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

Andrii Nakryiko says:

====================
bpf-next 2021-12-10 v2

We've added 115 non-merge commits during the last 26 day(s) which contain
a total of 182 files changed, 5747 insertions(+), 2564 deletions(-).

The main changes are:

1) Various samples fixes, from Alexander Lobakin.

2) BPF CO-RE support in kernel and light skeleton, from Alexei Starovoitov.

3) A batch of new unified APIs for libbpf, logging improvements, version
   querying, etc. Also a batch of old deprecations for old APIs and various
   bug fixes, in preparation for libbpf 1.0, from Andrii Nakryiko.

4) BPF documentation reorganization and improvements, from Christoph Hellwig
   and Dave Tucker.

5) Support for declarative initialization of BPF_MAP_TYPE_PROG_ARRAY in
   libbpf, from Hengqi Chen.

6) Verifier log fixes, from Hou Tao.

7) Runtime-bounded loops support with bpf_loop() helper, from Joanne Koong.

8) Extend branch record capturing to all platforms that support it,
   from Kajol Jain.

9) Light skeleton codegen improvements, from Kumar Kartikeya Dwivedi.

10) bpftool doc-generating script improvements, from Quentin Monnet.

11) Two libbpf v0.6 bug fixes, from Shuyi Cheng and Vincent Minet.

12) Deprecation warning fix for perf/bpf_counter, from Song Liu.

13) MAX_TAIL_CALL_CNT unification and MIPS build fix for libbpf,
    from Tiezhu Yang.

14) BTF_KING_TYPE_TAG follow-up fixes, from Yonghong Song.

15) Selftests fixes and improvements, from Ilya Leoshkevich, Jean-Philippe
    Brucker, Jiri Olsa, Maxim Mikityanskiy, Tirthendu Sarkar, Yucong Sun,
    and others.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (115 commits)
  libbpf: Add "bool skipped" to struct bpf_map
  libbpf: Fix typo in btf__dedup@LIBBPF_0.0.2 definition
  bpftool: Switch bpf_object__load_xattr() to bpf_object__load()
  selftests/bpf: Remove the only use of deprecated bpf_object__load_xattr()
  selftests/bpf: Add test for libbpf's custom log_buf behavior
  selftests/bpf: Replace all uses of bpf_load_btf() with bpf_btf_load()
  libbpf: Deprecate bpf_object__load_xattr()
  libbpf: Add per-program log buffer setter and getter
  libbpf: Preserve kernel error code and remove kprobe prog type guessing
  libbpf: Improve logging around BPF program loading
  libbpf: Allow passing user log setting through bpf_object_open_opts
  libbpf: Allow passing preallocated log_buf when loading BTF into kernel
  libbpf: Add OPTS-based bpf_btf_load() API
  libbpf: Fix bpf_prog_load() log_buf logic for log_level 0
  samples/bpf: Remove unneeded variable
  bpf: Remove redundant assignment to pointer t
  selftests/bpf: Fix a compilation warning
  perf/bpf_counter: Use bpf_map_create instead of bpf_create_map
  samples: bpf: Fix 'unknown warning group' build warning on Clang
  samples: bpf: Fix xdp_sample_user.o linking with Clang
  ...
====================

Link: https://lore.kernel.org/r/20211210234746.2100561-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 398 insertions, 12 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 48cdf5b425a7..8b00c6e4d6fb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -25,6 +25,7 @@
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <net/sock.h>
+#include "../tools/lib/bpf/relo_core.h"
 
 /* BTF (BPF Type Format) is the meta data format which describes
  * the data types of BPF program/map.  Hence, it basically focus
@@ -836,7 +837,7 @@ static const char *btf_show_name(struct btf_show *show)
 	const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)];
 	const char *name = NULL, *prefix = "", *parens = "";
 	const struct btf_member *m = show->state.member;
-	const struct btf_type *t = show->state.type;
+	const struct btf_type *t;
 	const struct btf_array *array;
 	u32 id = show->state.type_id;
 	const char *member = NULL;
@@ -2969,7 +2970,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
-		offset = btf_member_bit_offset(t, member);
+		offset = __btf_member_bit_offset(t, member);
 		if (is_union && offset) {
 			btf_verifier_log_member(env, t, member,
 						"Invalid member bits_offset");
@@ -3094,7 +3095,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t
 		if (off != -ENOENT)
 			/* only one such field is allowed */
 			return -E2BIG;
-		off = btf_member_bit_offset(t, member);
+		off = __btf_member_bit_offset(t, member);
 		if (off % 8)
 			/* valid C code cannot generate such BTF */
 			return -EINVAL;
@@ -3184,8 +3185,8 @@ static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
 
 		btf_show_start_member(show, member);
 
