From bbaf1ff06af49e856501024abbe161d96c1f0d66 Mon Sep 17 00:00:00 2001
From: Fangrui Song <maskray@google.com>
Date: Sat, 24 Jun 2023 00:18:56 +0000
Subject: bpf: Replace deprecated -target with --target= for Clang

The -target option has been deprecated since clang 3.4 in 2013. Therefore, use
the preferred --target=bpf form instead. This also matches how we use --target=
in scripts/Makefile.clang.

Signed-off-by: Fangrui Song <maskray@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://github.com/llvm/llvm-project/commit/274b6f0c87a6a1798de0a68135afc7f95def6277
Link: https://lore.kernel.org/bpf/20230624001856.1903733-1-maskray@google.com
---
 kernel/bpf/preload/iterators/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile
index 8937dc6bc8d0..b83c2f5e9be1 100644
--- a/kernel/bpf/preload/iterators/Makefile
+++ b/kernel/bpf/preload/iterators/Makefile
@@ -50,7 +50,7 @@ iterators.lskel-%.h: $(OUTPUT)/%/iterators.bpf.o | $(BPFTOOL)
 $(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BPF,$@)
 	$(Q)mkdir -p $(@D)
-	$(Q)$(CLANG) -g -O2 -target bpf -m$* $(INCLUDES)		      \
+	$(Q)$(CLANG) -g -O2 --target=bpf -m$* $(INCLUDES)		      \
 		 -c $(filter %.c,$^) -o $@ &&				      \
 	$(LLVM_STRIP) -g $@
 
-- 
cgit v1.2.3


From 819d43428a8661abccf8b9ecad94c7e6f23a0024 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 26 Jun 2023 14:25:21 -0700
Subject: bpf: Resolve modifiers when walking structs

It is impossible to use skb_frag_t in the tracing program. Resolve typedefs
when walking structs.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20230626212522.2414485-1-sdf@google.com
---
 kernel/bpf/btf.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel')

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 29fe21099298..3dd47451f097 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6135,6 +6135,8 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 
 	*flag = 0;
 again:
+	if (btf_type_is_modifier(t))
+		t = btf_type_skip_modifiers(btf, t->type, NULL);
 	tname = __btf_name_by_offset(btf, t->name_off);
 	if (!btf_type_is_struct(t)) {
 		bpf_log(log, "Type '%s' is not a struct\n", tname);
-- 
cgit v1.2.3


From cf6eeb8f9dace014f63a3b2e959d0922bf737233 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Tue, 4 Jul 2023 15:40:14 +0800
Subject: bpf: Remove unnecessary ring buffer size check

The theoretical maximum size of ring buffer is about 64GB, but now the
size of ring buffer is specified by max_entries in bpf_attr and its
maximum value is (4GB - 1), and it won't be possible for overflow.

So just remove the unnecessary size check in ringbuf_map_alloc() but
keep the comments for possible extension in future.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Closes: https://lore.kernel.org/bpf/9c636a63-1f3d-442d-9223-96c2dccb9469@moroto.mountain
Link: https://lore.kernel.org/bpf/20230704074014.216616-1-houtao@huaweicloud.com
---
 kernel/bpf/ringbuf.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 875ac9b698d9..f045fde632e5 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -23,15 +23,6 @@
 
 #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4)
 
-/* Maximum size of ring buffer area is limited by 32-bit page offset within
- * record header, counted in pages. Reserve 8 bits for extensibility, and take
- * into account few extra pages for consumer/producer pages and
- * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single
- * ring buffer.
- */
-#define RINGBUF_MAX_DATA_SZ \
-	(((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
-
 struct bpf_ringbuf {
 	wait_queue_head_t waitq;
 	struct irq_work work;
@@ -161,6 +152,17 @@ static void bpf_ringbuf_notify(struct irq_work *work)
 	wake_up_all(&rb->waitq);
 }
 
+/* Maximum size of ring buffer area is limited by 32-bit page offset within
+ * record header, counted in pages. Reserve 8 bits for extensibility, and
+ * take into account few extra pages for consumer/producer pages and
+ * non-mmap()'able parts, the current maximum size would be:
+ *
+ *     (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
+ *
+ * This gives 64GB limit, which seems plenty for single ring buffer. Now
+ * considering that the maximum value of data_sz is (4GB - 1), there
+ * will be no overflow, so just note the size limit in the comments.
+ */
 static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 {
 	struct bpf_ringbuf *rb;
@@ -193,12 +195,6 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
 	    !PAGE_ALIGNED(attr->max_entries))
 		return ERR_PTR(-EINVAL);
 
-#ifdef CONFIG_64BIT
-	/* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */
-	if (attr->max_entries > RINGBUF_MAX_DATA_SZ)
-		return ERR_PTR(-E2BIG);
-#endif
-
 	rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE);
 	if (!rb_map)
 		return ERR_PTR(-ENOMEM);
-- 
cgit v1.2.3


From 803370d3d37579e080e8c59f2360a072d0e45aff Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:29 +0000
Subject: bpf: add a new kfunc to return current bpf_map elements count

A bpf_map_sum_elem_count kfunc was added to simplify getting the sum of the map
per-cpu element counters. If a map doesn't implement the counter, then the
function will always return 0.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-3-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/map_iter.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index b0fa190b0979..d06d3b7150e5 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -93,7 +93,7 @@ static struct bpf_iter_reg bpf_map_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map, map),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &bpf_map_seq_info,
 };
@@ -193,3 +193,40 @@ static int __init bpf_map_iter_init(void)
 }
 
 late_initcall(bpf_map_iter_init);
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc s64 bpf_map_sum_elem_count(struct bpf_map *map)
+{
+	s64 *pcount;
+	s64 ret = 0;
+	int cpu;
+
+	if (!map || !map->elem_count)
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		pcount = per_cpu_ptr(map->elem_count, cpu);
+		ret += READ_ONCE(*pcount);
+	}
+	return ret;
+}
+
+__diag_pop();
+
+BTF_SET8_START(bpf_map_iter_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
+BTF_SET8_END(bpf_map_iter_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_map_iter_kfunc_ids,
+};
+
+static int init_subsystem(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_map_iter_kfunc_set);
+}
+late_initcall(init_subsystem);
-- 
cgit v1.2.3


From 9bc421b6be955c0960356210960d82707aa009e8 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:30 +0000
Subject: bpf: populate the per-cpu insertions/deletions counters for hashmaps

Initialize and utilize the per-cpu insertions/deletions counters for hash-based
maps. Non-trivial changes only apply to the preallocated maps for which the
{inc,dec}_elem_count functions are not called, as there's no need in counting
elements to sustain proper map operations.

To increase/decrease percpu counters for preallocated maps we add raw calls to
the bpf_map_{inc,dec}_elem_count functions so that the impact is minimal. For
dynamically allocated maps we add corresponding calls to the existing
{inc,dec}_elem_count functions.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-4-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/hashtab.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 56d3da7d0bc6..a8c7e1c5abfa 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -302,6 +302,7 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 	struct htab_elem *l;
 
 	if (node) {
+		bpf_map_inc_elem_count(&htab->map);
 		l = container_of(node, struct htab_elem, lru_node);
 		memcpy(l->key, key, htab->map.key_size);
 		return l;
@@ -510,12 +511,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
 		goto free_htab;
 
+	err = bpf_map_init_elem_count(&htab->map);
+	if (err)
+		goto free_htab;
+
 	err = -ENOMEM;
 	htab->buckets = bpf_map_area_alloc(htab->n_buckets *
 					   sizeof(struct bucket),
 					   htab->map.numa_node);
 	if (!htab->buckets)
-		goto free_htab;
+		goto free_elem_count;
 
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
 		htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map,
@@ -593,6 +598,8 @@ free_map_locked:
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);
 	bpf_mem_alloc_destroy(&htab->ma);
+free_elem_count:
+	bpf_map_free_elem_count(&htab->map);
 free_htab:
 	lockdep_unregister_key(&htab->lockdep_key);
 	bpf_map_area_free(htab);
@@ -804,6 +811,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 		if (l == tgt_l) {
 			hlist_nulls_del_rcu(&l->hash_node);
 			check_and_free_fields(htab, l);
+			bpf_map_dec_elem_count(&htab->map);
 			break;
 		}
 
@@ -900,6 +908,8 @@ static bool is_map_full(struct bpf_htab *htab)
 
 static void inc_elem_count(struct bpf_htab *htab)
 {
+	bpf_map_inc_elem_count(&htab->map);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_add_batch(&htab->pcount, 1, PERCPU_COUNTER_BATCH);
 	else
@@ -908,6 +918,8 @@ static void inc_elem_count(struct bpf_htab *htab)
 
 static void dec_elem_count(struct bpf_htab *htab)
 {
+	bpf_map_dec_elem_count(&htab->map);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_add_batch(&htab->pcount, -1, PERCPU_COUNTER_BATCH);
 	else
@@ -920,6 +932,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
+		bpf_map_dec_elem_count(&htab->map);
 		check_and_free_fields(htab, l);
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
@@ -1000,6 +1013,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			if (!l)
 				return ERR_PTR(-E2BIG);
 			l_new = container_of(l, struct htab_elem, fnode);
+			bpf_map_inc_elem_count(&htab->map);
 		}
 	} else {
 		if (is_map_full(htab))
@@ -1168,6 +1182,7 @@ err:
 static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
 {
 	check_and_free_fields(htab, elem);
+	bpf_map_dec_elem_count(&htab->map);
 	bpf_lru_push_free(&htab->lru, &elem->lru_node);
 }
 
@@ -1357,8 +1372,10 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 err:
 	htab_unlock_bucket(htab, b, hash, flags);
 err_lock_bucket:
-	if (l_new)
+	if (l_new) {
+		bpf_map_dec_elem_count(&htab->map);
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+	}
 	return ret;
 }
 
@@ -1523,6 +1540,7 @@ static void htab_map_free(struct bpf_map *map)
 		prealloc_destroy(htab);
 	}
 
+	bpf_map_free_elem_count(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);
-- 
cgit v1.2.3


From 515ee52b2224f73f63ac031cbf400cd513d2f45b Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 6 Jul 2023 13:39:31 +0000
Subject: bpf: make preloaded map iterators to display map elements count

Add another column to the /sys/fs/bpf/maps.debug iterator to display
cur_entries, the current number of entries in the map as is returned
by the bpf_map_sum_elem_count kfunc. Also fix formatting.

Example:

    # cat /sys/fs/bpf/maps.debug
      id name             max_entries  cur_entries
       2 iterator.rodata            1            0
     125 cilium_auth_map       524288          666
     126 cilium_runtime_          256            0
     127 cilium_signals            32            0
     128 cilium_node_map        16384         1344
     129 cilium_events             32            0
     ...

