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

Minor conflict, a CHECK was placed into an if() statement
in net-next, whilst a newline was added to that CHECK
call in 'net'.  Thanks to Daniel for the merge resolution.

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

2 files changed, 169 insertions, 12 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index da77a9388947..93d5a4eeec2a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
 	BPF_MAP_TYPE_CPUMAP,
+	BPF_MAP_TYPE_XSKMAP,
 };
 
 enum bpf_prog_type {
@@ -828,12 +829,12 @@ union bpf_attr {
  *
  * 		Also, be aware that the newer helper
  * 		**bpf_perf_event_read_value**\ () is recommended over
- * 		**bpf_perf_event_read*\ () in general. The latter has some ABI
+ * 		**bpf_perf_event_read**\ () in general. The latter has some ABI
  * 		quirks where error and counter value are used as a return code
  * 		(which is wrong to do since ranges may overlap). This issue is
- * 		fixed with bpf_perf_event_read_value(), which at the same time
- * 		provides more features over the **bpf_perf_event_read**\ ()
- * 		interface. Please refer to the description of
+ * 		fixed with **bpf_perf_event_read_value**\ (), which at the same
+ * 		time provides more features over the **bpf_perf_event_read**\
+ * 		() interface. Please refer to the description of
  * 		**bpf_perf_event_read_value**\ () for details.
  * 	Return
  * 		The value of the perf event counter read from the map, or a
@@ -1361,7 +1362,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops_kern *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
  * 	Description
  * 		Emulate a call to **setsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1435,7 +1436,7 @@ union bpf_attr {
  * 	Return
  * 		**SK_PASS** on success, or **SK_DROP** on error.
  *
- * int bpf_sock_map_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  * 	Description
  * 		Add an entry to, or update a *map* referencing sockets. The
  * 		*skops* is used as a new value for the entry associated to
@@ -1533,7 +1534,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_perf_prog_read_value(struct bpf_perf_event_data_kern *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
  * 	Description
  * 		For en eBPF program attached to a perf event, retrieve the
  * 		value of the event counter associated to *ctx* and store it in
@@ -1544,7 +1545,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops_kern *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
  * 	Description
  * 		Emulate a call to **getsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1588,7 +1589,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops_kern *bpf_sock, int argval)
+ * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
  * 	Description
  * 		Attempt to set the value of the **bpf_sock_ops_cb_flags** field
  * 		for the full TCP socket associated to *bpf_sock_ops* to
@@ -1721,7 +1722,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_bind(struct bpf_sock_addr_kern *ctx, struct sockaddr *addr, int addr_len)
+ * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
  * 	Description
  * 		Bind the socket associated to *ctx* to the address pointed by
  * 		*addr*, of length *addr_len*. This allows for making outgoing
@@ -1767,6 +1768,64 @@ union bpf_attr {
  * 		**CONFIG_XFRM** configuration option.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * 	Description
+ * 		Return a user or a kernel stack in bpf program provided buffer.
+ * 		To achieve this, the helper needs *ctx*, which is a pointer
+ * 		to the context on which the tracing program is executed.
+ * 		To store the stacktrace, the bpf program provides *buf* with
+ * 		a nonnegative *size*.
+ *
+ * 		The last argument, *flags*, holds the number of stack frames to
+ * 		skip (from 0 to 255), masked with
+ * 		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * 		the following flags:
+ *
+ * 		**BPF_F_USER_STACK**
+ * 			Collect a user space stack instead of a kernel stack.
+ * 		**BPF_F_USER_BUILD_ID**
+ * 			Collect buildid+offset instead of ips for user stack,
+ * 			only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ * 		**bpf_get_stack**\ () can collect up to
+ * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * 		to sufficient large buffer size. Note that
+ * 		this limit can be controlled with the **sysctl** program, and
+ * 		that it should be manually increased in order to profile long
+ * 		user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * 		::
+ *
+ * 			# sysctl kernel.perf_event_max_stack=<new value>
+ *
+ * 	Return
+ * 		a non-negative value equal to or less than size on success, or
+ * 		a negative error in case of failure.
+ *
+ * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * 	Description
+ * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * 		it provides an easy way to load *len* bytes from *offset*
+ * 		from the packet associated to *skb*, into the buffer pointed
+ * 		by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * 		a fifth argument *start_header* exists in order to select a
+ * 		base offset to start from. *start_header* can be one of:
+ *
+ * 		**BPF_HDR_START_MAC**
+ * 			Base offset to load data from is *skb*'s mac header.
+ * 		**BPF_HDR_START_NET**
+ * 			Base offset to load data from is *skb*'s network header.
+ *
+ * 		In general, "direct packet access" is the preferred method to
+ * 		access packet data, however, this helper is in particular useful
+ * 		in socket filters where *skb*\ **->data** does not always point
+ * 		to the start of the mac header and where "direct packet access"
+ * 		is not available.
+ *
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1835,7 +1894,9 @@ union bpf_attr {
 	FN(msg_pull_data),		\
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
-	FN(skb_get_xfrm_state),
+	FN(skb_get_xfrm_state),		\
+	FN(get_stack),			\
+	FN(skb_load_bytes_relative),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1869,11 +1930,14 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
 #define BPF_F_TUNINFO_IPV6		(1ULL << 0)
 
