aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/linux/bpf.h31
-rw-r--r--include/linux/bpf_types.h1
-rw-r--r--include/linux/netdevice.h1
-rw-r--r--include/trace/events/xdp.h80
-rw-r--r--include/uapi/linux/bpf.h1
-rw-r--r--kernel/bpf/Makefile1
-rw-r--r--kernel/bpf/cpumap.c702
-rw-r--r--kernel/bpf/syscall.c8
-rw-r--r--kernel/bpf/verifier.c8
-rw-r--r--net/core/dev.c27
-rw-r--r--net/core/filter.c140
-rw-r--r--samples/bpf/Makefile4
-rw-r--r--samples/bpf/xdp_redirect_cpu_kern.c609
-rw-r--r--samples/bpf/xdp_redirect_cpu_user.c697
-rw-r--r--tools/include/uapi/linux/bpf.h1
15 files changed, 2277 insertions, 34 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4373125de1f3..6d4dd844828a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -355,6 +355,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
+void __cpu_map_flush(struct bpf_map *map);
+struct xdp_buff;
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+ struct net_device *dev_rx);
+
/* Return map's numa specified by userspace */
static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
{
@@ -362,7 +369,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
attr->numa_node : NUMA_NO_NODE;
}
-#else
+#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
@@ -425,6 +432,28 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
static inline void __dev_map_flush(struct bpf_map *map)
{
}
+
+static inline
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ return NULL;
+}
+
+static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
+{
+}
+
+static inline void __cpu_map_flush(struct bpf_map *map)
+{
+}
+
+struct xdp_buff;
+static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return 0;
+}
#endif /* CONFIG_BPF_SYSCALL */
#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL)
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 6f1a567667b8..814c1081a4a9 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
#ifdef CONFIG_STREAM_PARSER
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
#endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 31bb3010c69b..bf014afcb914 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3260,6 +3260,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_core(struct sk_buff *skb);
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
void napi_gro_flush(struct napi_struct *napi, bool flush_old);
struct sk_buff *napi_get_frags(struct napi_struct *napi);
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 4e16c43fba10..0c8dec61987e 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -136,14 +136,90 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
__entry->map_id, __entry->map_index)
);
+#define devmap_ifindex(fwd, map) \
+ (!fwd ? 0 : \
+ (!map ? 0 : \
+ ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \
+ ((struct net_device *)fwd)->ifindex : 0)))
+
#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
- trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0, \
+ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \
0, map, idx)
#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
- trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0, \
+ trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
err, map, idx)
+TRACE_EVENT(xdp_cpumap_kthread,
+
+ TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
+ int sched),
+
+ TP_ARGS(map_id, processed, drops, sched),
+
+ TP_STRUCT__entry(
+ __field(int, map_id)
+ __field(u32, act)
+ __field(int, cpu)
+ __field(unsigned int, drops)
+ __field(unsigned int, processed)
+ __field(int, sched)
+ ),
+
+ TP_fast_assign(
+ __entry->map_id = map_id;
+ __entry->act = XDP_REDIRECT;
+ __entry->cpu = smp_processor_id();
+ __entry->drops = drops;
+ __entry->processed = processed;
+ __entry->sched = sched;
+ ),
+
+ TP_printk("kthread"
+ " cpu=%d map_id=%d action=%s"
+ " processed=%u drops=%u"
+ " sched=%d",
+ __entry->cpu, __entry->map_id,
+ __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+ __entry->processed, __entry->drops,
+ __entry->sched)
+);
+
+TRACE_EVENT(xdp_cpumap_enqueue,
+
+ TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
+ int to_cpu),
+
+ TP_ARGS(map_id, processed, drops, to_cpu),
+
+ TP_STRUCT__entry(
+ __field(int, map_id)
+ __field(u32, act)
+ __field(int, cpu)
+ __field(unsigned int, drops)
+ __field(unsigned int, processed)
+ __field(int, to_cpu)
+ ),
+
+ TP_fast_assign(
+ __entry->map_id = map_id;
+ __entry->act = XDP_REDIRECT;
+ __entry->cpu = smp_processor_id();
+ __entry->drops = drops;
+ __entry->processed = processed;
+ __entry->to_cpu = to_cpu;
+ ),
+
+ TP_printk("enqueue"
+ " cpu=%d map_id=%d action=%s"
+ " processed=%u drops=%u"
+ " to_cpu=%d",
+ __entry->cpu, __entry->map_id,
+ __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+ __entry->processed, __entry->drops,
+ __entry->to_cpu)
+);
+
#endif /* _TRACE_XDP_H */
#include <trace/define_trace.h>
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6db9e1d679cd..4303fb6c3817 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
};
enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 53fb09f92e3f..e597daae6120 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
ifeq ($(CONFIG_STREAM_PARSER),y)
obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
endif
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
new file mode 100644
index 000000000000..b4358d84ddf1
--- /dev/null
+++ b/kernel/bpf/cpumap.c
@@ -0,0 +1,702 @@
+/* bpf/cpumap.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2. See COPYING.
