'JOINED', but with EOR bit set) will
always arrive after the last data message from a leaving member.
Jon Maloy (18):
tipc: add ability to order and receive topology events in driver
tipc: improve address sanity check in tipc_connect()
tipc: add ability to obtain node availability status from other files
tipc: refactor function filter_rcv()
tipc: add new function for sending multiple small messages
tipc: improve destination linked list
tipc: introduce communication groups
tipc: add second source address to recvmsg()/recvfrom()
tipc: receive group membership events via member socket
tipc: introduce flow control for group broadcast messages
tipc: introduce group unicast messaging
tipc: introduce group anycast messaging
tipc: introduce group multicast messaging
tipc: guarantee group unicast doesn't bypass group broadcast
tipc: guarantee that group broadcast doesn't bypass group unicast
tipc: guarantee delivery of UP event before first broadcast
tipc: guarantee delivery of last broadcast before DOWN event
tipc: add multipoint-to-point flow control
include/uapi/linux/tipc.h | 15 +
net/tipc/Makefile | 2 +-
net/tipc/bcast.c | 18 +-
net/tipc/core.h | 5 +
net/tipc/group.c | 874 ++++++++++++++++++++++++++++++++++++++++++++++
net/tipc/group.h | 73 ++++
net/tipc/link.c | 9 +-
net/tipc/msg.c | 7 +
net/tipc/msg.h | 110 +++++-
net/tipc/name_table.c | 174 ++++++---
net/tipc/name_table.h | 28 +-
net/tipc/node.c | 42 ++-
net/tipc/node.h | 5 +-
net/tipc/server.c | 121 +++++--
net/tipc/server.h | 5 +-
net/tipc/socket.c | 770 +++++++++++++++++++++++++++++++---------
16 files changed, 1988 insertions(+), 270 deletions(-)
create mode 100644 net/tipc/group.c
create mode 100644 net/tipc/group.h
--
2.1.4
^ permalink raw reply
* [net-next 01/18] tipc: add ability to order and receive topology events in driver
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
As preparation for introducing communication groups, we add the ability
to issue topology subscriptions and receive topology events from kernel
space. This will make it possible for group member sockets to keep track
of other group members.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/core.h | 5 +++
net/tipc/msg.h | 1 +
net/tipc/server.c | 121 ++++++++++++++++++++++++++++++++++++++++++------------
net/tipc/server.h | 5 ++-
net/tipc/socket.c | 32 +++++++++------
5 files changed, 125 insertions(+), 39 deletions(-)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 5cc5398..9643426 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -132,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net)
return &tipc_net(net)->node_list;
}
+static inline struct tipc_server *tipc_topsrv(struct net *net)
+{
+ return tipc_net(net)->topsrv;
+}
+
static inline unsigned int tipc_hashfn(u32 addr)
{
return addr & (NODE_HTABLE_SIZE - 1);
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index c843fd2..d058b1c 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -78,6 +78,7 @@ struct plist;
#define MSG_FRAGMENTER 12
#define LINK_CONFIG 13
#define SOCK_WAKEUP 14 /* pseudo user */
+#define TOP_SRV 15 /* pseudo user */
/*
* Message header sizes
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 3cd6402..caec0d2 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -36,6 +36,8 @@
#include "server.h"
#include "core.h"
#include "socket.h"
+#include "addr.h"
+#include "msg.h"
#include <net/sock.h>
#include <linux/module.h>
@@ -105,13 +107,11 @@ static void tipc_conn_kref_release(struct kref *kref)
kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
sock_release(sock);
con->sock = NULL;
-
- spin_lock_bh(&s->idr_lock);
- idr_remove(&s->conn_idr, con->conid);
- s->idr_in_use--;
- spin_unlock_bh(&s->idr_lock);
}
-
+ spin_lock_bh(&s->idr_lock);
+ idr_remove(&s->conn_idr, con->conid);
+ s->idr_in_use--;
+ spin_unlock_bh(&s->idr_lock);
tipc_clean_outqueues(con);
kfree(con);
}
@@ -197,7 +197,8 @@ static void tipc_close_conn(struct tipc_conn *con)
struct tipc_server *s = con->server;
if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
- tipc_unregister_callbacks(con);
+ if (con->sock)
+ tipc_unregister_callbacks(con);
if (con->conid)
s->tipc_conn_release(con->conid, con->usr_data);
@@ -207,8 +208,8 @@ static void tipc_close_conn(struct tipc_conn *con)
* are harmless for us here as we have already deleted this
* connection from server connection list.
*/
- kernel_sock_shutdown(con->sock, SHUT_RDWR);
-
+ if (con->sock)
+ kernel_sock_shutdown(con->sock, SHUT_RDWR);
conn_put(con);
}
}
@@ -288,6 +289,7 @@ static int tipc_receive_from_sock(struct tipc_conn *con)
}
static int tipc_accept_from_sock(struct tipc_conn *con)
+
{
struct tipc_server *s = con->server;
struct socket *sock = con->sock;
@@ -473,6 +475,7 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
if (!queue_work(s->send_wq, &con->swork))
conn_put(con);
+
return 0;
}
@@ -487,38 +490,104 @@ void tipc_conn_terminate(struct tipc_server *s, int conid)
}
}
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
+ u32 lower, u32 upper, int *conid)
+{
+ struct tipc_server *s;
+ struct tipc_conn *con;
+ struct tipc_subscriber *scbr;
+ struct tipc_subscr sub;
+
+ sub.seq.type = type;
+ sub.seq.lower = lower;
+ sub.seq.upper = upper;
+ sub.timeout = TIPC_WAIT_FOREVER;
+ sub.filter = TIPC_SUB_PORTS;
+ *(u32 *)&sub.usr_handle = port;
+
+ con = tipc_alloc_conn(tipc_topsrv(net));
+ if (!con)
+ return false;
+
+ *conid = con->conid;
+ s = con->server;
+ scbr = s->tipc_conn_new(*conid);
+ if (!scbr) {
+ tipc_close_conn(con);
+ return false;
+ }
+
+ con->usr_data = scbr;
+ con->sock = NULL;
+ s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub));
+ return true;
+}
+
+void tipc_topsrv_kern_unsubscr(struct net *net, int conid)
+{
+ struct tipc_conn *con;
+
+ con = tipc_conn_lookup(tipc_topsrv(net), conid);
+ if (!con)
+ return;
+ tipc_close_conn(con);
+ conn_put(con);
+}
+
+static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt)
+{
+ u32 port = *(u32 *)&evt->s.usr_handle;
+ u32 self = tipc_own_addr(net);
+ struct sk_buff_head evtq;
+ struct sk_buff *skb;
+
+ skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt),
+ self, self, port, port, 0);
+ if (!skb)
+ return;
+ msg_set_dest_droppable(buf_msg(skb), true);
+ memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt));
+ skb_queue_head_init(&evtq);
+ __skb_queue_tail(&evtq, skb);
+ tipc_sk_rcv(net, &evtq);
+}
+
static void tipc_send_to_sock(struct tipc_conn *con)
{
int count = 0;
struct tipc_server *s = con->server;
+ struct tipc_event *evt;
struct outqueue_entry *e;
struct msghdr msg;
int ret;
spin_lock_bh(&con->outqueue_lock);
while (test_bit(CF_CONNECTED, &con->flags)) {
- e = list_entry(con->outqueue.next, struct outqueue_entry,
- list);
+ e = list_entry(con->outqueue.next, struct outqueue_entry, list);
if ((struct list_head *) e == &con->outqueue)
break;
- spin_unlock_bh(&con->outqueue_lock);
- memset(&msg, 0, sizeof(msg));
- msg.msg_flags = MSG_DONTWAIT;
+ spin_unlock_bh(&con->outqueue_lock);
- if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) {
- msg.msg_name = &e->dest;
- msg.msg_namelen = sizeof(struct sockaddr_tipc);
- }
- ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1,
- e->iov.iov_len);
- if (ret == -EWOULDBLOCK || ret == 0) {
- cond_resched();
- goto out;
- } else if (ret < 0) {
- goto send_err;
+ if (con->sock) {
+ memset(&msg, 0, sizeof(msg));
+ msg.msg_flags = MSG_DONTWAIT;
+ if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) {
+ msg.msg_name = &e->dest;
+ msg.msg_namelen = sizeof(struct sockaddr_tipc);
+ }
+ ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1,
+ e->iov.iov_len);
+ if (ret == -EWOULDBLOCK || ret == 0) {
+ cond_resched();
+ goto out;
+ } else if (ret < 0) {
+ goto send_err;
+ }
+ } else {
+ evt = e->iov.iov_base;
+ tipc_send_kern_top_evt(s->net, evt);
}
-
/* Don't starve users filling buffers */
if (++count >= MAX_SEND_MSG_COUNT) {
cond_resched();
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 34f8055..2113c91 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -83,13 +83,16 @@ struct tipc_server {
int tipc_conn_sendmsg(struct tipc_server *s, int conid,
struct sockaddr_tipc *addr, void *data, size_t len);
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
+ u32 lower, u32 upper, int *conid);
+void tipc_topsrv_kern_unsubscr(struct net *net, int conid);
+
/**
* tipc_conn_terminate - terminate connection with server
*
* Note: Must call it in process context since it might sleep
*/
void tipc_conn_terminate(struct tipc_server *s, int conid);
-
int tipc_server_start(struct tipc_server *s);
void tipc_server_stop(struct tipc_server *s);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d50edd6..9a7e7b5c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -896,6 +896,10 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
kfree_skb(skb);
}
+static void tipc_sk_top_evt(struct tipc_sock *tsk, struct tipc_event *evt)
+{
+}
+
/**
* tipc_sendmsg - send message in connectionless manner
* @sock: socket structure
@@ -1671,20 +1675,24 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
struct tipc_msg *hdr = buf_msg(skb);
unsigned int limit = rcvbuf_limit(sk, skb);
int err = TIPC_OK;
- int usr = msg_user(hdr);
- u32 onode;
-
- if (unlikely(msg_user(hdr) == CONN_MANAGER)) {
- tipc_sk_proto_rcv(tsk, skb, xmitq);
- return false;
- }
- if (unlikely(usr == SOCK_WAKEUP)) {
- onode = msg_orignode(hdr);
+ if (unlikely(!msg_isdata(hdr))) {
+ switch (msg_user(hdr)) {
+ case CONN_MANAGER:
+ tipc_sk_proto_rcv(tsk, skb, xmitq);
+ return false;
+ case SOCK_WAKEUP:
+ u32_del(&tsk->cong_links, msg_orignode(hdr));
+ tsk->cong_link_cnt--;
+ sk->sk_write_space(sk);
+ break;
+ case TOP_SRV:
+ tipc_sk_top_evt(tsk, (void *)msg_data(hdr));
+ break;
+ default:
+ break;
+ }
kfree_skb(skb);
- u32_del(&tsk->cong_links, onode);
- tsk->cong_link_cnt--;
- sk->sk_write_space(sk);
return false;
}
--
2.1.4
^ permalink raw reply related
* [net-next 02/18] tipc: improve address sanity check in tipc_connect()
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
The address given to tipc_connect() is not completely sanity checked,
under the assumption that this will be done later in the function
__tipc_sendmsg() when the address is used there.
However, the latter functon will in the next commits serve as caller
to several other send functions, so we want to move the corresponding
sanity check there to the beginning of that function, before we possibly
need to grab the address stored by tipc_connect(). We must therefore
be able to trust that this address already has been thoroughly checked.
We do this in this commit.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/socket.c | 31 +++++++++++++++----------------
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9a7e7b5c..7659e79 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1911,28 +1911,27 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
int previous;
int res = 0;
+ if (destlen != sizeof(struct sockaddr_tipc))
+ return -EINVAL;
+
lock_sock(sk);
- /* DGRAM/RDM connect(), just save the destaddr */
- if (tipc_sk_type_connectionless(sk)) {
- if (dst->family == AF_UNSPEC) {
- memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
- } else if (destlen != sizeof(struct sockaddr_tipc)) {
+ if (dst->family == AF_UNSPEC) {
+ memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
+ if (!tipc_sk_type_connectionless(sk))
res = -EINVAL;
- } else {
- memcpy(&tsk->peer, dest, destlen);
- }
goto exit;
+ } else if (dst->family != AF_TIPC) {
+ res = -EINVAL;
}
-
- /*
- * Reject connection attempt using multicast address
- *
- * Note: send_msg() validates the rest of the address fields,
- * so there's no need to do it here
- */
- if (dst->addrtype == TIPC_ADDR_MCAST) {
+ if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
res = -EINVAL;
+ if (res)
+ goto exit;
+
+ /* DGRAM/RDM connect(), just save the destaddr */
+ if (tipc_sk_type_connectionless(sk)) {
+ memcpy(&tsk->peer, dest, destlen);
goto exit;
}
--
2.1.4
^ permalink raw reply related
* [net-next 03/18] tipc: add ability to obtain node availability status from other files
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
In the coming commits, functions at the socket level will need the
ability to read the availability status of a given node. We therefore
introduce a new function for this purpose, while renaming the existing
static function currently having the wanted name.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/node.c | 26 +++++++++++++++++++++-----
net/tipc/node.h | 1 +
2 files changed, 22 insertions(+), 5 deletions(-)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 198dbc7..6cc1ae6 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -157,7 +157,7 @@ static void tipc_node_timeout(unsigned long data);
static void tipc_node_fsm_evt(struct tipc_node *n, int evt);
static struct tipc_node *tipc_node_find(struct net *net, u32 addr);
static void tipc_node_put(struct tipc_node *node);
-static bool tipc_node_is_up(struct tipc_node *n);
+static bool node_is_up(struct tipc_node *n);
struct tipc_sock_conn {
u32 port;
@@ -657,7 +657,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
*slot1 = i;
}
- if (!tipc_node_is_up(n)) {
+ if (!node_is_up(n)) {
if (tipc_link_peer_is_down(l))
tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
@@ -717,11 +717,27 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
tipc_sk_rcv(n->net, &le->inputq);
}
-static bool tipc_node_is_up(struct tipc_node *n)
+static bool node_is_up(struct tipc_node *n)
{
return n->active_links[0] != INVALID_BEARER_ID;
}
+bool tipc_node_is_up(struct net *net, u32 addr)
+{
+ struct tipc_node *n;
+ bool retval = false;
+
+ if (in_own_node(net, addr))
+ return true;
+
+ n = tipc_node_find(net, addr);
+ if (!n)
+ return false;
+ retval = node_is_up(n);
+ tipc_node_put(n);
+ return retval;
+}
+
void tipc_node_check_dest(struct net *net, u32 onode,
struct tipc_bearer *b,
u16 capabilities, u32 signature,
@@ -1149,7 +1165,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr))
goto attr_msg_full;
- if (tipc_node_is_up(node))
+ if (node_is_up(node))
if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP))
goto attr_msg_full;
@@ -1249,7 +1265,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
dst = n->addr;
if (in_own_node(net, dst))
continue;
- if (!tipc_node_is_up(n))
+ if (!node_is_up(n))
continue;
txskb = pskb_copy(skb, GFP_ATOMIC);
if (!txskb)
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 898c229..8db59fe 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -76,6 +76,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb);
int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port);
void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port);
int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel);
+bool tipc_node_is_up(struct net *net, u32 addr);
u16 tipc_node_get_capabilities(struct net *net, u32 addr);
int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb);
--
2.1.4
^ permalink raw reply related
* [net-next 04/18] tipc: refactor function filter_rcv()
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
In the following commits we will need to handle multiple incoming and
rejected/returned buffers in the function socket.c::filter_rcv().
