summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c11
-rw-r--r--kernel/bpf/bpf_iter.c11
-rw-r--r--kernel/bpf/bpf_local_storage.c8
-rw-r--r--kernel/bpf/btf.c56
-rw-r--r--kernel/bpf/cgroup.c182
-rw-r--r--kernel/bpf/core.c32
-rw-r--r--kernel/bpf/helpers.c382
-rw-r--r--kernel/bpf/local_storage.c9
-rw-r--r--kernel/bpf/syscall.c180
-rw-r--r--kernel/bpf/tnum.c5
-rw-r--r--kernel/bpf/trampoline.c41
-rw-r--r--kernel/bpf/verifier.c1785
-rw-r--r--kernel/cgroup/cgroup.c5
-rw-r--r--kernel/trace/bpf_trace.c2
14 files changed, 1976 insertions, 733 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index eb28c0f219ee..3d080916faf9 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -530,8 +530,6 @@ static int array_map_check_btf(const struct bpf_map *map,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
- u32 int_data;
-
/* One exception for keyless BTF: .bss/.data/.rodata map */
if (btf_type_is_void(key_type)) {
if (map->map_type != BPF_MAP_TYPE_ARRAY ||
@@ -544,14 +542,11 @@ static int array_map_check_btf(const struct bpf_map *map,
return 0;
}
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- /* bpf array can only take a u32 key. This check makes sure
+ /*
+ * Bpf array can only take a u32 key. This check makes sure
* that the btf matches the attr used during map_create.
*/
- if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+ if (!btf_type_is_i32(key_type))
return -EINVAL;
return 0;
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 380e9a7cac75..303ab1f42d3a 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -38,8 +38,7 @@ static DEFINE_MUTEX(link_mutex);
/* incremented on every opened seq_file */
static atomic64_t session_id;
-static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
- const struct bpf_iter_seq_info *seq_info);
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link);
static void bpf_iter_inc_seq_num(struct seq_file *seq)
{
@@ -257,7 +256,7 @@ static int iter_open(struct inode *inode, struct file *file)
{
struct bpf_iter_link *link = inode->i_private;
- return prepare_seq_file(file, link, __get_seq_info(link));
+ return prepare_seq_file(file, link);
}
static int iter_release(struct inode *inode, struct file *file)
@@ -586,9 +585,9 @@ static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
priv_data->done_stop = false;
}
-static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
- const struct bpf_iter_seq_info *seq_info)
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
{
+ const struct bpf_iter_seq_info *seq_info = __get_seq_info(link);
struct bpf_iter_priv_data *priv_data;
struct bpf_iter_target_info *tinfo;
struct bpf_prog *prog;
@@ -653,7 +652,7 @@ int bpf_iter_new_fd(struct bpf_link *link)
}
iter_link = container_of(link, struct bpf_iter_link, link);
- err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link));
+ err = prepare_seq_file(file, iter_link);
if (err)
goto free_file;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index fa56c30833ff..b931fbceb54d 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -722,13 +722,7 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
- u32 int_data;
-
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+ if (!btf_type_is_i32(key_type))
return -EINVAL;
return 0;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 1d2cf898e21e..05fd64a371af 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -858,26 +858,37 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
EXPORT_SYMBOL_GPL(btf_type_by_id);
/*
- * Regular int is not a bit field and it must be either
- * u8/u16/u32/u64 or __int128.
+ * Check that the type @t is a regular int. This means that @t is not
+ * a bit field and it has the same size as either of u8/u16/u32/u64
+ * or __int128. If @expected_size is not zero, then size of @t should
+ * be the same. A caller should already have checked that the type @t
+ * is an integer.
*/
+static bool __btf_type_int_is_regular(const struct btf_type *t, size_t expected_size)
+{
+ u32 int_data = btf_type_int(t);
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+
+ return BITS_PER_BYTE_MASKED(nr_bits) == 0 &&
+ BTF_INT_OFFSET(int_data) == 0 &&
+ (nr_bytes <= 16 && is_power_of_2(nr_bytes)) &&
+ (expected_size == 0 || nr_bytes == expected_size);
+}
+
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u8 nr_bits, nr_bytes;
- u32 int_data;
+ return __btf_type_int_is_regular(t, 0);
+}
- int_data = btf_type_int(t);
- nr_bits = BTF_INT_BITS(int_data);
- nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
- if (BITS_PER_BYTE_MASKED(nr_bits) ||
- BTF_INT_OFFSET(int_data) ||
- (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
- nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) &&
- nr_bytes != (2 * sizeof(u64)))) {
- return false;
- }
+bool btf_type_is_i32(const struct btf_type *t)
+{
+ return btf_type_is_int(t) && __btf_type_int_is_regular(t, 4);
+}
- return true;
+bool btf_type_is_i64(const struct btf_type *t)
+{
+ return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8);
}
/*
@@ -3443,7 +3454,8 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
node_field_name = strstr(value_type, ":");
if (!node_field_name)
return -EINVAL;
- value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL | __GFP_NOWARN);
+ value_type = kstrndup(value_type, node_field_name - value_type,
+ GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!value_type)
return -ENOMEM;
id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT);
@@ -3958,7 +3970,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
/* This needs to be kzalloc to zero out padding and unused fields, see
* comment in btf_record_equal.
*/
- rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL | __GFP_NOWARN);
+ rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!rec)
return ERR_PTR(-ENOMEM);
@@ -9019,7 +9031,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
bpf_free_cands_from_cache(*cc);
*cc = NULL;
}
- new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL);
+ new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL_ACCOUNT);
if (!new_cands) {
bpf_free_cands(cands);
return ERR_PTR(-ENOMEM);
@@ -9027,7 +9039,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
/* strdup the name, since it will stay in cache.
* the cands->name points to strings in prog's BTF and the prog can be unloaded.
*/
- new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL);
+ new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL_ACCOUNT);
bpf_free_cands(cands);
if (!new_cands->name) {
kfree(new_cands);
@@ -9111,7 +9123,7 @@ bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf,
continue;
/* most of the time there is only one candidate for a given kind+name pair */
- new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL);
+ new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL_ACCOUNT);
if (!new_cands) {
bpf_free_cands(cands);
return ERR_PTR(-ENOMEM);
@@ -9228,7 +9240,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
/* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5"
* into arrays of btf_ids of struct fields and array indices.
*/
- specs = kcalloc(3, sizeof(*specs), GFP_KERNEL);
+ specs = kcalloc(3, sizeof(*specs), GFP_KERNEL_ACCOUNT);
if (!specs)
return -ENOMEM;
@@ -9253,7 +9265,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
goto out;
}
if (cc->cnt) {
- cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL);
+ cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL_ACCOUNT);
if (!cands.cands) {
err = -ENOMEM;
goto out;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f4885514f007..cd220e861d67 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -658,6 +658,116 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs,
return NULL;
}
+static struct bpf_link *bpf_get_anchor_link(u32 flags, u32 id_or_fd)
+{
+ struct bpf_link *link = ERR_PTR(-EINVAL);
+
+ if (flags & BPF_F_ID)
+ link = bpf_link_by_id(id_or_fd);
+ else if (id_or_fd)
+ link = bpf_link_get_from_fd(id_or_fd);
+ return link;
+}
+
+static struct bpf_prog *bpf_get_anchor_prog(u32 flags, u32 id_or_fd)
+{
+ struct bpf_prog *prog = ERR_PTR(-EINVAL);
+
+ if (flags & BPF_F_ID)
+ prog = bpf_prog_by_id(id_or_fd);
+ else if (id_or_fd)
+ prog = bpf_prog_get(id_or_fd);
+ return prog;
+}
+
+static struct bpf_prog_list *get_prog_list(struct hlist_head *progs, struct bpf_prog *prog,
+ struct bpf_cgroup_link *link, u32 flags, u32 id_or_fd)
+{
+ bool is_link = flags & BPF_F_LINK, is_id = flags & BPF_F_ID;
+ struct bpf_prog_list *pltmp, *pl = ERR_PTR(-EINVAL);
+ bool preorder = flags & BPF_F_PREORDER;
+ struct bpf_link *anchor_link = NULL;
+ struct bpf_prog *anchor_prog = NULL;
+ bool is_before, is_after;
+
+ is_before = flags & BPF_F_BEFORE;
+ is_after = flags & BPF_F_AFTER;
+ if (is_link || is_id || id_or_fd) {
+ /* flags must have either BPF_F_BEFORE or BPF_F_AFTER */
+ if (is_before == is_after)
+ return ERR_PTR(-EINVAL);
+ if ((is_link && !link) || (!is_link && !prog))
+ return ERR_PTR(-EINVAL);
+ } else if (!hlist_empty(progs)) {
+ /* flags cannot have both BPF_F_BEFORE and BPF_F_AFTER */
+ if (is_before && is_after)
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (is_link) {
+ anchor_link = bpf_get_anchor_link(flags, id_or_fd);
+ if (IS_ERR(anchor_link))
+ return ERR_PTR(PTR_ERR(anchor_link));
+ } else if (is_id || id_or_fd) {
+ anchor_prog = bpf_get_anchor_prog(flags, id_or_fd);
+ if (IS_ERR(anchor_prog))
+ return ERR_PTR(PTR_ERR(anchor_prog));
+ }
+
+ if (!anchor_prog && !anchor_link) {
+ /* if there is no anchor_prog/anchor_link, then BPF_F_PREORDER
+ * doesn't matter since either prepend or append to a combined
+ * list of progs will end up with correct result.
+ */
+ hlist_for_each_entry(pltmp, progs, node) {
+ if (is_before)
+ return pltmp;
+ if (pltmp->node.next)
+ continue;
+ return pltmp;
+ }
+ return NULL;
+ }
+
+ hlist_for_each_entry(pltmp, progs, node) {
+ if ((anchor_prog && anchor_prog == pltmp->prog) ||
+ (anchor_link && anchor_link == &pltmp->link->link)) {
+ if (!!(pltmp->flags & BPF_F_PREORDER) != preorder)
+ goto out;
+ pl = pltmp;
+ goto out;
+ }
+ }
+
+ pl = ERR_PTR(-ENOENT);
+out:
+ if (anchor_link)
+ bpf_link_put(anchor_link);
+ else
+ bpf_prog_put(anchor_prog);
+ return pl;
+}
+
+static int insert_pl_to_hlist(struct bpf_prog_list *pl, struct hlist_head *progs,
+ struct bpf_prog *prog, struct bpf_cgroup_link *link,
+ u32 flags, u32 id_or_fd)
+{
+ struct bpf_prog_list *pltmp;
+
+ pltmp = get_prog_list(progs, prog, link, flags, id_or_fd);
+ if (IS_ERR(pltmp))
+ return PTR_ERR(pltmp);
+
+ if (!pltmp)
+ hlist_add_head(&pl->node, progs);
+ else if (flags & BPF_F_BEFORE)
+ hlist_add_before(&pl->node, &pltmp->node);
+ else
+ hlist_add_behind(&pl->node, &pltmp->node);
+
+ return 0;
+}
+
/**
* __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and
* propagate the change to descendants
@@ -667,6 +777,8 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs,
* @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
* @type: Type of attach operation
* @flags: Option flags
+ * @id_or_fd: Relative prog id or fd
+ * @revision: bpf_prog_list revision
*
* Exactly one of @prog or @link can be non-null.
* Must be called with cgroup_mutex held.
@@ -674,7 +786,8 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs,
static int __cgroup_bpf_attach(struct cgroup *cgrp,
struct bpf_prog *prog, struct bpf_prog *replace_prog,
struct bpf_cgroup_link *link,
- enum bpf_attach_type type, u32 flags)
+ enum bpf_attach_type type, u32 flags, u32 id_or_fd,
+ u64 revision)
{
u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
struct bpf_prog *old_prog = NULL;
@@ -690,6 +803,9 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
/* invalid combination */
return -EINVAL;
+ if ((flags & BPF_F_REPLACE) && (flags & (BPF_F_BEFORE | BPF_F_AFTER)))
+ /* only either replace or insertion with before/after */
+ return -EINVAL;
if (link && (prog || replace_prog))
/* only either link or prog/replace_prog can be specified */
return -EINVAL;
@@ -700,6 +816,8 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id);
if (atype < 0)
return -EINVAL;
+ if (revision && revision != cgrp->bpf.revisions[atype])
+ return -ESTALE;
progs = &cgrp->bpf.progs[atype];
@@ -728,22 +846,18 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
if (pl) {
old_prog = pl->prog;
} else {
- struct hlist_node *last = NULL;
-
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
if (!pl) {
bpf_cgroup_storages_free(new_storage);
return -ENOMEM;
}
- if (hlist_empty(progs))
- hlist_add_head(&pl->node, progs);
- else
- hlist_for_each(last, progs) {
- if (last->next)
- continue;
- hlist_add_behind(&pl->node, last);
- break;
- }
+
+ err = insert_pl_to_hlist(pl, progs, prog, link, flags, id_or_fd);
+ if (err) {
+ kfree(pl);
+ bpf_cgroup_storages_free(new_storage);
+ return err;
+ }
}
pl->prog = prog;
@@ -762,6 +876,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
if (err)
goto cleanup_trampoline;
+ cgrp->bpf.revisions[atype] += 1;
if (old_prog) {
if (type == BPF_LSM_CGROUP)
bpf_trampoline_unlink_cgroup_shim(old_prog);
@@ -793,12 +908,13 @@ static int cgroup_bpf_attach(struct cgroup *cgrp,
struct bpf_prog *prog, struct bpf_prog *replace_prog,
struct bpf_cgroup_link *link,
enum bpf_attach_type type,
- u32 flags)
+ u32 flags, u32 id_or_fd, u64 revision)
{
int ret;
cgroup_lock();
- ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags);
+ ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags,
+ id_or_fd, revision);
cgroup_unlock();
return ret;
}
@@ -886,6 +1002,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp,
if (!found)
return -ENOENT;
+ cgrp->bpf.revisions[atype] += 1;
old_prog = xchg(&link->link.prog, new_prog);
replace_effective_prog(cgrp, atype, link);
bpf_prog_put(old_prog);
@@ -1011,12 +1128,14 @@ found:
* @prog: A program to detach or NULL
* @link: A link to detach or NULL
* @type: Type of detach operation
+ * @revision: bpf_prog_list revision
*
* At most one of @prog or @link can be non-NULL.
* Must be called with cgroup_mutex held.
