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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-05-15

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

We've added 37 non-merge commits during the last 1 day(s) which contain
a total of 67 files changed, 741 insertions(+), 252 deletions(-).

The main changes are:

1) bpf_xdp_adjust_tail() now allows to grow the tail as well, from Jesper.

2) bpftool can probe CONFIG_HZ, from Daniel.

3) CAP_BPF is introduced to isolate user processes that use BPF infra and
   to secure BPF networking services by dropping CAP_SYS_ADMIN requirement
   in certain cases, from Alexei.
====================

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

2 files changed, 37 insertions, 1 deletions

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 3cc6d5d84aa4..3094fccf5a88 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -6,6 +6,8 @@
 #ifndef __LINUX_NET_XDP_H__
 #define __LINUX_NET_XDP_H__
 
+#include <linux/skbuff.h> /* skb_shared_info */
+
 /**
  * DOC: XDP RX-queue information
  *
@@ -70,13 +72,25 @@ struct xdp_buff {
 	void *data_hard_start;
 	unsigned long handle;
 	struct xdp_rxq_info *rxq;
+	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 };
 
+/* Reserve memory area at end-of data area.
+ *
+ * This macro reserves tailroom in the XDP buffer by limiting the
+ * XDP/BPF data access to data_hard_end.  Notice same area (and size)
+ * is used for XDP_PASS, when constructing the SKB via build_skb().
+ */
+#define xdp_data_hard_end(xdp)				\
+	((xdp)->data_hard_start + (xdp)->frame_sz -	\
+	 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
 struct xdp_frame {
 	void *data;
 	u16 len;
 	u16 headroom;
-	u16 metasize;
+	u32 metasize:8;
+	u32 frame_sz:24;
 	/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
 	 * while mem info is valid on remote CPU.
 	 */
@@ -91,6 +105,10 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame)
 	frame->dev_rx = NULL;
 }
 
+/* Avoids inlining WARN macro in fast-path */
+void xdp_warn(const char *msg, const char *func, const int line);
+#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
+
 struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
 
 /* Convert xdp_buff to xdp_frame */
@@ -111,6 +129,12 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
 	if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
 		return NULL;
 
+	/* Catch if driver didn't reserve tailroom for skb_shared_info */
+	if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
+		XDP_WARN("Driver BUG: missing reserved tailroom");
+		return NULL;
+	}
+
 	/* Store info in top of packet */
 	xdp_frame = xdp->data_hard_start;
 
@@ -118,6 +142,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
 	xdp_frame->len  = xdp->data_end - xdp->data;
 	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
 	xdp_frame->metasize = metasize;
+	xdp_frame->frame_sz = xdp->frame_sz;
 
 	/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
 	xdp_frame->mem = xdp->rxq->mem;
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 67191ccaab85..abd72de25fa4 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -236,6 +236,12 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
 	else
 		return address + offset;
 }
+
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return umem->chunk_size_nohr + umem->headroom;
+}
+
 #else
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
@@ -366,6 +372,11 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
 	return 0;
 }
 
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return 0;
+}
+
 static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
 	return -EOPNOTSUPP;