+ */
+
+/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
+ * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
+ *
+ * Unlike devmap which redirects XDP frames out another NIC device,
+ * this map type redirects raw XDP frames to another CPU. The remote
+ * CPU will do SKB-allocation and call the normal network stack.
+ *
+ * This is a scalability and isolation mechanism, that allow
+ * separating the early driver network XDP layer, from the rest of the
+ * netstack, and assigning dedicated CPUs for this stage. This
+ * basically allows for 10G wirespeed pre-filtering via bpf.
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/capability.h>
+#include <trace/events/xdp.h>
+
+#include <linux/netdevice.h> /* netif_receive_skb_core */
+#include <linux/etherdevice.h> /* eth_type_trans */
+
+/* General idea: XDP packets getting XDP redirected to another CPU,
+ * will maximum be stored/queued for one driver ->poll() call. It is
+ * guaranteed that setting flush bit and flush operation happen on
+ * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
+ * which queue in bpf_cpu_map_entry contains packets.
+ */
+
+#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */
+struct xdp_bulk_queue {
+ void *q[CPU_MAP_BULK_SIZE];
+ unsigned int count;
+};
+
+/* 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;
+
+ /* Queue with potential multi-producers, and single-consumer kthread */
+ struct ptr_ring *queue;
+ struct task_struct *kthread;
+ struct work_struct kthread_stop_wq;
+
+ atomic_t refcnt; /* Control when this struct can be free'ed */
+ struct rcu_head rcu;
+};
+
+struct bpf_cpu_map {
+ struct bpf_map map;
+ /* Below members specific for map type */
+ struct bpf_cpu_map_entry **cpu_map;
+ unsigned long __percpu *flush_needed;
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_bulk_queue *bq);
+
+static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
+{
+ return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_cpu_map *cmap;
+ int err = -ENOMEM;
+ u64 cost;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ /* check sanity of attributes */
+ if (attr->max_entries == 0 || attr->key_size != 4 ||
+ attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+ return ERR_PTR(-EINVAL);
+
+ cmap = kzalloc(sizeof(*cmap), GFP_USER);
+ if (!cmap)
+ return ERR_PTR(-ENOMEM);
+
+ /* mandatory map attributes */
+ cmap->map.map_type = attr->map_type;
+ cmap->map.key_size = attr->key_size;
+ cmap->map.value_size = attr->value_size;
+ cmap->map.max_entries = attr->max_entries;
+ cmap->map.map_flags = attr->map_flags;
+ cmap->map.numa_node = bpf_map_attr_numa_node(attr);
+
+ /* Pre-limit array size based on NR_CPUS, not final CPU check */
+ if (cmap->map.max_entries > NR_CPUS) {
+ err = -E2BIG;
+ goto free_cmap;
+ }
+
+ /* make sure page count doesn't overflow */
+ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
+ cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_cmap;
+ cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+ /* Notice returns -EPERM on if map size is larger than memlock limit */
+ ret = bpf_map_precharge_memlock(cmap->map.pages);
+ if (ret) {
+ err = ret;
+ goto free_cmap;
+ }
+
+ /* A per cpu bitfield with a bit per possible CPU in map */
+ cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
+ __alignof__(unsigned long));
+ if (!cmap->flush_needed)
+ goto free_cmap;
+
+ /* Alloc array for possible remote "destination" CPUs */
+ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
+ sizeof(struct bpf_cpu_map_entry *),
+ cmap->map.numa_node);
+ if (!cmap->cpu_map)
+ goto free_percpu;
+
+ return &cmap->map;
+free_percpu:
+ free_percpu(cmap->flush_needed);
+free_cmap:
+ kfree(cmap);
+ return ERR_PTR(err);
+}
+
+void __cpu_map_queue_destructor(void *ptr)
+{
+ /* The tear-down procedure should have made sure that queue is
+ * empty. See __cpu_map_entry_replace() and work-queue
+ * invoked cpu_map_kthread_stop(). Catch any broken behaviour
+ * gracefully and warn once.
