aboutsummaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/Kconfig1
-rw-r--r--kernel/bpf/Makefile3
-rw-r--r--kernel/bpf/arraymap.c58
-rw-r--r--kernel/bpf/bpf_iter.c8
-rw-r--r--kernel/bpf/bpf_local_storage.c49
-rw-r--r--kernel/bpf/bpf_lru_list.h1
-rw-r--r--kernel/bpf/bpf_struct_ops.c47
-rw-r--r--kernel/bpf/btf.c64
-rw-r--r--kernel/bpf/cgroup.c66
-rw-r--r--kernel/bpf/cgroup_iter.c65
-rw-r--r--kernel/bpf/core.c249
-rw-r--r--kernel/bpf/cpumap.c126
-rw-r--r--kernel/bpf/cpumask.c26
-rw-r--r--kernel/bpf/devmap.c12
-rw-r--r--kernel/bpf/disasm.c58
-rw-r--r--kernel/bpf/hashtab.c29
-rw-r--r--kernel/bpf/helpers.c203
-rw-r--r--kernel/bpf/inode.c7
-rw-r--r--kernel/bpf/map_iter.c40
-rw-r--r--kernel/bpf/memalloc.c526
-rw-r--r--kernel/bpf/mprog.c452
-rw-r--r--kernel/bpf/offload.c31
-rw-r--r--kernel/bpf/preload/iterators/Makefile2
-rw-r--r--kernel/bpf/preload/iterators/iterators.bpf.c9
-rw-r--r--kernel/bpf/preload/iterators/iterators.lskel-little-endian.h526
-rw-r--r--kernel/bpf/queue_stack_maps.c21
-rw-r--r--kernel/bpf/ringbuf.c29
-rw-r--r--kernel/bpf/stackmap.c2
-rw-r--r--kernel/bpf/syscall.c444
-rw-r--r--kernel/bpf/task_iter.c286
-rw-r--r--kernel/bpf/tcx.c346
-rw-r--r--kernel/bpf/trampoline.c9
-rw-r--r--kernel/bpf/verifier.c2319
33 files changed, 4752 insertions, 1362 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
index 2dfe1079f772..6a906ff93006 100644
--- a/kernel/bpf/Kconfig
+++ b/kernel/bpf/Kconfig
@@ -31,6 +31,7 @@ config BPF_SYSCALL
select TASKS_TRACE_RCU
select BINARY_PRINTF
select NET_SOCK_MSG if NET
+ select NET_XGRESS if NET
select PAGE_POOL if NET
default n
help
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 1d3892168d32..f526b7573e97 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
-obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o
obj-$(CONFIG_BPF_JIT) += trampoline.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o
obj-$(CONFIG_BPF_JIT) += dispatcher.o
@@ -21,6 +21,7 @@ obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
obj-$(CONFIG_BPF_SYSCALL) += offload.o
obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
+obj-$(CONFIG_BPF_SYSCALL) += tcx.o
endif
ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..c85ff9162a5c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
mutex_unlock(&aux->poke_mutex);
}
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+ struct bpf_prog *new, struct bpf_prog *old)
+{
+ WARN_ON_ONCE(1);
+}
+
static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
struct bpf_prog *old,
struct bpf_prog *new)
{
- u8 *old_addr, *new_addr, *old_bypass_addr;
struct prog_poke_elem *elem;
struct bpf_array_aux *aux;
@@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
list_for_each_entry(elem, &aux->poke_progs, list) {
struct bpf_jit_poke_descriptor *poke;
- int i, ret;
+ int i;
for (i = 0; i < elem->aux->size_poke_tab; i++) {
poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
* activated, so tail call updates can arrive from here
* while JIT is still finishing its final fixup for
* non-activated poke entries.
- * 3) On program teardown, the program's kallsym entry gets
- * removed out of RCU callback, but we can only untrack
- * from sleepable context, therefore bpf_arch_text_poke()
- * might not see that this is in BPF text section and
- * bails out with -EINVAL. As these are unreachable since
- * RCU grace period already passed, we simply skip them.
- * 4) Also programs reaching refcount of zero while patching
+ * 3) Also programs reaching refcount of zero while patching
* is in progress is okay since we're protected under
* poke_mutex and untrack the programs before the JIT
- * buffer is freed. When we're still in the middle of
- * patching and suddenly kallsyms entry of the program
- * gets evicted, we just skip the rest which is fine due
- * to point 3).
- * 5) Any other error happening below from bpf_arch_text_poke()
- * is a unexpected bug.
+ * buffer is freed.
*/
if (!READ_ONCE(poke->tailcall_target_stable))
continue;
@@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
poke->tail_call.key != key)
continue;
- old_bypass_addr = old ? NULL : poke->bypass_addr;
- old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
- new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
- if (new) {
- ret = bpf_arch_text_poke(poke->tailcall_target,
- BPF_MOD_JUMP,
- old_addr, new_addr);
- BUG_ON(ret < 0 && ret != -EINVAL);
- if (!old) {
- ret = bpf_arch_text_poke(poke->tailcall_bypass,
- BPF_MOD_JUMP,
- poke->bypass_addr,
- NULL);
- BUG_ON(ret < 0 && ret != -EINVAL);
- }
- } else {
- ret = bpf_arch_text_poke(poke->tailcall_bypass,
- BPF_MOD_JUMP,
- old_bypass_addr,
- poke->bypass_addr);
- BUG_ON(ret < 0 && ret != -EINVAL);
- /* let other CPUs finish the execution of program
- * so that it will not possible to expose them
- * to invalid nop, stack unwind, nop state
- */
- if (!ret)
- synchronize_rcu();
- ret = bpf_arch_text_poke(poke->tailcall_target,
- BPF_MOD_JUMP,
- old_addr, NULL);
- BUG_ON(ret < 0 && ret != -EINVAL);
- }
+ bpf_arch_poke_desc_update(poke, new, old);
}
}
}
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 96856f130cbf..0fae79164187 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -782,9 +782,7 @@ struct bpf_iter_num_kern {
int end; /* final value, exclusive */
} __aligned(8);
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
{
@@ -793,8 +791,6 @@ __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num));
BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num));
- BTF_TYPE_EMIT(struct btf_iter_num);
-
/* start == end is legit, it's an empty range and we'll just get NULL
* on first (and any subsequent) bpf_iter_num_next() call
*/
@@ -845,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it)
s->cur = s->end = 0;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b5149cfce7d4..146824cc9689 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -553,7 +553,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
void *value, u64 map_flags, gfp_t gfp_flags)
{
struct bpf_local_storage_data *old_sdata = NULL;
- struct bpf_local_storage_elem *selem = NULL;
+ struct bpf_local_storage_elem *alloc_selem, *selem = NULL;
struct bpf_local_storage *local_storage;
unsigned long flags;
int err;
@@ -607,11 +607,12 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
}
}
- if (gfp_flags == GFP_KERNEL) {
- selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
- if (!selem)
- return ERR_PTR(-ENOMEM);
- }
+ /* A lookup has just been done before and concluded a new selem is
+ * needed. The chance of an unnecessary alloc is unlikely.
+ */
+ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
+ if (!alloc_selem)
+ return ERR_PTR(-ENOMEM);
raw_spin_lock_irqsave(&local_storage->lock, flags);
@@ -623,13 +624,13 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
* simple.
*/
err = -EAGAIN;
- goto unlock_err;
+ goto unlock;
}
old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
err = check_flags(old_sdata, map_flags);
if (err)
- goto unlock_err;
+ goto unlock;
if (old_sdata && (map_flags & BPF_F_LOCK)) {
copy_map_value_locked(&smap->map, old_sdata->data, value,
@@ -638,23 +639,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
goto unlock;
}
- if (gfp_flags != GFP_KERNEL) {
- /* local_storage->lock is held. Hence, we are sure
- * we can unlink and uncharge the old_sdata successfully
- * later. Hence, instead of charging the new selem now
- * and then uncharge the old selem later (which may cause
- * a potential but unnecessary charge failure), avoid taking
- * a charge at all here (the "!old_sdata" check) and the
- * old_sdata will not be uncharged later during
- * bpf_selem_unlink_storage_nolock().
- */
- selem = bpf_selem_alloc(smap, owner, value, !old_sdata, gfp_flags);
- if (!selem) {
- err = -ENOMEM;
- goto unlock_err;
- }
- }
-
+ alloc_selem = NULL;
/* First, link the new selem to the map */
bpf_selem_link_map(smap, selem);
@@ -665,20 +650,16 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
if (old_sdata) {
bpf_selem_unlink_map(SELEM(old_sdata));
bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
- false, false);
+ true, false);
}
unlock:
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
- return SDATA(selem);
-
-unlock_err:
- raw_spin_unlock_irqrestore(&local_storage->lock, flags);
- if (selem) {
+ if (alloc_selem) {
mem_uncharge(smap, owner, smap->elem_size);
- bpf_selem_free(selem, smap, true);
+ bpf_selem_free(alloc_selem, smap, true);
}
- return ERR_PTR(err);
+ return err ? ERR_PTR(err) : SDATA(selem);
}
static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
@@ -779,7 +760,7 @@ void bpf_local_storage_destroy(struct bpf_local_storage *local_storage)
* of the loop will set the free_cgroup_storage to true.
*/
free_storage = bpf_selem_unlink_storage_nolock(
- local_storage, selem, false, true);
+ local_storage, selem, true, true);
}
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index 8f3c8b2b4490..cbd8d3720c2b 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -75,6 +75,5 @@ void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
void bpf_lru_destroy(struct bpf_lru *lru);
struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash);
void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node);
-void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node);
#endif
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 116a0ce378ec..db6176fb64dc 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -374,9 +374,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
struct bpf_struct_ops_value *uvalue, *kvalue;
const struct btf_member *member;
const struct btf_type *t = st_ops->type;
- struct bpf_tramp_links *tlinks = NULL;
+ struct bpf_tramp_links *tlinks;
void *udata, *kdata;
- int prog_fd, err = 0;
+ int prog_fd, err;
void *image, *image_end;
u32 i;
@@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
}
if (st_map->map.map_flags & BPF_F_LINK) {
- err = st_ops->validate(kdata);
- if (err)
- goto reset_unlock;
+ err = 0;
+ if (st_ops->validate) {
+ err = st_ops->validate(kdata);
+ if (err)
+ goto reset_unlock;
+ }
set_memory_rox((long)st_map->image, 1);
/* Let bpf_link handle registration & unregistration.
*
@@ -612,7 +615,10 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
if (st_map->links)
bpf_struct_ops_map_put_progs(st_map);
bpf_map_area_free(st_map->links);
- bpf_jit_free_exec(st_map->image);
+ if (st_map->image) {
+ bpf_jit_free_exec(st_map->image);
+ bpf_jit_uncharge_modmem(PAGE_SIZE);
+ }
bpf_map_area_free(st_map->uvalue);
bpf_map_area_free(st_map);
}
@@ -654,6 +660,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
struct bpf_struct_ops_map *st_map;
const struct btf_type *t, *vt;
struct bpf_map *map;
+ int ret;
st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
if (!st_ops)
@@ -663,9 +670,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
if (attr->value_size != vt->size)
return ERR_PTR(-EINVAL);
- if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update))
- return ERR_PTR(-EOPNOTSUPP);
-
t = st_ops->type;
st_map_size = sizeof(*st_map) +
@@ -681,12 +685,27 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
st_map->st_ops = st_ops;
map = &st_map->map;
+ ret = bpf_jit_charge_modmem(PAGE_SIZE);
+ if (ret) {
+ __bpf_struct_ops_map_free(map);
+ return ERR_PTR(ret);
+ }
+
+ st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+ if (!st_map->image) {
+ /* __bpf_struct_ops_map_free() uses st_map->image as flag
+ * for "charged or not". In this case, we need to unchange
+ * here.
+ */
+ bpf_jit_uncharge_modmem(PAGE_SIZE);
+ __bpf_struct_ops_map_free(map);
+ return ERR_PTR(-ENOMEM);
+ }
st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
st_map->links =
bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
NUMA_NO_NODE);
- st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
- if (!st_map->uvalue || !st_map->links || !st_map->image) {
+ if (!st_map->uvalue || !st_map->links) {
__bpf_struct_ops_map_free(map);
return ERR_PTR(-ENOMEM);
}
@@ -815,7 +834,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
struct bpf_struct_ops_map *st_map, *old_st_map;
struct bpf_map *old_map;
struct bpf_struct_ops_link *st_link;
- int err = 0;
+ int err;
st_link = container_of(link, struct bpf_struct_ops_link, link);
st_map = container_of(new_map, struct bpf_struct_ops_map, map);
@@ -823,6 +842,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map
if (!bpf_struct_ops_valid_to_reg(new_map))
return -EINVAL;
+ if (!st_map->st_ops->update)
+ return -EOPNOTSUPP;
+
mutex_lock(&update_mutex);
old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
@@ -904,4 +926,3 @@ err_out:
kfree(link);
return err;
}
-
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 817204d53372..15d71d2986d3 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -29,6 +29,7 @@
#include <net/netfilter/nf_bpf_link.h>
#include <net/sock.h>
+#include <net/xdp.h>
#include "../tools/lib/bpf/relo_core.h"
/* BTF (BPF Type Format) is the meta data format which describes
@@ -552,7 +553,7 @@ s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
return -ENOENT;
}
-static s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p)
+s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p)
{
struct btf *btf;
s32 ret;
@@ -3292,6 +3293,8 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
type = BPF_KPTR_UNREF;
else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
type = BPF_KPTR_REF;
+ else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off)))
+ type = BPF_KPTR_PERCPU;
else
return -EINVAL;
@@ -3307,10 +3310,10 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
return BTF_FIELD_FOUND;
}
-static const char *btf_find_decl_tag_value(const struct btf *btf,
- const struct btf_type *pt,
- int comp_idx, const char *tag_key)
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+ int comp_idx, const char *tag_key)
{
+ const char *value = NULL;
int i;
for (i = 1; i < btf_nr_types(btf); i++) {
@@ -3324,9 +3327,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf,
continue;
if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len))
continue;
- return __btf_name_by_offset(btf, t->name_off) + len;
+ /* Prevent duplicate entries for same type */
+ if (value)
+ return ERR_PTR(-EEXIST);
+ value = __btf_name_by_offset(btf, t->name_off) + len;
}
- return NULL;
+ if (!value)
+ return ERR_PTR(-ENOENT);
+ return value;
}
static int
@@ -3344,7 +3352,7 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
if (t->size != sz)
return BTF_FIELD_IGNORE;
value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:");
- if (!value_type)
+ if (IS_ERR(value_type))
return -EINVAL;
node_field_name = strstr(value_type, ":");
if (!node_field_name)
@@ -3456,6 +3464,7 @@ static int btf_find_struct_field(const struct btf *btf,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_find_kptr(btf, member_type, off, sz,
idx < info_cnt ? &info[idx] : &tmp);
if (ret < 0)
@@ -3522,6 +3531,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_find_kptr(btf, var_type, off, sz,
idx < info_cnt ? &info[idx] : &tmp);
if (ret < 0)
@@ -3782,6 +3792,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]);
if (ret < 0)
goto end;
@@ -6133,8 +6144,9 @@ 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);
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);
@@ -6142,6 +6154,14 @@ 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.
@@ -6302,15 +6322,6 @@ 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;
@@ -6368,7 +6379,7 @@ 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);
@@ -6476,7 +6487,7 @@ 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? */
@@ -6948,7 +6959,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
* (either PTR_TO_CTX or SCALAR_VALUE).
*/
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
- struct bpf_reg_state *regs)
+ struct bpf_reg_state *regs, bool is_ex_cb)
{
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
@@ -7005,7 +7016,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
tname, nargs, MAX_BPF_FUNC_REG_ARGS);
return -EINVAL;
}
- /* check that function returns int */
+ /* check that function returns int, exception cb also requires this */
t = btf_type_by_id(btf, t->type);
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
@@ -7054,6 +7065,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
i, btf_type_str(t), tname);
return -EINVAL;
}
+ /* We have already ensured that the callback returns an integer, just
+ * like all global subprogs. We need to determine it only has a single
+ * scalar argument.
+ */
+ if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
+ bpf_log(log, "exception cb only supports single integer argument\n");
+ return -EINVAL;
+ }
return 0;
}
@@ -7831,6 +7850,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
case BPF_PROG_TYPE_SYSCALL:
return BTF_KFUNC_HOOK_SYSCALL;
case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
return BTF_KFUNC_HOOK_CGROUP_SKB;
case BPF_PROG_TYPE_SCHED_ACT:
return BTF_KFUNC_HOOK_SCHED_ACT;
@@ -8500,7 +8520,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log,
tname = btf_name_by_offset(btf, walk_type->name_off);
ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix);
- if (ret < 0)
+ if (ret >= sizeof(safe_tname))
return false;
safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info));
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 5b2741aa0d9b..491d20038cbe 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -785,7 +785,8 @@ found:
* to descendants
* @cgrp: The cgroup which descendants to traverse
* @link: A link for which to replace BPF program
- * @type: Type of attach operation
+ * @new_prog: &struct bpf_prog for the target BPF program with its refcnt
+ * incremented
*
* Must be called with cgroup_mutex held.
*/
@@ -1334,7 +1335,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
* @skb: The skb that is being sent or received
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
*
* If no socket is passed, or the socket is not of type INET or INET6,
* this function does nothing and returns 0.
@@ -1424,7 +1425,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
/**
* __cgroup_bpf_run_filter_sk() - Run a program on a sock
* @sk: sock structure to manipulate
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
*
* socket is passed is expected to be of type INET or INET6.
*
@@ -1449,18 +1450,22 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
* provided by user sockaddr
* @sk: sock struct that will use sockaddr
* @uaddr: sockaddr struct provided by user
- * @type: The type of program to be executed
+ * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is
+ * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX
+ * uaddr.
+ * @atype: The type of program to be executed
* @t_ctx: Pointer to attach type specific context
* @flags: Pointer to u32 which contains higher bits of BPF program
* return value (OR'ed together).
*
- * socket is expected to be of type INET or INET6.
+ * socket is expected to be of type INET, INET6 or UNIX.
*
* This function will return %-EPERM if an attached program is found and
* returned value != 1 during execution. In all other cases, 0 is returned.
*/
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
struct sockaddr *uaddr,
+ int *uaddrlen,
enum cgroup_bpf_attach_type atype,
void *t_ctx,
u32 *flags)
@@ -1472,21 +1477,31 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
};
struct sockaddr_storage unspec;
struct cgroup *cgrp;
+ int ret;
/* Check socket family since not all sockets represent network
* endpoint (e.g. AF_UNIX).
*/
- if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 &&
+ sk->sk_family != AF_UNIX)
return 0;
if (!ctx.uaddr) {
memset(&unspec, 0, sizeof(unspec));
ctx.uaddr = (struct sockaddr *)&unspec;
+ ctx.uaddrlen = 0;
+ } else {
+ ctx.uaddrlen = *uaddrlen;
}
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
- 0, flags);
+ ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
+ 0, flags);
+
+ if (!ret && uaddr)
+ *uaddrlen = ctx.uaddrlen;
+
+ return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
@@ -1496,7 +1511,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
* @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
* sk with connection information (IP addresses, etc.) May not contain
* cgroup info if it is a req sock.
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
*
* socket passed is expected to be of type INET or INET6.
*
@@ -1670,7 +1685,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
* @ppos: value-result argument: value is position at which read from or write
* to sysctl is happening, result is new position if program overrode it,
* initial value otherwise
- * @type: type of program to be executed
+ * @atype: type of program to be executed
*
* Program is run when sysctl is being accessed, either read or written, and
* can allow or deny such access.
@@ -1785,7 +1800,7 @@ static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
}
int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
- int *optname, char __user *optval,
+ int *optname, sockptr_t optval,
int *optlen, char **kernel_optval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1808,7 +1823,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
ctx.optlen = *optlen;
- if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
+ if (copy_from_sockptr(ctx.optval, optval,
+ min(*optlen, max_optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1875,8 +1891,8 @@ out:
}
int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
- int optname, char __user *optval,
- int __user *optlen, int max_optlen,
+ int optname, sockptr_t optval,
+ sockptr_t optlen, int max_optlen,
int retval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1903,8 +1919,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
* one that kernel returned as well to let
* BPF programs inspect the value.
*/
-
- if (get_user(ctx.optlen, optlen)) {
+ if (copy_from_sockptr(&ctx.optlen, optlen,
+ sizeof(ctx.optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1915,8 +1931,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
}
orig_optlen = ctx.optlen;
- if (copy_from_user(ctx.optval, optval,
- min(ctx.optlen, max_optlen)) != 0) {
+ if (copy_from_sockptr(ctx.optval, optval,
+ min(ctx.optlen, max_optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1930,7 +1946,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
if (ret < 0)
goto out;
- if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+ if (!sockptr_is_null(optval) &&
+ (ctx.optlen > max_optlen || ctx.optlen < 0)) {
if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
ctx.optlen, max_optlen);
@@ -1942,11 +1959,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
}
if (ctx.optlen != 0) {
- if (optval && copy_to_user(optval, ctx.optval, ctx.optlen)) {
+ if (!sockptr_is_null(optval) &&
+ copy_to_sockptr(optval, ctx.optval, ctx.optlen)) {
ret = -EFAULT;
goto out;
}
- if (put_user(ctx.optlen, optlen)) {
+ if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) {
ret = -EFAULT;
goto out;
}
@@ -2519,10 +2537,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
return NULL;
default:
return &bpf_get_retval_proto;
@@ -2534,10 +2555,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
return NULL;
default:
return &bpf_set_retval_proto;
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 810378f04fbc..f04a468cf6a7 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__cgroup, cgroup),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &cgroup_iter_seq_info,
};
@@ -294,3 +294,66 @@ static int __init bpf_cgroup_iter_init(void)
}
late_initcall(bpf_cgroup_iter_init);
+
+struct bpf_iter_css {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_kern {
+ struct cgroup_subsys_state *start;
+ struct cgroup_subsys_state *pos;
+ unsigned int flags;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
+ struct cgroup_subsys_state *start, unsigned int flags)
+{
+ struct bpf_iter_css_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css));
+
+ kit->start = NULL;
+ switch (flags) {
+ case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+ case BPF_CGROUP_ITER_DESCENDANTS_POST:
+ case BPF_CGROUP_ITER_ANCESTORS_UP:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ kit->start = start;
+ kit->pos = NULL;
+ kit->flags = flags;
+ return 0;
+}
+
+__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it)
+{
+ struct bpf_iter_css_kern *kit = (void *)it;
+
+ if (!kit->start)
+ return NULL;
+
+ switch (kit->flags) {
+ case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+ kit->pos = css_next_descendant_pre(kit->pos, kit->start);
+ break;
+ case BPF_CGROUP_ITER_DESCENDANTS_POST:
+ kit->pos = css_next_descendant_post(kit->pos, kit->start);
+ break;
+ case BPF_CGROUP_ITER_ANCESTORS_UP:
+ kit->pos = kit->pos ? kit->pos->parent : kit->start;
+ }
+
+ return kit->pos;
+}
+
+__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
+{
+}
+
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index dc85240a0134..fe254ae035fe 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -61,6 +61,7 @@
#define AX regs[BPF_REG_AX]
#define ARG1 regs[BPF_REG_ARG1]
#define CTX regs[BPF_REG_CTX]
+#define OFF insn->off
#define IMM insn->imm
struct bpf_mem_alloc bpf_global_ma;
@@ -211,7 +212,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
const struct bpf_line_info *linfo;
void **jited_linfo;
- if (!prog->aux->jited_linfo)
+ if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt)
/* Userspace did not provide linfo */
return;
@@ -370,9 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
s32 end_new, s32 curr, const bool probe_pass)
{
- const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s64 off_min, off_max, off;
s32 delta = end_new - end_old;
- s32 off = insn->off;
+
+ if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ off = insn->imm;
+ off_min = S32_MIN;
+ off_max = S32_MAX;
+ } else {
+ off = insn->off;
+ off_min = S16_MIN;
+ off_max = S16_MAX;
+ }
if (curr < pos && curr + off + 1 >= end_old)
off += delta;
@@ -380,8 +390,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
off -= delta;
if (off < off_min || off > off_max)
return -ERANGE;
- if (!probe_pass)
- insn->off = off;
+ if (!probe_pass) {
+ if (insn->code == (BPF_JMP32 | BPF_JA))
+ insn->imm = off;
+ else
+ insn->off = off;
+ }
return 0;
}
@@ -529,7 +543,7 @@ static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
- for (i = 0; i < fp->aux->func_cnt; i++)
+ for (i = 0; i < fp->aux->real_func_cnt; i++)
bpf_prog_kallsyms_del(fp->aux->func[i]);
}
@@ -579,7 +593,7 @@ bpf_prog_ksym_set_name(struct bpf_prog *prog)
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
/* prog->aux->name will be ignored if full btf name is available */
- if (prog->aux->func_info_cnt) {
+ if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) {
type = btf_type_by_id(prog->aux->btf,
prog->aux->func_info[prog->aux->func_idx].type_id);
func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
@@ -613,7 +627,11 @@ static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
if (val < ksym->start)
return -1;
- if (val >= ksym->end)
+ /* Ensure that we detect return addresses as part of the program, when
+ * the final instruction is a call for a program part of the stack
+ * trace. Therefore, do val > ksym->end instead of val >= ksym->end.
