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>

7 files changed, 198 insertions, 5 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index a4c644c1c091..cb3c6b3b89c8 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -17,6 +17,8 @@ struct bpf_map;
 struct bpf_prog;
 struct bpf_sock_ops_kern;
 struct bpf_cgroup_storage;
+struct ctl_table;
+struct ctl_table_header;
 
 #ifdef CONFIG_CGROUP_BPF
 
@@ -109,6 +111,12 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
+				   struct ctl_table *table, int write,
+				   void __user *buf, size_t *pcount,
+				   loff_t *ppos, void **new_buf,
+				   enum bpf_attach_type type);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -253,6 +261,18 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 									      \
 	__ret;								      \
 })
+
+
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf)  \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
+						       buf, count, pos, nbuf,  \
+						       BPF_CGROUP_SYSCTL);     \
+	__ret;								       \
+})
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog);
 int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -321,6 +341,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e4d4c1771ab0..f15432d90728 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -202,6 +202,8 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
+	ARG_PTR_TO_INT,		/* pointer to int */
+	ARG_PTR_TO_LONG,	/* pointer to long */
 };
 
 /* type of values returned from helper functions */
@@ -987,6 +989,8 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
 extern const struct bpf_func_proto bpf_spin_lock_proto;
 extern const struct bpf_func_proto bpf_spin_unlock_proto;
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
+extern const struct bpf_func_proto bpf_strtol_proto;
+extern const struct bpf_func_proto bpf_strtoul_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 08bf2f1fe553..d26991a16894 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -28,6 +28,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b3ab61fe1932..1305ccbd8fe6 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -295,6 +295,11 @@ struct bpf_verifier_env {
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
+	struct {
+		int *insn_state;
+		int *insn_stack;
+		int cur_stack;
+	} cfg;
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
 	u32 insn_processed;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6074aa064b54..fb0edad75971 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -33,6 +33,8 @@ struct bpf_prog_aux;
 struct xdp_rxq_info;
 struct xdp_buff;
 struct sock_reuseport;
+struct ctl_table;
+struct ctl_table_header;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -1177,4 +1179,18 @@ struct bpf_sock_ops_kern {
 					 */
 };
 
+struct bpf_sysctl_kern {
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	void *cur_val;
+	size_t cur_len;
+	void *new_val;
+	size_t new_len;
+	int new_updated;
+	int write;
+	loff_t *ppos;
+	/* Temporary "register" for indirect stores to ppos. */
+	u64 tmp_reg;
+};
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e4ee92089dd6..6f42942a443b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1042,6 +1042,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
 struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+				 void *data, unsigned int frag_size);
 
 /**
  * alloc_skb - allocate a network buffer
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__ */