introduce support for XDP programs in CPUMAP

index 609f819ed08b..ab1c503808a4 100644
@@ -121,39 +121,48 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
 	xdp->frame_sz = frame->frame_sz;
 }
 
-/* Convert xdp_buff to xdp_frame */
 static inline
-struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
+int xdp_update_frame_from_buff(struct xdp_buff *xdp,
+			       struct xdp_frame *xdp_frame)
 {
-	struct xdp_frame *xdp_frame;
-	int metasize;
-	int headroom;
-
-	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
-		return xdp_convert_zc_to_xdp_frame(xdp);
+	int metasize, headroom;
 
 	/* Assure headroom is available for storing info */
 	headroom = xdp->data - xdp->data_hard_start;
 	metasize = xdp->data - xdp->data_meta;
 	metasize = metasize > 0 ? metasize : 0;
 	if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
-		return NULL;
+		return -ENOMEM;
 
 	/* Catch if driver didn't reserve tailroom for skb_shared_info */
 	if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
 		XDP_WARN("Driver BUG: missing reserved tailroom");
-		return NULL;
+		return -ENOMEM;
 	}
 
-	/* Store info in top of packet */
-	xdp_frame = xdp->data_hard_start;
-
 	xdp_frame->data = xdp->data;
 	xdp_frame->len  = xdp->data_end - xdp->data;
 	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
 	xdp_frame->metasize = metasize;
 	xdp_frame->frame_sz = xdp->frame_sz;
 
+	return 0;
+}
+
+/* Convert xdp_buff to xdp_frame */
+static inline
+struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
+{
+	struct xdp_frame *xdp_frame;
+
+	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		return xdp_convert_zc_to_xdp_frame(xdp);
+
+	/* Store info in top of packet */
+	xdp_frame = xdp->data_hard_start;
+	if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0))
+		return NULL;
+
 	/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
 	xdp_frame->mem = xdp->rxq->mem;
 

index f3468168982e..1a054737c35a 100644
@@ -684,6 +684,7 @@ int main(int argc, char **argv)
 	int add_cpu = -1;
 	int opt, err;
 	int prog_fd;
+	int *cpu, i;
 	__u32 qsize;
 
 	n_cpus = get_nprocs_conf();

@@ -719,6 +720,13 @@ int main(int argc, char **argv)
 	}
 	mark_cpus_unavailable();
 
+	cpu = malloc(n_cpus * sizeof(int));
+	if (!cpu) {
+		fprintf(stderr, "failed to allocate cpu array\n");
+		return EXIT_FAIL;
+	}
+	memset(cpu, 0, n_cpus * sizeof(int));
+
 	/* Parse commands line args */
 	while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzF",
 				  long_options, &longindex)) != -1) {

@@ -763,8 +771,7 @@ int main(int argc, char **argv)
 					errno, strerror(errno));
 				goto error;
 			}
-			create_cpu_entry(add_cpu, qsize, added_cpus, true);
-			added_cpus++;
+			cpu[added_cpus++] = add_cpu;
 			break;
 		case 'q':
 			qsize = atoi(optarg);

@@ -775,6 +782,7 @@ int main(int argc, char **argv)
 		case 'h':
 		error:
 		default:
+			free(cpu);
 			usage(argv, obj);
 			return EXIT_FAIL_OPTION;
 		}

@@ -787,16 +795,21 @@ int main(int argc, char **argv)
 	if (ifindex == -1) {
 		fprintf(stderr, "ERR: required option --dev missing\n");
 		usage(argv, obj);
-		return EXIT_FAIL_OPTION;
+		err = EXIT_FAIL_OPTION;
+		goto out;
 	}
 	/* 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, obj);
-		return EXIT_FAIL_OPTION;
+		err = EXIT_FAIL_OPTION;
+		goto out;
 	}
 
+	for (i = 0; i < added_cpus; i++)
+		create_cpu_entry(cpu[i], qsize, i, true);
+
 	/* Remove XDP program when program is interrupted or killed */
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);

@@ -804,27 +817,32 @@ int main(int argc, char **argv)
 	prog = bpf_object__find_program_by_title(obj, prog_name);
 	if (!prog) {
 		fprintf(stderr, "bpf_object__find_program_by_title failed\n");
-		return EXIT_FAIL;
+		err = EXIT_FAIL;
+		goto out;
 	}
 