*/
static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
- struct bpf_cgroup_link *link, enum bpf_attach_type type)
+ struct bpf_cgroup_link *link, enum bpf_attach_type type,
+ u64 revision)
{
enum cgroup_bpf_attach_type atype;
struct bpf_prog *old_prog;
@@ -1034,6 +1153,9 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
if (atype < 0)
return -EINVAL;
+ if (revision && revision != cgrp->bpf.revisions[atype])
+ return -ESTALE;
+
progs = &cgrp->bpf.progs[atype];
flags = cgrp->bpf.flags[atype];
@@ -1059,6 +1181,7 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
/* now can actually delete it from this cgroup list */
hlist_del(&pl->node);
+ cgrp->bpf.revisions[atype] += 1;
kfree(pl);
if (hlist_empty(progs))
@@ -1074,12 +1197,12 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
}
static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
- enum bpf_attach_type type)
+ enum bpf_attach_type type, u64 revision)
{
int ret;
cgroup_lock();
- ret = __cgroup_bpf_detach(cgrp, prog, NULL, type);
+ ret = __cgroup_bpf_detach(cgrp, prog, NULL, type, revision);
cgroup_unlock();
return ret;
}
@@ -1097,6 +1220,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
struct bpf_prog_array *effective;
int cnt, ret = 0, i;
int total_cnt = 0;
+ u64 revision = 0;
u32 flags;
if (effective_query && prog_attach_flags)
@@ -1134,6 +1258,10 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
return -EFAULT;
if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt)))
return -EFAULT;
+ if (!effective_query && from_atype == to_atype)
+ revision = cgrp->bpf.revisions[from_atype];
+ if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
+ return -EFAULT;
if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt)
/* return early if user requested only program count + flags */
return 0;
@@ -1216,7 +1344,8 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr,
}
ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL,
- attr->attach_type, attr->attach_flags);
+ attr->attach_type, attr->attach_flags,
+ attr->relative_fd, attr->expected_revision);
if (replace_prog)
bpf_prog_put(replace_prog);
@@ -1238,7 +1367,7 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
if (IS_ERR(prog))
prog = NULL;
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type);
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, attr->expected_revision);
if (prog)
bpf_prog_put(prog);
@@ -1267,7 +1396,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
}
WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
- cg_link->type));
+ cg_link->type, 0));
if (cg_link->type == BPF_LSM_CGROUP)
bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog);
@@ -1339,6 +1468,13 @@ static const struct bpf_link_ops bpf_cgroup_link_lops = {
.fill_link_info = bpf_cgroup_link_fill_link_info,
};
+#define BPF_F_LINK_ATTACH_MASK \
+ (BPF_F_ID | \
+ BPF_F_BEFORE | \
+ BPF_F_AFTER | \
+ BPF_F_PREORDER | \
+ BPF_F_LINK)
+
int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_link_primer link_primer;
@@ -1346,7 +1482,7 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
struct cgroup *cgrp;
int err;
- if (attr->link_create.flags)
+ if (attr->link_create.flags & (~BPF_F_LINK_ATTACH_MASK))
return -EINVAL;
cgrp = cgroup_get_from_fd(attr->link_create.target_fd);
@@ -1370,7 +1506,9 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
}
err = cgroup_bpf_attach(cgrp, NULL, NULL, link,
- link->type, BPF_F_ALLOW_MULTI);
+ link->type, BPF_F_ALLOW_MULTI | attr->link_create.flags,
+ attr->link_create.cgroup.relative_fd,
+ attr->link_create.cgroup.expected_revision);
if (err) {
bpf_link_cleanup(&link_primer);
goto out_put_cgroup;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c20babbf998f..e536a34a32c8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2102,14 +2102,15 @@ out:
#undef COND_JMP
/* ST, STX and LDX*/
ST_NOSPEC:
- /* Speculation barrier for mitigating Speculative Store Bypass.
- * In case of arm64, we rely on the firmware mitigation as
- * controlled via the ssbd kernel parameter. Whenever the
- * mitigation is enabled, it works for all of the kernel code
- * with no need to provide any additional instructions here.
- * In case of x86, we use 'lfence' insn for mitigation. We
- * reuse preexisting logic from Spectre v1 mitigation that
- * happens to produce the required code on x86 for v4 as well.
+ /* Speculation barrier for mitigating Speculative Store Bypass,
+ * Bounds-Check Bypass and Type Confusion. In case of arm64, we
+ * rely on the firmware mitigation as controlled via the ssbd
+ * kernel parameter. Whenever the mitigation is enabled, it
+ * works for all of the kernel code with no need to provide any
+ * additional instructions here. In case of x86, we use 'lfence'
+ * insn for mitigation. We reuse preexisting logic from Spectre
+ * v1 mitigation that happens to produce the required code on
+ * x86 for v4 as well.
*/
barrier_nospec();
CONT;
@@ -3034,6 +3035,21 @@ bool __weak bpf_jit_needs_zext(void)
return false;
}
+/* By default, enable the verifier's mitigations against Spectre v1 and v4 for
+ * all archs. The value returned must not change at runtime as there is
+ * currently no support for reloading programs that were loaded without
+ * mitigations.
+ */
+bool __weak bpf_jit_bypass_spec_v1(void)
+{
+ return false;
+}
+
+bool __weak bpf_jit_bypass_spec_v4(void)
+{
+ return false;
+}
+
/* Return true if the JIT inlines the call to the helper corresponding to
* the imm.
*
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b71e428ad936..2cdcf7b2c91e 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -24,6 +24,7 @@
#include <linux/bpf_mem_alloc.h>
#include <linux/kasan.h>
#include <linux/bpf_verifier.h>
+#include <linux/uaccess.h>
#include "../../lib/kstrtox.h"
@@ -3278,6 +3279,376 @@ __bpf_kfunc void __bpf_trap(void)
{
}
+/*
+ * Kfuncs for string operations.
+ *
+ * Since strings are not necessarily %NUL-terminated, we cannot directly call
+ * in-kernel implementations. Instead, we open-code the implementations using
+ * __get_kernel_nofault instead of plain dereference to make them safe.
+ */
+
+/**
+ * bpf_strcmp - Compare two strings
+ * @s1__ign: One string
+ * @s2__ign: Another string
+ *
+ * Return:
+ * * %0 - Strings are equal
+ * * %-1 - @s1__ign is smaller
+ * * %1 - @s2__ign is smaller
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of strings is too large
+ * * %-ERANGE - One of strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcmp(const char *s1__ign, const char *s2__ign)
+{
+ char c1, c2;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s1__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(s2__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&c1, s1__ign, char, err_out);
+ __get_kernel_nofault(&c2, s2__ign, char, err_out);
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (c1 == '\0')
+ return 0;
+ s1__ign++;
+ s2__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strnchr - Find a character in a length limited string
+ * @s__ign: The string to be searched
+ * @count: The number of characters to be searched
+ * @c: The character to search for
+ *
+ * Note that the %NUL-terminator is considered part of the string, and can
+ * be searched for.
+ *
+ * Return:
+ * * >=0 - Index of the first occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in the first @count characters of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnchr(const char *s__ign, size_t count, char c)
+{
+ char sc;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == c)
+ return i;
+ if (sc == '\0')
+ return -ENOENT;
+ s__ign++;
+ }
+ return i == XATTR_SIZE_MAX ? -E2BIG : -ENOENT;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strchr - Find the first occurrence of a character in a string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Note that the %NUL-terminator is considered part of the string, and can
+ * be searched for.
+ *
+ * Return:
+ * * >=0 - The index of the first occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strchr(const char *s__ign, char c)
+{
+ return bpf_strnchr(s__ign, XATTR_SIZE_MAX, c);
+}
+
+/**
+ * bpf_strchrnul - Find and return a character in a string, or end of string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Return:
+ * * >=0 - Index of the first occurrence of @c within @s__ign or index of
+ * the null byte at the end of @s__ign when @c is not found
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strchrnul(const char *s__ign, char c)
+{
+ char sc;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == '\0' || sc == c)
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strrchr - Find the last occurrence of a character in a string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Return:
+ * * >=0 - Index of the last occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strrchr(const char *s__ign, int c)
+{
+ char sc;
+ int i, last = -ENOENT;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == c)
+ last = i;
+ if (sc == '\0')
+ return last;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strlen - Calculate the length of a length-limited string
+ * @s__ign: The string
+ * @count: The maximum number of characters to count
+ *
+ * Return:
+ * * >=0 - The length of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnlen(const char *s__ign, size_t count)
+{
+ char c;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&c, s__ign, char, err_out);
+ if (c == '\0')
+ return i;
+ s__ign++;
+ }
+ return i == XATTR_SIZE_MAX ? -E2BIG : i;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strlen - Calculate the length of a string
+ * @s__ign: The string
+ *
+ * Return:
+ * * >=0 - The length of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strlen(const char *s__ign)
+{
+ return bpf_strnlen(s__ign, XATTR_SIZE_MAX);
+}
+
+/**
+ * bpf_strspn - Calculate the length of the initial substring of @s__ign which
+ * only contains letters in @accept__ign
+ * @s__ign: The string to be searched
+ * @accept__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - The length of the initial substring of @s__ign which only
+ * contains letters from @accept__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strspn(const char *s__ign, const char *accept__ign)
+{
+ char cs, ca;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(accept__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&cs, s__ign, char, err_out);
+ if (cs == '\0')
+ return i;
+ for (j = 0; j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&ca, accept__ign + j, char, err_out);
+ if (cs == ca || ca == '\0')
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (ca == '\0')
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * strcspn - Calculate the length of the initial substring of @s__ign which
+ * does not contain letters in @reject__ign
+ * @s__ign: The string to be searched
+ * @reject__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - The length of the initial substring of @s__ign which does not
+ * contain letters from @reject__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcspn(const char *s__ign, const char *reject__ign)
+{
+ char cs, cr;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(reject__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&cs, s__ign, char, err_out);
+ if (cs == '\0')
+ return i;
+ for (j = 0; j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&cr, reject__ign + j, char, err_out);
+ if (cs == cr || cr == '\0')
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (cr != '\0')
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strnstr - Find the first substring in a length-limited string
+ * @s1__ign: The string to be searched
+ * @s2__ign: The string to search for
+ * @len: the maximum number of characters to search
+ *
+ * Return:
+ * * >=0 - Index of the first character of the first occurrence of @s2__ign
+ * within the first @len characters of @s1__ign
+ * * %-ENOENT - @s2__ign not found in the first @len characters of @s1__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len)
+{
+ char c1, c2;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s1__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(s2__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&c2, s2__ign + j, char, err_out);
+ if (c2 == '\0')
+ return i;
+ __get_kernel_nofault(&c1, s1__ign + j, char, err_out);
+ if (c1 == '\0')
+ return -ENOENT;
+ if (c1 != c2)
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (i + j == len)
+ return -ENOENT;
+ s1__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strstr - Find the first substring in a string
+ * @s1__ign: The string to be searched
+ * @s2__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - Index of the first character of the first occurrence of @s2__ign
+ * within @s1__ign
+ * * %-ENOENT - @s2__ign is not a substring of @s1__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strstr(const char *s1__ign, const char *s2__ign)
+{
+ return bpf_strnstr(s1__ign, s2__ign, XATTR_SIZE_MAX);
+}
+
__bpf_kfunc_end_defs();
BTF_KFUNCS_START(generic_btf_ids)
@@ -3397,6 +3768,17 @@ BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPAB
BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
#endif
BTF_ID_FLAGS(func, __bpf_trap)
+BTF_ID_FLAGS(func, bpf_strcmp);
+BTF_ID_FLAGS(func, bpf_strchr);
+BTF_ID_FLAGS(func, bpf_strchrnul);
+BTF_ID_FLAGS(func, bpf_strnchr);
+BTF_ID_FLAGS(func, bpf_strrchr);
+BTF_ID_FLAGS(func, bpf_strlen);
+BTF_ID_FLAGS(func, bpf_strnlen);
+BTF_ID_FLAGS(func, bpf_strspn);
+BTF_ID_FLAGS(func, bpf_strcspn);
+BTF_ID_FLAGS(func, bpf_strstr);
+BTF_ID_FLAGS(func, bpf_strnstr);
BTF_KFUNCS_END(common_btf_ids)
static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 3969eb0382af..632d51b05fe9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -394,17 +394,10 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
return -EINVAL;
} else {
- u32 int_data;
-
/*
* Key is expected to be u64, which stores the cgroup_inode_id
*/
-
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data))
+ if (!btf_type_is_i64(key_type))
return -EINVAL;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dd5304c6ac3c..56500381c28a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3403,10 +3403,12 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
seq_printf(seq,
"attach_type:\t%d\n"
"target_obj_id:\t%u\n"
- "target_btf_id:\t%u\n",
+ "target_btf_id:\t%u\n"
+ "cookie:\t%llu\n",
tr_link->attach_type,
target_obj_id,
- target_btf_id);
+ target_btf_id,
+ tr_link->link.cookie);
}
static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
@@ -3416,6 +3418,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
container_of(link, struct bpf_tracing_link, link.link);
info->tracing.attach_type = tr_link->attach_type;
+ info->tracing.cookie = tr_link->link.cookie;
bpf_trampoline_unpack_key(tr_link->trampoline->key,
&info->tracing.target_obj_id,
&info->tracing.target_btf_id);
@@ -3651,8 +3654,10 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
container_of(link, struct bpf_raw_tp_link, link);
seq_printf(seq,
- "tp_name:\t%s\n",
- raw_tp_link->btp->tp->name);
+ "tp_name:\t%s\n"
+ "cookie:\t%llu\n",
+ raw_tp_link->btp->tp->name,
+ raw_tp_link->cookie);
}
static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen,
@@ -3688,6 +3693,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
return -EINVAL;
info->raw_tracepoint.tp_name_len = tp_len + 1;
+ info->raw_tracepoint.cookie = raw_tp_link->cookie;
if (!ubuf)
return 0;
@@ -3794,6 +3800,32 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
info->perf_event.kprobe.cookie = event->bpf_cookie;
return 0;
}
+
+static void bpf_perf_link_fdinfo_kprobe(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ const char *name;
+ int err;
+ u32 prog_id, type;
+ u64 offset, addr;
+ unsigned long missed;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &type, &name,
+ &offset, &addr, &missed);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "name:\t%s\n"
+ "offset:\t%#llx\n"
+ "missed:\t%lu\n"
+ "addr:\t%#llx\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, offset, missed, addr,
+ type == BPF_FD_TYPE_KRETPROBE ? "kretprobe" : "kprobe",
+ event->bpf_cookie);
+}
#endif
#ifdef CONFIG_UPROBE_EVENTS
@@ -3822,6 +3854,31 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset;
return 0;
}
+
+static void bpf_perf_link_fdinfo_uprobe(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ const char *name;
+ int err;
+ u32 prog_id, type;
+ u64 offset, ref_ctr_offset;
+ unsigned long missed;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &type, &name,
+ &offset, &ref_ctr_offset, &missed);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "name:\t%s\n"
+ "offset:\t%#llx\n"
+ "ref_ctr_offset:\t%#llx\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, offset, ref_ctr_offset,
+ type == BPF_FD_TYPE_URETPROBE ? "uretprobe" : "uprobe",
+ event->bpf_cookie);
+}
#endif
static int bpf_perf_link_fill_probe(const struct perf_event *event,
@@ -3890,10 +3947,79 @@ static int bpf_perf_link_fill_link_info(const struct bpf_link *link,
}
}
+static void bpf_perf_event_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ seq_printf(seq,
+ "type:\t%u\n"
+ "config:\t%llu\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ event->attr.type, event->attr.config,
+ "event", event->bpf_cookie);
+}
+
+static void bpf_tracepoint_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ int err;
+ const char *name;
+ u32 prog_id;
+
+ err = bpf_get_perf_event_info(event, &prog_id, NULL, &name, NULL,
+ NULL, NULL);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "tp_name:\t%s\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, "tracepoint", event->bpf_cookie);
+}
+
+static void bpf_probe_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE)
+ return bpf_perf_link_fdinfo_kprobe(event, seq);
+#endif
+
+#ifdef CONFIG_UPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE)
+ return bpf_perf_link_fdinfo_uprobe(event, seq);
+#endif
+}
+
+static void bpf_perf_link_show_fdinfo(const struct bpf_link *link,
+ struct seq_file *seq)
+{
+ 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;
+
+ switch (event->prog->type) {
+ case BPF_PROG_TYPE_PERF_EVENT:
+ return bpf_perf_event_link_show_fdinfo(event, seq);
+ case BPF_PROG_TYPE_TRACEPOINT:
+ return bpf_tracepoint_link_show_fdinfo(event, seq);
+ case BPF_PROG_TYPE_KPROBE:
+ return bpf_probe_link_show_fdinfo(event, seq);
+ default:
+ return;
+ }
+}
+
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,
+ .show_fdinfo = bpf_perf_link_show_fdinfo,
};
static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -4185,6 +4311,25 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
}
}
+static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype,
+ bool check_atype)
+{
+ switch (ptype) {
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ return true;
+ case BPF_PROG_TYPE_LSM:
+ return check_atype ? atype == BPF_LSM_CGROUP : true;
+ default:
+ return false;
+ }
+}
+
#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
#define BPF_F_ATTACH_MASK_BASE \
@@ -4215,6 +4360,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (bpf_mprog_supported(ptype)) {
if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
return -EINVAL;
+ } else if (is_cgroup_prog_type(ptype, 0, false)) {
+ if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG))
+ return -EINVAL;
} else {
if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
return -EINVAL;
@@ -4232,6 +4380,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
+ if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) {
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
+ goto out;
+ }
+
switch (ptype) {
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
@@ -4243,20 +4396,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_PROG_TYPE_FLOW_DISSECTOR:
ret = netns_bpf_prog_attach(attr, prog);
break;
- case BPF_PROG_TYPE_CGROUP_DEVICE:
- case BPF_PROG_TYPE_CGROUP_SKB:
- case BPF_PROG_TYPE_CGROUP_SOCK:
- case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
- case BPF_PROG_TYPE_CGROUP_SOCKOPT:
- case BPF_PROG_TYPE_CGROUP_SYSCTL:
- case BPF_PROG_TYPE_SOCK_OPS:
- case BPF_PROG_TYPE_LSM:
- if (ptype == BPF_PROG_TYPE_LSM &&
- prog->expected_attach_type != BPF_LSM_CGROUP)
- ret = -EINVAL;
- 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)
@@ -4267,7 +4406,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
default:
ret = -EINVAL;
}
-
+out:
if (ret)
bpf_prog_put(prog);
return ret;
@@ -4295,6 +4434,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
if (IS_ERR(prog))
return PTR_ERR(prog);
}
+ } else if (is_cgroup_prog_type(ptype, 0, false)) {
+ if (attr->attach_flags || attr->relative_fd)
+ return -EINVAL;
} else if (attr->attach_flags ||
attr->relative_fd ||
attr->expected_revision) {
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 9dbc31b25e3d..fa353c5d550f 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -83,6 +83,11 @@ struct tnum tnum_sub(struct tnum a, struct tnum b)
return TNUM(dv & ~mu, mu);
}
+struct tnum tnum_neg(struct tnum a)
+{
+ return tnum_sub(TNUM(0, 0), a);
+}
+
struct tnum tnum_and(struct tnum a, struct tnum b)
{
u64 alpha, beta, v;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index c4b1a98ff726..b1e358c16eeb 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -911,27 +911,32 @@ static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram
return bpf_prog_start_time();
}
-static void notrace update_prog_stats(struct bpf_prog *prog,
- u64 start)
+static void notrace __update_prog_stats(struct bpf_prog *prog, u64 start)
{
struct bpf_prog_stats *stats;
+ unsigned long flags;
+ u64 duration;
- if (static_branch_unlikely(&bpf_stats_enabled_key) &&
- /* static_key could be enabled in __bpf_prog_enter*
- * and disabled in __bpf_prog_exit*.