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Link: https://lore.kernel.org/r/20230706133932.45883-5-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/preload/iterators/iterators.bpf.c       |   9 +-
 .../iterators/iterators.lskel-little-endian.h      | 526 +++++++++++----------
 2 files changed, 275 insertions(+), 260 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 03af863314ea..b78968b63fab 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -73,6 +73,8 @@ static const char *get_name(struct btf *btf, long btf_id, const char *fallback)
 	return str + name_off;
 }
 
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
 SEC("iter/bpf_map")
 int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 {
@@ -84,9 +86,12 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 		return 0;
 
 	if (seq_num == 0)
-		BPF_SEQ_PRINTF(seq, "  id name             max_entries\n");
+		BPF_SEQ_PRINTF(seq, "  id name             max_entries  cur_entries\n");
+
+	BPF_SEQ_PRINTF(seq, "%4u %-16s  %10d   %10lld\n",
+		       map->id, map->name, map->max_entries,
+		       bpf_map_sum_elem_count(map));
 
-	BPF_SEQ_PRINTF(seq, "%4u %-16s%6d\n", map->id, map->name, map->max_entries);
 	return 0;
 }
 
diff --git a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
index 70f236a82fe1..5b98ab02025e 100644
--- a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
+++ b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-/* THIS FILE IS AUTOGENERATED! */
+/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */
 #ifndef __ITERATORS_BPF_SKEL_H__
 #define __ITERATORS_BPF_SKEL_H__
 
@@ -18,8 +18,6 @@ struct iterators_bpf {
 		int dump_bpf_map_fd;
 		int dump_bpf_prog_fd;
 	} links;
-	struct iterators_bpf__rodata {
-	} *rodata;
 };
 
 static inline int
@@ -68,7 +66,6 @@ iterators_bpf__destroy(struct iterators_bpf *skel)
 	iterators_bpf__detach(skel);
 	skel_closenz(skel->progs.dump_bpf_map.prog_fd);
 	skel_closenz(skel->progs.dump_bpf_prog.prog_fd);
-	skel_free_map_data(skel->rodata, skel->maps.rodata.initial_value, 4096);
 	skel_closenz(skel->maps.rodata.map_fd);
 	skel_free(skel);
 }
@@ -81,15 +78,6 @@ iterators_bpf__open(void)
 	if (!skel)
 		goto cleanup;
 	skel->ctx.sz = (void *)&skel->links - (void *)skel;
-	skel->rodata = skel_prep_map_data((void *)"\
-\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\
-\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\
-\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0", 4096, 98);
-	if (!skel->rodata)
-		goto cleanup;
-	skel->maps.rodata.initial_value = (__u64) (long) skel->rodata;
 	return skel;
 cleanup:
 	iterators_bpf__destroy(skel);
@@ -103,7 +91,7 @@ iterators_bpf__load(struct iterators_bpf *skel)
 	int err;
 
 	opts.ctx = (struct bpf_loader_ctx *)skel;
-	opts.data_sz = 6056;
+	opts.data_sz = 6208;
 	opts.data = (void *)"\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
@@ -138,190 +126,197 @@ iterators_bpf__load(struct iterators_bpf *skel)
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9f\xeb\x01\0\
-\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\xf9\x04\0\0\0\0\0\0\0\0\0\x02\x02\0\
+\x18\0\0\0\0\0\0\0\x80\x04\0\0\x80\x04\0\0\x31\x05\0\0\0\0\0\0\0\0\0\x02\x02\0\
 \0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\0\x04\
 \0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\0\0\0\0\0\
 \0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\0\0\0\x20\
-\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\0\0\xb1\0\
-\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\0\0\x80\0\
-\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\0\0\0\0\
-\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x94\x01\0\0\x03\0\0\x04\
-\x18\0\0\0\x9c\x01\0\0\x0e\0\0\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xa4\
-\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb0\x01\0\0\0\0\0\x08\x0f\0\0\0\xb6\x01\0\0\0\0\0\
-\x01\x04\0\0\0\x20\0\0\0\xc3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\
-\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xc8\x01\0\0\0\0\0\x01\x04\0\0\0\
-\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x2c\x02\0\0\x02\0\0\x04\x10\0\0\0\x13\0\
-\0\0\x03\0\0\0\0\0\0\0\x3f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x18\0\
-\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x44\x02\0\0\x01\0\0\x0c\
-\x16\0\0\0\x90\x02\0\0\x01\0\0\x04\x08\0\0\0\x99\x02\0\0\x19\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x02\x1a\0\0\0\xea\x02\0\0\x06\0\0\x04\x38\0\0\0\x9c\x01\0\0\x0e\0\0\
-\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xf7\x02\0\0\x1b\0\0\0\xc0\0\0\0\x08\
-\x03\0\0\x15\0\0\0\0\x01\0\0\x11\x03\0\0\x1d\0\0\0\x40\x01\0\0\x1b\x03\0\0\x1e\
-\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\0\0\0\0\
-\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x65\x03\0\0\x02\0\0\x04\
-\x08\0\0\0\x73\x03\0\0\x0e\0\0\0\0\0\0\0\x7c\x03\0\0\x0e\0\0\0\x20\0\0\0\x1b\
-\x03\0\0\x03\0\0\x04\x18\0\0\0\x86\x03\0\0\x1b\0\0\0\0\0\0\0\x8e\x03\0\0\x21\0\
-\0\0\x40\0\0\0\x94\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\0\0\0\
-\0\0\0\0\0\x02\x24\0\0\0\x98\x03\0\0\x01\0\0\x04\x04\0\0\0\xa3\x03\0\0\x0e\0\0\
-\0\0\0\0\0\x0c\x04\0\0\x01\0\0\x04\x04\0\0\0\x15\x04\0\0\x0e\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x8b\x04\0\0\0\0\0\x0e\x25\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\x9f\x04\
-\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\
-\x20\0\0\0\xb5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\
-\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xca\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe1\x04\0\0\0\0\0\x0e\x2d\0\0\
-\0\x01\0\0\0\xe9\x04\0\0\x04\0\0\x0f\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\x28\
-\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\0\
-\x11\0\0\0\xf1\x04\0\0\x01\0\0\x0f\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\x62\
-\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\
-\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
-\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\
-\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\x65\
-\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\
-\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\
-\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\
-\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\
-\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\
-\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\
-\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\
-\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\
-\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\
-\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\
-\x29\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\
-\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x30\
-\x3a\x32\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\
-\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\
-\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\
-\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\
-\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\
-\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\
-\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\
-\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\
-\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\
-\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\
-\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\
-\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\
-\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\
-\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\
-\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\
-\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\
-\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\
-\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\
-\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\
-\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\
-\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\
-\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\
-\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\
-\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\
-\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
-\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\
-\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\
-\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\
-\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\
-\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\
-\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\
-\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\
-\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\
-\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\
-\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\
-\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\
-\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\
-\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\
-\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
-\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\
-\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\
-\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
-\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
-\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\
-\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2d\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\
-\0\x04\0\0\0\x62\0\0\0\x01\0\0\0\x80\x04\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\
-\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\
-\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\
-\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\
-\x25\x73\x20\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\
-\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1b\0\0\
-\0\0\0\x79\x11\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\
-\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\
-\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\
-\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\
-\x7b\x1a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\
-\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x23\0\0\0\xb7\x03\0\0\x0e\0\0\0\
-\xb7\x05\0\0\x18\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\
-\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x3c\x01\0\x01\0\0\0\x42\0\0\
-\0\x7b\0\0\0\x24\x3c\x01\0\x02\0\0\0\x42\0\0\0\xee\0\0\0\x1d\x44\x01\0\x03\0\0\
-\0\x42\0\0\0\x0f\x01\0\0\x06\x4c\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\x40\
-\x01\0\x05\0\0\0\x42\0\0\0\x1a\x01\0\0\x1d\x40\x01\0\x06\0\0\0\x42\0\0\0\x43\
-\x01\0\0\x06\x58\x01\0\x08\0\0\0\x42\0\0\0\x56\x01\0\0\x03\x5c\x01\0\x0f\0\0\0\
-\x42\0\0\0\xdc\x01\0\0\x02\x64\x01\0\x1f\0\0\0\x42\0\0\0\x2a\x02\0\0\x01\x6c\
-\x01\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\
-\0\x10\0\0\0\x02\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\
-\x28\0\0\0\x08\0\0\0\x3f\x01\0\0\0\0\0\0\x78\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\
-\x88\0\0\0\x0d\0\0\0\xea\0\0\0\0\0\0\0\xa8\0\0\0\x0d\0\0\0\x3f\x01\0\0\0\0\0\0\
-\x1a\0\0\0\x21\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\
-\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\
-\0\0\0\0\0\x0a\0\0\0\x01\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\
-\0\0\0\0\x79\x12\x08\0\0\0\0\0\x15\x02\x3c\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x79\
-\x27\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\
-\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\
-\x31\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\
-\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\
-\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\
-\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\
-\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\
-\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\
-\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\
-\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\
-\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\
-\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\
-\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\
-\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\
-\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\
-\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x51\0\0\0\xb7\x03\0\0\x11\0\0\0\
-\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\
-\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x80\x01\0\x01\0\0\0\x42\0\0\
-\0\x7b\0\0\0\x24\x80\x01\0\x02\0\0\0\x42\0\0\0\x60\x02\0\0\x1f\x88\x01\0\x03\0\
-\0\0\x42\0\0\0\x84\x02\0\0\x06\x94\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\
-\x84\x01\0\x05\0\0\0\x42\0\0\0\x9d\x02\0\0\x0e\xa0\x01\0\x06\0\0\0\x42\0\0\0\
-\x1a\x01\0\0\x1d\x84\x01\0\x07\0\0\0\x42\0\0\0\x43\x01\0\0\x06\xa4\x01\0\x09\0\
-\0\0\x42\0\0\0\xaf\x02\0\0\x03\xa8\x01\0\x11\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\
-\xb0\x01\0\x18\0\0\0\x42\0\0\0\x5a\x03\0\0\x06\x04\x01\0\x1b\0\0\0\x42\0\0\0\0\
-\0\0\0\0\0\0\0\x1c\0\0\0\x42\0\0\0\xab\x03\0\0\x0f\x10\x01\0\x1d\0\0\0\x42\0\0\
-\0\xc0\x03\0\0\x2d\x14\x01\0\x1f\0\0\0\x42\0\0\0\xf7\x03\0\0\x0d\x0c\x01\0\x21\
-\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x22\0\0\0\x42\0\0\0\xc0\x03\0\0\x02\x14\x01\0\
-\x25\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x28\0\0\0\x42\0\0\0\0\0\0\0\0\0\
-\0\0\x29\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x1e\x04\
-\0\0\x0d\x18\x01\0\x2d\0\0\0\x42\0\0\0\x4c\x04\0\0\x1b\x1c\x01\0\x2e\0\0\0\x42\
-\0\0\0\x4c\x04\0\0\x06\x1c\x01\0\x2f\0\0\0\x42\0\0\0\x6f\x04\0\0\x0d\x24\x01\0\
-\x31\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\xb0\x01\0\x40\0\0\0\x42\0\0\0\x2a\x02\0\0\
-\x01\xc0\x01\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\
-\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x14\0\0\0\x3e\0\0\0\
-\0\0\0\0\x28\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x30\0\0\0\x08\0\0\0\x3f\x01\0\0\
-\0\0\0\0\x88\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x98\0\0\0\x1a\0\0\0\xea\0\0\0\0\
-\0\0\0\xb0\0\0\0\x1a\0\0\0\x52\x03\0\0\0\0\0\0\xb8\0\0\0\x1a\0\0\0\x56\x03\0\0\
-\0\0\0\0\xc8\0\0\0\x1f\0\0\0\x84\x03\0\0\0\0\0\0\xe0\0\0\0\x20\0\0\0\xea\0\0\0\
-\0\0\0\0\xf8\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x20\x01\0\0\x24\0\0\0\x3e\0\0\0\
-\0\0\0\0\x58\x01\0\0\x1a\0\0\0\xea\0\0\0\0\0\0\0\x68\x01\0\0\x20\0\0\0\x46\x04\
-\0\0\0\0\0\0\x90\x01\0\0\x1a\0\0\0\x3f\x01\0\0\0\0\0\0\xa0\x01\0\0\x1a\0\0\0\
-\x87\x04\0\0\0\0\0\0\xa8\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x42\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\
-\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x1a\0\
-\0\0\x01\0\0\0\0\0\0\0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\
-\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\
-\0\0\0\0";
-	opts.insns_sz = 2216;
+\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xb0\0\0\0\x03\0\0\x04\x18\0\0\0\xbe\0\
+\0\0\x09\0\0\0\0\0\0\0\xc2\0\0\0\x0b\0\0\0\x40\0\0\0\xcd\0\0\0\x0b\0\0\0\x80\0\
+\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd5\0\0\0\0\0\0\x07\0\0\0\0\xde\0\0\0\0\0\0\
+\x08\x0c\0\0\0\xe4\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xae\x01\0\0\x03\0\0\x04\
+\x18\0\0\0\xb6\x01\0\0\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\xbe\
+\x01\0\0\x0e\0\0\0\xa0\0\0\0\xca\x01\0\0\0\0\0\x08\x0f\0\0\0\xd0\x01\0\0\0\0\0\
+\x01\x04\0\0\0\x20\0\0\0\xdd\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\
+\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xe2\x01\0\0\0\0\0\x01\x04\0\0\0\
+\x20\0\0\0\0\0\0\0\x01\0\0\x0d\x14\0\0\0\x26\x05\0\0\x04\0\0\0\x2b\x02\0\0\0\0\
+\0\x08\x15\0\0\0\x31\x02\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\x01\x3b\x02\0\0\x01\0\
+\0\x0c\x13\0\0\0\0\0\0\0\0\0\0\x02\x18\0\0\0\x52\x02\0\0\x02\0\0\x04\x10\0\0\0\
+\x13\0\0\0\x03\0\0\0\0\0\0\0\x65\x02\0\0\x19\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
+\x1c\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x17\0\0\0\x6a\x02\0\0\x01\0\
+\0\x0c\x1a\0\0\0\xb6\x02\0\0\x01\0\0\x04\x08\0\0\0\xbf\x02\0\0\x1d\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x02\x1e\0\0\0\x10\x03\0\0\x06\0\0\x04\x38\0\0\0\xb6\x01\0\0\
+\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\x1d\x03\0\0\x1f\0\0\0\xc0\0\
+\0\0\x2e\x03\0\0\x19\0\0\0\0\x01\0\0\x37\x03\0\0\x21\0\0\0\x40\x01\0\0\x41\x03\
+\0\0\x22\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\
+\0\0\0\0\0\0\0\0\0\x02\x23\0\0\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x8b\x03\0\0\x02\0\
+\0\x04\x08\0\0\0\x99\x03\0\0\x0e\0\0\0\0\0\0\0\xa2\x03\0\0\x0e\0\0\0\x20\0\0\0\
+\x41\x03\0\0\x03\0\0\x04\x18\0\0\0\xac\x03\0\0\x1f\0\0\0\0\0\0\0\xb4\x03\0\0\
+\x25\0\0\0\x40\0\0\0\xba\x03\0\0\x27\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x26\0\0\
+\0\0\0\0\0\0\0\0\x02\x28\0\0\0\xbe\x03\0\0\x01\0\0\x04\x04\0\0\0\xc9\x03\0\0\
+\x0e\0\0\0\0\0\0\0\x32\x04\0\0\x01\0\0\x04\x04\0\0\0\x3b\x04\0\0\x0e\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x30\0\0\0\xb1\x04\0\0\0\0\0\
+\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x1a\0\0\0\
+\xc5\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\
+\x12\0\0\0\x20\0\0\0\xdb\x04\0\0\0\0\0\x0e\x2d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
+\0\0\0\0\x20\0\0\0\x12\0\0\0\x11\0\0\0\xf0\x04\0\0\0\0\0\x0e\x2f\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\x07\x05\0\0\0\0\0\x0e\
+\x31\0\0\0\x01\0\0\0\x0f\x05\0\0\x01\0\0\x0f\x04\0\0\0\x36\0\0\0\0\0\0\0\x04\0\
+\0\0\x16\x05\0\0\x04\0\0\x0f\x7b\0\0\0\x2a\0\0\0\0\0\0\0\x30\0\0\0\x2c\0\0\0\
+\x30\0\0\0\x1a\0\0\0\x2e\0\0\0\x4a\0\0\0\x20\0\0\0\x30\0\0\0\x6a\0\0\0\x11\0\0\
+\0\x1e\x05\0\0\x01\0\0\x0f\x04\0\0\0\x32\0\0\0\0\0\0\0\x04\0\0\0\x26\x05\0\0\0\
+\0\0\x0e\x06\0\0\0\x01\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\
+\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\
+\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\
+\x62\x70\x66\x5f\x6d\x61\x70\0\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x73\
+\x70\x73\x6b\x2f\x73\x72\x63\x2f\x62\x70\x66\x2d\x6e\x65\x78\x74\x2f\x6b\x65\
+\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\
+\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\
+\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\
+\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\
+\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\
+\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\
+\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\
+\x69\x67\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\
+\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\
+\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\
+\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\
+\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\
+\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\
+\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\
+\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\
+\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\
+\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\
+\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\
+\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\
+\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\
+\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\
+\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\
+\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\x31\x30\x64\x20\x20\x20\x25\x31\x30\
+\x6c\x6c\x64\x5c\x6e\x22\x2c\0\x7d\0\x5f\x5f\x73\x36\x34\0\x6c\x6f\x6e\x67\x20\
+\x6c\x6f\x6e\x67\0\x62\x70\x66\x5f\x6d\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\
+\x6d\x5f\x63\x6f\x75\x6e\x74\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\
+\x66\x5f\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
+\x5f\x70\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\
+\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\
+\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\
+\x20\x28\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\
+\x78\0\x09\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\
+\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
+\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\
+\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\
+\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\
+\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\
+\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\
+\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\
+\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\
+\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\
+\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\
+\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\
+\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\
+\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\
+\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\
+\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\
+\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\
+\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\
+\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\
+\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
+\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\
+\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\
+\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\
+\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\
+\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\
+\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
+\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
+\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\
+\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\
+\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x6b\x73\x79\x6d\
+\x73\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x64\x75\x6d\
+\x6d\x79\x5f\x6b\x73\x79\x6d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\xc9\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x7b\0\0\0\x01\0\0\0\
+\x80\0\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\
+\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x34\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\
+\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
+\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\
+\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\
+\x31\x30\x64\x20\x20\x20\x25\x31\x30\x6c\x6c\x64\x0a\0\x20\x20\x69\x64\x20\x6e\
+\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\
+\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
+\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\
+\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1d\0\0\0\0\0\x79\x21\
+\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe0\xff\
+\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\
+\x30\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\
+\xe0\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\
+\x7b\x2a\xe8\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\x7b\x1a\xf0\xff\0\0\0\0\xbf\x71\
+\0\0\0\0\0\0\x85\x20\0\0\0\0\0\0\x7b\x0a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\
+\x07\x04\0\0\xe0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\
+\x30\0\0\0\xb7\x03\0\0\x1a\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\
+\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\
+\x1e\x44\x01\0\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x44\x01\0\x02\0\0\0\x42\0\0\0\
+\xfb\0\0\0\x1d\x4c\x01\0\x03\0\0\0\x42\0\0\0\x1c\x01\0\0\x06\x54\x01\0\x04\0\0\
+\0\x42\0\0\0\x2b\x01\0\0\x1d\x48\x01\0\x05\0\0\0\x42\0\0\0\x50\x01\0\0\x06\x60\
+\x01\0\x07\0\0\0\x42\0\0\0\x63\x01\0\0\x03\x64\x01\0\x0e\0\0\0\x42\0\0\0\xf6\
+\x01\0\0\x02\x6c\x01\0\x21\0\0\0\x42\0\0\0\x29\x02\0\0\x01\x80\x01\0\0\0\0\0\
+\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\
+\x02\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x70\0\0\0\
+\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xf7\0\0\0\0\0\0\0\xa0\0\0\0\
+\x0d\0\0\0\x27\x01\0\0\0\0\0\0\x1a\0\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\
+\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\
+\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\
+\x65\x72\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x62\x70\x66\x5f\x6d\
+\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\x6d\x5f\x63\x6f\x75\x6e\x74\0\0\x47\
+\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x11\x08\0\0\0\0\
+\0\x15\x01\x3b\0\0\0\0\0\x79\x17\0\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\
+\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\
+\x18\x62\0\0\0\0\0\0\0\0\0\0\x4a\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x7e\0\0\0\x7b\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\
+\xff\0\0\0\0\xb7\x03\0\0\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\
+\x71\x28\0\0\0\0\0\x79\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\
+\0\0\x0f\x21\0\0\0\0\0\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\
+\0\x03\0\0\0\x0f\x13\0\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\
+\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\
+\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\
+\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\
+\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\
+\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\
+\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\
+\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\
+\xff\xff\xff\x79\xa1\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x6a\0\0\0\xb7\
+\x03\0\0\x11\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\
+\x95\0\0\0\0\0\0\0\0\0\0\0\x1b\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\x1e\x94\x01\0\
+\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x94\x01\0\x02\0\0\0\x42\0\0\0\x86\x02\0\0\
+\x1f\x9c\x01\0\x03\0\0\0\x42\0\0\0\xaa\x02\0\0\x06\xa8\x01\0\x04\0\0\0\x42\0\0\
+\0\xc3\x02\0\0\x0e\xb4\x01\0\x05\0\0\0\x42\0\0\0\x2b\x01\0\0\x1d\x98\x01\0\x06\
+\0\0\0\x42\0\0\0\x50\x01\0\0\x06\xb8\x01\0\x08\0\0\0\x42\0\0\0\xd5\x02\0\0\x03\
+\xbc\x01\0\x10\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x17\0\0\0\x42\0\0\0\
+\x80\x03\0\0\x06\x04\x01\0\x1a\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x1b\0\
+\0\0\x42\0\0\0\xd1\x03\0\0\x0f\x10\x01\0\x1c\0\0\0\x42\0\0\0\xe6\x03\0\0\x2d\
+\x14\x01\0\x1e\0\0\0\x42\0\0\0\x1d\x04\0\0\x0d\x0c\x01\0\x20\0\0\0\x42\0\0\0\
+\x45\x03\0\0\x02\xc4\x01\0\x21\0\0\0\x42\0\0\0\xe6\x03\0\0\x02\x14\x01\0\x24\0\
+\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x27\0\0\0\x42\0\0\0\x45\x03\0\0\x02\
+\xc4\x01\0\x28\0\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x2b\0\0\0\x42\0\0\0\
+\x44\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x72\x04\0\0\x1b\x1c\x01\0\x2d\0\
+\0\0\x42\0\0\0\x72\x04\0\0\x06\x1c\x01\0\x2e\0\0\0\x42\0\0\0\x95\x04\0\0\x0d\
+\x24\x01\0\x30\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x3f\0\0\0\x42\0\0\0\
+\x29\x02\0\0\x01\xd4\x01\0\0\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\
+\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x18\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x1c\0\0\
+\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x80\0\0\0\x1e\0\0\
+\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1e\0\0\0\xf7\0\0\0\0\0\0\0\xa8\0\0\0\x1e\0\0\0\
+\x78\x03\0\0\0\0\0\0\xb0\0\0\0\x1e\0\0\0\x7c\x03\0\0\0\0\0\0\xc0\0\0\0\x23\0\0\
+\0\xaa\x03\0\0\0\0\0\0\xd8\0\0\0\x24\0\0\0\xf7\0\0\0\0\0\0\0\xf0\0\0\0\x24\0\0\
+\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x28\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1e\0\
+\0\0\xf7\0\0\0\0\0\0\0\x60\x01\0\0\x24\0\0\0\x6c\x04\0\0\0\0\0\0\x88\x01\0\0\
+\x1e\0\0\0\x27\x01\0\0\0\0\0\0\x98\x01\0\0\x1e\0\0\0\xad\x04\0\0\0\0\0\0\xa0\
+\x01\0\0\x1c\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\
+\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\
+\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x19\0\0\0\x01\0\0\0\0\0\0\0\
+\x12\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\
+\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0";
+	opts.insns_sz = 2456;
 	opts.insns = (void *)"\
 \xbf\x16\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x78\xff\xff\xff\xb7\x02\0\
 \0\x88\0\0\0\xb7\x03\0\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x05\0\x14\0\0\0\0\0\x61\
@@ -331,79 +326,83 @@ iterators_bpf__load(struct iterators_bpf *skel)
 \0\0\0\x85\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\
 \0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xbf\x70\0\0\
 \0\0\0\0\x95\0\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x48\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\
-\0\0\x44\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\
-\0\0\0\0\x38\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\
-\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\
-\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\
+\xe8\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\
+\0\0\xe4\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\
+\0\0\0\0\xd8\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\
+\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\
 \xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xd4\xff\0\0\0\0\x63\x7a\x78\xff\0\0\0\0\
-\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x0e\0\0\x63\x01\0\0\0\
+\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x0f\0\0\x63\x01\0\0\0\
 \0\0\0\x61\x60\x1c\0\0\0\0\0\x15\0\x03\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x5c\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\
-\0\x50\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\
+\xfc\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\
+\0\xf0\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\
 \xc5\x07\xc3\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x71\0\0\0\0\0\
-\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x98\
-\x0e\0\0\xb7\x02\0\0\x62\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\
+\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x38\
+\x0f\0\0\xb7\x02\0\0\x7b\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\
 \0\0\0\x94\0\0\0\x05\0\x01\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x18\x62\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\x63\
-\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\
-\0\0\x10\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x0e\0\0\
-\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\
-\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\
+\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\x63\
+\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xb8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\
+\0\0\0\xc8\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\
+\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\
 \xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x9f\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\x63\
-\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\
+\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\x63\
+\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\
 \xb7\x03\0\0\x04\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x92\xff\
-\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
-\x78\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\x18\
-\x61\0\0\0\0\0\0\0\0\0\0\x70\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
-\0\0\0\x40\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x11\0\0\x7b\x01\0\0\0\0\0\0\
-\x18\x60\0\0\0\0\0\0\0\0\0\0\x48\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc8\x11\0\
-\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x10\0\0\x18\x61\0\0\0\0\
-\0\0\0\0\0\0\xe8\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\
-\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x11\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\
-\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x84\x11\0\0\x63\x01\0\0\0\0\0\0\x79\x60\
-\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\
-\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x11\0\0\x63\x01\0\0\0\0\0\
-\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xf8\x11\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\
+\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\
+\x20\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xf0\x0f\0\0\x18\
+\x61\0\0\0\0\0\0\0\0\0\0\x18\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
+\0\0\0\x08\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x60\x12\0\0\x7b\x01\0\0\0\0\0\0\
+\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x70\x12\0\
+\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xa0\x11\0\0\x18\x61\0\0\0\0\
+\0\0\0\0\0\0\x90\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\
+\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x12\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\
+\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x2c\x12\0\0\x63\x01\0\0\0\0\0\0\x79\x60\
+\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\
+\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x58\x12\0\0\x63\x01\0\0\0\0\0\
+\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x12\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\
 \x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\
-\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x68\x11\0\0\x63\x70\x6c\0\0\0\0\0\
-\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\
-\0\0\0\0\0\0\0\0\x68\x11\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\
-\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd8\x11\0\0\x61\x01\0\0\0\0\0\0\xd5\
-\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x4a\xff\0\0\
-\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x18\x61\0\
-\0\0\0\0\0\0\0\0\0\x10\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\
-\x18\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\
-\x60\0\0\0\0\0\0\0\0\0\0\x28\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x50\x17\0\0\
-\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x14\0\0\x18\x61\0\0\0\0\0\
-\0\0\0\0\0\x60\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x15\
-\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x78\x17\0\0\x7b\x01\0\0\0\0\
-\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x17\0\0\x63\x01\0\0\
-\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x1c\x17\0\0\x63\x01\
-\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\x7b\
-\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x48\x17\0\
-\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x90\x17\0\0\xb7\x02\0\0\x12\
-\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\
-\0\0\0\0\0\xc5\x07\x13\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\x63\
-\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\
-\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\
-\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x70\x17\0\0\x61\x01\
-\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\
-\x07\x01\xff\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\xd5\x01\
-\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\0\0\0\0\
-\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\x18\x61\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\xb7\0\0\0\
-\0\0\0\0\x95\0\0\0\0\0\0\0";
+\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x63\x70\x6c\0\0\0\0\0\
+\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\x18\x68\0\0\0\0\0\0\0\0\0\0\xa8\
+\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x12\0\0\xb7\x02\0\0\x17\0\0\0\xb7\x03\
+\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\
+\x07\x4d\xff\0\0\0\0\x75\x07\x03\0\0\0\0\0\x62\x08\x04\0\0\0\0\0\x6a\x08\x02\0\
+\0\0\0\0\x05\0\x0a\0\0\0\0\0\x63\x78\x04\0\0\0\0\0\xbf\x79\0\0\0\0\0\0\x77\x09\
+\0\0\x20\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\x63\x90\0\0\0\0\0\0\x55\
+\x09\x02\0\0\0\0\0\x6a\x08\x02\0\0\0\0\0\x05\0\x01\0\0\0\0\0\x6a\x08\x02\0\x40\
+\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\xb7\x03\0\
+\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\
+\0\0\x01\0\0\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\
+\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x80\x12\0\0\x61\x01\0\0\0\0\0\0\
+\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x2c\xff\
+\0\0\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\x18\
+\x61\0\0\0\0\0\0\0\0\0\0\xa8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\
+\0\0\0\xd8\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x17\0\0\x7b\x01\0\0\0\0\0\0\
+\x18\x60\0\0\0\0\0\0\0\0\0\0\xe0\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe8\x17\0\
+\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x14\0\0\x18\x61\0\0\0\0\
+\0\0\0\0\0\0\xf8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x78\
+\x16\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x10\x18\0\0\x7b\x01\0\0\
+\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x17\0\0\x63\x01\
+\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb4\x17\0\0\x63\
+\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x17\0\0\
+\x7b\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\
+\x17\0\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x18\0\0\xb7\x02\0\
+\0\x12\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\
+\x07\0\0\0\0\0\0\xc5\x07\xf5\xfe\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x17\0\
+\0\x63\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\
+\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x98\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\
+\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x08\x18\0\0\
+\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\
+\0\0\xc5\x07\xe3\xfe\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\
+\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\
+\0\0\0\0\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\
+\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\
+\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0";
 	err = bpf_load_and_run(&opts);
 	if (err < 0)
 		return err;
-	skel->rodata = skel_finalize_map_data(&skel->maps.rodata.initial_value,
-					4096, PROT_READ, skel->maps.rodata.map_fd);
-	if (!skel->rodata)
-		return -ENOMEM;
 	return 0;
 }
 
@@ -422,4 +421,15 @@ iterators_bpf__open_and_load(void)
 	return skel;
 }
 
+__attribute__((unused)) static void
+iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused)))
+{
+#ifdef __cplusplus
+#define _Static_assert static_assert
+#endif
+#ifdef __cplusplus
+#undef _Static_assert
+#endif
+}
+
 #endif /* __ITERATORS_BPF_SKEL_H__ */
-- 
cgit v1.2.3


From 7ac8d0d2619256cc13eaf4a889b3177a1607b02d Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:21 +0000
Subject: bpf: Support ->fill_link_info for kprobe_multi

With the addition of support for fill_link_info to the kprobe_multi link,
users will gain the ability to inspect it conveniently using the
`bpftool link show`. This enhancement provides valuable information to the
user, including the count of probed functions and their respective
addresses. It's important to note that if the kptr_restrict setting is not
permitted, the probed address will not be exposed, ensuring security.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

(limited to 'kernel')

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 03b7f6b8e4f0..acb3d6dd7a77 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2469,6 +2469,7 @@ struct bpf_kprobe_multi_link {
 	u32 cnt;
 	u32 mods_cnt;
 	struct module **mods;
+	u32 flags;
 };
 
 struct bpf_kprobe_multi_run_ctx {
@@ -2558,9 +2559,44 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
 	kfree(kmulti_link);
 }
 
+static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
+						struct bpf_link_info *info)
+{
+	u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs);
+	struct bpf_kprobe_multi_link *kmulti_link;
+	u32 ucount = info->kprobe_multi.count;
+	int err = 0, i;
+
+	if (!uaddrs ^ !ucount)
+		return -EINVAL;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	info->kprobe_multi.count = kmulti_link->cnt;
+	info->kprobe_multi.flags = kmulti_link->flags;
+
+	if (!uaddrs)
+		return 0;
+	if (ucount < kmulti_link->cnt)
+		err = -ENOSPC;
+	else
+		ucount = kmulti_link->cnt;
+
+	if (kallsyms_show_value(current_cred())) {
+		if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64)))
+			return -EFAULT;
+	} else {
+		for (i = 0; i < ucount; i++) {
+			if (put_user(0, uaddrs + i))
+				return -EFAULT;
+		}
+	}
+	return err;
+}
+
 static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
 	.release = bpf_kprobe_multi_link_release,
 	.dealloc = bpf_kprobe_multi_link_dealloc,
+	.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
 };
 
 static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
@@ -2872,6 +2908,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->addrs = addrs;
 	link->cookies = cookies;
 	link->cnt = cnt;
+	link->flags = flags;
 
 	if (cookies) {
 		/*
-- 
cgit v1.2.3


From f1a414537ecc18b5882a57045ce3e4a11e528290 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:24 +0000
Subject: bpf: Protect probed address based on kptr_restrict setting

The probed address can be accessed by userspace through querying the task
file descriptor (fd). However, it is crucial to adhere to the kptr_restrict
setting and refrain from exposing the address if it is not permitted.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-5-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/trace_kprobe.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1b3fa7b854aa..249eb14d0f7a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1551,7 +1551,10 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 	} else {
 		*symbol = NULL;
 		*probe_offset = 0;
-		*probe_addr = (unsigned long)tk->rp.kp.addr;
+		if (kallsyms_show_value(current_cred()))
+			*probe_addr = (unsigned long)tk->rp.kp.addr;
+		else
+			*probe_addr = 0;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 5125e757e62f6c1d5478db4c2b61a744060ddf3f Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:25 +0000
Subject: bpf: Clear the probe_addr for uprobe

To avoid returning uninitialized or random values when querying the file
descriptor (fd) and accessing probe_addr, it is necessary to clear the
variable prior to its use.

Fixes: 41bdc4b40ed6 ("bpf: introduce bpf subcommand BPF_TASK_FD_QUERY")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-6-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c    | 2 +-
 kernel/trace/trace_uprobe.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index acb3d6dd7a77..31ec0e2853ec 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2384,7 +2384,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 #ifdef CONFIG_UPROBE_EVENTS
 		if (flags & TRACE_EVENT_FL_UPROBE)
 			err = bpf_get_uprobe_info(event, fd_type, buf,
-						  probe_offset,
+						  probe_offset, probe_addr,
 						  event->attr.type == PERF_TYPE_TRACEPOINT);
 #endif
 	}
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8b92e34ff0c8..fd6c71450ba7 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1415,7 +1415,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
 
 int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 			const char **filename, u64 *probe_offset,
-			bool perf_type_tracepoint)
+			u64 *probe_addr, bool perf_type_tracepoint)
 {
 	const char *pevent = trace_event_name(event->tp_event);
 	const char *group = event->tp_event->class->system;
@@ -1432,6 +1432,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 				    : BPF_FD_TYPE_UPROBE;
 	*filename = tu->filename;
 	*probe_offset = tu->offset;
+	*probe_addr = 0;
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
-- 
cgit v1.2.3


From cd3910d005052382901fe3d0a3aeed48b1b64906 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:26 +0000
Subject: bpf: Expose symbol's respective address

Since different symbols can share the same name, it is insufficient to only
expose the symbol name. It is essential to also expose the symbol address
so that users can accurately identify which one is being probed.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-7-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/trace_kprobe.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 249eb14d0f7a..bf2872ca5aaf 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1544,18 +1544,10 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 
 	*fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
 					      : BPF_FD_TYPE_KPROBE;
-	if (tk->symbol) {
-		*symbol = tk->symbol;
-		*probe_offset = tk->rp.kp.offset;
-		*probe_addr = 0;
-	} else {
-		*symbol = NULL;
-		*probe_offset = 0;
-		if (kallsyms_show_value(current_cred()))
-			*probe_addr = (unsigned long)tk->rp.kp.addr;
-		else
-			*probe_addr = 0;
-	}
+	*probe_offset = tk->rp.kp.offset;
+	*probe_addr = kallsyms_show_value(current_cred()) ?
+		      (unsigned long)tk->rp.kp.addr : 0;
+	*symbol = tk->symbol;
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
-- 
cgit v1.2.3


From 57d485376552480602ab83bf7499b451bae5a1b9 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:27 +0000
Subject: bpf: Add a common helper bpf_copy_to_user()

Add a common helper bpf_copy_to_user(), which will be used at multiple
places.
No functional change.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-8-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a2aef900519c..4aa6e5776a04 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3295,6 +3295,25 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
 		   raw_tp_link->btp->tp->name);
 }
 
+static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen,
+			    u32 len)
+{
+	if (ulen >= len + 1) {
+		if (copy_to_user(ubuf, buf, len + 1))
+			return -EFAULT;
+	} else {
+		char zero = '\0';
+
+		if (copy_to_user(ubuf, buf, ulen - 1))
+			return -EFAULT;
+		if (put_user(zero, ubuf + ulen - 1))
+			return -EFAULT;
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
 static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 					  struct bpf_link_info *info)
 {
@@ -3313,20 +3332,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 	if (!ubuf)
 		return 0;
 
-	if (ulen >= tp_len + 1) {
-		if (copy_to_user(ubuf, tp_name, tp_len + 1))
-			return -EFAULT;
-	} else {
-		char zero = '\0';
-
-		if (copy_to_user(ubuf, tp_name, ulen - 1))
-			return -EFAULT;
-		if (put_user(zero, ubuf + ulen - 1))
-			return -EFAULT;
-		return -ENOSPC;
-	}
-
-	return 0;
+	return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len);
 }
 
 static const struct bpf_link_ops bpf_raw_tp_link_lops = {
-- 
cgit v1.2.3


From 1b715e1b0ec531fae72cd6698fe1c98affa436f8 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 9 Jul 2023 02:56:28 +0000
Subject: bpf: Support ->fill_link_info for perf_event

By introducing support for ->fill_link_info to the perf_event link, users
gain the ability to inspect it using `bpftool link show`. While the current
approach involves accessing this information via `bpftool perf show`,
consolidating link information for all link types in one place offers
greater convenience. Additionally, this patch extends support to the
generic perf event, which is not currently accommodated by
`bpftool perf show`. While only the perf type and config are exposed to
userspace, other attributes such as sample_period and sample_freq are
ignored. It's important to note that if kptr_restrict is not permitted, the
probed address will not be exposed, maintaining security measures.

A new enum bpf_perf_event_type is introduced to help the user understand
which struct is relevant.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20230709025630.3735-9-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c     | 146 +++++++++++++++++++++++++++++++++++++++++++++++
 kernel/trace/bpf_trace.c |  10 +++-
 2 files changed, 153 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4aa6e5776a04..ee8cb1a174aa 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3364,9 +3364,155 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
 	kfree(perf_link);
 }
 
+static int bpf_perf_link_fill_common(const struct perf_event *event,
+				     char __user *uname, u32 ulen,
+				     u64 *probe_offset, u64 *probe_addr,
+				     u32 *fd_type)
+{
+	const char *buf;
+	u32 prog_id;
+	size_t len;
+	int err;
+
+	if (!ulen ^ !uname)
+		return -EINVAL;
+	if (!uname)
+		return 0;
+
+	err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
+				      probe_offset, probe_addr);
+	if (err)
+		return err;
+
+	if (buf) {
+		len = strlen(buf);
+		err = bpf_copy_to_user(uname, buf, ulen, len);
+		if (err)
+			return err;
+	} else {
+		char zero = '\0';
+
+		if (put_user(zero, uname))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_KPROBE_EVENTS
+static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
+				     struct bpf_link_info *info)
+{
+	char __user *uname;
+	u64 addr, offset;
+	u32 ulen, type;
+	int err;
+
+	uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
+	ulen = info->perf_event.kprobe.name_len;
+	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+					&type);
+	if (err)
+		return err;
+	if (type == BPF_FD_TYPE_KRETPROBE)
+		info->perf_event.type = BPF_PERF_EVENT_KRETPROBE;
+	else
+		info->perf_event.type = BPF_PERF_EVENT_KPROBE;
+
+	info->perf_event.kprobe.offset = offset;
+	if (!kallsyms_show_value(current_cred()))
+		addr = 0;
+	info->perf_event.kprobe.addr = addr;
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_UPROBE_EVENTS
+static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
+				     struct bpf_link_info *info)
+{
+	char __user *uname;
+	u64 addr, offset;
+	u32 ulen, type;
+	int err;
+
+	uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
+	ulen = info->perf_event.uprobe.name_len;
+	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+					&type);
+	if (err)
+		return err;
+
+	if (type == BPF_FD_TYPE_URETPROBE)
+		info->perf_event.type = BPF_PERF_EVENT_URETPROBE;
+	else
+		info->perf_event.type = BPF_PERF_EVENT_UPROBE;
+	info->perf_event.uprobe.offset = offset;
+	return 0;
+}
+#endif
+
+static int bpf_perf_link_fill_probe(const struct perf_event *event,
+				    struct bpf_link_info *info)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+	if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE)
+		return bpf_perf_link_fill_kprobe(event, info);
+#endif
+#ifdef CONFIG_UPROBE_EVENTS
+	if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE)
+		return bpf_perf_link_fill_uprobe(event, info);
+#endif
+	return -EOPNOTSUPP;
+}
+
+static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
+					 struct bpf_link_info *info)
+{
+	char __user *uname;
+	u32 ulen;
+
+	uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
+	ulen = info->perf_event.tracepoint.name_len;
+	info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
+	return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL);
+}
+
+static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
+					 struct bpf_link_info *info)
+{
+	info->perf_event.event.type = event->attr.type;
+	info->perf_event.event.config = event->attr.config;
+	info->perf_event.type = BPF_PERF_EVENT_EVENT;
+	return 0;
+}
+
+static int bpf_perf_link_fill_link_info(const struct bpf_link *link,
+					struct bpf_link_info *info)
+{
+	struct bpf_perf_link *perf_link;
+	const struct perf_event *event;
+
+	perf_link = container_of(link, struct bpf_perf_link, link);
+	event = perf_get_event(perf_link->perf_file);
+	if (IS_ERR(event))
+		return PTR_ERR(event);
+
+	switch (event->prog->type) {
+	case BPF_PROG_TYPE_PERF_EVENT:
+		return bpf_perf_link_fill_perf_event(event, info);
+	case BPF_PROG_TYPE_TRACEPOINT:
+		return bpf_perf_link_fill_tracepoint(event, info);
+	case BPF_PROG_TYPE_KPROBE:
+		return bpf_perf_link_fill_probe(event, info);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct bpf_link_ops bpf_perf_link_lops = {
 	.release = bpf_perf_link_release,
 	.dealloc = bpf_perf_link_dealloc,
+	.fill_link_info = bpf_perf_link_fill_link_info,
 };
 
 static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 31ec0e2853ec..897edfc9ca12 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2369,9 +2369,13 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 	if (is_tracepoint || is_syscall_tp) {
 		*buf = is_tracepoint ? event->tp_event->tp->name
 				     : event->tp_event->name;
-		*fd_type = BPF_FD_TYPE_TRACEPOINT;
-		*probe_offset = 0x0;
-		*probe_addr = 0x0;
+		/* We allow NULL pointer for tracepoint */
+		if (fd_type)
+			*fd_type = BPF_FD_TYPE_TRACEPOINT;
+		if (probe_offset)
+			*probe_offset = 0x0;
+		if (probe_addr)
+			*probe_addr = 0x0;
 	} else {
 		/* kprobe/uprobe */
 		err = -EOPNOTSUPP;
-- 
cgit v1.2.3


From f42bcd168d034aa8abd9178c430b407be8c98827 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 11 Jul 2023 16:23:59 -0700
Subject: bpf: teach verifier actual bounds of bpf_get_smp_processor_id()
 result

bpf_get_smp_processor_id() helper returns current CPU on which BPF
program runs. It can't return value that is bigger than maximum allowed
number of CPUs (minus one, due to zero indexing). Teach BPF verifier to
recognize that. This makes it possible to use bpf_get_smp_processor_id()
result to index into arrays without extra checks, as demonstrated in
subsequent selftests/bpf patch.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230711232400.1658562-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 11e54dd8b6dd..81a93eeac7a0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25,6 +25,7 @@
 #include <linux/btf_ids.h>
 #include <linux/poison.h>
 #include <linux/module.h>
+#include <linux/cpumask.h>
 
 #include "disasm.h"
 
@@ -9116,19 +9117,33 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 {
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
 
-	if (ret_type != RET_INTEGER ||
-	    (func_id != BPF_FUNC_get_stack &&
-	     func_id != BPF_FUNC_get_task_stack &&
-	     func_id != BPF_FUNC_probe_read_str &&
-	     func_id != BPF_FUNC_probe_read_kernel_str &&
-	     func_id != BPF_FUNC_probe_read_user_str))
+	if (ret_type != RET_INTEGER)
 		return;
 
-	ret_reg->smax_value = meta->msize_max_value;
-	ret_reg->s32_max_value = meta->msize_max_value;
-	ret_reg->smin_value = -MAX_ERRNO;
-	ret_reg->s32_min_value = -MAX_ERRNO;
-	reg_bounds_sync(ret_reg);
+	switch (func_id) {
+	case BPF_FUNC_get_stack:
+	case BPF_FUNC_get_task_stack:
+	case BPF_FUNC_probe_read_str:
+	case BPF_FUNC_probe_read_kernel_str:
+	case BPF_FUNC_probe_read_user_str:
+		ret_reg->smax_value = meta->msize_max_value;
+		ret_reg->s32_max_value = meta->msize_max_value;
+		ret_reg->smin_value = -MAX_ERRNO;
+		ret_reg->s32_min_value = -MAX_ERRNO;
+		reg_bounds_sync(ret_reg);
+		break;
+	case BPF_FUNC_get_smp_processor_id:
+		ret_reg->umax_value = nr_cpu_ids - 1;
+		ret_reg->u32_max_value = nr_cpu_ids - 1;
+		ret_reg->smax_value = nr_cpu_ids - 1;
+		ret_reg->s32_max_value = nr_cpu_ids - 1;
+		ret_reg->umin_value = 0;
+		ret_reg->u32_min_value = 0;
+		ret_reg->smin_value = 0;
+		ret_reg->s32_min_value = 0;
+		reg_bounds_sync(ret_reg);
+		break;
+	}
 }
 
 static int
-- 
cgit v1.2.3


From 12c8d0f4c8702f88a74973fb7ced85b59043b0ab Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:34 -0700
Subject: bpf: Rename few bpf_mem_alloc fields.

Rename:
-       struct rcu_head rcu;
-       struct llist_head free_by_rcu;
-       struct llist_head waiting_for_gp;
-       atomic_t call_rcu_in_progress;
+       struct llist_head free_by_rcu_ttrace;
+       struct llist_head waiting_for_gp_ttrace;
+       struct rcu_head rcu_ttrace;
+       atomic_t call_rcu_ttrace_in_progress;
...
-	static void do_call_rcu(struct bpf_mem_cache *c)
+	static void do_call_rcu_ttrace(struct bpf_mem_cache *c)

to better indicate intended use.

The 'tasks trace' is shortened to 'ttrace' to reduce verbosity.
No functional changes.

Later patches will add free_by_rcu/waiting_for_gp fields to be used with normal RCU.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-2-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 57 ++++++++++++++++++++++++++-------------------------
 1 file changed, 29 insertions(+), 28 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 0668bcd7c926..cc5b8adb4c83 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -99,10 +99,11 @@ struct bpf_mem_cache {
 	int low_watermark, high_watermark, batch;
 	int percpu_size;
 
-	struct rcu_head rcu;
-	struct llist_head free_by_rcu;
-	struct llist_head waiting_for_gp;
-	atomic_t call_rcu_in_progress;
+	/* list of objects to be freed after RCU tasks trace GP */
+	struct llist_head free_by_rcu_ttrace;
+	struct llist_head waiting_for_gp_ttrace;
+	struct rcu_head rcu_ttrace;
+	atomic_t call_rcu_ttrace_in_progress;
 };
 
 struct bpf_mem_caches {
@@ -165,18 +166,18 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 	old_memcg = set_active_memcg(memcg);
 	for (i = 0; i < cnt; i++) {
 		/*
-		 * free_by_rcu is only manipulated by irq work refill_work().
+		 * free_by_rcu_ttrace is only manipulated by irq work refill_work().
 		 * IRQ works on the same CPU are called sequentially, so it is
 		 * safe to use __llist_del_first() here. If alloc_bulk() is
 		 * invoked by the initial prefill, there will be no running
 		 * refill_work(), so __llist_del_first() is fine as well.
 		 *
-		 * In most cases, objects on free_by_rcu are from the same CPU.
+		 * In most cases, objects on free_by_rcu_ttrace are from the same CPU.
 		 * If some objects come from other CPUs, it doesn't incur any
 		 * harm because NUMA_NO_NODE means the preference for current
 		 * numa node and it is not a guarantee.
 		 */
-		obj = __llist_del_first(&c->free_by_rcu);
+		obj = __llist_del_first(&c->free_by_rcu_ttrace);
 		if (!obj) {
 			/* Allocate, but don't deplete atomic reserves that typical
 			 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
@@ -232,10 +233,10 @@ static void free_all(struct llist_node *llnode, bool percpu)
 
 static void __free_rcu(struct rcu_head *head)
 {
-	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace);
 
-	free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
-	atomic_set(&c->call_rcu_in_progress, 0);
+	free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+	atomic_set(&c->call_rcu_ttrace_in_progress, 0);
 }
 
 static void __free_rcu_tasks_trace(struct rcu_head *head)
@@ -254,32 +255,32 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj)
 	struct llist_node *llnode = obj;
 
 	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
-	 * Nothing races to add to free_by_rcu list.
+	 * Nothing races to add to free_by_rcu_ttrace list.
 	 */
-	__llist_add(llnode, &c->free_by_rcu);
+	__llist_add(llnode, &c->free_by_rcu_ttrace);
 }
 
-static void do_call_rcu(struct bpf_mem_cache *c)
+static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 {
 	struct llist_node *llnode, *t;
 
-	if (atomic_xchg(&c->call_rcu_in_progress, 1))
+	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1))
 		return;
 
-	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
-	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
-		/* There is no concurrent __llist_add(waiting_for_gp) access.
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu_ttrace))
+		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
 		 * It doesn't race with llist_del_all either.
-		 * But there could be two concurrent llist_del_all(waiting_for_gp):
+		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
 		 * from __free_rcu() and from drain_mem_cache().
 		 */
-		__llist_add(llnode, &c->waiting_for_gp);
+		__llist_add(llnode, &c->waiting_for_gp_ttrace);
 	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
 	 * If RCU Tasks Trace grace period implies RCU grace period, free
 	 * these elements directly, else use call_rcu() to wait for normal
 	 * progs to finish and finally do free_one() on each element.
 	 */
-	call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
+	call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace);
 }
 
 static void free_bulk(struct bpf_mem_cache *c)
@@ -307,7 +308,7 @@ static void free_bulk(struct bpf_mem_cache *c)
 	/* and drain free_llist_extra */
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
 		enque_to_free(c, llnode);
-	do_call_rcu(c);
+	do_call_rcu_ttrace(c);
 }
 
 static void bpf_mem_refill(struct irq_work *work)
@@ -441,13 +442,13 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 
 	/* No progs are using this bpf_mem_cache, but htab_map_free() called
 	 * bpf_mem_cache_free() for all remaining elements and they can be in
-	 * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+	 * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now.
 	 *
-	 * Except for waiting_for_gp list, there are no concurrent operations
+	 * Except for waiting_for_gp_ttrace list, there are no concurrent operations
 	 * on these lists, so it is safe to use __llist_del_all().
 	 */
-	free_all(__llist_del_all(&c->free_by_rcu), percpu);
-	free_all(llist_del_all(&c->waiting_for_gp), percpu);
+	free_all(__llist_del_all(&c->free_by_rcu_ttrace), percpu);
+	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
 	free_all(__llist_del_all(&c->free_llist), percpu);
 	free_all(__llist_del_all(&c->free_llist_extra), percpu);
 }
@@ -462,7 +463,7 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 
 static void free_mem_alloc(struct bpf_mem_alloc *ma)
 {
-	/* waiting_for_gp lists was drained, but __free_rcu might
+	/* waiting_for_gp_ttrace lists was drained, but __free_rcu might
 	 * still execute. Wait for it now before we freeing percpu caches.
 	 *
 	 * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(),
@@ -535,7 +536,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			 */
 			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
-			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
+			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 		}
 		/* objcg is the same across cpus */
 		if (c->objcg)
@@ -550,7 +551,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				c = &cc->cache[i];
 				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
-				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
+				rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 			}
 		}
 		if (c->objcg)
-- 
cgit v1.2.3


From a80672d7e10edab757e771a1864ea2e1b9a31ac9 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:35 -0700
Subject: bpf: Simplify code of destroy_mem_alloc() with kmemdup().

Use kmemdup() to simplify the code.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-3-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index cc5b8adb4c83..b0011217be6c 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -499,7 +499,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
 		return;
 	}
 
-	copy = kmalloc(sizeof(*ma), GFP_KERNEL);
+	copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL);
 	if (!copy) {
 		/* Slow path with inline barrier-s */
 		free_mem_alloc(ma);
@@ -507,10 +507,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
 	}
 
 	/* Defer barriers into worker to let the rest of map memory to be freed */
-	copy->cache = ma->cache;
-	ma->cache = NULL;
-	copy->caches = ma->caches;
-	ma->caches = NULL;
+	memset(ma, 0, sizeof(*ma));
 	INIT_WORK(&copy->work, free_mem_alloc_deferred);
 	queue_work(system_unbound_wq, &copy->work);
 }
-- 
cgit v1.2.3


From 9de3e81521b4d943c9ec27ae2c871292c12f1409 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:36 -0700
Subject: bpf: Let free_all() return the number of freed elements.

Let free_all() helper return the number of freed elements.
It's not used in this patch, but helps in debug/development of bpf_mem_alloc.

For example this diff for __free_rcu():
-       free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+       printk("cpu %d freed %d objs after tasks trace\n", raw_smp_processor_id(),
+       	free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size));

would show how busy RCU tasks trace is.
In artificial benchmark where one cpu is allocating and different cpu is freeing
the RCU tasks trace won't be able to keep up and the list of objects
would keep growing from thousands to millions and eventually OOMing.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-4-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index b0011217be6c..693651d2648b 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -223,12 +223,16 @@ static void free_one(void *obj, bool percpu)
 	kfree(obj);
 }
 
-static void free_all(struct llist_node *llnode, bool percpu)
+static int free_all(struct llist_node *llnode, bool percpu)
 {
 	struct llist_node *pos, *t;
+	int cnt = 0;
 
-	llist_for_each_safe(pos, t, llnode)
+	llist_for_each_safe(pos, t, llnode) {
 		free_one(pos, percpu);
+		cnt++;
+	}
+	return cnt;
 }
 
 static void __free_rcu(struct rcu_head *head)
-- 
cgit v1.2.3


From 05ae68656a8e9d9386ce4243fe992122fd29bb51 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:37 -0700
Subject: bpf: Refactor alloc_bulk().

Factor out inner body of alloc_bulk into separate helper.
No functional changes.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-5-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 46 ++++++++++++++++++++++++++--------------------
 1 file changed, 26 insertions(+), 20 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 693651d2648b..9693b1f8cbda 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -154,11 +154,35 @@ static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
 #endif
 }
 
+static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+{
+	unsigned long flags;
+
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		/* In RT irq_work runs in per-cpu kthread, so disable
+		 * interrupts to avoid preemption and interrupts and
+		 * reduce the chance of bpf prog executing on this cpu
+		 * when active counter is busy.
+		 */
+		local_irq_save(flags);
+	/* alloc_bulk runs from irq_work which will not preempt a bpf
+	 * program that does unit_alloc/unit_free since IRQs are
+	 * disabled there. There is no race to increment 'active'
+	 * counter. It protects free_llist from corruption in case NMI
+	 * bpf prog preempted this loop.
+	 */
+	WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+	__llist_add(obj, &c->free_llist);
+	c->free_cnt++;
+	local_dec(&c->active);
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_restore(flags);
+}
+
 /* Mostly runs from irq_work except __init phase. */
 static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 {
 	struct mem_cgroup *memcg = NULL, *old_memcg;
-	unsigned long flags;
 	void *obj;
 	int i;
 
@@ -188,25 +212,7 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 			if (!obj)
 				break;
 		}
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			/* In RT irq_work runs in per-cpu kthread, so disable
-			 * interrupts to avoid preemption and interrupts and
-			 * reduce the chance of bpf prog executing on this cpu
-			 * when active counter is busy.
-			 */
-			local_irq_save(flags);
-		/* alloc_bulk runs from irq_work which will not preempt a bpf
-		 * program that does unit_alloc/unit_free since IRQs are
-		 * disabled there. There is no race to increment 'active'
-		 * counter. It protects free_llist from corruption in case NMI
-		 * bpf prog preempted this loop.
-		 */
-		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
-		__llist_add(obj, &c->free_llist);
-		c->free_cnt++;
-		local_dec(&c->active);
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			local_irq_restore(flags);
+		add_obj_to_free_list(c, obj);
 	}
 	set_active_memcg(old_memcg);
 	mem_cgroup_put(memcg);
-- 
cgit v1.2.3


From 18e027b1c7c6dd858b36305468251a5e4a6bcdf7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:38 -0700
Subject: bpf: Factor out inc/dec of active flag into helpers.

Factor out local_inc/dec_return(&c->active) into helpers.
No functional changes.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-6-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 9693b1f8cbda..052fc801fb9f 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -154,17 +154,15 @@ static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
 #endif
 }
 
-static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+static void inc_active(struct bpf_mem_cache *c, unsigned long *flags)
 {
-	unsigned long flags;
-
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		/* In RT irq_work runs in per-cpu kthread, so disable
 		 * interrupts to avoid preemption and interrupts and
 		 * reduce the chance of bpf prog executing on this cpu
 		 * when active counter is busy.
 		 */
-		local_irq_save(flags);
+		local_irq_save(*flags);
 	/* alloc_bulk runs from irq_work which will not preempt a bpf
 	 * program that does unit_alloc/unit_free since IRQs are
 	 * disabled there. There is no race to increment 'active'
@@ -172,13 +170,25 @@ static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
 	 * bpf prog preempted this loop.
 	 */
 	WARN_ON_ONCE(local_inc_return(&c->active) != 1);
-	__llist_add(obj, &c->free_llist);
-	c->free_cnt++;
+}
+
+static void dec_active(struct bpf_mem_cache *c, unsigned long flags)
+{
 	local_dec(&c->active);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		local_irq_restore(flags);
 }
 
+static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
+{
+	unsigned long flags;
+
+	inc_active(c, &flags);
+	__llist_add(obj, &c->free_llist);
+	c->free_cnt++;
+	dec_active(c, flags);
+}
+
 /* Mostly runs from irq_work except __init phase. */
 static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 {
@@ -300,17 +310,13 @@ static void free_bulk(struct bpf_mem_cache *c)
 	int cnt;
 
 	do {
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			local_irq_save(flags);
-		WARN_ON_ONCE(local_inc_return(&c->active) != 1);
+		inc_active(c, &flags);
 		llnode = __llist_del_first(&c->free_llist);
 		if (llnode)
 			cnt = --c->free_cnt;
 		else
 			cnt = 0;
-		local_dec(&c->active);
-		if (IS_ENABLED(CONFIG_PREEMPT_RT))
-			local_irq_restore(flags);
+		dec_active(c, flags);
 		if (llnode)
 			enque_to_free(c, llnode);
 	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
-- 
cgit v1.2.3


From 7468048237b8a99c03e1325b11373f9b29ef4139 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:39 -0700
Subject: bpf: Further refactor alloc_bulk().

In certain scenarios alloc_bulk() might be taking free objects mainly from
free_by_rcu_ttrace list. In such case get_memcg() and set_active_memcg() are
redundant, but they show up in perf profile. Split the loop and only set memcg
when allocating from slab. No performance difference in this patch alone, but
it helps in combination with further patches.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-7-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 052fc801fb9f..0ee566a7719a 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -196,8 +196,6 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 	void *obj;
 	int i;
 
-	memcg = get_memcg(c);
-	old_memcg = set_active_memcg(memcg);
 	for (i = 0; i < cnt; i++) {
 		/*
 		 * free_by_rcu_ttrace is only manipulated by irq work refill_work().
@@ -212,16 +210,24 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 		 * numa node and it is not a guarantee.
 		 */
 		obj = __llist_del_first(&c->free_by_rcu_ttrace);
-		if (!obj) {
-			/* Allocate, but don't deplete atomic reserves that typical
-			 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
-			 * will allocate from the current numa node which is what we
-			 * want here.
-			 */
-			obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
-			if (!obj)
-				break;
-		}
+		if (!obj)
+			break;
+		add_obj_to_free_list(c, obj);
+	}
+	if (i >= cnt)
+		return;
+
+	memcg = get_memcg(c);
+	old_memcg = set_active_memcg(memcg);
+	for (; i < cnt; i++) {
+		/* Allocate, but don't deplete atomic reserves that typical
+		 * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
+		 * will allocate from the current numa node which is what we
+		 * want here.
+		 */
+		obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
+		if (!obj)
+			break;
 		add_obj_to_free_list(c, obj);
 	}
 	set_active_memcg(old_memcg);
-- 
cgit v1.2.3


From d114dde245f9115b73756203b03a633a6fc1b36a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:40 -0700
Subject: bpf: Change bpf_mem_cache draining process.

The next patch will introduce cross-cpu llist access and existing
irq_work_sync() + drain_mem_cache() + rcu_barrier_tasks_trace() mechanism will
not be enough, since irq_work_sync() + drain_mem_cache() on cpu A won't
guarantee that llist on cpu A are empty. The free_bulk() on cpu B might add
objects back to llist of cpu A. Add 'bool draining' flag.
The modified sequence looks like:
for_each_cpu:
  WRITE_ONCE(c->draining, true); // do_call_rcu_ttrace() won't be doing call_rcu() any more
  irq_work_sync(); // wait for irq_work callback (free_bulk) to finish
  drain_mem_cache(); // free all objects
rcu_barrier_tasks_trace(); // wait for RCU callbacks to execute

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-8-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 0ee566a7719a..2615f296f052 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -98,6 +98,7 @@ struct bpf_mem_cache {
 	int free_cnt;
 	int low_watermark, high_watermark, batch;
 	int percpu_size;
+	bool draining;
 
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
@@ -301,6 +302,12 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 		 * from __free_rcu() and from drain_mem_cache().
 		 */
 		__llist_add(llnode, &c->waiting_for_gp_ttrace);
+
+	if (unlikely(READ_ONCE(c->draining))) {
+		__free_rcu(&c->rcu_ttrace);
+		return;
+	}
+
 	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
 	 * If RCU Tasks Trace grace period implies RCU grace period, free
 	 * these elements directly, else use call_rcu() to wait for normal
@@ -544,15 +551,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 		rcu_in_progress = 0;
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(ma->cache, cpu);
-			/*
-			 * refill_work may be unfinished for PREEMPT_RT kernel
-			 * in which irq work is invoked in a per-CPU RT thread.
-			 * It is also possible for kernel with
-			 * arch_irq_work_has_interrupt() being false and irq
-			 * work is invoked in timer interrupt. So waiting for
-			 * the completion of irq work to ease the handling of
-			 * concurrency.
-			 */
+			WRITE_ONCE(c->draining, true);
 			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
@@ -568,6 +567,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			cc = per_cpu_ptr(ma->caches, cpu);
 			for (i = 0; i < NUM_CACHES; i++) {
 				c = &cc->cache[i];
+				WRITE_ONCE(c->draining, true);
 				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
 				rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
-- 
cgit v1.2.3


From 822fb26bdb55932d0635f43cc418d2004b19e358 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:41 -0700
Subject: bpf: Add a hint to allocated objects.

To address OOM issue when one cpu is allocating and another cpu is freeing add
a target bpf_mem_cache hint to allocated objects and when local cpu free_llist
overflows free to that bpf_mem_cache. The hint addresses the OOM while
maintaining the same performance for common case when alloc/free are done on the
same cpu.

Note that do_call_rcu_ttrace() now has to check 'draining' flag in one more case,
since do_call_rcu_ttrace() is called not only for current cpu.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-9-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 50 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 19 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 2615f296f052..9986c6b7df4d 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -99,6 +99,7 @@ struct bpf_mem_cache {
 	int low_watermark, high_watermark, batch;
 	int percpu_size;
 	bool draining;
+	struct bpf_mem_cache *tgt;
 
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
@@ -199,18 +200,11 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 
 	for (i = 0; i < cnt; i++) {
 		/*
-		 * free_by_rcu_ttrace is only manipulated by irq work refill_work().
-		 * IRQ works on the same CPU are called sequentially, so it is
-		 * safe to use __llist_del_first() here. If alloc_bulk() is
-		 * invoked by the initial prefill, there will be no running
-		 * refill_work(), so __llist_del_first() is fine as well.
-		 *
-		 * In most cases, objects on free_by_rcu_ttrace are from the same CPU.
-		 * If some objects come from other CPUs, it doesn't incur any
-		 * harm because NUMA_NO_NODE means the preference for current
-		 * numa node and it is not a guarantee.
+		 * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
+		 * done only by one CPU == current CPU. Other CPUs might
+		 * llist_add() and llist_del_all() in parallel.
 		 */
-		obj = __llist_del_first(&c->free_by_rcu_ttrace);
+		obj = llist_del_first(&c->free_by_rcu_ttrace);
 		if (!obj)
 			break;
 		add_obj_to_free_list(c, obj);
@@ -284,18 +278,23 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj)
 	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
 	 * Nothing races to add to free_by_rcu_ttrace list.
 	 */
-	__llist_add(llnode, &c->free_by_rcu_ttrace);
+	llist_add(llnode, &c->free_by_rcu_ttrace);
 }
 
 static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 {
 	struct llist_node *llnode, *t;
 
-	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1))
+	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) {
+		if (unlikely(READ_ONCE(c->draining))) {
+			llnode = llist_del_all(&c->free_by_rcu_ttrace);
+			free_all(llnode, !!c->percpu_size);
+		}
 		return;
+	}
 
 	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
-	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu_ttrace))
+	llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace))
 		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
 		 * It doesn't race with llist_del_all either.
 		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
@@ -318,10 +317,13 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 
 static void free_bulk(struct bpf_mem_cache *c)
 {
+	struct bpf_mem_cache *tgt = c->tgt;
 	struct llist_node *llnode, *t;
 	unsigned long flags;
 	int cnt;
 
+	WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+
 	do {
 		inc_active(c, &flags);
 		llnode = __llist_del_first(&c->free_llist);
@@ -331,13 +333,13 @@ static void free_bulk(struct bpf_mem_cache *c)
 			cnt = 0;
 		dec_active(c, flags);
 		if (llnode)
-			enque_to_free(c, llnode);
+			enque_to_free(tgt, llnode);
 	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
 
 	/* and drain free_llist_extra */
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
-		enque_to_free(c, llnode);
-	do_call_rcu_ttrace(c);
+		enque_to_free(tgt, llnode);
+	do_call_rcu_ttrace(tgt);
 }
 
 static void bpf_mem_refill(struct irq_work *work)
@@ -436,6 +438,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->unit_size = unit_size;
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
+			c->tgt = c;
 			prefill_mem_cache(c, cpu);
 		}
 		ma->cache = pc;
@@ -458,6 +461,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c = &cc->cache[i];
 			c->unit_size = sizes[i];
 			c->objcg = objcg;
+			c->tgt = c;
 			prefill_mem_cache(c, cpu);
 		}
 	}
@@ -476,7 +480,7 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	 * Except for waiting_for_gp_ttrace list, there are no concurrent operations
 	 * on these lists, so it is safe to use __llist_del_all().
 	 */
-	free_all(__llist_del_all(&c->free_by_rcu_ttrace), percpu);
+	free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu);
 	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
 	free_all(__llist_del_all(&c->free_llist), percpu);
 	free_all(__llist_del_all(&c->free_llist_extra), percpu);
@@ -601,8 +605,10 @@ static void notrace *unit_alloc(struct bpf_mem_cache *c)
 	local_irq_save(flags);
 	if (local_inc_return(&c->active) == 1) {
 		llnode = __llist_del_first(&c->free_llist);
-		if (llnode)
+		if (llnode) {
 			cnt = --c->free_cnt;
+			*(struct bpf_mem_cache **)llnode = c;
+		}
 	}
 	local_dec(&c->active);
 	local_irq_restore(flags);
@@ -626,6 +632,12 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
 
 	BUILD_BUG_ON(LLIST_NODE_SZ > 8);
 
+	/*
+	 * Remember bpf_mem_cache that allocated this object.
+	 * The hint is not accurate.
+	 */
+	c->tgt = *(struct bpf_mem_cache **)llnode;
+
 	local_irq_save(flags);
 	if (local_inc_return(&c->active) == 1) {
 		__llist_add(llnode, &c->free_llist);
-- 
cgit v1.2.3


From 04fabf00b4d3aff5d010ecb617001814e409e24a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:42 -0700
Subject: bpf: Allow reuse from waiting_for_gp_ttrace list.

alloc_bulk() can reuse elements from free_by_rcu_ttrace.
Let it reuse from waiting_for_gp_ttrace as well to avoid unnecessary kmalloc().

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230706033447.54696-10-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 9986c6b7df4d..e5a87f6cf2cc 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -212,6 +212,15 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 	if (i >= cnt)
 		return;
 
+	for (; i < cnt; i++) {
+		obj = llist_del_first(&c->waiting_for_gp_ttrace);
+		if (!obj)
+			break;
+		add_obj_to_free_list(c, obj);
+	}
+	if (i >= cnt)
+		return;
+
 	memcg = get_memcg(c);
 	old_memcg = set_active_memcg(memcg);
 	for (; i < cnt; i++) {
@@ -295,12 +304,7 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 
 	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace))
-		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
-		 * It doesn't race with llist_del_all either.
-		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
-		 * from __free_rcu() and from drain_mem_cache().
-		 */
-		__llist_add(llnode, &c->waiting_for_gp_ttrace);
+		llist_add(llnode, &c->waiting_for_gp_ttrace);
 
 	if (unlikely(READ_ONCE(c->draining))) {
 		__free_rcu(&c->rcu_ttrace);
-- 
cgit v1.2.3


From 43a89baecfe200cb4530f42b9fcf904925d6d14a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 5 Jul 2023 20:34:43 -0700
Subject: rcu: Export rcu_request_urgent_qs_task()

If a CPU is executing a long series of non-sleeping system calls,
RCU grace periods can be delayed for on the order of a couple hundred
milliseconds.  This is normally not a problem, but if each system call
does a call_rcu(), those callbacks can stack up.  RCU will eventually
notice this callback storm, but use of rcu_request_urgent_qs_task()
allows the code invoking call_rcu() to give RCU a heads up.

This function is not for general use, not yet, anyway.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230706033447.54696-11-alexei.starovoitov@gmail.com
---
 kernel/rcu/rcu.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98c1544cf572..f95cfb5bf2ee 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -493,7 +493,6 @@ static inline void rcu_expedite_gp(void) { }
 static inline void rcu_unexpedite_gp(void) { }
 static inline void rcu_async_hurry(void) { }
 static inline void rcu_async_relax(void) { }
-static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 bool rcu_gp_is_normal(void);     /* Internal RCU use. */
 bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
@@ -508,7 +507,6 @@ void show_rcu_tasks_gp_kthreads(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void show_rcu_tasks_gp_kthreads(void) {}
 #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
-void rcu_request_urgent_qs_task(struct task_struct *t);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #define RCU_SCHEDULER_INACTIVE	0
-- 
cgit v1.2.3


From 5af6807bdb10d1af9d412d7d6c177ba8440adffb Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:45 -0700
Subject: bpf: Introduce bpf_mem_free_rcu() similar to kfree_rcu().

Introduce bpf_mem_[cache_]free_rcu() similar to kfree_rcu().
Unlike bpf_mem_[cache_]free() that links objects for immediate reuse into
per-cpu free list the _rcu() flavor waits for RCU grace period and then moves
objects into free_by_rcu_ttrace list where they are waiting for RCU
task trace grace period to be freed into slab.

The life cycle of objects:
alloc: dequeue free_llist
free: enqeueu free_llist
free_rcu: enqueue free_by_rcu -> waiting_for_gp
free_llist above high watermark -> free_by_rcu_ttrace
after RCU GP waiting_for_gp -> free_by_rcu_ttrace
free_by_rcu_ttrace -> waiting_for_gp_ttrace -> slab

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-13-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 129 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 126 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index e5a87f6cf2cc..17ef2e9b278a 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -101,6 +101,15 @@ struct bpf_mem_cache {
 	bool draining;
 	struct bpf_mem_cache *tgt;
 
+	/* list of objects to be freed after RCU GP */
+	struct llist_head free_by_rcu;
+	struct llist_node *free_by_rcu_tail;
+	struct llist_head waiting_for_gp;
+	struct llist_node *waiting_for_gp_tail;
+	struct rcu_head rcu;
+	atomic_t call_rcu_in_progress;
+	struct llist_head free_llist_extra_rcu;
+
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
 	struct llist_head waiting_for_gp_ttrace;
@@ -346,6 +355,69 @@ static void free_bulk(struct bpf_mem_cache *c)
 	do_call_rcu_ttrace(tgt);
 }
 
+static void __free_by_rcu(struct rcu_head *head)
+{
+	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
+	struct bpf_mem_cache *tgt = c->tgt;
+	struct llist_node *llnode;
+
+	llnode = llist_del_all(&c->waiting_for_gp);
+	if (!llnode)
+		goto out;
+
+	llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace);
+
+	/* Objects went through regular RCU GP. Send them to RCU tasks trace */
+	do_call_rcu_ttrace(tgt);
+out:
+	atomic_set(&c->call_rcu_in_progress, 0);
+}
+
+static void check_free_by_rcu(struct bpf_mem_cache *c)
+{
+	struct llist_node *llnode, *t;
+	unsigned long flags;
+
+	/* drain free_llist_extra_rcu */
+	if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) {
+		inc_active(c, &flags);
+		llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu))
+			if (__llist_add(llnode, &c->free_by_rcu))
+				c->free_by_rcu_tail = llnode;
+		dec_active(c, flags);
+	}
+
+	if (llist_empty(&c->free_by_rcu))
+		return;
+
+	if (atomic_xchg(&c->call_rcu_in_progress, 1)) {
+		/*
+		 * Instead of kmalloc-ing new rcu_head and triggering 10k
+		 * call_rcu() to hit rcutree.qhimark and force RCU to notice
+		 * the overload just ask RCU to hurry up. There could be many
+		 * objects in free_by_rcu list.
+		 * This hint reduces memory consumption for an artificial
+		 * benchmark from 2 Gbyte to 150 Mbyte.
+		 */
+		rcu_request_urgent_qs_task(current);
+		return;
+	}
+
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+
+	inc_active(c, &flags);
+	WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu));
+	c->waiting_for_gp_tail = c->free_by_rcu_tail;
+	dec_active(c, flags);
+
+	if (unlikely(READ_ONCE(c->draining))) {
+		free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
+		atomic_set(&c->call_rcu_in_progress, 0);
+	} else {
+		call_rcu_hurry(&c->rcu, __free_by_rcu);
+	}
+}
+
 static void bpf_mem_refill(struct irq_work *work)
 {
 	struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work);
@@ -360,6 +432,8 @@ static void bpf_mem_refill(struct irq_work *work)
 		alloc_bulk(c, c->batch, NUMA_NO_NODE);
 	else if (cnt > c->high_watermark)
 		free_bulk(c);
+
+	check_free_by_rcu(c);
 }
 
 static void notrace irq_work_raise(struct bpf_mem_cache *c)
@@ -488,6 +562,9 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
 	free_all(__llist_del_all(&c->free_llist), percpu);
 	free_all(__llist_del_all(&c->free_llist_extra), percpu);
+	free_all(__llist_del_all(&c->free_by_rcu), percpu);
+	free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu);
+	free_all(llist_del_all(&c->waiting_for_gp), percpu);
 }
 
 static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
@@ -500,8 +577,8 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 
 static void free_mem_alloc(struct bpf_mem_alloc *ma)
 {
-	/* waiting_for_gp_ttrace lists was drained, but __free_rcu might
-	 * still execute. Wait for it now before we freeing percpu caches.
+	/* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks
+	 * might still execute. Wait for them.
 	 *
 	 * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(),
 	 * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used
@@ -510,7 +587,8 @@ static void free_mem_alloc(struct bpf_mem_alloc *ma)
 	 * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by
 	 * using rcu_trace_implies_rcu_gp() as well.
 	 */
-	rcu_barrier_tasks_trace();
+	rcu_barrier(); /* wait for __free_by_rcu */
+	rcu_barrier_tasks_trace(); /* wait for __free_rcu */
 	if (!rcu_trace_implies_rcu_gp())
 		rcu_barrier();
 	free_mem_alloc_no_barrier(ma);
@@ -563,6 +641,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
+			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
 		/* objcg is the same across cpus */
 		if (c->objcg)
@@ -579,6 +658,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
 				rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
+				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
 		}
 		if (c->objcg)
@@ -663,6 +743,27 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
 		irq_work_raise(c);
 }
 
+static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr)
+{
+	struct llist_node *llnode = ptr - LLIST_NODE_SZ;
+	unsigned long flags;
+
+	c->tgt = *(struct bpf_mem_cache **)llnode;
+
+	local_irq_save(flags);
+	if (local_inc_return(&c->active) == 1) {
+		if (__llist_add(llnode, &c->free_by_rcu))
+			c->free_by_rcu_tail = llnode;
+	} else {
+		llist_add(llnode, &c->free_llist_extra_rcu);
+	}
+	local_dec(&c->active);
+	local_irq_restore(flags);
+
+	if (!atomic_read(&c->call_rcu_in_progress))
+		irq_work_raise(c);
+}
+
 /* Called from BPF program or from sys_bpf syscall.
  * In both cases migration is disabled.
  */
@@ -696,6 +797,20 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
 	unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
 }
 
+void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
+{
+	int idx;
+
+	if (!ptr)
+		return;
+
+	idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ));
+	if (idx < 0)
+		return;
+
+	unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr);
+}
+
 void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma)
 {
 	void *ret;
@@ -712,6 +827,14 @@ void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr)
 	unit_free(this_cpu_ptr(ma->cache), ptr);
 }
 
+void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
+{
+	if (!ptr)
+		return;
+
+	unit_free_rcu(this_cpu_ptr(ma->cache), ptr);
+}
+
 /* Directly does a kfree() without putting 'ptr' back to the free_llist
  * for reuse and without waiting for a rcu_tasks_trace gp.
  * The caller must first go through the rcu_tasks_trace gp for 'ptr'
-- 
cgit v1.2.3


From 8e07bb9ebcd9b9ddf58337253ee5522d86b99370 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 5 Jul 2023 20:34:46 -0700
Subject: bpf: Convert bpf_cpumask to bpf_mem_cache_free_rcu.

Convert bpf_cpumask to bpf_mem_cache_free_rcu.
Note that migrate_disable() in bpf_cpumask_release() is still necessary, since
bpf_cpumask_release() is a dtor. bpf_obj_free_fields() can be converted to do
migrate_disable() there in a follow up.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20230706033447.54696-14-alexei.starovoitov@gmail.com
---
 kernel/bpf/cpumask.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 938a60ff4295..6983af8e093c 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -9,7 +9,6 @@
 /**
  * struct bpf_cpumask - refcounted BPF cpumask wrapper structure
  * @cpumask:	The actual cpumask embedded in the struct.
- * @rcu:	The RCU head used to free the cpumask with RCU safety.
  * @usage:	Object reference counter. When the refcount goes to 0, the
  *		memory is released back to the BPF allocator, which provides
  *		RCU safety.
@@ -25,7 +24,6 @@
  */
 struct bpf_cpumask {
 	cpumask_t cpumask;
-	struct rcu_head rcu;
 	refcount_t usage;
 };
 
@@ -82,16 +80,6 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask)
 	return cpumask;
 }
 
-static void cpumask_free_cb(struct rcu_head *head)
-{
-	struct bpf_cpumask *cpumask;
-
-	cpumask = container_of(head, struct bpf_cpumask, rcu);
-	migrate_disable();
-	bpf_mem_cache_free(&bpf_cpumask_ma, cpumask);
-	migrate_enable();
-}
-
 /**
  * bpf_cpumask_release() - Release a previously acquired BPF cpumask.
  * @cpumask: The cpumask being released.
@@ -102,8 +90,12 @@ static void cpumask_free_cb(struct rcu_head *head)
  */
 __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
 {
-	if (refcount_dec_and_test(&cpumask->usage))
-		call_rcu(&cpumask->rcu, cpumask_free_cb);
+	if (!refcount_dec_and_test(&cpumask->usage))
+		return;
+
+	migrate_disable();
+	bpf_mem_cache_free_rcu(&bpf_cpumask_ma, cpumask);
+	migrate_enable();
 }
 
 /**
-- 
cgit v1.2.3


From 4ed8b5bcfada6687baa478bf8febe891d9107118 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Wed, 5 Jul 2023 20:34:47 -0700
Subject: bpf: Add object leak check.

The object leak check is cheap. Do it unconditionally to spot difficult races
in bpf_mem_alloc.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20230706033447.54696-15-alexei.starovoitov@gmail.com
---
 kernel/bpf/memalloc.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

(limited to 'kernel')

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 17ef2e9b278a..51d6389e5152 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -567,8 +567,43 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	free_all(llist_del_all(&c->waiting_for_gp), percpu);
 }
 
+static void check_mem_cache(struct bpf_mem_cache *c)
+{
+	WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace));
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
+	WARN_ON_ONCE(!llist_empty(&c->free_llist));
+	WARN_ON_ONCE(!llist_empty(&c->free_llist_extra));
+	WARN_ON_ONCE(!llist_empty(&c->free_by_rcu));
+	WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu));
+	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
+}
+
+static void check_leaked_objs(struct bpf_mem_alloc *ma)
+{
+	struct bpf_mem_caches *cc;
+	struct bpf_mem_cache *c;
+	int cpu, i;
+
+	if (ma->cache) {
+		for_each_possible_cpu(cpu) {
+			c = per_cpu_ptr(ma->cache, cpu);
+			check_mem_cache(c);
+		}
+	}
+	if (ma->caches) {
+		for_each_possible_cpu(cpu) {
+			cc = per_cpu_ptr(ma->caches, cpu);
+			for (i = 0; i < NUM_CACHES; i++) {
+				c = &cc->cache[i];
+				check_mem_cache(c);
+			}
+		}
+	}
+}
+
 static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 {
+	check_leaked_objs(ma);
 	free_percpu(ma->cache);
 	free_percpu(ma->caches);
 	ma->cache = NULL;
-- 
cgit v1.2.3


From 7ce4dc3e4a9d954c8a1fb483c7a527e9b060b860 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Jul 2023 02:56:39 +0000
Subject: bpf: Fix an error around PTR_UNTRUSTED

Per discussion with Alexei, the PTR_UNTRUSTED flag should not been
cleared when we start to walk a new struct, because the struct in
question may be a struct nested in a union. We should also check and set
this flag before we walk its each member, in case itself is a union.
We will clear this flag if the field is BTF_TYPE_SAFE_RCU_OR_NULL.

Fixes: 6fcd486b3a0a ("bpf: Refactor RCU enforcement in the verifier.")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230713025642.27477-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c      | 20 +++++++++-----------
 kernel/bpf/verifier.c |  5 +++++
 2 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'kernel')

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3dd47451f097..fae6fc24a845 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6133,7 +6133,6 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 	const char *tname, *mname, *tag_value;
 	u32 vlen, elem_id, mid;
 
-	*flag = 0;
 again:
 	if (btf_type_is_modifier(t))
 		t = btf_type_skip_modifiers(btf, t->type, NULL);
@@ -6144,6 +6143,14 @@ again:
 	}
 
 	vlen = btf_type_vlen(t);
+	if (BTF_INFO_KIND(t->info) == BTF_KIND_UNION && vlen != 1 && !(*flag & PTR_UNTRUSTED))
+		/*
+		 * walking unions yields untrusted pointers
+		 * with exception of __bpf_md_ptr and other
+		 * unions with a single member
+		 */
+		*flag |= PTR_UNTRUSTED;
+
 	if (off + size > t->size) {
 		/* If the last element is a variable size array, we may
 		 * need to relax the rule.
@@ -6304,15 +6311,6 @@ error:
 		 * of this field or inside of this struct
 		 */
 		if (btf_type_is_struct(mtype)) {
-			if (BTF_INFO_KIND(mtype->info) == BTF_KIND_UNION &&
-			    btf_type_vlen(mtype) != 1)
-				/*
-				 * walking unions yields untrusted pointers
-				 * with exception of __bpf_md_ptr and other
-				 * unions with a single member
-				 */
-				*flag |= PTR_UNTRUSTED;
-
 			/* our field must be inside that union or struct */
 			t = mtype;
 
@@ -6478,7 +6476,7 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  bool strict)
 {
 	const struct btf_type *type;
-	enum bpf_type_flag flag;
+	enum bpf_type_flag flag = 0;
 	int err;
 
 	/* Are we already done? */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 81a93eeac7a0..584eb34dce8a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6067,6 +6067,11 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 				   type_is_rcu_or_null(env, reg, field_name, btf_id)) {
 				/* __rcu tagged pointers can be NULL */
 				flag |= MEM_RCU | PTR_MAYBE_NULL;
+
+				/* We always trust them */
+				if (type_is_rcu_or_null(env, reg, field_name, btf_id) &&
+				    flag & PTR_UNTRUSTED)
+					flag &= ~PTR_UNTRUSTED;
 			} else if (flag & (MEM_PERCPU | MEM_USER)) {
 				/* keep as-is */
 			} else {
-- 
cgit v1.2.3


From 33937607efa050d9e237e0c4ac4ada02d961c466 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 13 Jul 2023 02:56:41 +0000
Subject: bpf: Fix an error in verifying a field in a union

We are utilizing BPF LSM to monitor BPF operations within our container
environment. When we add support for raw_tracepoint, it hits below
error.

; (const void *)attr->raw_tracepoint.name);
27: (79) r3 = *(u64 *)(r2 +0)
access beyond the end of member map_type (mend:4) in struct (anon) with off 0 size 8

It can be reproduced with below BPF prog.

SEC("lsm/bpf")
int BPF_PROG(bpf_audit, int cmd, union bpf_attr *attr, unsigned int size)
{
	switch (cmd) {
	case BPF_RAW_TRACEPOINT_OPEN:
		bpf_printk("raw_tracepoint is %s", attr->raw_tracepoint.name);
		break;
	default:
		break;
	}
	return 0;
}

The reason is that when accessing a field in a union, such as bpf_attr,
if the field is located within a nested struct that is not the first
member of the union, it can result in incorrect field verification.

  union bpf_attr {
      struct {
          __u32 map_type; <<<< Actually it will find that field.
          __u32 key_size;
          __u32 value_size;
         ...
      };
      ...
      struct {
          __u64 name;    <<<< We want to verify this field.
          __u32 prog_fd;
      } raw_tracepoint;
  };

Considering the potential deep nesting levels, finding a perfect
solution to address this issue has proven challenging. Therefore, I
propose a solution where we simply skip the verification process if the
field in question is located within a union.

Fixes: 7e3617a72df3 ("bpf: Add array support to btf_struct_access")
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20230713025642.27477-4-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index fae6fc24a845..a542760c807a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6368,7 +6368,7 @@ error:
 		 * that also allows using an array of int as a scratch
 		 * space. e.g. skb->cb[].
 		 */
-		if (off + size > mtrue_end) {
+		if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) {
 			bpf_log(log,
 				"access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n",
 				mname, mtrue_end, tname, off, size);
-- 
cgit v1.2.3