+ */
+ if (val > ksym->end)
return 1;
return 0;
@@ -723,7 +741,7 @@ bool is_bpf_text_address(unsigned long addr)
return ret;
}
-static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
{
struct bpf_ksym *ksym = bpf_ksym_find(addr);
@@ -860,7 +878,7 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
GFP_KERNEL);
if (!pack)
return NULL;
- pack->ptr = module_alloc(BPF_PROG_PACK_SIZE);
+ pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE);
if (!pack->ptr) {
kfree(pack);
return NULL;
@@ -884,7 +902,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
mutex_lock(&pack_mutex);
if (size > BPF_PROG_PACK_SIZE) {
size = round_up(size, PAGE_SIZE);
- ptr = module_alloc(size);
+ ptr = bpf_jit_alloc_exec(size);
if (ptr) {
bpf_fill_ill_insns(ptr, size);
set_vm_flush_reset_perms(ptr);
@@ -922,7 +940,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
mutex_lock(&pack_mutex);
if (hdr->size > BPF_PROG_PACK_SIZE) {
- module_memfree(hdr);
+ bpf_jit_free_exec(hdr);
goto out;
}
@@ -946,7 +964,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
BPF_PROG_CHUNK_COUNT, 0) == 0) {
list_del(&pack->list);
- module_memfree(pack->ptr);
+ bpf_jit_free_exec(pack->ptr);
kfree(pack);
}
out:
@@ -1198,7 +1216,7 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
if (!extra_pass)
addr = NULL;
else if (prog->aux->func &&
- off >= 0 && off < prog->aux->func_cnt)
+ off >= 0 && off < prog->aux->real_func_cnt)
addr = (u8 *)prog->aux->func[off]->bpf_func;
else
return -EINVAL;
@@ -1271,7 +1289,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
case BPF_ALU | BPF_MOD | BPF_K:
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
+ *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
case BPF_ALU64 | BPF_ADD | BPF_K:
@@ -1285,7 +1303,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
case BPF_ALU64 | BPF_MOD | BPF_K:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
+ *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
@@ -1523,6 +1541,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(ALU64, DIV, X), \
INSN_3(ALU64, MOD, X), \
INSN_2(ALU64, NEG), \
+ INSN_3(ALU64, END, TO_LE), \
/* Immediate based. */ \
INSN_3(ALU64, ADD, K), \
INSN_3(ALU64, SUB, K), \
@@ -1591,6 +1610,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(JMP, JSLE, K), \
INSN_3(JMP, JSET, K), \
INSN_2(JMP, JA), \
+ INSN_2(JMP32, JA), \
/* Store instructions. */ \
/* Register based. */ \
INSN_3(STX, MEM, B), \
@@ -1610,6 +1630,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
INSN_3(LDX, MEM, H), \
INSN_3(LDX, MEM, W), \
INSN_3(LDX, MEM, DW), \
+ INSN_3(LDX, MEMSX, B), \
+ INSN_3(LDX, MEMSX, H), \
+ INSN_3(LDX, MEMSX, W), \
/* Immediate based. */ \
INSN_3(LD, IMM, DW)
@@ -1635,12 +1658,6 @@ bool bpf_opcode_in_insntable(u8 code)
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
-{
- memset(dst, 0, size);
- return -EFAULT;
-}
-
/**
* ___bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1666,6 +1683,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H,
+ [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
@@ -1733,13 +1753,36 @@ select_insn:
DST = -DST;
CONT;
ALU_MOV_X:
- DST = (u32) SRC;
+ switch (OFF) {
+ case 0:
+ DST = (u32) SRC;
+ break;
+ case 8:
+ DST = (u32)(s8) SRC;
+ break;
+ case 16:
+ DST = (u32)(s16) SRC;
+ break;
+ }
CONT;
ALU_MOV_K:
DST = (u32) IMM;
CONT;
ALU64_MOV_X:
- DST = SRC;
+ switch (OFF) {
+ case 0:
+ DST = SRC;
+ break;
+ case 8:
+ DST = (s8) SRC;
+ break;
+ case 16:
+ DST = (s16) SRC;
+ break;
+ case 32:
+ DST = (s32) SRC;
+ break;
+ }
CONT;
ALU64_MOV_K:
DST = IMM;
@@ -1761,36 +1804,114 @@ select_insn:
(*(s64 *) &DST) >>= IMM;
CONT;
ALU64_MOD_X:
- div64_u64_rem(DST, SRC, &AX);
- DST = AX;
+ switch (OFF) {
+ case 0:
+ div64_u64_rem(DST, SRC, &AX);
+ DST = AX;
+ break;
+ case 1:
+ AX = div64_s64(DST, SRC);
+ DST = DST - AX * SRC;
+ break;
+ }
CONT;
ALU_MOD_X:
- AX = (u32) DST;
- DST = do_div(AX, (u32) SRC);
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) SRC);
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ AX = do_div(AX, abs((s32)SRC));
+ if ((s32)DST < 0)
+ DST = (u32)-AX;
+ else
+ DST = (u32)AX;
+ break;
+ }
CONT;
ALU64_MOD_K:
- div64_u64_rem(DST, IMM, &AX);
- DST = AX;
+ switch (OFF) {
+ case 0:
+ div64_u64_rem(DST, IMM, &AX);
+ DST = AX;
+ break;
+ case 1:
+ AX = div64_s64(DST, IMM);
+ DST = DST - AX * IMM;
+ break;
+ }
CONT;
ALU_MOD_K:
- AX = (u32) DST;
- DST = do_div(AX, (u32) IMM);
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) IMM);
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ AX = do_div(AX, abs((s32)IMM));
+ if ((s32)DST < 0)
+ DST = (u32)-AX;
+ else
+ DST = (u32)AX;
+ break;
+ }
CONT;
ALU64_DIV_X:
- DST = div64_u64(DST, SRC);
+ switch (OFF) {
+ case 0:
+ DST = div64_u64(DST, SRC);
+ break;
+ case 1:
+ DST = div64_s64(DST, SRC);
+ break;
+ }
CONT;
ALU_DIV_X:
- AX = (u32) DST;
- do_div(AX, (u32) SRC);
- DST = (u32) AX;
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ do_div(AX, (u32) SRC);
+ DST = (u32) AX;
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ do_div(AX, abs((s32)SRC));
+ if (((s32)DST < 0) == ((s32)SRC < 0))
+ DST = (u32)AX;
+ else
+ DST = (u32)-AX;
+ break;
+ }
CONT;
ALU64_DIV_K:
- DST = div64_u64(DST, IMM);
+ switch (OFF) {
+ case 0:
+ DST = div64_u64(DST, IMM);
+ break;
+ case 1:
+ DST = div64_s64(DST, IMM);
+ break;
+ }
CONT;
ALU_DIV_K:
- AX = (u32) DST;
- do_div(AX, (u32) IMM);
- DST = (u32) AX;
+ switch (OFF) {
+ case 0:
+ AX = (u32) DST;
+ do_div(AX, (u32) IMM);
+ DST = (u32) AX;
+ break;
+ case 1:
+ AX = abs((s32)DST);
+ do_div(AX, abs((s32)IMM));
+ if (((s32)DST < 0) == ((s32)IMM < 0))
+ DST = (u32)AX;
+ else
+ DST = (u32)-AX;
+ break;
+ }
CONT;
ALU_END_TO_BE:
switch (IMM) {
@@ -1818,6 +1939,19 @@ select_insn:
break;
}
CONT;
+ ALU64_END_TO_LE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) __swab16(DST);
+ break;
+ case 32:
+ DST = (__force u32) __swab32(DST);
+ break;
+ case 64:
+ DST = (__force u64) __swab64(DST);
+ break;
+ }
+ CONT;
/* CALL */
JMP_CALL:
@@ -1867,6 +2001,9 @@ out:
JMP_JA:
insn += insn->off;
CONT;
+ JMP32_JA:
+ insn += insn->imm;
+ CONT;
JMP_EXIT:
return BPF_R0;
/* JMP */
@@ -1931,8 +2068,8 @@ out:
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
CONT; \
LDX_PROBE_MEM_##SIZEOP: \
- bpf_probe_read_kernel(&DST, sizeof(SIZE), \
- (const void *)(long) (SRC + insn->off)); \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
DST = *((SIZE *)&DST); \
CONT;
@@ -1942,6 +2079,21 @@ out:
LDST(DW, u64)
#undef LDST
+#define LDSX(SIZEOP, SIZE) \
+ LDX_MEMSX_##SIZEOP: \
+ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
+ CONT; \
+ LDX_PROBE_MEMSX_##SIZEOP: \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
+ DST = *((SIZE *)&DST); \
+ CONT;
+
+ LDSX(B, s8)
+ LDSX(H, s16)
+ LDSX(W, s32)
+#undef LDSX
+
#define ATOMIC_ALU_OP(BOP, KOP) \
case BOP: \
if (BPF_SIZE(insn->code) == BPF_W) \
@@ -2577,7 +2729,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
#endif
if (aux->dst_trampoline)
bpf_trampoline_put(aux->dst_trampoline);
- for (i = 0; i < aux->func_cnt; i++) {
+ for (i = 0; i < aux->real_func_cnt; i++) {
/* We can just unlink the subprog poke descriptor table as
* it was originally linked to the main program and is also
* released along with it.
@@ -2585,7 +2737,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
aux->func[i]->aux->poke_tab = NULL;
bpf_jit_free(aux->func[i]);
}
- if (aux->func_cnt) {
+ if (aux->real_func_cnt) {
kfree(aux->func);
bpf_prog_unlock_free(aux->prog);
} else {
@@ -2770,6 +2922,15 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len)
return -ENOTSUPP;
}
+bool __weak bpf_jit_supports_exceptions(void)
+{
+ return false;
+}
+
+void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+}
+
#ifdef CONFIG_BPF_SYSCALL
static int __init bpf_global_ma_init(void)
{
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 286ab3db0fde..8a0bb80fe48a 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -61,8 +61,6 @@ struct bpf_cpu_map_entry {
/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
struct xdp_bulk_queue __percpu *bulkq;
- struct bpf_cpu_map *cmap;
-
/* Queue with potential multi-producers, and single-consumer kthread */
struct ptr_ring *queue;
struct task_struct *kthread;
@@ -70,11 +68,8 @@ struct bpf_cpu_map_entry {
struct bpf_cpumap_val value;
struct bpf_prog *prog;
- atomic_t refcnt; /* Control when this struct can be free'ed */
- struct rcu_head rcu;
-
- struct work_struct kthread_stop_wq;
struct completion kthread_running;
+ struct rcu_work free_work;
};
struct bpf_cpu_map {
@@ -119,11 +114,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
return &cmap->map;
}
-static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
- atomic_inc(&rcpu->refcnt);
-}
-
static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
{
/* The tear-down procedure should have made sure that queue is
@@ -144,35 +134,6 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
}
}
-static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
- if (atomic_dec_and_test(&rcpu->refcnt)) {
- if (rcpu->prog)
- bpf_prog_put(rcpu->prog);
- /* The queue should be empty at this point */
- __cpu_map_ring_cleanup(rcpu->queue);
- ptr_ring_cleanup(rcpu->queue, NULL);
- kfree(rcpu->queue);
- kfree(rcpu);
- }
-}
-
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
- struct bpf_cpu_map_entry *rcpu;
-
- rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
- /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
- * as it waits until all in-flight call_rcu() callbacks complete.
- */
- rcu_barrier();
-
- /* kthread_stop will wake_up_process and wait for it to complete */
- kthread_stop(rcpu->kthread);
-}
-
static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
struct list_head *listp,
struct xdp_cpumap_stats *stats)
@@ -397,7 +358,6 @@ static int cpu_map_kthread_run(void *data)
}
__set_current_state(TASK_RUNNING);
- put_cpu_map_entry(rcpu);
return 0;
}
@@ -474,9 +434,6 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
if (IS_ERR(rcpu->kthread))
goto free_prog;
- get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
- get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
-
/* Make sure kthread runs on a single CPU */
kthread_bind(rcpu->kthread, cpu);
wake_up_process(rcpu->kthread);
@@ -503,40 +460,40 @@ free_rcu:
return NULL;
}
-static void __cpu_map_entry_free(struct rcu_head *rcu)
+static void __cpu_map_entry_free(struct work_struct *work)
{
struct bpf_cpu_map_entry *rcpu;
/* This cpu_map_entry have been disconnected from map and one
- * RCU grace-period have elapsed. Thus, XDP cannot queue any
+ * RCU grace-period have elapsed. Thus, XDP cannot queue any
* new packets and cannot change/set flush_needed that can
* find this entry.
*/
- rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+ rcpu = container_of(to_rcu_work(work), struct bpf_cpu_map_entry, free_work);
+ /* kthread_stop will wake_up_process and wait for it to complete.
+ * cpu_map_kthread_run() makes sure the pointer ring is empty
+ * before exiting.
+ */
+ kthread_stop(rcpu->kthread);
+
+ if (rcpu->prog)
+ bpf_prog_put(rcpu->prog);
+ /* The queue should be empty at this point */
+ __cpu_map_ring_cleanup(rcpu->queue);
+ ptr_ring_cleanup(rcpu->queue, NULL);
+ kfree(rcpu->queue);
free_percpu(rcpu->bulkq);
- /* Cannot kthread_stop() here, last put free rcpu resources */
- put_cpu_map_entry(rcpu);
+ kfree(rcpu);
}
-/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
- * ensure any driver rcu critical sections have completed, but this
- * does not guarantee a flush has happened yet. Because driver side
- * rcu_read_lock/unlock only protects the running XDP program. The
- * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
- * pending flush op doesn't fail.
- *
- * The bpf_cpu_map_entry is still used by the kthread, and there can
- * still be pending packets (in queue and percpu bulkq). A refcnt
- * makes sure to last user (kthread_stop vs. call_rcu) free memory
- * resources.
- *
- * The rcu callback __cpu_map_entry_free flush remaining packets in
- * percpu bulkq to queue. Due to caller map_delete_elem() disable
- * preemption, cannot call kthread_stop() to make sure queue is empty.
- * Instead a work_queue is started for stopping kthread,
- * cpu_map_kthread_stop, which waits for an RCU grace period before
- * stopping kthread, emptying the queue.
+/* After the xchg of the bpf_cpu_map_entry pointer, we need to make sure the old
+ * entry is no longer in use before freeing. We use queue_rcu_work() to call
+ * __cpu_map_entry_free() in a separate workqueue after waiting for an RCU grace
+ * period. This means that (a) all pending enqueue and flush operations have
+ * completed (because of the RCU callback), and (b) we are in a workqueue
+ * context where we can stop the kthread and wait for it to exit before freeing
+ * everything.
*/
static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
@@ -545,9 +502,8 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
if (old_rcpu) {
- call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
- INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
- schedule_work(&old_rcpu->kthread_stop_wq);
+ INIT_RCU_WORK(&old_rcpu->free_work, __cpu_map_entry_free);
+ queue_rcu_work(system_wq, &old_rcpu->free_work);
}
}
@@ -559,7 +515,7 @@ static long cpu_map_delete_elem(struct bpf_map *map, void *key)
if (key_cpu >= map->max_entries)
return -EINVAL;
- /* notice caller map_delete_elem() use preempt_disable() */
+ /* notice caller map_delete_elem() uses rcu_read_lock() */
__cpu_map_entry_replace(cmap, key_cpu, NULL);
return 0;
}
@@ -595,7 +551,6 @@ static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
if (!rcpu)
return -ENOMEM;
- rcpu->cmap = cmap;
}
rcu_read_lock();
__cpu_map_entry_replace(cmap, key_cpu, rcpu);
@@ -611,16 +566,15 @@ static void cpu_map_free(struct bpf_map *map)
/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the bpf programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding critical sections in
- * these programs to complete. The rcu critical section only guarantees
- * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
- * It does __not__ ensure pending flush operations (if any) are
- * complete.
+ * these programs to complete. synchronize_rcu() below not only
+ * guarantees no further "XDP/bpf-side" reads against
+ * bpf_cpu_map->cpu_map, but also ensure pending flush operations
+ * (if any) are completed.
*/
-
synchronize_rcu();
- /* For cpu_map the remote CPUs can still be using the entries
- * (struct bpf_cpu_map_entry).
+ /* The only possible user of bpf_cpu_map_entry is
+ * cpu_map_kthread_run().
*/
for (i = 0; i < cmap->map.max_entries; i++) {
struct bpf_cpu_map_entry *rcpu;
@@ -629,8 +583,8 @@ static void cpu_map_free(struct bpf_map *map)
if (!rcpu)
continue;
- /* bq flush and cleanup happens after RCU grace-period */
- __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+ /* Stop kthread and cleanup entry directly */
+ __cpu_map_entry_free(&rcpu->free_work.work);
}
bpf_map_area_free(cmap->cpu_map);
bpf_map_area_free(cmap);
@@ -810,6 +764,16 @@ void __cpu_map_flush(void)
}
}
+#ifdef CONFIG_DEBUG_NET
+bool cpu_map_check_flush(void)
+{
+ if (list_empty(this_cpu_ptr(&cpu_map_flush_list)))
+ return false;
+ __cpu_map_flush();
+ return true;
+}
+#endif
+
static int __init cpu_map_init(void)
{
int cpu;
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 938a60ff4295..e01c741e54e7 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;
};
@@ -36,9 +34,7 @@ static bool cpu_valid(u32 cpu)
return cpu < nr_cpu_ids;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
/**
* bpf_cpumask_create() - Create a mutable BPF cpumask.
@@ -82,16 +78,6 @@ __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 +88,12 @@ 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();
}
/**
@@ -415,7 +405,7 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
return cpumask_any_and_distribute(src1, src2);
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(cpumask_kfunc_btf_ids)
BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 49cc0b5671c6..a936c704d4e7 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -65,7 +65,6 @@ struct xdp_dev_bulk_queue {
struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
- struct bpf_dtab *dtab;
struct bpf_prog *xdp_prog;
struct rcu_head rcu;
unsigned int idx;
@@ -419,6 +418,16 @@ void __dev_flush(void)
}
}
+#ifdef CONFIG_DEBUG_NET
+bool dev_check_flush(void)
+{
+ if (list_empty(this_cpu_ptr(&dev_flush_list)))
+ return false;
+ __dev_flush();
+ return true;
+}
+#endif
+
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
@@ -874,7 +883,6 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
}
dev->idx = idx;
- dev->dtab = dtab;
if (prog) {
dev->xdp_prog = prog;
dev->val.bpf_prog.id = prog->aux->id;
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 7b4afb7d96db..49940c26a227 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = {
[BPF_END >> 4] = "endian",
};
+static const char *const bpf_alu_sign_string[16] = {
+ [BPF_DIV >> 4] = "s/=",
+ [BPF_MOD >> 4] = "s%=",
+};
+
+static const char *const bpf_movsx_string[4] = {
+ [0] = "(s8)",
+ [1] = "(s16)",
+ [3] = "(s32)",
+};
+
static const char *const bpf_atomic_alu_string[16] = {
[BPF_ADD >> 4] = "add",
[BPF_AND >> 4] = "and",
@@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = {
[BPF_DW >> 3] = "u64",
};
+static const char *const bpf_ldsx_string[] = {
+ [BPF_W >> 3] = "s32",
+ [BPF_H >> 3] = "s16",
+ [BPF_B >> 3] = "s8",
+};
+
static const char *const bpf_jmp_string[16] = {
[BPF_JA >> 4] = "jmp",
[BPF_JEQ >> 4] = "==",
@@ -128,6 +145,27 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose,
insn->imm, insn->dst_reg);
}
+static void print_bpf_bswap_insn(bpf_insn_print_t verbose,
+ void *private_data,
+ const struct bpf_insn *insn)
+{
+ verbose(private_data, "(%02x) r%d = bswap%d r%d\n",
+ insn->code, insn->dst_reg,
+ insn->imm, insn->dst_reg);
+}
+
+static bool is_sdiv_smod(const struct bpf_insn *insn)
+{
+ return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) &&
+ insn->off == 1;
+}
+
+static bool is_movsx(const struct bpf_insn *insn)
+{
+ return BPF_OP(insn->code) == BPF_MOV &&
+ (insn->off == 8 || insn->off == 16 || insn->off == 32);
+}
+
void print_bpf_insn(const struct bpf_insn_cbs *cbs,
const struct bpf_insn *insn,
bool allow_ptr_leaks)
@@ -138,7 +176,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
if (class == BPF_ALU || class == BPF_ALU64) {
if (BPF_OP(insn->code) == BPF_END) {
if (class == BPF_ALU64)
- verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code);
+ print_bpf_bswap_insn(verbose, cbs->private_data, insn);
else
print_bpf_end_insn(verbose, cbs->private_data, insn);
} else if (BPF_OP(insn->code) == BPF_NEG) {
@@ -147,17 +185,20 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
insn->dst_reg, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg);
} else if (BPF_SRC(insn->code) == BPF_X) {
- verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n",
+ verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n",
insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+ : bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "",
class == BPF_ALU ? 'w' : 'r',
insn->src_reg);
} else {
verbose(cbs->private_data, "(%02x) %c%d %s %d\n",
insn->code, class == BPF_ALU ? 'w' : 'r',
insn->dst_reg,
- bpf_alu_string[BPF_OP(insn->code) >> 4],
+ is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4]
+ : bpf_alu_string[BPF_OP(insn->code) >> 4],
insn->imm);
}
} else if (class == BPF_STX) {
@@ -218,13 +259,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
}
} else if (class == BPF_LDX) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
return;
}
verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n",
insn->code, insn->dst_reg,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ BPF_MODE(insn->code) == BPF_MEM ?
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3] :
+ bpf_ldsx_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->off);
} else if (class == BPF_LD) {
if (BPF_MODE(insn->code) == BPF_ABS) {
@@ -279,6 +322,9 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
} else if (insn->code == (BPF_JMP | BPF_JA)) {
verbose(cbs->private_data, "(%02x) goto pc%+d\n",
insn->code, insn->off);
+ } else if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ verbose(cbs->private_data, "(%02x) gotol pc%+d\n",
+ insn->code, insn->imm);
} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
verbose(cbs->private_data, "(%02x) exit\n", insn->code);
} else if (BPF_SRC(insn->code) == BPF_X) {
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 56d3da7d0bc6..fd8d4b0addfc 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -155,13 +155,15 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
preempt_disable();
+ local_irq_save(flags);
if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
__this_cpu_dec(*(htab->map_locked[hash]));
+ local_irq_restore(flags);
preempt_enable();
return -EBUSY;
}
- raw_spin_lock_irqsave(&b->raw_lock, flags);
+ raw_spin_lock(&b->raw_lock);
*pflags = flags;
return 0;
@@ -172,8 +174,9 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
unsigned long flags)
{
hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
- raw_spin_unlock_irqrestore(&b->raw_lock, flags);
+ raw_spin_unlock(&b->raw_lock);
__this_cpu_dec(*(htab->map_locked[hash]));
+ local_irq_restore(flags);
preempt_enable();
}
@@ -302,6 +305,7 @@ 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 +514,16 @@ 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 +601,8 @@ 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 +814,7 @@ 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 +911,8 @@ 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 +921,8 @@ 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 +935,7 @@ 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 +1016,7 @@ 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 +1185,7 @@ 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 +1375,10 @@ 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 +1543,7 @@ 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);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9e80efa59a5d..56b0c1f678ee 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -22,6 +22,7 @@
#include <linux/security.h>
#include <linux/btf_ids.h>
#include <linux/bpf_mem_alloc.h>
+#include <linux/kasan.h>
#include "../../lib/kstrtox.h"
@@ -286,6 +287,7 @@ static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0");
BUILD_BUG_ON(sizeof(*l) != sizeof(__u32));
BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32));
+ preempt_disable();
arch_spin_lock(l);
}
@@ -294,6 +296,7 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
arch_spinlock_t *l = (void *)lock;
arch_spin_unlock(l);
+ preempt_enable();
}
#else
@@ -1174,13 +1177,6 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
ret = -EBUSY;
goto out;
}
- if (!atomic64_read(&map->usercnt)) {
- /* maps with timers must be either held by user space
- * or pinned in bpffs.
- */
- ret = -EPERM;
- goto out;
- }
/* allocate hrtimer via map_kmalloc to use memcg accounting */
t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
if (!t) {
@@ -1193,7 +1189,21 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
rcu_assign_pointer(t->callback_fn, NULL);
hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
t->timer.function = bpf_timer_cb;
- timer->timer = t;
+ WRITE_ONCE(timer->timer, t);
+ /* Guarantee the order between timer->timer and map->usercnt. So
+ * when there are concurrent uref release and bpf timer init, either
+ * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+ * timer or atomic64_read() below returns a zero usercnt.
+ */
+ smp_mb();
+ if (!atomic64_read(&map->usercnt)) {
+ /* maps with timers must be either held by user space
+ * or pinned in bpffs.
+ */
+ WRITE_ONCE(timer->timer, NULL);
+ kfree(t);
+ ret = -EPERM;
+ }
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
return ret;
@@ -1269,7 +1279,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
if (in_nmi())
return -EOPNOTSUPP;
- if (flags > BPF_F_TIMER_ABS)
+ if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN))
return -EINVAL;
__bpf_spin_lock_irqsave(&timer->lock);
t = timer->timer;
@@ -1283,6 +1293,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
else
mode = HRTIMER_MODE_REL_SOFT;
+ if (flags & BPF_F_TIMER_CPU_PIN)
+ mode |= HRTIMER_MODE_PINNED;
+
hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
@@ -1368,7 +1381,7 @@ void bpf_timer_cancel_and_free(void *val)
/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
* this timer, since it won't be initialized.
*/
- timer->timer = NULL;
+ WRITE_ONCE(timer->timer, NULL);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
if (!t)
@@ -1805,8 +1818,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
}
}
-void __bpf_obj_drop_impl(void *p, const struct btf_record *rec);
-
void bpf_list_head_free(const struct btf_field *field, void *list_head,
struct bpf_spin_lock *spin_lock)
{
@@ -1838,7 +1849,7 @@ unlock:
* bpf_list_head which needs to be freed.
*/
migrate_disable();
- __bpf_obj_drop_impl(obj, field->graph_root.value_rec);
+ __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
migrate_enable();
}
}
@@ -1877,14 +1888,12 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
migrate_disable();
- __bpf_obj_drop_impl(obj, field->graph_root.value_rec);
+ __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
migrate_enable();
}
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
{
@@ -1900,9 +1909,19 @@ __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
return p;
}
+__bpf_kfunc void *bpf_percpu_obj_new_impl(u64 local_type_id__k, void *meta__ign)
+{
+ u64 size = local_type_id__k;
+
+ /* The verifier has ensured that meta__ign must be NULL */
+ return bpf_mem_alloc(&bpf_global_percpu_ma, size);
+}
+
/* Must be called under migrate_disable(), as required by bpf_mem_free */
-void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
+void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu)
{
+ struct bpf_mem_alloc *ma;
+
if (rec && rec->refcount_off >= 0 &&
!refcount_dec_and_test((refcount_t *)(p + rec->refcount_off))) {
/* Object is refcounted and refcount_dec didn't result in 0
@@ -1913,7 +1932,15 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
if (rec)
bpf_obj_free_fields(rec, p);
- bpf_mem_free(&bpf_global_ma, p);
+
+ if (percpu)
+ ma = &bpf_global_percpu_ma;
+ else
+ ma = &bpf_global_ma;
+ if (rec && rec->refcount_off >= 0)
+ bpf_mem_free_rcu(ma, p);
+ else
+ bpf_mem_free(ma, p);
}
__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
@@ -1921,7 +1948,13 @@ __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
struct btf_struct_meta *meta = meta__ign;
void *p = p__alloc;
- __bpf_obj_drop_impl(p, meta ? meta->record : NULL);
+ __bpf_obj_drop_impl(p, meta ? meta->record : NULL, false);
+}
+
+__bpf_kfunc void bpf_percpu_obj_drop_impl(void *p__alloc, void *meta__ign)
+{
+ /* The verifier has ensured that meta__ign must be NULL */
+ bpf_mem_free_rcu(&bpf_global_percpu_ma, p__alloc);
}
__bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta__ign)
@@ -1942,23 +1975,29 @@ __bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta
return (void *)p__refcounted_kptr;
}
-static int __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head,
+static int __bpf_list_add(struct bpf_list_node_kern *node,
+ struct bpf_list_head *head,
bool tail, struct btf_record *rec, u64 off)
{
- struct list_head *n = (void *)node, *h = (void *)head;
+ struct list_head *n = &node->list_head, *h = (void *)head;
/* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
* called on its fields, so init here
*/
if (unlikely(!h->next))
INIT_LIST_HEAD(h);
- if (!list_empty(n)) {
+
+ /* node->owner != NULL implies !list_empty(n), no need to separately
+ * check the latter
+ */
+ if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
/* Only called from BPF prog, no need to migrate_disable */
- __bpf_obj_drop_impl((void *)n - off, rec);
+ __bpf_obj_drop_impl((void *)n - off, rec, false);
return -EINVAL;
}
tail ? list_add_tail(n, h) : list_add(n, h);
+ WRITE_ONCE(node->owner, head);
return 0;
}
@@ -1967,25 +2006,26 @@ __bpf_kfunc int bpf_list_push_front_impl(struct bpf_list_head *head,
struct bpf_list_node *node,
void *meta__ign, u64 off)
{
+ struct bpf_list_node_kern *n = (void *)node;
struct btf_struct_meta *meta = meta__ign;
- return __bpf_list_add(node, head, false,
- meta ? meta->record : NULL, off);
+ return __bpf_list_add(n, head, false, meta ? meta->record : NULL, off);
}
__bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head,
struct bpf_list_node *node,
void *meta__ign, u64 off)
{
+ struct bpf_list_node_kern *n = (void *)node;
struct btf_struct_meta *meta = meta__ign;
- return __bpf_list_add(node, head, true,
- meta ? meta->record : NULL, off);
+ return __bpf_list_add(n, head, true, meta ? meta->record : NULL, off);
}
static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail)
{
struct list_head *n, *h = (void *)head;
+ struct bpf_list_node_kern *node;
/* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
* called on its fields, so init here
@@ -1994,8 +2034,14 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai
INIT_LIST_HEAD(h);
if (list_empty(h))
return NULL;
+
n = tail ? h->prev : h->next;
+ node = container_of(n, struct bpf_list_node_kern, list_head);
+ if (WARN_ON_ONCE(READ_ONCE(node->owner) != head))
+ return NULL;
+
list_del_init(n);
+ WRITE_ONCE(node->owner, NULL);
return (struct bpf_list_node *)n;
}
@@ -2012,31 +2058,40 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
__bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
struct bpf_rb_node *node)
{
+ struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
struct rb_root_cached *r = (struct rb_root_cached *)root;
- struct rb_node *n = (struct rb_node *)node;
+ struct rb_node *n = &node_internal->rb_node;
- if (RB_EMPTY_NODE(n))
+ /* node_internal->owner != root implies either RB_EMPTY_NODE(n) or
+ * n is owned by some other tree. No need to check RB_EMPTY_NODE(n)
+ */
+ if (READ_ONCE(node_internal->owner) != root)
return NULL;
rb_erase_cached(n, r);
RB_CLEAR_NODE(n);
+ WRITE_ONCE(node_internal->owner, NULL);
return (struct bpf_rb_node *)n;
}
/* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF
* program
*/
-static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
+static int __bpf_rbtree_add(struct bpf_rb_root *root,
+ struct bpf_rb_node_kern *node,
void *less, struct btf_record *rec, u64 off)
{
struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node;
- struct rb_node *parent = NULL, *n = (struct rb_node *)node;
+ struct rb_node *parent = NULL, *n = &node->rb_node;
bpf_callback_t cb = (bpf_callback_t)less;
bool leftmost = true;
- if (!RB_EMPTY_NODE(n)) {
+ /* node->owner != NULL implies !RB_EMPTY_NODE(n), no need to separately
+ * check the latter
+ */
+ if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
/* Only called from BPF prog, no need to migrate_disable */
- __bpf_obj_drop_impl((void *)n - off, rec);
+ __bpf_obj_drop_impl((void *)n - off, rec, false);
return -EINVAL;
}
@@ -2052,6 +2107,7 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
rb_link_node(n, parent, link);
rb_insert_color_cached(n, (struct rb_root_cached *)root, leftmost);
+ WRITE_ONCE(node->owner, root);
return 0;
}
@@ -2060,8 +2116,9 @@ __bpf_kfunc int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node
void *meta__ign, u64 off)
{
struct btf_struct_meta *meta = meta__ign;
+ struct bpf_rb_node_kern *n = (void *)node;
- return __bpf_rbtree_add(root, node, (void *)less, meta ? meta->record : NULL, off);
+ return __bpf_rbtree_add(root, n, (void *)less, meta ? meta->record : NULL, off);
}
__bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root)
@@ -2167,7 +2224,12 @@ __bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid)
__bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task,
struct cgroup *ancestor)
{
- return task_under_cgroup_hierarchy(task, ancestor);
+ long ret;
+
+ rcu_read_lock();
+ ret = task_under_cgroup_hierarchy(task, ancestor);
+ rcu_read_unlock();
+ return ret;
}
#endif /* CONFIG_CGROUPS */
@@ -2239,11 +2301,14 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
case BPF_DYNPTR_TYPE_RINGBUF:
return ptr->data + ptr->offset + offset;
case BPF_DYNPTR_TYPE_SKB:
- return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
+ if (buffer__opt)
+ return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
+ else
+ return skb_pointer_if_linear(ptr->data, ptr->offset + offset, len);
case BPF_DYNPTR_TYPE_XDP:
{
void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
- if (xdp_ptr)
+ if (!IS_ERR_OR_NULL(xdp_ptr))
return xdp_ptr;
if (!buffer__opt)
@@ -2402,14 +2467,59 @@ __bpf_kfunc void bpf_rcu_read_unlock(void)
rcu_read_unlock();
}
-__diag_pop();
+struct bpf_throw_ctx {
+ struct bpf_prog_aux *aux;
+ u64 sp;
+ u64 bp;
+ int cnt;
+};
+
+static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+ struct bpf_throw_ctx *ctx = cookie;
+ struct bpf_prog *prog;
+
+ if (!is_bpf_text_address(ip))
+ return !ctx->cnt;
+ prog = bpf_prog_ksym_find(ip);
+ ctx->cnt++;
+ if (bpf_is_subprog(prog))
+ return true;
+ ctx->aux = prog->aux;
+ ctx->sp = sp;
+ ctx->bp = bp;
+ return false;
+}
+
+__bpf_kfunc void bpf_throw(u64 cookie)
+{
+ struct bpf_throw_ctx ctx = {};
+
+ arch_bpf_stack_walk(bpf_stack_walker, &ctx);
+ WARN_ON_ONCE(!ctx.aux);
+ if (ctx.aux)
+ WARN_ON_ONCE(!ctx.aux->exception_boundary);
+ WARN_ON_ONCE(!ctx.bp);
+ WARN_ON_ONCE(!ctx.cnt);
+ /* Prevent KASAN false positives for CONFIG_KASAN_STACK by unpoisoning
+ * deeper stack depths than ctx.sp as we do not return from bpf_throw,
+ * which skips compiler generated instrumentation to do the same.
