Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2020-06-30

The following pull-request contains BPF updates for your *net* tree.

We've added 28 non-merge commits during the last 9 day(s) which contain
a total of 35 files changed, 486 insertions(+), 232 deletions(-).

The main changes are:

1) Fix an incorrect verifier branch elimination for PTR_TO_BTF_ID pointer
   types, from Yonghong Song.

2) Fix UAPI for sockmap and flow_dissector progs that were ignoring various
   arguments passed to BPF_PROG_{ATTACH,DETACH}, from Lorenz Bauer & Jakub Sitnicki.

3) Fix broken AF_XDP DMA hacks that are poking into dma-direct and swiotlb
   internals and integrate it properly into DMA core, from Christoph Hellwig.

4) Fix RCU splat from recent changes to avoid skipping ingress policy when
   kTLS is enabled, from John Fastabend.

5) Fix BPF ringbuf map to enforce size to be the power of 2 in order for its
   position masking to work, from Andrii Nakryiko.

6) Fix regression from CAP_BPF work to re-allow CAP_SYS_ADMIN for loading
   of network programs, from Maciej Żenczykowski.

7) Fix libbpf section name prefix for devmap progs, from Jesper Dangaard Brouer.

8) Fix formatting in UAPI documentation for BPF helpers, from Quentin Monnet.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 97 insertions, 84 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index bfd4ccd80847..b03c469cd01f 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -147,6 +147,20 @@ int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f)
 	return a + (long)b + c + d + (long)e + f;
 }
 
+struct bpf_fentry_test_t {
+	struct bpf_fentry_test_t *a;
+};
+
+int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
+{
+	return (long)arg;
+}
+
+int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg)
+{
+	return (long)arg->a;
+}
+
 int noinline bpf_modify_return_test(int a, int *b)
 {
 	*b += 1;
@@ -185,6 +199,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 			      const union bpf_attr *kattr,
 			      union bpf_attr __user *uattr)
 {
+	struct bpf_fentry_test_t arg = {};
 	u16 side_effect = 0, ret = 0;
 	int b = 2, err = -EFAULT;
 	u32 retval = 0;
@@ -197,7 +212,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 		    bpf_fentry_test3(4, 5, 6) != 15 ||
 		    bpf_fentry_test4((void *)7, 8, 9, 10) != 34 ||
 		    bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 ||
-		    bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111)
+		    bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 ||
+		    bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 ||
+		    bpf_fentry_test8(&arg) != 0)
 			goto out;
 		break;
 	case BPF_MODIFY_RETURN:
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d02df0b6d0d9..142a8824f0a8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -70,10 +70,10 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 EXPORT_SYMBOL(skb_flow_dissector_init);
 
 #ifdef CONFIG_BPF_SYSCALL
-int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
+int flow_dissector_bpf_prog_attach_check(struct net *net,
+					 struct bpf_prog *prog)
 {
 	enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
-	struct bpf_prog *attached;
 
 	if (net == &init_net) {
 		/* BPF flow dissector in the root namespace overrides
@@ -86,26 +86,17 @@ int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
 		for_each_net(ns) {
 			if (ns == &init_net)
 				continue;
-			if (rcu_access_pointer(ns->bpf.progs[type]))
+			if (rcu_access_pointer(ns->bpf.run_array[type]))
 				return -EEXIST;
 		}
 	} else {
 		/* Make sure root flow dissector is not attached
 		 * when attaching to the non-root namespace.
 		 */
-		if (rcu_access_pointer(init_net.bpf.progs[type]))
+		if (rcu_access_pointer(init_net.bpf.run_array[type]))
 			return -EEXIST;
 	}
 
