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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-05-14

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

The main changes are:

1) Merged tag 'perf-for-bpf-2020-05-06' from tip tree that includes CAP_PERFMON.

2) support for narrow loads in bpf_sock_addr progs and additional
   helpers in cg-skb progs, from Andrey.

3) bpf benchmark runner, from Andrii.

4) arm and riscv JIT optimizations, from Luke.

5) bpf iterator infrastructure, from Yonghong.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

arch/arm/net/bpf_jit_32.c

@@ -795,6 +795,9 @@ static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 	case BPF_RSH:
 		emit(ARM_LSR_I(rd, rd, val), ctx);
 		break;
+	case BPF_ARSH:
+		emit(ARM_ASR_I(rd, rd, val), ctx);
+		break;
 	case BPF_NEG:
 		emit(ARM_RSB_I(rd, rd, val), ctx);
 		break;
@@ -860,8 +863,8 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
 	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
-	_emit(ARM_COND_MI, ARM_B(0), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
+	_emit(ARM_COND_PL,
+	      ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_ASR, rt), ctx);
 
 	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
@@ -1408,7 +1411,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU | BPF_RSH | BPF_X:
-	case BPF_ALU | BPF_ARSH | BPF_K:
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_K:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
@@ -1465,10 +1467,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
 		goto notyet;
-	/* dst = dst >> imm */
 	/* dst = dst << imm */
-	case BPF_ALU | BPF_RSH | BPF_K:
+	/* dst = dst >> imm */
+	/* dst = dst >> imm (signed) */
 	case BPF_ALU | BPF_LSH | BPF_K:
+	case BPF_ALU | BPF_RSH | BPF_K:
+	case BPF_ALU | BPF_ARSH | BPF_K:
 		if (unlikely(imm > 31))
 			return -EINVAL;
 		if (imm)

arch/arm/net/bpf_jit_32.h

@@ -94,6 +94,9 @@
 #define ARM_INST_LSR_I		0x01a00020
 #define ARM_INST_LSR_R		0x01a00030
 
+#define ARM_INST_ASR_I		0x01a00040
+#define ARM_INST_ASR_R		0x01a00050
+
 #define ARM_INST_MOV_R		0x01a00000
 #define ARM_INST_MOVS_R		0x01b00000
 #define ARM_INST_MOV_I		0x03a00000

arch/riscv/net/bpf_jit_comp64.c

@@ -515,7 +515,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_X:
@@ -542,13 +542,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 	/* dst = BSWAP##imm(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
-	{
-		int shift = 64 - imm;
-
-		emit(rv_slli(rd, rd, shift), ctx);
-		emit(rv_srli(rd, rd, shift), ctx);
+		switch (imm) {
+		case 16:
+			emit(rv_slli(rd, rd, 48), ctx);
+			emit(rv_srli(rd, rd, 48), ctx);
+			break;
+		case 32:
+			if (!aux->verifier_zext)
+				emit_zext_32(rd, ctx);
+			break;
+		case 64:
+			/* Do nothing */
+			break;
+		}
 		break;
-	}
+
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 		emit(rv_addi(RV_REG_T2, RV_REG_ZERO, 0), ctx);
 
@@ -692,19 +700,19 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_LSH | BPF_K:
 	case BPF_ALU64 | BPF_LSH | BPF_K:
 		emit(is64 ? rv_slli(rd, rd, imm) : rv_slliw(rd, rd, imm), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_RSH | BPF_K:
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		emit(is64 ? rv_srli(rd, rd, imm) : rv_srliw(rd, rd, imm), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_K:
 	case BPF_ALU64 | BPF_ARSH | BPF_K:
 		emit(is64 ? rv_srai(rd, rd, imm) : rv_sraiw(rd, rd, imm), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -784,11 +792,15 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_JMP32 | BPF_JSGE | BPF_K:
 	case BPF_JMP | BPF_JSLE | BPF_K:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
-	case BPF_JMP | BPF_JSET | BPF_K:
-	case BPF_JMP32 | BPF_JSET | BPF_K:
 		rvoff = rv_offset(i, off, ctx);
 		s = ctx->ninsns;
-		emit_imm(RV_REG_T1, imm, ctx);
+		if (imm) {
+			emit_imm(RV_REG_T1, imm, ctx);
+			rs = RV_REG_T1;
+		} else {
+			/* If imm is 0, simply use zero register. */
+			rs = RV_REG_ZERO;
+		}
 		if (!is64) {
 			if (is_signed_bpf_cond(BPF_OP(code)))
 				emit_sext_32_rd(&rd, ctx);
@@ -799,16 +811,28 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 		/* Adjust for extra insns */
 		rvoff -= (e - s) << 2;
+		emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+		break;
 