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		fprintf(stderr, "bpf_program__fd failed\n");
-		return EXIT_FAIL;
+		err = EXIT_FAIL;
+		goto out;
 	}
 
 	if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
 		fprintf(stderr, "link set xdp fd failed\n");
-		return EXIT_FAIL_XDP;
+		err = EXIT_FAIL_XDP;
+		goto out;
 	}
 
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
 	if (err) {
 		printf("can't get prog info - %s\n", strerror(errno));
-		return err;
+		goto out;
 	}
 	prog_id = info.id;
 
 	stats_poll(interval, use_separators, prog_name, stress_mode);
-	return EXIT_OK;
+out:
+	free(cpu);
+	return err;
 }

index 27595fc6da56..57402276d8af 100644
@@ -48,11 +48,15 @@ struct xdp_bulk_queue {
 	unsigned int count;
 };
 
+/* CPUMAP value */
+struct bpf_cpumap_val {
+	u32 qsize;	/* queue size */
+};
+
 /* Struct for every remote "destination" CPU in map */
 struct bpf_cpu_map_entry {
 	u32 cpu;    /* kthread CPU and map index */
 	int map_id; /* Back reference to map */
-	u32 qsize;  /* Queue size placeholder for map lookup */
 
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
 	struct xdp_bulk_queue __percpu *bulkq;

@@ -66,6 +70,8 @@ struct bpf_cpu_map_entry {
 
 	atomic_t refcnt; /* Control when this struct can be free'ed */
 	struct rcu_head rcu;
+
+	struct bpf_cpumap_val value;
 };
 
 struct bpf_cpu_map {

@@ -307,8 +313,8 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
-						       int map_id)
+static struct bpf_cpu_map_entry *
+__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
 {
 	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;

@@ -338,13 +344,13 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 	if (!rcpu->queue)
 		goto free_bulkq;
 
-	err = ptr_ring_init(rcpu->queue, qsize, gfp);
+	err = ptr_ring_init(rcpu->queue, value->qsize, gfp);
 	if (err)
 		goto free_queue;
 
 	rcpu->cpu    = cpu;
 	rcpu->map_id = map_id;
-	rcpu->qsize  = qsize;
+	rcpu->value.qsize  = value->qsize;
 
 	/* Setup kthread */
 	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,

@@ -437,12 +443,12 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpumap_val cpumap_value = {};
 	struct bpf_cpu_map_entry *rcpu;
-
 	/* Array index key correspond to CPU number */
 	u32 key_cpu = *(u32 *)key;
-	/* Value is the queue size */
-	u32 qsize = *(u32 *)value;
+
+	memcpy(&cpumap_value, value, map->value_size);
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;

@@ -450,18 +456,18 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -E2BIG;
 	if (unlikely(map_flags == BPF_NOEXIST))
 		return -EEXIST;
-	if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+	if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */
 		return -EOVERFLOW;
 
 	/* Make sure CPU is a valid possible cpu */
 	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
 		return -ENODEV;
 
-	if (qsize == 0) {
+	if (cpumap_value.qsize == 0) {
 		rcpu = NULL; /* Same as deleting */
 	} else {
 		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
-		rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+		rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id);
 		if (!rcpu)
 			return -ENOMEM;
 		rcpu->cmap = cmap;

@@ -523,7 +529,7 @@ static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
 	struct bpf_cpu_map_entry *rcpu =
 		__cpu_map_lookup_elem(map, *(u32 *)key);
 
-	return rcpu ? &rcpu->qsize : NULL;
+	return rcpu ? &rcpu->value.qsize : NULL;
 }
 
 static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)

index e042311f991f..d5bbcdcc8321 100644
@@ -1256,6 +1256,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_flush(void);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+bool cpu_map_prog_allowed(struct bpf_map *map);
 
 /* Return map's numa specified by userspace */
 static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)

@@ -1416,6 +1417,11 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
 	return 0;
 }
 
+static inline bool cpu_map_prog_allowed(struct bpf_map *map)
+{
+	return false;
+}
+
 static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
 				enum bpf_prog_type type)
 {

index b73d3e141323..06ec557c6bf5 100644
@@ -177,9 +177,9 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 TRACE_EVENT(xdp_cpumap_kthread,
 
