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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-02-28

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

We've added 41 non-merge commits during the last 7 day(s) which contain
a total of 49 files changed, 1383 insertions(+), 499 deletions(-).

The main changes are:

1) BPF and Real-Time nicely co-exist.

2) bpftool feature improvements.

3) retrieve bpf_sk_storage via INET_DIAG.
====================

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

drivers/net/virtio_net.c

@@ -371,7 +371,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
 				   unsigned int len, unsigned int truesize,
-				   bool hdr_valid)
+				   bool hdr_valid, unsigned int metasize)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -393,6 +393,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
+	/* hdr_valid means no XDP, so we can copy the vnet header */
 	if (hdr_valid)
 		memcpy(hdr, p, hdr_len);
 
@@ -405,6 +406,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 		copy = skb_tailroom(skb);
 	skb_put_data(skb, p, copy);
 
+	if (metasize) {
+		__skb_pull(skb, metasize);
+		skb_metadata_set(skb, metasize);
+	}
+
 	len -= copy;
 	offset += copy;
 
@@ -450,10 +456,6 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	int err;
 
-	/* virtqueue want to use data area in-front of packet */
-	if (unlikely(xdpf->metasize > 0))
-		return -EOPNOTSUPP;
-
 	if (unlikely(xdpf->headroom < vi->hdr_len))
 		return -EOVERFLOW;
 
@@ -644,6 +646,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	unsigned int delta = 0;
 	struct page *xdp_page;
 	int err;
+	unsigned int metasize = 0;
 
 	len -= vi->hdr_len;
 	stats->bytes += len;
@@ -683,8 +686,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 		xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
 		xdp.data = xdp.data_hard_start + xdp_headroom;
-		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
+		xdp.data_meta = xdp.data;
 		xdp.rxq = &rq->xdp_rxq;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -695,6 +698,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			/* Recalculate length in case bpf program changed it */
 			delta = orig_data - xdp.data;
 			len = xdp.data_end - xdp.data;
+			metasize = xdp.data - xdp.data_meta;
 			break;
 		case XDP_TX:
 			stats->xdp_tx++;
@@ -735,10 +739,13 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	}
 	skb_reserve(skb, headroom - delta);
 	skb_put(skb, len);
-	if (!delta) {
+	if (!xdp_prog) {
 		buf += header_offset;
 		memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
-	} /* keep zeroed vnet hdr since packet was changed by bpf */
+	} /* keep zeroed vnet hdr since XDP is loaded */
+
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 err:
 	return skb;
@@ -760,8 +767,8 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct virtnet_rq_stats *stats)
 {
 	struct page *page = buf;
-	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len,
-					  PAGE_SIZE, true);
+	struct sk_buff *skb =
+		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, true, 0);
 
 	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
@@ -793,6 +800,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	unsigned int truesize;
 	unsigned int headroom = mergeable_ctx_to_headroom(ctx);
 	int err;
+	unsigned int metasize = 0;
 
 	head_skb = NULL;
 	stats->bytes += len - vi->hdr_len;
@@ -839,33 +847,36 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		data = page_address(xdp_page) + offset;
 		xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
 		xdp.data = data + vi->hdr_len;
-		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + (len - vi->hdr_len);
+		xdp.data_meta = xdp.data;
 		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		stats->xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
+			metasize = xdp.data - xdp.data_meta;
+
 			/* recalculate offset to account for any header
-			 * adjustments. Note other cases do not build an
-			 * skb and avoid using offset
+			 * adjustments and minus the metasize to copy the
+			 * metadata in page_to_skb(). Note other cases do not
+			 * build an skb and avoid using offset
 			 */
-			offset = xdp.data -
-					page_address(xdp_page) - vi->hdr_len;
+			offset = xdp.data - page_address(xdp_page) -
+				 vi->hdr_len - metasize;
 
