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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-11-02

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

We've added 30 non-merge commits during the last 7 day(s) which contain
a total of 41 files changed, 1864 insertions(+), 474 deletions(-).

The main changes are:

1) Fix long standing user vs kernel access issue by introducing
   bpf_probe_read_user() and bpf_probe_read_kernel() helpers, from Daniel.

2) Accelerated xskmap lookup, from Björn and Maciej.

3) Support for automatic map pinning in libbpf, from Toke.

4) Cleanup of BTF-enabled raw tracepoints, from Alexei.

5) Various fixes to libbpf and selftests.
====================

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

5 files changed, 145 insertions, 77 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 171be30fe0ae..7c7f518811a6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -373,6 +373,11 @@ enum bpf_cgroup_storage_type {
 
 #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
 
+/* The longest tracepoint has 12 args.
+ * See include/trace/bpf_probe.h
+ */
+#define MAX_BPF_FUNC_ARGS 12
+
 struct bpf_prog_stats {
 	u64 cnt;
 	u64 nsecs;
@@ -1004,31 +1009,6 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr,
 }
 #endif
 
-#if defined(CONFIG_XDP_SOCKETS)
-struct xdp_sock;
-struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
-int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
-		       struct xdp_sock *xs);
-void __xsk_map_flush(struct bpf_map *map);
-#else
-struct xdp_sock;
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
-						     u32 key)
-{
-	return NULL;
-}
-
-static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
-				     struct xdp_sock *xs)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void __xsk_map_flush(struct bpf_map *map)
-{
-}
-#endif
-
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
 void bpf_sk_reuseport_detach(struct sock *sk);
 int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 36a9c2325176..de14872b01ba 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -26,6 +26,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
 BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d4ee6e942562..67f016010aad 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -311,6 +311,7 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
  * happens, handle that and return -EFAULT.
  */
 extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long probe_kernel_read_strict(void *dst, const void *src, size_t size);
 extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
@@ -337,7 +338,22 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size);
 extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
 extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
+/*
+ * probe_user_write(): safely attempt to write to a location in user space
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
+
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+				       long count);
+extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
 				     long count);
 extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index c9398ce7960f..e3780e4b74e1 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -69,7 +69,14 @@ struct xdp_umem {
 /* Nodes are linked in the struct xdp_sock map_list field, and used to
  * track which maps a certain socket reside in.
  */
-struct xsk_map;
+
+struct xsk_map {
+	struct bpf_map map;
+	struct list_head __percpu *flush_list;
+	spinlock_t lock; /* Synchronize map updates */
+	struct xdp_sock *xsk_map[];
+};
+
 struct xsk_map_node {
 	struct list_head node;
 	struct xsk_map *map;
@@ -109,8 +116,6 @@ struct xdp_sock {
 struct xdp_buff;
 #ifdef CONFIG_XDP_SOCKETS
 int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-void xsk_flush(struct xdp_sock *xs);
 bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
 /* Used from netdev driver */
 bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
@@ -134,6 +139,22 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 			     struct xdp_sock **map_entry);
 int xsk_map_inc(struct xsk_map *map);
 void xsk_map_put(struct xsk_map *map);
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+		       struct xdp_sock *xs);
+void __xsk_map_flush(struct bpf_map *map);
+
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+						     u32 key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *xs;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	xs = READ_ONCE(m->xsk_map[key]);
+	return xs;
+}
 
 static inline u64 xsk_umem_extract_addr(u64 addr)
 {
@@ -224,15 +245,6 @@ static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	return -ENOTSUPP;
 }
 
-static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
-{
-	return -ENOTSUPP;
-}
-
-static inline void xsk_flush(struct xdp_sock *xs)
-{
-}
-
 static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 {
 	return false;
@@ -357,6 +369,21 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
 	return 0;
 }
 
+static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+				     struct xdp_sock *xs)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void __xsk_map_flush(struct bpf_map *map)
+{
+}
+
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+						     u32 key)
+{
+	return NULL;
+}
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4af8b0819a32..df6809a76404 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -173,6 +173,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
 	BPF_PROG_TYPE_CGROUP_SOCKOPT,
+	BPF_PROG_TYPE_TRACING,
 };
 