- * And vice versa.
- * Hence check that 'start' is valid.
- */
- start > NO_START_TIME) {
- u64 duration = sched_clock() - start;
- unsigned long flags;
-
- stats = this_cpu_ptr(prog->stats);
- flags = u64_stats_update_begin_irqsave(&stats->syncp);
- u64_stats_inc(&stats->cnt);
- u64_stats_add(&stats->nsecs, duration);
- u64_stats_update_end_irqrestore(&stats->syncp, flags);
- }
+ /*
+ * static_key could be enabled in __bpf_prog_enter* and disabled in
+ * __bpf_prog_exit*. And vice versa. Check that 'start' is valid.
+ */
+ if (start <= NO_START_TIME)
+ return;
+
+ duration = sched_clock() - start;
+ stats = this_cpu_ptr(prog->stats);
+ flags = u64_stats_update_begin_irqsave(&stats->syncp);
+ u64_stats_inc(&stats->cnt);
+ u64_stats_add(&stats->nsecs, duration);
+ u64_stats_update_end_irqrestore(&stats->syncp, flags);
+}
+
+static __always_inline void notrace update_prog_stats(struct bpf_prog *prog,
+ u64 start)
+{
+ if (static_branch_unlikely(&bpf_stats_enabled_key))
+ __update_prog_stats(prog, start);
}
static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 169845710c7e..dd670ba41667 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -44,6 +44,11 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#undef BPF_LINK_TYPE
};
+enum bpf_features {
+ BPF_FEAT_RDONLY_CAST_TO_VOID = 0,
+ __MAX_BPF_FEAT,
+};
+
struct bpf_mem_alloc bpf_global_percpu_ma;
static bool bpf_global_percpu_ma_set;
@@ -405,7 +410,8 @@ static bool reg_not_null(const struct bpf_reg_state *reg)
type == PTR_TO_MAP_KEY ||
type == PTR_TO_SOCK_COMMON ||
(type == PTR_TO_BTF_ID && is_trusted_reg(reg)) ||
- type == PTR_TO_MEM;
+ type == PTR_TO_MEM ||
+ type == CONST_PTR_TO_MAP;
}
static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
@@ -1403,7 +1409,7 @@ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size)
goto out;
alloc_size = kmalloc_size_roundup(size_mul(new_n, size));
- new_arr = krealloc(arr, alloc_size, GFP_KERNEL);
+ new_arr = krealloc(arr, alloc_size, GFP_KERNEL_ACCOUNT);
if (!new_arr) {
kfree(arr);
return NULL;
@@ -1420,7 +1426,7 @@ out:
static int copy_reference_state(struct bpf_verifier_state *dst, const struct bpf_verifier_state *src)
{
dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs,
- sizeof(struct bpf_reference_state), GFP_KERNEL);
+ sizeof(struct bpf_reference_state), GFP_KERNEL_ACCOUNT);
if (!dst->refs)
return -ENOMEM;
@@ -1439,7 +1445,7 @@ static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_st
size_t n = src->allocated_stack / BPF_REG_SIZE;
dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!dst->stack)
return -ENOMEM;
@@ -1647,7 +1653,7 @@ static void update_peak_states(struct bpf_verifier_env *env)
{
u32 cur_states;
- cur_states = env->explored_states_size + env->free_list_size;
+ cur_states = env->explored_states_size + env->free_list_size + env->num_backedges;
env->peak_states = max(env->peak_states, cur_states);
}
@@ -1659,6 +1665,13 @@ static void free_func_state(struct bpf_func_state *state)
kfree(state);
}
+static void clear_jmp_history(struct bpf_verifier_state *state)
+{
+ kfree(state->jmp_history);
+ state->jmp_history = NULL;
+ state->jmp_history_cnt = 0;
+}
+
static void free_verifier_state(struct bpf_verifier_state *state,
bool free_self)
{
@@ -1669,11 +1682,12 @@ static void free_verifier_state(struct bpf_verifier_state *state,
state->frame[i] = NULL;
}
kfree(state->refs);
+ clear_jmp_history(state);
if (free_self)
kfree(state);
}
-/* struct bpf_verifier_state->{parent,loop_entry} refer to states
+/* struct bpf_verifier_state->parent refers to states
* that are in either of env->{expored_states,free_list}.
* In both cases the state is contained in struct bpf_verifier_state_list.
*/
@@ -1684,37 +1698,24 @@ static struct bpf_verifier_state_list *state_parent_as_list(struct bpf_verifier_
return NULL;
}
-static struct bpf_verifier_state_list *state_loop_entry_as_list(struct bpf_verifier_state *st)
-{
- if (st->loop_entry)
- return container_of(st->loop_entry, struct bpf_verifier_state_list, state);
- return NULL;
-}
+static bool incomplete_read_marks(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st);
/* A state can be freed if it is no longer referenced:
* - is in the env->free_list;
* - has no children states;
- * - is not used as loop_entry.
- *
- * Freeing a state can make it's loop_entry free-able.
*/
static void maybe_free_verifier_state(struct bpf_verifier_env *env,
struct bpf_verifier_state_list *sl)
{
- struct bpf_verifier_state_list *loop_entry_sl;
-
- while (sl && sl->in_free_list &&
- sl->state.branches == 0 &&
- sl->state.used_as_loop_entry == 0) {
- loop_entry_sl = state_loop_entry_as_list(&sl->state);
- if (loop_entry_sl)
- loop_entry_sl->state.used_as_loop_entry--;
- list_del(&sl->node);
- free_verifier_state(&sl->state, false);
- kfree(sl);
- env->free_list_size--;
- sl = loop_entry_sl;
- }
+ if (!sl->in_free_list
+ || sl->state.branches != 0
+ || incomplete_read_marks(env, &sl->state))
+ return;
+ list_del(&sl->node);
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ env->free_list_size--;
}
/* copy verifier state from src to dst growing dst stack space
@@ -1733,6 +1734,13 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
struct bpf_func_state *dst;
int i, err;
+ dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
+ src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+ GFP_KERNEL_ACCOUNT);
+ if (!dst_state->jmp_history)
+ return -ENOMEM;
+ dst_state->jmp_history_cnt = src->jmp_history_cnt;
+
/* if dst has more stack frames then src frame, free them, this is also
* necessary in case of exceptional exits using bpf_throw.
*/
@@ -1750,17 +1758,14 @@ 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->insn_hist_start = src->insn_hist_start;
- dst_state->insn_hist_end = src->insn_hist_end;
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;
dst_state->may_goto_depth = src->may_goto_depth;
- dst_state->loop_entry = src->loop_entry;
+ dst_state->equal_state = src->equal_state;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
- dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL_ACCOUNT);
if (!dst)
return -ENOMEM;
dst_state->frame[i] = dst;
@@ -1799,173 +1804,232 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta
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:
- * h = entries[h]
- * return h
- *
- * # Update n's loop entry if h comes before n in current DFS path.
- * def update_loop_entry(n, h):
- * if h in path and depths[entries.get(n, n)] < depths[n]:
- * entries[n] = h1
+/* Return IP for a given frame in a call stack */
+static u32 frame_insn_idx(struct bpf_verifier_state *st, u32 frame)
+{
+ return frame == st->curframe
+ ? st->insn_idx
+ : st->frame[frame + 1]->callsite;
+}
+
+/* For state @st look for a topmost frame with frame_insn_idx() in some SCC,
+ * if such frame exists form a corresponding @callchain as an array of
+ * call sites leading to this frame and SCC id.
+ * E.g.:
*
- * 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 = entries.get(succ, None)
- * 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)
+ * void foo() { A: loop {... SCC#1 ...}; }
+ * void bar() { B: loop { C: foo(); ... SCC#2 ... }
+ * D: loop { E: foo(); ... SCC#3 ... } }
+ * void main() { F: bar(); }
*
- * 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().
+ * @callchain at (A) would be either (F,SCC#2) or (F,SCC#3) depending
+ * on @st frame call sites being (F,C,A) or (F,E,A).
*/
-static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_env *env,
- struct bpf_verifier_state *st)
+static bool compute_scc_callchain(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st,
+ struct bpf_scc_callchain *callchain)
{
- struct bpf_verifier_state *topmost = st->loop_entry;
- u32 steps = 0;
+ u32 i, scc, insn_idx;
- while (topmost && topmost->loop_entry) {
- if (verifier_bug_if(steps++ > st->dfs_depth, env, "infinite loop"))
- return ERR_PTR(-EFAULT);
- topmost = topmost->loop_entry;
+ memset(callchain, 0, sizeof(*callchain));
+ for (i = 0; i <= st->curframe; i++) {
+ insn_idx = frame_insn_idx(st, i);
+ scc = env->insn_aux_data[insn_idx].scc;
+ if (scc) {
+ callchain->scc = scc;
+ break;
+ } else if (i < st->curframe) {
+ callchain->callsites[i] = insn_idx;
+ } else {
+ return false;
+ }
}
- return topmost;
+ return true;
}
-static void update_loop_entry(struct bpf_verifier_env *env,
- struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr)
+/* Check if bpf_scc_visit instance for @callchain exists. */
+static struct bpf_scc_visit *scc_visit_lookup(struct bpf_verifier_env *env,
+ struct bpf_scc_callchain *callchain)
{
- /* The hdr->branches check decides between cases B and C in
- * comment for get_loop_entry(). If hdr->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 (hdr->branches && hdr->dfs_depth < (cur->loop_entry ?: cur)->dfs_depth) {
- if (cur->loop_entry) {
- cur->loop_entry->used_as_loop_entry--;
- maybe_free_verifier_state(env, state_loop_entry_as_list(cur));
- }
- cur->loop_entry = hdr;
- hdr->used_as_loop_entry++;
+ struct bpf_scc_info *info = env->scc_info[callchain->scc];
+ struct bpf_scc_visit *visits = info->visits;
+ u32 i;
+
+ if (!info)
+ return NULL;
+ for (i = 0; i < info->num_visits; i++)
+ if (memcmp(callchain, &visits[i].callchain, sizeof(*callchain)) == 0)
+ return &visits[i];
+ return NULL;
+}
+
+/* Allocate a new bpf_scc_visit instance corresponding to @callchain.
+ * Allocated instances are alive for a duration of the do_check_common()
+ * call and are freed by free_states().