As a preparation for this, we generalize the function by handling
buffer queues instead of individual buffers. We also introduce a
help function tipc_skb_reject(), and rename filter_rcv() to
tipc_sk_filter_rcv() in line with other functions in socket.c.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/msg.c | 7 +++
net/tipc/msg.h | 2 +
net/tipc/socket.c | 157 +++++++++++++++++++++++++++---------------------------
3 files changed, 87 insertions(+), 79 deletions(-)
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 17146c1..1649d45 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -666,3 +666,10 @@ void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
}
kfree_skb(skb);
}
+
+void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
+{
+ if (tipc_msg_reverse(tipc_own_addr(net), &skb, err))
+ __skb_queue_tail(xmitq, skb);
+}
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index d058b1c..be3e38a 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -819,6 +819,8 @@ static inline bool msg_is_reset(struct tipc_msg *hdr)
struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp);
bool tipc_msg_validate(struct sk_buff *skb);
bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err);
+void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
+ struct sk_buff_head *xmitq);
void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type,
u32 hsize, u32 destnode);
struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7659e79..81b7d46c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -111,7 +111,7 @@ struct tipc_sock {
struct rcu_head rcu;
};
-static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static void tipc_data_ready(struct sock *sk);
static void tipc_write_space(struct sock *sk);
static void tipc_sock_destruct(struct sock *sk);
@@ -453,7 +453,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
msg_set_origport(msg, tsk->portid);
setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
sk->sk_shutdown = 0;
- sk->sk_backlog_rcv = tipc_backlog_rcv;
+ sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
@@ -850,12 +850,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
}
/**
- * tipc_sk_proto_rcv - receive a connection mng protocol message
+ * tipc_sk_conn_proto_rcv - receive a connection mng protocol message
* @tsk: receiving socket
* @skb: pointer to message buffer.
*/
-static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
- struct sk_buff_head *xmitq)
+static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
struct sock *sk = &tsk->sk;
u32 onode = tsk_own_node(tsk);
@@ -1536,14 +1536,41 @@ static void tipc_sock_destruct(struct sock *sk)
__skb_queue_purge(&sk->sk_receive_queue);
}
+static void tipc_sk_proto_rcv(struct sock *sk,
+ struct sk_buff_head *inputq,
+ struct sk_buff_head *xmitq)
+{
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct sk_buff *skb = __skb_dequeue(inputq);
+ struct tipc_msg *hdr = buf_msg(skb);
+
+ switch (msg_user(hdr)) {
+ case CONN_MANAGER:
+ tipc_sk_conn_proto_rcv(tsk, skb, xmitq);
+ return;
+ case SOCK_WAKEUP:
+ u32_del(&tsk->cong_links, msg_orignode(hdr));
+ tsk->cong_link_cnt--;
+ sk->sk_write_space(sk);
+ break;
+ case TOP_SRV:
+ tipc_sk_top_evt(tsk, (void *)msg_data(hdr));
+ break;
+ default:
+ break;
+ }
+
+ kfree_skb(skb);
+}
+
/**
- * filter_connect - Handle all incoming messages for a connection-based socket
+ * tipc_filter_connect - Handle incoming message for a connection-based socket
* @tsk: TIPC socket
* @skb: pointer to message buffer. Set to NULL if buffer is consumed
*
* Returns true if everything ok, false otherwise
*/
-static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
+static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
{
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
@@ -1657,7 +1684,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
}
/**
- * filter_rcv - validate incoming message
+ * tipc_sk_filter_rcv - validate incoming message
* @sk: socket
* @skb: pointer to message.
*
@@ -1666,75 +1693,49 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
*
* Called with socket lock already taken
*
- * Returns true if message was added to socket receive queue, otherwise false
*/
-static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
- struct sk_buff_head *xmitq)
+static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
+ bool sk_conn = !tipc_sk_type_connectionless(sk);
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *hdr = buf_msg(skb);
- unsigned int limit = rcvbuf_limit(sk, skb);
- int err = TIPC_OK;
+ struct net *net = sock_net(sk);
+ struct sk_buff_head inputq;
+ int limit, err = TIPC_OK;
- if (unlikely(!msg_isdata(hdr))) {
- switch (msg_user(hdr)) {
- case CONN_MANAGER:
- tipc_sk_proto_rcv(tsk, skb, xmitq);
- return false;
- case SOCK_WAKEUP:
- u32_del(&tsk->cong_links, msg_orignode(hdr));
- tsk->cong_link_cnt--;
- sk->sk_write_space(sk);
- break;
- case TOP_SRV:
- tipc_sk_top_evt(tsk, (void *)msg_data(hdr));
- break;
- default:
- break;
- }
- kfree_skb(skb);
- return false;
- }
+ TIPC_SKB_CB(skb)->bytes_read = 0;
+ __skb_queue_head_init(&inputq);
+ __skb_queue_tail(&inputq, skb);
- /* Drop if illegal message type */
- if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) {
- kfree_skb(skb);
- return false;
- }
+ if (unlikely(!msg_isdata(hdr)))
+ tipc_sk_proto_rcv(sk, &inputq, xmitq);
+ else if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG))
+ return kfree_skb(skb);
- /* Reject if wrong message type for current socket state */
- if (tipc_sk_type_connectionless(sk)) {
- if (msg_connected(hdr)) {
+ /* Validate and add to receive buffer if there is space */
+ while ((skb = __skb_dequeue(&inputq))) {
+ hdr = buf_msg(skb);
+ limit = rcvbuf_limit(sk, skb);
+ if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) ||
+ (!sk_conn && msg_connected(hdr)))
err = TIPC_ERR_NO_PORT;
- goto reject;
- }
- } else if (unlikely(!filter_connect(tsk, skb))) {
- err = TIPC_ERR_NO_PORT;
- goto reject;
- }
+ else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit)
+ err = TIPC_ERR_OVERLOAD;
- /* Reject message if there isn't room to queue it */
- if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) {
- err = TIPC_ERR_OVERLOAD;
- goto reject;
+ if (unlikely(err)) {
+ tipc_skb_reject(net, err, skb, xmitq);
+ err = TIPC_OK;
+ continue;
+ }
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ skb_set_owner_r(skb, sk);
+ sk->sk_data_ready(sk);
}
-
- /* Enqueue message */
- TIPC_SKB_CB(skb)->bytes_read = 0;
- __skb_queue_tail(&sk->sk_receive_queue, skb);
- skb_set_owner_r(skb, sk);
-
- sk->sk_data_ready(sk);
- return true;
-
-reject:
- if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err))
- __skb_queue_tail(xmitq, skb);
- return false;
}
/**
- * tipc_backlog_rcv - handle incoming message from backlog queue
+ * tipc_sk_backlog_rcv - handle incoming message from backlog queue
* @sk: socket
* @skb: message
*
@@ -1742,27 +1743,25 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
*
* Returns 0
*/
-static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
- unsigned int truesize = skb->truesize;
+ unsigned int before = sk_rmem_alloc_get(sk);
struct sk_buff_head xmitq;
u32 dnode, selector;
+ unsigned int added;
__skb_queue_head_init(&xmitq);
- if (likely(filter_rcv(sk, skb, &xmitq))) {
- atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt);
- return 0;
- }
+ tipc_sk_filter_rcv(sk, skb, &xmitq);
+ added = sk_rmem_alloc_get(sk) - before;
+ atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt);
- if (skb_queue_empty(&xmitq))
- return 0;
-
- /* Send response/rejected message */
- skb = __skb_dequeue(&xmitq);
- dnode = msg_destnode(buf_msg(skb));
- selector = msg_origport(buf_msg(skb));
- tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
+ /* Send pending response/rejected messages, if any */
+ while ((skb = __skb_dequeue(&xmitq))) {
+ selector = msg_origport(buf_msg(skb));
+ dnode = msg_destnode(buf_msg(skb));
+ tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
+ }
return 0;
}
@@ -1794,7 +1793,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
/* Add message directly to receive queue if possible */
if (!sock_owned_by_user(sk)) {
- filter_rcv(sk, skb, xmitq);
+ tipc_sk_filter_rcv(sk, skb, xmitq);
continue;
}
--
2.1.4
^ permalink raw reply related
* [net-next 05/18] tipc: add new function for sending multiple small messages
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
We see an increasing need to send multiple single-buffer messages
of TIPC_SYSTEM_IMPORTANCE to different individual destination nodes.
Instead of looping over the send queue and sending each buffer
individually, as we do now, we add a new help function
tipc_node_distr_xmit() to do this.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/node.c | 16 ++++++++++++++++
net/tipc/node.h | 1 +
net/tipc/socket.c | 14 ++------------
3 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6cc1ae6..89f8ac73 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1254,6 +1254,22 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode,
return 0;
}
+/* tipc_node_distr_xmit(): send single buffer msgs to individual destinations
+ * Note: this is only for SYSTEM_IMPORTANCE messages, which cannot be rejected
+ */
+int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *xmitq)
+{
+ struct sk_buff *skb;
+ u32 selector, dnode;
+
+ while ((skb = __skb_dequeue(xmitq))) {
+ selector = msg_origport(buf_msg(skb));
+ dnode = msg_destnode(buf_msg(skb));
+ tipc_node_xmit_skb(net, skb, dnode, selector);
+ }
+ return 0;
+}
+
void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
{
struct sk_buff *txskb;
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 8db59fe..df2f219 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -68,6 +68,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node,
char *linkname, size_t len);
int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode,
int selector);
+int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *list);
int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest,
u32 selector);
void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 81b7d46c..6b2b4ca 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1740,14 +1740,11 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
* @skb: message
*
* Caller must hold socket lock
- *
- * Returns 0
*/
static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
unsigned int before = sk_rmem_alloc_get(sk);
struct sk_buff_head xmitq;
- u32 dnode, selector;
unsigned int added;
__skb_queue_head_init(&xmitq);
@@ -1757,11 +1754,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt);
/* Send pending response/rejected messages, if any */
- while ((skb = __skb_dequeue(&xmitq))) {
- selector = msg_origport(buf_msg(skb));
- dnode = msg_destnode(buf_msg(skb));
- tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
- }
+ tipc_node_distr_xmit(sock_net(sk), &xmitq);
return 0;
}
@@ -1840,10 +1833,7 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
spin_unlock_bh(&sk->sk_lock.slock);
}
/* Send pending response/rejected messages, if any */
- while ((skb = __skb_dequeue(&xmitq))) {
- dnode = msg_destnode(buf_msg(skb));
- tipc_node_xmit_skb(net, skb, dnode, dport);
- }
+ tipc_node_distr_xmit(sock_net(sk), &xmitq);
sock_put(sk);
continue;
}
--
2.1.4
^ permalink raw reply related
* [net-next 06/18] tipc: improve destination linked list
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
We often see a need for a linked list of destination identities,
sometimes containing a port number, sometimes a node identity, and
sometimes both. The currently defined struct u32_list is not generic
enough to cover all cases, so we extend it to contain two u32 integers
and rename it to struct tipc_dest_list.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/bcast.c | 18 +++++------
net/tipc/name_table.c | 89 ++++++++++++++++++++++++++-------------------------
net/tipc/name_table.h | 22 ++++++++-----
net/tipc/socket.c | 12 +++----
4 files changed, 74 insertions(+), 67 deletions(-)
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index a140dd4..421fa44 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -259,19 +259,19 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
struct tipc_nlist *dests, u16 *cong_link_cnt)
{
struct sk_buff_head _pkts;
- struct u32_item *n, *tmp;
- u32 dst, selector;
+ struct tipc_dest *dst, *tmp;
+ u32 dnode, selector;
selector = msg_link_selector(buf_msg(skb_peek(pkts)));
skb_queue_head_init(&_pkts);
- list_for_each_entry_safe(n, tmp, &dests->list, list) {
- dst = n->value;
- if (!tipc_msg_pskb_copy(dst, pkts, &_pkts))
+ list_for_each_entry_safe(dst, tmp, &dests->list, list) {
+ dnode = dst->node;
+ if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts))
return -ENOMEM;
/* Any other return value than -ELINKCONG is ignored */
- if (tipc_node_xmit(net, &_pkts, dst, selector) == -ELINKCONG)
+ if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG)
(*cong_link_cnt)++;
}
return 0;
@@ -554,7 +554,7 @@ void tipc_nlist_add(struct tipc_nlist *nl, u32 node)
{
if (node == nl->self)
nl->local = true;
- else if (u32_push(&nl->list, node))
+ else if (tipc_dest_push(&nl->list, node, 0))