+ */
+ if (WARN_ON_ONCE(ptr))
+ page_frag_free(ptr);
+}
+
+static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+ if (atomic_dec_and_test(&rcpu->refcnt)) {
+ /* The queue should be empty at this point */
+ ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor);
+ kfree(rcpu->queue);
+ kfree(rcpu);
+ }
+}
+
+static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+ atomic_inc(&rcpu->refcnt);
+}
+
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+ struct bpf_cpu_map_entry *rcpu;
+
+ rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+ /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+ * as it waits until all in-flight call_rcu() callbacks complete.
+ */
+ rcu_barrier();
+
+ /* kthread_stop will wake_up_process and wait for it to complete */
+ kthread_stop(rcpu->kthread);
+}
+
+/* For now, xdp_pkt is a cpumap internal data structure, with info
+ * carried between enqueue to dequeue. It is mapped into the top
+ * headroom of the packet, to avoid allocating separate mem.
+ */
+struct xdp_pkt {
+ void *data;
+ u16 len;
+ u16 headroom;
+ u16 metasize;
+ struct net_device *dev_rx;
+};
+
+/* Convert xdp_buff to xdp_pkt */
+static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp)
+{
+ struct xdp_pkt *xdp_pkt;
+ int metasize;
+ int 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 ((headroom - metasize) < sizeof(*xdp_pkt))
+ return NULL;
+
+ /* Store info in top of packet */
+ xdp_pkt = xdp->data_hard_start;
+
+ xdp_pkt->data = xdp->data;
+ xdp_pkt->len = xdp->data_end - xdp->data;
+ xdp_pkt->headroom = headroom - sizeof(*xdp_pkt);
+ xdp_pkt->metasize = metasize;
+
+ return xdp_pkt;
+}
+
+struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_pkt *xdp_pkt)
+{
+ unsigned int frame_size;
+ void *pkt_data_start;
+ struct sk_buff *skb;
+
+ /* build_skb need to place skb_shared_info after SKB end, and
+ * also want to know the memory "truesize". Thus, need to
+ * know the memory frame size backing xdp_buff.
+ *
+ * XDP was designed to have PAGE_SIZE frames, but this
+ * assumption is not longer true with ixgbe and i40e. It
+ * would be preferred to set frame_size to 2048 or 4096
+ * depending on the driver.
+ * frame_size = 2048;
+ * frame_len = frame_size - sizeof(*xdp_pkt);
+ *
+ * Instead, with info avail, skb_shared_info in placed after
+ * packet len. This, unfortunately fakes the truesize.
+ * Another disadvantage of this approach, the skb_shared_info
+ * is not at a fixed memory location, with mixed length
+ * packets, which is bad for cache-line hotness.
+ */
+ frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ pkt_data_start = xdp_pkt->data - xdp_pkt->headroom;
+ skb = build_skb(pkt_data_start, frame_size);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, xdp_pkt->headroom);
+ __skb_put(skb, xdp_pkt->len);
+ if (xdp_pkt->metasize)
+ skb_metadata_set(skb, xdp_pkt->metasize);
+
+ /* Essential SKB info: protocol and skb->dev */
+ skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx);
+
+ /* Optional SKB info, currently missing:
+ * - HW checksum info (skb->ip_summed)
+ * - HW RX hash (skb_set_hash)
+ * - RX ring dev queue index (skb_record_rx_queue)
+ */
+
+ return skb;
+}
+
+static int cpu_map_kthread_run(void *data)
+{
+ struct bpf_cpu_map_entry *rcpu = data;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* When kthread gives stop order, then rcpu have been disconnected
+ * from map, thus no new packets can enter. Remaining in-flight
+ * per CPU stored packets are flushed to this queue. Wait honoring
+ * kthread_stop signal until queue is empty.