+ */
+static struct bpf_scc_visit *scc_visit_alloc(struct bpf_verifier_env *env,
+ struct bpf_scc_callchain *callchain)
+{
+ struct bpf_scc_visit *visit;
+ struct bpf_scc_info *info;
+ u32 scc, num_visits;
+ u64 new_sz;
+
+ scc = callchain->scc;
+ info = env->scc_info[scc];
+ num_visits = info ? info->num_visits : 0;
+ new_sz = sizeof(*info) + sizeof(struct bpf_scc_visit) * (num_visits + 1);
+ info = kvrealloc(env->scc_info[scc], new_sz, GFP_KERNEL_ACCOUNT);
+ if (!info)
+ return NULL;
+ env->scc_info[scc] = info;
+ info->num_visits = num_visits + 1;
+ visit = &info->visits[num_visits];
+ memset(visit, 0, sizeof(*visit));
+ memcpy(&visit->callchain, callchain, sizeof(*callchain));
+ return visit;
+}
+
+/* Form a string '(callsite#1,callsite#2,...,scc)' in env->tmp_str_buf */
+static char *format_callchain(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain)
+{
+ char *buf = env->tmp_str_buf;
+ int i, delta = 0;
+
+ delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "(");
+ for (i = 0; i < ARRAY_SIZE(callchain->callsites); i++) {
+ if (!callchain->callsites[i])
+ break;
+ delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u,",
+ callchain->callsites[i]);
+ }
+ delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u)", callchain->scc);
+ return env->tmp_str_buf;
+}
+
+/* If callchain for @st exists (@st is in some SCC), ensure that
+ * bpf_scc_visit instance for this callchain exists.
+ * If instance does not exist or is empty, assign visit->entry_state to @st.
+ */
+static int maybe_enter_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain))
+ return 0;
+ visit = scc_visit_lookup(env, &callchain);
+ visit = visit ?: scc_visit_alloc(env, &callchain);
+ if (!visit)
+ return -ENOMEM;
+ if (!visit->entry_state) {
+ visit->entry_state = st;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "SCC enter %s\n", format_callchain(env, &callchain));
+ }
+ return 0;
+}
+
+static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit);
+
+/* If callchain for @st exists (@st is in some SCC), make it empty:
+ * - set visit->entry_state to NULL;
+ * - flush accumulated backedges.
+ */
+static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain))
+ return 0;
+ visit = scc_visit_lookup(env, &callchain);
+ if (!visit) {
+ verifier_bug(env, "scc exit: no visit info for call chain %s",
+ format_callchain(env, &callchain));
+ return -EFAULT;
+ }
+ if (visit->entry_state != st)
+ return 0;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "SCC exit %s\n", format_callchain(env, &callchain));
+ visit->entry_state = NULL;
+ env->num_backedges -= visit->num_backedges;
+ visit->num_backedges = 0;
+ update_peak_states(env);
+ return propagate_backedges(env, visit);
+}
+
+/* Lookup an bpf_scc_visit instance corresponding to @st callchain
+ * and add @backedge to visit->backedges. @st callchain must exist.
+ */
+static int add_scc_backedge(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st,
+ struct bpf_scc_backedge *backedge)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain)) {
+ verifier_bug(env, "add backedge: no SCC in verification path, insn_idx %d",
+ st->insn_idx);
+ return -EFAULT;
+ }
+ visit = scc_visit_lookup(env, &callchain);
+ if (!visit) {
+ verifier_bug(env, "add backedge: no visit info for call chain %s",
+ format_callchain(env, &callchain));
+ return -EFAULT;
+ }
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "SCC backedge %s\n", format_callchain(env, &callchain));
+ backedge->next = visit->backedges;
+ visit->backedges = backedge;
+ visit->num_backedges++;
+ env->num_backedges++;
+ update_peak_states(env);
+ return 0;
+}
+
+/* bpf_reg_state->live marks for registers in a state @st are incomplete,
+ * if state @st is in some SCC and not all execution paths starting at this
+ * SCC are fully explored.
+ */
+static bool incomplete_read_marks(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain))
+ return false;
+ visit = scc_visit_lookup(env, &callchain);
+ if (!visit)
+ return false;
+ return !!visit->backedges;
+}
+
+static void free_backedges(struct bpf_scc_visit *visit)
+{
+ struct bpf_scc_backedge *backedge, *next;
+
+ for (backedge = visit->backedges; backedge; backedge = next) {
+ free_verifier_state(&backedge->state, false);
+ next = backedge->next;
+ kvfree(backedge);
}
+ visit->backedges = NULL;
}
-static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+static int update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
{
struct bpf_verifier_state_list *sl = NULL, *parent_sl;
struct bpf_verifier_state *parent;
+ int err;
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(env, st->parent, st->loop_entry);
-
/* WARN_ON(br > 1) technically makes sense here,
* but see comment in push_stack(), hence:
*/
@@ -1974,6 +2038,9 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
br);
if (br)
break;
+ err = maybe_exit_scc(env, st);
+ if (err)
+ return err;
parent = st->parent;
parent_sl = state_parent_as_list(st);
if (sl)
@@ -1981,6 +2048,7 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
st = parent;
sl = parent_sl;
}
+ return 0;
}
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
@@ -2012,6 +2080,18 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
return 0;
}
+static bool error_recoverable_with_nospec(int err)
+{
+ /* Should only return true for non-fatal errors that are allowed to
+ * occur during speculative verification. For these we can insert a
+ * nospec and the program might still be accepted. Do not include
+ * something like ENOMEM because it is likely to re-occur for the next
+ * architectural path once it has been recovered-from in all speculative
+ * paths.
+ */
+ return err == -EPERM || err == -EACCES || err == -EINVAL;
+}
+
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx,
bool speculative)
@@ -2020,9 +2100,9 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
struct bpf_verifier_stack_elem *elem;
int err;
- elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+ elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL_ACCOUNT);
if (!elem)
- goto err;
+ return NULL;
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
@@ -2032,12 +2112,12 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
env->stack_size++;
err = copy_verifier_state(&elem->st, cur);
if (err)
- goto err;
+ return NULL;
elem->st.speculative |= speculative;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) {
verbose(env, "The sequence of %d jumps is too complex.\n",
env->stack_size);
- goto err;
+ return NULL;
}
if (elem->st.parent) {
++elem->st.parent->branches;
@@ -2052,12 +2132,6 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
*/
}
return &elem->st;
-err:
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- /* pop all elements and return */
- while (!pop_stack(env, NULL, NULL, false));
- return NULL;
}
#define CALLER_SAVED_REGS 6
@@ -2787,9 +2861,9 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
struct bpf_verifier_stack_elem *elem;
struct bpf_func_state *frame;
- elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+ elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL_ACCOUNT);
if (!elem)
- goto err;
+ return NULL;
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
@@ -2801,35 +2875,24 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
verbose(env,
"The sequence of %d jumps is too complex for async cb.\n",
env->stack_size);
- goto err;
+ return NULL;
}
/* Unlike push_stack() do not copy_verifier_state().
* The caller state doesn't matter.
* This is async callback. It starts in a fresh stack.
* Initialize it similar to do_check_common().
- * But we do need to make sure to not clobber insn_hist, so we keep
- * chaining insn_hist_start/insn_hist_end indices as for a normal
- * child state.
*/
elem->st.branches = 1;
elem->st.in_sleepable = is_sleepable;
- elem->st.insn_hist_start = env->cur_state->insn_hist_end;
- elem->st.insn_hist_end = elem->st.insn_hist_start;
- frame = kzalloc(sizeof(*frame), GFP_KERNEL);
+ frame = kzalloc(sizeof(*frame), GFP_KERNEL_ACCOUNT);
if (!frame)
- goto err;
+ return NULL;
init_func_state(env, frame,
BPF_MAIN_FUNC /* callsite */,
0 /* frameno within this callchain */,
subprog /* subprog number within this prog */);
elem->st.frame[0] = frame;
return &elem->st;
-err:
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- /* pop all elements and return */
- while (!pop_stack(env, NULL, NULL, false));
- return NULL;
}
@@ -3167,7 +3230,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
return -EINVAL;
}
- tab = kzalloc(sizeof(*tab), GFP_KERNEL);
+ tab = kzalloc(sizeof(*tab), GFP_KERNEL_ACCOUNT);
if (!tab)
return -ENOMEM;
prog_aux->kfunc_tab = tab;
@@ -3183,7 +3246,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
return 0;
if (!btf_tab && offset) {
- btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL);
+ btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL_ACCOUNT);
if (!btf_tab)
return -ENOMEM;
prog_aux->kfunc_btf_tab = btf_tab;
@@ -3843,10 +3906,11 @@ static void linked_regs_unpack(u64 val, struct linked_regs *s)
}
/* for any branch, call, exit record the history of jmps in the given state */
-static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
- int insn_flags, u64 linked_regs)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+ int insn_flags, u64 linked_regs)
{
- struct bpf_insn_hist_entry *p;
+ u32 cnt = cur->jmp_history_cnt;
+ struct bpf_jmp_history_entry *p;
size_t alloc_size;
/* combine instruction flags if we already recorded this instruction */
@@ -3866,32 +3930,29 @@ static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_s
return 0;
}
- if (cur->insn_hist_end + 1 > env->insn_hist_cap) {
- alloc_size = size_mul(cur->insn_hist_end + 1, sizeof(*p));
- p = kvrealloc(env->insn_hist, alloc_size, GFP_USER);
- if (!p)
- return -ENOMEM;
- env->insn_hist = p;
- env->insn_hist_cap = alloc_size / sizeof(*p);
- }
+ cnt++;
+ alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
+ p = krealloc(cur->jmp_history, alloc_size, GFP_KERNEL_ACCOUNT);
+ if (!p)
+ return -ENOMEM;
+ cur->jmp_history = p;
- p = &env->insn_hist[cur->insn_hist_end];
+ p = &cur->jmp_history[cnt - 1];
p->idx = env->insn_idx;
p->prev_idx = env->prev_insn_idx;
p->flags = insn_flags;
p->linked_regs = linked_regs;
-
- cur->insn_hist_end++;
+ cur->jmp_history_cnt = cnt;
env->cur_hist_ent = p;
return 0;
}
-static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *env,
- u32 hist_start, u32 hist_end, int insn_idx)
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+ u32 hist_end, int insn_idx)
{
- if (hist_end > hist_start && env->insn_hist[hist_end - 1].idx == insn_idx)
- return &env->insn_hist[hist_end - 1];
+ if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+ return &st->jmp_history[hist_end - 1];
return NULL;
}
@@ -3908,26 +3969,25 @@ static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *
* history entry recording a jump from last instruction of parent state and
* first instruction of given state.
*/
-static int get_prev_insn_idx(const struct bpf_verifier_env *env,
- struct bpf_verifier_state *st,
- int insn_idx, u32 hist_start, u32 *hist_endp)
+static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
+ u32 *history)
{
- u32 hist_end = *hist_endp;
- u32 cnt = hist_end - hist_start;
+ u32 cnt = *history;
- if (insn_idx == st->first_insn_idx) {
+ if (i == st->first_insn_idx) {
if (cnt == 0)
return -ENOENT;
- if (cnt == 1 && env->insn_hist[hist_start].idx == insn_idx)
+ if (cnt == 1 && st->jmp_history[0].idx == i)
return -ENOENT;
}
- if (cnt && env->insn_hist[hist_end - 1].idx == insn_idx) {
- (*hist_endp)--;
- return env->insn_hist[hist_end - 1].prev_idx;
+ if (cnt && st->jmp_history[cnt - 1].idx == i) {
+ i = st->jmp_history[cnt - 1].prev_idx;
+ (*history)--;
} else {
- return insn_idx - 1;
+ i--;
}
+ return i;
}
static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
@@ -4108,7 +4168,7 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
/* If any register R in hist->linked_regs is marked as precise in bt,
* do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs.
*/
-static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_insn_hist_entry *hist)
+static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist)
{
struct linked_regs linked_regs;
bool some_precise = false;
@@ -4153,7 +4213,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
* - *was* processed previously during backtracking.
*/
static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
- struct bpf_insn_hist_entry *hist, struct backtrack_state *bt)
+ struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
{
struct bpf_insn *insn = env->prog->insnsi + idx;
u8 class = BPF_CLASS(insn->code);
@@ -4571,7 +4631,7 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
* SCALARS, as well as any other registers and slots that contribute to
* a tracked state of given registers/stack slots, depending on specific BPF
* assembly instructions (see backtrack_insns() for exact instruction handling
- * logic). This backtracking relies on recorded insn_hist and is able to
+ * logic). This backtracking relies on recorded jmp_history and is able to
* traverse entire chain of parent states. This process ends only when all the
* necessary registers/slots and their transitive dependencies are marked as
* precise.
@@ -4651,23 +4711,27 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
* mark_all_scalars_imprecise() to hopefully get more permissive and generic
* finalized states which help in short circuiting more future states.
*/
-static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
+static int __mark_chain_precision(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *starting_state,
+ int regno,
+ bool *changed)
{
+ struct bpf_verifier_state *st = starting_state;
struct backtrack_state *bt = &env->bt;
- struct bpf_verifier_state *st = env->cur_state;
int first_idx = st->first_insn_idx;
- int last_idx = env->insn_idx;
+ int last_idx = starting_state->insn_idx;
int subseq_idx = -1;
struct bpf_func_state *func;
+ bool tmp, skip_first = true;
struct bpf_reg_state *reg;
- bool skip_first = true;
int i, fr, err;
if (!env->bpf_capable)
return 0;
+ changed = changed ?: &tmp;
/* set frame number from which we are starting to backtrack */
- bt_init(bt, env->cur_state->curframe);
+ bt_init(bt, starting_state->curframe);
/* Do sanity checks against current state of register and/or stack
* slot, but don't set precise flag in current state, as precision
@@ -4688,9 +4752,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
for (;;) {
DECLARE_BITMAP(mask, 64);
- u32 hist_start = st->insn_hist_start;
- u32 hist_end = st->insn_hist_end;
- struct bpf_insn_hist_entry *hist;
+ u32 history = st->jmp_history_cnt;
+ struct bpf_jmp_history_entry *hist;
if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4712,8 +4775,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
for_each_set_bit(i, mask, 32) {
reg = &st->frame[0]->regs[i];
bt_clear_reg(bt, i);
- if (reg->type == SCALAR_VALUE)
+ if (reg->type == SCALAR_VALUE) {
reg->precise = true;
+ *changed = true;
+ }
}
return 0;
}
@@ -4728,11 +4793,11 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
err = 0;
skip_first = false;
} else {
- hist = get_insn_hist_entry(env, hist_start, hist_end, i);
+ hist = get_jmp_hist_entry(st, history, i);
err = backtrack_insn(env, i, subseq_idx, hist, bt);
}
if (err == -ENOTSUPP) {
- mark_all_scalars_precise(env, env->cur_state);
+ mark_all_scalars_precise(env, starting_state);
bt_reset(bt);
return 0;
} else if (err) {
@@ -4745,7 +4810,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
*/
return 0;
subseq_idx = i;
- i = get_prev_insn_idx(env, st, i, hist_start, &hist_end);
+ i = get_prev_insn_idx(st, i, &history);
if (i == -ENOENT)
break;
if (i >= env->prog->len) {
@@ -4772,10 +4837,12 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bt_clear_frame_reg(bt, fr, i);
continue;
}
- if (reg->precise)
+ if (reg->precise) {
bt_clear_frame_reg(bt, fr, i);
- else
+ } else {
reg->precise = true;
+ *changed = true;
+ }
}
bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
@@ -4790,10 +4857,12 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
continue;
}
reg = &func->stack[i].spilled_ptr;
- if (reg->precise)
+ if (reg->precise) {
bt_clear_frame_slot(bt, fr, i);
- else
+ } else {
reg->precise = true;
+ *changed = true;
+ }
}
if (env->log.level & BPF_LOG_LEVEL2) {
fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
@@ -4820,7 +4889,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
* fallback to marking all precise
*/
if (!bt_empty(bt)) {
- mark_all_scalars_precise(env, env->cur_state);
+ mark_all_scalars_precise(env, starting_state);
bt_reset(bt);
}
@@ -4829,15 +4898,16 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
int mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
- return __mark_chain_precision(env, regno);
+ return __mark_chain_precision(env, env->cur_state, regno, NULL);
}
/* mark_chain_precision_batch() assumes that env->bt is set in the caller to
* desired reg and stack masks across all relevant frames
*/
-static int mark_chain_precision_batch(struct bpf_verifier_env *env)
+static int mark_chain_precision_batch(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *starting_state)
{
- return __mark_chain_precision(env, -1);
+ return __mark_chain_precision(env, starting_state, -1, NULL);
}
static bool is_spillable_regtype(enum bpf_reg_type type)
@@ -5026,7 +5096,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
}
if (sanitize)
- env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+ env->insn_aux_data[insn_idx].nospec_result = true;
}
err = destroy_if_dynptr_stack_slot(env, state, spi);
@@ -5109,7 +5179,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
}
if (insn_flags)
- return push_insn_history(env, env->cur_state, insn_flags, 0);
+ return push_jmp_history(env, env->cur_state, insn_flags, 0);
return 0;
}
@@ -5416,7 +5486,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
insn_flags = 0; /* we are not restoring spilled register */
}
if (insn_flags)
- return push_insn_history(env, env->cur_state, insn_flags, 0);
+ return push_jmp_history(env, env->cur_state, insn_flags, 0);
return 0;
}
@@ -7469,6 +7539,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
}
} else if (base_type(reg->type) == PTR_TO_MEM) {
bool rdonly_mem = type_is_rdonly_mem(reg->type);
+ bool rdonly_untrusted = rdonly_mem && (reg->type & PTR_UNTRUSTED);
if (type_may_be_null(reg->type)) {
verbose(env, "R%d invalid mem access '%s'\n", regno,
@@ -7488,8 +7559,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
return -EACCES;
}
- err = check_mem_region_access(env, regno, off, size,
- reg->mem_size, false);
+ /*
+ * Accesses to untrusted PTR_TO_MEM are done through probe
+ * instructions, hence no need to check bounds in that case.
