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

Alexei Starovoitov says:

====================
pull-request: bpf 2018-12-05

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

The main changes are:

1) fix bpf uapi pointers for 32-bit architectures, from Daniel.

2) improve verifer ability to handle progs with a lot of branches, from Alexei.

3) strict btf checks, from Yonghong.

4) bpf_sk_lookup api cleanup, from Joe.

5) other misc fixes
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/powerpc/net/bpf_jit_comp64.c

@@ -891,6 +891,55 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 	return 0;
 }
 
+/* Fix the branch target addresses for subprog calls */
+static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image,
+				       struct codegen_context *ctx, u32 *addrs)
+{
+	const struct bpf_insn *insn = fp->insnsi;
+	bool func_addr_fixed;
+	u64 func_addr;
+	u32 tmp_idx;
+	int i, ret;
+
+	for (i = 0; i < fp->len; i++) {
+		/*
+		 * During the extra pass, only the branch target addresses for
+		 * the subprog calls need to be fixed. All other instructions
+		 * can left untouched.
+		 *
+		 * The JITed image length does not change because we already
+		 * ensure that the JITed instruction sequence for these calls
+		 * are of fixed length by padding them with NOPs.
+		 */
+		if (insn[i].code == (BPF_JMP | BPF_CALL) &&
+		    insn[i].src_reg == BPF_PSEUDO_CALL) {
+			ret = bpf_jit_get_func_addr(fp, &insn[i], true,
+						    &func_addr,
+						    &func_addr_fixed);
+			if (ret < 0)
+				return ret;
+
+			/*
+			 * Save ctx->idx as this would currently point to the
+			 * end of the JITed image and set it to the offset of
+			 * the instruction sequence corresponding to the
+			 * subprog call temporarily.
+			 */
+			tmp_idx = ctx->idx;
+			ctx->idx = addrs[i] / 4;
+			bpf_jit_emit_func_call_rel(image, ctx, func_addr);
+
+			/*
+			 * Restore ctx->idx here. This is safe as the length
+			 * of the JITed sequence remains unchanged.
+			 */
+			ctx->idx = tmp_idx;
+		}
+	}
+
+	return 0;
+}
+
 struct powerpc64_jit_data {
 	struct bpf_binary_header *header;
 	u32 *addrs;
@@ -989,6 +1038,22 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 skip_init_ctx:
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
 
+	if (extra_pass) {
+		/*
+		 * Do not touch the prologue and epilogue as they will remain
+		 * unchanged. Only fix the branch target address for subprog
+		 * calls in the body.
+		 *
+		 * This does not change the offsets and lengths of the subprog
+		 * call instruction sequences and hence, the size of the JITed
+		 * image as well.
+		 */
+		bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs);
+
+		/* There is no need to perform the usual passes. */
+		goto skip_codegen_passes;
+	}
+
 	/* Code generation passes 1-2 */
 	for (pass = 1; pass < 3; pass++) {
 		/* Now build the prologue, body code & epilogue for real. */
@@ -1002,6 +1067,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 				proglen - (cgctx.idx * 4), cgctx.seen);
 	}
 
+skip_codegen_passes:
 	if (bpf_jit_enable > 1)
 		/*
 		 * Note that we output the base address of the code_base

include/linux/filter.h

@@ -449,6 +449,13 @@ struct sock_reuseport;
 	offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1
 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2)				\
 	offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1
+#if BITS_PER_LONG == 64
+# define bpf_ctx_range_ptr(TYPE, MEMBER)					\
+	offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1
+#else
+# define bpf_ctx_range_ptr(TYPE, MEMBER)					\
+	offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1
+#endif /* BITS_PER_LONG == 64 */
 