nl->remote++;
}
@@ -562,13 +562,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node)
{
if (node == nl->self)
nl->local = false;
- else if (u32_del(&nl->list, node))
+ else if (tipc_dest_del(&nl->list, node, 0))
nl->remote--;
}
void tipc_nlist_purge(struct tipc_nlist *nl)
{
- u32_list_purge(&nl->list);
+ tipc_dest_list_purge(&nl->list);
nl->remote = 0;
nl->local = 0;
}
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bd0aac8..20f75b1 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -634,7 +634,7 @@ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
info = sseq->info;
list_for_each_entry(publ, &info->node_list, node_list) {
if (publ->scope <= limit)
- u32_push(dports, publ->ref);
+ tipc_dest_push(dports, 0, publ->ref);
}
if (info->cluster_list_size != info->node_list_size)
@@ -1057,78 +1057,79 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-bool u32_find(struct list_head *l, u32 value)
+struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port)
{
- struct u32_item *item;
+ struct tipc_dest *dst;
+ u64 value = (u64)node << 32 | port;
- list_for_each_entry(item, l, list) {
- if (item->value == value)
- return true;
+ list_for_each_entry(dst, l, list) {
+ if (dst->value != value)
+ continue;
+ return dst;
}
- return false;
+ return NULL;
}
-bool u32_push(struct list_head *l, u32 value)
+bool tipc_dest_push(struct list_head *l, u32 node, u32 port)
{
- struct u32_item *item;
+ struct tipc_dest *dst;
+ u64 value = (u64)node << 32 | port;
- list_for_each_entry(item, l, list) {
- if (item->value == value)
- return false;
- }
- item = kmalloc(sizeof(*item), GFP_ATOMIC);
- if (unlikely(!item))
+ if (tipc_dest_find(l, node, port))
return false;
- item->value = value;
- list_add(&item->list, l);
+ dst = kmalloc(sizeof(*dst), GFP_ATOMIC);
+ if (unlikely(!dst))
+ return false;
+ dst->value = value;
+ list_add(&dst->list, l);
return true;
}
-u32 u32_pop(struct list_head *l)
+bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port)
{
- struct u32_item *item;
- u32 value = 0;
+ struct tipc_dest *dst;
if (list_empty(l))
- return 0;
- item = list_first_entry(l, typeof(*item), list);
- value = item->value;
- list_del(&item->list);
- kfree(item);
- return value;
+ return false;
+ dst = list_first_entry(l, typeof(*dst), list);
+ if (port)
+ *port = dst->port;
+ if (node)
+ *node = dst->node;
+ list_del(&dst->list);
+ kfree(dst);
+ return true;
}
-bool u32_del(struct list_head *l, u32 value)
+bool tipc_dest_del(struct list_head *l, u32 node, u32 port)
{
- struct u32_item *item, *tmp;
+ struct tipc_dest *dst;
- list_for_each_entry_safe(item, tmp, l, list) {
- if (item->value != value)
- continue;
- list_del(&item->list);
- kfree(item);
- return true;
- }
- return false;
+ dst = tipc_dest_find(l, node, port);
+ if (!dst)
+ return false;
+ list_del(&dst->list);
+ kfree(dst);
+ return true;
}
-void u32_list_purge(struct list_head *l)
+void tipc_dest_list_purge(struct list_head *l)
{
- struct u32_item *item, *tmp;
+ struct tipc_dest *dst, *tmp;
- list_for_each_entry_safe(item, tmp, l, list) {
- list_del(&item->list);
- kfree(item);
+ list_for_each_entry_safe(dst, tmp, l, list) {
+ list_del(&dst->list);
+ kfree(dst);
}
}
-int u32_list_len(struct list_head *l)
+int tipc_dest_list_len(struct list_head *l)
{
- struct u32_item *item;
+ struct tipc_dest *dst;
int i = 0;
- list_for_each_entry(item, l, list) {
+ list_for_each_entry(dst, l, list) {
i++;
}
return i;
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 6ebdeb1..d121175 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -120,16 +120,22 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
int tipc_nametbl_init(struct net *net);
void tipc_nametbl_stop(struct net *net);
-struct u32_item {
+struct tipc_dest {
struct list_head list;
- u32 value;
+ union {
+ struct {
+ u32 port;
+ u32 node;
+ };
+ u64 value;
+ };
};
-bool u32_push(struct list_head *l, u32 value);
-u32 u32_pop(struct list_head *l);
-bool u32_find(struct list_head *l, u32 value);
-bool u32_del(struct list_head *l, u32 value);
-void u32_list_purge(struct list_head *l);
-int u32_list_len(struct list_head *l);
+struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port);
+bool tipc_dest_push(struct list_head *l, u32 node, u32 port);
+bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port);
+bool tipc_dest_del(struct list_head *l, u32 node, u32 port);
+void tipc_dest_list_purge(struct list_head *l);
+int tipc_dest_list_len(struct list_head *l);
#endif
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 6b2b4ca..850358f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -565,7 +565,7 @@ static int tipc_release(struct socket *sock)
/* Reject any messages that accumulated in backlog queue */
release_sock(sk);
- u32_list_purge(&tsk->cong_links);
+ tipc_dest_list_purge(&tsk->cong_links);
tsk->cong_link_cnt = 0;
call_rcu(&tsk->rcu, tipc_sk_callback);
sock->sk = NULL;
@@ -826,8 +826,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
tipc_nametbl_mc_translate(net,
msg_nametype(msg), msg_namelower(msg),
msg_nameupper(msg), scope, &dports);
- portid = u32_pop(&dports);
- for (; portid; portid = u32_pop(&dports)) {
+ while (tipc_dest_pop(&dports, NULL, &portid)) {
_skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
if (_skb) {
msg_set_destport(buf_msg(_skb), portid);
@@ -1000,7 +999,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
}
/* Block or return if destination link is congested */
- rc = tipc_wait_for_cond(sock, &timeout, !u32_find(clinks, dnode));
+ rc = tipc_wait_for_cond(sock, &timeout,
+ !tipc_dest_find(clinks, dnode, 0));
if (unlikely(rc))
return rc;
@@ -1012,7 +1012,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
if (unlikely(rc == -ELINKCONG)) {
- u32_push(clinks, dnode);
+ tipc_dest_push(clinks, dnode, 0);
tsk->cong_link_cnt++;
rc = 0;
}
@@ -1549,7 +1549,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
tipc_sk_conn_proto_rcv(tsk, skb, xmitq);
return;
case SOCK_WAKEUP:
- u32_del(&tsk->cong_links, msg_orignode(hdr));
+ tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);
tsk->cong_link_cnt--;
sk->sk_write_space(sk);
break;
--
2.1.4
^ permalink raw reply related
* [net-next 15/18] tipc: guarantee that group broadcast doesn't bypass group unicast
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
We need a mechanism guaranteeing that group unicasts sent out from a
socket are not bypassed by later sent broadcasts from the same socket.
We do this as follows:
- Each time a unicast is sent, we set a the broadcast method for the
socket to "replicast" and "mandatory". This forces the first
subsequent broadcast message to follow the same network and data path
as the preceding unicast to a destination, hence preventing it from
overtaking the latter.
- In order to make the 'same data path' statement above true, we let
group unicasts pass through the multicast link input queue, instead
of as previously through the unicast link input queue.
- In the first broadcast following a unicast, we set a new header flag,
requiring all recipients to immediately acknowledge its reception.
- During the period before all the expected acknowledges are received,
the socket refuses to accept any more broadcast attempts, i.e., by
blocking or returning EAGAIN. This period should typically not be
longer than a few microseconds.
- When all acknowledges have been received, the sending socket will
open up for subsequent broadcasts, this time giving the link layer
freedom to itself select the best transmission method.
- The forced and/or abrupt transmission method changes described above
may lead to broadcasts arriving out of order to the recipients. We
remedy this by introducing code that checks and if necessary
re-orders such messages at the receiving end.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/group.c | 47 +++++++++++++++++++++++++++++++++++++++++------
net/tipc/group.h | 4 +---
net/tipc/link.c | 5 ++---
net/tipc/msg.h | 21 +++++++++++++++++++++
net/tipc/socket.c | 34 +++++++++++++++++++++++++++++-----
5 files changed, 94 insertions(+), 17 deletions(-)
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 5edceb6..1203929 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -71,6 +71,7 @@ struct tipc_member {
u16 advertised;
u16 window;
u16 bc_rcv_nxt;
+ u16 bc_acked;
bool usr_pending;
};
@@ -87,6 +88,7 @@ struct tipc_group {
u32 portid;
u16 member_cnt;
u16 bc_snd_nxt;
+ u16 bc_ackers;
bool loopback;
bool events;
};
@@ -258,6 +260,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
m->group = grp;
m->node = node;
m->port = port;
+ m->bc_acked = grp->bc_snd_nxt - 1;
grp->member_cnt++;
tipc_group_add_to_tree(grp, m);
tipc_nlist_add(&grp->dests, m->node);
@@ -275,6 +278,11 @@ static void tipc_group_delete_member(struct tipc_group *grp,
{
rb_erase(&m->tree_node, &grp->members);
grp->member_cnt--;
+
+ /* Check if we were waiting for replicast ack from this member */
+ if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1))
+ grp->bc_ackers--;
+
list_del_init(&m->list);
list_del_init(&m->congested);
@@ -325,16 +333,23 @@ void tipc_group_update_member(struct tipc_member *m, int len)
list_add_tail(&m->congested, &grp->congested);
}
-void tipc_group_update_bc_members(struct tipc_group *grp, int len)
+void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack)
{
struct tipc_member *m;
struct rb_node *n;
+ u16 prev = grp->bc_snd_nxt - 1;
for (n = rb_first(&grp->members); n; n = rb_next(n)) {
m = container_of(n, struct tipc_member, tree_node);
- if (tipc_group_is_enabled(m))
+ if (tipc_group_is_enabled(m)) {
tipc_group_update_member(m, len);
+ m->bc_acked = prev;
+ }
}
+
+ /* Mark number of acknowledges to expect, if any */
+ if (ack)
+ grp->bc_ackers = grp->member_cnt;
grp->bc_snd_nxt++;
}
@@ -375,6 +390,10 @@ bool tipc_group_bc_cong(struct tipc_group *grp, int len)
{
struct tipc_member *m = NULL;
+ /* If prev bcast was replicast, reject until all receivers have acked */
+ if (grp->bc_ackers)
+ return true;
+
if (list_empty(&grp->congested))
return false;
@@ -394,7 +413,7 @@ static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq)
u16 bc_seqno = msg_grp_bc_seqno(hdr);
int mtyp = msg_type(hdr);
- /* Bcast may be bypassed by unicast, - sort it in */
+ /* Bcast may be bypassed by unicast or other bcast, - sort it in */
if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) {
skb_queue_walk_safe(defq, _skb, tmp) {
_hdr = buf_msg(_skb);
@@ -418,7 +437,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
struct sk_buff_head *defq;
struct tipc_member *m;
struct tipc_msg *hdr;
- bool deliver, update;
+ bool ack, deliver, update;
u32 node, port;
int mtyp, blks;
@@ -454,6 +473,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
hdr = buf_msg(skb);
mtyp = msg_type(hdr);
deliver = true;
+ ack = false;
update = false;
if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt))
@@ -469,6 +489,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
/* Fall thru */
case TIPC_GRP_BCAST_MSG:
m->bc_rcv_nxt++;
+ ack = msg_grp_bc_ack_req(hdr);
break;
case TIPC_GRP_UCAST_MSG:
break;
@@ -483,6 +504,9 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
else
kfree_skb(skb);
+ if (ack)
+ tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq);
+
if (!update)
continue;
@@ -543,6 +567,8 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
} else if (mtyp == GRP_ADV_MSG) {
msg_set_adv_win(hdr, adv);
m->advertised += adv;
+ } else if (mtyp == GRP_ACK_MSG) {
+ msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt);
}
__skb_queue_tail(xmitq, skb);
}
@@ -596,7 +622,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
}
/* Otherwise deliver already received WITHDRAW event */
__skb_queue_tail(inputq, m->event_msg);
- *usr_wakeup = m->usr_pending;
+ *usr_wakeup = true;
tipc_group_delete_member(grp, m);
list_del_init(&m->congested);
return;
@@ -608,6 +634,15 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
m->usr_pending = false;
list_del_init(&m->congested);
return;
+ case GRP_ACK_MSG:
+ if (!m)
+ return;
+ m->bc_acked = msg_grp_bc_acked(hdr);
+ if (--grp->bc_ackers)
+ break;
+ *usr_wakeup = true;
+ m->usr_pending = false;
+ return;
default:
pr_warn("Received unknown GROUP_PROTO message\n");
}
@@ -681,7 +716,7 @@ void tipc_group_member_evt(struct tipc_group *grp,
TIPC_SKB_CB(skb)->orig_member = m->instance;
- *usr_wakeup = m->usr_pending;
+ *usr_wakeup = true;
m->usr_pending = false;
/* Hold back event if more messages might be expected */
diff --git a/net/tipc/group.h b/net/tipc/group.h
index e432066..d525e1c 100644
--- a/net/tipc/group.h
+++ b/net/tipc/group.h
@@ -61,7 +61,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup,
struct tipc_msg *hdr,
struct sk_buff_head *inputq,
struct sk_buff_head *xmitq);
-void tipc_group_update_bc_members(struct tipc_group *grp, int len);
+void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack);
bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
int len, struct tipc_member **m);
bool tipc_group_bc_cong(struct tipc_group *grp, int len);
@@ -69,7 +69,5 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
u32 port, struct sk_buff_head *xmitq);
u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