-	attached = rcu_dereference_protected(net->bpf.progs[type],
-					     lockdep_is_held(&netns_bpf_mutex));
-	if (attached == prog)
-		/* The same program cannot be attached twice */
-		return -EINVAL;
-
-	rcu_assign_pointer(net->bpf.progs[type], prog);
-	if (attached)
-		bpf_prog_put(attached);
 	return 0;
 }
 #endif /* CONFIG_BPF_SYSCALL */
@@ -903,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net,
 	struct flow_dissector_key_addrs *key_addrs;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
-	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
 	bool mpls_el = false;
@@ -960,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net,
 	WARN_ON_ONCE(!net);
 	if (net) {
 		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+		struct bpf_prog_array *run_array;
 
 		rcu_read_lock();
-		attached = rcu_dereference(init_net.bpf.progs[type]);
-
-		if (!attached)
-			attached = rcu_dereference(net->bpf.progs[type]);
+		run_array = rcu_dereference(init_net.bpf.run_array[type]);
+		if (!run_array)
+			run_array = rcu_dereference(net->bpf.run_array[type]);
 
-		if (attached) {
+		if (run_array) {
 			struct bpf_flow_keys flow_keys;
 			struct bpf_flow_dissector ctx = {
 				.flow_keys = &flow_keys,
@@ -975,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net,
 				.data_end = data + hlen,
 			};
 			__be16 n_proto = proto;
+			struct bpf_prog *prog;
 
 			if (skb) {
 				ctx.skb = skb;
@@ -985,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net,
 				n_proto = skb->protocol;
 			}
 
-			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
+			prog = READ_ONCE(run_array->items[0].prog);
+			ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
 					       hlen, flags);
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 351afbf6bfba..6a32a1fd34f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -683,7 +683,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
 	return container_of(parser, struct sk_psock, parser);
 }
 
-static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
+static void sk_psock_skb_redirect(struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
@@ -715,12 +715,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
 	}
 }
 
-static void sk_psock_tls_verdict_apply(struct sk_psock *psock,
-				       struct sk_buff *skb, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict)
 {
 	switch (verdict) {
 	case __SK_REDIRECT:
-		sk_psock_skb_redirect(psock, skb);
+		sk_psock_skb_redirect(skb);
 		break;
 	case __SK_PASS:
 	case __SK_DROP:
@@ -741,8 +740,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
 	}
+	sk_psock_tls_verdict_apply(skb, ret);
 	rcu_read_unlock();
-	sk_psock_tls_verdict_apply(psock, skb, ret);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
@@ -770,7 +769,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 		}
 		goto out_free;
 	case __SK_REDIRECT:
-		sk_psock_skb_redirect(psock, skb);
+		sk_psock_skb_redirect(skb);
 		break;
 	case __SK_DROP:
 		/* fall-through */
@@ -782,11 +781,18 @@ out_free:
 
 static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 {
-	struct sk_psock *psock = sk_psock_from_strp(strp);
+	struct sk_psock *psock;
 	struct bpf_prog *prog;
 	int ret = __SK_DROP;
+	struct sock *sk;
 
 	rcu_read_lock();
+	sk = strp->sk;
+	psock = sk_psock(sk);
+	if (unlikely(!psock)) {
+		kfree_skb(skb);
+		goto out;
+	}
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
 		skb_orphan(skb);
@@ -794,8 +800,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
 	}
-	rcu_read_unlock();
 	sk_psock_verdict_apply(psock, skb, ret);
+out:
+	rcu_read_unlock();
 }
 
 static int sk_psock_strp_read_done(struct strparser *strp, int err)
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4059f94e9bb5..0971f17e8e54 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -70,11 +70,49 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
 	struct fd f;
 	int ret;
 
+	if (attr->attach_flags || attr->replace_bpf_fd)
+		return -EINVAL;
+
 	f = fdget(ufd);
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	ret = sock_map_prog_update(map, prog, attr->attach_type);
+	ret = sock_map_prog_update(map, prog, NULL, attr->attach_type);
+	fdput(f);
+	return ret;
+}
+
+int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+	u32 ufd = attr->target_fd;
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	struct fd f;
+	int ret;
+
+	if (attr->attach_flags || attr->replace_bpf_fd)
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	prog = bpf_prog_get(attr->attach_bpf_fd);
+	if (IS_ERR(prog)) {
+		ret = PTR_ERR(prog);
+		goto put_map;
+	}
+
+	if (prog->type != ptype) {
+		ret = -EINVAL;
+		goto put_prog;
+	}
+
+	ret = sock_map_prog_update(map, NULL, prog, attr->attach_type);
+put_prog:
+	bpf_prog_put(prog);
+put_map:
 	fdput(f);
 	return ret;
 }
@@ -1203,27 +1241,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
 }
 