 #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE)				\
 	({									\

include/uapi/linux/bpf.h

@@ -2170,7 +2170,7 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
- * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
@@ -2187,12 +2187,14 @@ union bpf_attr {
  *		**sizeof**\ (*tuple*\ **->ipv6**)
  *			Look for an IPv6 socket.
  *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
  *
  *		All values for *flags* are reserved for future usage, and must
  *		be left at zero.
@@ -2201,8 +2203,10 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, the *struct bpf_sock*
+ *		result is from reuse->socks[] using the hash of the tuple.
  *
- * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for UDP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
@@ -2219,12 +2223,14 @@ union bpf_attr {
  *		**sizeof**\ (*tuple*\ **->ipv6**)
  *			Look for an IPv6 socket.
  *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
  *
  *		All values for *flags* are reserved for future usage, and must
  *		be left at zero.
@@ -2233,6 +2239,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, the *struct bpf_sock*
+ *		result is from reuse->socks[] using the hash of the tuple.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
@@ -2405,6 +2413,9 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
+/* Current network namespace */
+#define BPF_F_CURRENT_NETNS		(-1L)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -2422,6 +2433,12 @@ enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6_INLINE
 };
 
+#define __bpf_md_ptr(type, name)	\
+union {					\
+	type name;			\
+	__u64 :64;			\
+} __attribute__((aligned(8)))
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -2456,7 +2473,7 @@ struct __sk_buff {
 	/* ... here. */
 
 	__u32 data_meta;
-	struct bpf_flow_keys *flow_keys;
+	__bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
 };
 
 struct bpf_tunnel_key {
@@ -2572,8 +2589,8 @@ enum sk_action {
  * be added to the end of this structure
  */
 struct sk_msg_md {
-	void *data;
-	void *data_end;
+	__bpf_md_ptr(void *, data);
+	__bpf_md_ptr(void *, data_end);
 
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
@@ -2589,8 +2606,9 @@ struct sk_reuseport_md {
 	 * Start of directly accessible data. It begins from
 	 * the tcp/udp header.
 	 */
-	void *data;
-	void *data_end;		/* End of directly accessible data */
+	__bpf_md_ptr(void *, data);
+	/* End of directly accessible data */
+	__bpf_md_ptr(void *, data_end);
 	/*
 	 * Total length of packet (starting from the tcp/udp header).
 	 * Note that the directly accessible bytes (data_end - data)

kernel/bpf/btf.c

@@ -5,6 +5,7 @@
 #include <uapi/linux/types.h>
 #include <linux/seq_file.h>
 #include <linux/compiler.h>
+#include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
@@ -426,6 +427,30 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 		offset < btf->hdr.str_len;
 }
 
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+	/* offset must be valid */
+	const char *src = &btf->strings[offset];
+	const char *src_limit;
+
+	if (!isalpha(*src) && *src != '_')
+		return false;
+
+	/* set a limit on identifier length */
+	src_limit = src + KSYM_NAME_LEN;
+	src++;
+	while (*src && src < src_limit) {
+		if (!isalnum(*src) && *src != '_')
+			return false;
+		src++;
+	}
+
+	return !*src;
+}
+
 static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
@@ -1143,6 +1168,22 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	/* typedef type must have a valid name, and other ref types,
+	 * volatile, const, restrict, should have a null name.
+	 */
+	if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
+		if (!t->name_off ||
+		    !btf_name_valid_identifier(env->btf, t->name_off)) {
+			btf_verifier_log_type(env, t, "Invalid name");
+			return -EINVAL;
+		}
+	} else {
+		if (t->name_off) {
+			btf_verifier_log_type(env, t, "Invalid name");
+			return -EINVAL;
+		}
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	return 0;
@@ -1300,6 +1341,13 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	/* fwd type must have a valid name */
+	if (!t->name_off ||
+	    !btf_name_valid_identifier(env->btf, t->name_off)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	return 0;
@@ -1356,6 +1404,12 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	/* array type should not have a name */
+	if (t->name_off) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
 	if (btf_type_vlen(t)) {
 		btf_verifier_log_type(env, t, "vlen != 0");
 		return -EINVAL;
@@ -1532,6 +1586,13 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	/* struct type either no name or a valid one */
+	if (t->name_off &&
+	    !btf_name_valid_identifier(env->btf, t->name_off)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	last_offset = 0;
@@ -1543,6 +1604,12 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		/* struct member either no name or a valid one */
+		if (member->name_off &&
+		    !btf_name_valid_identifier(btf, member->name_off)) {
+			btf_verifier_log_member(env, t, member, "Invalid name");
+			return -EINVAL;
+		}
 		/* A member cannot be in type void */
 		if (!member->type || !BTF_TYPE_ID_VALID(member->type)) {
 			btf_verifier_log_member(env, t, member,
@@ -1730,6 +1797,13 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	/* enum type either no name or a valid one */
+	if (t->name_off &&
+	    !btf_name_valid_identifier(env->btf, t->name_off)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	for (i = 0; i < nr_enums; i++) {
@@ -1739,6 +1813,14 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		/* enum member must have a valid name */
+		if (!enums[i].name_off ||
+		    !btf_name_valid_identifier(btf, enums[i].name_off)) {
+			btf_verifier_log_type(env, t, "Invalid name");
+			return -EINVAL;
+		}
+
+
 		btf_verifier_log(env, "\t%s val=%d\n",
 				 btf_name_by_offset(btf, enums[i].name_off),
 				 enums[i].val);