-		member_offset = btf_member_bit_offset(t, member);
-		bitfield_size = btf_member_bitfield_size(t, member);
+		member_offset = __btf_member_bit_offset(t, member);
+		bitfield_size = __btf_member_bitfield_size(t, member);
 		bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
 		bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		if (bitfield_size) {
@@ -4472,8 +4473,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 		log->len_total = log_size;
 
 		/* log attributes have to be sane */
-		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
-		    !log->level || !log->ubuf) {
+		if (!bpf_verifier_log_attr_valid(log)) {
 			err = -EINVAL;
 			goto errout;
 		}
@@ -5060,7 +5060,7 @@ again:
 		if (array_elem->nelems != 0)
 			goto error;
 
-		moff = btf_member_bit_offset(t, member) / 8;
+		moff = __btf_member_bit_offset(t, member) / 8;
 		if (off < moff)
 			goto error;
 
@@ -5083,14 +5083,14 @@ error:
 
 	for_each_member(i, t, member) {
 		/* offset of the field in bytes */
-		moff = btf_member_bit_offset(t, member) / 8;
+		moff = __btf_member_bit_offset(t, member) / 8;
 		if (off + size <= moff)
 			/* won't find anything, field is already too far */
 			break;
 
-		if (btf_member_bitfield_size(t, member)) {
-			u32 end_bit = btf_member_bit_offset(t, member) +
-				btf_member_bitfield_size(t, member);
+		if (__btf_member_bitfield_size(t, member)) {
+			u32 end_bit = __btf_member_bit_offset(t, member) +
+				__btf_member_bitfield_size(t, member);
 
 			/* off <= moff instead of off == moff because clang
 			 * does not generate a BTF member for anonymous
@@ -6169,6 +6169,8 @@ btf_module_read(struct file *file, struct kobject *kobj,
 	return len;
 }
 
+static void purge_cand_cache(struct btf *btf);
+
 static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			     void *module)
 {
@@ -6203,6 +6205,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			goto out;
 		}
 
+		purge_cand_cache(NULL);
 		mutex_lock(&btf_module_mutex);
 		btf_mod->module = module;
 		btf_mod->btf = btf;
@@ -6245,6 +6248,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			list_del(&btf_mod->list);
 			if (btf_mod->sysfs_attr)
 				sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
+			purge_cand_cache(btf_mod->btf);
 			btf_put(btf_mod->btf);
 			kfree(btf_mod->sysfs_attr);
 			kfree(btf_mod);
@@ -6406,3 +6410,385 @@ DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
 DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
 
 #endif
+
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+			      const struct btf *targ_btf, __u32 targ_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static bool bpf_core_is_flavor_sep(const char *s)
+{
+	/* check X___Y name pattern, where X and Y are not underscores */
+	return s[0] != '_' &&				      /* X */
+	       s[1] == '_' && s[2] == '_' && s[3] == '_' &&   /* ___ */
+	       s[4] != '_';				      /* Y */
+}
+
+size_t bpf_core_essential_name_len(const char *name)
+{
+	size_t n = strlen(name);
+	int i;
+
+	for (i = n - 5; i >= 0; i--) {
+		if (bpf_core_is_flavor_sep(name + i))
+			return i + 1;
+	}
+	return n;
+}
+
+struct bpf_cand_cache {
+	const char *name;
+	u32 name_len;
+	u16 kind;
+	u16 cnt;
+	struct {
+		const struct btf *btf;
+		u32 id;
+	} cands[];
+};
+
+static void bpf_free_cands(struct bpf_cand_cache *cands)
+{
+	if (!cands->cnt)
+		/* empty candidate array was allocated on stack */
+		return;
+	kfree(cands);
+}
+
+static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands)
+{
+	kfree(cands->name);
+	kfree(cands);
+}
+
+#define VMLINUX_CAND_CACHE_SIZE 31
+static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE];
+
+#define MODULE_CAND_CACHE_SIZE 31
+static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE];
+
+static DEFINE_MUTEX(cand_cache_mutex);
+
+static void __print_cand_cache(struct bpf_verifier_log *log,
+			       struct bpf_cand_cache **cache,
+			       int cache_size)
+{
+	struct bpf_cand_cache *cc;
+	int i, j;
+
+	for (i = 0; i < cache_size; i++) {
+		cc = cache[i];
+		if (!cc)
+			continue;
+		bpf_log(log, "[%d]%s(", i, cc->name);
+		for (j = 0; j < cc->cnt; j++) {
+			bpf_log(log, "%d", cc->cands[j].id);
+			if (j < cc->cnt - 1)
+				bpf_log(log, " ");
+		}
+		bpf_log(log, "), ");
+	}
+}
+
+static void print_cand_cache(struct bpf_verifier_log *log)
+{
+	mutex_lock(&cand_cache_mutex);
+	bpf_log(log, "vmlinux_cand_cache:");
+	__print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
+	bpf_log(log, "\nmodule_cand_cache:");
+	__print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+	bpf_log(log, "\n");
+	mutex_unlock(&cand_cache_mutex);
+}
+
+static u32 hash_cands(struct bpf_cand_cache *cands)
+{
+	return jhash(cands->name, cands->name_len, 0);
+}
+
+static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands,
+					       struct bpf_cand_cache **cache,
+					       int cache_size)
+{
+	struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size];
+
+	if (cc && cc->name_len == cands->name_len &&
+	    !strncmp(cc->name, cands->name, cands->name_len))
+		return cc;
+	return NULL;
+}
+
+static size_t sizeof_cands(int cnt)
+{
+	return offsetof(struct bpf_cand_cache, cands[cnt]);
+}
+
+static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
+						  struct bpf_cand_cache **cache,
+						  int cache_size)
+{
+	struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands;
+
+	if (*cc) {
+		bpf_free_cands_from_cache(*cc);
+		*cc = NULL;
+	}
+	new_cands = kmalloc(sizeof_cands(cands->cnt), GFP_KERNEL);
+	if (!new_cands) {
+		bpf_free_cands(cands);
+		return ERR_PTR(-ENOMEM);
+	}
+	memcpy(new_cands, cands, sizeof_cands(cands->cnt));
+	/* strdup the name, since it will stay in cache.
+	 * the cands->name points to strings in prog's BTF and the prog can be unloaded.
+	 */
+	new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL);
+	bpf_free_cands(cands);
+	if (!new_cands->name) {
+		kfree(new_cands);
+		return ERR_PTR(-ENOMEM);
+	}
+	*cc = new_cands;
+	return new_cands;
+}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache,
+			       int cache_size)
+{
+	struct bpf_cand_cache *cc;
+	int i, j;
+
+	for (i = 0; i < cache_size; i++) {
+		cc = cache[i];
+		if (!cc)
+			continue;
+		if (!btf) {
+			/* when new module is loaded purge all of module_cand_cache,
+			 * since new module might have candidates with the name
+			 * that matches cached cands.
+			 */
+			bpf_free_cands_from_cache(cc);
+			cache[i] = NULL;
+			continue;
+		}
+		/* when module is unloaded purge cache entries
+		 * that match module's btf
+		 */
+		for (j = 0; j < cc->cnt; j++)
+			if (cc->cands[j].btf == btf) {
+				bpf_free_cands_from_cache(cc);
+				cache[i] = NULL;
+				break;
+			}
+	}
+
+}
+
+static void purge_cand_cache(struct btf *btf)
+{
+	mutex_lock(&cand_cache_mutex);
+	__purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+	mutex_unlock(&cand_cache_mutex);
+}
+#endif
+
+static struct bpf_cand_cache *
+bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf,
+		   int targ_start_id)
+{
+	struct bpf_cand_cache *new_cands;
+	const struct btf_type *t;
+	const char *targ_name;
+	size_t targ_essent_len;
+	int n, i;
+
+	n = btf_nr_types(targ_btf);
+	for (i = targ_start_id; i < n; i++) {
+		t = btf_type_by_id(targ_btf, i);
+		if (btf_kind(t) != cands->kind)
+			continue;
+
+		targ_name = btf_name_by_offset(targ_btf, t->name_off);
+		if (!targ_name)
+			continue;
+
+		/* the resched point is before strncmp to make sure that search
+		 * for non-existing name will have a chance to schedule().
+		 */
+		cond_resched();
+
+		if (strncmp(cands->name, targ_name, cands->name_len) != 0)
+			continue;
+
+		targ_essent_len = bpf_core_essential_name_len(targ_name);
+		if (targ_essent_len != cands->name_len)
+			continue;
+
+		/* most of the time there is only one candidate for a given kind+name pair */
+		new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL);
+		if (!new_cands) {
+			bpf_free_cands(cands);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		memcpy(new_cands, cands, sizeof_cands(cands->cnt));
+		bpf_free_cands(cands);
+		cands = new_cands;
+		cands->cands[cands->cnt].btf = targ_btf;
+		cands->cands[cands->cnt].id = i;
+		cands->cnt++;
+	}
+	return cands;
+}
+
+static struct bpf_cand_cache *
+bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id)
+{
+	struct bpf_cand_cache *cands, *cc, local_cand = {};
+	const struct btf *local_btf = ctx->btf;
+	const struct btf_type *local_type;
+	const struct btf *main_btf;
+	size_t local_essent_len;
+	struct btf *mod_btf;
+	const char *name;
+	int id;
+
+	main_btf = bpf_get_btf_vmlinux();
+	if (IS_ERR(main_btf))
+		return (void *)main_btf;
+
+	local_type = btf_type_by_id(local_btf, local_type_id);
+	if (!local_type)
+		return ERR_PTR(-EINVAL);
+
+	name = btf_name_by_offset(local_btf, local_type->name_off);
+	if (str_is_empty(name))
+		return ERR_PTR(-EINVAL);
+	local_essent_len = bpf_core_essential_name_len(name);
+
+	cands = &local_cand;
+	cands->name = name;
+	cands->kind = btf_kind(local_type);
+	cands->name_len = local_essent_len;
+
+	cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
+	/* cands is a pointer to stack here */
+	if (cc) {
+		if (cc->cnt)
+			return cc;
+		goto check_modules;
+	}
+
+	/* Attempt to find target candidates in vmlinux BTF first */
+	cands = bpf_core_add_cands(cands, main_btf, 1);
+	if (IS_ERR(cands))
+		return cands;
+
+	/* cands is a pointer to kmalloced memory here if cands->cnt > 0 */
+
+	/* populate cache even when cands->cnt == 0 */
+	cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
+	if (IS_ERR(cc))
+		return cc;
+
+	/* if vmlinux BTF has any candidate, don't go for module BTFs */
+	if (cc->cnt)
+		return cc;
+
+check_modules:
+	/* cands is a pointer to stack here and cands->cnt == 0 */
+	cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+	if (cc)
+		/* if cache has it return it even if cc->cnt == 0 */
+		return cc;
+
+	/* If candidate is not found in vmlinux's BTF then search in module's BTFs */
+	spin_lock_bh(&btf_idr_lock);
+	idr_for_each_entry(&btf_idr, mod_btf, id) {
+		if (!btf_is_module(mod_btf))
+			continue;
+		/* linear search could be slow hence unlock/lock
+		 * the IDR to avoiding holding it for too long
+		 */
+		btf_get(mod_btf);
+		spin_unlock_bh(&btf_idr_lock);
+		cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf));
+		if (IS_ERR(cands)) {
+			btf_put(mod_btf);
+			return cands;
+		}
+		spin_lock_bh(&btf_idr_lock);
+		btf_put(mod_btf);
+	}
+	spin_unlock_bh(&btf_idr_lock);
+	/* cands is a pointer to kmalloced memory here if cands->cnt > 0
+	 * or pointer to stack if cands->cnd == 0.
+	 * Copy it into the cache even when cands->cnt == 0 and
+	 * return the result.
+	 */
+	return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE);
+}
+
+int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
+		   int relo_idx, void *insn)
+{
+	bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL;
+	struct bpf_core_cand_list cands = {};
+	struct bpf_core_spec *specs;
+	int err;
+
+	/* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5"
+	 * into arrays of btf_ids of struct fields and array indices.
+	 */
+	specs = kcalloc(3, sizeof(*specs), GFP_KERNEL);
+	if (!specs)
+		return -ENOMEM;
+
+	if (need_cands) {
+		struct bpf_cand_cache *cc;
+		int i;
+
+		mutex_lock(&cand_cache_mutex);
+		cc = bpf_core_find_cands(ctx, relo->type_id);
+		if (IS_ERR(cc)) {
+			bpf_log(ctx->log, "target candidate search failed for %d\n",
+				relo->type_id);
+			err = PTR_ERR(cc);
+			goto out;
+		}
+		if (cc->cnt) {
+			cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL);
+			if (!cands.cands) {
+				err = -ENOMEM;
+				goto out;
+			}
+		}
+		for (i = 0; i < cc->cnt; i++) {
+			bpf_log(ctx->log,
+				"CO-RE relocating %s %s: found target candidate [%d]\n",
+				btf_kind_str[cc->kind], cc->name, cc->cands[i].id);
+			cands.cands[i].btf = cc->cands[i].btf;
+			cands.cands[i].id = cc->cands[i].id;
+		}
+		cands.len = cc->cnt;
+		/* cand_cache_mutex needs to span the cache lookup and
+		 * copy of btf pointer into bpf_core_cand_list,
+		 * since module can be unloaded while bpf_core_apply_relo_insn
+		 * is working with module's btf.
+		 */
+	}
+
+	err = bpf_core_apply_relo_insn((void *)ctx->log, insn, relo->insn_off / 8,
+				       relo, relo_idx, ctx->btf, &cands, specs);
+out:
+	kfree(specs);
+	if (need_cands) {
+		kfree(cands.cands);
+		mutex_unlock(&cand_cache_mutex);
+		if (ctx->log->level & BPF_LOG_LEVEL2)
+			print_cand_cache(ctx->log);
+	}
+	return err;
+}