 int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-			 u32 which)
+			 struct bpf_prog *old, u32 which)
 {
 	struct sk_psock_progs *progs = sock_map_progs(map);
+	struct bpf_prog **pprog;
 
 	if (!progs)
 		return -EOPNOTSUPP;
 
 	switch (which) {
 	case BPF_SK_MSG_VERDICT:
-		psock_set_prog(&progs->msg_parser, prog);
+		pprog = &progs->msg_parser;
 		break;
 	case BPF_SK_SKB_STREAM_PARSER:
-		psock_set_prog(&progs->skb_parser, prog);
+		pprog = &progs->skb_parser;
 		break;
 	case BPF_SK_SKB_STREAM_VERDICT:
-		psock_set_prog(&progs->skb_verdict, prog);
+		pprog = &progs->skb_verdict;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
+	if (old)
+		return psock_replace_prog(pprog, prog, old);
+
+	psock_set_prog(pprog, prog);
 	return 0;
 }
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 540ed75e4482..08b80669f649 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -2,9 +2,6 @@
 
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/swiotlb.h>
 
 #include "xsk_queue.h"
 
@@ -55,7 +52,6 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
 	pool->free_heads_cnt = chunks;
 	pool->headroom = headroom;
 	pool->chunk_size = chunk_size;
-	pool->cheap_dma = true;
 	pool->unaligned = unaligned;
 	pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM;
 	INIT_LIST_HEAD(&pool->free_list);
@@ -125,48 +121,6 @@ static void xp_check_dma_contiguity(struct xsk_buff_pool *pool)
 	}
 }
 
-static bool __maybe_unused xp_check_swiotlb_dma(struct xsk_buff_pool *pool)
-{
-#if defined(CONFIG_SWIOTLB)
-	phys_addr_t paddr;
-	u32 i;
-
-	for (i = 0; i < pool->dma_pages_cnt; i++) {
-		paddr = dma_to_phys(pool->dev, pool->dma_pages[i]);
-		if (is_swiotlb_buffer(paddr))
-			return false;
-	}
-#endif
-	return true;
-}
-
-static bool xp_check_cheap_dma(struct xsk_buff_pool *pool)
-{
-#if defined(CONFIG_HAS_DMA)
-	const struct dma_map_ops *ops = get_dma_ops(pool->dev);
-
-	if (ops) {
-		return !ops->sync_single_for_cpu &&
-			!ops->sync_single_for_device;
-	}
-
-	if (!dma_is_direct(ops))
-		return false;
-
-	if (!xp_check_swiotlb_dma(pool))
-		return false;
-
-	if (!dev_is_dma_coherent(pool->dev)) {
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) ||		\
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) ||	\
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE)
-		return false;
-#endif
-	}
-#endif
-	return true;
-}
-
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages)
 {
@@ -180,6 +134,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 
 	pool->dev = dev;
 	pool->dma_pages_cnt = nr_pages;
+	pool->dma_need_sync = false;
 
 	for (i = 0; i < pool->dma_pages_cnt; i++) {
 		dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE,
@@ -188,14 +143,13 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 			xp_dma_unmap(pool, attrs);
 			return -ENOMEM;
 		}
+		if (dma_need_sync(dev, dma))
+			pool->dma_need_sync = true;
 		pool->dma_pages[i] = dma;
 	}
 
 	if (pool->unaligned)
 		xp_check_dma_contiguity(pool);
-
-	pool->dev = dev;
-	pool->cheap_dma = xp_check_cheap_dma(pool);
 	return 0;
 }
 EXPORT_SYMBOL(xp_dma_map);
@@ -280,7 +234,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
 	xskb->xdp.data_meta = xskb->xdp.data;
 
-	if (!pool->cheap_dma) {
+	if (pool->dma_need_sync) {
 		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
 						 pool->frame_len,
 						 DMA_BIDIRECTIONAL);