kernel/bpf/verifier.c

@@ -175,6 +175,7 @@ struct bpf_verifier_stack_elem {
 
 #define BPF_COMPLEXITY_LIMIT_INSNS	131072
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
+#define BPF_COMPLEXITY_LIMIT_STATES	64
 
 #define BPF_MAP_PTR_UNPRIV	1UL
 #define BPF_MAP_PTR_POISON	((void *)((0xeB9FUL << 1) +	\
@@ -3751,6 +3752,79 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 	}
 }
 
+/* compute branch direction of the expression "if (reg opcode val) goto target;"
+ * and return:
+ *  1 - branch will be taken and "goto target" will be executed
+ *  0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
+ */
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+{
+	if (__is_pointer_value(false, reg))
+		return -1;
+
+	switch (opcode) {
+	case BPF_JEQ:
+		if (tnum_is_const(reg->var_off))
+			return !!tnum_equals_const(reg->var_off, val);
+		break;
+	case BPF_JNE:
+		if (tnum_is_const(reg->var_off))
+			return !tnum_equals_const(reg->var_off, val);
+		break;
+	case BPF_JGT:
+		if (reg->umin_value > val)
+			return 1;
+		else if (reg->umax_value <= val)
+			return 0;
+		break;
+	case BPF_JSGT:
+		if (reg->smin_value > (s64)val)
+			return 1;
+		else if (reg->smax_value < (s64)val)
+			return 0;
+		break;
+	case BPF_JLT:
+		if (reg->umax_value < val)
+			return 1;
+		else if (reg->umin_value >= val)
+			return 0;
+		break;
+	case BPF_JSLT:
+		if (reg->smax_value < (s64)val)
+			return 1;
+		else if (reg->smin_value >= (s64)val)
+			return 0;
+		break;
+	case BPF_JGE:
+		if (reg->umin_value >= val)
+			return 1;
+		else if (reg->umax_value < val)
+			return 0;
+		break;
+	case BPF_JSGE:
+		if (reg->smin_value >= (s64)val)
+			return 1;
+		else if (reg->smax_value < (s64)val)
+			return 0;
+		break;
+	case BPF_JLE:
+		if (reg->umax_value <= val)
+			return 1;
+		else if (reg->umin_value > val)
+			return 0;
+		break;
+	case BPF_JSLE:
+		if (reg->smax_value <= (s64)val)
+			return 1;
+		else if (reg->smin_value > (s64)val)
+			return 0;
+		break;
+	}
+
+	return -1;
+}
+
 /* Adjusts the register min/max values in the case that the dst_reg is the
  * variable register that we are working on, and src_reg is a constant or we're
  * simply doing a BPF_K check.
@@ -4152,21 +4226,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 
 	dst_reg = &regs[insn->dst_reg];
 