+ */
+ if (!rdonly_untrusted)
+ err = check_mem_region_access(env, regno, off, size,
+ reg->mem_size, false);
if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
@@ -8953,7 +9029,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->type\n");
- return -EACCES;
+ return -EFAULT;
}
switch (meta->map_ptr->map_type) {
@@ -9489,7 +9565,7 @@ static int get_constant_map_key(struct bpf_verifier_env *env,
* to prevent pruning on it.
*/
bt_set_frame_slot(&env->bt, key->frameno, spi);
- err = mark_chain_precision_batch(env);
+ err = mark_chain_precision_batch(env, env->cur_state);
if (err < 0)
return err;
@@ -9641,7 +9717,7 @@ skip_type_check:
* that kernel subsystem misconfigured verifier
*/
verbose(env, "invalid map_ptr to access map->key\n");
- return -EACCES;
+ return -EFAULT;
}
key_size = meta->map_ptr->key_size;
err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL);
@@ -9668,7 +9744,7 @@ skip_type_check:
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->value\n");
- return -EACCES;
+ return -EFAULT;
}
meta->raw_mode = arg_type & MEM_UNINIT;
err = check_helper_mem_access(env, regno, meta->map_ptr->value_size,
@@ -10278,7 +10354,7 @@ static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int calls
}
caller = state->frame[state->curframe];
- callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+ callee = kzalloc(sizeof(*callee), GFP_KERNEL_ACCOUNT);
if (!callee)
return -ENOMEM;
state->frame[state->curframe + 1] = callee;
@@ -10964,7 +11040,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
if (map == NULL) {
verbose(env, "kernel subsystem misconfigured verifier\n");
- return -EINVAL;
+ return -EFAULT;
}
/* In case of read-only, some additional restrictions
@@ -11003,7 +11079,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) {
verbose(env, "kernel subsystem misconfigured verifier\n");
- return -EINVAL;
+ return -EFAULT;
}
reg = &regs[BPF_REG_3];
@@ -11145,7 +11221,7 @@ static int check_get_func_ip(struct bpf_verifier_env *env)
return -ENOTSUPP;
}
-static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env)
{
return &env->insn_aux_data[env->insn_idx];
}
@@ -11257,7 +11333,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
func_id_name(func_id), func_id);
- return -EINVAL;
+ return -EFAULT;
}
memset(&meta, 0, sizeof(meta));
@@ -11559,7 +11635,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (meta.map_ptr == NULL) {
verbose(env,
"kernel subsystem misconfigured verifier\n");
- return -EINVAL;
+ return -EFAULT;
}
if (func_id == BPF_FUNC_map_lookup_elem &&
@@ -11652,7 +11728,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
verbose(env, "verifier internal error:");
verbose(env, "func %s has non-overwritten BPF_PTR_POISON return type\n",
func_id_name(func_id));
- return -EINVAL;
+ return -EFAULT;
}
ret_btf = btf_vmlinux;
ret_btf_id = *fn->ret_btf_id;
@@ -13536,16 +13612,24 @@ static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_ca
regs[BPF_REG_0].btf_id = meta->ret_btf_id;
} else if (meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
ret_t = btf_type_by_id(desc_btf, meta->arg_constant.value);
- if (!ret_t || !btf_type_is_struct(ret_t)) {
+ if (!ret_t) {
+ verbose(env, "Unknown type ID %lld passed to kfunc bpf_rdonly_cast\n",
+ meta->arg_constant.value);
+ return -EINVAL;
+ } else if (btf_type_is_struct(ret_t)) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
+ regs[BPF_REG_0].btf = desc_btf;
+ regs[BPF_REG_0].btf_id = meta->arg_constant.value;
+ } else if (btf_type_is_void(ret_t)) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED;
+ regs[BPF_REG_0].mem_size = 0;
+ } else {
verbose(env,
- "kfunc bpf_rdonly_cast type ID argument must be of a struct\n");
+ "kfunc bpf_rdonly_cast type ID argument must be of a struct or void\n");
return -EINVAL;
}
-
- mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
- regs[BPF_REG_0].btf = desc_btf;
- regs[BPF_REG_0].btf_id = meta->arg_constant.value;
} else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice] ||
meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) {
enum bpf_type_flag type_flag = get_dynptr_type_flag(meta->initialized_dynptr.type);
@@ -14013,7 +14097,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
const struct bpf_insn *insn)
{
- return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
+ return env->bypass_spec_v1 ||
+ BPF_SRC(insn->code) == BPF_K ||
+ cur_aux(env)->nospec;
}
static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
@@ -14213,7 +14299,7 @@ static int sanitize_err(struct bpf_verifier_env *env,
case REASON_STACK:
verbose(env, "R%d could not be pushed for speculative verification, %s\n",
dst, err);
- break;
+ return -ENOMEM;
default:
verbose(env, "verifier internal error: unknown reason (%d)\n",
reason);
@@ -14283,7 +14369,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env,
}
break;
default:
- break;
+ return -EOPNOTSUPP;
}
return 0;
@@ -14310,7 +14396,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
struct bpf_sanitize_info info = {};
u8 opcode = BPF_OP(insn->code);
u32 dst = insn->dst_reg;
- int ret;
+ int ret, bounds_ret;
dst_reg = &regs[dst];
@@ -14342,6 +14428,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
return -EACCES;
}
+ /*
+ * Accesses to untrusted PTR_TO_MEM are done through probe
+ * instructions, hence no need to track offsets.
+ */
+ if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED))
+ return 0;
+
switch (base_type(ptr_reg->type)) {
case PTR_TO_CTX:
case PTR_TO_MAP_VALUE:
@@ -14510,11 +14603,19 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
return -EINVAL;
reg_bounds_sync(dst_reg);
- if (sanitize_check_bounds(env, insn, dst_reg) < 0)
- return -EACCES;
+ bounds_ret = sanitize_check_bounds(env, insn, dst_reg);
+ if (bounds_ret == -EACCES)
+ return bounds_ret;
if (sanitize_needed(opcode)) {
ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
&info, true);
+ if (verifier_bug_if(!can_skip_alu_sanitation(env, insn)
+ && !env->cur_state->speculative
+ && bounds_ret
+ && !ret,
+ env, "Pointer type unsupported by sanitize_check_bounds() not rejected by retrieve_ptr_limit() as required")) {
+ return -EFAULT;
+ }
if (ret < 0)
return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
@@ -14529,14 +14630,25 @@ static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
s32 *dst_smax = &dst_reg->s32_max_value;
u32 *dst_umin = &dst_reg->u32_min_value;
u32 *dst_umax = &dst_reg->u32_max_value;
+ u32 umin_val = src_reg->u32_min_value;
+ u32 umax_val = src_reg->u32_max_value;
+ bool min_overflow, max_overflow;
if (check_add_overflow(*dst_smin, src_reg->s32_min_value, dst_smin) ||
check_add_overflow(*dst_smax, src_reg->s32_max_value, dst_smax)) {
*dst_smin = S32_MIN;
*dst_smax = S32_MAX;
}
- if (check_add_overflow(*dst_umin, src_reg->u32_min_value, dst_umin) ||
- check_add_overflow(*dst_umax, src_reg->u32_max_value, dst_umax)) {
+
+ /* If either all additions overflow or no additions overflow, then
+ * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax =
+ * dst_umax + src_umax. Otherwise (some additions overflow), set
+ * the output bounds to unbounded.
+ */
+ min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin);
+ max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax);
+
+ if (!min_overflow && max_overflow) {
*dst_umin = 0;
*dst_umax = U32_MAX;
}
@@ -14549,14 +14661,25 @@ static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
s64 *dst_smax = &dst_reg->smax_value;
u64 *dst_umin = &dst_reg->umin_value;
u64 *dst_umax = &dst_reg->umax_value;
+ u64 umin_val = src_reg->umin_value;
+ u64 umax_val = src_reg->umax_value;
+ bool min_overflow, max_overflow;
if (check_add_overflow(*dst_smin, src_reg->smin_value, dst_smin) ||
check_add_overflow(*dst_smax, src_reg->smax_value, dst_smax)) {
*dst_smin = S64_MIN;
*dst_smax = S64_MAX;
}
- if (check_add_overflow(*dst_umin, src_reg->umin_value, dst_umin) ||
- check_add_overflow(*dst_umax, src_reg->umax_value, dst_umax)) {
+
+ /* If either all additions overflow or no additions overflow, then
+ * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax =
+ * dst_umax + src_umax. Otherwise (some additions overflow), set
+ * the output bounds to unbounded.
+ */
+ min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin);
+ max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax);
+
+ if (!min_overflow && max_overflow) {
*dst_umin = 0;
*dst_umax = U64_MAX;
}
@@ -14567,8 +14690,11 @@ static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
{
s32 *dst_smin = &dst_reg->s32_min_value;
s32 *dst_smax = &dst_reg->s32_max_value;
+ u32 *dst_umin = &dst_reg->u32_min_value;
+ u32 *dst_umax = &dst_reg->u32_max_value;
u32 umin_val = src_reg->u32_min_value;
u32 umax_val = src_reg->u32_max_value;
+ bool min_underflow, max_underflow;
if (check_sub_overflow(*dst_smin, src_reg->s32_max_value, dst_smin) ||
check_sub_overflow(*dst_smax, src_reg->s32_min_value, dst_smax)) {
@@ -14576,14 +14702,18 @@ static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
*dst_smin = S32_MIN;
*dst_smax = S32_MAX;
}
- if (dst_reg->u32_min_value < umax_val) {
- /* Overflow possible, we know nothing */
- dst_reg->u32_min_value = 0;
- dst_reg->u32_max_value = U32_MAX;
- } else {
- /* Cannot overflow (as long as bounds are consistent) */
- dst_reg->u32_min_value -= umax_val;
- dst_reg->u32_max_value -= umin_val;
+
+ /* If either all subtractions underflow or no subtractions
+ * underflow, it is okay to set: dst_umin = dst_umin - src_umax,
+ * dst_umax = dst_umax - src_umin. Otherwise (some subtractions
+ * underflow), set the output bounds to unbounded.
+ */
+ min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin);
+ max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax);
+
+ if (min_underflow && !max_underflow) {
+ *dst_umin = 0;
+ *dst_umax = U32_MAX;
}
}
@@ -14592,8 +14722,11 @@ static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
{
s64 *dst_smin = &dst_reg->smin_value;
s64 *dst_smax = &dst_reg->smax_value;
+ u64 *dst_umin = &dst_reg->umin_value;
+ u64 *dst_umax = &dst_reg->umax_value;
u64 umin_val = src_reg->umin_value;
u64 umax_val = src_reg->umax_value;
+ bool min_underflow, max_underflow;
if (check_sub_overflow(*dst_smin, src_reg->smax_value, dst_smin) ||
check_sub_overflow(*dst_smax, src_reg->smin_value, dst_smax)) {
@@ -14601,14 +14734,18 @@ static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
*dst_smin = S64_MIN;
*dst_smax = S64_MAX;
}
- if (dst_reg->umin_value < umax_val) {
- /* Overflow possible, we know nothing */
- dst_reg->umin_value = 0;
- dst_reg->umax_value = U64_MAX;
- } else {
- /* Cannot overflow (as long as bounds are consistent) */
- dst_reg->umin_value -= umax_val;
- dst_reg->umax_value -= umin_val;
+
+ /* If either all subtractions underflow or no subtractions
+ * underflow, it is okay to set: dst_umin = dst_umin - src_umax,
+ * dst_umax = dst_umax - src_umin. Otherwise (some subtractions
+ * underflow), set the output bounds to unbounded.