-		if (BPF_OP(code) == BPF_JSET) {
-			/* Adjust for and */
-			rvoff -= 4;
-			emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx);
-			emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff,
-				    ctx);
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		rvoff = rv_offset(i, off, ctx);
+		s = ctx->ninsns;
+		if (is_12b_int(imm)) {
+			emit(rv_andi(RV_REG_T1, rd, imm), ctx);
 		} else {
-			emit_branch(BPF_OP(code), rd, RV_REG_T1, rvoff, ctx);
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx);
 		}
+		/* For jset32, we should clear the upper 32 bits of t1, but
+		 * sign-extension is sufficient here and saves one instruction,
+		 * as t1 is used only in comparison against zero.
+		 */
+		if (!is64 && imm < 0)
+			emit(rv_addiw(RV_REG_T1, RV_REG_T1, 0), ctx);
+		e = ctx->ninsns;
+		rvoff -= (e - s) << 2;
+		emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
 		break;
 
 	/* function call */

arch/x86/net/bpf_jit_comp32.c

@@ -1475,8 +1475,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
 		const bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
-		const bool dstk = insn->dst_reg == BPF_REG_AX ? false : true;
-		const bool sstk = insn->src_reg == BPF_REG_AX ? false : true;
+		const bool dstk = insn->dst_reg != BPF_REG_AX;
+		const bool sstk = insn->src_reg != BPF_REG_AX;
 		const u8 code = insn->code;
 		const u8 *dst = bpf2ia32[insn->dst_reg];
 		const u8 *src = bpf2ia32[insn->src_reg];

fs/proc/proc_net.c

@@ -98,6 +98,25 @@ static const struct proc_ops proc_net_seq_ops = {
 	.proc_release	= seq_release_net,
 };
 
+int bpf_iter_init_seq_net(void *priv_data)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	p->net = get_net(current->nsproxy->net_ns);
+#endif
+	return 0;
+}
+
+void bpf_iter_fini_seq_net(void *priv_data)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	put_net(p->net);
+#endif
+}
+
 struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
 		struct proc_dir_entry *parent, const struct seq_operations *ops,
 		unsigned int state_size, void *data)

include/linux/bpf.h

@@ -31,6 +31,7 @@ struct seq_file;
 struct btf;
 struct btf_type;
 struct exception_table_entry;
+struct seq_operations;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -319,6 +320,7 @@ enum bpf_reg_type {
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
 	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
+	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -641,6 +643,12 @@ struct bpf_jit_poke_descriptor {
 	u16 reason;
 };
 
+/* reg_type info for ctx arguments */
+struct bpf_ctx_arg_aux {
+	u32 offset;
+	enum bpf_reg_type reg_type;
+};
+
 struct bpf_prog_aux {
 	atomic64_t refcnt;
 	u32 used_map_cnt;
@@ -652,6 +660,8 @@ struct bpf_prog_aux {
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+	u32 ctx_arg_info_size;
+	const struct bpf_ctx_arg_aux *ctx_arg_info;
 	struct bpf_prog *linked_prog;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
@@ -1021,6 +1031,7 @@ static inline void bpf_enable_instrumentation(void)
 
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
+extern const struct file_operations bpf_iter_fops;
 
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	extern const struct bpf_prog_ops _name ## _prog_ops; \
@@ -1080,6 +1091,7 @@ int  generic_map_update_batch(struct bpf_map *map,
 int  generic_map_delete_batch(struct bpf_map *map,
 			      const union bpf_attr *attr,
 			      union bpf_attr __user *uattr);
+struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
@@ -1126,6 +1138,40 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
 int bpf_obj_get_user(const char __user *pathname, int flags);
 