-	/* detect if R == 0 where R was initialized to zero earlier */
-	if (BPF_SRC(insn->code) == BPF_K &&
-	    (opcode == BPF_JEQ || opcode == BPF_JNE) &&
-	    dst_reg->type == SCALAR_VALUE &&
-	    tnum_is_const(dst_reg->var_off)) {
-		if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) ||
-		    (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) {
-			/* if (imm == imm) goto pc+off;
-			 * only follow the goto, ignore fall-through
-			 */
+	if (BPF_SRC(insn->code) == BPF_K) {
+		int pred = is_branch_taken(dst_reg, insn->imm, opcode);
+
+		if (pred == 1) {
+			 /* only follow the goto, ignore fall-through */
 			*insn_idx += insn->off;
 			return 0;
-		} else {
-			/* if (imm != imm) goto pc+off;
-			 * only follow fall-through branch, since
+		} else if (pred == 0) {
+			/* only follow fall-through branch, since
 			 * that's where the program will go
 			 */
 			return 0;
@@ -4980,7 +5048,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	struct bpf_verifier_state_list *new_sl;
 	struct bpf_verifier_state_list *sl;
 	struct bpf_verifier_state *cur = env->cur_state, *new;
-	int i, j, err;
+	int i, j, err, states_cnt = 0;
 
 	sl = env->explored_states[insn_idx];
 	if (!sl)
@@ -5007,8 +5075,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 			return 1;
 		}
 		sl = sl->next;
+		states_cnt++;
 	}
 
+	if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+		return 0;
+
 	/* there were no equivalent states, remember current one.
 	 * technically the current state is not proven to be safe yet,
 	 * but it will either reach outer most bpf_exit (which means it's safe)
@@ -5148,6 +5220,9 @@ static int do_check(struct bpf_verifier_env *env)
 			goto process_bpf_exit;
 		}
 
+		if (signal_pending(current))
+			return -EAGAIN;
+
 		if (need_resched())
 			cond_resched();
 

net/bpf/test_run.c

@@ -28,12 +28,13 @@ static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
 	return ret;
 }
 
-static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
+static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret,
+			u32 *time)
 {
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 };
 	enum bpf_cgroup_storage_type stype;
 	u64 time_start, time_spent = 0;
-	u32 ret = 0, i;
+	u32 i;
 
 	for_each_cgroup_storage_type(stype) {
 		storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
@@ -49,7 +50,7 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
 		repeat = 1;
 	time_start = ktime_get_ns();
 	for (i = 0; i < repeat; i++) {
-		ret = bpf_test_run_one(prog, ctx, storage);
+		*ret = bpf_test_run_one(prog, ctx, storage);
 		if (need_resched()) {
 			if (signal_pending(current))
 				break;
@@ -65,7 +66,7 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
 	for_each_cgroup_storage_type(stype)
 		bpf_cgroup_storage_free(storage[stype]);
 
-	return ret;
+	return 0;
 }
 
 static int bpf_test_finish(const union bpf_attr *kattr,
@@ -165,7 +166,12 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
-	retval = bpf_test_run(prog, skb, repeat, &duration);
+	ret = bpf_test_run(prog, skb, repeat, &retval, &duration);
+	if (ret) {
+		kfree_skb(skb);
+		kfree(sk);
+		return ret;
+	}
 	if (!is_l2) {
 		if (skb_headroom(skb) < hh_len) {
 			int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
@@ -212,11 +218,14 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp.rxq = &rxqueue->xdp_rxq;
 