+ */
+ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+ unsigned int processed = 0, drops = 0, sched = 0;
+ struct xdp_pkt *xdp_pkt;
+
+ /* Release CPU reschedule checks */
+ if (__ptr_ring_empty(rcpu->queue)) {
+ __set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+ sched = 1;
+ } else {
+ sched = cond_resched();
+ }
+ __set_current_state(TASK_RUNNING);
+
+ /* Process packets in rcpu->queue */
+ local_bh_disable();
+ /*
+ * The bpf_cpu_map_entry is single consumer, with this
+ * kthread CPU pinned. Lockless access to ptr_ring
+ * consume side valid as no-resize allowed of queue.
+ */
+ while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) {
+ struct sk_buff *skb;
+ int ret;
+
+ skb = cpu_map_build_skb(rcpu, xdp_pkt);
+ if (!skb) {
+ page_frag_free(xdp_pkt);
+ continue;
+ }
+
+ /* Inject into network stack */
+ ret = netif_receive_skb_core(skb);
+ if (ret == NET_RX_DROP)
+ drops++;
+
+ /* Limit BH-disable period */
+ if (++processed == 8)
+ break;
+ }
+ /* Feedback loop via tracepoint */
+ trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+
+ local_bh_enable(); /* resched point, may call do_softirq() */
+ }
+ __set_current_state(TASK_RUNNING);
+
+ put_cpu_map_entry(rcpu);
+ return 0;
+}
+
+struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
+{
+ gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+ struct bpf_cpu_map_entry *rcpu;
+ int numa, err;
+
+ /* Have map->numa_node, but choose node of redirect target CPU */
+ numa = cpu_to_node(cpu);
+
+ rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+ if (!rcpu)
+ return NULL;
+
+ /* Alloc percpu bulkq */
+ rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
+ sizeof(void *), gfp);
+ if (!rcpu->bulkq)
+ goto free_rcu;
+
+ /* Alloc queue */
+ rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+ if (!rcpu->queue)
+ goto free_bulkq;
+
+ err = ptr_ring_init(rcpu->queue, qsize, gfp);
+ if (err)
+ goto free_queue;
+
+ rcpu->cpu = cpu;
+ rcpu->map_id = map_id;
+ rcpu->qsize = qsize;
+
+ /* Setup kthread */
+ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
+ "cpumap/%d/map:%d", cpu, map_id);
+ if (IS_ERR(rcpu->kthread))
+ goto free_ptr_ring;
+
+ get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
+ get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
+
+ /* Make sure kthread runs on a single CPU */
+ kthread_bind(rcpu->kthread, cpu);
+ wake_up_process(rcpu->kthread);
+
+ return rcpu;
+
+free_ptr_ring:
+ ptr_ring_cleanup(rcpu->queue, NULL);
+free_queue:
+ kfree(rcpu->queue);
+free_bulkq:
+ free_percpu(rcpu->bulkq);
+free_rcu:
+ kfree(rcpu);
+ return NULL;
+}
+
+void __cpu_map_entry_free(struct rcu_head *rcu)
+{
+ struct bpf_cpu_map_entry *rcpu;
+ int cpu;
+
+ /* This cpu_map_entry have been disconnected from map and one
+ * RCU graze-period have elapsed. Thus, XDP cannot queue any
+ * new packets and cannot change/set flush_needed that can
+ * find this entry.
+ */
+ rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+
+ /* Flush remaining packets in percpu bulkq */
+ for_each_online_cpu(cpu) {
+ struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
+
+ /* No concurrent bq_enqueue can run at this point */
+ bq_flush_to_queue(rcpu, bq);
+ }
+ free_percpu(rcpu->bulkq);
+ /* Cannot kthread_stop() here, last put free rcpu resources */
+ put_cpu_map_entry(rcpu);
+}
+
+/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
+ * ensure any driver rcu critical sections have completed, but this
+ * does not guarantee a flush has happened yet. Because driver side
+ * rcu_read_lock/unlock only protects the running XDP program. The
+ * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
+ * pending flush op doesn't fail.
+ *
+ * The bpf_cpu_map_entry is still used by the kthread, and there can
+ * still be pending packets (in queue and percpu bulkq). A refcnt
+ * makes sure to last user (kthread_stop vs. call_rcu) free memory
+ * resources.