-			/* recalculate len if xdp.data or xdp.data_end were
-			 * adjusted
+			/* recalculate len if xdp.data, xdp.data_end or
+			 * xdp.data_meta were adjusted
 			 */
-			len = xdp.data_end - xdp.data + vi->hdr_len;
+			len = xdp.data_end - xdp.data + vi->hdr_len + metasize;
 			/* We can only create skb based on xdp_page. */
 			if (unlikely(xdp_page != page)) {
 				rcu_read_unlock();
 				put_page(page);
-				head_skb = page_to_skb(vi, rq, xdp_page,
-						       offset, len,
-						       PAGE_SIZE, false);
+				head_skb = page_to_skb(vi, rq, xdp_page, offset,
+						       len, PAGE_SIZE, false,
+						       metasize);
 				return head_skb;
 			}
 			break;
@@ -921,7 +932,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		goto err_skb;
 	}
 
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
+			       metasize);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))

include/linux/bpf-cgroup.h

@@ -36,7 +36,7 @@ struct bpf_cgroup_storage_map;
 
 struct bpf_storage_buffer {
 	struct rcu_head rcu;
-	char data[0];
+	char data[];
 };
 
 struct bpf_cgroup_storage {

include/linux/bpf.h

@@ -859,7 +859,7 @@ struct bpf_prog_array_item {
 
 struct bpf_prog_array {
 	struct rcu_head rcu;
-	struct bpf_prog_array_item items[0];
+	struct bpf_prog_array_item items[];
 };
 
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
@@ -885,7 +885,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		struct bpf_prog *_prog;			\
 		struct bpf_prog_array *_array;		\
 		u32 _ret = 1;				\
-		preempt_disable();			\
+		migrate_disable();			\
 		rcu_read_lock();			\
 		_array = rcu_dereference(array);	\
 		if (unlikely(check_non_null && !_array))\
@@ -898,7 +898,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		}					\
 _out:							\
 		rcu_read_unlock();			\
-		preempt_enable();			\
+		migrate_enable();			\
 		_ret;					\
 	 })
 
@@ -932,7 +932,7 @@ _out:							\
 		u32 ret;				\
 		u32 _ret = 1;				\
 		u32 _cn = 0;				\
-		preempt_disable();			\
+		migrate_disable();			\
 		rcu_read_lock();			\
 		_array = rcu_dereference(array);	\
 		_item = &_array->items[0];		\
@@ -944,7 +944,7 @@ _out:							\
 			_item++;			\
 		}					\
 		rcu_read_unlock();			\
-		preempt_enable();			\
+		migrate_enable();			\
 		if (_ret)				\
 			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
 		else					\
@@ -961,6 +961,36 @@ _out:							\
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 
+/*
+ * Block execution of BPF programs attached to instrumentation (perf,
+ * kprobes, tracepoints) to prevent deadlocks on map operations as any of
+ * these events can happen inside a region which holds a map bucket lock
+ * and can deadlock on it.
+ *
+ * Use the preemption safe inc/dec variants on RT because migrate disable
+ * is preemptible on RT and preemption in the middle of the RMW operation
+ * might lead to inconsistent state. Use the raw variants for non RT
+ * kernels as migrate_disable() maps to preempt_disable() so the slightly
+ * more expensive save operation can be avoided.
+ */
+static inline void bpf_disable_instrumentation(void)
+{
+	migrate_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		this_cpu_inc(bpf_prog_active);
+	else
+		__this_cpu_inc(bpf_prog_active);
+}
+
+static inline void bpf_enable_instrumentation(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		this_cpu_dec(bpf_prog_active);
+	else
+		__this_cpu_dec(bpf_prog_active);
+	migrate_enable();
+}
+
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 
@@ -993,6 +1023,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 
+struct bpf_map *bpf_map_get(u32 ufd);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
 void bpf_map_inc(struct bpf_map *map);

include/linux/filter.h

@@ -561,7 +561,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 
 #define __BPF_PROG_RUN(prog, ctx, dfunc)	({			\
 	u32 ret;							\
-	cant_sleep();							\
+	cant_migrate();							\
 	if (static_branch_unlikely(&bpf_stats_enabled_key)) {		\
 		struct bpf_prog_stats *stats;				\
 		u64 start = sched_clock();				\
@@ -576,8 +576,30 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 	}								\
 	ret; })
 