+ */
+ kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
+ ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+ WARN(1, "A call to BPF exception callback should never return\n");
+}
+
+__bpf_kfunc_end_defs();
BTF_SET8_START(generic_btf_ids)
#ifdef CONFIG_KEXEC_CORE
BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
#endif
BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_percpu_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_percpu_obj_drop_impl, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_list_push_front_impl)
BTF_ID_FLAGS(func, bpf_list_push_back_impl)
@@ -2429,6 +2539,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
#endif
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_throw)
BTF_SET8_END(generic_btf_ids)
static const struct btf_kfunc_id_set generic_kfunc_set = {
@@ -2455,6 +2566,20 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW)
BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
+BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, bpf_dynptr_adjust)
BTF_ID_FLAGS(func, bpf_dynptr_is_null)
BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 4174f76133df..1aafb2ff2e95 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -118,9 +118,7 @@ static struct inode *bpf_get_inode(struct super_block *sb,
return ERR_PTR(-ENOSPC);
inode->i_ino = get_next_ino();
- inode->i_atime = current_time(inode);
- inode->i_mtime = inode->i_atime;
- inode->i_ctime = inode->i_atime;
+ simple_inode_init_ts(inode);
inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
@@ -148,8 +146,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
d_instantiate(dentry, inode);
dget(dentry);
- dir->i_mtime = current_time(dir);
- dir->i_ctime = dir->i_mtime;
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
}
static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir,
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index b0fa190b0979..6abd7c5df4b3 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -78,8 +78,7 @@ static const struct seq_operations bpf_map_seq_ops = {
.show = bpf_map_seq_show,
};
-BTF_ID_LIST(btf_bpf_map_id)
-BTF_ID(struct, bpf_map)
+BTF_ID_LIST_GLOBAL_SINGLE(btf_bpf_map_id, struct, bpf_map)
static const struct bpf_iter_seq_info bpf_map_seq_info = {
.seq_ops = &bpf_map_seq_ops,
@@ -93,7 +92,7 @@ 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 +192,38 @@ static int __init bpf_map_iter_init(void)
}
late_initcall(bpf_map_iter_init);
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc s64 bpf_map_sum_elem_count(const 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;
+}
+
+__bpf_kfunc_end_defs();
+
+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_UNSPEC, &bpf_map_iter_kfunc_set);
+}
+late_initcall(init_subsystem);
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 0668bcd7c926..6a51cfe4c2d6 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -98,11 +98,23 @@ struct bpf_mem_cache {
int free_cnt;
int low_watermark, high_watermark, batch;
int percpu_size;
+ bool draining;
+ struct bpf_mem_cache *tgt;
- struct rcu_head rcu;
+ /* 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;
+ struct rcu_head rcu_ttrace;
+ atomic_t call_rcu_ttrace_in_progress;
};
struct bpf_mem_caches {
@@ -153,59 +165,87 @@ static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
#endif
}
+static void inc_active(struct bpf_mem_cache *c, 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);
+}
+
+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)
+static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
{
struct mem_cgroup *memcg = NULL, *old_memcg;
- unsigned long flags;
+ gfp_t gfp;
void *obj;
int i;
- memcg = get_memcg(c);
- old_memcg = set_active_memcg(memcg);
+ gfp = __GFP_NOWARN | __GFP_ACCOUNT;
+ gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL;
+
for (i = 0; i < cnt; i++) {
/*
- * free_by_rcu 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.
- * 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);
- 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 (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.
+ obj = llist_del_first(&c->free_by_rcu_ttrace);
+ if (!obj)
+ break;
+ add_obj_to_free_list(c, obj);
+ }
+ 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++) {
+ /* 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.
*/
- 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);
+ obj = __alloc(c, node, gfp);
+ if (!obj)
+ break;
+ add_obj_to_free_list(c, obj);
}
set_active_memcg(old_memcg);
mem_cgroup_put(memcg);
@@ -222,20 +262,24 @@ 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)
{
- 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)
@@ -254,60 +298,132 @@ 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)) {
+ 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_add(llnode, &c->waiting_for_gp_ttrace);
+
+ if (unlikely(READ_ONCE(c->draining))) {
+ __free_rcu(&c->rcu_ttrace);
+ 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.
- * It doesn't race with llist_del_all either.
- * But there could be two concurrent llist_del_all(waiting_for_gp):
- * from __free_rcu() and from drain_mem_cache().
- */
- __llist_add(llnode, &c->waiting_for_gp);
/* 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)
{
+ 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);
+ WARN_ON_ONCE(tgt->percpu_size != c->percpu_size);
+
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);
+ 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(c);
+ enque_to_free(tgt, llnode);
+ 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;
+
+ WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+ WARN_ON_ONCE(tgt->percpu_size != c->percpu_size);
+
+ 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)
@@ -321,9 +437,11 @@ static void bpf_mem_refill(struct irq_work *work)
/* irq_work runs on this cpu and kmalloc will allocate
* from the current numa node which is what we want here.
*/
- alloc_bulk(c, c->batch, NUMA_NO_NODE);
+ alloc_bulk(c, c->batch, NUMA_NO_NODE, true);
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)
@@ -345,8 +463,7 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
* Typical case will be between 11K and 116K closer to 11K.
* bpf progs can and should share bpf_mem_cache when possible.
*/
-
-static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+static void init_refill_work(struct bpf_mem_cache *c)
{
init_irq_work(&c->refill_work, bpf_mem_refill);
if (c->unit_size <= 256) {
@@ -362,12 +479,36 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
c->high_watermark = max(96 * 256 / c->unit_size, 3);
}
c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+}
+static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+{
/* To avoid consuming memory assume that 1st run of bpf
* prog won't be doing more than 4 map_update_elem from
* irq disabled region
*/
- alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
+ alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
+}
+
+static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
+{
+ struct llist_node *first;
+ unsigned int obj_size;
+
+ first = c->free_llist.first;
+ if (!first)
+ return 0;
+
+ if (c->percpu_size)
+ obj_size = pcpu_alloc_size(((void **)first)[1]);
+ else
+ obj_size = ksize(first);
+ if (obj_size != c->unit_size) {
+ WARN_ONCE(1, "bpf_mem_cache[%u]: percpu %d, unexpected object size %u, expect %u\n",
+ idx, c->percpu_size, obj_size, c->unit_size);
+ return -EINVAL;
+ }
+ return 0;
}
/* When size != 0 bpf_mem_cache for each cpu.
@@ -380,20 +521,22 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
{
static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+ int cpu, i, err, unit_size, percpu_size = 0;
struct bpf_mem_caches *cc, __percpu *pcc;
struct bpf_mem_cache *c, __percpu *pc;
struct obj_cgroup *objcg = NULL;
- int cpu, i, unit_size, percpu_size = 0;
+
+ /* room for llist_node and per-cpu pointer */
+ if (percpu)
+ percpu_size = LLIST_NODE_SZ + sizeof(void *);
+ ma->percpu = percpu;
if (size) {
pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
if (!pc)
return -ENOMEM;
- if (percpu)
- /* room for llist_node and per-cpu pointer */
- percpu_size = LLIST_NODE_SZ + sizeof(void *);
- else
+ if (!percpu)
size += LLIST_NODE_SZ; /* room for llist_node */
unit_size = size;
@@ -406,19 +549,18 @@ 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;
+ init_refill_work(c);
prefill_mem_cache(c, cpu);
}
ma->cache = pc;
return 0;
}
- /* size == 0 && percpu is an invalid combination */
- if (WARN_ON_ONCE(percpu))
- return -EINVAL;
-
pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
if (!pcc)
return -ENOMEM;
+ err = 0;
#ifdef CONFIG_MEMCG_KMEM
objcg = get_obj_cgroup_from_current();
#endif
@@ -428,11 +570,32 @@ 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->percpu_size = percpu_size;
+ c->tgt = c;
+
+ init_refill_work(c);
+ /* Another bpf_mem_cache will be used when allocating
+ * c->unit_size in bpf_mem_alloc(), so doesn't prefill
+ * for the bpf_mem_cache because these free objects will
+ * never be used.
+ */
+ if (i != bpf_mem_cache_idx(c->unit_size))
+ continue;
prefill_mem_cache(c, cpu);
+ err = check_obj_size(c, i);
+ if (err)
+ goto out;
}
}
+
+out:
ma->caches = pcc;
- return 0;
+ /* refill_work is either zeroed or initialized, so it is safe to
+ * call irq_work_sync().
+ */
+ if (err)
+ bpf_mem_alloc_destroy(ma);
+ return err;
}
static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -441,19 +604,57 @@ 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);
+ 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 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;
@@ -462,8 +663,8 @@ 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 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
@@ -472,7 +673,8 @@ 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);
@@ -498,7 +700,7 @@ 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);
@@ -506,10 +708,7 @@ 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);
}
@@ -524,17 +723,10 @@ 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);
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
/* objcg is the same across cpus */
@@ -548,8 +740,10 @@ 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);
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
}
@@ -581,16 +775,23 @@ 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);
WARN_ON(cnt < 0);
if (cnt < c->low_watermark)
irq_work_raise(c);
+ /* Enable IRQ after the enqueue of irq work completes, so irq work
+ * will run after IRQ is enabled and free_llist may be refilled by
+ * irq work before other task preempts current task.
+ */
+ local_irq_restore(flags);
+
return llnode;
}
@@ -606,6 +807,12 @@ 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);
@@ -620,11 +827,37 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
llist_add(llnode, &c->free_llist_extra);
}
local_dec(&c->active);
- local_irq_restore(flags);
if (cnt > c->high_watermark)
/* free few objects from current cpu into global kmalloc pool */
irq_work_raise(c);
+ /* Enable IRQ after irq_work_raise() completes, otherwise when current
+ * task is preempted by task which does unit_alloc(), unit_alloc() may
+ * return NULL unexpectedly because irq work is already pending but can
+ * not been triggered and free_llist can not be refilled timely.
+ */
+ local_irq_restore(flags);
+}
+
+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);
+
+ if (!atomic_read(&c->call_rcu_in_progress))
+ irq_work_raise(c);
+ local_irq_restore(flags);
}
/* Called from BPF program or from sys_bpf syscall.
@@ -646,6 +879,17 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
return !ret ? NULL : ret + LLIST_NODE_SZ;
}
+static notrace int bpf_mem_free_idx(void *ptr, bool percpu)
+{
+ size_t size;
+
+ if (percpu)
+ size = pcpu_alloc_size(*((void **)ptr));
+ else
+ size = ksize(ptr - LLIST_NODE_SZ);
+ return bpf_mem_cache_idx(size);
+}
+
void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
{
int idx;
@@ -653,13 +897,27 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
if (!ptr)
return;
- idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ));
+ idx = bpf_mem_free_idx(ptr, ma->percpu);
if (idx < 0)
return;
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_free_idx(ptr, ma->percpu);
+ 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;
@@ -676,6 +934,14 @@ 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'
@@ -712,9 +978,49 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
memcg = get_memcg(c);
old_memcg = set_active_memcg(memcg);
ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT);
+ if (ret)
+ *(struct bpf_mem_cache **)ret = c;
set_active_memcg(old_memcg);
mem_cgroup_put(memcg);
}
return !ret ? NULL : ret + LLIST_NODE_SZ;
}
+
+/* The alignment of dynamic per-cpu area is 8, so c->unit_size and the
+ * actual size of dynamic per-cpu area will always be matched and there is
+ * no need to adjust size_index for per-cpu allocation. However for the
+ * simplicity of the implementation, use an unified size_index for both
+ * kmalloc and per-cpu allocation.
+ */
+static __init int bpf_mem_cache_adjust_size(void)
+{
+ unsigned int size;
+
+ /* Adjusting the indexes in size_index() according to the object_size
+ * of underlying slab cache, so bpf_mem_alloc() will select a
+ * bpf_mem_cache with unit_size equal to the object_size of
+ * the underlying slab cache.
+ *
+ * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is
+ * 256-bytes, so only do adjustment for [8-bytes, 192-bytes].
+ */
+ for (size = 192; size >= 8; size -= 8) {
+ unsigned int kmalloc_size, index;
+
+ kmalloc_size = kmalloc_size_roundup(size);
+ if (kmalloc_size == size)
+ continue;
+
+ if (kmalloc_size <= 192)
+ index = size_index[(kmalloc_size - 1) / 8];
+ else
+ index = fls(kmalloc_size - 1) - 1;
+ /* Only overwrite if necessary */
+ if (size_index[(size - 1) / 8] != index)
+ size_index[(size - 1) / 8] = index;
+ }
+
+ return 0;
+}
+subsys_initcall(bpf_mem_cache_adjust_size);
diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
new file mode 100644
index 000000000000..1394168062e8
--- /dev/null
+++ b/kernel/bpf/mprog.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+
+static int bpf_mprog_link(struct bpf_tuple *tuple,
+ u32 id_or_fd, u32 flags,
+ enum bpf_prog_type type)
+{
+ struct bpf_link *link = ERR_PTR(-EINVAL);
+ bool id = flags & BPF_F_ID;
+
+ if (id)
+ link = bpf_link_by_id(id_or_fd);
+ else if (id_or_fd)
+ link = bpf_link_get_from_fd(id_or_fd);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+ if (type && link->prog->type != type) {
+ bpf_link_put(link);
+ return -EINVAL;
+ }
+
+ tuple->link = link;
+ tuple->prog = link->prog;
+ return 0;
+}
+
+static int bpf_mprog_prog(struct bpf_tuple *tuple,
+ u32 id_or_fd, u32 flags,
+ enum bpf_prog_type type)
+{
+ struct bpf_prog *prog = ERR_PTR(-EINVAL);
+ bool id = flags & BPF_F_ID;
+
+ if (id)
+ prog = bpf_prog_by_id(id_or_fd);
+ else if (id_or_fd)
+ prog = bpf_prog_get(id_or_fd);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+ if (type && prog->type != type) {
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
+ tuple->link = NULL;
+ tuple->prog = prog;
+ return 0;
+}
+
+static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple,
+ u32 id_or_fd, u32 flags,
+ enum bpf_prog_type type)
+{
+ bool link = flags & BPF_F_LINK;
+ bool id = flags & BPF_F_ID;
+
+ memset(tuple, 0, sizeof(*tuple));
+ if (link)
+ return bpf_mprog_link(tuple, id_or_fd, flags, type);
+ /* If no relevant flag is set and no id_or_fd was passed, then
+ * tuple link/prog is just NULLed. This is the case when before/
+ * after selects first/last position without passing fd.
+ */
+ if (!id && !id_or_fd)
+ return 0;
+ return bpf_mprog_prog(tuple, id_or_fd, flags, type);
+}
+
+static void bpf_mprog_tuple_put(struct bpf_tuple *tuple)
+{
+ if (tuple->link)
+ bpf_link_put(tuple->link);
+ else if (tuple->prog)
+ bpf_prog_put(tuple->prog);
+}
+
+/* The bpf_mprog_{replace,delete}() operate on exact idx position with the
+ * one exception that for deletion we support delete from front/back. In
+ * case of front idx is -1, in case of back idx is bpf_mprog_total(entry).
+ * Adjustment to first and last entry is trivial. The bpf_mprog_insert()
+ * we have to deal with the following cases:
+ *
+ * idx + before:
+ *
+ * Insert P4 before P3: idx for old array is 1, idx for new array is 2,
+ * hence we adjust target idx for the new array, so that memmove copies
+ * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting
+ * before P1 would have old idx -1 and new idx 0.
+ *
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3|
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ *
+ * idx + after:
+ *
+ * Insert P4 after P2: idx for old array is 2, idx for new array is 2.
+ * Again, memmove copies P1 and P2 to the new entry, and we insert P4
+ * into idx 2. Inserting after P3 would have both old/new idx at 4 aka
+ * bpf_mprog_total(entry).
+ *
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3|
+ * +--+--+--+ +--+--+--+--+ +--+--+--+--+
+ */
+static int bpf_mprog_replace(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_tuple *ntuple, int idx)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ struct bpf_prog *oprog;
+
+ bpf_mprog_read(entry, idx, &fp, &cp);
+ oprog = READ_ONCE(fp->prog);
+ bpf_mprog_write(fp, cp, ntuple);
+ if (!ntuple->link) {
+ WARN_ON_ONCE(cp->link);
+ bpf_prog_put(oprog);
+ }
+ *entry_new = entry;
+ return 0;
+}
+
+static int bpf_mprog_insert(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_tuple *ntuple, int idx, u32 flags)
+{
+ int total = bpf_mprog_total(entry);
+ struct bpf_mprog_entry *peer;
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+
+ peer = bpf_mprog_peer(entry);
+ bpf_mprog_entry_copy(peer, entry);
+ if (idx == total)
+ goto insert;
+ else if (flags & BPF_F_BEFORE)
+ idx += 1;
+ bpf_mprog_entry_grow(peer, idx);
+insert:
+ bpf_mprog_read(peer, idx, &fp, &cp);
+ bpf_mprog_write(fp, cp, ntuple);
+ bpf_mprog_inc(peer);
+ *entry_new = peer;
+ return 0;
+}
+
+static int bpf_mprog_delete(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_tuple *dtuple, int idx)
+{
+ int total = bpf_mprog_total(entry);
+ struct bpf_mprog_entry *peer;
+
+ peer = bpf_mprog_peer(entry);
+ bpf_mprog_entry_copy(peer, entry);
+ if (idx == -1)
+ idx = 0;
+ else if (idx == total)
+ idx = total - 1;
+ bpf_mprog_entry_shrink(peer, idx);
+ bpf_mprog_dec(peer);
+ bpf_mprog_mark_for_release(peer, dtuple);
+ *entry_new = peer;
+ return 0;
+}
+
+/* In bpf_mprog_pos_*() we evaluate the target position for the BPF
+ * program/link that needs to be replaced, inserted or deleted for
+ * each "rule" independently. If all rules agree on that position
+ * or existing element, then enact replacement, addition or deletion.
+ * If this is not the case, then the request cannot be satisfied and
+ * we bail out with an error.
+ */
+static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ int i;
+
+ for (i = 0; i < bpf_mprog_total(entry); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ if (tuple->prog == READ_ONCE(fp->prog))
+ return tuple->link == cp->link ? i : -EBUSY;
+ }
+ return -ENOENT;
+}
+
+static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ int i;
+
+ for (i = 0; i < bpf_mprog_total(entry); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ if (tuple->prog == READ_ONCE(fp->prog) &&
+ (!tuple->link || tuple->link == cp->link))
+ return i - 1;
+ }
+ return tuple->prog ? -ENOENT : -1;
+}
+
+static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple)
+{
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ int i;
+
+ for (i = 0; i < bpf_mprog_total(entry); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ if (tuple->prog == READ_ONCE(fp->prog) &&
+ (!tuple->link || tuple->link == cp->link))
+ return i + 1;
+ }
+ return tuple->prog ? -ENOENT : bpf_mprog_total(entry);
+}
+
+int bpf_mprog_attach(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_prog *prog_new, struct bpf_link *link,
+ struct bpf_prog *prog_old,
+ u32 flags, u32 id_or_fd, u64 revision)
+{
+ struct bpf_tuple rtuple, ntuple = {
+ .prog = prog_new,
+ .link = link,
+ }, otuple = {
+ .prog = prog_old,
+ .link = link,
+ };
+ int ret, idx = -ERANGE, tidx;
+
+ if (revision && revision != bpf_mprog_revision(entry))
+ return -ESTALE;
+ if (bpf_mprog_exists(entry, prog_new))
+ return -EEXIST;
+ ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd,
+ flags & ~BPF_F_REPLACE,
+ prog_new->type);
+ if (ret)
+ return ret;
+ if (flags & BPF_F_REPLACE) {
+ tidx = bpf_mprog_pos_exact(entry, &otuple);
+ if (tidx < 0) {
+ ret = tidx;
+ goto out;
+ }
+ idx = tidx;
+ } else if (bpf_mprog_total(entry) == bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
+ }
+ if (flags & BPF_F_BEFORE) {
+ tidx = bpf_mprog_pos_before(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < -1 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (flags & BPF_F_AFTER) {
+ tidx = bpf_mprog_pos_after(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < 0 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (idx < -1) {
+ if (rtuple.prog || flags) {
+ ret = -EINVAL;
+ goto out;
+ }
+ idx = bpf_mprog_total(entry);
+ flags = BPF_F_AFTER;
+ }
+ if (idx >= bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
+ }
+ if (flags & BPF_F_REPLACE)
+ ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx);
+ else
+ ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags);
+out:
+ bpf_mprog_tuple_put(&rtuple);
+ return ret;
+}
+
+static int bpf_mprog_fetch(struct bpf_mprog_entry *entry,
+ struct bpf_tuple *tuple, int idx)
+{
+ int total = bpf_mprog_total(entry);
+ struct bpf_mprog_cp *cp;
+ struct bpf_mprog_fp *fp;
+ struct bpf_prog *prog;
+ struct bpf_link *link;
+
+ if (idx == -1)
+ idx = 0;
+ else if (idx == total)
+ idx = total - 1;
+ bpf_mprog_read(entry, idx, &fp, &cp);
+ prog = READ_ONCE(fp->prog);
+ link = cp->link;
+ /* The deletion request can either be without filled tuple in which
+ * case it gets populated here based on idx, or with filled tuple
+ * where the only thing we end up doing is the WARN_ON_ONCE() assert.
+ * If we hit a BPF link at the given index, it must not be removed
+ * from opts path.
+ */
+ if (link && !tuple->link)
+ return -EBUSY;
+ WARN_ON_ONCE(tuple->prog && tuple->prog != prog);
+ WARN_ON_ONCE(tuple->link && tuple->link != link);
+ tuple->prog = prog;
+ tuple->link = link;
+ return 0;
+}
+
+int bpf_mprog_detach(struct bpf_mprog_entry *entry,
+ struct bpf_mprog_entry **entry_new,
+ struct bpf_prog *prog, struct bpf_link *link,
+ u32 flags, u32 id_or_fd, u64 revision)
+{
+ struct bpf_tuple rtuple, dtuple = {
+ .prog = prog,
+ .link = link,
+ };
+ int ret, idx = -ERANGE, tidx;
+
+ if (flags & BPF_F_REPLACE)
+ return -EINVAL;
+ if (revision && revision != bpf_mprog_revision(entry))
+ return -ESTALE;
+ if (!bpf_mprog_total(entry))
+ return -ENOENT;
+ ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags,
+ prog ? prog->type :
+ BPF_PROG_TYPE_UNSPEC);
+ if (ret)
+ return ret;
+ if (dtuple.prog) {
+ tidx = bpf_mprog_pos_exact(entry, &dtuple);
+ if (tidx < 0) {
+ ret = tidx;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (flags & BPF_F_BEFORE) {
+ tidx = bpf_mprog_pos_before(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < -1 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (flags & BPF_F_AFTER) {
+ tidx = bpf_mprog_pos_after(entry, &rtuple);
+ if (tidx < -1 || (idx >= -1 && tidx != idx)) {
+ ret = tidx < 0 ? tidx : -ERANGE;
+ goto out;
+ }
+ idx = tidx;
+ }
+ if (idx < -1) {
+ if (rtuple.prog || flags) {
+ ret = -EINVAL;
+ goto out;
+ }
+ idx = bpf_mprog_total(entry);
+ flags = BPF_F_AFTER;
+ }
+ if (idx >= bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
+ }
+ ret = bpf_mprog_fetch(entry, &dtuple, idx);
+ if (ret)
+ goto out;
+ ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx);
+out:
+ bpf_mprog_tuple_put(&rtuple);
+ return ret;
+}
+
+int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
+ struct bpf_mprog_entry *entry)
+{
+ u32 __user *uprog_flags, *ulink_flags;
+ u32 __user *uprog_id, *ulink_id;
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ struct bpf_prog *prog;
+ const u32 flags = 0;
+ u32 id, count = 0;
+ u64 revision = 1;
+ int i, ret = 0;
+
+ if (attr->query.query_flags || attr->query.attach_flags)
+ return -EINVAL;
+ if (entry) {
+ revision = bpf_mprog_revision(entry);
+ count = bpf_mprog_total(entry);
+ }
+ if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+ return -EFAULT;
+ if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
+ return -EFAULT;
+ if (copy_to_user(&uattr->query.count, &count, sizeof(count)))
+ return -EFAULT;
+ uprog_id = u64_to_user_ptr(attr->query.prog_ids);
+ uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags);
+ ulink_id = u64_to_user_ptr(attr->query.link_ids);
+ ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags);
+ if (attr->query.count == 0 || !uprog_id || !count)
+ return 0;
+ if (attr->query.count < count) {
+ count = attr->query.count;
+ ret = -ENOSPC;
+ }
+ for (i = 0; i < bpf_mprog_max(); i++) {
+ bpf_mprog_read(entry, i, &fp, &cp);
+ prog = READ_ONCE(fp->prog);
+ if (!prog)
+ break;
+ id = prog->aux->id;
+ if (copy_to_user(uprog_id + i, &id, sizeof(id)))
+ return -EFAULT;
+ if (uprog_flags &&
+ copy_to_user(uprog_flags + i, &flags, sizeof(flags)))
+ return -EFAULT;
+ id = cp->link ? cp->link->id : 0;
+ if (ulink_id &&
+ copy_to_user(ulink_id + i, &id, sizeof(id)))
+ return -EFAULT;
+ if (ulink_flags &&
+ copy_to_user(ulink_flags + i, &flags, sizeof(flags)))
+ return -EFAULT;
+ if (i + 1 == count)
+ break;
+ }
+ return ret;
+}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 8a26cd8814c1..1a4fec330eaa 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -25,6 +25,7 @@
#include <linux/rhashtable.h>
#include <linux/rtnetlink.h>
#include <linux/rwsem.h>
+#include <net/xdp.h>
/* Protects offdevs, members of bpf_offload_netdev and offload members
* of all progs.
@@ -198,12 +199,14 @@ static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *n
offload->netdev = netdev;
ondev = bpf_offload_find_netdev(offload->netdev);
+ /* When program is offloaded require presence of "true"
+ * bpf_offload_netdev, avoid the one created for !ondev case below.
