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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-10-14

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

12 days of development and
85 files changed, 1889 insertions(+), 1020 deletions(-)

The main changes are:

1) auto-generation of bpf_helper_defs.h, from Andrii.

2) split of bpf_helpers.h into bpf_{helpers, helper_defs, endian, tracing}.h
   and move into libbpf, from Andrii.

3) Track contents of read-only maps as scalars in the verifier, from Andrii.

4) small x86 JIT optimization, from Daniel.

5) cross compilation support, from Ivan.

6) bpf flow_dissector enhancements, from Jakub and Stanislav.
====================

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

Documentation/bpf/prog_flow_dissector.rst

@@ -142,3 +142,6 @@ BPF flow dissector doesn't support exporting all the metadata that in-kernel
 C-based implementation can export. Notable example is single VLAN (802.1Q)
 and double VLAN (802.1AD) tags. Please refer to the ``struct bpf_flow_keys``
 for a set of information that's currently can be exported from the BPF context.
+
+When BPF flow dissector is attached to the root network namespace (machine-wide
+policy), users can't override it in their child network namespaces.

arch/x86/net/bpf_jit_comp.c

@@ -909,6 +909,16 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSLT | BPF_K:
 		case BPF_JMP32 | BPF_JSGE | BPF_K:
 		case BPF_JMP32 | BPF_JSLE | BPF_K:
+			/* test dst_reg, dst_reg to save one extra byte */
+			if (imm32 == 0) {
+				if (BPF_CLASS(insn->code) == BPF_JMP)
+					EMIT1(add_2mod(0x48, dst_reg, dst_reg));
+				else if (is_ereg(dst_reg))
+					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
+				goto emit_cond_jmp;
+			}
+
 			/* cmp dst_reg, imm8/32 */
 			if (BPF_CLASS(insn->code) == BPF_JMP)
 				EMIT1(add_1mod(0x48, dst_reg));

include/linux/bpf.h

@@ -363,7 +363,7 @@ struct bpf_prog_stats {
 	u64 cnt;
 	u64 nsecs;
 	struct u64_stats_sync syncp;
-};
+} __aligned(2 * sizeof(u64));
 
 struct bpf_prog_aux {
 	atomic_t refcnt;

include/uapi/linux/bpf.h

@@ -794,7 +794,7 @@ union bpf_attr {
  * 		A 64-bit integer containing the current GID and UID, and
  * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
  *
- * int bpf_get_current_comm(char *buf, u32 size_of_buf)
+ * int bpf_get_current_comm(void *buf, u32 size_of_buf)
  * 	Description
  * 		Copy the **comm** attribute of the current task into *buf* of
  * 		*size_of_buf*. The **comm** attribute contains the name of
@@ -1023,7 +1023,7 @@ union bpf_attr {
  * 		The realm of the route for the packet associated to *skb*, or 0
  * 		if none was found.
  *
- * int bpf_perf_event_output(struct pt_regs *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
  * 	Description
  * 		Write raw *data* blob into a special BPF perf event held by
  * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -1068,7 +1068,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+ * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
  * 	Description
  * 		This helper was provided as an easy way to load data from a
  * 		packet. It can be used to load *len* bytes from *offset* from
@@ -1085,7 +1085,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_get_stackid(struct pt_regs *ctx, struct bpf_map *map, u64 flags)
+ * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
  * 	Description
  * 		Walk a user or a kernel stack and return its id. To achieve
  * 		this, the helper needs *ctx*, which is a pointer to the context
@@ -1154,7 +1154,7 @@ union bpf_attr {
  * 		The checksum result, or a negative error code in case of
  * 		failure.
  *
- * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
  * 	Description
  * 		Retrieve tunnel options metadata for the packet associated to
  * 		*skb*, and store the raw tunnel option data to the buffer *opt*
@@ -1172,7 +1172,7 @@ union bpf_attr {
  * 	Return
  * 		The size of the option data retrieved.
  *
- * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
  * 	Description
  * 		Set tunnel options metadata for the packet associated to *skb*
  * 		to the option data contained in the raw buffer *opt* of *size*.
@@ -1511,7 +1511,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *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
@@ -1595,7 +1595,7 @@ union bpf_attr {
  * 	Return
  * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
  *
- * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
  * 		Redirect the packet to the socket referenced by *map* (of type
  * 		**BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
@@ -1715,7 +1715,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *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
@@ -1947,7 +1947,7 @@ union bpf_attr {
  * 	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)
+ * int bpf_get_stack(void *ctx, 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
@@ -1980,7 +1980,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const void *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*
@@ -2033,7 +2033,7 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
- * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
  *		The *skops* is used as a new value for the entry associated to
@@ -2392,7 +2392,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
  *	Description
  *		For socket policies, insert *len* bytes into *msg* at offset
  *		*start*.
@@ -2408,9 +2408,9 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
- * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
  *	Description
- *		Will remove *pop* bytes from a *msg* starting at byte *start*.
+ *		Will remove *len* bytes from a *msg* starting at byte *start*.
  *		This may result in **ENOMEM** errors under certain situations if
  *		an allocation and copy are required due to a full ring buffer.
  *		However, the helper will try to avoid doing the allocation
@@ -2505,7 +2505,7 @@ union bpf_attr {
  *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
- * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
+ * int bpf_skb_ecn_set_ce(struct sk_buff *skb)
  *	Description
  *		Set ECN (Explicit Congestion Notification) field of IP header
  *		to **CE** (Congestion Encountered) if current value is **ECT**

kernel/bpf/verifier.c

@@ -2739,6 +2739,41 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 	reg->smax_value = reg->umax_value;
 }
 