 	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
-		 int sched),
+		 int sched, unsigned int xdp_pass, unsigned int xdp_drop),
 
-	TP_ARGS(map_id, processed, drops, sched),
+	TP_ARGS(map_id, processed, drops, sched, xdp_pass, xdp_drop),
 
 	TP_STRUCT__entry(
 		__field(int, map_id)

@@ -188,6 +188,8 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__field(unsigned int, drops)
 		__field(unsigned int, processed)
 		__field(int, sched)
+		__field(unsigned int, xdp_pass)
+		__field(unsigned int, xdp_drop)
 	),
 
 	TP_fast_assign(

@@ -197,16 +199,20 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__entry->drops		= drops;
 		__entry->processed	= processed;
 		__entry->sched	= sched;
+		__entry->xdp_pass	= xdp_pass;
+		__entry->xdp_drop	= xdp_drop;
 	),
 
 	TP_printk("kthread"
 		  " cpu=%d map_id=%d action=%s"
 		  " processed=%u drops=%u"
-		  " sched=%d",
+		  " sched=%d"
+		  " xdp_pass=%u xdp_drop=%u",
 		  __entry->cpu, __entry->map_id,
 		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
 		  __entry->processed, __entry->drops,
-		  __entry->sched)
+		  __entry->sched,
+		  __entry->xdp_pass, __entry->xdp_drop)
 );
 
 TRACE_EVENT(xdp_cpumap_enqueue,

index f74bc4a2385e..10158943c0db 100644
@@ -226,6 +226,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
+	BPF_XDP_CPUMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 

196 lines not on this page · raw message

index 10684833f864..4b95adaa4641 100644
@@ -5429,6 +5429,8 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
 			if (dev_map_can_have_prog(new->aux->used_maps[i]))
 				return -EINVAL;
+			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+				return -EINVAL;
 		}
 	}
 

@@ -8853,6 +8855,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
+		if (prog->expected_attach_type == BPF_XDP_CPUMAP) {
+			NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device");
+			bpf_prog_put(prog);
+			return -EINVAL;
+		}
+
 		/* prog->aux->id may be 0 for orphaned device-bound progs */
 		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);

index 2e9dbfd8e60c..0c748c95179e 100644
@@ -7021,6 +7021,13 @@ static bool xdp_is_valid_access(int off, int size,
 		}
 	}
 
+	if (prog->expected_attach_type == BPF_XDP_CPUMAP) {
+		switch (off) {
+		case offsetof(struct xdp_md, ingress_ifindex):
+			return false;
+		}
+	}
+
 	if (type == BPF_WRITE) {
 		if (bpf_prog_is_dev_bound(prog->aux)) {
 			switch (off) {

index f74bc4a2385e..10158943c0db 100644
@@ -226,6 +226,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
+	BPF_XDP_CPUMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 

index 06ec557c6bf5..162ce06c6da0 100644
@@ -177,9 +177,11 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 TRACE_EVENT(xdp_cpumap_kthread,
 
 	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
-		 int sched, unsigned int xdp_pass, unsigned int xdp_drop),
+		 int sched, unsigned int xdp_pass, unsigned int xdp_drop,
+		 unsigned int xdp_redirect),
 
-	TP_ARGS(map_id, processed, drops, sched, xdp_pass, xdp_drop),
+	TP_ARGS(map_id, processed, drops, sched, xdp_pass, xdp_drop,
+		xdp_redirect),
 
 	TP_STRUCT__entry(
 		__field(int, map_id)

@@ -190,6 +192,7 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__field(int, sched)
 		__field(unsigned int, xdp_pass)
 		__field(unsigned int, xdp_drop)
+		__field(unsigned int, xdp_redirect)
 	),
 
 	TP_fast_assign(

@@ -201,18 +204,19 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__entry->sched	= sched;
 		__entry->xdp_pass	= xdp_pass;
 		__entry->xdp_drop	= xdp_drop;
+		__entry->xdp_redirect	= xdp_redirect;
 	),
 