void tipc_group_update_member(struct tipc_member *m, int len);
-struct tipc_member *tipc_group_find_sender(struct tipc_group *grp,
- u32 node, u32 port);
int tipc_group_size(struct tipc_group *grp);
#endif
diff --git a/net/tipc/link.c b/net/tipc/link.c
index bd25bff..70a2149 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1046,13 +1046,12 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
case TIPC_MEDIUM_IMPORTANCE:
case TIPC_HIGH_IMPORTANCE:
case TIPC_CRITICAL_IMPORTANCE:
- if (unlikely(msg_mcast(hdr))) {
+ if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) {
skb_queue_tail(l->bc_rcvlink->inputq, skb);
return true;
}
- case CONN_MANAGER:
case GROUP_PROTOCOL:
- skb_queue_tail(inputq, skb);
+ case CONN_MANAGER:
return true;
case NAME_DISTRIBUTOR:
l->bc_rcvlink->state = LINK_ESTABLISHED;
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index b40a050..1c088a1 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -547,6 +547,7 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
#define GRP_JOIN_MSG 0
#define GRP_LEAVE_MSG 1
#define GRP_ADV_MSG 2
+#define GRP_ACK_MSG 3
/*
* Word 1
@@ -839,6 +840,16 @@ static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n)
msg_set_bits(m, 9, 16, 0xffff, n);
}
+static inline u16 msg_grp_bc_acked(struct tipc_msg *m)
+{
+ return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n)
+{
+ msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
/* Word 10
*/
static inline u16 msg_grp_evt(struct tipc_msg *m)
@@ -851,6 +862,16 @@ static inline void msg_set_grp_evt(struct tipc_msg *m, int n)
msg_set_bits(m, 10, 0, 0x3, n);
}
+static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m)
+{
+ return msg_bits(m, 10, 0, 0x1);
+}
+
+static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n)
+{
+ msg_set_bits(m, 10, 0, 0x1, n);
+}
+
static inline u16 msg_grp_bc_seqno(struct tipc_msg *m)
{
return msg_bits(m, 10, 16, 0xffff);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 015cdd9..379c5b9 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -825,6 +825,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
struct msghdr *m, struct tipc_member *mb,
u32 dnode, u32 dport, int dlen)
{
+ struct tipc_mc_method *method = &tsk->mc_method;
struct tipc_msg *hdr = &tsk->phdr;
struct sk_buff_head pkts;
u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group);
@@ -852,9 +853,12 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
tsk->cong_link_cnt++;
}
- /* Update send window and sequence number */
+ /* Update send window */
tipc_group_update_member(mb, blks);
+ /* A broadcast sent within next EXPIRE period must follow same path */
+ method->rcast = true;
+ method->mandatory = true;
return dlen;
}
@@ -1005,6 +1009,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
struct tipc_nlist *dsts = tipc_group_dests(grp);
struct tipc_mc_method *method = &tsk->mc_method;
struct sk_buff_head pkts;
+ bool ack = method->mandatory && method->rcast;
int blks = tsk_blocks(MCAST_H_SIZE + dlen);
int mtu = tipc_bcast_get_mtu(net);
int rc = -EHOSTUNREACH;
@@ -1031,6 +1036,9 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
msg_set_destnode(hdr, 0);
msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp));
+ /* Avoid getting stuck with repeated forced replicasts */
+ msg_set_grp_bc_ack_req(hdr, ack);
+
/* Build message as chain of buffers */
skb_queue_head_init(&pkts);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
@@ -1038,13 +1046,17 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
return rc;
/* Send message */
- rc = tipc_mcast_xmit(net, &pkts, method, dsts,
- &tsk->cong_link_cnt);
+ rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt);
if (unlikely(rc))
return rc;
/* Update broadcast sequence number and send windows */
- tipc_group_update_bc_members(tsk->group, blks);
+ tipc_group_update_bc_members(tsk->group, blks, ack);
+
+ /* Broadcast link is now free to choose method for next broadcast */
+ method->mandatory = false;
+ method->expires = jiffies;
+
return dlen;
}
@@ -1106,9 +1118,9 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
u32 self = tipc_own_addr(net);
u32 scope = TIPC_CLUSTER_SCOPE;
struct sk_buff_head tmpq;
- uint hsz;
struct sk_buff *skb, *_skb;
u32 lower = 0, upper = ~0;
+ int user, mtyp, hsz;
__skb_queue_head_init(&tmpq);
INIT_LIST_HEAD(&dports);
@@ -1116,6 +1128,18 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
skb = tipc_skb_peek(arrvq, &inputq->lock);
for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
msg = buf_msg(skb);
+ user = msg_user(msg);
+ mtyp = msg_type(msg);
+ if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
+ spin_lock_bh(&inputq->lock);
+ if (skb_peek(arrvq) == skb) {
+ __skb_dequeue(arrvq);
+ __skb_queue_tail(inputq, skb);
+ }
+ refcount_dec(&skb->users);
+ spin_unlock_bh(&inputq->lock);
+ continue;
+ }
hsz = skb_headroom(skb) + msg_hdr_sz(msg);
oport = msg_origport(msg);
onode = msg_orignode(msg);
--
2.1.4
^ permalink raw reply related
* [net-next 08/18] tipc: add second source address to recvmsg()/recvfrom()
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
With group communication, it becomes important for a message receiver to
identify not only from which socket (identfied by a node:port tuple) the
message was sent, but also the logical identity (type:instance) of the
sending member.
We fix this by adding a second instance of struct sockaddr_tipc to the
source address area when a message is read. The extra address struct
is filled in with data found in the received message header (type,) and
in the local member representation struct (instance.)
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/group.c | 3 +++
net/tipc/msg.h | 1 +
net/tipc/socket.c | 52 ++++++++++++++++++++++++++++++++++------------------
3 files changed, 38 insertions(+), 18 deletions(-)
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 20663e5..b30e24a 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -61,6 +61,7 @@ struct tipc_member {
struct list_head list;
u32 node;
u32 port;
+ u32 instance;
enum mbr_state state;
u16 bc_rcv_nxt;
};
@@ -282,6 +283,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
if (!tipc_group_is_receiver(m))
goto drop;
+ TIPC_SKB_CB(skb)->orig_member = m->instance;
__skb_queue_tail(inputq, skb);
m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1;
@@ -388,6 +390,7 @@ void tipc_group_member_evt(struct tipc_group *grp,
m->state = MBR_PUBLISHED;
else
m->state = MBR_JOINED;
+ m->instance = evt->found_lower;
tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
} else if (evt->event == TIPC_WITHDRAWN) {
if (!m)
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 7ba1045..6bf9840 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -100,6 +100,7 @@ struct plist;
struct tipc_skb_cb {
u32 bytes_read;
+ u32 orig_member;
struct sk_buff *tail;
bool validated;
u16 chain_imp;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1e5de367..43a74b8 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1222,26 +1222,42 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
}
/**
- * set_orig_addr - capture sender's address for received message
+ * tipc_sk_set_orig_addr - capture sender's address for received message
* @m: descriptor for message info
- * @msg: received message header
+ * @hdr: received message header
*
* Note: Address is not captured if not requested by receiver.
*/
-static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)
-{
- DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name);
-
- if (addr) {
- addr->family = AF_TIPC;
- addr->addrtype = TIPC_ADDR_ID;
- memset(&addr->addr, 0, sizeof(addr->addr));
- addr->addr.id.ref = msg_origport(msg);
- addr->addr.id.node = msg_orignode(msg);
- addr->addr.name.domain = 0; /* could leave uninitialized */
- addr->scope = 0; /* could leave uninitialized */
- m->msg_namelen = sizeof(struct sockaddr_tipc);
- }
+static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
+{
+ struct tipc_msg *hdr = buf_msg(skb);
+ struct sockaddr_pair {
+ struct sockaddr_tipc sock;
+ struct sockaddr_tipc member;
+ };
+ DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name);
+
+ if (!srcaddr)
+ return;
+
+ srcaddr->sock.family = AF_TIPC;
+ srcaddr->sock.addrtype = TIPC_ADDR_ID;
+ srcaddr->sock.addr.id.ref = msg_origport(hdr);
+ srcaddr->sock.addr.id.node = msg_orignode(hdr);
+ srcaddr->sock.addr.name.domain = 0;
+ srcaddr->sock.scope = 0;
+ m->msg_namelen = sizeof(struct sockaddr_tipc);
+
+ if (!msg_in_group(hdr))
+ return;
+
+ /* Group message users may also want to know sending member's id */
+ srcaddr->member.family = AF_TIPC;
+ srcaddr->member.addrtype = TIPC_ADDR_NAME;
+ srcaddr->member.addr.name.name.type = msg_nametype(hdr);
+ srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
+ srcaddr->member.addr.name.domain = 0;
+ m->msg_namelen = sizeof(*srcaddr);
}
/**
@@ -1432,7 +1448,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
} while (1);
/* Collect msg meta data, including error code and rejected data */
- set_orig_addr(m, hdr);
+ tipc_sk_set_orig_addr(m, skb);
rc = tipc_sk_anc_data_recv(m, hdr, tsk);
if (unlikely(rc))
goto exit;
@@ -1526,7 +1542,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
/* Collect msg meta data, incl. error code and rejected data */
if (!copied) {
- set_orig_addr(m, hdr);
+ tipc_sk_set_orig_addr(m, skb);
rc = tipc_sk_anc_data_recv(m, hdr, tsk);
if (rc)
break;
--
2.1.4
^ permalink raw reply related
* [net-next 07/18] tipc: introduce communication groups
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
As a preparation for introducing flow control for multicast and datagram
messaging we need a more strictly defined framework than we have now. A
socket must be able keep track of exactly how many and which other
sockets it is allowed to communicate with at any moment, and keep the
necessary state for those.
We therefore introduce a new concept we have named Communication Groups.
Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN.
The call takes four parameters: 'type' serves as group identifier,
'instance' serves as an logical member identifier, and 'scope' indicates
the visibility of the group (node/cluster/zone). Finally, 'flags' makes
it possible to set certain properties for the member. For now, there is
only one flag, indicating if the creator of the socket wants to receive
a copy of broadcast or multicast messages it is sending via the socket,
and if wants to be eligible as destination for its own anycasts.
A group is closed, i.e., sockets which have not joined a group will
not be able to send messages to or receive messages from members of
the group, and vice versa.
Any member of a group can send multicast ('group broadcast') messages
to all group members, optionally including itself, using the primitive
send(). The messages are received via the recvmsg() primitive. A socket
can only be member of one group at a time.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
include/uapi/linux/tipc.h | 14 ++
net/tipc/Makefile | 2 +-
net/tipc/group.c | 404 ++++++++++++++++++++++++++++++++++++++++++++++
net/tipc/group.h | 64 ++++++++
net/tipc/link.c | 3 +-
net/tipc/msg.h | 42 ++++-
net/tipc/name_table.c | 44 +++--
net/tipc/name_table.h | 3 +
net/tipc/node.h | 3 +-
net/tipc/socket.c | 201 ++++++++++++++++++++---
10 files changed, 740 insertions(+), 40 deletions(-)
create mode 100644 net/tipc/group.c
create mode 100644 net/tipc/group.h
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 5351b08..5f7b2c4 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -231,6 +231,20 @@ struct sockaddr_tipc {
#define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */
#define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */
#define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */
+#define TIPC_GROUP_JOIN 135 /* Takes struct tipc_group_req* */
+#define TIPC_GROUP_LEAVE 136 /* No argument */
+
+/*
+ * Flag values
+ */
+#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */
+
+struct tipc_group_req {
+ __u32 type; /* group id */
+ __u32 instance; /* member id */
+ __u32 scope; /* zone/cluster/node */
+ __u32 flags;
+};
/*
* Maximum sizes of TIPC bearer-related names (including terminating NULL)
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 31b9f9c..a3af73e 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -8,7 +8,7 @@ tipc-y += addr.o bcast.o bearer.o \
core.o link.o discover.o msg.o \
name_distr.o subscr.o monitor.o name_table.o net.o \
netlink.o netlink_compat.o node.o socket.o eth_media.o \
- server.o socket.o
+ server.o socket.o group.o
tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o
tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o
diff --git a/net/tipc/group.c b/net/tipc/group.c
new file mode 100644
index 0000000..20663e5
--- /dev/null
+++ b/net/tipc/group.c
@@ -0,0 +1,404 @@
+/*
+ * net/tipc/group.c: TIPC group messaging code
+ *
+ * Copyright (c) 2017, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "core.h"
+#include "addr.h"
+#include "group.h"
+#include "bcast.h"
+#include "server.h"
+#include "msg.h"
+#include "socket.h"
+#include "node.h"
+#include "name_table.h"
+#include "subscr.h"
+
+#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1)
