Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-07-13

We've added 67 non-merge commits during the last 15 day(s) which contain
a total of 106 files changed, 4444 insertions(+), 619 deletions(-).

The main changes are:

1) Fix bpftool build in presence of stale vmlinux.h,
   from Alexander Lobakin.

2) Introduce bpf_me_mcache_free_rcu() and fix OOM under stress,
   from Alexei Starovoitov.

3) Teach verifier actual bounds of bpf_get_smp_processor_id()
   and fix perf+libbpf issue related to custom section handling,
   from Andrii Nakryiko.

4) Introduce bpf map element count, from Anton Protopopov.

5) Check skb ownership against full socket, from Kui-Feng Lee.

6) Support for up to 12 arguments in BPF trampoline, from Menglong Dong.

7) Export rcu_request_urgent_qs_task, from Paul E. McKenney.

8) Fix BTF walking of unions, from Yafang Shao.

9) Extend link_info for kprobe_multi and perf_event links,
   from Yafang Shao.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (67 commits)
  selftests/bpf: Add selftest for PTR_UNTRUSTED
  bpf: Fix an error in verifying a field in a union
  selftests/bpf: Add selftests for nested_trust
  bpf: Fix an error around PTR_UNTRUSTED
  selftests/bpf: add testcase for TRACING with 6+ arguments
  bpf, x86: allow function arguments up to 12 for TRACING
  bpf, x86: save/restore regs with BPF_DW size
  bpftool: Use "fallthrough;" keyword instead of comments
  bpf: Add object leak check.
  bpf: Convert bpf_cpumask to bpf_mem_cache_free_rcu.
  bpf: Introduce bpf_mem_free_rcu() similar to kfree_rcu().
  selftests/bpf: Improve test coverage of bpf_mem_alloc.
  rcu: Export rcu_request_urgent_qs_task()
  bpf: Allow reuse from waiting_for_gp_ttrace list.
  bpf: Add a hint to allocated objects.
  bpf: Change bpf_mem_cache draining process.
  bpf: Further refactor alloc_bulk().
  bpf: Factor out inc/dec of active flag into helpers.
  bpf: Refactor alloc_bulk().
  bpf: Let free_all() return the number of freed elements.
  ...
====================

Link: https://lore.kernel.org/r/20230714020910.80794-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 268 insertions, 35 deletions

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ed86b37d8024..3b0da19715e1 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -741,6 +741,14 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, tracing))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_NETFILTER:
+		attr.link_create.netfilter.pf = OPTS_GET(opts, netfilter.pf, 0);
+		attr.link_create.netfilter.hooknum = OPTS_GET(opts, netfilter.hooknum, 0);
+		attr.link_create.netfilter.priority = OPTS_GET(opts, netfilter.priority, 0);
+		attr.link_create.netfilter.flags = OPTS_GET(opts, netfilter.flags, 0);
+		if (!OPTS_ZEROED(opts, netfilter))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9aa0ee473754..c676295ab9bf 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -349,6 +349,12 @@ struct bpf_link_create_opts {
 		struct {
 			__u64 cookie;
 		} tracing;
+		struct {
+			__u32 pf;
+			__u32 hooknum;
+			__s32 priority;
+			__u32 flags;
+		} netfilter;
 	};
 	size_t :0;
 };
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index 0a5bf1937a7c..c12f8320e668 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -80,16 +80,6 @@ struct hashmap {
 	size_t sz;
 };
 
-#define HASHMAP_INIT(hash_fn, equal_fn, ctx) {	\
-	.hash_fn = (hash_fn),			\
-	.equal_fn = (equal_fn),			\
-	.ctx = (ctx),				\
-	.buckets = NULL,			\
-	.cap = 0,				\
-	.cap_bits = 0,				\
-	.sz = 0,				\
-}
-
 void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
 		   hashmap_equal_fn equal_fn, void *ctx);
 struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 214f828ece6b..63311a73c16d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5471,6 +5471,10 @@ static int load_module_btfs(struct bpf_object *obj)
 		err = bpf_btf_get_next_id(id, &id);
 		if (err && errno == ENOENT)
 			return 0;
+		if (err && errno == EPERM) {
+			pr_debug("skipping module BTFs loading, missing privileges\n");
+			return 0;
+		}
 		if (err) {
 			err = -errno;
 			pr_warn("failed to iterate BTF objects: %d\n", err);
@@ -6157,7 +6161,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 	if (main_prog == subprog)
 		return 0;
 	relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos));
-	if (!relos)
+	/* if new count is zero, reallocarray can return a valid NULL result;
+	 * in this case the previous pointer will be freed, so we *have to*
+	 * reassign old pointer to the new value (even if it's NULL)
+	 */
+	if (!relos && new_cnt)
 		return -ENOMEM;
 	if (subprog->nr_reloc)
 		memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc,
@@ -8528,7 +8536,8 @@ int bpf_program__set_insns(struct bpf_program *prog,
 		return -EBUSY;
 
 	insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns));
-	if (!insns) {
+	/* NULL is a valid return from reallocarray if the new count is zero */
+	if (!insns && new_insn_cnt) {
 		pr_warn("prog '%s': failed to realloc prog code\n", prog->name);
 		return -ENOMEM;
 	}
@@ -8558,13 +8567,31 @@ enum bpf_prog_type bpf_program__type(const struct bpf_program *prog)
 	return prog->type;
 }
 
+static size_t custom_sec_def_cnt;
+static struct bpf_sec_def *custom_sec_defs;
+static struct bpf_sec_def custom_fallback_def;
+static bool has_custom_fallback_def;
+static int last_custom_sec_def_handler_id;
+
 int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
 {
 	if (prog->obj->loaded)
 		return libbpf_err(-EBUSY);
 
+	/* if type is not changed, do nothing */
+	if (prog->type == type)
+		return 0;
+
 	prog->type = type;
-	prog->sec_def = NULL;
+
+	/* If a program type was changed, we need to reset associated SEC()
+	 * handler, as it will be invalid now. The only exception is a generic
+	 * fallback handler, which by definition is program type-agnostic and
+	 * is a catch-all custom handler, optionally set by the application,
+	 * so should be able to handle any type of BPF program.
+	 */
+	if (prog->sec_def != &custom_fallback_def)
+		prog->sec_def = NULL;
 	return 0;
 }
 
@@ -8740,13 +8767,6 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("netfilter",		NETFILTER, BPF_NETFILTER, SEC_NONE),
 };
 
-static size_t custom_sec_def_cnt;
-static struct bpf_sec_def *custom_sec_defs;
-static struct bpf_sec_def custom_fallback_def;
-static bool has_custom_fallback_def;
-
-static int last_custom_sec_def_handler_id;
-
 int libbpf_register_prog_handler(const char *sec,
 				 enum bpf_prog_type prog_type,
 				 enum bpf_attach_type exp_attach_type,
@@ -8826,7 +8846,11 @@ int libbpf_unregister_prog_handler(int handler_id)
 
 	/* try to shrink the array, but it's ok if we couldn't */
 	sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs));
-	if (sec_defs)
+	/* if new count is zero, reallocarray can return a valid NULL result;
+	 * in this case the previous pointer will be freed, so we *have to*
+	 * reassign old pointer to the new value (even if it's NULL)
+	 */
+	if (sec_defs || custom_sec_def_cnt == 0)
 		custom_sec_defs = sec_defs;
 
 	return 0;
@@ -10224,6 +10248,18 @@ static const char *tracefs_uprobe_events(void)
 	return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events";
 }
 
+static const char *tracefs_available_filter_functions(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions"
+			     : TRACEFS"/available_filter_functions";
+}
+
+static const char *tracefs_available_filter_functions_addrs(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions_addrs"
+			     : TRACEFS"/available_filter_functions_addrs";
+}
+
 static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *kfunc_name, size_t offset)
 {
@@ -10539,25 +10575,158 @@ struct kprobe_multi_resolve {
 	size_t cnt;
 };
 
-static int
-resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
-			const char *sym_name, void *ctx)
+struct avail_kallsyms_data {
+	char **syms;
+	size_t cnt;
+	struct kprobe_multi_resolve *res;
+};
+
+static int avail_func_cmp(const void *a, const void *b)
 {
-	struct kprobe_multi_resolve *res = ctx;
+	return strcmp(*(const char **)a, *(const char **)b);
+}
+
+static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type,
+			     const char *sym_name, void *ctx)
+{
+	struct avail_kallsyms_data *data = ctx;
+	struct kprobe_multi_resolve *res = data->res;
 	int err;
 
-	if (!glob_match(sym_name, res->pattern))
+	if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp))
 		return 0;
 
-	err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long),
-				res->cnt + 1);
+	err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1);
 	if (err)
 		return err;
 
-	res->addrs[res->cnt++] = (unsigned long) sym_addr;
+	res->addrs[res->cnt++] = (unsigned long)sym_addr;
 	return 0;
 }
 
+static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res)
+{
+	const char *available_functions_file = tracefs_available_filter_functions();
+	struct avail_kallsyms_data data;
+	char sym_name[500];
+	FILE *f;
+	int err = 0, ret, i;
+	char **syms = NULL;
+	size_t cap = 0, cnt = 0;
+
+	f = fopen(available_functions_file, "re");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s: %d\n", available_functions_file, err);
+		return err;
+	}
+
+	while (true) {
+		char *name;
+
+		ret = fscanf(f, "%499s%*[^\n]\n", sym_name);
+		if (ret == EOF && feof(f))
+			break;
+
+		if (ret != 1) {
+			pr_warn("failed to parse available_filter_functions entry: %d\n", ret);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (!glob_match(sym_name, res->pattern))
+			continue;
+
+		err = libbpf_ensure_mem((void **)&syms, &cap, sizeof(*syms), cnt + 1);
+		if (err)
+			goto cleanup;
+
+		name = strdup(sym_name);
+		if (!name) {
+			err = -errno;
+			goto cleanup;
+		}
+
+		syms[cnt++] = name;
+	}
+
+	/* no entries found, bail out */
+	if (cnt == 0) {
+		err = -ENOENT;
+		goto cleanup;
+	}
+
+	/* sort available functions */
+	qsort(syms, cnt, sizeof(*syms), avail_func_cmp);
+
+	data.syms = syms;
+	data.res = res;
+	data.cnt = cnt;
+	libbpf_kallsyms_parse(avail_kallsyms_cb, &data);
+
+	if (res->cnt == 0)
+		err = -ENOENT;
+
+cleanup:
+	for (i = 0; i < cnt; i++)
+		free((char *)syms[i]);
+	free(syms);
+
+	fclose(f);
+	return err;
+}
+
+static bool has_available_filter_functions_addrs(void)
+{
+	return access(tracefs_available_filter_functions_addrs(), R_OK) != -1;
+}
+
+static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res)
+{
+	const char *available_path = tracefs_available_filter_functions_addrs();
+	char sym_name[500];
+	FILE *f;
+	int ret, err = 0;
+	unsigned long long sym_addr;
+
+	f = fopen(available_path, "re");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s: %d\n", available_path, err);
+		return err;
+	}
+
+	while (true) {
+		ret = fscanf(f, "%llx %499s%*[^\n]\n", &sym_addr, sym_name);
+		if (ret == EOF && feof(f))
+			break;
+
+		if (ret != 2) {
+			pr_warn("failed to parse available_filter_functions_addrs entry: %d\n",
+				ret);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (!glob_match(sym_name, res->pattern))
+			continue;
+
+		err = libbpf_ensure_mem((void **)&res->addrs, &res->cap,
+					sizeof(*res->addrs), res->cnt + 1);
+		if (err)
+			goto cleanup;
+
+		res->addrs[res->cnt++] = (unsigned long)sym_addr;
+	}
+
+	if (res->cnt == 0)
+		err = -ENOENT;
+
+cleanup:
+	fclose(f);
+	return err;
+}
+
 struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
@@ -10594,13 +10763,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (pattern) {
-		err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
+		if (has_available_filter_functions_addrs())
+			err = libbpf_available_kprobes_parse(&res);
+		else
+			err = libbpf_available_kallsyms_parse(&res);
 		if (err)
 			goto error;
-		if (!res.cnt) {
-			err = -ENOENT;
-			goto error;
-		}
 		addrs = res.addrs;
 		cnt = res.cnt;
 	}
@@ -11811,6 +11979,48 @@ static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_l
 	return libbpf_get_error(*link);
 }
 
+struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog,
+					       const struct bpf_netfilter_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, lopts);
+	struct bpf_link *link;
+	int prog_fd, link_fd;
+
+	if (!OPTS_VALID(opts, bpf_netfilter_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
+	link = calloc(1, sizeof(*link));
+	if (!link)
+		return libbpf_err_ptr(-ENOMEM);
+
+	link->detach = &bpf_link__detach_fd;
+
+	lopts.netfilter.pf = OPTS_GET(opts, pf, 0);
+	lopts.netfilter.hooknum = OPTS_GET(opts, hooknum, 0);
+	lopts.netfilter.priority = OPTS_GET(opts, priority, 0);
+	lopts.netfilter.flags = OPTS_GET(opts, flags, 0);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts);
+	if (link_fd < 0) {
+		char errmsg[STRERR_BUFSIZE];
+
+		link_fd = -errno;
+		free(link);
+		pr_warn("prog '%s': failed to attach to netfilter: %s\n",
+			prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
+		return libbpf_err_ptr(link_fd);
+	}
+	link->fd = link_fd;
+
+	return link;
+}
+
 struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 {
 	struct bpf_link *link = NULL;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 754da73c643b..10642ad69d76 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -718,6 +718,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
+struct bpf_netfilter_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+
+	__u32 pf;
+	__u32 hooknum;
+	__s32 priority;
+	__u32 flags;
+};
+#define bpf_netfilter_opts__last_field flags
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netfilter(const struct bpf_program *prog,
+			      const struct bpf_netfilter_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 7521a2fb7626..d9ec4407befa 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -395,4 +395,5 @@ LIBBPF_1.2.0 {
 LIBBPF_1.3.0 {
 	global:
 		bpf_obj_pin_opts;
+		bpf_program__attach_netfilter;
 } LIBBPF_1.2.0;
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index f1a141555f08..37455d00b239 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -852,8 +852,11 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 		 * system is so exhausted on memory, it's the least of user's
 		 * concerns, probably.
 		 * So just do our best here to return those IDs to usdt_manager.
+		 * Another edge case when we can legitimately get NULL is when
+		 * new_cnt is zero, which can happen in some edge cases, so we
+		 * need to be careful about that.
 		 */
-		if (new_free_ids) {
+		if (new_free_ids || new_cnt == 0) {
 			memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids,
 			       usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids));
 			man->free_spec_ids = new_free_ids;