+static bool bpf_map_is_rdonly(const struct bpf_map *map)
+{
+	return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+}
+
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+{
+	void *ptr;
+	u64 addr;
+	int err;
+
+	err = map->ops->map_direct_value_addr(map, &addr, off);
+	if (err)
+		return err;
+	ptr = (void *)(long)addr + off;
+
+	switch (size) {
+	case sizeof(u8):
+		*val = (u64)*(u8 *)ptr;
+		break;
+	case sizeof(u16):
+		*val = (u64)*(u16 *)ptr;
+		break;
+	case sizeof(u32):
+		*val = (u64)*(u32 *)ptr;
+		break;
+	case sizeof(u64):
+		*val = *(u64 *)ptr;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -2776,9 +2811,27 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err)
 			return err;
 		err = check_map_access(env, regno, off, size, false);
-		if (!err && t == BPF_READ && value_regno >= 0)
-			mark_reg_unknown(env, regs, value_regno);
+		if (!err && t == BPF_READ && value_regno >= 0) {
+			struct bpf_map *map = reg->map_ptr;
+
+			/* if map is read-only, track its contents as scalars */
+			if (tnum_is_const(reg->var_off) &&
+			    bpf_map_is_rdonly(map) &&
+			    map->ops->map_direct_value_addr) {
+				int map_off = off + reg->var_off.value;
+				u64 val = 0;
 
+				err = bpf_map_direct_read(map, map_off, size,
+							  &val);
+				if (err)
+					return err;
+
+				regs[value_regno].type = SCALAR_VALUE;
+				__mark_reg_known(&regs[value_regno], val);
+			} else {
+				mark_reg_unknown(env, regs, value_regno);
+			}
+		}
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
 

net/core/flow_dissector.c

@@ -114,19 +114,50 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 {
 	struct bpf_prog *attached;
 	struct net *net;
+	int ret = 0;
 
 	net = current->nsproxy->net_ns;
 	mutex_lock(&flow_dissector_mutex);
+
+	if (net == &init_net) {
+		/* BPF flow dissector in the root namespace overrides
+		 * any per-net-namespace one. When attaching to root,
+		 * make sure we don't have any BPF program attached
+		 * to the non-root namespaces.
+		 */
+		struct net *ns;
+
+		for_each_net(ns) {
+			if (ns == &init_net)
+				continue;
+			if (rcu_access_pointer(ns->flow_dissector_prog)) {
+				ret = -EEXIST;
+				goto out;
+			}
+		}
+	} else {
+		/* Make sure root flow dissector is not attached
+		 * when attaching to the non-root namespace.
+		 */
+		if (rcu_access_pointer(init_net.flow_dissector_prog)) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+
 	attached = rcu_dereference_protected(net->flow_dissector_prog,
 					     lockdep_is_held(&flow_dissector_mutex));
-	if (attached) {
-		/* Only one BPF program can be attached at a time */
-		mutex_unlock(&flow_dissector_mutex);
-		return -EEXIST;
+	if (attached == prog) {
+		/* The same program cannot be attached twice */
+		ret = -EINVAL;
+		goto out;
 	}
 	rcu_assign_pointer(net->flow_dissector_prog, prog);
+	if (attached)
+		bpf_prog_put(attached);
+out:
 	mutex_unlock(&flow_dissector_mutex);
-	return 0;
+	return ret;
 }
 
 int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
@@ -910,7 +941,10 @@ bool __skb_flow_dissect(const struct net *net,
 	WARN_ON_ONCE(!net);
 	if (net) {
 		rcu_read_lock();
-		attached = rcu_dereference(net->flow_dissector_prog);
+		attached = rcu_dereference(init_net.flow_dissector_prog);
+
+		if (!attached)
+			attached = rcu_dereference(net->flow_dissector_prog);
 
 		if (attached) {
 			struct bpf_flow_keys flow_keys;

net/core/xdp.c

@@ -386,7 +386,7 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
 
 /* XDP RX runs under NAPI protection, and in different delivery error
  * scenarios (e.g. queue full), it is possible to return the xdp_frame
- * while still leveraging this protection.  The @napi_direct boolian
+ * while still leveraging this protection.  The @napi_direct boolean
  * is used for those calls sites.  Thus, allowing for faster recycling
  * of xdp_frames/pages in those cases.
  */