+#define ADV_IDLE ADV_UNIT
+
+enum mbr_state {
+ MBR_QUARANTINED,
+ MBR_DISCOVERED,
+ MBR_JOINING,
+ MBR_PUBLISHED,
+ MBR_JOINED,
+ MBR_LEAVING
+};
+
+struct tipc_member {
+ struct rb_node tree_node;
+ struct list_head list;
+ u32 node;
+ u32 port;
+ enum mbr_state state;
+ u16 bc_rcv_nxt;
+};
+
+struct tipc_group {
+ struct rb_root members;
+ struct tipc_nlist dests;
+ struct net *net;
+ int subid;
+ u32 type;
+ u32 instance;
+ u32 domain;
+ u32 scope;
+ u32 portid;
+ u16 member_cnt;
+ u16 bc_snd_nxt;
+ bool loopback;
+};
+
+static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
+ int mtyp, struct sk_buff_head *xmitq);
+
+u16 tipc_group_bc_snd_nxt(struct tipc_group *grp)
+{
+ return grp->bc_snd_nxt;
+}
+
+static bool tipc_group_is_receiver(struct tipc_member *m)
+{
+ return m && m->state >= MBR_JOINED;
+}
+
+int tipc_group_size(struct tipc_group *grp)
+{
+ return grp->member_cnt;
+}
+
+struct tipc_group *tipc_group_create(struct net *net, u32 portid,
+ struct tipc_group_req *mreq)
+{
+ struct tipc_group *grp;
+ u32 type = mreq->type;
+
+ grp = kzalloc(sizeof(*grp), GFP_ATOMIC);
+ if (!grp)
+ return NULL;
+ tipc_nlist_init(&grp->dests, tipc_own_addr(net));
+ grp->members = RB_ROOT;
+ grp->net = net;
+ grp->portid = portid;
+ grp->domain = addr_domain(net, mreq->scope);
+ grp->type = type;
+ grp->instance = mreq->instance;
+ grp->scope = mreq->scope;
+ grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK;
+ if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid))
+ return grp;
+ kfree(grp);
+ return NULL;
+}
+
+void tipc_group_delete(struct net *net, struct tipc_group *grp)
+{
+ struct rb_root *tree = &grp->members;
+ struct sk_buff_head xmitq;
+ struct tipc_member *m, *tmp;
+
+ __skb_queue_head_init(&xmitq);
+
+ rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
+ tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
+ list_del(&m->list);
+ kfree(m);
+ }
+ tipc_node_distr_xmit(net, &xmitq);
+ tipc_nlist_purge(&grp->dests);
+ tipc_topsrv_kern_unsubscr(net, grp->subid);
+ kfree(grp);
+}
+
+struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
+ u32 node, u32 port)
+{
+ struct tipc_member *m;
+ struct rb_node *n = grp->members.rb_node;
+ u64 nkey, key = (u64)node << 32 | port;
+
+ while (n) {
+ m = container_of(n, struct tipc_member, tree_node);
+ nkey = (u64)m->node << 32 | m->port;
+ if (key < nkey)
+ n = n->rb_left;
+ else if (key > nkey)
+ n = n->rb_right;
+ else
+ return m;
+ }
+ return NULL;
+}
+
+static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
+ u32 node)
+{
+ struct tipc_member *m;
+ struct rb_node *n;
+
+ for (n = rb_first(&grp->members); n; n = rb_next(n)) {
+ m = container_of(n, struct tipc_member, tree_node);
+ if (m->node == node)
+ return m;
+ }
+ return NULL;
+}
+
+static void tipc_group_add_to_tree(struct tipc_group *grp,
+ struct tipc_member *m)
+{
+ struct rb_node **n, *parent = NULL;
+ u64 nkey, key = (u64)m->node << 32 | m->port;
+ struct tipc_member *tmp;
+
+ n = &grp->members.rb_node;
+ while (*n) {
+ tmp = container_of(*n, struct tipc_member, tree_node);
+ parent = *n;
+ tmp = container_of(parent, struct tipc_member, tree_node);
+ nkey = (u64)tmp->node << 32 | tmp->port;
+ if (key < nkey)
+ n = &(*n)->rb_left;
+ else if (key > nkey)
+ n = &(*n)->rb_right;
+ else
+ return;
+ }
+ rb_link_node(&m->tree_node, parent, n);
+ rb_insert_color(&m->tree_node, &grp->members);
+}
+
+static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
+ u32 node, u32 port,
+ int state)
+{
+ struct tipc_member *m;
+
+ m = kzalloc(sizeof(*m), GFP_ATOMIC);
+ if (!m)
+ return NULL;
+ INIT_LIST_HEAD(&m->list);
+ m->node = node;
+ m->port = port;
+ grp->member_cnt++;
+ tipc_group_add_to_tree(grp, m);
+ tipc_nlist_add(&grp->dests, m->node);
+ m->state = state;
+ return m;
+}
+
+void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port)
+{
+ tipc_group_create_member(grp, node, port, MBR_DISCOVERED);
+}
+
+static void tipc_group_delete_member(struct tipc_group *grp,
+ struct tipc_member *m)
+{
+ rb_erase(&m->tree_node, &grp->members);
+ grp->member_cnt--;
+ list_del_init(&m->list);
+
+ /* If last member on a node, remove node from dest list */
+ if (!tipc_group_find_node(grp, m->node))
+ tipc_nlist_del(&grp->dests, m->node);
+
+ kfree(m);
+}
+
+struct tipc_nlist *tipc_group_dests(struct tipc_group *grp)
+{
+ return &grp->dests;
+}
+
+void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+ int *scope)
+{
+ seq->type = grp->type;
+ seq->lower = grp->instance;
+ seq->upper = grp->instance;
+ *scope = grp->scope;
+}
+
+void tipc_group_update_bc_members(struct tipc_group *grp)
+{
+ grp->bc_snd_nxt++;
+}
+
+/* tipc_group_filter_msg() - determine if we should accept arriving message
+ */
+void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
+ struct sk_buff_head *xmitq)
+{
+ struct sk_buff *skb = __skb_dequeue(inputq);
+ struct tipc_member *m;
+ struct tipc_msg *hdr;
+ u32 node, port;
+ int mtyp;
+
+ if (!skb)
+ return;
+
+ hdr = buf_msg(skb);
+ mtyp = msg_type(hdr);
+ node = msg_orignode(hdr);
+ port = msg_origport(hdr);
+
+ if (!msg_in_group(hdr))
+ goto drop;
+
+ m = tipc_group_find_member(grp, node, port);
+ if (!tipc_group_is_receiver(m))
+ goto drop;
+
+ __skb_queue_tail(inputq, skb);
+
+ m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1;
+ return;
+drop:
+ kfree_skb(skb);
+}
+
+static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
+ int mtyp, struct sk_buff_head *xmitq)
+{
+ struct sk_buff *skb;
+ struct tipc_msg *hdr;
+
+ skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0,
+ m->node, tipc_own_addr(grp->net),
+ m->port, grp->portid, 0);
+ if (!skb)
+ return;
+
+ hdr = buf_msg(skb);
+ if (mtyp == GRP_JOIN_MSG)
+ msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt);
+ __skb_queue_tail(xmitq, skb);
+}
+
+void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr,
+ struct sk_buff_head *xmitq)
+{
+ struct tipc_member *m;
+ u32 node = msg_orignode(hdr);
+ u32 port = msg_origport(hdr);
+
+ if (!grp)
+ return;
+
+ m = tipc_group_find_member(grp, node, port);
+
+ switch (msg_type(hdr)) {
+ case GRP_JOIN_MSG:
+ if (!m)
+ m = tipc_group_create_member(grp, node, port,
+ MBR_QUARANTINED);
+ if (!m)
+ return;
+ m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr);
+
+ /* Wait until PUBLISH event is received */
+ if (m->state == MBR_DISCOVERED)
+ m->state = MBR_JOINING;
+ else if (m->state == MBR_PUBLISHED)
+ m->state = MBR_JOINED;
+ return;
+ case GRP_LEAVE_MSG:
+ if (!m)
+ return;
+
+ /* Wait until WITHDRAW event is received */
+ if (m->state != MBR_LEAVING) {
+ m->state = MBR_LEAVING;
+ return;
+ }
+ /* Otherwise deliver already received WITHDRAW event */
+ tipc_group_delete_member(grp, m);
+ return;
+ default:
+ pr_warn("Received unknown GROUP_PROTO message\n");
+ }
+}
+
+/* tipc_group_member_evt() - receive and handle a member up/down event
+ */
+void tipc_group_member_evt(struct tipc_group *grp,
+ struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
+{
+ struct tipc_msg *hdr = buf_msg(skb);
+ struct tipc_event *evt = (void *)msg_data(hdr);
+ struct tipc_member *m;
+ struct net *net;
+ u32 port = evt->port.ref;
+ u32 node = evt->port.node;
+ u32 self;
+
+ if (!grp)
+ goto drop;
+
+ net = grp->net;
+ self = tipc_own_addr(net);
+ if (!grp->loopback && node == self && port == grp->portid)
+ goto drop;
+
+ m = tipc_group_find_member(grp, node, port);
+
+ if (evt->event == TIPC_PUBLISHED) {
+ if (!m)
+ m = tipc_group_create_member(grp, node, port,
+ MBR_DISCOVERED);
+ if (!m)
+ goto drop;
+
+ /* Wait if JOIN message not yet received */
+ if (m->state == MBR_DISCOVERED)
+ m->state = MBR_PUBLISHED;
+ else
+ m->state = MBR_JOINED;
+ tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
+ } else if (evt->event == TIPC_WITHDRAWN) {
+ if (!m)
+ goto drop;
+
+ /* Keep back event if more messages might be expected */
+ if (m->state != MBR_LEAVING && tipc_node_is_up(net, node))
+ m->state = MBR_LEAVING;
+ else
+ tipc_group_delete_member(grp, m);
+ }
+drop:
+ kfree_skb(skb);
+}
diff --git a/net/tipc/group.h b/net/tipc/group.h
new file mode 100644
index 0000000..9bdf447
--- /dev/null
+++ b/net/tipc/group.h
@@ -0,0 +1,64 @@
+/*
+ * net/tipc/group.h: Include file for TIPC group unicast/multicast functions
+ *
+ * Copyright (c) 2017, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_GROUP_H
+#define _TIPC_GROUP_H
+
+#include "core.h"
+
+struct tipc_group;
+struct tipc_member;
+struct tipc_msg;
+
+struct tipc_group *tipc_group_create(struct net *net, u32 portid,
+ struct tipc_group_req *mreq);
+void tipc_group_delete(struct net *net, struct tipc_group *grp);
+void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port);
+struct tipc_nlist *tipc_group_dests(struct tipc_group *grp);
+void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+ int *scope);
+void tipc_group_filter_msg(struct tipc_group *grp,
+ struct sk_buff_head *inputq,
+ struct sk_buff_head *xmitq);
+void tipc_group_member_evt(struct tipc_group *grp,
+ struct sk_buff *skb,
+ struct sk_buff_head *xmitq);
+void tipc_group_proto_rcv(struct tipc_group *grp,
+ struct tipc_msg *hdr,
+ struct sk_buff_head *xmitq);
+void tipc_group_update_bc_members(struct tipc_group *grp);
+u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
+int tipc_group_size(struct tipc_group *grp);
+#endif
diff --git a/net/tipc/link.c b/net/tipc/link.c
index ac0144f..bd25bff 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1046,11 +1046,12 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
case TIPC_MEDIUM_IMPORTANCE:
case TIPC_HIGH_IMPORTANCE:
case TIPC_CRITICAL_IMPORTANCE:
- if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) {
+ if (unlikely(msg_mcast(hdr))) {
skb_queue_tail(l->bc_rcvlink->inputq, skb);
return true;
}
case CONN_MANAGER:
+ case GROUP_PROTOCOL:
skb_queue_tail(inputq, skb);
return true;
case NAME_DISTRIBUTOR:
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index be3e38a..7ba1045 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1,7 +1,7 @@
/*
* net/tipc/msg.h: Include file for TIPC message header routines
*
- * Copyright (c) 2000-2007, 2014-2015 Ericsson AB
+ * Copyright (c) 2000-2007, 2014-2016 Ericsson AB
* Copyright (c) 2005-2008, 2010-2011, Wind River Systems
* All rights reserved.
*
@@ -65,6 +65,7 @@ struct plist;
#define TIPC_MCAST_MSG 1
#define TIPC_NAMED_MSG 2
#define TIPC_DIRECT_MSG 3
+#define TIPC_GRP_BCAST_MSG 4
/*
* Internal message users
@@ -73,6 +74,7 @@ struct plist;
#define MSG_BUNDLER 6
#define LINK_PROTOCOL 7
#define CONN_MANAGER 8
+#define GROUP_PROTOCOL 9
#define TUNNEL_PROTOCOL 10
#define NAME_DISTRIBUTOR 11
#define MSG_FRAGMENTER 12
@@ -87,6 +89,7 @@ struct plist;
#define BASIC_H_SIZE 32 /* Basic payload message */
#define NAMED_H_SIZE 40 /* Named payload message */
#define MCAST_H_SIZE 44 /* Multicast payload message */
+#define GROUP_H_SIZE 44 /* Group payload message */
#define INT_H_SIZE 40 /* Internal messages */
#define MIN_H_SIZE 24 /* Smallest legal TIPC header size */
#define MAX_H_SIZE 60 /* Largest possible TIPC header size */
@@ -252,6 +255,11 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n)
msg_set_bits(m, 1, 29, 0x7, n);
}
+static inline int msg_in_group(struct tipc_msg *m)
+{
+ return (msg_type(m) == TIPC_GRP_BCAST_MSG);
+}
+
static inline u32 msg_named(struct tipc_msg *m)
{
return msg_type(m) == TIPC_NAMED_MSG;
@@ -259,7 +267,9 @@ static inline u32 msg_named(struct tipc_msg *m)
static inline u32 msg_mcast(struct tipc_msg *m)
{
- return msg_type(m) == TIPC_MCAST_MSG;
+ int mtyp = msg_type(m);
+
+ return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG));
}
static inline u32 msg_connected(struct tipc_msg *m)
@@ -515,6 +525,12 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
#define DSC_RESP_MSG 1
/*
+ * Group protocol message types
+ */
+#define GRP_JOIN_MSG 0
+#define GRP_LEAVE_MSG 1
+
+/*
* Word 1
*/
static inline u32 msg_seq_gap(struct tipc_msg *m)
@@ -795,6 +811,28 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n)
msg_set_bits(m, 9, 0, 0xffff, n);
}
+static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m)
+{
+ return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n)
+{
+ msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+/* Word 10
+ */
+static inline u16 msg_grp_bc_seqno(struct tipc_msg *m)
+{
+ return msg_bits(m, 10, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n)
+{
+ msg_set_bits(m, 10, 16, 0xffff, n);
+}
+
static inline bool msg_peer_link_is_up(struct tipc_msg *m)
{
if (likely(msg_user(m) != LINK_PROTOCOL))
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 20f75b1..941aed3 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -43,6 +43,7 @@
#include "bcast.h"
#include "addr.h"
#include "node.h"
+#include "group.h"
#include <net/genetlink.h>
#define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */
@@ -596,18 +597,6 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
return ref;
}
-/**
- * tipc_nametbl_mc_translate - find multicast destinations
- *
- * Creates list of all local ports that overlap the given multicast address;
- * also determines if any off-node ports overlap.
- *
- * Note: Publications with a scope narrower than 'limit' are ignored.