+ *
+ * The rcu callback __cpu_map_entry_free flush remaining packets in
+ * percpu bulkq to queue. Due to caller map_delete_elem() disable
+ * preemption, cannot call kthread_stop() to make sure queue is empty.
+ * Instead a work_queue is started for stopping kthread,
+ * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * stopping kthread, emptying the queue.
+ */
+void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+ u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+{
+ struct bpf_cpu_map_entry *old_rcpu;
+
+ old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+ if (old_rcpu) {
+ call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
+ INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
+ schedule_work(&old_rcpu->kthread_stop_wq);
+ }
+}
+
+int cpu_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ u32 key_cpu = *(u32 *)key;
+
+ if (key_cpu >= map->max_entries)
+ return -EINVAL;
+
+ /* notice caller map_delete_elem() use preempt_disable() */
+ __cpu_map_entry_replace(cmap, key_cpu, NULL);
+ return 0;
+}
+
+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_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;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ return -EINVAL;
+ if (unlikely(key_cpu >= cmap->map.max_entries))
+ return -E2BIG;
+ if (unlikely(map_flags == BPF_NOEXIST))
+ return -EEXIST;
+ if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+ return -EOVERFLOW;
+
+ /* Make sure CPU is a valid possible cpu */
+ if (!cpu_possible(key_cpu))
+ return -ENODEV;
+
+ if (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);
+ if (!rcpu)
+ return -ENOMEM;
+ }
+ rcu_read_lock();
+ __cpu_map_entry_replace(cmap, key_cpu, rcpu);
+ rcu_read_unlock();
+ return 0;
+}
+
+void cpu_map_free(struct bpf_map *map)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ int cpu;
+ u32 i;
+
+ /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+ * so the bpf programs (can be more than one that used this map) were
+ * disconnected from events. Wait for outstanding critical sections in
+ * these programs to complete. The rcu critical section only guarantees
+ * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
+ * It does __not__ ensure pending flush operations (if any) are
+ * complete.
+ */
+ synchronize_rcu();
+
+ /* To ensure all pending flush operations have completed wait for flush
+ * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+ * Because the above synchronize_rcu() ensures the map is disconnected
+ * from the program we can assume no new bits will be set.
+ */
+ for_each_online_cpu(cpu) {
+ unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu);
+
+ while (!bitmap_empty(bitmap, cmap->map.max_entries))
+ cond_resched();
+ }
+
+ /* For cpu_map the remote CPUs can still be using the entries
+ * (struct bpf_cpu_map_entry).
+ */
+ for (i = 0; i < cmap->map.max_entries; i++) {
+ struct bpf_cpu_map_entry *rcpu;
+
+ rcpu = READ_ONCE(cmap->cpu_map[i]);
+ if (!rcpu)
+ continue;
+
+ /* bq flush and cleanup happens after RCU graze-period */
+ __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+ }
+ free_percpu(cmap->flush_needed);
+ bpf_map_area_free(cmap->cpu_map);
+ kfree(cmap);
+}
+
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ struct bpf_cpu_map_entry *rcpu;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ rcpu = READ_ONCE(cmap->cpu_map[key]);
+ return rcpu;
+}
+
+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;
+}
+
+static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ u32 index = key ? *(u32 *)key : U32_MAX;
+ u32 *next = next_key;
+
+ if (index >= cmap->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (index == cmap->map.max_entries - 1)
+ return -ENOENT;
+ *next = index + 1;
+ return 0;
+}
+
+const struct bpf_map_ops cpu_map_ops = {
+ .map_alloc = cpu_map_alloc,
+ .map_free = cpu_map_free,
+ .map_delete_elem = cpu_map_delete_elem,
+ .map_update_elem = cpu_map_update_elem,
+ .map_lookup_elem = cpu_map_lookup_elem,
+ .map_get_next_key = cpu_map_get_next_key,
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_bulk_queue *bq)
+{
+ unsigned int processed = 0, drops = 0;
+ const int to_cpu = rcpu->cpu;
+ struct ptr_ring *q;
+ int i;
+
+ if (unlikely(!bq->count))
+ return 0;
+
+ q = rcpu->queue;
+ spin_lock(&q->producer_lock);
+
+ for (i = 0; i < bq->count; i++) {
+ void *xdp_pkt = bq->q[i];
+ int err;
+
+ err = __ptr_ring_produce(q, xdp_pkt);
+ if (err) {
+ drops++;
+ page_frag_free(xdp_pkt); /* Free xdp_pkt */
+ }
+ processed++;
+ }
+ bq->count = 0;
+ spin_unlock(&q->producer_lock);
+
+ /* Feedback loop via tracepoints */
+ trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
+ return 0;
+}
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
+{
+ struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+
+ if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
+ bq_flush_to_queue(rcpu, bq);
+
+ /* Notice, xdp_buff/page MUST be queued here, long enough for
+ * driver to code invoking us to finished, due to driver
+ * (e.g. ixgbe) recycle tricks based on page-refcnt.
