bpf: cpumap: Implement generic cpumap

This change implements CPUMAP redirect support for generic XDP programs.
The idea is to reuse the cpu map entry's queue that is used to push
native xdp frames for redirecting skb to a different CPU. This will
match native XDP behavior (in that RPS is invoked again for packet
reinjected into networking stack).

To be able to determine whether the incoming skb is from the driver or
cpumap, we reuse skb->redirected bit that skips generic XDP processing
when it is set. To always make use of this, CONFIG_NET_REDIRECT guard on
it has been lifted and it is always available.

>From the redirect side, we add the skb to ptr_ring with its lowest bit
set to 1.  This should be safe as skb is not 1-byte aligned. This allows
kthread to discern between xdp_frames and sk_buff. On consumption of the
ptr_ring item, the lowest bit is unset.

In the end, the skb is simply added to the list that kthread is anyway
going to maintain for xdp_frames converted to skb, and then received
again by using netif_receive_skb_list.

Bulking optimization for generic cpumap is left as an exercise for a
future patch for now.

Since cpumap entry progs are now supported, also remove check in
generic_xdp_install for the cpumap.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20210702111825.491065-4-memxor@gmail.com

1 files changed, 98 insertions, 18 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 480e936c54d0..585b2b77ccc4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -16,6 +16,7 @@
  * netstack, and assigning dedicated CPUs for this stage.  This
  * basically allows for 10G wirespeed pre-filtering via bpf.
  */
+#include <linux/bitops.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/ptr_ring.h>
@@ -168,6 +169,46 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
+				     struct list_head *listp,
+				     struct xdp_cpumap_stats *stats)
+{
+	struct sk_buff *skb, *tmp;
+	struct xdp_buff xdp;
+	u32 act;
+	int err;
+
+	list_for_each_entry_safe(skb, tmp, listp, list) {
+		act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog);
+		switch (act) {
+		case XDP_PASS:
+			break;
+		case XDP_REDIRECT:
+			skb_list_del_init(skb);
+			err = xdp_do_generic_redirect(skb->dev, skb, &xdp,
+						      rcpu->prog);
+			if (unlikely(err)) {
+				kfree_skb(skb);
+				stats->drop++;
+			} else {
+				stats->redirect++;
+			}
+			return;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+			fallthrough;
+		case XDP_ABORTED:
+			trace_xdp_exception(skb->dev, rcpu->prog, act);
+			fallthrough;
+		case XDP_DROP:
+			skb_list_del_init(skb);
+			kfree_skb(skb);
+			stats->drop++;
+			return;
+		}
+	}
+}
+
 static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				    void **frames, int n,
 				    struct xdp_cpumap_stats *stats)
@@ -176,11 +217,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
-	if (!rcpu->prog)
-		return n;
-
-	rcu_read_lock_bh();
-
 	xdp_set_return_frame_no_direct();
 	xdp.rxq = &rxq;
 
@@ -227,17 +263,37 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 		}
 	}
 
+	xdp_clear_return_frame_no_direct();
+
+	return nframes;
+}
+
+#define CPUMAP_BATCH 8
+
+static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
+				int xdp_n, struct xdp_cpumap_stats *stats,
+				struct list_head *list)
+{
+	int nframes;
+
+	if (!rcpu->prog)
+		return xdp_n;
+
+	rcu_read_lock_bh();
+
+	nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats);
+
 	if (stats->redirect)
-		xdp_do_flush_map();
+		xdp_do_flush();
 
-	xdp_clear_return_frame_no_direct();
+	if (unlikely(!list_empty(list)))
+		cpu_map_bpf_prog_run_skb(rcpu, list, stats);
 
 	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
 
 	return nframes;
 }
 
-#define CPUMAP_BATCH 8
 
 static int cpu_map_kthread_run(void *data)
 {
@@ -254,9 +310,9 @@ static int cpu_map_kthread_run(void *data)
 		struct xdp_cpumap_stats stats = {}; /* zero stats */
 		unsigned int kmem_alloc_drops = 0, sched = 0;
 		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
+		int i, n, m, nframes, xdp_n;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		int i, n, m, nframes;
 		LIST_HEAD(list);
 
 		/* Release CPU reschedule checks */
@@ -280,9 +336,20 @@ static int cpu_map_kthread_run(void *data)
 		 */
 		n = __ptr_ring_consume_batched(rcpu->queue, frames,
 					       CPUMAP_BATCH);
-		for (i = 0; i < n; i++) {
+		for (i = 0, xdp_n = 0; i < n; i++) {
 			void *f = frames[i];
-			struct page *page = virt_to_page(f);
+			struct page *page;
+
+			if (unlikely(__ptr_test_bit(0, &f))) {
+				struct sk_buff *skb = f;
+
+				__ptr_clear_bit(0, &skb);
+				list_add_tail(&skb->list, &list);
+				continue;
+			}
+
+			frames[xdp_n++] = f;
+			page = virt_to_page(f);
 
 			/* Bring struct page memory area to curr CPU. Read by
 			 * build_skb_around via page_is_pfmemalloc(), and when
@@ -292,7 +359,7 @@ static int cpu_map_kthread_run(void *data)
 		}
 
 		/* Support running another XDP prog on this CPU */
-		nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats);
+		nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list);
 		if (nframes) {
 			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
 			if (unlikely(m == 0)) {
@@ -330,12 +397,6 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-bool cpu_map_prog_allowed(struct bpf_map *map)
-{
-	return map->map_type == BPF_MAP_TYPE_CPUMAP &&
-	       map->value_size != offsetofend(struct bpf_cpumap_val, qsize);
-}
-
 static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
 {
 	struct bpf_prog *prog;
@@ -701,6 +762,25 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 	return 0;
 }
 
+int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
+			     struct sk_buff *skb)
+{
+	int ret;
+
+	__skb_pull(skb, skb->mac_len);
+	skb_set_redirected(skb, false);
+	__ptr_set_bit(0, &skb);
+
+	ret = ptr_ring_produce(rcpu->queue, skb);
+	if (ret < 0)
+		goto trace;
+
+	wake_up_process(rcpu->kthread);
+trace:
+	trace_xdp_cpumap_enqueue(rcpu->map_id, !ret, !!ret, rcpu->cpu);
+	return ret;
+}
+
 void __cpu_map_flush(void)
 {
 	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);