+ */
+ min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin);
+ max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax);
+
+ if (min_underflow && !max_underflow) {
+ *dst_umin = 0;
+ *dst_umax = U64_MAX;
}
}
@@ -15070,6 +15207,7 @@ static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn,
switch (BPF_OP(insn->code)) {
case BPF_ADD:
case BPF_SUB:
+ case BPF_NEG:
case BPF_AND:
case BPF_XOR:
case BPF_OR:
@@ -15138,6 +15276,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
scalar_min_max_sub(dst_reg, &src_reg);
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
break;
+ case BPF_NEG:
+ env->fake_reg[0] = *dst_reg;
+ __mark_reg_known(dst_reg, 0);
+ scalar32_min_max_sub(dst_reg, &env->fake_reg[0]);
+ scalar_min_max_sub(dst_reg, &env->fake_reg[0]);
+ dst_reg->var_off = tnum_neg(env->fake_reg[0].var_off);
+ break;
case BPF_MUL:
dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
scalar32_min_max_mul(dst_reg, &src_reg);
@@ -15277,12 +15422,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
if (WARN_ON_ONCE(ptr_reg)) {
print_verifier_state(env, vstate, vstate->curframe, true);
verbose(env, "verifier internal error: unexpected ptr_reg\n");
- return -EINVAL;
+ return -EFAULT;
}
if (WARN_ON(!src_reg)) {
print_verifier_state(env, vstate, vstate->curframe, true);
verbose(env, "verifier internal error: no src_reg\n");
- return -EINVAL;
+ return -EFAULT;
}
err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
if (err)
@@ -15361,7 +15506,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* check dest operand */
- err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ if (opcode == BPF_NEG) {
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+ err = err ?: adjust_scalar_min_max_vals(env, insn,
+ &regs[insn->dst_reg],
+ regs[insn->dst_reg]);
+ } else {
+ err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ }
if (err)
return err;
@@ -16472,7 +16624,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
if (insn_flags) {
- err = push_insn_history(env, this_branch, insn_flags, 0);
+ err = push_jmp_history(env, this_branch, insn_flags, 0);
if (err)
return err;
}
@@ -16530,7 +16682,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
collect_linked_regs(this_branch, dst_reg->id, &linked_regs);
if (linked_regs.cnt > 1) {
- err = push_insn_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
+ err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
if (err)
return err;
}
@@ -16728,7 +16880,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
dst_reg->type = CONST_PTR_TO_MAP;
} else {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
return 0;
@@ -16775,7 +16927,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (!env->ops->gen_ld_abs) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
@@ -17605,17 +17757,18 @@ static int check_cfg(struct bpf_verifier_env *env)
int *insn_stack, *insn_state, *insn_postorder;
int ex_insn_beg, i, ret = 0;
- insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
if (!insn_state)
return -ENOMEM;
- insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
if (!insn_stack) {
kvfree(insn_state);
return -ENOMEM;
}
- insn_postorder = env->cfg.insn_postorder = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_postorder = env->cfg.insn_postorder =
+ kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
if (!insn_postorder) {
kvfree(insn_state);
kvfree(insn_stack);
@@ -17749,7 +17902,7 @@ static int check_btf_func_early(struct bpf_verifier_env *env,
urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
min_size = min_t(u32, krec_size, urec_size);
- krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
+ krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!krecord)
return -ENOMEM;
@@ -17849,7 +18002,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
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);
+ info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!info_aux)
return -ENOMEM;
@@ -17935,7 +18088,7 @@ static int check_btf_line(struct bpf_verifier_env *env,
* pass in a smaller bpf_line_info object.
*/
linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info),
- GFP_KERNEL | __GFP_NOWARN);
+ GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!linfo)
return -ENOMEM;
@@ -18258,10 +18411,6 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
{
int i;
- if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
- /* all regs in this state in all frames were already marked */
- return;
-
for (i = 0; i <= st->curframe; i++)
clean_func_state(env, st->frame[i]);
}
@@ -18301,7 +18450,6 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
static void clean_live_states(struct bpf_verifier_env *env, int insn,
struct bpf_verifier_state *cur)
{
- struct bpf_verifier_state *loop_entry;
struct bpf_verifier_state_list *sl;
struct list_head *pos, *head;
@@ -18310,12 +18458,14 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn,
sl = container_of(pos, struct bpf_verifier_state_list, node);
if (sl->state.branches)
continue;
- loop_entry = get_loop_entry(env, &sl->state);
- if (!IS_ERR_OR_NULL(loop_entry) && loop_entry->branches)
- continue;
if (sl->state.insn_idx != insn ||
!same_callsites(&sl->state, cur))
continue;
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE)
+ /* all regs in this state in all frames were already marked */
+ continue;
+ if (incomplete_read_marks(env, &sl->state))
+ continue;
clean_verifier_state(env, &sl->state);
}
}
@@ -18762,9 +18912,7 @@ static bool states_equal(struct bpf_verifier_env *env,
* and all frame states need to be equivalent
*/
for (i = 0; i <= old->curframe; i++) {
- insn_idx = i == old->curframe
- ? env->insn_idx
- : old->frame[i + 1]->callsite;
+ insn_idx = frame_insn_idx(old, i);
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
if (!func_states_equal(env, old->frame[i], cur->frame[i], insn_idx, exact))
@@ -18811,12 +18959,15 @@ static int propagate_liveness_reg(struct bpf_verifier_env *env,
*/
static int propagate_liveness(struct bpf_verifier_env *env,
const struct bpf_verifier_state *vstate,
- struct bpf_verifier_state *vparent)
+ struct bpf_verifier_state *vparent,
+ bool *changed)
{
struct bpf_reg_state *state_reg, *parent_reg;
struct bpf_func_state *state, *parent;
int i, frame, err = 0;
+ bool tmp = false;
+ changed = changed ?: &tmp;
if (vparent->curframe != vstate->curframe) {
WARN(1, "propagate_live: parent frame %d current frame %d\n",
vparent->curframe, vstate->curframe);
@@ -18835,6 +18986,7 @@ static int propagate_liveness(struct bpf_verifier_env *env,
&parent_reg[i]);
if (err < 0)
return err;
+ *changed |= err > 0;
if (err == REG_LIVE_READ64)
mark_insn_zext(env, &parent_reg[i]);
}
@@ -18846,6 +18998,7 @@ static int propagate_liveness(struct bpf_verifier_env *env,
state_reg = &state->stack[i].spilled_ptr;
err = propagate_liveness_reg(env, state_reg,
parent_reg);
+ *changed |= err > 0;
if (err < 0)
return err;
}
@@ -18857,7 +19010,9 @@ static int propagate_liveness(struct bpf_verifier_env *env,
* propagate them into the current state
*/
static int propagate_precision(struct bpf_verifier_env *env,
- const struct bpf_verifier_state *old)
+ const struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur,
+ bool *changed)
{
struct bpf_reg_state *state_reg;
struct bpf_func_state *state;
@@ -18905,13 +19060,53 @@ static int propagate_precision(struct bpf_verifier_env *env,
verbose(env, "\n");
}
- err = mark_chain_precision_batch(env);
+ err = __mark_chain_precision(env, cur, -1, changed);
if (err < 0)
return err;
return 0;
}
+#define MAX_BACKEDGE_ITERS 64
+
+/* Propagate read and precision marks from visit->backedges[*].state->equal_state
+ * to corresponding parent states of visit->backedges[*].state until fixed point is reached,
+ * then free visit->backedges.
+ * After execution of this function incomplete_read_marks() will return false
+ * for all states corresponding to @visit->callchain.
+ */
+static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit)
+{
+ struct bpf_scc_backedge *backedge;
+ struct bpf_verifier_state *st;
+ bool changed;
+ int i, err;
+
+ i = 0;
+ do {
+ if (i++ > MAX_BACKEDGE_ITERS) {
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "%s: too many iterations\n", __func__);
+ for (backedge = visit->backedges; backedge; backedge = backedge->next)
+ mark_all_scalars_precise(env, &backedge->state);
+ break;
+ }
+ changed = false;
+ for (backedge = visit->backedges; backedge; backedge = backedge->next) {
+ st = &backedge->state;
+ err = propagate_liveness(env, st->equal_state, st, &changed);
+ if (err)
+ return err;
+ err = propagate_precision(env, st->equal_state, st, &changed);
+ if (err)
+ return err;
+ }
+ } while (changed);
+
+ free_backedges(visit);
+ return 0;
+}
+
static bool states_maybe_looping(struct bpf_verifier_state *old,
struct bpf_verifier_state *cur)
{
@@ -19021,14 +19216,14 @@ 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;
- struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry;
+ struct bpf_verifier_state *cur = env->cur_state, *new;
+ bool force_new_state, add_new_state, loop;
int i, j, n, err, states_cnt = 0;
- bool force_new_state, add_new_state, force_exact;
struct list_head *pos, *tmp, *head;
force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) ||
/* Avoid accumulating infinitely long jmp history */
- cur->insn_hist_end - cur->insn_hist_start > 40;
+ cur->jmp_history_cnt > 40;
/* bpf progs typically have pruning point every 4 instructions
* http://vger.kernel.org/bpfconf2019.html#session-1
@@ -19045,6 +19240,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
clean_live_states(env, insn_idx, cur);
+ loop = false;
head = explored_state(env, insn_idx);
list_for_each_safe(pos, tmp, head) {
sl = container_of(pos, struct bpf_verifier_state_list, node);
@@ -19124,7 +19320,7 @@ 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) {
- update_loop_entry(env, cur, &sl->state);
+ loop = true;
goto hit;
}
}
@@ -19133,7 +19329,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
if (is_may_goto_insn_at(env, insn_idx)) {
if (sl->state.may_goto_depth != cur->may_goto_depth &&
states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
- update_loop_entry(env, cur, &sl->state);
+ loop = true;
goto hit;
}
}
@@ -19175,38 +19371,9 @@ skip_inf_loop_check:
add_new_state = false;
goto miss;
}
- /* 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(env, &sl->state);
- if (IS_ERR(loop_entry))
- return PTR_ERR(loop_entry);
- force_exact = loop_entry && loop_entry->branches > 0;
- if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) {
- if (force_exact)
- update_loop_entry(env, cur, loop_entry);
+ /* See comments for mark_all_regs_read_and_precise() */
+ loop = incomplete_read_marks(env, &sl->state);
+ if (states_equal(env, &sl->state, cur, loop ? RANGE_WITHIN : NOT_EXACT)) {
hit:
sl->hit_cnt++;
/* reached equivalent register/stack state,
@@ -19219,7 +19386,7 @@ hit:
* they'll be immediately forgotten as we're pruning
* this state and will pop a new one.
*/
- err = propagate_liveness(env, &sl->state, cur);
+ err = propagate_liveness(env, &sl->state, cur, NULL);
/* if previous state reached the exit with precision and
* current state is equivalent to it (except precision marks)
@@ -19227,10 +19394,98 @@ hit:
* the current state.
*/
if (is_jmp_point(env, env->insn_idx))
- err = err ? : push_insn_history(env, cur, 0, 0);
- err = err ? : propagate_precision(env, &sl->state);
+ err = err ? : push_jmp_history(env, cur, 0, 0);
+ err = err ? : propagate_precision(env, &sl->state, cur, NULL);
if (err)
return err;
+ /* When processing iterator based loops above propagate_liveness and
+ * propagate_precision calls are not sufficient to transfer all relevant
+ * read and precision marks. E.g. consider the following case:
+ *
+ * .-> A --. Assume the states are visited in the order A, B, C.
+ * | | | Assume that state B reaches a state equivalent to state A.
+ * | v v At this point, state C is not processed yet, so state A
+ * '-- B C has not received any read or precision marks from C.
+ * Thus, marks propagated from A to B are incomplete.
+ *
+ * The verifier mitigates this by performing the following steps:
+ *
+ * - Prior to the main verification pass, strongly connected components
+ * (SCCs) are computed over the program's control flow graph,
+ * intraprocedurally.
+ *
+ * - During the main verification pass, `maybe_enter_scc()` checks
+ * whether the current verifier state is entering an SCC. If so, an
+ * instance of a `bpf_scc_visit` object is created, and the state
+ * entering the SCC is recorded as the entry state.
+ *
+ * - This instance is associated not with the SCC itself, but with a
+ * `bpf_scc_callchain`: a tuple consisting of the call sites leading to
+ * the SCC and the SCC id. See `compute_scc_callchain()`.
+ *
+ * - When a verification path encounters a `states_equal(...,
+ * RANGE_WITHIN)` condition, there exists a call chain describing the
+ * current state and a corresponding `bpf_scc_visit` instance. A copy
+ * of the current state is created and added to
+ * `bpf_scc_visit->backedges`.
+ *
+ * - When a verification path terminates, `maybe_exit_scc()` is called
+ * from `update_branch_counts()`. For states with `branches == 0`, it
+ * checks whether the state is the entry state of any `bpf_scc_visit`
+ * instance. If it is, this indicates that all paths originating from
+ * this SCC visit have been explored. `propagate_backedges()` is then
+ * called, which propagates read and precision marks through the
+ * backedges until a fixed point is reached.
+ * (In the earlier example, this would propagate marks from A to B,
+ * from C to A, and then again from A to B.)
+ *
+ * A note on callchains
+ * --------------------
+ *
+ * Consider the following example:
+ *
+ * void foo() { loop { ... SCC#1 ... } }
+ * void main() {
+ * A: foo();
+ * B: ...
+ * C: foo();
+ * }
+ *
+ * Here, there are two distinct callchains leading to SCC#1:
+ * - (A, SCC#1)
+ * - (C, SCC#1)
+ *
+ * Each callchain identifies a separate `bpf_scc_visit` instance that
+ * accumulates backedge states. The `propagate_{liveness,precision}()`
+ * functions traverse the parent state of each backedge state, which
+ * means these parent states must remain valid (i.e., not freed) while
+ * the corresponding `bpf_scc_visit` instance exists.
+ *
+ * Associating `bpf_scc_visit` instances directly with SCCs instead of
+ * callchains would break this invariant:
+ * - States explored during `C: foo()` would contribute backedges to
+ * SCC#1, but SCC#1 would only be exited once the exploration of
+ * `A: foo()` completes.
+ * - By that time, the states explored between `A: foo()` and `C: foo()`
+ * (i.e., `B: ...`) may have already been freed, causing the parent
+ * links for states from `C: foo()` to become invalid.
+ */
+ if (loop) {
+ struct bpf_scc_backedge *backedge;
+
+ backedge = kzalloc(sizeof(*backedge), GFP_KERNEL_ACCOUNT);
+ if (!backedge)
+ return -ENOMEM;
+ err = copy_verifier_state(&backedge->state, cur);
+ backedge->state.equal_state = &sl->state;
+ backedge->state.insn_idx = insn_idx;
+ err = err ?: add_scc_backedge(env, &sl->state, backedge);
+ if (err) {
+ free_verifier_state(&backedge->state, false);
+ kvfree(backedge);
+ return err;
+ }
+ }
return 1;
}
miss:
@@ -19282,7 +19537,7 @@ miss:
* When looping the sl->state.branches will be > 0 and this state
* will not be considered for equivalence until branches == 0.