-#define BPF_PROG_RUN(prog, ctx) __BPF_PROG_RUN(prog, ctx,		\
-					       bpf_dispatcher_nopfunc)
+#define BPF_PROG_RUN(prog, ctx)						\
+	__BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nopfunc)
+
+/*
+ * Use in preemptible and therefore migratable context to make sure that
+ * the execution of the BPF program runs on one CPU.
+ *
+ * This uses migrate_disable/enable() explicitly to document that the
+ * invocation of a BPF program does not require reentrancy protection
+ * against a BPF program which is invoked from a preempting task.
+ *
+ * For non RT enabled kernels migrate_disable/enable() maps to
+ * preempt_disable/enable(), i.e. it disables also preemption.
+ */
+static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
+					  const void *ctx)
+{
+	u32 ret;
+
+	migrate_disable();
+	ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nopfunc);
+	migrate_enable();
+	return ret;
+}
 
 #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
 
@@ -655,6 +677,7 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 	return qdisc_skb_cb(skb)->data;
 }
 
+/* Must be invoked with migration disabled */
 static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
 					 struct sk_buff *skb)
 {
@@ -680,9 +703,9 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
 {
 	u32 res;
 
-	preempt_disable();
+	migrate_disable();
 	res = __bpf_prog_run_save_cb(prog, skb);
-	preempt_enable();
+	migrate_enable();
 	return res;
 }
 
@@ -695,9 +718,7 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
 	if (unlikely(prog->cb_access))
 		memset(cb_data, 0, BPF_SKB_CB_LEN);
 
-	preempt_disable();
-	res = BPF_PROG_RUN(prog, skb);
-	preempt_enable();
+	res = bpf_prog_run_pin_on_cpu(prog, skb);
 	return res;
 }
 

include/linux/inet_diag.h

@@ -15,11 +15,9 @@ struct netlink_callback;
 struct inet_diag_handler {
 	void		(*dump)(struct sk_buff *skb,
 				struct netlink_callback *cb,
-				const struct inet_diag_req_v2 *r,
-				struct nlattr *bc);
+				const struct inet_diag_req_v2 *r);
 
-	int		(*dump_one)(struct sk_buff *in_skb,
-				    const struct nlmsghdr *nlh,
+	int		(*dump_one)(struct netlink_callback *cb,
 				    const struct inet_diag_req_v2 *req);
 
 	void		(*idiag_get_info)(struct sock *sk,
@@ -40,18 +38,25 @@ struct inet_diag_handler {
 	__u16		idiag_info_size;
 };
 
+struct bpf_sk_storage_diag;
+struct inet_diag_dump_data {
+	struct nlattr *req_nlas[__INET_DIAG_REQ_MAX];
+#define inet_diag_nla_bc req_nlas[INET_DIAG_REQ_BYTECODE]
+#define inet_diag_nla_bpf_stgs req_nlas[INET_DIAG_REQ_SK_BPF_STORAGES]
+
+	struct bpf_sk_storage_diag *bpf_stg_diag;
+};
+
 struct inet_connection_sock;
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
-		      struct sk_buff *skb, const struct inet_diag_req_v2 *req,
-		      struct user_namespace *user_ns,
-		      u32 pid, u32 seq, u16 nlmsg_flags,
-		      const struct nlmsghdr *unlh, bool net_admin);
+		      struct sk_buff *skb, struct netlink_callback *cb,
+		      const struct inet_diag_req_v2 *req,
+		      u16 nlmsg_flags, bool net_admin);
 void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb,
 			 struct netlink_callback *cb,
-			 const struct inet_diag_req_v2 *r,
-			 struct nlattr *bc);
+			 const struct inet_diag_req_v2 *r);
 int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
-			    struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+			    struct netlink_callback *cb,
 			    const struct inet_diag_req_v2 *req);
 
 struct sock *inet_diag_find_one_icsk(struct net *net,

include/linux/kernel.h

@@ -257,6 +257,13 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
 
+#ifndef CONFIG_PREEMPT_RT
+# define cant_migrate()		cant_sleep()
+#else
+  /* Placeholder for now */
+# define cant_migrate()		do { } while (0)
+#endif
+
 /**
  * abs - return absolute value of an argument
  * @x: the value.  If it is unsigned type, it is converted to signed type first.