- * (i.e. local node-scope publications mustn't receive messages arriving
- * from another node, even if the multcast link brought it here)
- *
- * Returns non-zero if any off-node ports overlap
- */
int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
u32 limit, struct list_head *dports)
{
@@ -679,6 +668,37 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
rcu_read_unlock();
}
+/* tipc_nametbl_build_group - build list of communication group members
+ */
+void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
+ u32 type, u32 domain)
+{
+ struct sub_seq *sseq, *stop;
+ struct publication *p;
+ struct name_info *info;
+ struct name_seq *seq;
+
+ rcu_read_lock();
+ seq = nametbl_find_seq(net, type);
+ if (!seq)
+ goto exit;
+
+ spin_lock_bh(&seq->lock);
+ sseq = seq->sseqs;
+ stop = seq->sseqs + seq->first_free;
+ for (; sseq != stop; sseq++) {
+ info = sseq->info;
+ list_for_each_entry(p, &info->zone_list, zone_list) {
+ if (!tipc_in_scope(domain, p->node))
+ continue;
+ tipc_group_add_member(grp, p->node, p->ref);
+ }
+ }
+ spin_unlock_bh(&seq->lock);
+exit:
+ rcu_read_unlock();
+}
+
/*
* tipc_nametbl_publish - add name publication to network name tables
*/
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index d121175..97646b1 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -40,6 +40,7 @@
struct tipc_subscription;
struct tipc_plist;
struct tipc_nlist;
+struct tipc_group;
/*
* TIPC name types reserved for internal TIPC use (both current and planned)
@@ -101,6 +102,8 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node);
int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
u32 limit, struct list_head *dports);
+void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
+ u32 type, u32 domain);
void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
u32 upper, u32 domain,
struct tipc_nlist *nodes);
diff --git a/net/tipc/node.h b/net/tipc/node.h
index df2f219..acd58d2 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -48,7 +48,8 @@ enum {
TIPC_BCAST_SYNCH = (1 << 1),
TIPC_BCAST_STATE_NACK = (1 << 2),
TIPC_BLOCK_FLOWCTL = (1 << 3),
- TIPC_BCAST_RCAST = (1 << 4)
+ TIPC_BCAST_RCAST = (1 << 4),
+ TIPC_MCAST_GROUPS = (1 << 5)
};
#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 850358f..1e5de367 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1,7 +1,7 @@
/*
* net/tipc/socket.c: TIPC socket API
*
- * Copyright (c) 2001-2007, 2012-2016, Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2017, Ericsson AB
* Copyright (c) 2004-2008, 2010-2013, Wind River Systems
* All rights reserved.
*
@@ -45,6 +45,7 @@
#include "socket.h"
#include "bcast.h"
#include "netlink.h"
+#include "group.h"
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */
@@ -78,7 +79,7 @@ enum {
* @conn_timeout: the time we can wait for an unresponded setup request
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
* @cong_link_cnt: number of congested links
- * @sent_unacked: # messages sent by socket, and not yet acked by peer
+ * @snt_unacked: # messages sent by socket, and not yet acked by peer
* @rcv_unacked: # messages read by user, but not yet acked back to peer
* @peer: 'connected' peer for dgram/rdm
* @node: hash table node
@@ -109,6 +110,7 @@ struct tipc_sock {
struct rhash_head node;
struct tipc_mc_method mc_method;
struct rcu_head rcu;
+ struct tipc_group *group;
};
static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
@@ -123,6 +125,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq);
static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq);
+static int tipc_sk_leave(struct tipc_sock *tsk);
static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
static int tipc_sk_insert(struct tipc_sock *tsk);
static void tipc_sk_remove(struct tipc_sock *tsk);
@@ -559,6 +562,7 @@ static int tipc_release(struct socket *sock)
__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
sk->sk_shutdown = SHUTDOWN_MASK;
+ tipc_sk_leave(tsk);
tipc_sk_withdraw(tsk, 0, NULL);
sk_stop_timer(sk, &sk->sk_timer);
tipc_sk_remove(tsk);
@@ -601,7 +605,10 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
res = tipc_sk_withdraw(tsk, 0, NULL);
goto exit;
}
-
+ if (tsk->group) {
+ res = -EACCES;
+ goto exit;
+ }
if (uaddr_len < sizeof(struct sockaddr_tipc)) {
res = -EINVAL;
goto exit;
@@ -698,6 +705,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_group *grp = tsk->group;
u32 mask = 0;
sock_poll_wait(file, sk_sleep(sk), wait);
@@ -718,8 +726,9 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
mask |= (POLLIN | POLLRDNORM);
break;
case TIPC_OPEN:
- if (!tsk->cong_link_cnt)
- mask |= POLLOUT;
+ if (!grp || tipc_group_size(grp))
+ if (!tsk->cong_link_cnt)
+ mask |= POLLOUT;
if (tipc_sk_type_connectionless(sk) &&
(!skb_queue_empty(&sk->sk_receive_queue)))
mask |= (POLLIN | POLLRDNORM);
@@ -757,6 +766,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
struct tipc_nlist dsts;
int rc;
+ if (tsk->group)
+ return -EACCES;
+
/* Block or return if any destination link is congested */
rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt);
if (unlikely(rc))
@@ -794,6 +806,64 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
}
/**
+ * tipc_send_group_bcast - send message to all members in communication group
+ * @sk: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
+ int dlen, long timeout)
+{
+ struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_group *grp = tsk->group;
+ struct tipc_msg *hdr = &tsk->phdr;
+ struct tipc_nlist *dsts = tipc_group_dests(grp);
+ struct tipc_mc_method *method = &tsk->mc_method;
+ struct sk_buff_head pkts;
+ int mtu = tipc_bcast_get_mtu(net);
+ int rc = -EHOSTUNREACH;
+
+ if (!dsts->local && !dsts->remote)
+ return -EHOSTUNREACH;
+
+ /* Block or return if any destination link is congested */
+ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt);
+ if (unlikely(rc))
+ return rc;
+
+ /* Complete message header */
+ msg_set_type(hdr, TIPC_GRP_BCAST_MSG);
+ msg_set_hdr_sz(hdr, MCAST_H_SIZE);
+ msg_set_destport(hdr, 0);
+ msg_set_destnode(hdr, 0);
+ msg_set_nameinst(hdr, 0);
+ msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp));
+
+ /* Build message as chain of buffers */
+ skb_queue_head_init(&pkts);
+ rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
+ if (unlikely(rc != dlen))
+ return rc;
+
+ /* Send message */
+ rc = tipc_mcast_xmit(net, &pkts, method, dsts,
+ &tsk->cong_link_cnt);
+ if (unlikely(rc))
+ return rc;
+
+ /* Update broadcast sequence number */
+ tipc_group_update_bc_members(tsk->group);
+
+ return dlen;
+}
+
+/**
* tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
* @arrvq: queue with arriving messages, to be cloned after destination lookup
* @inputq: queue with cloned messages, delivered to socket after dest lookup
@@ -805,11 +875,13 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
{
struct tipc_msg *msg;
struct list_head dports;
- u32 portid;
+ u32 portid, oport, onode;
+ u32 self = tipc_own_addr(net);
u32 scope = TIPC_CLUSTER_SCOPE;
struct sk_buff_head tmpq;
uint hsz;
struct sk_buff *skb, *_skb;
+ u32 lower = 0, upper = ~0;
__skb_queue_head_init(&tmpq);
INIT_LIST_HEAD(&dports);
@@ -818,14 +890,18 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
msg = buf_msg(skb);
hsz = skb_headroom(skb) + msg_hdr_sz(msg);
-
- if (in_own_node(net, msg_orignode(msg)))
+ oport = msg_origport(msg);
+ onode = msg_orignode(msg);
+ if (onode == self)
scope = TIPC_NODE_SCOPE;
/* Create destination port list and message clones: */
- tipc_nametbl_mc_translate(net,
- msg_nametype(msg), msg_namelower(msg),
- msg_nameupper(msg), scope, &dports);
+ if (!msg_in_group(msg)) {
+ lower = msg_namelower(msg);
+ upper = msg_nameupper(msg);
+ }
+ tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper,
+ scope, &dports);
while (tipc_dest_pop(&dports, NULL, &portid)) {
_skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
if (_skb) {
@@ -895,10 +971,6 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
kfree_skb(skb);
}
-static void tipc_sk_top_evt(struct tipc_sock *tsk, struct tipc_event *evt)
-{
-}
-
/**
* tipc_sendmsg - send message in connectionless manner
* @sock: socket structure
@@ -934,6 +1006,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
struct list_head *clinks = &tsk->cong_links;
bool syn = !tipc_sk_type_connectionless(sk);
+ struct tipc_group *grp = tsk->group;
struct tipc_msg *hdr = &tsk->phdr;
struct tipc_name_seq *seq;
struct sk_buff_head pkts;
@@ -944,6 +1017,9 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
return -EMSGSIZE;
+ if (unlikely(grp))
+ return tipc_send_group_bcast(sock, m, dlen, timeout);
+
if (unlikely(!dest)) {
dest = &tsk->peer;
if (!syn || dest->family != AF_TIPC)
@@ -1543,6 +1619,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
struct tipc_sock *tsk = tipc_sk(sk);
struct sk_buff *skb = __skb_dequeue(inputq);
struct tipc_msg *hdr = buf_msg(skb);
+ struct tipc_group *grp = tsk->group;
switch (msg_user(hdr)) {
case CONN_MANAGER:
@@ -1553,8 +1630,12 @@ static void tipc_sk_proto_rcv(struct sock *sk,
tsk->cong_link_cnt--;
sk->sk_write_space(sk);
break;
+ case GROUP_PROTOCOL:
+ tipc_group_proto_rcv(grp, hdr, xmitq);
+ break;
case TOP_SRV:
- tipc_sk_top_evt(tsk, (void *)msg_data(hdr));
+ tipc_group_member_evt(tsk->group, skb, xmitq);
+ skb = NULL;
break;
default:
break;
@@ -1699,6 +1780,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
{
bool sk_conn = !tipc_sk_type_connectionless(sk);
struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_group *grp = tsk->group;
struct tipc_msg *hdr = buf_msg(skb);
struct net *net = sock_net(sk);
struct sk_buff_head inputq;
@@ -1710,15 +1792,19 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
if (unlikely(!msg_isdata(hdr)))
tipc_sk_proto_rcv(sk, &inputq, xmitq);
- else if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG))
+ else if (unlikely(msg_type(hdr) > TIPC_GRP_BCAST_MSG))
return kfree_skb(skb);
+ if (unlikely(grp))
+ tipc_group_filter_msg(grp, &inputq, xmitq);
+
/* Validate and add to receive buffer if there is space */
while ((skb = __skb_dequeue(&inputq))) {
hdr = buf_msg(skb);
limit = rcvbuf_limit(sk, skb);
if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) ||
- (!sk_conn && msg_connected(hdr)))
+ (!sk_conn && msg_connected(hdr)) ||
+ (!grp && msg_in_group(hdr)))
err = TIPC_ERR_NO_PORT;
else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit)
err = TIPC_ERR_OVERLOAD;
@@ -1837,7 +1923,6 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
sock_put(sk);
continue;
}
-
/* No destination socket => dequeue skb if still there */
skb = tipc_skb_dequeue(inputq, dport);
if (!skb)
@@ -1905,6 +1990,11 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
lock_sock(sk);
+ if (tsk->group) {
+ res = -EINVAL;
+ goto exit;
+ }
+
if (dst->family == AF_UNSPEC) {
memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
if (!tipc_sk_type_connectionless(sk))
@@ -2341,6 +2431,52 @@ void tipc_sk_rht_destroy(struct net *net)
rhashtable_destroy(&tn->sk_rht);
}
+static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
+{
+ struct net *net = sock_net(&tsk->sk);
+ struct tipc_group *grp = tsk->group;
+ u32 domain = addr_domain(net, mreq->scope);
+ struct tipc_msg *hdr = &tsk->phdr;
+ struct tipc_name_seq seq;
+ int rc;
+
+ if (mreq->type < TIPC_RESERVED_TYPES)
+ return -EACCES;
+ if (grp)
+ return -EACCES;
+ grp = tipc_group_create(net, tsk->portid, mreq);
+ if (!grp)
+ return -ENOMEM;
+ tsk->group = grp;
+ msg_set_lookup_scope(hdr, mreq->scope);
+ msg_set_nametype(hdr, mreq->type);
+ msg_set_dest_droppable(hdr, true);
+ seq.type = mreq->type;
+ seq.lower = mreq->instance;
+ seq.upper = seq.lower;
+ tipc_nametbl_build_group(net, grp, mreq->type, domain);
+ rc = tipc_sk_publish(tsk, mreq->scope, &seq);
+ if (rc)
+ tipc_group_delete(net, grp);
+ return rc;
+}
+
+static int tipc_sk_leave(struct tipc_sock *tsk)
+{
+ struct net *net = sock_net(&tsk->sk);
+ struct tipc_group *grp = tsk->group;
+ struct tipc_name_seq seq;
+ int scope;
+
+ if (!grp)
+ return -EINVAL;
+ tipc_group_self(grp, &seq, &scope);
+ tipc_group_delete(net, grp);
+ tsk->group = NULL;
+ tipc_sk_withdraw(tsk, scope, &seq);
+ return 0;
+}
+
/**
* tipc_setsockopt - set socket option
* @sock: socket structure
@@ -2359,6 +2495,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_group_req mreq;
u32 value = 0;
int res = 0;
@@ -2374,9 +2511,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
case TIPC_CONN_TIMEOUT:
if (ol < sizeof(value))
return -EINVAL;
- res = get_user(value, (u32 __user *)ov);
- if (res)
- return res;
+ if (get_user(value, (u32 __user *)ov))
+ return -EFAULT;
+ break;
+ case TIPC_GROUP_JOIN:
+ if (ol < sizeof(mreq))
+ return -EINVAL;
+ if (copy_from_user(&mreq, ov, sizeof(mreq)))
+ return -EFAULT;
break;
default:
if (ov || ol)
@@ -2409,6 +2551,12 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
tsk->mc_method.rcast = true;
tsk->mc_method.mandatory = true;
break;
+ case TIPC_GROUP_JOIN:
+ res = tipc_sk_join(tsk, &mreq);
+ break;
+ case TIPC_GROUP_LEAVE:
+ res = tipc_sk_leave(tsk);
+ break;
default:
res = -EINVAL;
}
@@ -2436,7 +2584,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- int len;
+ struct tipc_name_seq seq;
+ int len, scope;
u32 value;
int res;
@@ -2470,6 +2619,12 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
case TIPC_SOCK_RECVQ_DEPTH:
value = skb_queue_len(&sk->sk_receive_queue);
break;
+ case TIPC_GROUP_JOIN:
+ seq.type = 0;
+ if (tsk->group)
+ tipc_group_self(tsk->group, &seq, &scope);
+ value = seq.type;
+ break;
default:
res = -EINVAL;
}
--
2.1.4
^ permalink raw reply related
* [net-next 09/18] tipc: receive group membership events via member socket
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
Like with any other service, group members' availability can be
subscribed for by connecting to be topology server. However, because
the events arrive via a different socket than the member socket, there
is a real risk that membership events my arrive out of synch with the
actual JOIN/LEAVE action. I.e., it is possible to receive the first
messages from a new member before the corresponding JOIN event arrives,
just as it is possible to receive the last messages from a leaving
member after the LEAVE event has already been received.