+ *
+ * Thus, incoming xdp_pkt is always queued here (else we race
+ * with another CPU on page-refcnt and remaining driver code).
+ * Queue time is very short, as driver will invoke flush
+ * operation, when completing napi->poll call.
+ */
+ bq->q[bq->count++] = xdp_pkt;
+ return 0;
+}
+
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ struct xdp_pkt *xdp_pkt;
+
+ xdp_pkt = convert_to_xdp_pkt(xdp);
+ if (!xdp_pkt)
+ return -EOVERFLOW;
+
+ /* Info needed when constructing SKB on remote CPU */
+ xdp_pkt->dev_rx = dev_rx;
+
+ bq_enqueue(rcpu, xdp_pkt);
+ return 0;
+}
+
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+
+ __set_bit(bit, bitmap);
+}
+
+void __cpu_map_flush(struct bpf_map *map)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+ u32 bit;
+
+ /* The napi->poll softirq makes sure __cpu_map_insert_ctx()
+ * and __cpu_map_flush() happen on same CPU. Thus, the percpu
+ * bitmap indicate which percpu bulkq have packets.
+ */
+ for_each_set_bit(bit, bitmap, map->max_entries) {
+ struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]);
+ struct xdp_bulk_queue *bq;
+
+ /* This is possible if entry is removed by user space
+ * between xdp redirect and flush op.
+ */
+ if (unlikely(!rcpu))
+ continue;
+
+ __clear_bit(bit, bitmap);
+
+ /* Flush all frames in bulkq to real queue */
+ bq = this_cpu_ptr(rcpu->bulkq);
+ bq_flush_to_queue(rcpu, bq);
+
+ /* If already running, costs spin_lock_irqsave + smb_mb */
+ wake_up_process(rcpu->kthread);
+ }
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d124e702e040..54fba06942f5 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -592,6 +592,12 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
+ /* Need to create a kthread, thus must support schedule */
+ if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ err = map->ops->map_update_elem(map, key, value, attr->flags);
+ goto out;
+ }
+
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
* inside bpf map update or delete otherwise deadlocks are possible
*/
@@ -622,7 +628,7 @@ static int map_update_elem(union bpf_attr *attr)
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
-
+out:
if (!err)
trace_bpf_map_update_elem(map, ufd, key, value);
free_value:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9755279d94cb..e4d5136725a2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1444,6 +1444,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
+ /* Restrict bpf side of cpumap, open when use-cases appear */
+ case BPF_MAP_TYPE_CPUMAP:
+ if (func_id != BPF_FUNC_redirect_map)
+ goto error;
+ break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (func_id != BPF_FUNC_map_lookup_elem)
@@ -1481,7 +1486,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
goto error;
break;
case BPF_FUNC_redirect_map:
- if (map->map_type != BPF_MAP_TYPE_DEVMAP)
+ if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+ map->map_type != BPF_MAP_TYPE_CPUMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
diff --git a/net/core/dev.c b/net/core/dev.c
index d2b20e73080e..cf5894f0e6eb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4492,6 +4492,33 @@ out:
return ret;
}
+/**
+ * netif_receive_skb_core - special purpose version of netif_receive_skb
+ * @skb: buffer to process
+ *
+ * More direct receive version of netif_receive_skb(). It should
+ * only be used by callers that have a need to skip RPS and Generic XDP.