*/
- new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
+ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL_ACCOUNT);
if (!new_sl)
return -ENOMEM;
env->total_states++;
@@ -19306,11 +19561,17 @@ miss:
new->insn_idx = insn_idx;
WARN_ONCE(new->branches != 1,
"BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx);
+ err = maybe_enter_scc(env, new);
+ if (err) {
+ free_verifier_state(new, false);
+ kvfree(new_sl);
+ return err;
+ }
cur->parent = new;
cur->first_insn_idx = insn_idx;
- cur->insn_hist_start = cur->insn_hist_end;
cur->dfs_depth = new->dfs_depth + 1;
+ clear_jmp_history(cur);
list_add(&new_sl->node, head);
/* connect new state to parentage chain. Current frame needs all
@@ -19382,10 +19643,27 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
!reg_type_mismatch_ok(prev));
}
+static bool is_ptr_to_mem_or_btf_id(enum bpf_reg_type type)
+{
+ switch (base_type(type)) {
+ case PTR_TO_MEM:
+ case PTR_TO_BTF_ID:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool is_ptr_to_mem(enum bpf_reg_type type)
+{
+ return base_type(type) == PTR_TO_MEM;
+}
+
static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type,
bool allow_trust_mismatch)
{
enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type;
+ enum bpf_reg_type merged_type;
if (*prev_type == NOT_INIT) {
/* Saw a valid insn
@@ -19402,15 +19680,24 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
* Reject it.
*/
if (allow_trust_mismatch &&
- base_type(type) == PTR_TO_BTF_ID &&
- base_type(*prev_type) == PTR_TO_BTF_ID) {
+ is_ptr_to_mem_or_btf_id(type) &&
+ is_ptr_to_mem_or_btf_id(*prev_type)) {
/*
* 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_MEMSX.
+ * Same behavior of MEM_RDONLY flag.
*/
- *prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
+ if (is_ptr_to_mem(type) || is_ptr_to_mem(*prev_type))
+ merged_type = PTR_TO_MEM;
+ else
+ merged_type = PTR_TO_BTF_ID;
+ if ((type & PTR_UNTRUSTED) || (*prev_type & PTR_UNTRUSTED))
+ merged_type |= PTR_UNTRUSTED;
+ if ((type & MEM_RDONLY) || (*prev_type & MEM_RDONLY))
+ merged_type |= MEM_RDONLY;
+ *prev_type = merged_type;
} else {
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
@@ -19420,20 +19707,223 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
return 0;
}
+enum {
+ PROCESS_BPF_EXIT = 1
+};
+
+static int process_bpf_exit_full(struct bpf_verifier_env *env,
+ bool *do_print_state,
+ bool exception_exit)
+{
+ /* We must do check_reference_leak here before
+ * prepare_func_exit to handle the case when
+ * state->curframe > 0, it may be a callback function,
+ * for which reference_state must match caller reference
+ * state when it exits.
+ */
+ int err = check_resource_leak(env, exception_exit,
+ !env->cur_state->curframe,
+ "BPF_EXIT instruction in main prog");
+ 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)
+ return PROCESS_BPF_EXIT;
+
+ if (env->cur_state->curframe) {
+ /* exit from nested function */
+ err = prepare_func_exit(env, &env->insn_idx);
+ if (err)
+ return err;
+ *do_print_state = true;
+ return 0;
+ }
+
+ err = check_return_code(env, BPF_REG_0, "R0");
+ if (err)
+ return err;
+ return PROCESS_BPF_EXIT;
+}
+
+static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state)
+{
+ int err;
+ struct bpf_insn *insn = &env->prog->insnsi[env->insn_idx];
+ u8 class = BPF_CLASS(insn->code);
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ err = check_alu_op(env, insn);
+ if (err)
+ return err;
+
+ } else if (class == BPF_LDX) {
+ bool is_ldsx = BPF_MODE(insn->code) == BPF_MEMSX;
+
+ /* Check for reserved fields is already done in
+ * resolve_pseudo_ldimm64().
+ */
+ err = check_load_mem(env, insn, false, is_ldsx, true, "ldx");
+ if (err)
+ return err;
+ } else if (class == BPF_STX) {
+ if (BPF_MODE(insn->code) == BPF_ATOMIC) {
+ err = check_atomic(env, insn);
+ if (err)
+ return err;
+ env->insn_idx++;
+ return 0;
+ }
+
+ if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
+ verbose(env, "BPF_STX uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ err = check_store_reg(env, insn, false);
+ if (err)
+ return err;
+ } else if (class == BPF_ST) {
+ enum bpf_reg_type dst_reg_type;
+
+ if (BPF_MODE(insn->code) != BPF_MEM ||
+ insn->src_reg != BPF_REG_0) {
+ verbose(env, "BPF_ST uses reserved fields\n");
+ return -EINVAL;
+ }
+ /* check src operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg_type = cur_regs(env)[insn->dst_reg].type;
+
+ /* 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, false);
+ if (err)
+ return err;
+
+ err = save_aux_ptr_type(env, dst_reg_type, false);
+ if (err)
+ return err;
+ } else if (class == BPF_JMP || class == BPF_JMP32) {
+ u8 opcode = BPF_OP(insn->code);
+
+ env->jmps_processed++;
+ if (opcode == BPF_CALL) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ (insn->src_reg != BPF_PSEUDO_KFUNC_CALL &&
+ insn->off != 0) ||
+ (insn->src_reg != BPF_REG_0 &&
+ insn->src_reg != BPF_PSEUDO_CALL &&
+ insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
+ insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) {
+ verbose(env, "BPF_CALL uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (env->cur_state->active_locks) {
+ if ((insn->src_reg == BPF_REG_0 &&
+ insn->imm != BPF_FUNC_spin_unlock) ||
+ (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
+ (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) {
+ verbose(env,
+ "function calls are not allowed while holding a lock\n");
+ return -EINVAL;
+ }
+ }
+ 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) {
+ err = check_kfunc_call(env, insn, &env->insn_idx);
+ if (!err && is_bpf_throw_kfunc(insn))
+ return process_bpf_exit_full(env, do_print_state, true);
+ } 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->src_reg != BPF_REG_0 ||
+ insn->dst_reg != BPF_REG_0 ||
+ (class == BPF_JMP && insn->imm != 0) ||
+ (class == BPF_JMP32 && insn->off != 0)) {
+ verbose(env, "BPF_JA uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (class == BPF_JMP)
+ env->insn_idx += insn->off + 1;
+ else
+ env->insn_idx += insn->imm + 1;
+ return 0;
+ } else if (opcode == BPF_EXIT) {
+ 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) {
+ verbose(env, "BPF_EXIT uses reserved fields\n");
+ return -EINVAL;
+ }
+ return process_bpf_exit_full(env, do_print_state, false);
+ } else {
+ err = check_cond_jmp_op(env, insn, &env->insn_idx);
+ if (err)
+ return err;
+ }
+ } else if (class == BPF_LD) {
+ u8 mode = BPF_MODE(insn->code);
+
+ if (mode == BPF_ABS || mode == BPF_IND) {
+ err = check_ld_abs(env, insn);
+ if (err)
+ return err;
+
+ } else if (mode == BPF_IMM) {
+ err = check_ld_imm(env, insn);
+ if (err)
+ return err;
+
+ env->insn_idx++;
+ sanitize_mark_insn_seen(env);
+ } else {
+ verbose(env, "invalid BPF_LD mode\n");
+ return -EINVAL;
+ }
+ } else {
+ verbose(env, "unknown insn class %d\n", class);
+ return -EINVAL;
+ }
+
+ env->insn_idx++;
+ return 0;
+}
+
static int do_check(struct bpf_verifier_env *env)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state = env->cur_state;
struct bpf_insn *insns = env->prog->insnsi;
- struct bpf_reg_state *regs;
int insn_cnt = env->prog->len;
bool do_print_state = false;
int prev_insn_idx = -1;
for (;;) {
- bool exception_exit = false;
struct bpf_insn *insn;
- u8 class;
int err;
/* reset current history entry on each new instruction */
@@ -19447,7 +19937,6 @@ static int do_check(struct bpf_verifier_env *env)
}
insn = &insns[env->insn_idx];
- class = BPF_CLASS(insn->code);
if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
@@ -19457,6 +19946,7 @@ static int do_check(struct bpf_verifier_env *env)
}
state->last_insn_idx = env->prev_insn_idx;
+ state->insn_idx = env->insn_idx;
if (is_prune_point(env, env->insn_idx)) {
err = is_state_visited(env, env->insn_idx);
@@ -19478,7 +19968,7 @@ static int do_check(struct bpf_verifier_env *env)
}
if (is_jmp_point(env, env->insn_idx)) {
- err = push_insn_history(env, state, 0, 0);
+ err = push_jmp_history(env, state, 0, 0);
if (err)
return err;
}
@@ -19517,215 +20007,60 @@ static int do_check(struct bpf_verifier_env *env)
return err;
}
- regs = cur_regs(env);
sanitize_mark_insn_seen(env);
prev_insn_idx = env->insn_idx;
- if (class == BPF_ALU || class == BPF_ALU64) {
- err = check_alu_op(env, insn);
- if (err)
- return err;
-
- } else if (class == BPF_LDX) {
- bool is_ldsx = BPF_MODE(insn->code) == BPF_MEMSX;
+ /* Reduce verification complexity by stopping speculative path
+ * verification when a nospec is encountered.
+ */
+ if (state->speculative && cur_aux(env)->nospec)
+ goto process_bpf_exit;
- /* Check for reserved fields is already done in
- * resolve_pseudo_ldimm64().
+ err = do_check_insn(env, &do_print_state);
+ if (error_recoverable_with_nospec(err) && state->speculative) {
+ /* Prevent this speculative path from ever reaching the
+ * insn that would have been unsafe to execute.
*/
- err = check_load_mem(env, insn, false, is_ldsx, true,
- "ldx");
- if (err)
- return err;
- } else if (class == BPF_STX) {
- if (BPF_MODE(insn->code) == BPF_ATOMIC) {
- err = check_atomic(env, insn);
- if (err)
- return err;
- env->insn_idx++;
- continue;
- }
-
- if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
- verbose(env, "BPF_STX uses reserved fields\n");
- return -EINVAL;
- }
-
- err = check_store_reg(env, insn, false);
- if (err)
- return err;
- } else if (class == BPF_ST) {
- enum bpf_reg_type dst_reg_type;
-
- if (BPF_MODE(insn->code) != BPF_MEM ||
- insn->src_reg != BPF_REG_0) {
- verbose(env, "BPF_ST uses reserved fields\n");
- return -EINVAL;
- }
- /* check src operand */
- err = check_reg_arg(env, insn->dst_reg, SRC_OP);
- if (err)
- return err;
-
- dst_reg_type = regs[insn->dst_reg].type;
-
- /* 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, false);
- if (err)
- return err;
-
- err = save_aux_ptr_type(env, dst_reg_type, false);
+ cur_aux(env)->nospec = true;
+ /* If it was an ADD/SUB insn, potentially remove any
+ * markings for alu sanitization.
+ */
+ cur_aux(env)->alu_state = 0;
+ goto process_bpf_exit;
+ } else if (err < 0) {
+ return err;
+ } else if (err == PROCESS_BPF_EXIT) {
+ goto process_bpf_exit;
+ }
+ WARN_ON_ONCE(err);
+
+ if (state->speculative && cur_aux(env)->nospec_result) {
+ /* If we are on a path that performed a jump-op, this
+ * may skip a nospec patched-in after the jump. This can
+ * currently never happen because nospec_result is only
+ * used for the write-ops
+ * `*(size*)(dst_reg+off)=src_reg|imm32` which must
+ * never skip the following insn. Still, add a warning
+ * to document this in case nospec_result is used
+ * elsewhere in the future.
+ */
+ WARN_ON_ONCE(env->insn_idx != prev_insn_idx + 1);
+process_bpf_exit:
+ mark_verifier_state_scratched(env);
+ err = update_branch_counts(env, env->cur_state);
if (err)
return err;
- } else if (class == BPF_JMP || class == BPF_JMP32) {
- u8 opcode = BPF_OP(insn->code);
-
- env->jmps_processed++;
- if (opcode == BPF_CALL) {
- if (BPF_SRC(insn->code) != BPF_K ||
- (insn->src_reg != BPF_PSEUDO_KFUNC_CALL
- && insn->off != 0) ||
- (insn->src_reg != BPF_REG_0 &&
- insn->src_reg != BPF_PSEUDO_CALL &&
- insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
- insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
- verbose(env, "BPF_CALL uses reserved fields\n");
- return -EINVAL;
- }
-
- if (env->cur_state->active_locks) {
- if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) ||
- (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
- (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) {
- verbose(env, "function calls are not allowed while holding a lock\n");
- return -EINVAL;
- }
- }
- 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) {
- err = check_kfunc_call(env, insn, &env->insn_idx);
- 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->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0 ||
- (class == BPF_JMP && insn->imm != 0) ||
- (class == BPF_JMP32 && insn->off != 0)) {
- verbose(env, "BPF_JA uses reserved fields\n");
- return -EINVAL;
- }
-
- if (class == BPF_JMP)
- env->insn_idx += insn->off + 1;
- else
- env->insn_idx += insn->imm + 1;
- continue;
-
- } else if (opcode == BPF_EXIT) {
- 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) {
- verbose(env, "BPF_EXIT uses reserved fields\n");
- return -EINVAL;
- }
-process_bpf_exit_full:
- /* We must do check_reference_leak here before
- * prepare_func_exit to handle the case when
- * state->curframe > 0, it may be a callback
- * function, for which reference_state must
- * match caller reference state when it exits.
- */
- err = check_resource_leak(env, exception_exit, !env->cur_state->curframe,
- "BPF_EXIT instruction in main prog");
- 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);
- if (err)
- return err;
- do_print_state = true;
- continue;
- }
-
- err = check_return_code(env, BPF_REG_0, "R0");
- if (err)
- return err;
-process_bpf_exit:
- mark_verifier_state_scratched(env);
- update_branch_counts(env, env->cur_state);
- err = pop_stack(env, &prev_insn_idx,
- &env->insn_idx, pop_log);
- if (err < 0) {
- if (err != -ENOENT)
- return err;
- break;
- } else {
- if (verifier_bug_if(env->cur_state->loop_entry, env,
- "broken loop detection"))
- return -EFAULT;
- do_print_state = true;
- continue;
- }
- } else {
- err = check_cond_jmp_op(env, insn, &env->insn_idx);
- if (err)
- return err;
- }
- } else if (class == BPF_LD) {
- u8 mode = BPF_MODE(insn->code);
-
- if (mode == BPF_ABS || mode == BPF_IND) {
- err = check_ld_abs(env, insn);
- if (err)
- return err;
-
- } else if (mode == BPF_IMM) {
- err = check_ld_imm(env, insn);
- if (err)
+ err = pop_stack(env, &prev_insn_idx, &env->insn_idx,
+ pop_log);
+ if (err < 0) {
+ if (err != -ENOENT)
return err;
-
- env->insn_idx++;
- sanitize_mark_insn_seen(env);
+ break;
} else {
- verbose(env, "invalid BPF_LD mode\n");
- return -EINVAL;
+ do_print_state = true;
+ continue;
}
- } else {
- verbose(env, "unknown insn class %d\n", class);
- return -EINVAL;
}
-
- env->insn_idx++;
}
return 0;
@@ -20797,7 +21132,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
-(subprogs[0].stack_depth + 8));
if (epilogue_cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
} else if (epilogue_cnt) {
/* Save the ARG_PTR_TO_CTX for the epilogue to use */
cnt = 0;
@@ -20820,13 +21155,13 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (ops->gen_prologue || env->seen_direct_write) {
if (!ops->gen_prologue) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
} else if (cnt) {
new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
if (!new_prog)
@@ -20853,6 +21188,29 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
bpf_convert_ctx_access_t convert_ctx_access;
u8 mode;
+ if (env->insn_aux_data[i + delta].nospec) {
+ WARN_ON_ONCE(env->insn_aux_data[i + delta].alu_state);
+ struct bpf_insn patch[] = {
+ BPF_ST_NOSPEC(),
+ *insn,
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ /* This can not be easily merged with the
+ * nospec_result-case, because an insn may require a
+ * nospec before and after itself. Therefore also do not
+ * 'continue' here but potentially apply further
+ * patching to insn. *insn should equal patch[1] now.