Since each member socket is internally also subscribing for membership
events, we now fix this problem by passing those events on to the user
via the member socket. We leverage the already present member synch-
ronization protocol to guarantee correct message/event order. An event
is delivered to the user as an empty message where the two source
addresses identify the new/lost member. Furthermore, we set the MSG_OOB
bit in the message flags to mark it as an event. If the event is an
indication about a member loss we also set the MSG_EOR bit, so it can
be distinguished from a member addition event.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
include/uapi/linux/tipc.h | 1 +
net/tipc/group.c | 60 +++++++++++++++++++++++++++++++++++++----------
net/tipc/group.h | 2 ++
net/tipc/msg.h | 22 +++++++++++++++--
net/tipc/socket.c | 43 +++++++++++++++++++++------------
5 files changed, 98 insertions(+), 30 deletions(-)
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 5f7b2c4..ef41c11 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -238,6 +238,7 @@ struct sockaddr_tipc {
* Flag values
*/
#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */
+#define TIPC_GROUP_MEMBER_EVTS 0x2 /* Receive membership events in socket */
struct tipc_group_req {
__u32 type; /* group id */
diff --git a/net/tipc/group.c b/net/tipc/group.c
index b30e24a..fe2a76f 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -59,6 +59,7 @@ enum mbr_state {
struct tipc_member {
struct rb_node tree_node;
struct list_head list;
+ struct sk_buff *event_msg;
u32 node;
u32 port;
u32 instance;
@@ -79,6 +80,7 @@ struct tipc_group {
u16 member_cnt;
u16 bc_snd_nxt;
bool loopback;
+ bool events;
};
static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
@@ -117,6 +119,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid,
grp->instance = mreq->instance;
grp->scope = mreq->scope;
grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK;
+ grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS;
if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid))
return grp;
kfree(grp);
@@ -279,6 +282,13 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
if (!msg_in_group(hdr))
goto drop;
+ if (mtyp == TIPC_GRP_MEMBER_EVT) {
+ if (!grp->events)
+ goto drop;
+ __skb_queue_tail(inputq, skb);
+ return;
+ }
+
m = tipc_group_find_member(grp, node, port);
if (!tipc_group_is_receiver(m))
goto drop;
@@ -311,6 +321,7 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
}
void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr,
+ struct sk_buff_head *inputq,
struct sk_buff_head *xmitq)
{
struct tipc_member *m;
@@ -332,10 +343,12 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr,
m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr);
/* Wait until PUBLISH event is received */
- if (m->state == MBR_DISCOVERED)
+ if (m->state == MBR_DISCOVERED) {
m->state = MBR_JOINING;
- else if (m->state == MBR_PUBLISHED)
+ } else if (m->state == MBR_PUBLISHED) {
m->state = MBR_JOINED;
+ __skb_queue_tail(inputq, m->event_msg);
+ }
return;
case GRP_LEAVE_MSG:
if (!m)
@@ -347,6 +360,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr,
return;
}
/* Otherwise deliver already received WITHDRAW event */
+ __skb_queue_tail(inputq, m->event_msg);
tipc_group_delete_member(grp, m);
return;
default:
@@ -354,16 +368,17 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr,
}
}
-/* tipc_group_member_evt() - receive and handle a member up/down event
- */
void tipc_group_member_evt(struct tipc_group *grp,
struct sk_buff *skb,
+ struct sk_buff_head *inputq,
struct sk_buff_head *xmitq)
{
struct tipc_msg *hdr = buf_msg(skb);
struct tipc_event *evt = (void *)msg_data(hdr);
struct tipc_member *m;
struct net *net;
+ int event = evt->event;
+ u32 instance = evt->found_lower;
u32 port = evt->port.ref;
u32 node = evt->port.node;
u32 self;
@@ -376,32 +391,51 @@ void tipc_group_member_evt(struct tipc_group *grp,
if (!grp->loopback && node == self && port == grp->portid)
goto drop;
+ /* Convert message before delivery to user */
+ msg_set_hdr_sz(hdr, GROUP_H_SIZE);
+ msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE);
+ msg_set_type(hdr, TIPC_GRP_MEMBER_EVT);
+ msg_set_origport(hdr, port);
+ msg_set_orignode(hdr, node);
+ msg_set_nametype(hdr, grp->type);
+ msg_set_grp_evt(hdr, event);
+
m = tipc_group_find_member(grp, node, port);
- if (evt->event == TIPC_PUBLISHED) {
+ if (event == TIPC_PUBLISHED) {
if (!m)
m = tipc_group_create_member(grp, node, port,
MBR_DISCOVERED);
if (!m)
goto drop;
- /* Wait if JOIN message not yet received */
- if (m->state == MBR_DISCOVERED)
+ /* Hold back event if JOIN message not yet received */
+ if (m->state == MBR_DISCOVERED) {
+ m->event_msg = skb;
m->state = MBR_PUBLISHED;
- else
+ } else {
+ __skb_queue_tail(inputq, skb);
m->state = MBR_JOINED;
- m->instance = evt->found_lower;
+ }
+ m->instance = instance;
+ TIPC_SKB_CB(skb)->orig_member = m->instance;
tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
- } else if (evt->event == TIPC_WITHDRAWN) {
+ } else if (event == TIPC_WITHDRAWN) {
if (!m)
goto drop;
- /* Keep back event if more messages might be expected */
- if (m->state != MBR_LEAVING && tipc_node_is_up(net, node))
+ TIPC_SKB_CB(skb)->orig_member = m->instance;
+
+ /* Hold back event if more messages might be expected */
+ if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) {
+ m->event_msg = skb;
m->state = MBR_LEAVING;
- else
+ } else {
+ __skb_queue_tail(inputq, skb);
tipc_group_delete_member(grp, m);
+ }
}
+ return;
drop:
kfree_skb(skb);
}
diff --git a/net/tipc/group.h b/net/tipc/group.h
index 9bdf447..5d3f10d 100644
--- a/net/tipc/group.h
+++ b/net/tipc/group.h
@@ -54,9 +54,11 @@ void tipc_group_filter_msg(struct tipc_group *grp,
struct sk_buff_head *xmitq);
void tipc_group_member_evt(struct tipc_group *grp,
struct sk_buff *skb,
+ struct sk_buff_head *inputq,
struct sk_buff_head *xmitq);
void tipc_group_proto_rcv(struct tipc_group *grp,
struct tipc_msg *hdr,
+ struct sk_buff_head *inputq,
struct sk_buff_head *xmitq);
void tipc_group_update_bc_members(struct tipc_group *grp);
u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 6bf9840..3384ee6 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -65,7 +65,8 @@ struct plist;
#define TIPC_MCAST_MSG 1
#define TIPC_NAMED_MSG 2
#define TIPC_DIRECT_MSG 3
-#define TIPC_GRP_BCAST_MSG 4
+#define TIPC_GRP_MEMBER_EVT 4
+#define TIPC_GRP_BCAST_MSG 5
/*
* Internal message users
@@ -258,7 +259,14 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n)
static inline int msg_in_group(struct tipc_msg *m)
{
- return (msg_type(m) == TIPC_GRP_BCAST_MSG);
+ int mtyp = msg_type(m);
+
+ return (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MEMBER_EVT);
+}
+
+static inline bool msg_is_grp_evt(struct tipc_msg *m)
+{
+ return msg_type(m) == TIPC_GRP_MEMBER_EVT;
}
static inline u32 msg_named(struct tipc_msg *m)
@@ -824,6 +832,16 @@ static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n)
/* Word 10
*/
+static inline u16 msg_grp_evt(struct tipc_msg *m)
+{
+ return msg_bits(m, 10, 0, 0x3);
+}
+
+static inline void msg_set_grp_evt(struct tipc_msg *m, int n)
+{
+ msg_set_bits(m, 10, 0, 0x3, n);
+}
+
static inline u16 msg_grp_bc_seqno(struct tipc_msg *m)
{
return msg_bits(m, 10, 16, 0xffff);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43a74b8..ed0907c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -706,39 +706,41 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_group *grp = tsk->group;
- u32 mask = 0;
+ struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+ u32 revents = 0;
sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ revents |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ revents |= POLLHUP;
switch (sk->sk_state) {
case TIPC_ESTABLISHED:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
- mask |= POLLOUT;
+ revents |= POLLOUT;
/* fall thru' */
case TIPC_LISTEN:
case TIPC_CONNECTING:
- if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= (POLLIN | POLLRDNORM);
+ if (skb)
+ revents |= POLLIN | POLLRDNORM;
break;
case TIPC_OPEN:
if (!grp || tipc_group_size(grp))
if (!tsk->cong_link_cnt)
- mask |= POLLOUT;
- if (tipc_sk_type_connectionless(sk) &&
- (!skb_queue_empty(&sk->sk_receive_queue)))
- mask |= (POLLIN | POLLRDNORM);
+ revents |= POLLOUT;
+ if (!tipc_sk_type_connectionless(sk))
+ break;
+ if (!skb)
+ break;
+ revents |= POLLIN | POLLRDNORM;
break;
case TIPC_DISCONNECTING:
- mask = (POLLIN | POLLRDNORM | POLLHUP);
+ revents = POLLIN | POLLRDNORM | POLLHUP;
break;
}
-
- return mask;
+ return revents;
}
/**
@@ -1418,6 +1420,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
struct sk_buff *skb;
struct tipc_msg *hdr;
bool connected = !tipc_sk_type_connectionless(sk);
+ bool grp_evt;
int rc, err, hlen, dlen, copy;
long timeout;
@@ -1442,6 +1445,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
dlen = msg_data_sz(hdr);
hlen = msg_hdr_sz(hdr);
err = msg_errcode(hdr);
+ grp_evt = msg_is_grp_evt(hdr);
if (likely(dlen || err))
break;
tsk_advance_rx_queue(sk);
@@ -1468,11 +1472,20 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
if (unlikely(rc))
goto exit;
+ /* Mark message as group event if applicable */
+ if (unlikely(grp_evt)) {
+ if (msg_grp_evt(hdr) == TIPC_WITHDRAWN)
+ m->msg_flags |= MSG_EOR;
+ m->msg_flags |= MSG_OOB;
+ copy = 0;
+ }
+
/* Caption of data or error code/rejected data was successful */
if (unlikely(flags & MSG_PEEK))
goto exit;
tsk_advance_rx_queue(sk);
+
if (likely(!connected))
goto exit;
@@ -1647,10 +1660,10 @@ static void tipc_sk_proto_rcv(struct sock *sk,
sk->sk_write_space(sk);
break;
case GROUP_PROTOCOL:
- tipc_group_proto_rcv(grp, hdr, xmitq);
+ tipc_group_proto_rcv(grp, hdr, inputq, xmitq);
break;
case TOP_SRV:
- tipc_group_member_evt(tsk->group, skb, xmitq);
+ tipc_group_member_evt(tsk->group, skb, inputq, xmitq);
skb = NULL;
break;
default:
--
2.1.4
^ permalink raw reply related
* [net-next 11/18] tipc: introduce group unicast messaging
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
We now make it possible to send connectionless unicast messages
within a communication group. To send a message, the sender can use
either a direct port address, aka port identity, or an indirect port
name to be looked up.