+ * Caller must also take care of handling if (page_is_)pfmemalloc.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb_core(struct sk_buff *skb)
+{
+ int ret;
+
+ rcu_read_lock();
+ ret = __netif_receive_skb_core(skb, false);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(netif_receive_skb_core);
+
static int __netif_receive_skb(struct sk_buff *skb)
{
int ret;
diff --git a/net/core/filter.c b/net/core/filter.c
index 140fa9f9c0f4..4d88e0665c41 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2526,10 +2526,36 @@ static int __bpf_tx_xdp(struct net_device *dev,
err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
if (err)
return err;
- if (map)
+ dev->netdev_ops->ndo_xdp_flush(dev);
+ return 0;
+}
+
+static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
+ struct bpf_map *map,
+ struct xdp_buff *xdp,
+ u32 index)
+{
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ struct net_device *dev = fwd;
+
+ if (!dev->netdev_ops->ndo_xdp_xmit)
+ return -EOPNOTSUPP;
+
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+ if (err)
+ return err;
__dev_map_insert_ctx(map, index);
- else
- dev->netdev_ops->ndo_xdp_flush(dev);
+
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ struct bpf_cpu_map_entry *rcpu = fwd;
+
+ err = cpu_map_enqueue(rcpu, xdp, dev_rx);
+ if (err)
+ return err;
+ __cpu_map_insert_ctx(map, index);
+ }
return 0;
}
@@ -2539,11 +2565,33 @@ void xdp_do_flush_map(void)
struct bpf_map *map = ri->map_to_flush;
ri->map_to_flush = NULL;
- if (map)
- __dev_map_flush(map);
+ if (map) {
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ __dev_map_flush(map);
+ break;
+ case BPF_MAP_TYPE_CPUMAP:
+ __cpu_map_flush(map);
+ break;
+ default:
+ break;
+ }
+ }
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
+{
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ return __dev_map_lookup_elem(map, index);
+ case BPF_MAP_TYPE_CPUMAP:
+ return __cpu_map_lookup_elem(map, index);
+ default:
+ return NULL;
+ }
+}
+
static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
unsigned long aux)
{
@@ -2556,8 +2604,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
- struct net_device *fwd = NULL;
u32 index = ri->ifindex;
+ void *fwd = NULL;
int err;
ri->ifindex = 0;
@@ -2570,7 +2618,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
goto err;
}
- fwd = __dev_map_lookup_elem(map, index);
+ fwd = __xdp_map_lookup_elem(map, index);
if (!fwd) {
err = -EINVAL;
goto err;
@@ -2578,7 +2626,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
if (ri->map_to_flush && ri->map_to_flush != map)
xdp_do_flush_map();
- err = __bpf_tx_xdp(fwd, map, xdp, index);
+ err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index);
if (unlikely(err))
goto err;
@@ -2620,54 +2668,88 @@ err:
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
+{
+ unsigned int len;
+
+ if (unlikely(!(fwd->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+ if (skb->len > len)
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
- unsigned int len;
int err = 0;
ri->ifindex = 0;
ri->map = NULL;
ri->map_owner = 0;
- if (map) {
- if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
- err = -EFAULT;
- map = NULL;
- goto err;
- }
- fwd = __dev_map_lookup_elem(map, index);
- } else {
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
+ err = -EFAULT;
+ map = NULL;
+ goto err;
}
+ fwd = __xdp_map_lookup_elem(map, index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
}
- if (unlikely(!(fwd->flags & IFF_UP))) {
- err = -ENETDOWN;
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+ skb->dev = fwd;
+ } else {
+ /* TODO: Handle BPF_MAP_TYPE_CPUMAP */
+ err = -EBADRQC;
goto err;
}
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len) {
- err = -EMSGSIZE;
+ _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+ return 0;
+err:
+ _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+ return err;
+}
+
+int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ u32 index = ri->ifindex;
+ struct net_device *fwd;
+ int err = 0;
+
+ if (ri->map)
+ return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+
+ ri->ifindex = 0;
+ fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
goto err;
}
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+
skb->dev = fwd;
- map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
- : _trace_xdp_redirect(dev, xdp_prog, index);
+ _trace_xdp_redirect(dev, xdp_prog, index);
return 0;
err:
- map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err)
- : _trace_xdp_redirect_err(dev, xdp_prog, index, err);
+ _trace_xdp_redirect_err(dev, xdp_prog, index, err);
return err;
}
EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 81f9fcd736b7..3534ccfb5920 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, &eth_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, &eth_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;
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index fb4fb81ce5b0..fa93033dc521 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
};
enum bpf_prog_type {
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.