+ */
+ }
+
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) ||
@@ -20902,7 +21260,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
}
if (type == BPF_WRITE &&
- env->insn_aux_data[i + delta].sanitize_stack_spill) {
+ env->insn_aux_data[i + delta].nospec_result) {
+ /* nospec_result is only used to mitigate Spectre v4 and
+ * to limit verification-time for Spectre v1.
+ */
struct bpf_insn patch[] = {
*insn,
BPF_ST_NOSPEC(),
@@ -20944,6 +21305,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
* for this case.
*/
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
+ case PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED:
if (type == BPF_READ) {
if (BPF_MODE(insn->code) == BPF_MEM)
insn->code = BPF_LDX | BPF_PROBE_MEM |
@@ -20983,7 +21345,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (type == BPF_WRITE) {
verbose(env, "bpf verifier narrow ctx access misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
size_code = BPF_H;
@@ -21002,7 +21364,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (cnt == 0 || cnt >= INSN_BUF_SIZE ||
(ctx_field_size && !target_size)) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
if (is_narrower_load && size < target_size) {
@@ -21010,7 +21372,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
off, size, size_default) * 8;
if (shift && cnt + 1 >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier narrow ctx load misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
if (ctx_field_size <= 4) {
if (shift)
@@ -21775,7 +22137,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
cnt = env->ops->gen_ld_abs(insn, insn_buf);
if (cnt == 0 || cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
@@ -22111,7 +22473,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto patch_map_ops_generic;
if (cnt <= 0 || cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
new_prog = bpf_patch_insn_data(env, i + delta,
@@ -22471,7 +22833,7 @@ next_insn:
!map_ptr->ops->map_poke_untrack ||
!map_ptr->ops->map_poke_run) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux);
@@ -22661,7 +23023,12 @@ static void free_states(struct bpf_verifier_env *env)
{
struct bpf_verifier_state_list *sl;
struct list_head *head, *pos, *tmp;
- int i;
+ struct bpf_scc_info *info;
+ int i, j;
+
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ while (!pop_stack(env, NULL, NULL, false));
list_for_each_safe(pos, tmp, &env->free_list) {
sl = container_of(pos, struct bpf_verifier_state_list, node);
@@ -22670,6 +23037,14 @@ static void free_states(struct bpf_verifier_env *env)
}
INIT_LIST_HEAD(&env->free_list);
+ for (i = 0; i < env->scc_cnt; ++i) {
+ info = env->scc_info[i];
+ for (j = 0; j < info->num_visits; j++)
+ free_backedges(&info->visits[j]);
+ kvfree(info);
+ env->scc_info[i] = NULL;
+ }
+
if (!env->explored_states)
return;
@@ -22697,13 +23072,13 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
env->prev_linfo = NULL;
env->pass_cnt++;
- state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+ state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL_ACCOUNT);
if (!state)
return -ENOMEM;
state->curframe = 0;
state->speculative = false;
state->branches = 1;
- state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
+ state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL_ACCOUNT);
if (!state->frame[0]) {
kfree(state);
return -ENOMEM;
@@ -22806,14 +23181,6 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
ret = do_check(env);
out:
- /* check for NULL is necessary, since cur_state can be freed inside
- * do_check() under memory pressure.
- */
- if (env->cur_state) {
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- }
- while (!pop_stack(env, NULL, NULL, false));
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
@@ -22929,7 +23296,7 @@ static void print_verification_stats(struct bpf_verifier_env *env)
int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
const struct bpf_ctx_arg_aux *info, u32 cnt)
{
- prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL);
+ prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL_ACCOUNT);
prog->aux->ctx_arg_info_size = cnt;
return prog->aux->ctx_arg_info ? 0 : -ENOMEM;
@@ -23671,6 +24038,7 @@ static bool can_jump(struct bpf_insn *insn)
case BPF_JSLT:
case BPF_JSLE:
case BPF_JCOND:
+ case BPF_JSET:
return true;
}
@@ -23873,7 +24241,7 @@ static int compute_live_registers(struct bpf_verifier_env *env)
* - repeat the computation while {in,out} fields changes for
* any instruction.
*/
- state = kvcalloc(insn_cnt, sizeof(*state), GFP_KERNEL);
+ state = kvcalloc(insn_cnt, sizeof(*state), GFP_KERNEL_ACCOUNT);
if (!state) {
err = -ENOMEM;
goto out;
@@ -23911,6 +24279,10 @@ static int compute_live_registers(struct bpf_verifier_env *env)
if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "Live regs before insn:\n");
for (i = 0; i < insn_cnt; ++i) {
+ if (env->insn_aux_data[i].scc)
+ verbose(env, "%3d ", env->insn_aux_data[i].scc);
+ else
+ verbose(env, " ");
verbose(env, "%3d: ", i);
for (j = BPF_REG_0; j < BPF_REG_10; ++j)
if (insn_aux[i].live_regs_before & BIT(j))
@@ -23932,6 +24304,185 @@ out:
return err;
}
+/*
+ * Compute strongly connected components (SCCs) on the CFG.
+ * Assign an SCC number to each instruction, recorded in env->insn_aux[*].scc.
+ * If instruction is a sole member of its SCC and there are no self edges,
+ * assign it SCC number of zero.
+ * Uses a non-recursive adaptation of Tarjan's algorithm for SCC computation.
+ */
+static int compute_scc(struct bpf_verifier_env *env)
+{
+ const u32 NOT_ON_STACK = U32_MAX;
+
+ struct bpf_insn_aux_data *aux = env->insn_aux_data;
+ const u32 insn_cnt = env->prog->len;
+ int stack_sz, dfs_sz, err = 0;
+ u32 *stack, *pre, *low, *dfs;
+ u32 succ_cnt, i, j, t, w;
+ u32 next_preorder_num;
+ u32 next_scc_id;
+ bool assign_scc;
+ u32 succ[2];
+
+ next_preorder_num = 1;
+ next_scc_id = 1;
+ /*
+ * - 'stack' accumulates vertices in DFS order, see invariant comment below;
+ * - 'pre[t] == p' => preorder number of vertex 't' is 'p';
+ * - 'low[t] == n' => smallest preorder number of the vertex reachable from 't' is 'n';
+ * - 'dfs' DFS traversal stack, used to emulate explicit recursion.
+ */
+ stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
+ pre = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
+ low = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
+ dfs = kvcalloc(insn_cnt, sizeof(*dfs), GFP_KERNEL_ACCOUNT);
+ if (!stack || !pre || !low || !dfs) {
+ err = -ENOMEM;
+ goto exit;
+ }
+ /*
+ * References:
+ * [1] R. Tarjan "Depth-First Search and Linear Graph Algorithms"
+ * [2] D. J. Pearce "A Space-Efficient Algorithm for Finding Strongly Connected Components"
+ *
+ * The algorithm maintains the following invariant:
+ * - suppose there is a path 'u' ~> 'v', such that 'pre[v] < pre[u]';
+ * - then, vertex 'u' remains on stack while vertex 'v' is on stack.
+ *
+ * Consequently:
+ * - If 'low[v] < pre[v]', there is a path from 'v' to some vertex 'u',
+ * such that 'pre[u] == low[v]'; vertex 'u' is currently on the stack,
+ * and thus there is an SCC (loop) containing both 'u' and 'v'.
+ * - If 'low[v] == pre[v]', loops containing 'v' have been explored,
+ * and 'v' can be considered the root of some SCC.
+ *
+ * Here is a pseudo-code for an explicitly recursive version of the algorithm:
+ *
+ * NOT_ON_STACK = insn_cnt + 1
+ * pre = [0] * insn_cnt
+ * low = [0] * insn_cnt
+ * scc = [0] * insn_cnt
+ * stack = []
+ *
+ * next_preorder_num = 1
+ * next_scc_id = 1
+ *
+ * def recur(w):
+ * nonlocal next_preorder_num
+ * nonlocal next_scc_id
+ *
+ * pre[w] = next_preorder_num
+ * low[w] = next_preorder_num
+ * next_preorder_num += 1
+ * stack.append(w)
+ * for s in successors(w):
+ * # Note: for classic algorithm the block below should look as:
+ * #
+ * # if pre[s] == 0:
+ * # recur(s)
+ * # low[w] = min(low[w], low[s])
+ * # elif low[s] != NOT_ON_STACK:
+ * # low[w] = min(low[w], pre[s])
+ * #
+ * # But replacing both 'min' instructions with 'low[w] = min(low[w], low[s])'
+ * # does not break the invariant and makes itartive version of the algorithm
+ * # simpler. See 'Algorithm #3' from [2].
+ *
+ * # 's' not yet visited
+ * if pre[s] == 0:
+ * recur(s)
+ * # if 's' is on stack, pick lowest reachable preorder number from it;
+ * # if 's' is not on stack 'low[s] == NOT_ON_STACK > low[w]',
+ * # so 'min' would be a noop.
+ * low[w] = min(low[w], low[s])
+ *
+ * if low[w] == pre[w]:
+ * # 'w' is the root of an SCC, pop all vertices
+ * # below 'w' on stack and assign same SCC to them.
+ * while True:
+ * t = stack.pop()
+ * low[t] = NOT_ON_STACK
+ * scc[t] = next_scc_id
+ * if t == w:
+ * break
+ * next_scc_id += 1
+ *
+ * for i in range(0, insn_cnt):
+ * if pre[i] == 0:
+ * recur(i)
+ *
+ * Below implementation replaces explicit recusion with array 'dfs'.
+ */
+ for (i = 0; i < insn_cnt; i++) {
+ if (pre[i])
+ continue;
+ stack_sz = 0;
+ dfs_sz = 1;
+ dfs[0] = i;
+dfs_continue:
+ while (dfs_sz) {
+ w = dfs[dfs_sz - 1];
+ if (pre[w] == 0) {
+ low[w] = next_preorder_num;
+ pre[w] = next_preorder_num;
+ next_preorder_num++;
+ stack[stack_sz++] = w;
+ }
+ /* Visit 'w' successors */
+ succ_cnt = insn_successors(env->prog, w, succ);
+ for (j = 0; j < succ_cnt; ++j) {
+ if (pre[succ[j]]) {
+ low[w] = min(low[w], low[succ[j]]);
+ } else {
+ dfs[dfs_sz++] = succ[j];
+ goto dfs_continue;
+ }
+ }
+ /*
+ * Preserve the invariant: if some vertex above in the stack
+ * is reachable from 'w', keep 'w' on the stack.
+ */
+ if (low[w] < pre[w]) {
+ dfs_sz--;
+ goto dfs_continue;
+ }
+ /*
+ * Assign SCC number only if component has two or more elements,
+ * or if component has a self reference.
+ */
+ assign_scc = stack[stack_sz - 1] != w;
+ for (j = 0; j < succ_cnt; ++j) {
+ if (succ[j] == w) {
+ assign_scc = true;
+ break;
+ }
+ }
+ /* Pop component elements from stack */
+ do {
+ t = stack[--stack_sz];
+ low[t] = NOT_ON_STACK;
+ if (assign_scc)
+ aux[t].scc = next_scc_id;
+ } while (t != w);
+ if (assign_scc)
+ next_scc_id++;
+ dfs_sz--;
+ }
+ }
+ env->scc_info = kvcalloc(next_scc_id, sizeof(*env->scc_info), GFP_KERNEL_ACCOUNT);
+ if (!env->scc_info) {
+ err = -ENOMEM;
+ goto exit;
+ }
+exit:
+ kvfree(stack);
+ kvfree(pre);
+ kvfree(low);
+ kvfree(dfs);
+ return err;
+}
+
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
{
u64 start_time = ktime_get_ns();
@@ -23940,6 +24491,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
u32 log_true_size;
bool is_priv;
+ BTF_TYPE_EMIT(enum bpf_features);
+
/* no program is valid */
if (ARRAY_SIZE(bpf_verifier_ops) == 0)
return -EINVAL;
@@ -23947,7 +24500,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
/* 'struct bpf_verifier_env' can be global, but since it's not small,
* allocate/free it every time bpf_check() is called
*/
- env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
+ env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL_ACCOUNT);
if (!env)
return -ENOMEM;
@@ -24010,7 +24563,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
env->explored_states = kvcalloc(state_htab_size(env),
sizeof(struct list_head),
- GFP_USER);
+ GFP_KERNEL_ACCOUNT);
ret = -ENOMEM;
if (!env->explored_states)
goto skip_full_check;
@@ -24053,6 +24606,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (ret)
goto skip_full_check;
+ ret = compute_scc(env);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = compute_live_registers(env);
if (ret < 0)
goto skip_full_check;
@@ -24137,7 +24694,7 @@ skip_full_check:
/* if program passed verifier, update used_maps in bpf_prog_info */
env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
sizeof(env->used_maps[0]),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!env->prog->aux->used_maps) {
ret = -ENOMEM;
@@ -24152,7 +24709,7 @@ skip_full_check:
/* if program passed verifier, update used_btfs in bpf_prog_aux */
env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt,
sizeof(env->used_btfs[0]),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!env->prog->aux->used_btfs) {
ret = -ENOMEM;
goto err_release_maps;
@@ -24193,9 +24750,9 @@ err_unlock:
if (!is_priv)
mutex_unlock(&bpf_verifier_lock);
vfree(env->insn_aux_data);
- kvfree(env->insn_hist);
err_free_env:
kvfree(env->cfg.insn_postorder);
+ kvfree(env->scc_info);
kvfree(env);
return ret;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a723b7dc6e4e..312c6a8b55bb 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2074,6 +2074,11 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
for_each_subsys(ss, ssid)
INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
+#ifdef CONFIG_CGROUP_BPF
+ for (int i = 0; i < ARRAY_SIZE(cgrp->bpf.revisions); i++)
+ cgrp->bpf.revisions[i] = 1;
+#endif
+
init_waitqueue_head(&cgrp->offline_waitq);
INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 132c8be6f635..0a06ea6638fe 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1270,7 +1270,7 @@ __bpf_kfunc_start_defs();
* Return: a bpf_key pointer with a valid key pointer if the key is found, a
* NULL pointer otherwise.
*/
-__bpf_kfunc struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+__bpf_kfunc struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags)
{
key_ref_t key_ref;
struct bpf_key *bkey;
generated by cgit v1.2.3 (git 2.46.0) at 2025-12-09 06:32:29 +0000