-	retval = bpf_test_run(prog, &xdp, repeat, &duration);
+	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration);
+	if (ret)
+		goto out;
 	if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN ||
 	    xdp.data_end != xdp.data + size)
 		size = xdp.data_end - xdp.data;
 	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+out:
 	kfree(data);
 	return ret;
 }

net/core/filter.c

@@ -4890,22 +4890,23 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	struct net *net;
 
 	family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
-	if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
+	if (unlikely(family == AF_UNSPEC || flags ||
+		     !((s32)netns_id < 0 || netns_id <= S32_MAX)))
 		goto out;
 
 	if (skb->dev)
 		caller_net = dev_net(skb->dev);
 	else
 		caller_net = sock_net(skb->sk);
-	if (netns_id) {
+	if ((s32)netns_id < 0) {
+		net = caller_net;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+	} else {
 		net = get_net_ns_by_id(caller_net, netns_id);
 		if (unlikely(!net))
 			goto out;
 		sk = sk_lookup(net, tuple, skb, family, proto);
 		put_net(net);
-	} else {
-		net = caller_net;
-		sk = sk_lookup(net, tuple, skb, family, proto);
 	}
 
 	if (sk)
@@ -5435,8 +5436,8 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 		if (size != size_default)
 			return false;
 		break;
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
-		if (size != sizeof(struct bpf_flow_keys *))
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+		if (size != sizeof(__u64))
 			return false;
 		break;
 	default:
@@ -5464,7 +5465,7 @@ static bool sk_filter_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 		return false;
 	}
@@ -5489,7 +5490,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
@@ -5530,7 +5531,7 @@ static bool lwt_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		return false;
 	}
 
@@ -5756,7 +5757,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 		return false;
 	}
@@ -5958,7 +5959,7 @@ static bool sk_skb_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		return false;
 	}
 
@@ -6039,7 +6040,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
-	case bpf_ctx_range(struct __sk_buff, flow_keys):
+	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		info->reg_type = PTR_TO_FLOW_KEYS;
 		break;
 	case bpf_ctx_range(struct __sk_buff, tc_classid):

tools/bpf/bpftool/btf_dumper.c

@@ -32,7 +32,7 @@ static void btf_dumper_ptr(const void *data, json_writer_t *jw,
 }
 
 static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
-			       const void *data)
+			       __u8 bit_offset, const void *data)
 {
 	int actual_type_id;
 
@@ -40,7 +40,7 @@ static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
 	if (actual_type_id < 0)
 		return actual_type_id;
 
-	return btf_dumper_do_type(d, actual_type_id, 0, data);
+	return btf_dumper_do_type(d, actual_type_id, bit_offset, data);
 }
 
 static void btf_dumper_enum(const void *data, json_writer_t *jw)
@@ -237,7 +237,7 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
-		return btf_dumper_modifier(d, type_id, data);
+		return btf_dumper_modifier(d, type_id, bit_offset, data);
 	default:
 		jsonw_printf(d->jw, "(unsupported-kind");
 		return -EINVAL;

tools/include/uapi/linux/bpf.h

@@ -2170,7 +2170,7 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
- * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
@@ -2187,12 +2187,14 @@ union bpf_attr {
  *		**sizeof**\ (*tuple*\ **->ipv6**)
  *			Look for an IPv6 socket.
  *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
  *
  *		All values for *flags* are reserved for future usage, and must
  *		be left at zero.
@@ -2201,8 +2203,10 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, the *struct bpf_sock*
+ *		result is from reuse->socks[] using the hash of the tuple.
  *
- * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for UDP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
@@ -2219,12 +2223,14 @@ union bpf_attr {
  *		**sizeof**\ (*tuple*\ **->ipv6**)
  *			Look for an IPv6 socket.
  *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
  *
  *		All values for *flags* are reserved for future usage, and must
  *		be left at zero.
@@ -2233,6 +2239,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, the *struct bpf_sock*
+ *		result is from reuse->socks[] using the hash of the tuple.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
@@ -2405,6 +2413,9 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
+/* Current network namespace */
+#define BPF_F_CURRENT_NETNS		(-1L)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -2422,6 +2433,12 @@ enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6_INLINE
 };
 
+#define __bpf_md_ptr(type, name)	\
+union {					\
+	type name;			\
+	__u64 :64;			\
+} __attribute__((aligned(8)))
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -2456,7 +2473,7 @@ struct __sk_buff {
 	/* ... here. */
 