+ */
+ if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) {
+ err = -EINVAL;
+ goto err_free;
+ }
if (!ondev) {
- if (bpf_prog_is_offloaded(prog->aux)) {
- err = -EINVAL;
- goto err_free;
- }
-
/* When only binding to the device, explicitly
* create an entry in the hashtable.
*/
@@ -231,7 +234,14 @@ int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
attr->prog_type != BPF_PROG_TYPE_XDP)
return -EINVAL;
- if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY)
+ if (attr->prog_flags & ~(BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_XDP_HAS_FRAGS))
+ return -EINVAL;
+
+ /* Frags are allowed only if program is dev-bound-only, but not
+ * if it is requesting bpf offload.
+ */
+ if (attr->prog_flags & BPF_F_XDP_HAS_FRAGS &&
+ !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY))
return -EINVAL;
if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS &&
@@ -844,10 +854,11 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
if (!ops)
goto out;
- if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP))
- p = ops->xmo_rx_timestamp;
- else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
- p = ops->xmo_rx_hash;
+#define XDP_METADATA_KFUNC(name, _, __, xmo) \
+ if (func_id == bpf_xdp_metadata_kfunc_id(name)) p = ops->xmo;
+ XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+
out:
up_read(&bpf_devs_lock);
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 $@
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__ */
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8d2ddcb7566b..d869f51ea93a 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
int err = 0;
void *ptr;
- raw_spin_lock_irqsave(&qs->lock, flags);
+ if (in_nmi()) {
+ if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+ return -EBUSY;
+ } else {
+ raw_spin_lock_irqsave(&qs->lock, flags);
+ }
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
@@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
void *ptr;
u32 index;
- raw_spin_lock_irqsave(&qs->lock, flags);
+ if (in_nmi()) {
+ if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+ return -EBUSY;
+ } else {
+ raw_spin_lock_irqsave(&qs->lock, flags);
+ }
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
@@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
if (flags & BPF_NOEXIST || flags > BPF_EXIST)
return -EINVAL;
- raw_spin_lock_irqsave(&qs->lock, irq_flags);
+ if (in_nmi()) {
+ if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
+ return -EBUSY;
+ } else {
+ raw_spin_lock_irqsave(&qs->lock, irq_flags);
+ }
if (queue_stack_map_is_full(qs)) {
if (!replace) {
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 875ac9b698d9..0ee653a936ea 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);
@@ -774,8 +770,7 @@ schedule_work_return:
/* Prevent the clearing of the busy-bit from being reordered before the
* storing of any rb consumer or producer positions.
*/
- smp_mb__before_atomic();
- atomic_set(&rb->busy, 0);
+ atomic_set_release(&rb->busy, 0);
if (flags & BPF_RB_FORCE_WAKEUP)
irq_work_queue(&rb->work);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 458bb80b14d5..d6b277482085 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -28,7 +28,7 @@ struct bpf_stack_map {
void *elems;
struct pcpu_freelist freelist;
u32 n_buckets;
- struct stack_map_bucket *buckets[];
+ struct stack_map_bucket *buckets[] __counted_by(n_buckets);
};
static inline bool stack_map_use_build_id(struct bpf_map *map)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a2aef900519c..0ed286b8a0f0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -35,7 +35,10 @@
#include <linux/rcupdate_trace.h>
#include <linux/memcontrol.h>
#include <linux/trace_events.h>
+
#include <net/netfilter/nf_bpf_link.h>
+#include <net/netkit.h>
+#include <net/tcx.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -512,6 +515,7 @@ void btf_record_free(struct btf_record *rec)
switch (rec->fields[i].type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
if (rec->fields[i].kptr.module)
module_put(rec->fields[i].kptr.module);
btf_put(rec->fields[i].kptr.btf);
@@ -558,6 +562,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
switch (fields[i].type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
btf_get(fields[i].kptr.btf);
if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) {
ret = -ENXIO;
@@ -622,8 +627,6 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj)
bpf_timer_cancel_and_free(obj + rec->timer_off);
}
-extern void __bpf_obj_drop_impl(void *p, const struct btf_record *rec);
-
void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
{
const struct btf_field *fields;
@@ -648,6 +651,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
WRITE_ONCE(*(u64 *)field_ptr, 0);
break;
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0);
if (!xchgd_field)
break;
@@ -655,11 +659,10 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
if (!btf_is_kernel(field->kptr.btf)) {
pointee_struct_meta = btf_find_struct_meta(field->kptr.btf,
field->kptr.btf_id);
- WARN_ON_ONCE(!pointee_struct_meta);
migrate_disable();
__bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ?
- pointee_struct_meta->record :
- NULL);
+ pointee_struct_meta->record : NULL,
+ fields[i].type == BPF_KPTR_PERCPU);
migrate_enable();
} else {
field->kptr.dtor(xchgd_field);
@@ -1044,6 +1047,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
case BPF_REFCOUNT:
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
@@ -2441,14 +2445,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
return 0;
default:
return -EINVAL;
@@ -2744,7 +2753,7 @@ free_used_maps:
* period before we can tear down JIT memory since symbols
* are already exposed under kallsyms.
*/
- __bpf_prog_put_noref(prog, prog->aux->func_cnt);
+ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
return err;
free_prog_sec:
free_uid(prog->aux->user);
@@ -2813,10 +2822,12 @@ static void bpf_link_free_id(int id)
/* Clean up bpf_link and corresponding anon_inode file and FD. After
* anon_inode is created, bpf_link can't be just kfree()'d due to deferred
- * anon_inode's release() call. This helper marksbpf_link as
+ * anon_inode's release() call. This helper marks bpf_link as
* defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt
* is not decremented, it's the responsibility of a calling code that failed
* to complete bpf_link initialization.
+ * This helper eventually calls link's dealloc callback, but does not call
+ * link's release callback.
*/
void bpf_link_cleanup(struct bpf_link_primer *primer)
{
@@ -3295,6 +3306,25 @@ 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 +3343,7 @@ 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 = {
@@ -3358,9 +3375,156 @@ 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, unsigned long *missed)
+{
+ const char *buf;
+ u32 prog_id;
+ size_t len;
+ int err;
+
+ if (!ulen ^ !uname)
+ return -EINVAL;
+
+ err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
+ probe_offset, probe_addr, missed);
+ if (err)
+ return err;
+ if (!uname)
+ return 0;
+ 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)
+{
+ unsigned long missed;
+ 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, &missed);
+ 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;
+ info->perf_event.kprobe.missed = missed;
+ 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, NULL);
+ 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, 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)
@@ -3502,34 +3666,6 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
return fd;
}
-static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
- enum bpf_attach_type attach_type)
-{
- switch (prog->type) {
- case BPF_PROG_TYPE_CGROUP_SOCK:
- case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
- case BPF_PROG_TYPE_CGROUP_SOCKOPT:
- case BPF_PROG_TYPE_SK_LOOKUP:
- return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
- case BPF_PROG_TYPE_CGROUP_SKB:
- if (!capable(CAP_NET_ADMIN))
- /* cg-skb progs can be loaded by unpriv user.
- * check permissions at attach time.
- */
- return -EPERM;
- return prog->enforce_expected_attach_type &&
- prog->expected_attach_type != attach_type ?
- -EINVAL : 0;
- case BPF_PROG_TYPE_KPROBE:
- if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
- attach_type != BPF_TRACE_KPROBE_MULTI)
- return -EINVAL;
- return 0;
- default:
- return 0;
- }
-}
-
static enum bpf_prog_type
attach_type_to_prog_type(enum bpf_attach_type attach_type)
{
@@ -3546,14 +3682,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
return BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
case BPF_CGROUP_SOCK_OPS:
return BPF_PROG_TYPE_SOCK_OPS;
@@ -3588,15 +3729,87 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
return BPF_PROG_TYPE_XDP;
case BPF_LSM_CGROUP:
return BPF_PROG_TYPE_LSM;
+ case BPF_TCX_INGRESS:
+ case BPF_TCX_EGRESS:
+ case BPF_NETKIT_PRIMARY:
+ case BPF_NETKIT_PEER:
+ return BPF_PROG_TYPE_SCHED_CLS;
default:
return BPF_PROG_TYPE_UNSPEC;
}
}
-#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
+static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
+ enum bpf_attach_type attach_type)
+{
+ enum bpf_prog_type ptype;
-#define BPF_F_ATTACH_MASK \
- (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
+ switch (prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_SK_LOOKUP:
+ return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ if (!capable(CAP_NET_ADMIN))
+ /* cg-skb progs can be loaded by unpriv user.
+ * check permissions at attach time.
+ */
+ return -EPERM;
+ return prog->enforce_expected_attach_type &&
+ prog->expected_attach_type != attach_type ?
+ -EINVAL : 0;
+ case BPF_PROG_TYPE_EXT:
+ return 0;
+ case BPF_PROG_TYPE_NETFILTER:
+ if (attach_type != BPF_NETFILTER)
+ return -EINVAL;
+ return 0;
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ if (attach_type != BPF_PERF_EVENT)
+ return -EINVAL;
+ return 0;
+ case BPF_PROG_TYPE_KPROBE:
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
+ attach_type != BPF_TRACE_KPROBE_MULTI)
+ return -EINVAL;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
+ attach_type != BPF_TRACE_UPROBE_MULTI)
+ return -EINVAL;
+ if (attach_type != BPF_PERF_EVENT &&
+ attach_type != BPF_TRACE_KPROBE_MULTI &&
+ attach_type != BPF_TRACE_UPROBE_MULTI)
+ return -EINVAL;
+ return 0;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attach_type != BPF_TCX_INGRESS &&
+ attach_type != BPF_TCX_EGRESS &&
+ attach_type != BPF_NETKIT_PRIMARY &&
+ attach_type != BPF_NETKIT_PEER)
+ return -EINVAL;
+ return 0;
+ default:
+ ptype = attach_type_to_prog_type(attach_type);
+ if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type)
+ return -EINVAL;
+ return 0;
+ }
+}
+
+#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
+
+#define BPF_F_ATTACH_MASK_BASE \
+ (BPF_F_ALLOW_OVERRIDE | \
+ BPF_F_ALLOW_MULTI | \
+ BPF_F_REPLACE)
+
+#define BPF_F_ATTACH_MASK_MPROG \
+ (BPF_F_REPLACE | \
+ BPF_F_BEFORE | \
+ BPF_F_AFTER | \
+ BPF_F_ID | \
+ BPF_F_LINK)
static int bpf_prog_attach(const union bpf_attr *attr)
{
@@ -3607,12 +3820,19 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
- if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
- return -EINVAL;
-
ptype = attach_type_to_prog_type(attr->attach_type);
if (ptype == BPF_PROG_TYPE_UNSPEC)
return -EINVAL;
+ if (bpf_mprog_supported(ptype)) {
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+ return -EINVAL;
+ } else {
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
+ return -EINVAL;
+ if (attr->relative_fd ||
+ attr->expected_revision)
+ return -EINVAL;
+ }
prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
if (IS_ERR(prog))
@@ -3648,6 +3868,13 @@ static int bpf_prog_attach(const union bpf_attr *attr)
else
ret = cgroup_bpf_prog_attach(attr, ptype, prog);
break;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attr->attach_type == BPF_TCX_INGRESS ||
+ attr->attach_type == BPF_TCX_EGRESS)
+ ret = tcx_prog_attach(attr, prog);
+ else
+ ret = netkit_prog_attach(attr, prog);
+ break;
default:
ret = -EINVAL;
}
@@ -3657,25 +3884,45 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return ret;
}
-#define BPF_PROG_DETACH_LAST_FIELD attach_type
+#define BPF_PROG_DETACH_LAST_FIELD expected_revision
static int bpf_prog_detach(const union bpf_attr *attr)
{
+ struct bpf_prog *prog = NULL;
enum bpf_prog_type ptype;
+ int ret;
if (CHECK_ATTR(BPF_PROG_DETACH))
return -EINVAL;
ptype = attach_type_to_prog_type(attr->attach_type);
+ if (bpf_mprog_supported(ptype)) {
+ if (ptype == BPF_PROG_TYPE_UNSPEC)
+ return -EINVAL;
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+ return -EINVAL;
+ if (attr->attach_bpf_fd) {
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+ }
+ } else if (attr->attach_flags ||
+ attr->relative_fd ||
+ attr->expected_revision) {
+ return -EINVAL;
+ }
switch (ptype) {
case BPF_PROG_TYPE_SK_MSG:
case BPF_PROG_TYPE_SK_SKB:
- return sock_map_prog_detach(attr, ptype);
+ ret = sock_map_prog_detach(attr, ptype);
+ break;
case BPF_PROG_TYPE_LIRC_MODE2:
- return lirc_prog_detach(attr);
+ ret = lirc_prog_detach(attr);
+ break;
case BPF_PROG_TYPE_FLOW_DISSECTOR:
- return netns_bpf_prog_detach(attr, ptype);
+ ret = netns_bpf_prog_detach(attr, ptype);
+ break;
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_CGROUP_SKB:
case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -3684,13 +3931,25 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_LSM:
- return cgroup_bpf_prog_detach(attr, ptype);
+ ret = cgroup_bpf_prog_detach(attr, ptype);
+ break;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attr->attach_type == BPF_TCX_INGRESS ||
+ attr->attach_type == BPF_TCX_EGRESS)
+ ret = tcx_prog_detach(attr, prog);
+ else
+ ret = netkit_prog_detach(attr, prog);
+ break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
+
+ if (prog)
+ bpf_prog_put(prog);
+ return ret;
}
-#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags
+#define BPF_PROG_QUERY_LAST_FIELD query.revision
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
@@ -3713,14 +3972,19 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET6_POST_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
case BPF_CGROUP_SYSCTL:
@@ -3738,6 +4002,12 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_SK_MSG_VERDICT:
case BPF_SK_SKB_VERDICT:
return sock_map_bpf_prog_query(attr, uattr);
+ case BPF_TCX_INGRESS:
+ case BPF_TCX_EGRESS:
+ return tcx_prog_query(attr, uattr);
+ case BPF_NETKIT_PRIMARY:
+ case BPF_NETKIT_PEER:
+ return netkit_prog_query(attr, uattr);
default:
return -EINVAL;
}
@@ -4583,7 +4853,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
&buf, &probe_offset,
- &probe_addr);
+ &probe_addr, NULL);
if (!err)
err = bpf_task_fd_query_copy(attr, uattr, prog_id,
fd_type, buf,
@@ -4655,10 +4925,9 @@ err_put:
return err;
}
-#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies
+#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid
static int link_create(union bpf_attr *attr, bpfptr_t uattr)
{
- enum bpf_prog_type ptype;
struct bpf_prog *prog;
int ret;
@@ -4678,38 +4947,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
goto out;
switch (prog->type) {
- case BPF_PROG_TYPE_EXT:
- break;
- case BPF_PROG_TYPE_NETFILTER:
- if (attr->link_create.attach_type != BPF_NETFILTER) {
- ret = -EINVAL;
- goto out;
- }
- break;
- case BPF_PROG_TYPE_PERF_EVENT:
- case BPF_PROG_TYPE_TRACEPOINT:
- if (attr->link_create.attach_type != BPF_PERF_EVENT) {
- ret = -EINVAL;
- goto out;
- }
- break;
- case BPF_PROG_TYPE_KPROBE:
- if (attr->link_create.attach_type != BPF_PERF_EVENT &&
- attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) {
- ret = -EINVAL;
- goto out;
- }
- break;
- default:
- ptype = attach_type_to_prog_type(attr->link_create.attach_type);
- if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
- ret = -EINVAL;
- goto out;
- }
- break;
- }
-
- switch (prog->type) {
case BPF_PROG_TYPE_CGROUP_SKB:
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@@ -4751,6 +4988,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
case BPF_PROG_TYPE_XDP:
ret = bpf_xdp_link_attach(attr, prog);
break;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ if (attr->link_create.attach_type == BPF_TCX_INGRESS ||
+ attr->link_create.attach_type == BPF_TCX_EGRESS)
+ ret = tcx_link_attach(attr, prog);
+ else
+ ret = netkit_link_attach(attr, prog);
+ break;
case BPF_PROG_TYPE_NETFILTER:
ret = bpf_nf_link_attach(attr, prog);
break;
@@ -4762,8 +5006,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
case BPF_PROG_TYPE_KPROBE:
if (attr->link_create.attach_type == BPF_PERF_EVENT)
ret = bpf_perf_link_attach(attr, prog);
- else
+ else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI)
ret = bpf_kprobe_multi_link_attach(attr, prog);
+ else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI)
+ ret = bpf_uprobe_multi_link_attach(attr, prog);
break;
default:
ret = -EINVAL;
@@ -5304,9 +5550,9 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
}
run_ctx.bpf_cookie = 0;
- run_ctx.saved_run_ctx = NULL;
if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) {
/* recursion detected */
+ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx);
bpf_prog_put(prog);
return -EBUSY;
}
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index c4ab9d6cdbe9..26082b97894d 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -7,7 +7,9 @@
#include <linux/fs.h>
#include <linux/fdtable.h>
#include <linux/filter.h>
+#include <linux/bpf_mem_alloc.h>
#include <linux/btf_ids.h>
+#include <linux/mm_types.h>
#include "mmap_unlock_work.h"
static const char * const iter_task_type_names[] = {
@@ -35,16 +37,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
u32 *tid,
bool skip_if_dup_files)
{
- struct task_struct *task, *next_task;
+ struct task_struct *task;
struct pid *pid;
- u32 saved_tid;
+ u32 next_tid;
if (!*tid) {
/* The first time, the iterator calls this function. */
pid = find_pid_ns(common->pid, common->ns);
- if (!pid)
- return NULL;
-
task = get_pid_task(pid, PIDTYPE_TGID);
if (!task)
return NULL;
@@ -66,44 +65,27 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
return task;
}
- pid = find_pid_ns(common->pid_visiting, common->ns);
- if (!pid)
- return NULL;
-
- task = get_pid_task(pid, PIDTYPE_PID);
+ task = find_task_by_pid_ns(common->pid_visiting, common->ns);
if (!task)
return NULL;
retry:
- if (!pid_alive(task)) {
- put_task_struct(task);
- return NULL;
- }
+ task = next_thread(task);
- next_task = next_thread(task);
- put_task_struct(task);
- if (!next_task)
- return NULL;
-
- saved_tid = *tid;
- *tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns);
- if (!*tid || *tid == common->pid) {
+ next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns);
+ if (!next_tid || next_tid == common->pid) {
/* Run out of tasks of a process. The tasks of a
* thread_group are linked as circular linked list.
*/
- *tid = saved_tid;
return NULL;
}
- get_task_struct(next_task);
- common->pid_visiting = *tid;
-
- if (skip_if_dup_files && task->files == task->group_leader->files) {
- task = next_task;
+ if (skip_if_dup_files && task->files == task->group_leader->files)
goto retry;
- }
- return next_task;
+ *tid = common->pid_visiting = next_tid;
+ get_task_struct(task);
+ return task;
}
static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common,
@@ -308,11 +290,9 @@ again:
rcu_read_lock();
for (;; curr_fd++) {
struct file *f;
- f = task_lookup_next_fd_rcu(curr_task, &curr_fd);
+ f = task_lookup_next_fdget_rcu(curr_task, &curr_fd);
if (!f)
break;
- if (!get_file_rcu(f))
- continue;
/* set info->fd */
info->fd = curr_fd;
@@ -724,7 +704,7 @@ static struct bpf_iter_reg task_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &task_seq_info,
.fill_link_info = bpf_iter_fill_link_info,
@@ -823,6 +803,244 @@ const struct bpf_func_proto bpf_find_vma_proto = {
.arg5_type = ARG_ANYTHING,
};
+struct bpf_iter_task_vma_kern_data {
+ struct task_struct *task;
+ struct mm_struct *mm;
+ struct mmap_unlock_irq_work *work;
+ struct vma_iterator vmi;
+};
+
+struct bpf_iter_task_vma {
+ /* opaque iterator state; having __u64 here allows to preserve correct
+ * alignment requirements in vmlinux.h, generated from BTF
+ */
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+/* Non-opaque version of bpf_iter_task_vma */
+struct bpf_iter_task_vma_kern {
+ struct bpf_iter_task_vma_kern_data *data;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
+ struct task_struct *task, u64 addr)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+ bool irq_work_busy = false;
+ int err;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma));
+
+ /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized
+ * before, so non-NULL kit->data doesn't point to previously
+ * bpf_mem_alloc'd bpf_iter_task_vma_kern_data
+ */
+ kit->data = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_iter_task_vma_kern_data));
+ if (!kit->data)
+ return -ENOMEM;
+
+ kit->data->task = get_task_struct(task);
+ kit->data->mm = task->mm;
+ if (!kit->data->mm) {
+ err = -ENOENT;
+ goto err_cleanup_iter;
+ }
+
+ /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */
+ irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work);
+ if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) {
+ err = -EBUSY;
+ goto err_cleanup_iter;
+ }
+
+ vma_iter_init(&kit->data->vmi, kit->data->mm, addr);
+ return 0;
+
+err_cleanup_iter:
+ if (kit->data->task)
+ put_task_struct(kit->data->task);
+ bpf_mem_free(&bpf_global_ma, kit->data);
+ /* NULL kit->data signals failed bpf_iter_task_vma initialization */
+ kit->data = NULL;
+ return err;
+}
+
+__bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+
+ if (!kit->data) /* bpf_iter_task_vma_new failed */
+ return NULL;
+ return vma_next(&kit->data->vmi);
+}
+
+__bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+
+ if (kit->data) {
+ bpf_mmap_unlock_mm(kit->data->work, kit->data->mm);
+ put_task_struct(kit->data->task);
+ bpf_mem_free(&bpf_global_ma, kit->data);
+ }
+}
+
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
+
+struct bpf_iter_css_task {
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_task_kern {
+ struct css_task_iter *css_it;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+ struct cgroup_subsys_state *css, unsigned int flags)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) !=
+ __alignof__(struct bpf_iter_css_task));
+ kit->css_it = NULL;
+ switch (flags) {
+ case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED:
+ case CSS_TASK_ITER_PROCS:
+ case 0:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter));
+ if (!kit->css_it)
+ return -ENOMEM;
+ css_task_iter_start(css, flags, kit->css_it);
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ if (!kit->css_it)
+ return NULL;
+ return css_task_iter_next(kit->css_it);
+}
+
+__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ if (!kit->css_it)
+ return;
+ css_task_iter_end(kit->css_it);
+ bpf_mem_free(&bpf_global_ma, kit->css_it);
+}
+
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
+
+struct bpf_iter_task {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_task_kern {
+ struct task_struct *task;
+ struct task_struct *pos;
+ unsigned int flags;
+} __attribute__((aligned(8)));
+
+enum {
+ /* all process in the system */
+ BPF_TASK_ITER_ALL_PROCS,
+ /* all threads in the system */
+ BPF_TASK_ITER_ALL_THREADS,
+ /* all threads of a specific process */
+ BPF_TASK_ITER_PROC_THREADS
+};
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
+ struct task_struct *task__nullable, unsigned int flags)
+{
+ struct bpf_iter_task_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
+ __alignof__(struct bpf_iter_task));
+
+ kit->task = kit->pos = NULL;
+ switch (flags) {
+ case BPF_TASK_ITER_ALL_THREADS:
+ case BPF_TASK_ITER_ALL_PROCS:
+ break;
+ case BPF_TASK_ITER_PROC_THREADS:
+ if (!task__nullable)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (flags == BPF_TASK_ITER_PROC_THREADS)
+ kit->task = task__nullable;
+ else
+ kit->task = &init_task;
+ kit->pos = kit->task;
+ kit->flags = flags;
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it)
+{
+ struct bpf_iter_task_kern *kit = (void *)it;
+ struct task_struct *pos;
+ unsigned int flags;
+
+ flags = kit->flags;
+ pos = kit->pos;
+
+ if (!pos)
+ return pos;
+
+ if (flags == BPF_TASK_ITER_ALL_PROCS)
+ goto get_next_task;
+
+ kit->pos = next_thread(kit->pos);
+ if (kit->pos == kit->task) {
+ if (flags == BPF_TASK_ITER_PROC_THREADS) {
+ kit->pos = NULL;
+ return pos;
+ }
+ } else
+ return pos;
+
+get_next_task:
+ kit->pos = next_task(kit->pos);
+ kit->task = kit->pos;
+ if (kit->pos == &init_task)
+ kit->pos = NULL;
+
+ return pos;
+}
+
+__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
+{
+}
+
+__bpf_kfunc_end_defs();
+
DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
static void do_mmap_read_unlock(struct irq_work *entry)
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
new file mode 100644
index 000000000000..2e4885e7781f
--- /dev/null
+++ b/kernel/bpf/tcx.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mprog.h>
+#include <linux/netdevice.h>
+
+#include <net/tcx.h>
+
+int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ bool created, ingress = attr->attach_type == BPF_TCX_INGRESS;
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct bpf_prog *replace_prog = NULL;
+ struct net_device *dev;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ if (attr->attach_flags & BPF_F_REPLACE) {
+ replace_prog = bpf_prog_get_type(attr->replace_bpf_fd,
+ prog->type);
+ if (IS_ERR(replace_prog)) {
+ ret = PTR_ERR(replace_prog);
+ replace_prog = NULL;
+ goto out;
+ }
+ }
+ entry = tcx_entry_fetch_or_create(dev, ingress, &created);
+ if (!entry) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog,
+ attr->attach_flags, attr->relative_fd,
+ attr->expected_revision);
+ if (!ret) {
+ if (entry != entry_new) {
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_inc(ingress);
+ }
+ bpf_mprog_commit(entry);
+ } else if (created) {
+ tcx_entry_free(entry);
+ }
+out:
+ if (replace_prog)
+ bpf_prog_put(replace_prog);
+ rtnl_unlock();
+ return ret;
+}
+
+int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ bool ingress = attr->attach_type == BPF_TCX_INGRESS;
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags,
+ attr->relative_fd, attr->expected_revision);
+ if (!ret) {
+ if (!tcx_entry_is_active(entry_new))
+ entry_new = NULL;
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_dec(ingress);
+ bpf_mprog_commit(entry);
+ if (!entry_new)
+ tcx_entry_free(entry);
+ }
+out:
+ rtnl_unlock();
+ return ret;
+}
+
+void tcx_uninstall(struct net_device *dev, bool ingress)
+{
+ struct bpf_mprog_entry *entry, *entry_new = NULL;
+ struct bpf_tuple tuple = {};
+ struct bpf_mprog_fp *fp;
+ struct bpf_mprog_cp *cp;
+ bool active;
+
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry)
+ return;
+ active = tcx_entry(entry)->miniq_active;
+ if (active)
+ bpf_mprog_clear_all(entry, &entry_new);
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ bpf_mprog_foreach_tuple(entry, fp, cp, tuple) {
+ if (tuple.link)
+ tcx_link(tuple.link)->dev = NULL;
+ else
+ bpf_prog_put(tuple.prog);
+ tcx_skeys_dec(ingress);
+ }
+ if (!active)
+ tcx_entry_free(entry);
+}
+
+int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+ bool ingress = attr->query.attach_type == BPF_TCX_INGRESS;
+ struct net *net = current->nsproxy->net_ns;
+ struct net_device *dev;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->query.target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ ret = bpf_mprog_query(attr, uattr, tcx_entry_fetch(dev, ingress));
+out:
+ rtnl_unlock();
+ return ret;
+}
+
+static int tcx_link_prog_attach(struct bpf_link *link, u32 flags, u32 id_or_fd,
+ u64 revision)
+{
+ struct tcx_link *tcx = tcx_link(link);
+ bool created, ingress = tcx->location == BPF_TCX_INGRESS;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev = tcx->dev;
+ int ret;
+
+ ASSERT_RTNL();
+ entry = tcx_entry_fetch_or_create(dev, ingress, &created);
+ if (!entry)
+ return -ENOMEM;
+ ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags,
+ id_or_fd, revision);
+ if (!ret) {
+ if (entry != entry_new) {
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_inc(ingress);
+ }
+ bpf_mprog_commit(entry);
+ } else if (created) {
+ tcx_entry_free(entry);
+ }
+ return ret;
+}
+
+static void tcx_link_release(struct bpf_link *link)
+{
+ struct tcx_link *tcx = tcx_link(link);
+ bool ingress = tcx->location == BPF_TCX_INGRESS;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev;
+ int ret = 0;
+
+ rtnl_lock();
+ dev = tcx->dev;
+ if (!dev)
+ goto out;
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0);
+ if (!ret) {
+ if (!tcx_entry_is_active(entry_new))
+ entry_new = NULL;
+ tcx_entry_update(dev, entry_new, ingress);
+ tcx_entry_sync();
+ tcx_skeys_dec(ingress);
+ bpf_mprog_commit(entry);
+ if (!entry_new)
+ tcx_entry_free(entry);
+ tcx->dev = NULL;
+ }
+out:
+ WARN_ON_ONCE(ret);
+ rtnl_unlock();
+}
+
+static int tcx_link_update(struct bpf_link *link, struct bpf_prog *nprog,
+ struct bpf_prog *oprog)
+{
+ struct tcx_link *tcx = tcx_link(link);
+ bool ingress = tcx->location == BPF_TCX_INGRESS;
+ struct bpf_mprog_entry *entry, *entry_new;
+ struct net_device *dev;
+ int ret = 0;
+
+ rtnl_lock();
+ dev = tcx->dev;
+ if (!dev) {
+ ret = -ENOLINK;
+ goto out;
+ }
+ if (oprog && link->prog != oprog) {
+ ret = -EPERM;