 enum bpf_attach_type {
@@ -199,6 +200,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_UDP6_RECVMSG,
 	BPF_CGROUP_GETSOCKOPT,
 	BPF_CGROUP_SETSOCKOPT,
+	BPF_TRACE_RAW_TP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -561,10 +563,13 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
- * 		address *src* and store the data in *dst*.
+ * 		kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * 		Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
+ * 		instead.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
@@ -1426,45 +1431,14 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
  * 	Description
- * 		Copy a NUL terminated string from an unsafe address
- * 		*unsafe_ptr* to *dst*. The *size* should include the
- * 		terminating NUL byte. In case the string length is smaller than
- * 		*size*, the target is not padded with further NUL bytes. If the
- * 		string length is larger than *size*, just *size*-1 bytes are
- * 		copied and the last byte is set to NUL.
- *
- * 		On success, the length of the copied string is returned. This
- * 		makes this helper useful in tracing programs for reading
- * 		strings, and more importantly to get its length at runtime. See
- * 		the following snippet:
- *
- * 		::
- *
- * 			SEC("kprobe/sys_open")
- * 			void bpf_sys_open(struct pt_regs *ctx)
- * 			{
- * 			        char buf[PATHLEN]; // PATHLEN is defined to 256
- * 			        int res = bpf_probe_read_str(buf, sizeof(buf),
- * 				                             ctx->di);
- *
- * 				// Consume buf, for example push it to
- * 				// userspace via bpf_perf_event_output(); we
- * 				// can use res (the string length) as event
- * 				// size, after checking its boundaries.
- * 			}
- *
- * 		In comparison, using **bpf_probe_read()** helper here instead
- * 		to read the string would require to estimate the length at
- * 		compile time, and would often result in copying more memory
- * 		than necessary.
+ * 		Copy a NUL terminated string from an unsafe kernel address
+ * 		*unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * 		more details.
  *
- * 		Another useful use case is when parsing individual process
- * 		arguments or individual environment variables navigating
- * 		*current*\ **->mm->arg_start** and *current*\
- * 		**->mm->env_start**: using this helper and the return value,
- * 		one can quickly iterate at the right offset of the memory area.
+ * 		Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
+ * 		instead.
  * 	Return
  * 		On success, the strictly positive length of the string,
  * 		including the trailing NUL character. On error, a negative
@@ -2775,6 +2749,72 @@ union bpf_attr {
  * 		restricted to raw_tracepoint bpf programs.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Safely attempt to read *size* bytes from user space address
+ * 		*unsafe_ptr* and store the data in *dst*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Safely attempt to read *size* bytes from kernel space address
+ * 		*unsafe_ptr* and store the data in *dst*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Copy a NUL terminated string from an unsafe user address
+ * 		*unsafe_ptr* to *dst*. The *size* should include the
+ * 		terminating NUL byte. In case the string length is smaller than
+ * 		*size*, the target is not padded with further NUL bytes. If the
+ * 		string length is larger than *size*, just *size*-1 bytes are
+ * 		copied and the last byte is set to NUL.
+ *
+ * 		On success, the length of the copied string is returned. This
+ * 		makes this helper useful in tracing programs for reading
+ * 		strings, and more importantly to get its length at runtime. See
+ * 		the following snippet:
+ *
+ * 		::
+ *
+ * 			SEC("kprobe/sys_open")
+ * 			void bpf_sys_open(struct pt_regs *ctx)
+ * 			{
+ * 			        char buf[PATHLEN]; // PATHLEN is defined to 256
+ * 			        int res = bpf_probe_read_user_str(buf, sizeof(buf),
+ * 				                                  ctx->di);
+ *
+ * 				// Consume buf, for example push it to
+ * 				// userspace via bpf_perf_event_output(); we
+ * 				// can use res (the string length) as event
+ * 				// size, after checking its boundaries.
+ * 			}
+ *
+ * 		In comparison, using **bpf_probe_read_user()** helper here
+ * 		instead to read the string would require to estimate the length
+ * 		at compile time, and would often result in copying more memory
+ * 		than necessary.
+ *
+ * 		Another useful use case is when parsing individual process
+ * 		arguments or individual environment variables navigating
+ * 		*current*\ **->mm->arg_start** and *current*\
+ * 		**->mm->env_start**: using this helper and the return value,
+ * 		one can quickly iterate at the right offset of the memory area.
+ * 	Return
+ * 		On success, the strictly positive length of the string,
+ * 		including the trailing NUL character. On error, a negative
+ * 		value.
+ *
+ * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * 		to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * 	Return
+ * 		On success, the strictly positive length of the string,	including
+ * 		the trailing NUL character. On error, a negative value.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2888,7 +2928,11 @@ union bpf_attr {
 	FN(sk_storage_delete),		\
 	FN(send_signal),		\
 	FN(tcp_gen_syncookie),		\
-	FN(skb_output),
+	FN(skb_output),			\
+	FN(probe_read_user),		\
+	FN(probe_read_kernel),		\
+	FN(probe_read_user_str),	\
+	FN(probe_read_kernel_str),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call