 	__u32 data_meta;
-	struct bpf_flow_keys *flow_keys;
+	__bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
 };
 
 struct bpf_tunnel_key {
@@ -2572,8 +2589,8 @@ enum sk_action {
  * be added to the end of this structure
  */
 struct sk_msg_md {
-	void *data;
-	void *data_end;
+	__bpf_md_ptr(void *, data);
+	__bpf_md_ptr(void *, data_end);
 
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
@@ -2589,8 +2606,9 @@ struct sk_reuseport_md {
 	 * Start of directly accessible data. It begins from
 	 * the tcp/udp header.
 	 */
-	void *data;
-	void *data_end;		/* End of directly accessible data */
+	__bpf_md_ptr(void *, data);
+	/* End of directly accessible data */
+	__bpf_md_ptr(void *, data_end);
 	/*
 	 * Total length of packet (starting from the tcp/udp header).
 	 * Note that the directly accessible bytes (data_end - data)

tools/testing/selftests/bpf/bpf_helpers.h

@@ -154,12 +154,12 @@ static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
 	(void *) BPF_FUNC_skb_ancestor_cgroup_id;
 static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx,
 					     struct bpf_sock_tuple *tuple,
-					     int size, unsigned int netns_id,
+					     int size, unsigned long long netns_id,
 					     unsigned long long flags) =
 	(void *) BPF_FUNC_sk_lookup_tcp;
 static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
 					     struct bpf_sock_tuple *tuple,
-					     int size, unsigned int netns_id,
+					     int size, unsigned long long netns_id,
 					     unsigned long long flags) =
 	(void *) BPF_FUNC_sk_lookup_udp;
 static int (*bpf_sk_release)(struct bpf_sock *sk) =

tools/testing/selftests/bpf/test_sk_lookup_kern.c

@@ -72,7 +72,7 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 
 	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
-	sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0);
 	if (sk)
 		bpf_sk_release(sk);
 	return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
@@ -84,7 +84,7 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb)
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
 
-	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	if (sk)
 		bpf_sk_release(sk);
 	return 0;
@@ -97,7 +97,7 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb)
 	struct bpf_sock *sk;
 	__u32 family = 0;
 
-	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	if (sk) {
 		bpf_sk_release(sk);
 		family = sk->family;
@@ -112,7 +112,7 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb)
 	struct bpf_sock *sk;
 	__u32 family;
 
-	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	if (sk) {
 		sk += 1;
 		bpf_sk_release(sk);
@@ -127,7 +127,7 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
 	struct bpf_sock *sk;
 	__u32 family;
 
-	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	sk += 1;
 	if (sk)
 		bpf_sk_release(sk);
@@ -139,7 +139,7 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 
-	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	return 0;
 }
 
@@ -149,7 +149,7 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb)
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
 
-	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	bpf_sk_release(sk);
 	bpf_sk_release(sk);
 	return 0;
@@ -161,7 +161,7 @@ int bpf_sk_lookup_test4(struct __sk_buff *skb)
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
 
-	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	bpf_sk_release(sk);
 	return 0;
 }
@@ -169,7 +169,7 @@ int bpf_sk_lookup_test4(struct __sk_buff *skb)
 void lookup_no_release(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
-	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 }
 
 SEC("fail_no_release_subcall")

tools/testing/selftests/bpf/test_verifier.c

@@ -8576,7 +8576,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_IMM(BPF_JA, 0, 0, -7),
 		},
 		.fixup_map_hash_8b = { 4 },
-		.errstr = "R0 invalid mem access 'inv'",
+		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
 	{
@@ -10547,7 +10547,7 @@ static struct bpf_test tests[] = {
 		"check deducing bounds from const, 5",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
-			BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
+			BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 1, 1),
 			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 			BPF_EXIT_INSN(),
 		},
@@ -14230,7 +14230,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 
 	reject_from_alignment = fd_prog < 0 &&
 				(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
-				strstr(bpf_vlog, "Unknown alignment.");
+				strstr(bpf_vlog, "misaligned");
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	if (reject_from_alignment) {
 		printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",