 	TP_printk("kthread"
 		  " cpu=%d map_id=%d action=%s"
 		  " processed=%u drops=%u"
 		  " sched=%d"
-		  " xdp_pass=%u xdp_drop=%u",
+		  " xdp_pass=%u xdp_drop=%u xdp_redirect=%u",
 		  __entry->cpu, __entry->map_id,
 		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
 		  __entry->processed, __entry->drops,
 		  __entry->sched,
-		  __entry->xdp_pass, __entry->xdp_drop)
+		  __entry->xdp_pass, __entry->xdp_drop, __entry->xdp_redirect)
 );
 
 TRACE_EVENT(xdp_cpumap_enqueue,

index 24ab0a6b9772..a45157627fbc 100644
@@ -248,7 +248,7 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
-		unsigned int xdp_pass = 0, xdp_drop = 0;
+		unsigned int xdp_pass = 0, xdp_drop = 0, xdp_redirect = 0;
 		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
 		unsigned int drops = 0, sched = 0;
 		void *xdp_frames[CPUMAP_BATCH];

@@ -279,7 +279,7 @@ static int cpu_map_kthread_run(void *data)
 		n = ptr_ring_consume_batched(rcpu->queue, xdp_frames,
 					     CPUMAP_BATCH);
 
-		rcu_read_lock();
+		rcu_read_lock_bh();
 
 		prog = READ_ONCE(rcpu->prog);
 		for (i = 0; i < n; i++) {

@@ -315,6 +315,16 @@ static int cpu_map_kthread_run(void *data)
 					xdp_pass++;
 				}
 				break;
+			case XDP_REDIRECT:
+				err = xdp_do_redirect(xdpf->dev_rx, &xdp,
+						      prog);
+				if (unlikely(err)) {
+					xdp_return_frame(xdpf);
+					drops++;
+				} else {
+					xdp_redirect++;
+				}
+				break;
 			default:
 				bpf_warn_invalid_xdp_action(act);
 				/* fallthrough */

@@ -325,7 +335,10 @@ static int cpu_map_kthread_run(void *data)
 			}
 		}
 
-		rcu_read_unlock();
+		if (xdp_redirect)
+			xdp_do_flush_map();
+
+		rcu_read_unlock_bh();
 
 		m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp,
 					  nframes, skbs);

@@ -354,7 +367,7 @@ static int cpu_map_kthread_run(void *data)
 		}
 		/* Feedback loop via tracepoint */
 		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched,
-					 xdp_pass, xdp_drop);
+					 xdp_pass, xdp_drop, xdp_redirect);
 
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}

index 2baf8db1f7e7..30f500237753 100644
@@ -17,11 +17,20 @@
 
 #define MAX_CPUS NR_CPUS
 
+/* CPUMAP value */
+struct bpf_cpumap_val {
+	u32 qsize;
+	union {
+		int fd;
+		u32 id;
+	} prog;
+};
+
 /* Special map type that can XDP_REDIRECT frames to another CPU */
 struct {
 	__uint(type, BPF_MAP_TYPE_CPUMAP);
 	__uint(key_size, sizeof(u32));
-	__uint(value_size, sizeof(u32));
+	__uint(value_size, sizeof(struct bpf_cpumap_val));
 	__uint(max_entries, MAX_CPUS);
 } cpu_map SEC(".maps");
 

@@ -30,6 +39,9 @@ struct datarec {
 	__u64 processed;
 	__u64 dropped;
 	__u64 issue;
+	__u64 xdp_pass;
+	__u64 xdp_drop;
+	__u64 xdp_redirect;
 };
 
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success

@@ -692,13 +704,16 @@ int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
  * 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;
+	u64 __pad;			// First 8 bytes are not accessible
+	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;
+	unsigned int xdp_pass;		//	offset:32; size:4; signed:0;
+	unsigned int xdp_drop;		//	offset:36; size:4; signed:0;
+	unsigned int xdp_redirect;	//	offset:40; size:4; signed:0;
 };
 
 SEC("tracepoint/xdp/xdp_cpumap_kthread")

@@ -712,6 +727,9 @@ int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
 		return 0;
 	rec->processed += ctx->processed;
 	rec->dropped   += ctx->drops;
+	rec->xdp_pass  += ctx->xdp_pass;
+	rec->xdp_drop  += ctx->xdp_drop;
+	rec->xdp_redirect  += ctx->xdp_redirect;
 
 	/* Count times kthread yielded CPU via schedule call */
 	if (ctx->sched)

231 lines not on this page · raw message