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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-04-22

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

The main changes are:

1) allow stack/queue helpers from more bpf program types, from Alban.

2) allow parallel verification of root bpf programs, from Alexei.

3) introduce bpf sysctl hook for trusted root cases, from Andrey.

4) recognize var/datasec in btf deduplication, from Andrii.

5) cpumap performance optimizations, from Jesper.

6) verifier prep for alu32 optimization, from Jiong.

7) libbpf xsk cleanup, from Magnus.

8) other various fixes and cleanups.
====================

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

1 files changed, 149 insertions, 5 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2e96d0b4bf65..eaf2d3284248 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -167,6 +167,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LIRC_MODE2,
 	BPF_PROG_TYPE_SK_REUSEPORT,
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
+	BPF_PROG_TYPE_CGROUP_SYSCTL,
 };
 
 enum bpf_attach_type {
@@ -188,6 +189,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_UDP6_SENDMSG,
 	BPF_LIRC_MODE2,
 	BPF_FLOW_DISSECTOR,
+	BPF_CGROUP_SYSCTL,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1735,12 +1737,19 @@ union bpf_attr {
  * 		error if an eBPF program tries to set a callback that is not
  * 		supported in the current kernel.
  *
- * 		The supported callback values that *argval* can combine are:
+ * 		*argval* is a flag array which can combine these flags:
  *
  * 		* **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
  * 		* **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
  * 		* **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
  *
+ * 		Therefore, this function can be used to clear a callback flag by
+ * 		setting the appropriate bit to zero. e.g. to disable the RTO
+ * 		callback:
+ *
+ * 		**bpf_sock_ops_cb_flags_set(bpf_sock,**
+ * 			**bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
+ *
  * 		Here are some examples of where one could call such eBPF
  * 		program:
  *
@@ -2504,6 +2513,122 @@ union bpf_attr {
  * 	Return
  * 		0 if iph and th are a valid SYN cookie ACK, or a negative error
  * 		otherwise.
+ *
+ * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ *	Description
+ *		Get name of sysctl in /proc/sys/ and copy it into provided by
+ *		program buffer *buf* of size *buf_len*.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ *		If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ *		copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ *		only (e.g. "tcp_mem").
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ *	Description
+ *		Get current value of sysctl as it is presented in /proc/sys
+ *		(incl. newline, etc), and copy it as a string into provided
+ *		by program buffer *buf* of size *buf_len*.
+ *
+ *		The whole value is copied, no matter what file position user
+ *		space issued e.g. sys_read at.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ *		**-EINVAL** if current value was unavailable, e.g. because
+ *		sysctl is uninitialized and read returns -EIO for it.
+ *
+ * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ *	Description
+ *		Get new value being written by user space to sysctl (before
+ *		the actual write happens) and copy it as a string into
+ *		provided by program buffer *buf* of size *buf_len*.
+ *
+ *		User space may write new value at file position > 0.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ *		**-EINVAL** if sysctl is being read.
+ *
+ * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ *	Description
+ *		Override new value being written by user space to sysctl with
+ *		value provided by program in buffer *buf* of size *buf_len*.
+ *
+ *		*buf* should contain a string in same form as provided by user
+ *		space on sysctl write.
+ *
+ *		User space may write new value at file position > 0. To override
+ *		the whole sysctl value file position should be set to zero.
+ *	Return
+ *		0 on success.
+ *
+ *		**-E2BIG** if the *buf_len* is too big.
+ *
+ *		**-EINVAL** if sysctl is being read.
+ *
+ * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ *	Description
+ *		Convert the initial part of the string from buffer *buf* of
+ *		size *buf_len* to a long integer according to the given base
+ *		and save the result in *res*.
+ *
+ *		The string may begin with an arbitrary amount of white space
+ *		(as determined by isspace(3)) followed by a single optional '-'
+ *		sign.
+ *
+ *		Five least significant bits of *flags* encode base, other bits
+ *		are currently unused.
+ *
+ *		Base must be either 8, 10, 16 or 0 to detect it automatically
+ *		similar to user space strtol(3).
+ *	Return
+ *		Number of characters consumed on success. Must be positive but
+ *		no more than buf_len.
+ *
+ *		**-EINVAL** if no valid digits were found or unsupported base
+ *		was provided.
+ *
+ *		**-ERANGE** if resulting value was out of range.
+ *
+ * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ *	Description
+ *		Convert the initial part of the string from buffer *buf* of
+ *		size *buf_len* to an unsigned long integer according to the
+ *		given base and save the result in *res*.
+ *
+ *		The string may begin with an arbitrary amount of white space
+ *		(as determined by isspace(3)).
+ *
+ *		Five least significant bits of *flags* encode base, other bits
+ *		are currently unused.
+ *
+ *		Base must be either 8, 10, 16 or 0 to detect it automatically
+ *		similar to user space strtoul(3).
+ *	Return
+ *		Number of characters consumed on success. Must be positive but
+ *		no more than buf_len.
+ *
+ *		**-EINVAL** if no valid digits were found or unsupported base
+ *		was provided.
+ *
+ *		**-ERANGE** if resulting value was out of range.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2606,7 +2731,13 @@ union bpf_attr {
 	FN(skb_ecn_set_ce),		\
 	FN(get_listener_sock),		\
 	FN(skc_lookup_tcp),		\
-	FN(tcp_check_syncookie),
+	FN(tcp_check_syncookie),	\
+	FN(sysctl_get_name),		\
+	FN(sysctl_get_current_value),	\
+	FN(sysctl_get_new_value),	\
+	FN(sysctl_set_new_value),	\
+	FN(strtol),			\
+	FN(strtoul),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2668,17 +2799,20 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
-#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
-#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
 
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
-#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
 					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
+/* BPF_FUNC_sysctl_get_name flags. */
+#define BPF_F_SYSCTL_BASE_NAME		(1ULL << 0)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -3308,4 +3442,14 @@ struct bpf_line_info {
 struct bpf_spin_lock {
 	__u32	val;
 };
+
+struct bpf_sysctl {
+	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
+				 * Allows 1,2,4-byte read, but no write.
+				 */
+	__u32	file_pos;	/* Sysctl file position to read from, write to.
+				 * Allows 1,2,4-byte read an 4-byte write.
+				 */
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */