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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-11-02

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

We've added 30 non-merge commits during the last 7 day(s) which contain
a total of 41 files changed, 1864 insertions(+), 474 deletions(-).

The main changes are:

1) Fix long standing user vs kernel access issue by introducing
   bpf_probe_read_user() and bpf_probe_read_kernel() helpers, from Daniel.

2) Accelerated xskmap lookup, from Björn and Maciej.

3) Support for automatic map pinning in libbpf, from Toke.

4) Cleanup of BTF-enabled raw tracepoints, from Alexei.

5) Various fixes to libbpf and selftests.
====================

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

4 files changed, 73 insertions, 96 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 658d68d409a4..97e37d82a1cc 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -668,9 +668,6 @@ static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
 {
 	struct latch_tree_node *n;
 
-	if (!bpf_jit_kallsyms_enabled())
-		return NULL;
-
 	n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
 	return n ?
 	       container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
@@ -1309,11 +1306,12 @@ bool bpf_opcode_in_insntable(u8 code)
 }
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read(void * dst, u32 size, const void * unsafe_ptr)
+u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
 {
 	memset(dst, 0, size);
 	return -EFAULT;
 }
+
 /**
  *	__bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1569,9 +1567,9 @@ out:
 	LDST(W,  u32)
 	LDST(DW, u64)
 #undef LDST
-#define LDX_PROBE(SIZEOP, SIZE)						\
-	LDX_PROBE_MEM_##SIZEOP:						\
-		bpf_probe_read(&DST, SIZE, (const void *)(long) SRC);	\
+#define LDX_PROBE(SIZEOP, SIZE)							\
+	LDX_PROBE_MEM_##SIZEOP:							\
+		bpf_probe_read_kernel(&DST, SIZE, (const void *)(long) SRC);	\
 		CONT;
 	LDX_PROBE(B,  1)
 	LDX_PROBE(H,  2)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 57eacd5fc24a..6d9ce95e5a8d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1579,7 +1579,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			   u32 btf_id)
 {
 	switch (prog_type) {
-	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_TRACING:
 		if (btf_id > BTF_MAX_TYPE)
 			return -EINVAL;
 		break;
@@ -1842,13 +1842,13 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		return PTR_ERR(prog);
 
 	if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
+	    prog->type != BPF_PROG_TYPE_TRACING &&
 	    prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
 		err = -EINVAL;
 		goto out_put_prog;
 	}
 
-	if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT &&
-	    prog->aux->attach_btf_id) {
+	if (prog->type == BPF_PROG_TYPE_TRACING) {
 		if (attr->raw_tracepoint.name) {
 			/* raw_tp name should not be specified in raw_tp
 			 * programs that were verified via in-kernel BTF info
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c59778c0fc4d..2f2374967b36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6279,6 +6279,11 @@ static int check_return_code(struct bpf_verifier_env *env)
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		break;
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+		if (!env->prog->aux->attach_btf_id)
+			return 0;
+		range = tnum_const(0);
+		break;
 	default:
 		return 0;
 	}
@@ -9376,24 +9381,36 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
 	u32 btf_id = prog->aux->attach_btf_id;
+	const char prefix[] = "btf_trace_";
 	const struct btf_type *t;
 	const char *tname;
 
-	if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && btf_id) {
-		const char prefix[] = "btf_trace_";
+	if (prog->type != BPF_PROG_TYPE_TRACING)
+		return 0;
 
-		t = btf_type_by_id(btf_vmlinux, btf_id);
-		if (!t) {
-			verbose(env, "attach_btf_id %u is invalid\n", btf_id);
-			return -EINVAL;
-		}
+	if (!btf_id) {
+		verbose(env, "Tracing programs must provide btf_id\n");
+		return -EINVAL;
+	}
+	t = btf_type_by_id(btf_vmlinux, btf_id);
+	if (!t) {
+		verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+		return -EINVAL;
+	}
+	tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+	if (!tname) {
+		verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
+		return -EINVAL;
+	}
+
+	switch (prog->expected_attach_type) {
+	case BPF_TRACE_RAW_TP:
 		if (!btf_type_is_typedef(t)) {
 			verbose(env, "attach_btf_id %u is not a typedef\n",
 				btf_id);
 			return -EINVAL;
 		}
-		tname = btf_name_by_offset(btf_vmlinux, t->name_off);
-		if (!tname || strncmp(prefix, tname, sizeof(prefix) - 1)) {
+		if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
 			verbose(env, "attach_btf_id %u points to wrong type name %s\n",
 				btf_id, tname);
 			return -EINVAL;
@@ -9414,8 +9431,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_name = tname;
 		prog->aux->attach_func_proto = t;
 		prog->aux->attach_btf_trace = true;
+		return 0;
+	default:
+		return -EINVAL;
 	}
-	return 0;
 }
 
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index 82a1ffe15dfa..da16c30868f3 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -9,13 +9,6 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 
-struct xsk_map {
-	struct bpf_map map;
-	struct xdp_sock **xsk_map;
-	struct list_head __percpu *flush_list;
-	spinlock_t lock; /* Synchronize map updates */
-};
-
 int xsk_map_inc(struct xsk_map *map)
 {
 	struct bpf_map *m = &map->map;
@@ -80,9 +73,10 @@ static void xsk_map_sock_delete(struct xdp_sock *xs,
 
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
+	struct bpf_map_memory mem;
+	int cpu, err, numa_node;
 	struct xsk_map *m;
-	int cpu, err;
-	u64 cost;
+	u64 cost, size;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -92,44 +86,35 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
 		return ERR_PTR(-EINVAL);
 
-	m = kzalloc(sizeof(*m), GFP_USER);
-	if (!m)
+	numa_node = bpf_map_attr_numa_node(attr);
+	size = struct_size(m, xsk_map, attr->max_entries);
+	cost = size + array_size(sizeof(*m->flush_list), num_possible_cpus());
+
+	err = bpf_map_charge_init(&mem, cost);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	m = bpf_map_area_alloc(size, numa_node);
+	if (!m) {
+		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	bpf_map_init_from_attr(&m->map, attr);
+	bpf_map_charge_move(&m->map.memory, &mem);
 	spin_lock_init(&m->lock);
 
-	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
-	cost += sizeof(struct list_head) * num_possible_cpus();
-
-	/* Notice returns -EPERM on if map size is larger than memlock limit */
-	err = bpf_map_charge_init(&m->map.memory, cost);
-	if (err)
-		goto free_m;
-
-	err = -ENOMEM;
-
 	m->flush_list = alloc_percpu(struct list_head);
-	if (!m->flush_list)
-		goto free_charge;
+	if (!m->flush_list) {
+		bpf_map_charge_finish(&m->map.memory);
+		bpf_map_area_free(m);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	for_each_possible_cpu(cpu)
 		INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));
 
-	m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
-					sizeof(struct xdp_sock *),
-					m->map.numa_node);
-	if (!m->xsk_map)
-		goto free_percpu;
 	return &m->map;
-
-free_percpu:
-	free_percpu(m->flush_list);
-free_charge:
-	bpf_map_charge_finish(&m->map.memory);
-free_m:
-	kfree(m);
-	return ERR_PTR(err);
 }
 
 static void xsk_map_free(struct bpf_map *map)
@@ -139,8 +124,7 @@ static void xsk_map_free(struct bpf_map *map)
 	bpf_clear_redirect_map(map);
 	synchronize_net();
 	free_percpu(m->flush_list);
-	bpf_map_area_free(m->xsk_map);
-	kfree(m);
+	bpf_map_area_free(m);
 }
 
 static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -160,45 +144,20 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *xs;
-
-	if (key >= map->max_entries)
-		return NULL;
-
-	xs = READ_ONCE(m->xsk_map[key]);
-	return xs;
-}
-
-int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
-		       struct xdp_sock *xs)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
-	int err;
-
-	err = xsk_rcv(xs, xdp);
-	if (err)
-		return err;
-
-	if (!xs->flush_node.prev)
-		list_add(&xs->flush_node, flush_list);
-
-	return 0;
-}
-
-void __xsk_map_flush(struct bpf_map *map)
+static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
-	struct xdp_sock *xs, *tmp;
-
-	list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
-		xsk_flush(xs);
-		__list_del_clearprev(&xs->flush_node);
-	}
+	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
+	struct bpf_insn *insn = insn_buf;
+
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *)));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map));
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp);
+	*insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+	return insn - insn_buf;
 }
 
 static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
@@ -312,6 +271,7 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_free = xsk_map_free,
 	.map_get_next_key = xsk_map_get_next_key,
 	.map_lookup_elem = xsk_map_lookup_elem,
+	.map_gen_lookup = xsk_map_gen_lookup,
 	.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
 	.map_update_elem = xsk_map_update_elem,
 	.map_delete_elem = xsk_map_delete_elem,