+#define BPF_ITER_FUNC_PREFIX "bpf_iter_"
+#define DEFINE_BPF_ITER_FUNC(target, args...)			\
+	extern int bpf_iter_ ## target(args);			\
+	int __init bpf_iter_ ## target(args) { return 0; }
+
+typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);
+typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
+
+#define BPF_ITER_CTX_ARG_MAX 2
+struct bpf_iter_reg {
+	const char *target;
+	const struct seq_operations *seq_ops;
+	bpf_iter_init_seq_priv_t init_seq_private;
+	bpf_iter_fini_seq_priv_t fini_seq_private;
+	u32 seq_priv_size;
+	u32 ctx_arg_info_size;
+	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
+};
+
+struct bpf_iter_meta {
+	__bpf_md_ptr(struct seq_file *, seq);
+	u64 session_id;
+	u64 seq_num;
+};
+
+int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
+void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
+bool bpf_iter_prog_supported(struct bpf_prog *prog);
+int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int bpf_iter_new_fd(struct bpf_link *link);
+bool bpf_link_is_iter(struct bpf_link *link);
+struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
+int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
+
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,

include/linux/bpf_types.h

@@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
 #ifdef CONFIG_CGROUP_BPF
 BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
 #endif
+BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)

include/linux/capability.h

@@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct
 extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
+static inline bool perfmon_capable(void)
+{
+	return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN);
+}
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);

include/linux/filter.h

@@ -545,10 +545,8 @@ struct bpf_prog {
 	unsigned int		(*bpf_func)(const void *ctx,
 					    const struct bpf_insn *insn);
 	/* Instructions for interpreter */
-	union {
-		struct sock_filter	insns[0];
-		struct bpf_insn		insnsi[0];
-	};
+	struct sock_filter	insns[0];
+	struct bpf_insn		insnsi[];
 };
 
 struct sk_filter {

include/linux/proc_fs.h

@@ -105,6 +105,9 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 						    void *data);
 extern struct pid *tgid_pidfd_to_pid(const struct file *file);
 
+extern int bpf_iter_init_seq_net(void *priv_data);
+extern void bpf_iter_fini_seq_net(void *priv_data);
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must

include/net/inet_common.h

@@ -35,8 +35,14 @@ int inet_shutdown(struct socket *sock, int how);
 int inet_listen(struct socket *sock, int backlog);
 void inet_sock_destruct(struct sock *sk);
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+/* Don't allocate port at this moment, defer to connect. */
+#define BIND_FORCE_ADDRESS_NO_PORT	(1 << 0)
+/* Grab and release socket lock. */
+#define BIND_WITH_LOCK			(1 << 1)
+/* Called from BPF program. */
+#define BIND_FROM_BPF			(1 << 2)
 int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
-		bool force_bind_address_no_port, bool with_lock);
+		u32 flags);
 int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 		 int peer);
 int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);

include/net/ip6_fib.h

@@ -544,6 +544,13 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric)
 	return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
 }
 
+#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_iter__ipv6_route {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct fib6_info *, rt);
+};
+#endif
+
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 static inline bool fib6_has_custom_rules(const struct net *net)
 {

include/net/ipv6_stubs.h

@@ -63,7 +63,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly;
 /* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
 struct ipv6_bpf_stub {
 	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
-			  bool force_bind_address_no_port, bool with_lock);
+			  u32 flags);
 	struct sock *(*udp6_lib_lookup)(struct net *net,
 				     const struct in6_addr *saddr, __be16 sport,
 				     const struct in6_addr *daddr, __be16 dport,

include/net/xdp_sock.h

@@ -50,7 +50,6 @@ struct xdp_umem {
 	u32 headroom;
 	u32 chunk_size_nohr;
 	struct user_struct *user;
-	unsigned long address;
 	refcount_t users;
 	struct work_struct work;
 	struct page **pgs;
@@ -62,8 +61,8 @@ struct xdp_umem {
 	struct net_device *dev;
 	struct xdp_umem_fq_reuse *fq_reuse;
 	bool zc;
-	spinlock_t xsk_list_lock;
-	struct list_head xsk_list;
+	spinlock_t xsk_tx_list_lock;
+	struct list_head xsk_tx_list;
 };
 
 /* Nodes are linked in the struct xdp_sock map_list field, and used to