-/* BPF_FUNC_get_stackid flags. */
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
 #define BPF_F_SKIP_FIELD_MASK		0xffULL
 #define BPF_F_USER_STACK		(1ULL << 8)
+/* flags used by BPF_FUNC_get_stackid only. */
 #define BPF_F_FAST_STACK_CMP		(1ULL << 9)
 #define BPF_F_REUSE_STACKID		(1ULL << 10)
+/* flags used by BPF_FUNC_get_stack only. */
+#define BPF_F_USER_BUILD_ID		(1ULL << 11)
 
 /* BPF_FUNC_skb_set_tunnel_key flags. */
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
@@ -1893,6 +1957,12 @@ enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
 };
 
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+	BPF_HDR_START_MAC,
+	BPF_HDR_START_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
new file mode 100644
index 000000000000..77b88c4efe98
--- /dev/null
+++ b/include/uapi/linux/if_xdp.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+ *
+ * if_xdp: XDP socket user-space interface
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ *	      Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef _LINUX_IF_XDP_H
+#define _LINUX_IF_XDP_H
+
+#include <linux/types.h>
+
+/* Options for the sxdp_flags field */
+#define XDP_SHARED_UMEM 1
+
+struct sockaddr_xdp {
+	__u16 sxdp_family;
+	__u32 sxdp_ifindex;
+	__u32 sxdp_queue_id;
+	__u32 sxdp_shared_umem_fd;
+	__u16 sxdp_flags;
+};
+
+/* XDP socket options */
+#define XDP_RX_RING			1
+#define XDP_TX_RING			2
+#define XDP_UMEM_REG			3
+#define XDP_UMEM_FILL_RING		4
+#define XDP_UMEM_COMPLETION_RING	5
+#define XDP_STATISTICS			6
+
+struct xdp_umem_reg {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 frame_size; /* Frame size */
+	__u32 frame_headroom; /* Frame head room */
+};
+
+struct xdp_statistics {
+	__u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+	__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
+	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+};
+
+/* Pgoff for mmaping the rings */
+#define XDP_PGOFF_RX_RING			  0
+#define XDP_PGOFF_TX_RING		 0x80000000
+#define XDP_UMEM_PGOFF_FILL_RING	0x100000000
+#define XDP_UMEM_PGOFF_COMPLETION_RING	0x180000000
+
+struct xdp_desc {
+	__u32 idx;
+	__u32 len;
+	__u16 offset;
+	__u8 flags;
+	__u8 padding[5];
+};
+
+struct xdp_ring {
+	__u32 producer __attribute__((aligned(64)));
+	__u32 consumer __attribute__((aligned(64)));
+};
+
+/* Used for the RX and TX queues for packets */
+struct xdp_rxtx_ring {
+	struct xdp_ring ptrs;
+	struct xdp_desc desc[0] __attribute__((aligned(64)));
+};
+
+/* Used for the fill and completion queues for buffers */
+struct xdp_umem_ring {
+	struct xdp_ring ptrs;
+	__u32 desc[0] __attribute__((aligned(64)));
+};
+
+#endif /* _LINUX_IF_XDP_H */