+ goto out;
+ }
+ oprog = link->prog;
+ if (oprog == nprog) {
+ bpf_prog_put(nprog);
+ goto out;
+ }
+ entry = tcx_entry_fetch(dev, ingress);
+ if (!entry) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog,
+ BPF_F_REPLACE | BPF_F_ID,
+ link->prog->aux->id, 0);
+ if (!ret) {
+ WARN_ON_ONCE(entry != entry_new);
+ oprog = xchg(&link->prog, nprog);
+ bpf_prog_put(oprog);
+ bpf_mprog_commit(entry);
+ }
+out:
+ rtnl_unlock();
+ return ret;
+}
+
+static void tcx_link_dealloc(struct bpf_link *link)
+{
+ kfree(tcx_link(link));
+}
+
+static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
+{
+ const struct tcx_link *tcx = tcx_link(link);
+ u32 ifindex = 0;
+
+ rtnl_lock();
+ if (tcx->dev)
+ ifindex = tcx->dev->ifindex;
+ rtnl_unlock();
+
+ seq_printf(seq, "ifindex:\t%u\n", ifindex);
+ seq_printf(seq, "attach_type:\t%u (%s)\n",
+ tcx->location,
+ tcx->location == BPF_TCX_INGRESS ? "ingress" : "egress");
+}
+
+static int tcx_link_fill_info(const struct bpf_link *link,
+ struct bpf_link_info *info)
+{
+ const struct tcx_link *tcx = tcx_link(link);
+ u32 ifindex = 0;
+
+ rtnl_lock();
+ if (tcx->dev)
+ ifindex = tcx->dev->ifindex;
+ rtnl_unlock();
+
+ info->tcx.ifindex = ifindex;
+ info->tcx.attach_type = tcx->location;
+ return 0;
+}
+
+static int tcx_link_detach(struct bpf_link *link)
+{
+ tcx_link_release(link);
+ return 0;
+}
+
+static const struct bpf_link_ops tcx_link_lops = {
+ .release = tcx_link_release,
+ .detach = tcx_link_detach,
+ .dealloc = tcx_link_dealloc,
+ .update_prog = tcx_link_update,
+ .show_fdinfo = tcx_link_fdinfo,
+ .fill_link_info = tcx_link_fill_info,
+};
+
+static int tcx_link_init(struct tcx_link *tcx,
+ struct bpf_link_primer *link_primer,
+ const union bpf_attr *attr,
+ struct net_device *dev,
+ struct bpf_prog *prog)
+{
+ bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog);
+ tcx->location = attr->link_create.attach_type;
+ tcx->dev = dev;
+ return bpf_link_prime(&tcx->link, link_primer);
+}
+
+int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ struct net *net = current->nsproxy->net_ns;
+ struct bpf_link_primer link_primer;
+ struct net_device *dev;
+ struct tcx_link *tcx;
+ int ret;
+
+ rtnl_lock();
+ dev = __dev_get_by_index(net, attr->link_create.target_ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ tcx = kzalloc(sizeof(*tcx), GFP_USER);
+ if (!tcx) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = tcx_link_init(tcx, &link_primer, attr, dev, prog);
+ if (ret) {
+ kfree(tcx);
+ goto out;
+ }
+ ret = tcx_link_prog_attach(&tcx->link, attr->link_create.flags,
+ attr->link_create.tcx.relative_fd,
+ attr->link_create.tcx.expected_revision);
+ if (ret) {
+ tcx->dev = NULL;
+ bpf_link_cleanup(&link_primer);
+ goto out;
+ }
+ ret = bpf_link_settle(&link_primer);
+out:
+ rtnl_unlock();
+ return ret;
+}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 78acf28d4873..e97aeda3a86b 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -415,8 +415,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
goto out;
}
- /* clear all bits except SHARE_IPMODIFY */
- tr->flags &= BPF_TRAMP_F_SHARE_IPMODIFY;
+ /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
+ tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) {
@@ -926,13 +926,12 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
migrate_disable();
might_fault();
+ run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
bpf_prog_inc_misses_counter(prog);
return 0;
}
-
- run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
-
return bpf_prog_start_time();
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 02a021c524ab..af2819d5c8ee 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25,6 +25,9 @@
#include <linux/btf_ids.h>
#include <linux/poison.h>
#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
+#include <net/xdp.h>
#include "disasm.h"
@@ -39,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#undef BPF_LINK_TYPE
};
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -302,7 +308,7 @@ struct bpf_kfunc_call_arg_meta {
/* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling,
* generally to pass info about user-defined local kptr types to later
* verification logic
- * bpf_obj_drop
+ * bpf_obj_drop/bpf_percpu_obj_drop
* Record the local kptr type to be drop'd
* bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type)
* Record the local kptr type to be refcount_incr'd and use
@@ -334,6 +340,7 @@ struct bpf_kfunc_call_arg_meta {
struct btf *btf_vmlinux;
static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
static const struct bpf_line_info *
find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
@@ -540,12 +547,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
return func_id == BPF_FUNC_dynptr_data;
}
-static bool is_callback_calling_kfunc(u32 btf_id);
+static bool is_sync_callback_calling_kfunc(u32 btf_id);
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
-static bool is_callback_calling_function(enum bpf_func_id func_id)
+static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_for_each_map_elem ||
- func_id == BPF_FUNC_timer_set_callback ||
func_id == BPF_FUNC_find_vma ||
func_id == BPF_FUNC_loop ||
func_id == BPF_FUNC_user_ringbuf_drain;
@@ -556,6 +563,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id)
return func_id == BPF_FUNC_timer_set_callback;
}
+static bool is_callback_calling_function(enum bpf_func_id func_id)
+{
+ return is_sync_callback_calling_function(func_id) ||
+ is_async_callback_calling_function(func_id);
+}
+
+static bool is_sync_callback_calling_insn(struct bpf_insn *insn)
+{
+ return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) ||
+ (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm));
+}
+
static bool is_storage_get_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_storage_get ||
@@ -1170,7 +1189,12 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg
static void __mark_reg_known_zero(struct bpf_reg_state *reg);
+static bool in_rcu_cs(struct bpf_verifier_env *env);
+
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta);
+
static int mark_stack_slots_iter(struct bpf_verifier_env *env,
+ struct bpf_kfunc_call_arg_meta *meta,
struct bpf_reg_state *reg, int insn_idx,
struct btf *btf, u32 btf_id, int nr_slots)
{
@@ -1191,6 +1215,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env,
__mark_reg_known_zero(st);
st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
+ if (is_kfunc_rcu_protected(meta)) {
+ if (in_rcu_cs(env))
+ st->type |= MEM_RCU;
+ else
+ st->type |= PTR_UNTRUSTED;
+ }
st->live |= REG_LIVE_WRITTEN;
st->ref_obj_id = i == 0 ? id : 0;
st->iter.btf = btf;
@@ -1265,7 +1295,7 @@ static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env,
return true;
}
-static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
struct btf *btf, u32 btf_id, int nr_slots)
{
struct bpf_func_state *state = func(env, reg);
@@ -1273,26 +1303,28 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_
spi = iter_get_spi(env, reg, nr_slots);
if (spi < 0)
- return false;
+ return -EINVAL;
for (i = 0; i < nr_slots; i++) {
struct bpf_stack_state *slot = &state->stack[spi - i];
struct bpf_reg_state *st = &slot->spilled_ptr;
+ if (st->type & PTR_UNTRUSTED)
+ return -EPROTO;
/* only main (first) slot has ref_obj_id set */
if (i == 0 && !st->ref_obj_id)
- return false;
+ return -EINVAL;
if (i != 0 && st->ref_obj_id)
- return false;
+ return -EINVAL;
if (st->iter.btf != btf || st->iter.btf_id != btf_id)
- return false;
+ return -EINVAL;
for (j = 0; j < BPF_REG_SIZE; j++)
if (slot->slot_type[j] != STACK_ITER)
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
}
/* Check if given stack slot is "special":
@@ -1339,6 +1371,50 @@ static void scrub_spilled_slot(u8 *stype)
*stype = STACK_MISC;
}
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ const char **sep)
+{
+ struct {
+ const char *name;
+ u64 val;
+ bool omit;
+ } minmaxs[] = {
+ {"smin", reg->smin_value, reg->smin_value == S64_MIN},
+ {"smax", reg->smax_value, reg->smax_value == S64_MAX},
+ {"umin", reg->umin_value, reg->umin_value == 0},
+ {"umax", reg->umax_value, reg->umax_value == U64_MAX},
+ {"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+ {"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
+ {"umin32", reg->u32_min_value, reg->u32_min_value == 0},
+ {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX},
+ }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
+ bool neg1, neg2;
+
+ for (m1 = &minmaxs[0]; m1 < mend; m1++) {
+ if (m1->omit)
+ continue;
+
+ neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
+
+ verbose(env, "%s%s=", *sep, m1->name);
+ *sep = ",";
+
+ for (m2 = m1 + 2; m2 < mend; m2 += 2) {
+ if (m2->omit || m2->val != m1->val)
+ continue;
+ /* don't mix negatives with positives */
+ neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
+ if (neg2 != neg1)
+ continue;
+ m2->omit = true;
+ verbose(env, "%s=", m2->name);
+ }
+
+ verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
+ }
+}
+
static void print_verifier_state(struct bpf_verifier_env *env,
const struct bpf_func_state *state,
bool print_all)
@@ -1402,34 +1478,13 @@ static void print_verifier_state(struct bpf_verifier_env *env,
*/
verbose_a("imm=%llx", reg->var_off.value);
} else {
- if (reg->smin_value != reg->umin_value &&
- reg->smin_value != S64_MIN)
- verbose_a("smin=%lld", (long long)reg->smin_value);
- if (reg->smax_value != reg->umax_value &&
- reg->smax_value != S64_MAX)
- verbose_a("smax=%lld", (long long)reg->smax_value);
- if (reg->umin_value != 0)
- verbose_a("umin=%llu", (unsigned long long)reg->umin_value);
- if (reg->umax_value != U64_MAX)
- verbose_a("umax=%llu", (unsigned long long)reg->umax_value);
+ print_scalar_ranges(env, reg, &sep);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose_a("var_off=%s", tn_buf);
}
- if (reg->s32_min_value != reg->smin_value &&
- reg->s32_min_value != S32_MIN)
- verbose_a("s32_min=%d", (int)(reg->s32_min_value));
- if (reg->s32_max_value != reg->smax_value &&
- reg->s32_max_value != S32_MAX)
- verbose_a("s32_max=%d", (int)(reg->s32_max_value));
- if (reg->u32_min_value != reg->umin_value &&
- reg->u32_min_value != U32_MIN)
- verbose_a("u32_min=%d", (int)(reg->u32_min_value));
- if (reg->u32_max_value != reg->umax_value &&
- reg->u32_max_value != U32_MAX)
- verbose_a("u32_max=%d", (int)(reg->u32_max_value));
}
#undef verbose_a
@@ -1513,7 +1568,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (state->in_async_callback_fn)
verbose(env, " async_cb");
verbose(env, "\n");
- mark_verifier_state_clean(env);
+ if (!print_all)
+ mark_verifier_state_clean(env);
}
static inline u32 vlog_alignment(u32 pos)
@@ -1746,7 +1802,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
return -ENOMEM;
dst_state->jmp_history_cnt = src->jmp_history_cnt;
- /* if dst has more stack frames then src frame, free them */
+ /* if dst has more stack frames then src frame, free them, this is also
+ * necessary in case of exceptional exits using bpf_throw.
+ */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
@@ -1760,6 +1818,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
dst_state->parent = src->parent;
dst_state->first_insn_idx = src->first_insn_idx;
dst_state->last_insn_idx = src->last_insn_idx;
+ dst_state->dfs_depth = src->dfs_depth;
+ dst_state->callback_unroll_depth = src->callback_unroll_depth;
+ dst_state->used_as_loop_entry = src->used_as_loop_entry;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
@@ -1775,11 +1836,203 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
return 0;
}
+static u32 state_htab_size(struct bpf_verifier_env *env)
+{
+ return env->prog->len;
+}
+
+static struct bpf_verifier_state_list **explored_state(struct bpf_verifier_env *env, int idx)
+{
+ struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_func_state *state = cur->frame[cur->curframe];
+
+ return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
+}
+
+static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b)
+{
+ int fr;
+
+ if (a->curframe != b->curframe)
+ return false;
+
+ for (fr = a->curframe; fr >= 0; fr--)
+ if (a->frame[fr]->callsite != b->frame[fr]->callsite)
+ return false;
+
+ return true;
+}
+
+/* Open coded iterators allow back-edges in the state graph in order to
+ * check unbounded loops that iterators.
+ *
+ * In is_state_visited() it is necessary to know if explored states are
+ * part of some loops in order to decide whether non-exact states
+ * comparison could be used:
+ * - non-exact states comparison establishes sub-state relation and uses
+ * read and precision marks to do so, these marks are propagated from
+ * children states and thus are not guaranteed to be final in a loop;
+ * - exact states comparison just checks if current and explored states
+ * are identical (and thus form a back-edge).
+ *
+ * Paper "A New Algorithm for Identifying Loops in Decompilation"
+ * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient
+ * algorithm for loop structure detection and gives an overview of
+ * relevant terminology. It also has helpful illustrations.
+ *
+ * [1] https://api.semanticscholar.org/CorpusID:15784067
+ *
+ * We use a similar algorithm but because loop nested structure is
+ * irrelevant for verifier ours is significantly simpler and resembles
+ * strongly connected components algorithm from Sedgewick's textbook.
+ *
+ * Define topmost loop entry as a first node of the loop traversed in a
+ * depth first search starting from initial state. The goal of the loop
+ * tracking algorithm is to associate topmost loop entries with states
+ * derived from these entries.
+ *
+ * For each step in the DFS states traversal algorithm needs to identify
+ * the following situations:
+ *
+ * initial initial initial
+ * | | |
+ * V V V
+ * ... ... .---------> hdr
+ * | | | |
+ * V V | V
+ * cur .-> succ | .------...
+ * | | | | | |
+ * V | V | V V
+ * succ '-- cur | ... ...
+ * | | |
+ * | V V
+ * | succ <- cur
+ * | |
+ * | V
+ * | ...
+ * | |
+ * '----'
+ *
+ * (A) successor state of cur (B) successor state of cur or it's entry
+ * not yet traversed are in current DFS path, thus cur and succ
+ * are members of the same outermost loop
+ *
+ * initial initial
+ * | |
+ * V V
+ * ... ...
+ * | |
+ * V V
+ * .------... .------...
+ * | | | |
+ * V V V V
+ * .-> hdr ... ... ...
+ * | | | | |
+ * | V V V V
+ * | succ <- cur succ <- cur
+ * | | |
+ * | V V
+ * | ... ...
+ * | | |
+ * '----' exit
+ *
+ * (C) successor state of cur is a part of some loop but this loop
+ * does not include cur or successor state is not in a loop at all.
+ *
+ * Algorithm could be described as the following python code:
+ *
+ * traversed = set() # Set of traversed nodes
+ * entries = {} # Mapping from node to loop entry
+ * depths = {} # Depth level assigned to graph node
+ * path = set() # Current DFS path
+ *
+ * # Find outermost loop entry known for n
+ * def get_loop_entry(n):
+ * h = entries.get(n, None)
+ * while h in entries and entries[h] != h:
+ * h = entries[h]
+ * return h
+ *
+ * # Update n's loop entry if h's outermost entry comes
+ * # before n's outermost entry in current DFS path.
+ * def update_loop_entry(n, h):
+ * n1 = get_loop_entry(n) or n
+ * h1 = get_loop_entry(h) or h
+ * if h1 in path and depths[h1] <= depths[n1]:
+ * entries[n] = h1
+ *
+ * def dfs(n, depth):
+ * traversed.add(n)
+ * path.add(n)
+ * depths[n] = depth
+ * for succ in G.successors(n):
+ * if succ not in traversed:
+ * # Case A: explore succ and update cur's loop entry
+ * # only if succ's entry is in current DFS path.
+ * dfs(succ, depth + 1)
+ * h = get_loop_entry(succ)
+ * update_loop_entry(n, h)
+ * else:
+ * # Case B or C depending on `h1 in path` check in update_loop_entry().
+ * update_loop_entry(n, succ)
+ * path.remove(n)
+ *
+ * To adapt this algorithm for use with verifier:
+ * - use st->branch == 0 as a signal that DFS of succ had been finished
+ * and cur's loop entry has to be updated (case A), handle this in
+ * update_branch_counts();
+ * - use st->branch > 0 as a signal that st is in the current DFS path;
+ * - handle cases B and C in is_state_visited();
+ * - update topmost loop entry for intermediate states in get_loop_entry().
+ */
+static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_state *st)
+{
+ struct bpf_verifier_state *topmost = st->loop_entry, *old;
+
+ while (topmost && topmost->loop_entry && topmost != topmost->loop_entry)
+ topmost = topmost->loop_entry;
+ /* Update loop entries for intermediate states to avoid this
+ * traversal in future get_loop_entry() calls.
+ */
+ while (st && st->loop_entry != topmost) {
+ old = st->loop_entry;
+ st->loop_entry = topmost;
+ st = old;
+ }
+ return topmost;
+}
+
+static void update_loop_entry(struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr)
+{
+ struct bpf_verifier_state *cur1, *hdr1;
+
+ cur1 = get_loop_entry(cur) ?: cur;
+ hdr1 = get_loop_entry(hdr) ?: hdr;
+ /* The head1->branches check decides between cases B and C in
+ * comment for get_loop_entry(). If hdr1->branches == 0 then
+ * head's topmost loop entry is not in current DFS path,
+ * hence 'cur' and 'hdr' are not in the same loop and there is
+ * no need to update cur->loop_entry.
+ */
+ if (hdr1->branches && hdr1->dfs_depth <= cur1->dfs_depth) {
+ cur->loop_entry = hdr;
+ hdr->used_as_loop_entry = true;
+ }
+}
+
static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
{
while (st) {
u32 br = --st->branches;
+ /* br == 0 signals that DFS exploration for 'st' is finished,
+ * thus it is necessary to update parent's loop entry if it
+ * turned out that st is a part of some loop.
+ * This is a part of 'case A' in get_loop_entry() comment.
+ */
+ if (br == 0 && st->parent && st->loop_entry)
+ update_loop_entry(st->parent, st->loop_entry);
+
/* WARN_ON(br > 1) technically makes sense here,
* but see comment in push_stack(), hence:
*/
@@ -2452,6 +2705,68 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
return env->subprog_cnt - 1;
}
+static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env)
+{
+ struct bpf_prog_aux *aux = env->prog->aux;
+ struct btf *btf = aux->btf;
+ const struct btf_type *t;
+ u32 main_btf_id, id;
+ const char *name;
+ int ret, i;
+
+ /* Non-zero func_info_cnt implies valid btf */
+ if (!aux->func_info_cnt)
+ return 0;
+ main_btf_id = aux->func_info[0].type_id;
+
+ t = btf_type_by_id(btf, main_btf_id);
+ if (!t) {
+ verbose(env, "invalid btf id for main subprog in func_info\n");
+ return -EINVAL;
+ }
+
+ name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:");
+ if (IS_ERR(name)) {
+ ret = PTR_ERR(name);
+ /* If there is no tag present, there is no exception callback */
+ if (ret == -ENOENT)
+ ret = 0;
+ else if (ret == -EEXIST)
+ verbose(env, "multiple exception callback tags for main subprog\n");
+ return ret;
+ }
+
+ ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC);
+ if (ret < 0) {
+ verbose(env, "exception callback '%s' could not be found in BTF\n", name);
+ return ret;
+ }
+ id = ret;
+ t = btf_type_by_id(btf, id);
+ if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+ verbose(env, "exception callback '%s' must have global linkage\n", name);
+ return -EINVAL;
+ }
+ ret = 0;
+ for (i = 0; i < aux->func_info_cnt; i++) {
+ if (aux->func_info[i].type_id != id)
+ continue;
+ ret = aux->func_info[i].insn_off;
+ /* Further func_info and subprog checks will also happen
+ * later, so assume this is the right insn_off for now.
+ */
+ if (!ret) {
+ verbose(env, "invalid exception callback insn_off in func_info: 0\n");
+ ret = -EINVAL;
+ }
+ }
+ if (!ret) {
+ verbose(env, "exception callback type id not found in func_info\n");
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
#define MAX_KFUNC_DESCS 256
#define MAX_KFUNC_BTFS 256
@@ -2791,8 +3106,8 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
{
struct bpf_subprog_info *subprog = env->subprog_info;
+ int i, ret, insn_cnt = env->prog->len, ex_cb_insn;
struct bpf_insn *insn = env->prog->insnsi;
- int i, ret, insn_cnt = env->prog->len;
/* Add entry function. */
ret = add_subprog(env, 0);
@@ -2818,6 +3133,26 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
return ret;
}
+ ret = bpf_find_exception_callback_insn_off(env);
+ if (ret < 0)
+ return ret;
+ ex_cb_insn = ret;
+
+ /* If ex_cb_insn > 0, this means that the main program has a subprog
+ * marked using BTF decl tag to serve as the exception callback.
+ */
+ if (ex_cb_insn) {
+ ret = add_subprog(env, ex_cb_insn);
+ if (ret < 0)
+ return ret;
+ for (i = 1; i < env->subprog_cnt; i++) {
+ if (env->subprog_info[i].start != ex_cb_insn)
+ continue;
+ env->exception_callback_subprog = i;
+ break;
+ }
+ }
+
/* Add a fake 'exit' subprog which could simplify subprog iteration
* logic. 'subprog_cnt' should not be increased.
*/
@@ -2854,7 +3189,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
- off = i + insn[i].off + 1;
+ if (code == (BPF_JMP32 | BPF_JA))
+ off = i + insn[i].imm + 1;
+ else
+ off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
@@ -2863,9 +3201,10 @@ next:
if (i == subprog_end - 1) {
/* to avoid fall-through from one subprog into another
* the last insn of the subprog should be either exit
- * or unconditional jump back
+ * or unconditional jump back or bpf_throw call
*/
if (code != (BPF_JMP | BPF_EXIT) &&
+ code != (BPF_JMP32 | BPF_JA) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
@@ -3011,8 +3350,10 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
+ if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32))
+ return false;
+
if (class == BPF_ALU64 || class == BPF_JMP ||
- /* BPF_END always use BPF_ALU class. */
(class == BPF_ALU && op == BPF_END && insn->imm == 64))
return true;
@@ -3021,7 +3362,7 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (class == BPF_LDX) {
if (t != SRC_OP)
- return BPF_SIZE(code) == BPF_DW;
+ return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX;
/* LDX source must be ptr. */
return true;
}
@@ -3110,13 +3451,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env,
reg->subreg_def = DEF_NOT_SUBREG;
}
-static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
- enum reg_arg_type t)
+static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno,
+ enum reg_arg_type t)
{
- struct bpf_verifier_state *vstate = env->cur_state;
- struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
- struct bpf_reg_state *reg, *regs = state->regs;
+ struct bpf_reg_state *reg;
bool rw64;
if (regno >= MAX_BPF_REG) {
@@ -3157,6 +3496,15 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
return 0;
}
+static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
+ enum reg_arg_type t)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+
+ return __check_reg_arg(env, state->regs, regno, t);
+}
+
static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
{
env->insn_aux_data[idx].jmp_point = true;
@@ -3192,12 +3540,29 @@ static int push_jmp_history(struct bpf_verifier_env *env,
/* Backtrack one insn at a time. If idx is not at the top of recorded
* history then previous instruction came from straight line execution.
+ * Return -ENOENT if we exhausted all instructions within given state.
+ *
+ * It's legal to have a bit of a looping with the same starting and ending
+ * insn index within the same state, e.g.: 3->4->5->3, so just because current
+ * instruction index is the same as state's first_idx doesn't mean we are
+ * done. If there is still some jump history left, we should keep going. We
+ * need to take into account that we might have a jump history between given
+ * state's parent and itself, due to checkpointing. In this case, we'll have
+ * history entry recording a jump from last instruction of parent state and
+ * first instruction of given state.
*/
static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
u32 *history)
{
u32 cnt = *history;
+ if (i == st->first_insn_idx) {
+ if (cnt == 0)
+ return -ENOENT;
+ if (cnt == 1 && st->jmp_history[0].idx == i)
+ return -ENOENT;
+ }
+
if (cnt && st->jmp_history[cnt - 1].idx == i) {
i = st->jmp_history[cnt - 1].prev_idx;
(*history)--;
@@ -3378,6 +3743,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
}
}
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
+
/* For given verifier state backtrack_insn() is called from the last insn to
* the first insn. Its purpose is to compute a bitmask of registers and
* stack slots that needs precision in the parent verifier state.
@@ -3418,9 +3785,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
if (class == BPF_ALU || class == BPF_ALU64) {
if (!bt_is_reg_set(bt, dreg))
return 0;
- if (opcode == BPF_MOV) {
+ if (opcode == BPF_END || opcode == BPF_NEG) {
+ /* sreg is reserved and unused
+ * dreg still need precision before this insn
+ */
+ return 0;
+ } else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- /* dreg = sreg
+ /* dreg = sreg or dreg = (s8, s16, s32)sreg
* dreg needs precision after this insn
* sreg needs precision before this insn
*/
@@ -3548,16 +3920,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
return -EFAULT;
return 0;
}
- } else if ((bpf_helper_call(insn) &&
- is_callback_calling_function(insn->imm) &&
- !is_async_callback_calling_function(insn->imm)) ||
- (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
- /* callback-calling helper or kfunc call, which means
- * we are exiting from subprog, but unlike the subprog
- * call handling above, we shouldn't propagate
- * precision of r1-r5 (if any requested), as they are
- * not actually arguments passed directly to callback
- * subprogs
+ } else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) {
+ /* exit from callback subprog to callback-calling helper or
+ * kfunc call. Use idx/subseq_idx check to discern it from
+ * straight line code backtracking.
+ * Unlike the subprog call handling above, we shouldn't
+ * propagate precision of r1-r5 (if any requested), as they are
+ * not actually arguments passed directly to callback subprogs
*/
if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
@@ -3592,10 +3961,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
} else if (opcode == BPF_EXIT) {
bool r0_precise;
+ /* Backtracking to a nested function call, 'idx' is a part of
+ * the inner frame 'subseq_idx' is a part of the outer frame.
+ * In case of a regular function call, instructions giving
+ * precision to registers R1-R5 should have been found already.
+ * In case of a callback, it is ok to have R1-R5 marked for
+ * backtracking, as these registers are set by the function
+ * invoking callback.
+ */
+ if (subseq_idx >= 0 && calls_callback(env, subseq_idx))
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+ bt_clear_reg(bt, i);
if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
- /* if backtracing was looking for registers R1-R5
- * they should have been found already.
- */
verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
@@ -4039,11 +4416,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bitmap_from_u64(mask, bt_reg_mask(bt));
for_each_set_bit(i, mask, 32) {
reg = &st->frame[0]->regs[i];
- if (reg->type != SCALAR_VALUE) {
- bt_clear_reg(bt, i);
- continue;
- }
- reg->precise = true;
+ bt_clear_reg(bt, i);
+ if (reg->type == SCALAR_VALUE)
+ reg->precise = true;
}
return 0;
}
@@ -4074,10 +4449,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
* Nothing to be tracked further in the parent state.
*/
return 0;
- if (i == first_idx)
- break;
subseq_idx = i;
i = get_prev_insn_idx(st, i, &history);
+ if (i == -ENOENT)
+ break;
if (i >= env->prog->len) {
/* This can happen if backtracking reached insn 0
* and there are still reg_mask or stack_mask
@@ -4352,7 +4727,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
insn->imm != 0 && env->bpf_capable) {
struct bpf_reg_state fake_reg = {};
- __mark_reg_known(&fake_reg, (u32)insn->imm);
+ __mark_reg_known(&fake_reg, insn->imm);
fake_reg.type = SCALAR_VALUE;
save_register_state(state, spi, &fake_reg, size);
} else if (reg && is_spillable_regtype(reg->type)) {
@@ -4982,20 +5357,24 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
struct bpf_reg_state *reg, u32 regno)
{
const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id);
- int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+ int perm_flags;
const char *reg_name = "";
- /* Only unreferenced case accepts untrusted pointers */
- if (kptr_field->type == BPF_KPTR_UNREF)
- perm_flags |= PTR_UNTRUSTED;
+ if (btf_is_kernel(reg->btf)) {
+ perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+
+ /* Only unreferenced case accepts untrusted pointers */
+ if (kptr_field->type == BPF_KPTR_UNREF)
+ perm_flags |= PTR_UNTRUSTED;
+ } else {
+ perm_flags = PTR_MAYBE_NULL | MEM_ALLOC;
+ if (kptr_field->type == BPF_KPTR_PERCPU)
+ perm_flags |= MEM_PERCPU;
+ }
if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
goto bad_type;
- if (!btf_is_kernel(reg->btf)) {
- verbose(env, "R%d must point to kernel BTF\n", regno);
- return -EINVAL;
- }
/* We need to verify reg->type and reg->btf, before accessing reg->btf */
reg_name = btf_type_name(reg->btf, reg->btf_id);
@@ -5008,7 +5387,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
if (__check_ptr_off_reg(env, reg, regno, true))
return -EACCES;
- /* A full type match is needed, as BTF can be vmlinux or module BTF, and
+ /* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and
* we also need to take into account the reg->off.
*
* We want to support cases like:
@@ -5034,7 +5413,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
*/
if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
kptr_field->kptr.btf, kptr_field->kptr.btf_id,
- kptr_field->type == BPF_KPTR_REF))
+ kptr_field->type != BPF_KPTR_UNREF))
goto bad_type;
return 0;
bad_type:
@@ -5054,13 +5433,17 @@ bad_type:
*/
static bool in_rcu_cs(struct bpf_verifier_env *env)
{
- return env->cur_state->active_rcu_lock || !env->prog->aux->sleepable;
+ return env->cur_state->active_rcu_lock ||
+ env->cur_state->active_lock.ptr ||
+ !env->prog->aux->sleepable;
}
/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
BTF_SET_START(rcu_protected_types)
BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
+#endif
BTF_ID(struct, bpf_cpumask)
BTF_ID(struct, task_struct)
BTF_SET_END(rcu_protected_types)
@@ -5076,7 +5459,18 @@ static bool rcu_safe_kptr(const struct btf_field *field)
{
const struct btf_field_kptr *kptr = &field->kptr;
- return field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id);
+ return field->type == BPF_KPTR_PERCPU ||
+ (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id));
+}
+
+static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
+{
+ if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) {
+ if (kptr_field->type != BPF_KPTR_PERCPU)
+ return PTR_MAYBE_NULL | MEM_RCU;
+ return PTR_MAYBE_NULL | MEM_RCU | MEM_PERCPU;
+ }
+ return PTR_MAYBE_NULL | PTR_UNTRUSTED;
}
static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
@@ -5102,7 +5496,8 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
/* We only allow loading referenced kptr, since it will be marked as
* untrusted, similar to unreferenced kptr.
*/
- if (class != BPF_LDX && kptr_field->type == BPF_KPTR_REF) {
+ if (class != BPF_LDX &&
+ (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) {
verbose(env, "store to referenced kptr disallowed\n");
return -EACCES;
}
@@ -5113,10 +5508,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
* value from map as PTR_TO_BTF_ID, with the correct type.
*/
mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf,
- kptr_field->kptr.btf_id,
- rcu_safe_kptr(kptr_field) && in_rcu_cs(env) ?
- PTR_MAYBE_NULL | MEM_RCU :
- PTR_MAYBE_NULL | PTR_UNTRUSTED);
+ kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field));
/* For mark_ptr_or_null_reg */
val_reg->id = ++env->id_gen;
} else if (class == BPF_STX) {
@@ -5170,6 +5562,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
switch (field->type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
if (src != ACCESS_DIRECT) {
verbose(env, "kptr cannot be accessed indirectly by helper\n");
return -EACCES;
@@ -5412,12 +5805,25 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
return reg->type == PTR_TO_FLOW_KEYS;
}
+static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
+#ifdef CONFIG_NET
+ [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+ [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+#endif
+ [CONST_PTR_TO_MAP] = btf_bpf_map_id,
+};
+
static bool is_trusted_reg(const struct bpf_reg_state *reg)
{
/* A referenced register is always trusted. */
if (reg->ref_obj_id)
return true;
+ /* Types listed in the reg2btf_ids are always trusted */
+ if (reg2btf_ids[base_type(reg->type)])
+ return true;
+
/* If a register is not referenced, it is trusted if it has the
* MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the
* other type modifiers may be safe, but we elect to take an opt-in
@@ -5624,6 +6030,27 @@ continue_func:
for (; i < subprog_end; i++) {
int next_insn, sidx;
+ if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) {
+ bool err = false;
+
+ if (!is_bpf_throw_kfunc(insn + i))
+ continue;
+ if (subprog[idx].is_cb)
+ err = true;
+ for (int c = 0; c < frame && !err; c++) {
+ if (subprog[ret_prog[c]].is_cb) {
+ err = true;
+ break;
+ }
+ }
+ if (!err)
+ continue;
+ verbose(env,
+ "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n",
+ i, idx);
+ return -EINVAL;
+ }
+
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
/* remember insn and function to return to */
@@ -5646,6 +6073,10 @@ continue_func:
/* async callbacks don't increase bpf prog stack size unless called directly */
if (!bpf_pseudo_call(insn + i))
continue;
+ if (subprog[sidx].is_exception_cb) {
+ verbose(env, "insn %d cannot call exception cb directly\n", i);
+ return -EINVAL;
+ }
}
i = next_insn;
idx = sidx;
@@ -5667,8 +6098,13 @@ continue_func:
* tail call counter throughout bpf2bpf calls combined with tailcalls
*/
if (tail_call_reachable)
- for (j = 0; j < frame; j++)
+ for (j = 0; j < frame; j++) {
+ if (subprog[ret_prog[j]].is_exception_cb) {
+ verbose(env, "cannot tail call within exception cb\n");
+ return -EINVAL;
+ }
subprog[ret_prog[j]].tail_call_reachable = true;
+ }
if (subprog[0].tail_call_reachable)
env->prog->aux->tail_call_reachable = true;
@@ -5813,6 +6249,147 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
__reg_combine_64_into_32(reg);
}
+static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->smin_value = reg->s32_min_value = S8_MIN;
+ reg->smax_value = reg->s32_max_value = S8_MAX;
+ } else if (size == 2) {
+ reg->smin_value = reg->s32_min_value = S16_MIN;
+ reg->smax_value = reg->s32_max_value = S16_MAX;
+ } else {
+ /* size == 4 */
+ reg->smin_value = reg->s32_min_value = S32_MIN;
+ reg->smax_value = reg->s32_max_value = S32_MAX;
+ }
+ reg->umin_value = reg->u32_min_value = 0;
+ reg->umax_value = U64_MAX;
+ reg->u32_max_value = U32_MAX;
+ reg->var_off = tnum_unknown;
+}
+
+static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval;
+ u64 top_smax_value, top_smin_value;
+ u64 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u64_cval = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u64_cval);
+ else if (size == 2)
+ reg->var_off = tnum_const((s16)u64_cval);
+ else
+ /* size == 4 */
+ reg->var_off = tnum_const((s32)u64_cval);
+
+ u64_cval = reg->var_off.value;
+ reg->smax_value = reg->smin_value = u64_cval;
+ reg->umax_value = reg->umin_value = u64_cval;
+ reg->s32_max_value = reg->s32_min_value = u64_cval;
+ reg->u32_max_value = reg->u32_min_value = u64_cval;
+ return;
+ }
+
+ top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits;
+ top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s64_min and s64_min after sign extension */
+ if (size == 1) {
+ init_s64_max = (s8)reg->smax_value;
+ init_s64_min = (s8)reg->smin_value;
+ } else if (size == 2) {
+ init_s64_max = (s16)reg->smax_value;
+ init_s64_min = (s16)reg->smin_value;
+ } else {
+ init_s64_max = (s32)reg->smax_value;
+ init_s64_min = (s32)reg->smin_value;
+ }
+
+ s64_max = max(init_s64_max, init_s64_min);
+ s64_min = min(init_s64_max, init_s64_min);
+
+ /* both of s64_max/s64_min positive or negative */
+ if ((s64_max >= 0) == (s64_min >= 0)) {
+ reg->smin_value = reg->s32_min_value = s64_min;
+ reg->smax_value = reg->s32_max_value = s64_max;
+ reg->umin_value = reg->u32_min_value = s64_min;
+ reg->umax_value = reg->u32_max_value = s64_max;
+ reg->var_off = tnum_range(s64_min, s64_max);
+ return;
+ }
+
+out:
+ set_sext64_default_val(reg, size);
+}
+
+static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->s32_min_value = S8_MIN;
+ reg->s32_max_value = S8_MAX;
+ } else {
+ /* size == 2 */
+ reg->s32_min_value = S16_MIN;
+ reg->s32_max_value = S16_MAX;
+ }
+ reg->u32_min_value = 0;
+ reg->u32_max_value = U32_MAX;
+}
+
+static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val;
+ u32 top_smax_value, top_smin_value;
+ u32 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u32_val = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u32_val);
+ else
+ reg->var_off = tnum_const((s16)u32_val);
+
+ u32_val = reg->var_off.value;
+ reg->s32_min_value = reg->s32_max_value = u32_val;
+ reg->u32_min_value = reg->u32_max_value = u32_val;
+ return;
+ }
+
+ top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits;
+ top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s32_min and s32_min after sign extension */
+ if (size == 1) {
+ init_s32_max = (s8)reg->s32_max_value;
+ init_s32_min = (s8)reg->s32_min_value;
+ } else {
+ /* size == 2 */
+ init_s32_max = (s16)reg->s32_max_value;
+ init_s32_min = (s16)reg->s32_min_value;
+ }
+ s32_max = max(init_s32_max, init_s32_min);
+ s32_min = min(init_s32_max, init_s32_min);
+
+ if ((s32_min >= 0) == (s32_max >= 0)) {
+ reg->s32_min_value = s32_min;
+ reg->s32_max_value = s32_max;
+ reg->u32_min_value = (u32)s32_min;
+ reg->u32_max_value = (u32)s32_max;
+ return;
+ }
+
+out:
+ set_sext32_default_val(reg, size);
+}
+
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
/* A map is considered read-only if the following condition are true:
@@ -5833,7 +6410,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map)
!bpf_map_write_active(map);
}
-static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
+ bool is_ldsx)
{
void *ptr;
u64 addr;
@@ -5846,13 +6424,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
switch (size) {
case sizeof(u8):
- *val = (u64)*(u8 *)ptr;
+ *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr;
break;
case sizeof(u16):
- *val = (u64)*(u16 *)ptr;
+ *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr;
break;
case sizeof(u32):
- *val = (u64)*(u32 *)ptr;
+ *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr;
break;
case sizeof(u64):
*val = *(u64 *)ptr;
@@ -6042,7 +6620,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
}
if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) &&
- !reg->ref_obj_id) {
+ !(reg->type & MEM_RCU) && !reg->ref_obj_id) {
verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n");
return -EFAULT;
}
@@ -6085,6 +6663,11 @@ 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 {
@@ -6266,7 +6849,7 @@ static int check_stack_access_within_bounds(
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
int off, int bpf_size, enum bpf_access_type t,
- int value_regno, bool strict_alignment_once)
+ int value_regno, bool strict_alignment_once, bool is_ldsx)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
@@ -6327,7 +6910,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
u64 val = 0;
err = bpf_map_direct_read(map, map_off, size,
- &val);
+ &val, is_ldsx);
if (err)
return err;
@@ -6497,8 +7080,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
- /* b/h/w load zero-extends, mark upper bits as known 0 */
- coerce_reg_to_size(&regs[value_regno], size);
+ if (!is_ldsx)
+ /* b/h/w load zero-extends, mark upper bits as known 0 */
+ coerce_reg_to_size(&regs[value_regno], size);
+ else
+ coerce_reg_to_size_sx(&regs[value_regno], size);
}
return err;
}
@@ -6590,17 +7176,17 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
* case to simulate the register fill.
*/
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_READ, -1, true);
+ BPF_SIZE(insn->code), BPF_READ, -1, true, false);
if (!err && load_reg >= 0)
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, load_reg,
- true);
+ true, false);
if (err)
return err;
/* Check whether we can write into the same memory. */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+ BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
if (err)
return err;
@@ -6846,7 +7432,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return zero_size_allowed ? 0 : -EACCES;
return check_mem_access(env, env->insn_idx, regno, offset, BPF_B,
- atype, -1, false);
+ atype, -1, false, false);
}
fallthrough;
@@ -7145,7 +7731,7 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno,
verbose(env, "off=%d doesn't point to kptr\n", kptr_off);
return -EACCES;
}
- if (kptr_field->type != BPF_KPTR_REF) {
+ if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) {
verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off);
return -EACCES;
}
@@ -7218,7 +7804,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
/* we write BPF_DW bits (8 bytes) at a time */
for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -7311,20 +7897,29 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
- err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots);
+ err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots);
if (err)
return err;
} else {
/* iter_next() or iter_destroy() expect initialized iter state*/
- if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) {
+ err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots);
+ switch (err) {
+ case 0:
+ break;
+ case -EINVAL:
verbose(env, "expected an initialized iter_%s as arg #%d\n",
iter_type_str(meta->btf, btf_id), regno);
- return -EINVAL;
+ return err;
+ case -EPROTO:
+ verbose(env, "expected an RCU CS when using %s\n", meta->func_name);
+ return err;
+ default:
+ return err;
}
spi = iter_get_spi(env, reg, nr_slots);
@@ -7350,6 +7945,81 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
return 0;
}
+/* Look for a previous loop entry at insn_idx: nearest parent state
+ * stopped at insn_idx with callsites matching those in cur->frame.
+ */
+static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *cur,
+ int insn_idx)
+{
+ struct bpf_verifier_state_list *sl;
+ struct bpf_verifier_state *st;
+
+ /* Explored states are pushed in stack order, most recent states come first */
+ sl = *explored_state(env, insn_idx);
+ for (; sl; sl = sl->next) {
+ /* If st->branches != 0 state is a part of current DFS verification path,
+ * hence cur & st for a loop.
+ */
+ st = &sl->state;
+ if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) &&
+ st->dfs_depth < cur->dfs_depth)
+ return st;
+ }
+
+ return NULL;
+}
+
+static void reset_idmap_scratch(struct bpf_verifier_env *env);
+static bool regs_exact(const struct bpf_reg_state *rold,
+ const struct bpf_reg_state *rcur,
+ struct bpf_idmap *idmap);
+
+static void maybe_widen_reg(struct bpf_verifier_env *env,
+ struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
+ struct bpf_idmap *idmap)
+{
+ if (rold->type != SCALAR_VALUE)
+ return;
+ if (rold->type != rcur->type)
+ return;
+ if (rold->precise || rcur->precise || regs_exact(rold, rcur, idmap))
+ return;
+ __mark_reg_unknown(env, rcur);
+}
+
+static int widen_imprecise_scalars(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur)
+{
+ struct bpf_func_state *fold, *fcur;
+ int i, fr;
+
+ reset_idmap_scratch(env);
+ for (fr = old->curframe; fr >= 0; fr--) {
+ fold = old->frame[fr];
+ fcur = cur->frame[fr];
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ maybe_widen_reg(env,
+ &fold->regs[i],
+ &fcur->regs[i],
+ &env->idmap_scratch);
+
+ for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) {
+ if (!is_spilled_reg(&fold->stack[i]) ||
+ !is_spilled_reg(&fcur->stack[i]))
+ continue;
+
+ maybe_widen_reg(env,
+ &fold->stack[i].spilled_ptr,
+ &fcur->stack[i].spilled_ptr,
+ &env->idmap_scratch);
+ }
+ }
+ return 0;
+}
+
/* process_iter_next_call() is called when verifier gets to iterator's next
* "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer
* to it as just "iter_next()" in comments below.
@@ -7391,25 +8061,47 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
* is some statically known limit on number of iterations (e.g., if there is
* an explicit `if n > 100 then break;` statement somewhere in the loop).
*
- * One very subtle but very important aspect is that we *always* simulate NULL
- * condition first (as the current state) before we simulate non-NULL case.
- * This has to do with intricacies of scalar precision tracking. By simulating
- * "exit condition" of iter_next() returning NULL first, we make sure all the
- * relevant precision marks *that will be set **after** we exit iterator loop*
- * are propagated backwards to common parent state of NULL and non-NULL
- * branches. Thanks to that, state equivalence checks done later in forked
- * state, when reaching iter_next() for ACTIVE iterator, can assume that
- * precision marks are finalized and won't change. Because simulating another
- * ACTIVE iterator iteration won't change them (because given same input
- * states we'll end up with exactly same output states which we are currently
- * comparing; and verification after the loop already propagated back what
- * needs to be **additionally** tracked as precise). It's subtle, grok
- * precision tracking for more intuitive understanding.
+ * Iteration convergence logic in is_state_visited() relies on exact
+ * states comparison, which ignores read and precision marks.
+ * This is necessary because read and precision marks are not finalized
+ * while in the loop. Exact comparison might preclude convergence for
+ * simple programs like below:
+ *
+ * i = 0;
+ * while(iter_next(&it))
+ * i++;
+ *
+ * At each iteration step i++ would produce a new distinct state and
+ * eventually instruction processing limit would be reached.
+ *
+ * To avoid such behavior speculatively forget (widen) range for
+ * imprecise scalar registers, if those registers were not precise at the
+ * end of the previous iteration and do not match exactly.
+ *
+ * This is a conservative heuristic that allows to verify wide range of programs,
+ * however it precludes verification of programs that conjure an
+ * imprecise value on the first loop iteration and use it as precise on a second.
+ * For example, the following safe program would fail to verify:
+ *
+ * struct bpf_num_iter it;
+ * int arr[10];
+ * int i = 0, a = 0;
+ * bpf_iter_num_new(&it, 0, 10);
+ * while (bpf_iter_num_next(&it)) {
+ * if (a == 0) {
+ * a = 1;
+ * i = 7; // Because i changed verifier would forget
+ * // it's range on second loop entry.
+ * } else {
+ * arr[i] = 42; // This would fail to verify.
+ * }
+ * }
+ * bpf_iter_num_destroy(&it);
*/
static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
struct bpf_kfunc_call_arg_meta *meta)
{
- struct bpf_verifier_state *cur_st = env->cur_state, *queued_st;
+ struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st;
struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr;
struct bpf_reg_state *cur_iter, *queued_iter;
int iter_frameno = meta->iter.frameno;
@@ -7427,6 +8119,19 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
}
if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) {
+ /* Because iter_next() call is a checkpoint is_state_visitied()
+ * should guarantee parent state with same call sites and insn_idx.
+ */
+ if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx ||
+ !same_callsites(cur_st->parent, cur_st)) {
+ verbose(env, "bug: bad parent state for iter next call");
+ return -EFAULT;
+ }
+ /* Note cur_st->parent in the call below, it is necessary to skip
+ * checkpoint created for cur_st by is_state_visited()
+ * right at this instruction.
+ */
+ prev_st = find_prev_entry(env, cur_st->parent, insn_idx);
/* branch out active iter state */
queued_st = push_stack(env, insn_idx + 1, insn_idx, false);
if (!queued_st)
@@ -7435,6 +8140,8 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
queued_iter = &queued_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr;
queued_iter->iter.state = BPF_ITER_STATE_ACTIVE;
queued_iter->iter.depth++;
+ if (prev_st)
+ widen_imprecise_scalars(env, prev_st, queued_st);
queued_fr = queued_st->frame[queued_st->curframe];
mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]);
@@ -7578,6 +8285,7 @@ static const struct bpf_reg_types btf_ptr_types = {
static const struct bpf_reg_types percpu_btf_ptr_types = {
.types = {
PTR_TO_BTF_ID | MEM_PERCPU,
+ PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU,
PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED,
}
};
@@ -7656,8 +8364,10 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
if (base_type(arg_type) == ARG_PTR_TO_MEM)
type &= ~DYNPTR_TYPE_FLAG_MASK;
- if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type))
+ if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type)) {
type &= ~MEM_ALLOC;
+ type &= ~MEM_PERCPU;
+ }
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
expected = compatible->types[i];
@@ -7740,14 +8450,19 @@ found:
break;
}
case PTR_TO_BTF_ID | MEM_ALLOC:
+ case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC:
if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock &&
meta->func_id != BPF_FUNC_kptr_xchg) {
verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n");
return -EFAULT;
}
- /* Handled by helper specific checks */
+ if (meta->func_id == BPF_FUNC_kptr_xchg) {
+ if (map_kptr_match_type(env, meta->kptr_field, reg, regno))
+ return -EACCES;
+ }
break;
case PTR_TO_BTF_ID | MEM_PERCPU:
+ case PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU:
case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED:
/* Handled by helper specific checks */
break;
@@ -7797,17 +8512,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK)
return 0;
- if ((type_is_ptr_alloc_obj(type) || type_is_non_owning_ref(type)) && reg->off) {
- if (reg_find_field_offset(reg, reg->off, BPF_GRAPH_NODE_OR_ROOT))
- return __check_ptr_off_reg(env, reg, regno, true);
-
- verbose(env, "R%d must have zero offset when passed to release func\n",
- regno);
- verbose(env, "No graph node or root found at R%d type:%s off:%d\n", regno,
- btf_type_name(reg->btf, reg->btf_id), reg->off);
- return -EINVAL;
- }
-
/* Doing check_ptr_off_reg check for the offset will catch this
* because fixed_off_ok is false, but checking here allows us
* to give the user a better error message.
@@ -7842,6 +8546,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
case PTR_TO_BTF_ID | PTR_TRUSTED:
case PTR_TO_BTF_ID | MEM_RCU:
case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF:
+ case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU:
/* When referenced PTR_TO_BTF_ID is passed to release function,
* its fixed offset must be 0. In the other cases, fixed offset
* can be non-zero. This was already checked above. So pass
@@ -8671,7 +9376,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env,
/* after the call registers r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
- check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK);
}
}
@@ -8684,11 +9389,10 @@ static int set_callee_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee, int insn_idx);
-static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
- int *insn_idx, int subprog,
- set_callee_state_fn set_callee_state_cb)
+static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite,
+ set_callee_state_fn set_callee_state_cb,
+ struct bpf_verifier_state *state)
{
- struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
int err;
@@ -8698,53 +9402,72 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -E2BIG;
}
- caller = state->frame[state->curframe];
if (state->frame[state->curframe + 1]) {
verbose(env, "verifier bug. Frame %d already allocated\n",
state->curframe + 1);
return -EFAULT;
}
+ caller = state->frame[state->curframe];
+ callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+ if (!callee)
+ return -ENOMEM;
+ state->frame[state->curframe + 1] = callee;
+
+ /* callee cannot access r0, r6 - r9 for reading and has to write
+ * into its own stack before reading from it.
+ * callee can read/write into caller's stack
+ */
+ init_func_state(env, callee,
+ /* remember the callsite, it will be used by bpf_exit */
+ callsite,
+ state->curframe + 1 /* frameno within this callchain */,
+ subprog /* subprog number within this prog */);
+ /* Transfer references to the callee */
+ err = copy_reference_state(callee, caller);
+ err = err ?: set_callee_state_cb(env, caller, callee, callsite);
+ if (err)
+ goto err_out;
+
+ /* only increment it after check_reg_arg() finished */
+ state->curframe++;
+
+ return 0;
+
+err_out:
+ free_func_state(callee);
+ state->frame[state->curframe + 1] = NULL;
+ return err;
+}
+
+static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ int insn_idx, int subprog,
+ set_callee_state_fn set_callee_state_cb)
+{
+ struct bpf_verifier_state *state = env->cur_state, *callback_state;
+ struct bpf_func_state *caller, *callee;
+ int err;
+
+ caller = state->frame[state->curframe];
err = btf_check_subprog_call(env, subprog, caller->regs);
if (err == -EFAULT)
return err;
- if (subprog_is_global(env, subprog)) {
- if (err) {
- verbose(env, "Caller passes invalid args into func#%d\n",
- subprog);
- return err;
- } else {
- if (env->log.level & BPF_LOG_LEVEL)
- verbose(env,
- "Func#%d is global and valid. Skipping.\n",
- subprog);
- clear_caller_saved_regs(env, caller->regs);
-
- /* All global functions return a 64-bit SCALAR_VALUE */
- mark_reg_unknown(env, caller->regs, BPF_REG_0);
- caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
-
- /* continue with next insn after call */
- return 0;
- }
- }
/* set_callee_state is used for direct subprog calls, but we are
* interested in validating only BPF helpers that can call subprogs as
* callbacks
*/
- if (set_callee_state_cb != set_callee_state) {
- if (bpf_pseudo_kfunc_call(insn) &&
- !is_callback_calling_kfunc(insn->imm)) {
- verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
- func_id_name(insn->imm), insn->imm);
- return -EFAULT;
- } else if (!bpf_pseudo_kfunc_call(insn) &&
- !is_callback_calling_function(insn->imm)) { /* helper */
- verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
- func_id_name(insn->imm), insn->imm);
- return -EFAULT;
- }
+ env->subprog_info[subprog].is_cb = true;
+ if (bpf_pseudo_kfunc_call(insn) &&
+ !is_sync_callback_calling_kfunc(insn->imm)) {
+ verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
+ func_id_name(insn->imm), insn->imm);
+ return -EFAULT;
+ } else if (!bpf_pseudo_kfunc_call(insn) &&
+ !is_callback_calling_function(insn->imm)) { /* helper */
+ verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
+ func_id_name(insn->imm), insn->imm);
+ return -EFAULT;
}
if (insn->code == (BPF_JMP | BPF_CALL) &&
@@ -8755,53 +9478,83 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
/* there is no real recursion here. timer callbacks are async */
env->subprog_info[subprog].is_async_cb = true;
async_cb = push_async_cb(env, env->subprog_info[subprog].start,
- *insn_idx, subprog);
+ insn_idx, subprog);
if (!async_cb)
return -EFAULT;
callee = async_cb->frame[0];
callee->async_entry_cnt = caller->async_entry_cnt + 1;
/* Convert bpf_timer_set_callback() args into timer callback args */
- err = set_callee_state_cb(env, caller, callee, *insn_idx);
+ err = set_callee_state_cb(env, caller, callee, insn_idx);
if (err)
return err;
+ return 0;
+ }
+
+ /* for callback functions enqueue entry to callback and
+ * proceed with next instruction within current frame.
+ */
+ callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false);
+ if (!callback_state)
+ return -ENOMEM;
+
+ err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb,
+ callback_state);
+ if (err)
+ return err;
+
+ callback_state->callback_unroll_depth++;
+ callback_state->frame[callback_state->curframe - 1]->callback_depth++;
+ caller->callback_depth = 0;
+ return 0;
+}
+
+static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ int *insn_idx)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_state *caller;
+ int err, subprog, target_insn;
+
+ target_insn = *insn_idx + insn->imm + 1;
+ subprog = find_subprog(env, target_insn);
+ if (subprog < 0) {
+ verbose(env, "verifier bug. No program starts at insn %d\n", target_insn);
+ return -EFAULT;
+ }
+
+ caller = state->frame[state->curframe];
+ err = btf_check_subprog_call(env, subprog, caller->regs);
+ if (err == -EFAULT)
+ return err;
+ if (subprog_is_global(env, subprog)) {
+ if (err) {
+ verbose(env, "Caller passes invalid args into func#%d\n", subprog);
+ return err;
+ }
+
+ if (env->log.level & BPF_LOG_LEVEL)
+ verbose(env, "Func#%d is global and valid. Skipping.\n", subprog);
clear_caller_saved_regs(env, caller->regs);
+
+ /* All global functions return a 64-bit SCALAR_VALUE */
mark_reg_unknown(env, caller->regs, BPF_REG_0);
caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
/* continue with next insn after call */
return 0;
}
- callee = kzalloc(sizeof(*callee), GFP_KERNEL);
- if (!callee)
- return -ENOMEM;
- state->frame[state->curframe + 1] = callee;
-
- /* callee cannot access r0, r6 - r9 for reading and has to write
- * into its own stack before reading from it.
- * callee can read/write into caller's stack
+ /* for regular function entry setup new frame and continue
+ * from that frame.
*/
- init_func_state(env, callee,
- /* remember the callsite, it will be used by bpf_exit */
- *insn_idx /* callsite */,
- state->curframe + 1 /* frameno within this callchain */,
- subprog /* subprog number within this prog */);
-
- /* Transfer references to the callee */
- err = copy_reference_state(callee, caller);
+ err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
if (err)
- goto err_out;
-
- err = set_callee_state_cb(env, caller, callee, *insn_idx);
- if (err)
- goto err_out;
+ return err;
clear_caller_saved_regs(env, caller->regs);
- /* only increment it after check_reg_arg() finished */
- state->curframe++;
-
/* and go analyze first insn of the callee */
*insn_idx = env->subprog_info[subprog].start - 1;
@@ -8809,14 +9562,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
verbose(env, "caller:\n");
print_verifier_state(env, caller, true);
verbose(env, "callee:\n");
- print_verifier_state(env, callee, true);
+ print_verifier_state(env, state->frame[state->curframe], true);
}
- return 0;
-err_out:
- free_func_state(callee);
- state->frame[state->curframe + 1] = NULL;
- return err;
+ return 0;
}
int map_set_for_each_callback_args(struct bpf_verifier_env *env,
@@ -8860,22 +9609,6 @@ static int set_callee_state(struct bpf_verifier_env *env,
return 0;
}
-static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
- int *insn_idx)
-{
- int subprog, target_insn;
-
- target_insn = *insn_idx + insn->imm + 1;
- subprog = find_subprog(env, target_insn);
- if (subprog < 0) {
- verbose(env, "verifier bug. No program starts at insn %d\n",
- target_insn);
- return -EFAULT;
- }
-
- return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
-}
-
static int set_map_elem_callback_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee,
@@ -9068,9 +9801,10 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
- struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_verifier_state *state = env->cur_state, *prev_st;
struct bpf_func_state *caller, *callee;
struct bpf_reg_state *r0;
+ bool in_callback_fn;
int err;
callee = state->frame[state->curframe];
@@ -9099,6 +9833,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
return -EINVAL;
}
+ if (!calls_callback(env, callee->callsite)) {
+ verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n",
+ *insn_idx, callee->callsite);
+ return -EFAULT;
+ }
} else {
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
@@ -9116,16 +9855,44 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
return err;
}
- *insn_idx = callee->callsite + 1;
+ /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite,
+ * there function call logic would reschedule callback visit. If iteration
+ * converges is_state_visited() would prune that visit eventually.
+ */
+ in_callback_fn = callee->in_callback_fn;
+ if (in_callback_fn)
+ *insn_idx = callee->callsite;
+ else
+ *insn_idx = callee->callsite + 1;
+
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee, true);
verbose(env, "to caller at %d:\n", *insn_idx);
print_verifier_state(env, caller, true);
}
- /* clear everything in the callee */
+ /* clear everything in the callee. In case of exceptional exits using
+ * bpf_throw, this will be done by copy_verifier_state for extra frames. */
free_func_state(callee);
state->frame[state->curframe--] = NULL;
+
+ /* for callbacks widen imprecise scalars to make programs like below verify:
+ *
+ * struct ctx { int i; }
+ * void cb(int idx, struct ctx *ctx) { ctx->i++; ... }
+ * ...
+ * struct ctx = { .i = 0; }
+ * bpf_loop(100, cb, &ctx, 0);
+ *
+ * This is similar to what is done in process_iter_next_call() for open
+ * coded iterators.
+ */
+ prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL;
+ if (prev_st) {
+ err = widen_imprecise_scalars(env, prev_st, state);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -9135,19 +9902,33 @@ 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
@@ -9233,17 +10014,17 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
}
-static int check_reference_leak(struct bpf_verifier_env *env)
+static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit)
{
struct bpf_func_state *state = cur_func(env);
bool refs_lingering = false;
int i;
- if (state->frameno && !state->in_callback_fn)
+ if (!exception_exit && state->frameno && !state->in_callback_fn)
return 0;
for (i = 0; i < state->acquired_refs; i++) {
- if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+ if (!exception_exit && state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
continue;
verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
state->refs[i].id, state->refs[i].insn_idx);
@@ -9350,6 +10131,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
int *insn_idx_p)
{
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+ bool returns_cpu_specific_alloc_ptr = false;
const struct bpf_func_proto *fn = NULL;
enum bpf_return_type ret_type;
enum bpf_type_flag ret_flag;
@@ -9441,7 +10223,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
*/
for (i = 0; i < meta.access_size; i++) {
err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -9460,6 +10242,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -EFAULT;
}
err = unmark_stack_slots_dynptr(env, &regs[meta.release_regno]);
+ } else if (func_id == BPF_FUNC_kptr_xchg && meta.ref_obj_id) {
+ u32 ref_obj_id = meta.ref_obj_id;
+ bool in_rcu = in_rcu_cs(env);
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+
+ err = release_reference_state(cur_func(env), ref_obj_id);
+ if (!err) {
+ bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ if (reg->ref_obj_id == ref_obj_id) {
+ if (in_rcu && (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) {
+ reg->ref_obj_id = 0;
+ reg->type &= ~MEM_ALLOC;
+ reg->type |= MEM_RCU;
+ } else {
+ mark_reg_invalid(env, reg);
+ }
+ }
+ }));
+ }
} else if (meta.ref_obj_id) {
err = release_reference(env, meta.ref_obj_id);
} else if (register_is_null(&regs[meta.release_regno])) {
@@ -9477,7 +10279,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
switch (func_id) {
case BPF_FUNC_tail_call:
- err = check_reference_leak(env);
+ err = check_reference_leak(env, false);
if (err) {
verbose(env, "tail_call would lead to reference leak\n");
return err;
@@ -9493,24 +10295,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
}
break;
case BPF_FUNC_for_each_map_elem:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_map_elem_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_map_elem_callback_state);
break;
case BPF_FUNC_timer_set_callback:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_timer_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_timer_callback_state);
break;
case BPF_FUNC_find_vma:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_find_vma_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_find_vma_callback_state);
break;
case BPF_FUNC_snprintf:
err = check_bpf_snprintf_call(env, regs);
break;
case BPF_FUNC_loop:
update_loop_inline_state(env, meta.subprogno);
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_loop_callback_state);
+ /* Verifier relies on R1 value to determine if bpf_loop() iteration
+ * is finished, thus mark it precise.
+ */
+ err = mark_chain_precision(env, BPF_REG_1);
+ if (err)
+ return err;
+ if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) {
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_loop_callback_state);
+ } else {
+ cur_func(env)->callback_depth = 0;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "frame%d bpf_loop iteration limit reached\n",
+ env->cur_state->curframe);
+ }
break;
case BPF_FUNC_dynptr_from_mem:
if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
@@ -9588,9 +10403,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
break;
}
+ case BPF_FUNC_per_cpu_ptr:
+ case BPF_FUNC_this_cpu_ptr:
+ {
+ struct bpf_reg_state *reg = &regs[BPF_REG_1];
+ const struct btf_type *type;
+
+ if (reg->type & MEM_RCU) {
+ type = btf_type_by_id(reg->btf, reg->btf_id);
+ if (!type || !btf_type_is_struct(type)) {
+ verbose(env, "Helper has invalid btf/btf_id in R1\n");
+ return -EFAULT;
+ }
+ returns_cpu_specific_alloc_ptr = true;
+ env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true;
+ }
+ break;
+ }
case BPF_FUNC_user_ringbuf_drain:
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_user_ringbuf_callback_state);
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_user_ringbuf_callback_state);
break;
}
@@ -9677,14 +10509,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = tsize;
} else {
- /* MEM_RDONLY may be carried from ret_flag, but it
- * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
- * it will confuse the check of PTR_TO_BTF_ID in
- * check_mem_access().
- */
- ret_flag &= ~MEM_RDONLY;
+ if (returns_cpu_specific_alloc_ptr) {
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU;
+ } else {
+ /* MEM_RDONLY may be carried from ret_flag, but it
+ * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+ * it will confuse the check of PTR_TO_BTF_ID in
+ * check_mem_access().
+ */
+ ret_flag &= ~MEM_RDONLY;
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
+ }
- regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
regs[BPF_REG_0].btf = meta.ret_btf;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
@@ -9700,8 +10536,11 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (func_id == BPF_FUNC_kptr_xchg) {
ret_btf = meta.kptr_field->kptr.btf;
ret_btf_id = meta.kptr_field->kptr.btf_id;
- if (!btf_is_kernel(ret_btf))
+ if (!btf_is_kernel(ret_btf)) {
regs[BPF_REG_0].type |= MEM_ALLOC;
+ if (meta.kptr_field->type == BPF_KPTR_PERCPU)
+ regs[BPF_REG_0].type |= MEM_PERCPU;
+ }
} else {
if (fn->ret_btf_id == BPF_PTR_POISON) {
verbose(env, "verifier internal error:");
@@ -9848,6 +10687,11 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta)
return meta->kfunc_flags & KF_RCU;
}
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta)
+{
+ return meta->kfunc_flags & KF_RCU_PROTECTED;
+}
+
static bool __kfunc_param_match_suffix(const struct btf *btf,
const struct btf_param *arg,
const char *suffix)
@@ -9922,6 +10766,11 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf
return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr");
}
+static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg)
+{
+ return __kfunc_param_match_suffix(btf, arg, "__nullable");
+}
+
static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
const struct btf_param *arg,
const char *name)
@@ -10050,15 +10899,6 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env,
return true;
}
-
-static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
-#ifdef CONFIG_NET
- [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
- [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
- [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
-#endif
-};
-
enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CTX,
KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */
@@ -10073,6 +10913,7 @@ enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CALLBACK,
KF_ARG_PTR_TO_RB_ROOT,
KF_ARG_PTR_TO_RB_NODE,
+ KF_ARG_PTR_TO_NULL,
};
enum special_kfunc_type {
@@ -10095,6 +10936,10 @@ enum special_kfunc_type {
KF_bpf_dynptr_slice,
KF_bpf_dynptr_slice_rdwr,
KF_bpf_dynptr_clone,
+ KF_bpf_percpu_obj_new_impl,
+ KF_bpf_percpu_obj_drop_impl,
+ KF_bpf_throw,
+ KF_bpf_iter_css_task_new,
};
BTF_SET_START(special_kfunc_set)
@@ -10115,6 +10960,12 @@ BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
+BTF_ID(func, bpf_percpu_obj_new_impl)
+BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
+BTF_ID(func, bpf_iter_css_task_new)
+#endif
BTF_SET_END(special_kfunc_set)
BTF_ID_LIST(special_kfunc_list)
@@ -10137,6 +10988,14 @@ BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
+BTF_ID(func, bpf_percpu_obj_new_impl)
+BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
+BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
{
@@ -10217,6 +11076,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
return KF_ARG_PTR_TO_CALLBACK;
+ if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
+ return KF_ARG_PTR_TO_NULL;
if (argno + 1 < nargs &&
(is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
@@ -10303,6 +11164,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
struct bpf_verifier_state *state = env->cur_state;
+ struct btf_record *rec = reg_btf_record(reg);
if (!state->active_lock.ptr) {
verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n");
@@ -10315,6 +11177,9 @@ static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state
}
reg->type |= NON_OWN_REF;
+ if (rec->refcount_off >= 0)
+ reg->type |= MEM_RCU;
+
return 0;
}
@@ -10445,11 +11310,17 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id)
btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
}
-static bool is_callback_calling_kfunc(u32 btf_id)
+static bool is_sync_callback_calling_kfunc(u32 btf_id)
{
return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
}
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn)
+{
+ return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
+ insn->imm == special_kfunc_list[KF_bpf_throw];
+}
+
static bool is_rbtree_lock_required_kfunc(u32 btf_id)
{
return is_bpf_rbtree_api_kfunc(btf_id);
@@ -10657,6 +11528,28 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
&meta->arg_rbtree_root.field);
}
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
+static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
+{
+ enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+
+ switch (prog_type) {
+ case BPF_PROG_TYPE_LSM:
+ return true;
+ case BPF_PROG_TYPE_TRACING:
+ if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+ return true;
+ fallthrough;
+ default:
+ return env->prog->aux->sleepable;
+ }
+}
+
static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta,
int insn_idx)
{
@@ -10743,7 +11636,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) &&
- (register_is_null(reg) || type_may_be_null(reg->type))) {
+ (register_is_null(reg) || type_may_be_null(reg->type)) &&
+ !is_kfunc_arg_nullable(meta->btf, &args[i])) {
verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i);
return -EACCES;
}
@@ -10768,6 +11662,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
return kf_arg_type;
switch (kf_arg_type) {
+ case KF_ARG_PTR_TO_NULL:
+ continue;
case KF_ARG_PTR_TO_ALLOC_BTF_ID:
case KF_ARG_PTR_TO_BTF_ID:
if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta))
@@ -10827,7 +11723,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
break;
case KF_ARG_PTR_TO_ALLOC_BTF_ID:
- if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (meta->func_id != special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ verbose(env, "arg#%d expected for bpf_obj_drop_impl()\n", i);
+ return -EINVAL;
+ }
+ } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) {
+ if (meta->func_id != special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
+ verbose(env, "arg#%d expected for bpf_percpu_obj_drop_impl()\n", i);
+ return -EINVAL;
+ }
+ } else {
verbose(env, "arg#%d expected pointer to allocated object\n", i);
return -EINVAL;
}
@@ -10835,8 +11741,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
verbose(env, "allocated object must be referenced\n");
return -EINVAL;
}
- if (meta->btf == btf_vmlinux &&
- meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ if (meta->btf == btf_vmlinux) {
meta->arg_btf = reg->btf;
meta->arg_btf_id = reg->btf_id;
}
@@ -10898,6 +11803,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
break;
}
case KF_ARG_PTR_TO_ITER:
+ if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
+ if (!check_css_task_iter_allowlist(env)) {
+ verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
+ return -EINVAL;
+ }
+ }
ret = process_iter_arg(env, regno, insn_idx, meta);
if (ret < 0)
return ret;
@@ -11027,6 +11938,10 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
break;
}
case KF_ARG_PTR_TO_CALLBACK:
+ if (reg->type != PTR_TO_FUNC) {
+ verbose(env, "arg%d expected pointer to func\n", i);
+ return -EINVAL;
+ }
meta->subprogno = reg->subprogno;
break;
case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
@@ -11047,10 +11962,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i);
return -EINVAL;
}
- if (rec->refcount_off >= 0) {
- verbose(env, "bpf_refcount_acquire calls are disabled for now\n");
- return -EINVAL;
- }
+
meta->arg_btf = reg->btf;
meta->arg_btf_id = reg->btf_id;
break;
@@ -11108,6 +12020,8 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
return 0;
}
+static int check_return_code(struct bpf_verifier_env *env, int regno);
+
static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
{
@@ -11148,18 +12062,39 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EACCES;
}
+ /* Check the arguments */
+ err = check_kfunc_args(env, &meta, insn_idx);
+ if (err < 0)
+ return err;
+
+ if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+ err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+ set_rbtree_add_callback_state);
+ if (err) {
+ verbose(env, "kfunc %s#%d failed callback verification\n",
+ func_name, meta.func_id);
+ return err;
+ }
+ }
+
rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);
if (env->cur_state->active_rcu_lock) {
struct bpf_func_state *state;
struct bpf_reg_state *reg;
+ u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER);
+
+ if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
+ verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
+ return -EACCES;
+ }
if (rcu_lock) {
verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
return -EINVAL;
} else if (rcu_unlock) {
- bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({
if (reg->type & MEM_RCU) {
reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL);
reg->type |= PTR_UNTRUSTED;
@@ -11177,10 +12112,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EINVAL;
}
- /* Check the arguments */
- err = check_kfunc_args(env, &meta, insn_idx);
- if (err < 0)
- return err;
/* In case of release function, we get register number of refcounted
* PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now.
*/
@@ -11214,13 +12145,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
- if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
- err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
- set_rbtree_add_callback_state);
- if (err) {
- verbose(env, "kfunc %s#%d failed callback verification\n",
+ if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
+ if (!bpf_jit_supports_exceptions()) {
+ verbose(env, "JIT does not support calling kfunc %s#%d\n",
func_name, meta.func_id);
- return err;
+ return -ENOTSUPP;
+ }
+ env->seen_exception = true;
+
+ /* In the case of the default callback, the cookie value passed
+ * to bpf_throw becomes the return value of the program.
+ */
+ if (!env->exception_callback_subprog) {
+ err = check_return_code(env, BPF_REG_1);
+ if (err < 0)
+ return err;
}
}
@@ -11234,6 +12173,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* Only exception is bpf_obj_new_impl */
if (meta.btf != btf_vmlinux ||
(meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl] &&
+ meta.func_id != special_kfunc_list[KF_bpf_percpu_obj_new_impl] &&
meta.func_id != special_kfunc_list[KF_bpf_refcount_acquire_impl])) {
verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
return -EINVAL;
@@ -11247,13 +12187,29 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id);
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
- if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+ meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ struct btf_struct_meta *struct_meta;
struct btf *ret_btf;
u32 ret_btf_id;
- if (unlikely(!bpf_global_ma_set))
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
return -ENOMEM;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!bpf_global_percpu_ma_set) {
+ mutex_lock(&bpf_percpu_ma_lock);
+ if (!bpf_global_percpu_ma_set) {
+ err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
+ if (!err)
+ bpf_global_percpu_ma_set = true;
+ }
+ mutex_unlock(&bpf_percpu_ma_lock);
+ if (err)
+ return err;
+ }
+ }
+
if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
return -EINVAL;
@@ -11264,24 +12220,38 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* This may be NULL due to user not supplying a BTF */
if (!ret_btf) {
- verbose(env, "bpf_obj_new requires prog BTF\n");
+ verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n");
return -EINVAL;
}
ret_t = btf_type_by_id(ret_btf, ret_btf_id);
if (!ret_t || !__btf_type_is_struct(ret_t)) {
- verbose(env, "bpf_obj_new type ID argument must be of a struct\n");
+ verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n");
return -EINVAL;
}
+ struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
+ verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n");
+ return -EINVAL;
+ }
+
+ if (struct_meta) {
+ verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n");
+ return -EINVAL;
+ }
+ }
+
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
regs[BPF_REG_0].btf = ret_btf;
regs[BPF_REG_0].btf_id = ret_btf_id;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl])
+ regs[BPF_REG_0].type |= MEM_PERCPU;
insn_aux->obj_new_size = ret_t->size;
- insn_aux->kptr_struct_meta =
- btf_find_struct_meta(ret_btf, ret_btf_id);
+ insn_aux->kptr_struct_meta = struct_meta;
} else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
@@ -11418,7 +12388,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
regs[BPF_REG_0].id = ++env->id_gen;
} else if (btf_type_is_void(t)) {
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
- if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
insn_aux->kptr_struct_meta =
btf_find_struct_meta(meta.arg_btf,
meta.arg_btf_id);
@@ -12907,7 +13878,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
- BPF_CLASS(insn->code) == BPF_ALU64) {
+ (BPF_CLASS(insn->code) == BPF_ALU64 &&
+ BPF_SRC(insn->code) != BPF_TO_LE)) {
verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
@@ -12932,11 +13904,24 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
+ if (BPF_CLASS(insn->code) == BPF_ALU) {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ } else {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
+ insn->off != 32) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
@@ -12960,18 +13945,42 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
!tnum_is_const(src_reg->var_off);
if (BPF_CLASS(insn->code) == BPF_ALU64) {
- /* case: R1 = R2
- * copy register state to dest reg
- */
- if (need_id)
- /* Assign src and dst registers the same ID
- * that will be used by find_equal_scalars()
- * to propagate min/max range.
+ if (insn->off == 0) {
+ /* case: R1 = R2
+ * copy register state to dest reg
*/
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = DEF_NOT_SUBREG;
+ if (need_id)
+ /* Assign src and dst registers the same ID
+ * that will be used by find_equal_scalars()
+ * to propagate min/max range.
+ */
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ /* case: R1 = (s8, s16 s32)R2 */
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose(env,
+ "R%d sign-extension part of pointer\n",
+ insn->src_reg);
+ return -EACCES;
+ } else if (src_reg->type == SCALAR_VALUE) {
+ bool no_sext;
+
+ no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ }
+ }
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
@@ -12980,19 +13989,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
-
- if (is_src_reg_u32 && need_id)
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- /* Make sure ID is cleared if src_reg is not in u32 range otherwise
- * dst_reg min/max could be incorrectly
- * propagated into src_reg by find_equal_scalars()
- */
- if (!is_src_reg_u32)
- dst_reg->id = 0;
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = env->insn_idx + 1;
+ if (insn->off == 0) {
+ bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
+
+ if (is_src_reg_u32 && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ /* Make sure ID is cleared if src_reg is not in u32
+ * range otherwise dst_reg min/max could be incorrectly
+ * propagated into src_reg by find_equal_scalars()
+ */
+ if (!is_src_reg_u32)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ } else {
+ /* case: W1 = (s8, s16)W2 */
+ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
+ }
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
@@ -13023,7 +14046,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -13032,7 +14056,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
} else {
- if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+ if (insn->src_reg != BPF_REG_0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -13160,12 +14185,16 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
return !!tnum_equals_const(subreg, val);
else if (val < reg->u32_min_value || val > reg->u32_max_value)
return 0;
+ else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
+ return 0;
break;
case BPF_JNE:
if (tnum_is_const(subreg))
return !tnum_equals_const(subreg, val);
else if (val < reg->u32_min_value || val > reg->u32_max_value)
return 1;
+ else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
+ return 1;
break;
case BPF_JSET:
if ((~subreg.mask & subreg.value) & val)
@@ -13237,12 +14266,16 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return !!tnum_equals_const(reg->var_off, val);
else if (val < reg->umin_value || val > reg->umax_value)
return 0;
+ else if (sval < reg->smin_value || sval > reg->smax_value)
+ return 0;
break;
case BPF_JNE:
if (tnum_is_const(reg->var_off))
return !tnum_equals_const(reg->var_off, val);
else if (val < reg->umin_value || val > reg->umax_value)
return 1;
+ else if (sval < reg->smin_value || sval > reg->smax_value)
+ return 1;
break;
case BPF_JSET:
if ((~reg->var_off.mask & reg->var_off.value) & val)
@@ -13817,6 +14850,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return -EINVAL;
}
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg = &regs[insn->dst_reg];
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -13828,12 +14867,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
if (err)
return err;
- if (is_pointer_value(env, insn->src_reg)) {
+ src_reg = &regs[insn->src_reg];
+ if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) &&
+ is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->src_reg);
return -EACCES;
}
- src_reg = &regs[insn->src_reg];
} else {
if (insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -13841,12 +14881,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
}
- /* check src2 operand */
- err = check_reg_arg(env, insn->dst_reg, SRC_OP);
- if (err)
- return err;
-
- dst_reg = &regs[insn->dst_reg];
is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
if (BPF_SRC(insn->code) == BPF_K) {
@@ -13903,6 +14937,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
!sanitize_speculative_path(env, insn, *insn_idx + 1,
*insn_idx))
return -EFAULT;
+ if (env->log.level & BPF_LOG_LEVEL)
+ print_insn_state(env, this_branch->frame[this_branch->curframe]);
*insn_idx += insn->off;
return 0;
} else if (pred == 0) {
@@ -13915,6 +14951,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
*insn_idx + insn->off + 1,
*insn_idx))
return -EFAULT;
+ if (env->log.level & BPF_LOG_LEVEL)
+ print_insn_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
@@ -14193,7 +15231,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
* gen_ld_abs() may terminate the program at runtime, leading to
* reference leak.
*/
- err = check_reference_leak(env);
+ err = check_reference_leak(env, false);
if (err) {
verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n");
return err;
@@ -14242,19 +15280,19 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
-static int check_return_code(struct bpf_verifier_env *env)
+static int check_return_code(struct bpf_verifier_env *env, int regno)
{
struct tnum enforce_attach_type_range = tnum_unknown;
const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
- struct tnum range = tnum_range(0, 1);
+ struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
struct bpf_func_state *frame = env->cur_state->frame[0];
const bool is_subprog = frame->subprogno;
/* LSM and struct_ops func-ptr's return type could be "void" */
- if (!is_subprog) {
+ if (!is_subprog || frame->in_exception_callback_fn) {
switch (prog_type) {
case BPF_PROG_TYPE_LSM:
if (prog->expected_attach_type == BPF_LSM_CGROUP)
@@ -14276,36 +15314,36 @@ static int check_return_code(struct bpf_verifier_env *env)
* of bpf_exit, which means that program wrote
* something into it earlier
*/
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ err = check_reg_arg(env, regno, SRC_OP);
if (err)
return err;
- if (is_pointer_value(env, BPF_REG_0)) {
- verbose(env, "R0 leaks addr as return value\n");
+ if (is_pointer_value(env, regno)) {
+ verbose(env, "R%d leaks addr as return value\n", regno);
return -EACCES;
}
- reg = cur_regs(env) + BPF_REG_0;
+ reg = cur_regs(env) + regno;
if (frame->in_async_callback_fn) {
/* enforce return zero from async callbacks like timer */
if (reg->type != SCALAR_VALUE) {
- verbose(env, "In async callback the register R0 is not a known value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "In async callback the register R%d is not a known value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
- if (!tnum_in(tnum_const(0), reg->var_off)) {
- verbose_invalid_scalar(env, reg, &range, "async callback", "R0");
+ if (!tnum_in(const_0, reg->var_off)) {
+ verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
return -EINVAL;
}
return 0;
}
- if (is_subprog) {
+ if (is_subprog && !frame->in_exception_callback_fn) {
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
return 0;
@@ -14315,10 +15353,13 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
- env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
range = tnum_range(1, 1);
if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
@@ -14387,8 +15428,8 @@ static int check_return_code(struct bpf_verifier_env *env)
}
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At program exit the register R0 is not a known value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "At program exit the register R%d is not a known value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -14447,21 +15488,6 @@ enum {
BRANCH = 2,
};
-static u32 state_htab_size(struct bpf_verifier_env *env)
-{
- return env->prog->len;
-}
-
-static struct bpf_verifier_state_list **explored_state(
- struct bpf_verifier_env *env,
- int idx)
-{
- struct bpf_verifier_state *cur = env->cur_state;
- struct bpf_func_state *state = cur->frame[cur->curframe];
-
- return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
-}
-
static void mark_prune_point(struct bpf_verifier_env *env, int idx)
{
env->insn_aux_data[idx].prune_point = true;
@@ -14482,6 +15508,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx)
return env->insn_aux_data[insn_idx].force_checkpoint;
}
+static void mark_calls_callback(struct bpf_verifier_env *env, int idx)
+{
+ env->insn_aux_data[idx].calls_callback = true;
+}
+
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx)
+{
+ return env->insn_aux_data[insn_idx].calls_callback;
+}
enum {
DONE_EXPLORING = 0,
@@ -14493,8 +15528,7 @@ enum {
* w - next instruction
* e - edge
*/
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
- bool loop_ok)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
{
int *insn_stack = env->cfg.insn_stack;
int *insn_state = env->cfg.insn_state;
@@ -14526,7 +15560,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
insn_stack[env->cfg.cur_stack++] = w;
return KEEP_EXPLORING;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
- if (loop_ok && env->bpf_capable)
+ if (env->bpf_capable)
return DONE_EXPLORING;
verbose_linfo(env, t, "%d: ", t);
verbose_linfo(env, w, "%d: ", w);
@@ -14546,24 +15580,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
struct bpf_verifier_env *env,
bool visit_callee)
{
- int ret;
+ int ret, insn_sz;
- ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+ insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
+ ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
if (ret)
return ret;
- mark_prune_point(env, t + 1);
+ mark_prune_point(env, t + insn_sz);
/* when we exit from subprog, we need to record non-linear history */
- mark_jmp_point(env, t + 1);
+ mark_jmp_point(env, t + insn_sz);
if (visit_callee) {
mark_prune_point(env, t);
- ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env,
- /* It's ok to allow recursion from CFG point of
- * view. __check_func_call() will do the actual
- * check.
- */
- bpf_pseudo_func(insns + t));
+ ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
}
return ret;
}
@@ -14576,15 +15606,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
static int visit_insn(int t, struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
- int ret;
+ int ret, off, insn_sz;
if (bpf_pseudo_func(insn))
return visit_func_call_insn(t, insns, env, true);
/* All non-branch instructions have a single fall-through edge. */
if (BPF_CLASS(insn->code) != BPF_JMP &&
- BPF_CLASS(insn->code) != BPF_JMP32)
- return push_insn(t, t + 1, FALLTHROUGH, env, false);
+ BPF_CLASS(insn->code) != BPF_JMP32) {
+ insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
+ return push_insn(t, t + insn_sz, FALLTHROUGH, env);
+ }
switch (BPF_OP(insn->code)) {
case BPF_EXIT:
@@ -14598,6 +15630,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
* async state will be pushed for further exploration.
*/
mark_prune_point(env, t);
+ /* For functions that invoke callbacks it is not known how many times
+ * callback would be called. Verifier models callback calling functions
+ * by repeatedly visiting callback bodies and returning to origin call
+ * instruction.
+ * In order to stop such iteration verifier needs to identify when a
+ * state identical some state from a previous iteration is reached.
+ * Check below forces creation of checkpoint before callback calling
+ * instruction to allow search for such identical states.
+ */
+ if (is_sync_callback_calling_insn(insn)) {
+ mark_calls_callback(env, t);
+ mark_force_checkpoint(env, t);
+ mark_prune_point(env, t);
+ mark_jmp_point(env, t);
+ }
if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
struct bpf_kfunc_call_arg_meta meta;
@@ -14624,14 +15671,18 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
if (BPF_SRC(insn->code) != BPF_K)
return -EINVAL;
+ if (BPF_CLASS(insn->code) == BPF_JMP)
+ off = insn->off;
+ else
+ off = insn->imm;
+
/* unconditional jump with single edge */
- ret = push_insn(t, t + insn->off + 1, FALLTHROUGH, env,
- true);
+ ret = push_insn(t, t + off + 1, FALLTHROUGH, env);
if (ret)
return ret;
- mark_prune_point(env, t + insn->off + 1);
- mark_jmp_point(env, t + insn->off + 1);
+ mark_prune_point(env, t + off + 1);
+ mark_jmp_point(env, t + off + 1);
return ret;
@@ -14639,11 +15690,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
/* conditional jump with two edges */
mark_prune_point(env, t);
- ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret)
return ret;
- return push_insn(t, t + insn->off + 1, BRANCH, env, true);
+ return push_insn(t, t + insn->off + 1, BRANCH, env);
}
}
@@ -14654,8 +15705,8 @@ static int check_cfg(struct bpf_verifier_env *env)
{
int insn_cnt = env->prog->len;
int *insn_stack, *insn_state;
- int ret = 0;
- int i;
+ int ex_insn_beg, i, ret = 0;
+ bool ex_done = false;
insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
@@ -14671,6 +15722,7 @@ static int check_cfg(struct bpf_verifier_env *env)
insn_stack[0] = 0; /* 0 is the first instruction */
env->cfg.cur_stack = 1;
+walk_cfg:
while (env->cfg.cur_stack > 0) {
int t = insn_stack[env->cfg.cur_stack - 1];
@@ -14697,12 +15749,32 @@ static int check_cfg(struct bpf_verifier_env *env)
goto err_free;
}
+ if (env->exception_callback_subprog && !ex_done) {
+ ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start;
+
+ insn_state[ex_insn_beg] = DISCOVERED;
+ insn_stack[0] = ex_insn_beg;
+ env->cfg.cur_stack = 1;
+ ex_done = true;
+ goto walk_cfg;
+ }
+
for (i = 0; i < insn_cnt; i++) {
+ struct bpf_insn *insn = &env->prog->insnsi[i];
+
if (insn_state[i] != EXPLORED) {
verbose(env, "unreachable insn %d\n", i);
ret = -EINVAL;
goto err_free;
}
+ if (bpf_is_ldimm64(insn)) {
+ if (insn_state[i + 1] != 0) {
+ verbose(env, "jump into the middle of ldimm64 insn %d\n", i);
+ ret = -EINVAL;
+ goto err_free;
+ }
+ i++; /* skip second half of ldimm64 */
+ }
}
ret = 0; /* cfg looks good */
@@ -14734,20 +15806,18 @@ static int check_abnormal_return(struct bpf_verifier_env *env)
#define MIN_BPF_FUNCINFO_SIZE 8
#define MAX_FUNCINFO_REC_SIZE 252
-static int check_btf_func(struct bpf_verifier_env *env,
- const union bpf_attr *attr,
- bpfptr_t uattr)
+static int check_btf_func_early(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
{
- const struct btf_type *type, *func_proto, *ret_type;
- u32 i, nfuncs, urec_size, min_size;
u32 krec_size = sizeof(struct bpf_func_info);
+ const struct btf_type *type, *func_proto;
+ u32 i, nfuncs, urec_size, min_size;
struct bpf_func_info *krecord;
- struct bpf_func_info_aux *info_aux = NULL;
struct bpf_prog *prog;
const struct btf *btf;
- bpfptr_t urecord;
u32 prev_offset = 0;
- bool scalar_return;
+ bpfptr_t urecord;
int ret = -ENOMEM;
nfuncs = attr->func_info_cnt;
@@ -14757,11 +15827,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
return 0;
}
- if (nfuncs != env->subprog_cnt) {
- verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
- return -EINVAL;
- }
-
urec_size = attr->func_info_rec_size;
if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
urec_size > MAX_FUNCINFO_REC_SIZE ||
@@ -14779,9 +15844,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
if (!krecord)
return -ENOMEM;
- info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
- if (!info_aux)
- goto err_free;
for (i = 0; i < nfuncs; i++) {
ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
@@ -14820,11 +15882,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
goto err_free;
}
- if (env->subprog_info[i].start != krecord[i].insn_off) {
- verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
- goto err_free;
- }
-
/* check type_id */
type = btf_type_by_id(btf, krecord[i].type_id);
if (!type || !btf_type_is_func(type)) {
@@ -14832,12 +15889,77 @@ static int check_btf_func(struct bpf_verifier_env *env,
krecord[i].type_id);
goto err_free;
}
- info_aux[i].linkage = BTF_INFO_VLEN(type->info);
func_proto = btf_type_by_id(btf, type->type);
if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
/* btf_func_check() already verified it during BTF load */
goto err_free;
+
+ prev_offset = krecord[i].insn_off;
+ bpfptr_add(&urecord, urec_size);
+ }
+
+ prog->aux->func_info = krecord;
+ prog->aux->func_info_cnt = nfuncs;
+ return 0;
+
+err_free:
+ kvfree(krecord);
+ return ret;
+}
+
+static int check_btf_func(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ const struct btf_type *type, *func_proto, *ret_type;
+ u32 i, nfuncs, urec_size;
+ struct bpf_func_info *krecord;
+ struct bpf_func_info_aux *info_aux = NULL;
+ struct bpf_prog *prog;
+ const struct btf *btf;
+ bpfptr_t urecord;
+ bool scalar_return;
+ int ret = -ENOMEM;
+
+ nfuncs = attr->func_info_cnt;
+ if (!nfuncs) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+ if (nfuncs != env->subprog_cnt) {
+ verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
+ return -EINVAL;
+ }
+
+ urec_size = attr->func_info_rec_size;
+
+ prog = env->prog;
+ btf = prog->aux->btf;
+
+ urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
+
+ krecord = prog->aux->func_info;
+ info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+ if (!info_aux)
+ return -ENOMEM;
+
+ for (i = 0; i < nfuncs; i++) {
+ /* check insn_off */
+ ret = -EINVAL;
+
+ if (env->subprog_info[i].start != krecord[i].insn_off) {
+ verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
+ goto err_free;
+ }
+
+ /* Already checked type_id */
+ type = btf_type_by_id(btf, krecord[i].type_id);
+ info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+ /* Already checked func_proto */
+ func_proto = btf_type_by_id(btf, type->type);
+
ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
scalar_return =
btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type);
@@ -14850,17 +15972,13 @@ static int check_btf_func(struct bpf_verifier_env *env,
goto err_free;
}
- prev_offset = krecord[i].insn_off;
bpfptr_add(&urecord, urec_size);
}
- prog->aux->func_info = krecord;
- prog->aux->func_info_cnt = nfuncs;
prog->aux->func_info_aux = info_aux;
return 0;
err_free:
- kvfree(krecord);
kfree(info_aux);
return ret;
}
@@ -14873,7 +15991,8 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
if (!aux->func_info)
return;
- for (i = 0; i < env->subprog_cnt; i++)
+ /* func_info is not available for hidden subprogs */
+ for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++)
aux->func_info[i].insn_off = env->subprog_info[i].start;
}
@@ -15077,9 +16196,9 @@ static int check_core_relo(struct bpf_verifier_env *env,
return err;
}
-static int check_btf_info(struct bpf_verifier_env *env,
- const union bpf_attr *attr,
- bpfptr_t uattr)
+static int check_btf_info_early(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
{
struct btf *btf;
int err;
@@ -15099,6 +16218,24 @@ static int check_btf_info(struct bpf_verifier_env *env,
}
env->prog->aux->btf = btf;
+ err = check_btf_func_early(env, attr, uattr);
+ if (err)
+ return err;
+ return 0;
+}
+
+static int check_btf_info(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ int err;
+
+ if (!attr->func_info_cnt && !attr->line_info_cnt) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+
err = check_btf_func(env, attr, uattr);
if (err)
return err;
@@ -15257,18 +16394,14 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn,
struct bpf_verifier_state *cur)
{
struct bpf_verifier_state_list *sl;
- int i;
sl = *explored_state(env, insn);
while (sl) {
if (sl->state.branches)
goto next;
if (sl->state.insn_idx != insn ||
- sl->state.curframe != cur->curframe)
+ !same_callsites(&sl->state, cur))
goto next;
- for (i = 0; i <= cur->curframe; i++)
- if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
- goto next;
clean_verifier_state(env, &sl->state);
next:
sl = sl->next;
@@ -15286,8 +16419,11 @@ static bool regs_exact(const struct bpf_reg_state *rold,
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
- struct bpf_reg_state *rcur, struct bpf_idmap *idmap)
+ struct bpf_reg_state *rcur, struct bpf_idmap *idmap, bool exact)
{
+ if (exact)
+ return regs_exact(rold, rcur, idmap);
+
if (!(rold->live & REG_LIVE_READ))
/* explored state didn't use this */
return true;
@@ -15404,7 +16540,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
}
static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
- struct bpf_func_state *cur, struct bpf_idmap *idmap)
+ struct bpf_func_state *cur, struct bpf_idmap *idmap, bool exact)
{
int i, spi;
@@ -15417,7 +16553,12 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
spi = i / BPF_REG_SIZE;
- if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+ if (exact &&
+ old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+ return false;
+
+ if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) && !exact) {
i += BPF_REG_SIZE - 1;
/* explored state didn't use this */
continue;
@@ -15467,7 +16608,7 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
* return false to continue verification of this path
*/
if (!regsafe(env, &old->stack[spi].spilled_ptr,
- &cur->stack[spi].spilled_ptr, idmap))
+ &cur->stack[spi].spilled_ptr, idmap, exact))
return false;
break;
case STACK_DYNPTR:
@@ -15549,16 +16690,16 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur,
* the current state will reach 'bpf_exit' instruction safely
*/
static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old,
- struct bpf_func_state *cur)
+ struct bpf_func_state *cur, bool exact)
{
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (!regsafe(env, &old->regs[i], &cur->regs[i],
- &env->idmap_scratch))
+ &env->idmap_scratch, exact))
return false;
- if (!stacksafe(env, old, cur, &env->idmap_scratch))
+ if (!stacksafe(env, old, cur, &env->idmap_scratch, exact))
return false;
if (!refsafe(old, cur, &env->idmap_scratch))
@@ -15567,17 +16708,23 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
return true;
}
+static void reset_idmap_scratch(struct bpf_verifier_env *env)
+{
+ env->idmap_scratch.tmp_id_gen = env->id_gen;
+ memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
+}
+
static bool states_equal(struct bpf_verifier_env *env,
struct bpf_verifier_state *old,
- struct bpf_verifier_state *cur)
+ struct bpf_verifier_state *cur,
+ bool exact)
{
int i;
if (old->curframe != cur->curframe)
return false;
- env->idmap_scratch.tmp_id_gen = env->id_gen;
- memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
+ reset_idmap_scratch(env);
/* Verification state from speculative execution simulation
* must never prune a non-speculative execution one.
@@ -15607,7 +16754,7 @@ static bool states_equal(struct bpf_verifier_env *env,
for (i = 0; i <= old->curframe; i++) {
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
- if (!func_states_equal(env, old->frame[i], cur->frame[i]))
+ if (!func_states_equal(env, old->frame[i], cur->frame[i], exact))
return false;
}
return true;
@@ -15861,10 +17008,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl, **pprev;
- struct bpf_verifier_state *cur = env->cur_state, *new;
- int i, j, err, states_cnt = 0;
+ struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry;
+ int i, j, n, err, states_cnt = 0;
bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx);
bool add_new_state = force_new_state;
+ bool force_exact;
/* bpf progs typically have pruning point every 4 instructions
* http://vger.kernel.org/bpfconf2019.html#session-1
@@ -15917,9 +17065,33 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* It's safe to assume that iterator loop will finish, taking into
* account iter_next() contract of eventually returning
* sticky NULL result.
+ *
+ * Note, that states have to be compared exactly in this case because
+ * read and precision marks might not be finalized inside the loop.
+ * E.g. as in the program below:
+ *
+ * 1. r7 = -16
+ * 2. r6 = bpf_get_prandom_u32()
+ * 3. while (bpf_iter_num_next(&fp[-8])) {
+ * 4. if (r6 != 42) {
+ * 5. r7 = -32
+ * 6. r6 = bpf_get_prandom_u32()
+ * 7. continue
+ * 8. }
+ * 9. r0 = r10
+ * 10. r0 += r7
+ * 11. r8 = *(u64 *)(r0 + 0)
+ * 12. r6 = bpf_get_prandom_u32()
+ * 13. }
+ *
+ * Here verifier would first visit path 1-3, create a checkpoint at 3
+ * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does
+ * not have read or precision mark for r7 yet, thus inexact states
+ * comparison would discard current state with r7=-32
+ * => unsafe memory access at 11 would not be caught.
*/
if (is_iter_next_insn(env, insn_idx)) {
- if (states_equal(env, &sl->state, cur)) {
+ if (states_equal(env, &sl->state, cur, true)) {
struct bpf_func_state *cur_frame;
struct bpf_reg_state *iter_state, *iter_reg;
int spi;
@@ -15935,17 +17107,29 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
*/
spi = __get_spi(iter_reg->off + iter_reg->var_off.value);
iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr;
- if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE)
+ if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) {
+ update_loop_entry(cur, &sl->state);
goto hit;
+ }
}
goto skip_inf_loop_check;
}
+ if (calls_callback(env, insn_idx)) {
+ if (states_equal(env, &sl->state, cur, true))
+ goto hit;
+ goto skip_inf_loop_check;
+ }
/* attempt to detect infinite loop to avoid unnecessary doomed work */
if (states_maybe_looping(&sl->state, cur) &&
- states_equal(env, &sl->state, cur) &&
- !iter_active_depths_differ(&sl->state, cur)) {
+ states_equal(env, &sl->state, cur, false) &&
+ !iter_active_depths_differ(&sl->state, cur) &&
+ sl->state.callback_unroll_depth == cur->callback_unroll_depth) {
verbose_linfo(env, insn_idx, "; ");
verbose(env, "infinite loop detected at insn %d\n", insn_idx);
+ verbose(env, "cur state:");
+ print_verifier_state(env, cur->frame[cur->curframe], true);
+ verbose(env, "old state:");
+ print_verifier_state(env, sl->state.frame[cur->curframe], true);
return -EINVAL;
}
/* if the verifier is processing a loop, avoid adding new state
@@ -15967,7 +17151,36 @@ skip_inf_loop_check:
add_new_state = false;
goto miss;
}
- if (states_equal(env, &sl->state, cur)) {
+ /* If sl->state is a part of a loop and this loop's entry is a part of
+ * current verification path then states have to be compared exactly.
+ * 'force_exact' is needed to catch the following case:
+ *
+ * initial Here state 'succ' was processed first,
+ * | it was eventually tracked to produce a
+ * V state identical to 'hdr'.
+ * .---------> hdr All branches from 'succ' had been explored
+ * | | and thus 'succ' has its .branches == 0.
+ * | V
+ * | .------... Suppose states 'cur' and 'succ' correspond
+ * | | | to the same instruction + callsites.
+ * | V V In such case it is necessary to check
+ * | ... ... if 'succ' and 'cur' are states_equal().
+ * | | | If 'succ' and 'cur' are a part of the
+ * | V V same loop exact flag has to be set.
+ * | succ <- cur To check if that is the case, verify
+ * | | if loop entry of 'succ' is in current
+ * | V DFS path.
+ * | ...
+ * | |
+ * '----'
+ *
+ * Additional details are in the comment before get_loop_entry().
+ */
+ loop_entry = get_loop_entry(&sl->state);
+ force_exact = loop_entry && loop_entry->branches > 0;
+ if (states_equal(env, &sl->state, cur, force_exact)) {
+ if (force_exact)
+ update_loop_entry(cur, loop_entry);
hit:
sl->hit_cnt++;
/* reached equivalent register/stack state,
@@ -16006,13 +17219,18 @@ miss:
* to keep checking from state equivalence point of view.
* Higher numbers increase max_states_per_insn and verification time,
* but do not meaningfully decrease insn_processed.
+ * 'n' controls how many times state could miss before eviction.
+ * Use bigger 'n' for checkpoints because evicting checkpoint states
+ * too early would hinder iterator convergence.
*/
- if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+ n = is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3;
+ if (sl->miss_cnt > sl->hit_cnt * n + n) {
/* the state is unlikely to be useful. Remove it to
* speed up verification
*/
*pprev = sl->next;
- if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE &&
+ !sl->state.used_as_loop_entry) {
u32 br = sl->state.branches;
WARN_ONCE(br,
@@ -16081,6 +17299,7 @@ next:
cur->parent = new;
cur->first_insn_idx = insn_idx;
+ cur->dfs_depth = new->dfs_depth + 1;
clear_jmp_history(cur);
new_sl->next = *explored_state(env, insn_idx);
*explored_state(env, insn_idx) = new_sl;
@@ -16178,7 +17397,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
* Have to support a use case when one path through
* the program yields TRUSTED pointer while another
* is UNTRUSTED. Fallback to UNTRUSTED to generate
- * BPF_PROBE_MEM.
+ * BPF_PROBE_MEM/BPF_PROBE_MEMSX.
*/
*prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
} else {
@@ -16201,6 +17420,7 @@ static int do_check(struct bpf_verifier_env *env)
int prev_insn_idx = -1;
for (;;) {
+ bool exception_exit = false;
struct bpf_insn *insn;
u8 class;
int err;
@@ -16319,7 +17539,8 @@ static int do_check(struct bpf_verifier_env *env)
*/
err = check_mem_access(env, env->insn_idx, insn->src_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_READ, insn->dst_reg, false);
+ BPF_READ, insn->dst_reg, false,
+ BPF_MODE(insn->code) == BPF_MEMSX);
if (err)
return err;
@@ -16356,7 +17577,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, insn->src_reg, false);
+ BPF_WRITE, insn->src_reg, false, false);
if (err)
return err;
@@ -16381,7 +17602,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
@@ -16414,27 +17635,35 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
}
- if (insn->src_reg == BPF_PSEUDO_CALL)
+ if (insn->src_reg == BPF_PSEUDO_CALL) {
err = check_func_call(env, insn, &env->insn_idx);
- else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
+ } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
err = check_kfunc_call(env, insn, &env->insn_idx);
- else
+ if (!err && is_bpf_throw_kfunc(insn)) {
+ exception_exit = true;
+ goto process_bpf_exit_full;
+ }
+ } else {
err = check_helper_call(env, insn, &env->insn_idx);
+ }
if (err)
return err;
mark_reg_scratched(env, BPF_REG_0);
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
- insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
+ (class == BPF_JMP && insn->imm != 0) ||
+ (class == BPF_JMP32 && insn->off != 0)) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
- env->insn_idx += insn->off + 1;
+ if (class == BPF_JMP)
+ env->insn_idx += insn->off + 1;
+ else
+ env->insn_idx += insn->imm + 1;
continue;
} else if (opcode == BPF_EXIT) {
@@ -16446,14 +17675,15 @@ static int do_check(struct bpf_verifier_env *env)
verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
-
+process_bpf_exit_full:
if (env->cur_state->active_lock.ptr &&
!in_rbtree_lock_required_cb(env)) {
verbose(env, "bpf_spin_unlock is missing\n");
return -EINVAL;
}
- if (env->cur_state->active_rcu_lock) {
+ if (env->cur_state->active_rcu_lock &&
+ !in_rbtree_lock_required_cb(env)) {
verbose(env, "bpf_rcu_read_unlock is missing\n");
return -EINVAL;
}
@@ -16464,10 +17694,23 @@ static int do_check(struct bpf_verifier_env *env)
* function, for which reference_state must
* match caller reference state when it exits.
*/
- err = check_reference_leak(env);
+ err = check_reference_leak(env, exception_exit);
if (err)
return err;
+ /* The side effect of the prepare_func_exit
+ * which is being skipped is that it frees
+ * bpf_func_state. Typically, process_bpf_exit
+ * will only be hit with outermost exit.
+ * copy_verifier_state in pop_stack will handle
+ * freeing of any extra bpf_func_state left over
+ * from not processing all nested function
+ * exits. We also skip return code checks as
+ * they are not needed for exceptional exits.
+ */
+ if (exception_exit)
+ goto process_bpf_exit;
+
if (state->curframe) {
/* exit from nested function */
err = prepare_func_exit(env, &env->insn_idx);
@@ -16477,7 +17720,7 @@ static int do_check(struct bpf_verifier_env *env)
continue;
}
- err = check_return_code(env);
+ err = check_return_code(env, BPF_REG_0);
if (err)
return err;
process_bpf_exit:
@@ -16733,11 +17976,6 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
return -EINVAL;
}
-
- if (prog->aux->sleepable) {
- verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
- return -EINVAL;
- }
}
if (btf_record_has_field(map->record, BPF_TIMER)) {
@@ -16809,7 +18047,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
+ ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) ||
+ insn->imm != 0)) {
verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
@@ -17280,13 +18519,13 @@ static bool insn_is_cond_jump(u8 code)
{
u8 op;
+ op = BPF_OP(code);
if (BPF_CLASS(code) == BPF_JMP32)
- return true;
+ return op != BPF_JA;
if (BPF_CLASS(code) != BPF_JMP)
return false;
- op = BPF_OP(code);
return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
}
@@ -17503,11 +18742,15 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ u8 mode;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) {
type = BPF_READ;
} else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
@@ -17566,8 +18809,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
*/
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
if (type == BPF_READ) {
- insn->code = BPF_LDX | BPF_PROBE_MEM |
- BPF_SIZE((insn)->code);
+ if (BPF_MODE(insn->code) == BPF_MEM)
+ insn->code = BPF_LDX | BPF_PROBE_MEM |
+ BPF_SIZE((insn)->code);
+ else
+ insn->code = BPF_LDX | BPF_PROBE_MEMSX |
+ BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
}
continue;
@@ -17577,6 +18824,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
+ mode = BPF_MODE(insn->code);
/* If the read access is a narrower load of the field,
* convert to a 4/8-byte load, to minimum program type specific
@@ -17636,6 +18884,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
(1ULL << size * 8) - 1);
}
}
+ if (mode == BPF_MEMSX)
+ insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X,
+ insn->dst_reg, insn->dst_reg,
+ size * 8, 0);
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
@@ -17755,11 +19007,15 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- BPF_MODE(insn->code) == BPF_PROBE_MEM)
+ (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
num_exentries++;
}
func[i]->aux->num_exentries = num_exentries;
func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
+ func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb;
+ if (!i)
+ func[i]->aux->exception_boundary = env->seen_exception;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
@@ -17799,7 +19055,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* the call instruction, as an index for this list
*/
func[i]->aux->func = func;
- func[i]->aux->func_cnt = env->subprog_cnt;
+ func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
+ func[i]->aux->real_func_cnt = env->subprog_cnt;
}
for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
@@ -17845,7 +19102,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
prog->aux->extable = func[0]->aux->extable;
prog->aux->num_exentries = func[0]->aux->num_exentries;
prog->aux->func = func;
- prog->aux->func_cnt = env->subprog_cnt;
+ prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
+ prog->aux->real_func_cnt = env->subprog_cnt;
+ prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func;
+ prog->aux->exception_boundary = func[0]->aux->exception_boundary;
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
@@ -18012,21 +19272,42 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn->imm = BPF_CALL_IMM(desc->addr);
if (insn->off)
return 0;
- if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size;
+ if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && kptr_struct_meta) {
+ verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size);
insn_buf[1] = addr[0];
insn_buf[2] = addr[1];
insn_buf[3] = *insn;
*cnt = 4;
} else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
+ if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] && kptr_struct_meta) {
+ verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
+ if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
+ !kptr_struct_meta) {
+ verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
insn_buf[0] = addr[0];
insn_buf[1] = addr[1];
insn_buf[2] = *insn;
@@ -18034,6 +19315,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
} else if (desc->func_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+ struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
int struct_meta_reg = BPF_REG_3;
int node_offset_reg = BPF_REG_4;
@@ -18043,6 +19325,12 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
node_offset_reg = BPF_REG_5;
}
+ if (!kptr_struct_meta) {
+ verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
__fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg,
node_offset_reg, insn, insn_buf, cnt);
} else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
@@ -18053,6 +19341,33 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return 0;
}
+/* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */
+static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len)
+{
+ struct bpf_subprog_info *info = env->subprog_info;
+ int cnt = env->subprog_cnt;
+ struct bpf_prog *prog;
+
+ /* We only reserve one slot for hidden subprogs in subprog_info. */
+ if (env->hidden_subprog_cnt) {
+ verbose(env, "verifier internal error: only one hidden subprog supported\n");
+ return -EFAULT;
+ }
+ /* We're not patching any existing instruction, just appending the new
+ * ones for the hidden subprog. Hence all of the adjustment operations
+ * in bpf_patch_insn_data are no-ops.
+ */
+ prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len);
+ if (!prog)
+ return -ENOMEM;
+ env->prog = prog;
+ info[cnt + 1].start = info[cnt].start;
+ info[cnt].start = prog->len - len + 1;
+ env->subprog_cnt++;
+ env->hidden_subprog_cnt++;
+ return 0;
+}
+
/* Do various post-verification rewrites in a single program pass.
* These rewrites simplify JIT and interpreter implementations.
*/
@@ -18071,6 +19386,26 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
struct bpf_map *map_ptr;
int i, ret, cnt, delta = 0;
+ if (env->seen_exception && !env->exception_callback_subprog) {
+ struct bpf_insn patch[] = {
+ env->prog->insnsi[insn_cnt - 1],
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ };
+
+ ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch));
+ if (ret < 0)
+ return ret;
+ prog = env->prog;
+ insn = prog->insnsi;
+
+ env->exception_callback_subprog = env->subprog_cnt - 1;
+ /* Don't update insn_cnt, as add_hidden_subprog always appends insns */
+ env->subprog_info[env->exception_callback_subprog].is_cb = true;
+ env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
+ env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+ }
+
for (i = 0; i < insn_cnt; i++, insn++) {
/* Make divide-by-zero exceptions impossible. */
if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
@@ -18340,6 +19675,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto patch_call_imm;
}
+ /* bpf_per_cpu_ptr() and bpf_this_cpu_ptr() */
+ if (env->insn_aux_data[i + delta].call_with_percpu_alloc_ptr) {
+ /* patch with 'r1 = *(u64 *)(r1 + 0)' since for percpu data,
+ * bpf_mem_alloc() returns a ptr to the percpu data ptr.
+ */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+ insn_buf[1] = *insn;
+ cnt = 2;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ goto patch_call_imm;
+ }
+
/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
* and other inlining handlers are currently limited to 64 bit
* only.
@@ -18749,7 +20103,7 @@ static void free_states(struct bpf_verifier_env *env)
}
}
-static int do_check_common(struct bpf_verifier_env *env, int subprog)
+static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state;
@@ -18780,7 +20134,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
regs = state->frame[state->curframe]->regs;
if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
- ret = btf_prepare_func_args(env, subprog, regs);
+ ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
if (ret)
goto out;
for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
@@ -18796,6 +20150,12 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
regs[i].id = ++env->id_gen;
}
}
+ if (is_ex_cb) {
+ state->frame[0]->in_exception_callback_fn = true;
+ env->subprog_info[subprog].is_cb = true;
+ env->subprog_info[subprog].is_async_cb = true;
+ env->subprog_info[subprog].is_exception_cb = true;
+ }
} else {
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
@@ -18860,7 +20220,7 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
continue;
env->insn_idx = env->subprog_info[i].start;
WARN_ON_ONCE(env->insn_idx == 0);
- ret = do_check_common(env, i);
+ ret = do_check_common(env, i, env->exception_callback_subprog == i);
if (ret) {
return ret;
} else if (env->log.level & BPF_LOG_LEVEL) {
@@ -18877,7 +20237,7 @@ static int do_check_main(struct bpf_verifier_env *env)
int ret;
env->insn_idx = 0;
- ret = do_check_common(env, 0);
+ ret = do_check_common(env, 0, false);
if (!ret)
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return ret;
@@ -19046,6 +20406,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
bpf_log(log, "Subprog %s doesn't exist\n", tname);
return -EINVAL;
}
+ if (aux->func && aux->func[subprog]->aux->exception_cb) {
+ bpf_log(log,
+ "%s programs cannot attach to exception callback\n",
+ prog_extension ? "Extension" : "FENTRY/FEXIT");
+ return -EINVAL;
+ }
conservative = aux->func_info_aux[subprog].unreliable;
if (prog_extension) {
if (conservative) {
@@ -19375,6 +20741,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
if (!tr)
return -ENOMEM;
+ if (tgt_prog && tgt_prog->aux->tail_call_reachable)
+ tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX;
+
prog->aux->dst_trampoline = tr;
return 0;
}
@@ -19470,6 +20839,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (!env->explored_states)
goto skip_full_check;
+ ret = check_btf_info_early(env, attr, uattr);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = add_subprog_and_kfunc(env);
if (ret < 0)
goto skip_full_check;