This type of messages are subject to the same start synchronization
and flow control mechanism as group broadcast messages.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/group.c | 48 ++++++++++++++++++++++-
net/tipc/group.h | 3 ++
net/tipc/msg.h | 3 +-
net/tipc/socket.c | 112 +++++++++++++++++++++++++++++++++++++++++++++++++-----
4 files changed, 153 insertions(+), 13 deletions(-)
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 50dd7d1..2d624c0 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -186,6 +186,17 @@ struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
return NULL;
}
+static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp,
+ u32 node, u32 port)
+{
+ struct tipc_member *m;
+
+ m = tipc_group_find_member(grp, node, port);
+ if (m && tipc_group_is_enabled(m))
+ return m;
+ return NULL;
+}
+
static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
u32 node)
{
@@ -318,9 +329,42 @@ void tipc_group_update_bc_members(struct tipc_group *grp, int len)
grp->bc_snd_nxt++;
}
-bool tipc_group_bc_cong(struct tipc_group *grp, int len)
+bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
+ int len, struct tipc_member **mbr)
{
+ struct sk_buff_head xmitq;
struct tipc_member *m;
+ int adv, state;
+
+ if (list_empty(&grp->congested))
+ return false;
+
+ m = tipc_group_find_dest(grp, dnode, dport);
+ *mbr = m;
+ if (!m)
+ return false;
+ if (m->usr_pending)
+ return true;
+ if (m->window >= len)
+ return false;
+ m->usr_pending = true;
+
+ /* If not fully advertised, do it now to prevent mutual blocking */
+ adv = m->advertised;
+ state = m->state;
+ if (state < MBR_JOINED)
+ return true;
+ if (state == MBR_JOINED && adv == ADV_IDLE)
+ return true;
+ skb_queue_head_init(&xmitq);
+ tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq);
+ tipc_node_distr_xmit(grp->net, &xmitq);
+ return true;
+}
+
+bool tipc_group_bc_cong(struct tipc_group *grp, int len)
+{
+ struct tipc_member *m = NULL;
if (list_empty(&grp->congested))
return false;
@@ -329,7 +373,7 @@ bool tipc_group_bc_cong(struct tipc_group *grp, int len)
if (m->window >= len)
return false;
- return true;
+ return tipc_group_cong(grp, m->node, m->port, len, &m);
}
/* tipc_group_filter_msg() - determine if we should accept arriving message
diff --git a/net/tipc/group.h b/net/tipc/group.h
index 0e2740e..8f77290 100644
--- a/net/tipc/group.h
+++ b/net/tipc/group.h
@@ -61,9 +61,12 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup,
struct sk_buff_head *inputq,
struct sk_buff_head *xmitq);
void tipc_group_update_bc_members(struct tipc_group *grp, int len);
+bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
+ int len, struct tipc_member **m);
bool tipc_group_bc_cong(struct tipc_group *grp, int len);
void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
u32 port, struct sk_buff_head *xmitq);
u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
+void tipc_group_update_member(struct tipc_member *m, int len);
int tipc_group_size(struct tipc_group *grp);
#endif
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 820720c..7430fe7 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -67,6 +67,7 @@ struct plist;
#define TIPC_DIRECT_MSG 3
#define TIPC_GRP_MEMBER_EVT 4
#define TIPC_GRP_BCAST_MSG 5
+#define TIPC_GRP_UCAST_MSG 6
/*
* Internal message users
@@ -261,7 +262,7 @@ static inline int msg_in_group(struct tipc_msg *m)
{
int mtyp = msg_type(m);
- return (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MEMBER_EVT);
+ return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG;
}
static inline bool msg_is_grp_evt(struct tipc_msg *m)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d2f83fc9..4f7fee2 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -813,6 +813,93 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
}
/**
+ * tipc_send_group_msg - send a message to a member in the group
+ * @net: network namespace
+ * @m: message to send
+ * @mb: group member
+ * @dnode: destination node
+ * @dport: destination port
+ * @dlen: total length of message data
+ */
+static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
+ struct msghdr *m, struct tipc_member *mb,
+ u32 dnode, u32 dport, int dlen)
+{
+ struct tipc_msg *hdr = &tsk->phdr;
+ struct sk_buff_head pkts;
+ int blks = tsk_blocks(GROUP_H_SIZE + dlen);
+ int mtu, rc;
+
+ /* Complete message header */
+ msg_set_type(hdr, TIPC_GRP_UCAST_MSG);
+ msg_set_hdr_sz(hdr, GROUP_H_SIZE);
+ msg_set_destport(hdr, dport);
+ msg_set_destnode(hdr, dnode);
+
+ /* Build message as chain of buffers */
+ skb_queue_head_init(&pkts);
+ mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
+ rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
+ if (unlikely(rc != dlen))
+ return rc;
+
+ /* Send message */
+ rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
+ if (unlikely(rc == -ELINKCONG)) {
+ tipc_dest_push(&tsk->cong_links, dnode, 0);
+ tsk->cong_link_cnt++;
+ }
+
+ /* Update send window and sequence number */
+ tipc_group_update_member(mb, blks);
+
+ return dlen;
+}
+
+/**
+ * tipc_send_group_unicast - send message to a member in the group
+ * @sock: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
+ int dlen, long timeout)
+{
+ DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+ struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_group *grp = tsk->group;
+ struct tipc_member *mb = NULL;
+ int blks = tsk_blocks(GROUP_H_SIZE + dlen);
+ u32 node, port;
+ int rc;
+
+ node = dest->addr.id.node;
+ port = dest->addr.id.ref;
+ if (!port && !node)
+ return -EHOSTUNREACH;
+
+ /* Block or return if destination link or member is congested */
+ rc = tipc_wait_for_cond(sock, &timeout,
+ !tipc_dest_find(&tsk->cong_links, node, 0) &&
+ !tipc_group_cong(grp, node, port, blks, &mb));
+ if (unlikely(rc))
+ return rc;
+
+ if (unlikely(!mb))
+ return -EHOSTUNREACH;
+
+ rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen);
+
+ return rc ? rc : dlen;
+}
+
+/**
* tipc_send_group_bcast - send message to all members in communication group
* @sk: socket structure
* @m: message to send
@@ -1025,8 +1112,20 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
return -EMSGSIZE;
- if (unlikely(grp && !dest))
- return tipc_send_group_bcast(sock, m, dlen, timeout);
+ if (likely(dest)) {
+ if (unlikely(m->msg_namelen < sizeof(*dest)))
+ return -EINVAL;
+ if (unlikely(dest->family != AF_TIPC))
+ return -EINVAL;
+ }
+
+ if (grp) {
+ if (!dest)
+ return tipc_send_group_bcast(sock, m, dlen, timeout);
+ if (dest->addrtype == TIPC_ADDR_ID)
+ return tipc_send_group_unicast(sock, m, dlen, timeout);
+ return -EINVAL;
+ }
if (unlikely(!dest)) {
dest = &tsk->peer;
@@ -1034,12 +1133,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
return -EDESTADDRREQ;
}
- if (unlikely(m->msg_namelen < sizeof(*dest)))
- return -EINVAL;
-
- if (unlikely(dest->family != AF_TIPC))
- return -EINVAL;
-
if (unlikely(syn)) {
if (sk->sk_state == TIPC_LISTEN)
return -EPIPE;
@@ -1072,7 +1165,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
msg_set_destport(hdr, dport);
if (unlikely(!dport && !dnode))
return -EHOSTUNREACH;
-
} else if (dest->addrtype == TIPC_ADDR_ID) {
dnode = dest->addr.id.node;
msg_set_type(hdr, TIPC_DIRECT_MSG);
@@ -1845,7 +1937,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
if (unlikely(!msg_isdata(hdr)))
tipc_sk_proto_rcv(sk, &inputq, xmitq);
- else if (unlikely(msg_type(hdr) > TIPC_GRP_BCAST_MSG))
+ else if (unlikely(msg_type(hdr) > TIPC_GRP_UCAST_MSG))
return kfree_skb(skb);
if (unlikely(grp))
--
2.1.4
^ permalink raw reply related
* [net-next 12/18] tipc: introduce group anycast messaging
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
In this commit, we make it possible to send connectionless unicast
messages to any member corresponding to the given member identity,
when there is more than one such member. The sender must use a
TIPC_ADDR_NAME address to achieve this effect.
We also perform load balancing between the destinations, i.e., we
primarily select one which has advertised sufficient send window
to not cause a block/EAGAIN delay, if any. This mechanism is
overlayed on the always present round-robin selection.
Anycast messages are subject to the same start synchronization
and flow control mechanism as group broadcast messages.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/group.c | 7 +++++
net/tipc/group.h | 3 ++
net/tipc/name_table.c | 41 +++++++++++++++++++++++++
net/tipc/name_table.h | 3 ++
net/tipc/socket.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 138 insertions(+)
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 2d624c0..d3b8aba 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -116,6 +116,13 @@ static bool tipc_group_is_receiver(struct tipc_member *m)
return m && m->state >= MBR_JOINED;
}
+u32 tipc_group_exclude(struct tipc_group *grp)
+{
+ if (!grp->loopback)
+ return grp->portid;
+ return 0;
+}
+
int tipc_group_size(struct tipc_group *grp)
{
return grp->member_cnt;
diff --git a/net/tipc/group.h b/net/tipc/group.h
index 8f77290..e432066 100644
--- a/net/tipc/group.h
+++ b/net/tipc/group.h
@@ -49,6 +49,7 @@ void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port);
struct tipc_nlist *tipc_group_dests(struct tipc_group *grp);
void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
int *scope);
+u32 tipc_group_exclude(struct tipc_group *grp);
void tipc_group_filter_msg(struct tipc_group *grp,
struct sk_buff_head *inputq,
struct sk_buff_head *xmitq);
@@ -68,5 +69,7 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
u32 port, struct sk_buff_head *xmitq);
u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
void tipc_group_update_member(struct tipc_member *m, int len);
+struct tipc_member *tipc_group_find_sender(struct tipc_group *grp,
+ u32 node, u32 port);
int tipc_group_size(struct tipc_group *grp);
#endif
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 941aed3..a87aff0 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -597,6 +597,47 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
return ref;
}
+bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain,
+ struct list_head *dsts, int *dstcnt, u32 exclude,
+ bool all)
+{
+ struct publication *publ;
+ struct name_info *info;
+ struct name_seq *seq;
+ struct sub_seq *sseq;
+ u32 self = tipc_own_addr(net);
+
+ if (!tipc_in_scope(domain, self))
+ return false;
+
+ *dstcnt = 0;
+ rcu_read_lock();
+ seq = nametbl_find_seq(net, type);
+ if (unlikely(!seq))
+ goto exit;
+ spin_lock_bh(&seq->lock);
+ sseq = nameseq_find_subseq(seq, instance);
+ if (likely(sseq)) {
+ info = sseq->info;
+ list_for_each_entry(publ, &info->zone_list, zone_list) {
+ if (!tipc_in_scope(domain, publ->node))
+ continue;
+ if (publ->ref == exclude && publ->node == self)
+ continue;
+ tipc_dest_push(dsts, publ->node, publ->ref);
+ (*dstcnt)++;
+ if (all)
+ continue;
+ list_move_tail(&publ->zone_list, &info->zone_list);
+ break;
+ }
+ }
+ spin_unlock_bh(&seq->lock);
+exit:
+ rcu_read_unlock();
+ return !list_empty(dsts);
+}
+
int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
u32 limit, struct list_head *dports)
{
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 97646b1..71926e4 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -107,6 +107,9 @@ void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
u32 upper, u32 domain,
struct tipc_nlist *nodes);
+bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain,
+ struct list_head *dsts, int *dstcnt, u32 exclude,
+ bool all);
struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
u32 upper, u32 scope, u32 port_ref,
u32 key);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 4f7fee2..5ea93ac 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -900,6 +900,88 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
}
/**
+ * tipc_send_group_anycast - send message to any member with given identity
+ * @sock: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
+ int dlen, long timeout)
+{
+ DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+ struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_group *grp = tsk->group;
+ struct tipc_member *first = NULL;
+ struct tipc_member *mbr = NULL;
+ struct list_head *cong_links = &tsk->cong_links;
+ struct list_head dsts;
+ int blks = tsk_blocks(GROUP_H_SIZE + dlen);
+ u32 type, inst, domain;
+ u32 node, port, exclude;
+ int lookups = 0;
+ int dstcnt, rc;
+ bool cong;
+
+ INIT_LIST_HEAD(&dsts);
+
+ type = dest->addr.name.name.type;
+ inst = dest->addr.name.name.instance;
+ domain = addr_domain(net, dest->scope);
+ exclude = tipc_group_exclude(grp);
+
+ while (++lookups < 4) {
+ first = NULL;
+
+ /* Look for a non-congested destination member, if any */
+ while (1) {
+ if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts,
+ &dstcnt, exclude, false))
+ return -EHOSTUNREACH;
+ tipc_dest_pop(&dsts, &node, &port);
+ cong = tipc_group_cong(grp, node, port, blks, &mbr);
+ if (!cong)
+ break;
+ if (mbr == first)
+ break;
+ if (!first)
+ first = mbr;
+ }
+
+ /* Start over if destination was not in member list */
+ if (unlikely(!mbr))
+ continue;
+
+ if (likely(!cong && !tipc_dest_find(cong_links, node, 0)))
+ break;
+
+ /* Block or return if destination link or member is congested */
+ rc = tipc_wait_for_cond(sock, &timeout,
+ !tipc_dest_find(cong_links, node, 0) &&
+ !tipc_group_cong(grp, node, port,
+ blks, &mbr));
+ if (unlikely(rc))
+ return rc;
+
+ /* Send, unless destination disappeared while waiting */
+ if (likely(mbr))
+ break;
+ }
+
+ if (unlikely(lookups >= 4))
+ return -EHOSTUNREACH;
+
+ rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen);
+
+ return rc ? rc : dlen;
+}
+
+/**
* tipc_send_group_bcast - send message to all members in communication group
* @sk: socket structure
* @m: message to send
@@ -1122,6 +1204,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (grp) {
if (!dest)
return tipc_send_group_bcast(sock, m, dlen, timeout);
+ if (dest->addrtype == TIPC_ADDR_NAME)
+ return tipc_send_group_anycast(sock, m, dlen, timeout);
if (dest->addrtype == TIPC_ADDR_ID)
return tipc_send_group_unicast(sock, m, dlen, timeout);
return -EINVAL;
--
2.1.4
^ permalink raw reply related
* [net-next 16/18] tipc: guarantee delivery of UP event before first broadcast
From: Jon Maloy @ 2017-10-12 14:02 UTC (permalink / raw)
To: davem, netdev; +Cc: parthasarathy.bhuvaragan, ying.xue, tipc-discussion
In-Reply-To: <1507816959-31787-1-git-send-email-jon.maloy@ericsson.com>
The following scenario is possible:
- A user joins a group, and immediately sends out a broadcast message
to its members.
- The broadcast message, following a different data path than the
initial JOIN message sent out during the joining procedure, arrives
to a receiver before the latter..
- The receiver drops the message, since it is not ready to accept any
messages until the JOIN has arrived.
We avoid this by treating group protocol JOIN messages like unicast
messages.
- We let them pass through the recipient's multicast input queue, just
like ordinary unicasts.
- We force the first following broadacst to be sent as replicated
unicast and being acknowledged by the recipient before accepting
any more broadcast transmissions.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
---
net/tipc/link.c | 7 +++++--
net/tipc/socket.c | 4 ++++
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 70a2149..723dd69 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1039,6 +1039,7 @@ int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker,
static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *inputq)
{
+ struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq;
struct tipc_msg *hdr = buf_msg(skb);
switch (msg_user(hdr)) {
@@ -1047,12 +1048,14 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
case TIPC_HIGH_IMPORTANCE:
case TIPC_CRITICAL_IMPORTANCE:
if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) {
- skb_queue_tail(l->bc_rcvlink->inputq, skb);
+ skb_queue_tail(mc_inputq, skb);
return true;
}
- case GROUP_PROTOCOL:
case CONN_MANAGER:
return true;
+ case GROUP_PROTOCOL:
+ skb_queue_tail(mc_inputq, skb);
+ return true;
case NAME_DISTRIBUTOR:
l->bc_rcvlink->state = LINK_ESTABLISHED;
skb_queue_tail(l->namedq, skb);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 379c5b9..358a603 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2761,6 +2761,10 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
rc = tipc_sk_publish(tsk, mreq->scope, &seq);
if (rc)
tipc_group_delete(net, grp);
+
+ /* Eliminate any risk that a broadcast overtakes the sent JOIN */
+ tsk->mc_method.rcast = true;
+ tsk->mc_method.mandatory = true;
return rc;
}
--
2.1.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox