summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2021-12-31 14:35:40 +0000
committerDavid S. Miller <davem@davemloft.net>2021-12-31 14:35:40 +0000
commite63a02348958cd7cc8c8401c94de57ad97b5d06c (patch)
treed3f07960e158be75c3002c13d3dc2c142a65fbb7 /kernel
parentce2b6eb409ad40607193641c3ec18c3457e1f57c (diff)
parent9e6b19a66d9b6b94395478fe79c5a3ccba181ad3 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says: ==================== pull-request: bpf-next 2021-12-30 The following pull-request contains BPF updates for your *net-next* tree. We've added 72 non-merge commits during the last 20 day(s) which contain a total of 223 files changed, 3510 insertions(+), 1591 deletions(-). The main changes are: 1) Automatic setrlimit in libbpf when bpf is memcg's in the kernel, from Andrii. 2) Beautify and de-verbose verifier logs, from Christy. 3) Composable verifier types, from Hao. 4) bpf_strncmp helper, from Hou. 5) bpf.h header dependency cleanup, from Jakub. 6) get_func_[arg|ret|arg_cnt] helpers, from Jiri. 7) Sleepable local storage, from KP. 8) Extend kfunc with PTR_TO_CTX, PTR_TO_MEM argument support, from Kumar. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/bloom_filter.c6
-rw-r--r--kernel/bpf/bpf_inode_storage.c6
-rw-r--r--kernel/bpf/bpf_local_storage.c50
-rw-r--r--kernel/bpf/bpf_task_storage.c6
-rw-r--r--kernel/bpf/btf.c124
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/cpumap.c4
-rw-r--r--kernel/bpf/devmap.c4
-rw-r--r--kernel/bpf/helpers.c29
-rw-r--r--kernel/bpf/local_storage.c3
-rw-r--r--kernel/bpf/lpm_trie.c2
-rw-r--r--kernel/bpf/map_iter.c4
-rw-r--r--kernel/bpf/net_namespace.c1
-rw-r--r--kernel/bpf/reuseport_array.c6
-rw-r--r--kernel/bpf/ringbuf.c2
-rw-r--r--kernel/bpf/syscall.c3
-rw-r--r--kernel/bpf/trampoline.c8
-rw-r--r--kernel/bpf/verifier.c696
-rw-r--r--kernel/cgroup/cgroup.c1
-rw-r--r--kernel/sysctl.c1
-rw-r--r--kernel/trace/bpf_trace.c81
-rw-r--r--kernel/trace/trace_kprobe.c1
-rw-r--r--kernel/trace/trace_uprobe.c1
23 files changed, 672 insertions, 369 deletions
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index 277a05e9c984..b141a1346f72 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -82,6 +82,11 @@ static int bloom_map_delete_elem(struct bpf_map *map, void *value)
return -EOPNOTSUPP;
}
+static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ return -EOPNOTSUPP;
+}
+
static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
{
u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
@@ -192,6 +197,7 @@ const struct bpf_map_ops bloom_filter_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc = bloom_map_alloc,
.map_free = bloom_map_free,
+ .map_get_next_key = bloom_map_get_next_key,
.map_push_elem = bloom_map_push_elem,
.map_peek_elem = bloom_map_peek_elem,
.map_pop_elem = bloom_map_pop_elem,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 96ceed0e0fb5..e29d9e3d853e 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -17,6 +17,7 @@
#include <linux/bpf_lsm.h>
#include <linux/btf_ids.h>
#include <linux/fdtable.h>
+#include <linux/rcupdate_trace.h>
DEFINE_BPF_STORAGE_CACHE(inode_cache);
@@ -44,7 +45,8 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
if (!bsb)
return NULL;
- inode_storage = rcu_dereference(bsb->storage);
+ inode_storage =
+ rcu_dereference_check(bsb->storage, bpf_rcu_lock_held());
if (!inode_storage)
return NULL;
@@ -172,6 +174,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
{
struct bpf_local_storage_data *sdata;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
return (unsigned long)NULL;
@@ -204,6 +207,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
BPF_CALL_2(bpf_inode_storage_delete,
struct bpf_map *, map, struct inode *, inode)
{
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!inode)
return -EINVAL;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b305270b7a4b..71de2a89869c 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -11,6 +11,9 @@
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/rcupdate_wait.h>
#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
@@ -81,6 +84,22 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
return NULL;
}
+void bpf_local_storage_free_rcu(struct rcu_head *rcu)
+{
+ struct bpf_local_storage *local_storage;
+
+ local_storage = container_of(rcu, struct bpf_local_storage, rcu);
+ kfree_rcu(local_storage, rcu);
+}
+
+static void bpf_selem_free_rcu(struct rcu_head *rcu)
+{
+ struct bpf_local_storage_elem *selem;
+
+ selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+ kfree_rcu(selem, rcu);
+}
+
/* local_storage->lock must be held and selem->local_storage == local_storage.
* The caller must ensure selem->smap is still valid to be
* dereferenced for its smap->elem_size and smap->cache_idx.
@@ -93,7 +112,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
bool free_local_storage;
void *owner;
- smap = rcu_dereference(SDATA(selem)->smap);
+ smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
owner = local_storage->owner;
/* All uncharging on the owner must be done first.
@@ -118,12 +137,12 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
*
* Although the unlock will be done under
* rcu_read_lock(), it is more intutivie to
- * read if kfree_rcu(local_storage, rcu) is done
+ * read if the freeing of the storage is done
* after the raw_spin_unlock_bh(&local_storage->lock).
*
* Hence, a "bool free_local_storage" is returned
- * to the caller which then calls the kfree_rcu()
- * after unlock.
+ * to the caller which then calls then frees the storage after
+ * all the RCU grace periods have expired.
*/
}
hlist_del_init_rcu(&selem->snode);
@@ -131,8 +150,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
SDATA(selem))
RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
- kfree_rcu(selem, rcu);
-
+ call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
return free_local_storage;
}
@@ -146,7 +164,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
/* selem has already been unlinked from sk */
return;
- local_storage = rcu_dereference(selem->local_storage);
+ local_storage = rcu_dereference_check(selem->local_storage,
+ bpf_rcu_lock_held());
raw_spin_lock_irqsave(&local_storage->lock, flags);
if (likely(selem_linked_to_storage(selem)))
free_local_storage = bpf_selem_unlink_storage_nolock(
@@ -154,7 +173,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
if (free_local_storage)
- kfree_rcu(local_storage, rcu);
+ call_rcu_tasks_trace(&local_storage->rcu,
+ bpf_local_storage_free_rcu);
}
void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
@@ -174,7 +194,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
/* selem has already be unlinked from smap */
return;
- smap = rcu_dereference(SDATA(selem)->smap);
+ smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
b = select_bucket(smap, selem);
raw_spin_lock_irqsave(&b->lock, flags);
if (likely(selem_linked_to_map(selem)))
@@ -213,12 +233,14 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
struct bpf_local_storage_elem *selem;
/* Fast path (cache hit) */
- sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+ sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx],
+ bpf_rcu_lock_held());
if (sdata && rcu_access_pointer(sdata->smap) == smap)
return sdata;
/* Slow path (cache miss) */
- hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+ hlist_for_each_entry_rcu(selem, &local_storage->list, snode,
+ rcu_read_lock_trace_held())
if (rcu_access_pointer(SDATA(selem)->smap) == smap)
break;
@@ -306,7 +328,8 @@ int bpf_local_storage_alloc(void *owner,
* bucket->list, first_selem can be freed immediately
* (instead of kfree_rcu) because
* bpf_local_storage_map_free() does a
- * synchronize_rcu() before walking the bucket->list.
+ * synchronize_rcu_mult (waiting for both sleepable and
+ * normal programs) before walking the bucket->list.
* Hence, no one is accessing selem from the
* bucket->list under rcu_read_lock().
*/
@@ -342,7 +365,8 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
!map_value_has_spin_lock(&smap->map)))
return ERR_PTR(-EINVAL);
- local_storage = rcu_dereference(*owner_storage(smap, owner));
+ local_storage = rcu_dereference_check(*owner_storage(smap, owner),
+ bpf_rcu_lock_held());
if (!local_storage || hlist_empty(&local_storage->list)) {
/* Very first elem for the owner */
err = check_flags(NULL, map_flags);
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index bb69aea1a777..5da7bed0f5f6 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -17,6 +17,7 @@
#include <uapi/linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/fdtable.h>
+#include <linux/rcupdate_trace.h>
DEFINE_BPF_STORAGE_CACHE(task_cache);
@@ -59,7 +60,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map,
struct bpf_local_storage *task_storage;
struct bpf_local_storage_map *smap;
- task_storage = rcu_dereference(task->bpf_storage);
+ task_storage =
+ rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held());
if (!task_storage)
return NULL;
@@ -229,6 +231,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *,
{
struct bpf_local_storage_data *sdata;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
return (unsigned long)NULL;
@@ -260,6 +263,7 @@ BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
{
int ret;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!task)
return -EINVAL;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 8b00c6e4d6fb..33bb8ae4a804 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4826,7 +4826,7 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
return prog->aux->attach_btf;
}
-static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
+static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
{
/* t comes in already as a pointer */
t = btf_type_by_id(btf, t->type);
@@ -4835,8 +4835,7 @@ static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST)
t = btf_type_by_id(btf, t->type);
- /* char, signed char, unsigned char */
- return btf_type_is_int(t) && t->size == 1;
+ return btf_type_is_int(t);
}
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
@@ -4941,10 +4940,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+ u32 type, flag;
- if (ctx_arg_info->offset == off &&
- (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
- ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+ type = base_type(ctx_arg_info->reg_type);
+ flag = type_flag(ctx_arg_info->reg_type);
+ if (ctx_arg_info->offset == off && type == PTR_TO_BUF &&
+ (flag & PTR_MAYBE_NULL)) {
info->reg_type = ctx_arg_info->reg_type;
return true;
}
@@ -4957,7 +4958,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
*/
return true;
- if (is_string_ptr(btf, t))
+ if (is_int_ptr(btf, t))
return true;
/* this is a pointer to another type */
@@ -5575,12 +5576,53 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
#endif
};
+/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */
+static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log,
+ const struct btf *btf,
+ const struct btf_type *t, int rec)
+{
+ const struct btf_type *member_type;
+ const struct btf_member *member;
+ u32 i;
+
+ if (!btf_type_is_struct(t))
+ return false;
+
+ for_each_member(i, t, member) {
+ const struct btf_array *array;
+
+ member_type = btf_type_skip_modifiers(btf, member->type, NULL);
+ if (btf_type_is_struct(member_type)) {
+ if (rec >= 3) {
+ bpf_log(log, "max struct nesting depth exceeded\n");
+ return false;
+ }
+ if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1))
+ return false;
+ continue;
+ }
+ if (btf_type_is_array(member_type)) {
+ array = btf_type_array(member_type);
+ if (!array->nelems)
+ return false;
+ member_type = btf_type_skip_modifiers(btf, array->type, NULL);
+ if (!btf_type_is_scalar(member_type))
+ return false;
+ continue;
+ }
+ if (!btf_type_is_scalar(member_type))
+ return false;
+ }
+ return true;
+}
+
static int btf_check_func_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
struct bpf_reg_state *regs,
bool ptr_to_mem_ok)
{
struct bpf_verifier_log *log = &env->log;
+ bool is_kfunc = btf_is_kernel(btf);
const char *func_name, *ref_tname;
const struct btf_type *t, *ref_t;
const struct btf_param *args;
@@ -5633,7 +5675,20 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
ref_tname = btf_name_by_offset(btf, ref_t->name_off);
- if (btf_is_kernel(btf)) {
+ if (btf_get_prog_ctx_type(log, btf, t,
+ env->prog->type, i)) {
+ /* If function expects ctx type in BTF check that caller
+ * is passing PTR_TO_CTX.
+ */
+ if (reg->type != PTR_TO_CTX) {
+ bpf_log(log,
+ "arg#%d expected pointer to ctx, but got %s\n",
+ i, btf_type_str(t));
+ return -EINVAL;
+ }
+ if (check_ctx_reg(env, reg, regno))
+ return -EINVAL;
+ } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) {
const struct btf_type *reg_ref_t;
const struct btf *reg_btf;
const char *reg_ref_tname;
@@ -5649,14 +5704,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
if (reg->type == PTR_TO_BTF_ID) {
reg_btf = reg->btf;
reg_ref_id = reg->btf_id;
- } else if (reg2btf_ids[reg->type]) {
+ } else {
reg_btf = btf_vmlinux;
reg_ref_id = *reg2btf_ids[reg->type];
- } else {
- bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n",
- func_name, i,
- btf_type_str(ref_t), ref_tname, regno);
- return -EINVAL;
}
reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id,
@@ -5672,23 +5722,24 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
reg_ref_tname);
return -EINVAL;
}
- } else if (btf_get_prog_ctx_type(log, btf, t,
- env->prog->type, i)) {
- /* If function expects ctx type in BTF check that caller
- * is passing PTR_TO_CTX.
- */
- if (reg->type != PTR_TO_CTX) {
- bpf_log(log,
- "arg#%d expected pointer to ctx, but got %s\n",
- i, btf_type_str(t));
- return -EINVAL;
- }
- if (check_ctx_reg(env, reg, regno))
- return -EINVAL;
} else if (ptr_to_mem_ok) {
const struct btf_type *resolve_ret;
u32 type_size;
+ if (is_kfunc) {
+ /* Permit pointer to mem, but only when argument
+ * type is pointer to scalar, or struct composed
+ * (recursively) of scalars.
+ */
+ if (!btf_type_is_scalar(ref_t) &&
+ !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) {
+ bpf_log(log,
+ "arg#%d pointer type %s %s must point to scalar or struct with scalar\n",
+ i, btf_type_str(ref_t), ref_tname);
+ return -EINVAL;
+ }
+ }
+
resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
if (IS_ERR(resolve_ret)) {
bpf_log(log,
@@ -5701,6 +5752,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
if (check_mem_reg(env, reg, regno, type_size))
return -EINVAL;
} else {
+ bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i,
+ is_kfunc ? "kernel " : "", func_name, func_id);
return -EINVAL;
}
}
@@ -5750,7 +5803,7 @@ int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
struct bpf_reg_state *regs)
{
- return btf_check_func_arg_match(env, btf, func_id, regs, false);
+ return btf_check_func_arg_match(env, btf, func_id, regs, true);
}
/* Convert BTF of a function into bpf_reg_state if possible
@@ -5858,7 +5911,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
return -EINVAL;
}
- reg->type = PTR_TO_MEM_OR_NULL;
+ reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
reg->id = ++env->id_gen;
continue;
@@ -6352,7 +6405,7 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
.func = bpf_btf_find_by_name_kind,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_ANYTHING,
@@ -6534,12 +6587,11 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
bpf_free_cands_from_cache(*cc);
*cc = NULL;
}
- new_cands = kmalloc(sizeof_cands(cands->cnt), GFP_KERNEL);
+ new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL);
if (!new_cands) {
bpf_free_cands(cands);
return ERR_PTR(-ENOMEM);
}
- memcpy(new_cands, cands, sizeof_cands(cands->cnt));
/* strdup the name, since it will stay in cache.
* the cands->name points to strings in prog's BTF and the prog can be unloaded.
*/
@@ -6657,7 +6709,7 @@ bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id)
main_btf = bpf_get_btf_vmlinux();
if (IS_ERR(main_btf))
- return (void *)main_btf;
+ return ERR_CAST(main_btf);
local_type = btf_type_by_id(local_btf, local_type_id);
if (!local_type)
@@ -6684,14 +6736,14 @@ bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id)
/* Attempt to find target candidates in vmlinux BTF first */
cands = bpf_core_add_cands(cands, main_btf, 1);
if (IS_ERR(cands))
- return cands;
+ return ERR_CAST(cands);
/* cands is a pointer to kmalloced memory here if cands->cnt > 0 */
/* populate cache even when cands->cnt == 0 */
cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
if (IS_ERR(cc))
- return cc;
+ return ERR_CAST(cc);
/* if vmlinux BTF has any candidate, don't go for module BTFs */
if (cc->cnt)
@@ -6717,7 +6769,7 @@ check_modules:
cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf));
if (IS_ERR(cands)) {
btf_put(mod_btf);
- return cands;
+ return ERR_CAST(cands);
}
spin_lock_bh(&btf_idr_lock);
btf_put(mod_btf);
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 43eb3501721b..514b4681a90a 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1789,7 +1789,7 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 585b2b77ccc4..0421061d95f1 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -195,7 +195,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
}
return;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(skb->dev, rcpu->prog, act);
@@ -254,7 +254,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
}
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
fallthrough;
case XDP_DROP:
xdp_return_frame(xdpf);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index f02d04540c0c..6feea293ff10 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -348,7 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
frames[nframes++] = xdpf;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dev, xdp_prog, act);
@@ -507,7 +507,7 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev
__skb_push(skb, skb->mac_len);
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dst->dev, dst->xdp_prog, act);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 19fecfeaa9c2..01cfdf40c838 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
#include <linux/rcupdate.h>
#include <linux/random.h>
#include <linux/smp.h>
@@ -530,7 +531,7 @@ const struct bpf_func_proto bpf_strtol_proto = {
.func = bpf_strtol,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_PTR_TO_LONG,
@@ -558,13 +559,27 @@ const struct bpf_func_proto bpf_strtoul_proto = {
.func = bpf_strtoul,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_PTR_TO_LONG,
};
#endif
+BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
+{
+ return strncmp(s1, s2, s1_sz);
+}
+
+const struct bpf_func_proto bpf_strncmp_proto = {
+ .func = bpf_strncmp,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_PTR_TO_CONST_STR,
+};
+
BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
struct bpf_pidns_info *, nsdata, u32, size)
{
@@ -630,7 +645,7 @@ const struct bpf_func_proto bpf_event_output_data_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -667,7 +682,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
.func = bpf_per_cpu_ptr,
.gpl_only = false,
- .ret_type = RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+ .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY,
.arg1_type = ARG_PTR_TO_PERCPU_BTF_ID,
.arg2_type = ARG_ANYTHING,
};
@@ -680,7 +695,7 @@ BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
.func = bpf_this_cpu_ptr,
.gpl_only = false,
- .ret_type = RET_PTR_TO_MEM_OR_BTF_ID,
+ .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY,
.arg1_type = ARG_PTR_TO_PERCPU_BTF_ID,
};
@@ -1011,7 +1026,7 @@ const struct bpf_func_proto bpf_snprintf_proto = {
.arg1_type = ARG_PTR_TO_MEM_OR_NULL,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_PTR_TO_CONST_STR,
- .arg4_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1378,6 +1393,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_for_each_map_elem_proto;
case BPF_FUNC_loop:
return &bpf_loop_proto;
+ case BPF_FUNC_strncmp:
+ return &bpf_strncmp_proto;
default:
break;
}
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 035e9e3a7132..23f7f9d08a62 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -163,8 +163,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
return 0;
}
- new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) +
- map->value_size,
+ new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size),
__GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
map->numa_node);
if (!new)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 423549d2c52e..5763cc7ac4f1 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -412,7 +412,7 @@ static int trie_update_elem(struct bpf_map *map,
rcu_assign_pointer(im_node->child[1], node);
}
- /* Finally, assign the intermediate node to the determined spot */
+ /* Finally, assign the intermediate node to the determined slot */
rcu_assign_pointer(*slot, im_node);
out:
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 6a9542af4212..b0fa190b0979 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = {
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__bpf_map_elem, key),
- PTR_TO_RDONLY_BUF_OR_NULL },
+ PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
{ offsetof(struct bpf_iter__bpf_map_elem, value),
- PTR_TO_RDWR_BUF_OR_NULL },
+ PTR_TO_BUF | PTR_MAYBE_NULL },
},
};
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 542f275bf252..868cc2c43899 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
+#include <linux/bpf-netns.h>
#include <linux/filter.h>
#include <net/net_namespace.h>
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 93a55391791a..556a769b5b80 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -152,16 +152,12 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
{
int numa_node = bpf_map_attr_numa_node(attr);
struct reuseport_array *array;
- u64 array_size;
if (!bpf_capable())
return ERR_PTR(-EPERM);
- array_size = sizeof(*array);
- array_size += (u64)attr->max_entries * sizeof(struct sock *);
-
/* allocate all map elements and zero-initialize them */
- array = bpf_map_area_alloc(array_size, numa_node);
+ array = bpf_map_area_alloc(struct_size(array, ptrs, attr->max_entries), numa_node);
if (!array)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 9e0c10c6892a..638d7fd7b375 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = {
.func = bpf_ringbuf_output,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ddd81d543203..fa4505f9b611 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
#include <linux/bpf_trace.h>
#include <linux/bpf_lirc.h>
#include <linux/bpf_verifier.h>
@@ -4772,7 +4773,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e98de5e73ba5..4b6974a195c1 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -27,6 +27,14 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
/* serializes access to trampoline_table */
static DEFINE_MUTEX(trampoline_mutex);
+bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
+{
+ enum bpf_attach_type eatype = prog->expected_attach_type;
+
+ return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
+ eatype == BPF_MODIFY_RETURN;
+}
+
void *bpf_jit_alloc_exec_page(void)
{
void *image;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cd79bb12d076..b70c66c6db3b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4,6 +4,7 @@
* Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
*/
#include <uapi/linux/btf.h>
+#include <linux/bpf-cgroup.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
@@ -441,18 +442,6 @@ static bool reg_type_not_null(enum bpf_reg_type type)
type == PTR_TO_SOCK_COMMON;
}
-static bool reg_type_may_be_null(enum bpf_reg_type type)
-{
- return type == PTR_TO_MAP_VALUE_OR_NULL ||
- type == PTR_TO_SOCKET_OR_NULL ||
- type == PTR_TO_SOCK_COMMON_OR_NULL ||
- type == PTR_TO_TCP_SOCK_OR_NULL ||
- type == PTR_TO_BTF_ID_OR_NULL ||
- type == PTR_TO_MEM_OR_NULL ||
- type == PTR_TO_RDONLY_BUF_OR_NULL ||
- type == PTR_TO_RDWR_BUF_OR_NULL;
-}
-
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return reg->type == PTR_TO_MAP_VALUE &&
@@ -461,12 +450,14 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
{
- return type == PTR_TO_SOCKET ||
- type == PTR_TO_SOCKET_OR_NULL ||
- type == PTR_TO_TCP_SOCK ||
- type == PTR_TO_TCP_SOCK_OR_NULL ||
- type == PTR_TO_MEM ||
- type == PTR_TO_MEM_OR_NULL;
+ return base_type(type) == PTR_TO_SOCKET ||
+ base_type(type) == PTR_TO_TCP_SOCK ||
+ base_type(type) == PTR_TO_MEM;
+}
+
+static bool type_is_rdonly_mem(u32 type)
+{
+ return type & MEM_RDONLY;
}
static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
@@ -474,14 +465,9 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
return type == ARG_PTR_TO_SOCK_COMMON;
}
-static bool arg_type_may_be_null(enum bpf_arg_type type)
+static bool type_may_be_null(u32 type)
{
- return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
- type == ARG_PTR_TO_MEM_OR_NULL ||
- type == ARG_PTR_TO_CTX_OR_NULL ||
- type == ARG_PTR_TO_SOCKET_OR_NULL ||
- type == ARG_PTR_TO_ALLOC_MEM_OR_NULL ||
- type == ARG_PTR_TO_STACK_OR_NULL;
+ return type & PTR_MAYBE_NULL;
}
/* Determine whether the function releases some resources allocated by another
@@ -541,39 +527,54 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
insn->imm == BPF_CMPXCHG;
}
-/* string representation of 'enum bpf_reg_type' */
-static const char * const reg_type_str[] = {
- [NOT_INIT] = "?",
- [SCALAR_VALUE] = "inv",
- [PTR_TO_CTX] = "ctx",
- [CONST_PTR_TO_MAP] = "map_ptr",
- [PTR_TO_MAP_VALUE] = "map_value",
- [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
- [PTR_TO_STACK] = "fp",
- [PTR_TO_PACKET] = "pkt",
- [PTR_TO_PACKET_META] = "pkt_meta",
- [PTR_TO_PACKET_END] = "pkt_end",
- [PTR_TO_FLOW_KEYS] = "flow_keys",
- [PTR_TO_SOCKET] = "sock",
- [PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
- [PTR_TO_SOCK_COMMON] = "sock_common",
- [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
- [PTR_TO_TCP_SOCK] = "tcp_sock",
- [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
- [PTR_TO_TP_BUFFER] = "tp_buffer",
- [PTR_TO_XDP_SOCK] = "xdp_sock",
- [PTR_TO_BTF_ID] = "ptr_",
- [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_",
- [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
- [PTR_TO_MEM] = "mem",
- [PTR_TO_MEM_OR_NULL] = "mem_or_null",
- [PTR_TO_RDONLY_BUF] = "rdonly_buf",
- [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
- [PTR_TO_RDWR_BUF] = "rdwr_buf",
- [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
- [PTR_TO_FUNC] = "func",
- [PTR_TO_MAP_KEY] = "map_key",
-};
+/* string representation of 'enum bpf_reg_type'
+ *
+ * Note that reg_type_str() can not appear more than once in a single verbose()
+ * statement.
+ */
+static const char *reg_type_str(struct bpf_verifier_env *env,
+ enum bpf_reg_type type)
+{
+ char postfix[16] = {0}, prefix[16] = {0};
+ static const char * const str[] = {
+ [NOT_INIT] = "?",
+ [SCALAR_VALUE] = "inv",
+ [PTR_TO_CTX] = "ctx",
+ [CONST_PTR_TO_MAP] = "map_ptr",
+ [PTR_TO_MAP_VALUE] = "map_value",
+ [PTR_TO_STACK] = "fp",
+ [PTR_TO_PACKET] = "pkt",
+ [PTR_TO_PACKET_META] = "pkt_meta",
+ [PTR_TO_PACKET_END] = "pkt_end",
+ [PTR_TO_FLOW_KEYS] = "flow_keys",
+ [PTR_TO_SOCKET] = "sock",
+ [PTR_TO_SOCK_COMMON] = "sock_common",
+ [PTR_TO_TCP_SOCK] = "tcp_sock",
+ [PTR_TO_TP_BUFFER] = "tp_buffer",
+ [PTR_TO_XDP_SOCK] = "xdp_sock",
+ [PTR_TO_BTF_ID] = "ptr_",
+ [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
+ [PTR_TO_MEM] = "mem",
+ [PTR_TO_BUF] = "buf",
+ [PTR_TO_FUNC] = "func",
+ [PTR_TO_MAP_KEY] = "map_key",
+ };
+
+ if (type & PTR_MAYBE_NULL) {
+ if (base_type(type) == PTR_TO_BTF_ID ||
+ base_type(type) == PTR_TO_PERCPU_BTF_ID)
+ strncpy(postfix, "or_null_", 16);
+ else
+ strncpy(postfix, "_or_null", 16);
+ }
+
+ if (type & MEM_RDONLY)
+ strncpy(prefix, "rdonly_", 16);
+
+ snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
+ prefix, str[base_type(type)], postfix);
+ return env->type_str_buf;
+}
static char slot_type_char[] = {
[STACK_INVALID] = '?',
@@ -608,6 +609,44 @@ static const char *kernel_type_name(const struct btf* btf, u32 id)
return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
}
+static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
+{
+ env->scratched_regs |= 1U << regno;
+}
+
+static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
+{
+ env->scratched_stack_slots |= 1UL << spi;
+}
+
+static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
+{
+ return (env->scratched_regs >> regno) & 1;
+}
+
+static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
+{
+ return (env->scratched_stack_slots >> regno) & 1;
+}
+
+static bool verifier_state_scratched(const struct bpf_verifier_env *env)
+{
+ return env->scratched_regs || env->scratched_stack_slots;
+}
+
+static void mark_verifier_state_clean(struct bpf_verifier_env *env)
+{
+ env->scratched_regs = 0U;
+ env->scratched_stack_slots = 0UL;
+}
+
+/* Used for printing the entire verifier state. */
+static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
+{
+ env->scratched_regs = ~0U;
+ env->scratched_stack_slots = ~0UL;
+}
+
/* The reg state of a pointer or a bounded scalar was saved when
* it was spilled to the stack.
*/
@@ -623,7 +662,8 @@ static void scrub_spilled_slot(u8 *stype)
}
static void print_verifier_state(struct bpf_verifier_env *env,
- const struct bpf_func_state *state)
+ const struct bpf_func_state *state,
+ bool print_all)
{
const struct bpf_reg_state *reg;
enum bpf_reg_type t;
@@ -636,9 +676,11 @@ static void print_verifier_state(struct bpf_verifier_env *env,
t = reg->type;
if (t == NOT_INIT)
continue;
+ if (!print_all && !reg_scratched(env, i))
+ continue;
verbose(env, " R%d", i);
print_liveness(env, reg->live);
- verbose(env, "=%s", reg_type_str[t]);
+ verbose(env, "=%s", reg_type_str(env, t));
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
@@ -646,9 +688,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
} else {
- if (t == PTR_TO_BTF_ID ||
- t == PTR_TO_BTF_ID_OR_NULL ||
- t == PTR_TO_PERCPU_BTF_ID)
+ if (base_type(t) == PTR_TO_BTF_ID ||
+ base_type(t) == PTR_TO_PERCPU_BTF_ID)
verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id));
verbose(env, "(id=%d", reg->id);
if (reg_type_may_be_refcounted_or_null(t))
@@ -657,10 +698,9 @@ static void print_verifier_state(struct bpf_verifier_env *env,
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
verbose(env, ",r=%d", reg->range);
- else if (t == CONST_PTR_TO_MAP ||
- t == PTR_TO_MAP_KEY ||
- t == PTR_TO_MAP_VALUE ||
- t == PTR_TO_MAP_VALUE_OR_NULL)
+ else if (base_type(t) == CONST_PTR_TO_MAP ||
+ base_type(t) == PTR_TO_MAP_KEY ||
+ base_type(t) == PTR_TO_MAP_VALUE)
verbose(env, ",ks=%d,vs=%d",
reg->map_ptr->key_size,
reg->map_ptr->value_size);
@@ -725,12 +765,14 @@ static void print_verifier_state(struct bpf_verifier_env *env,
types_buf[BPF_REG_SIZE] = 0;
if (!valid)
continue;
+ if (!print_all && !stack_slot_scratched(env, i))
+ continue;
verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
print_liveness(env, state->stack[i].spilled_ptr.live);
if (is_spilled_reg(&state->stack[i])) {
reg = &state->stack[i].spilled_ptr;
t = reg->type;
- verbose(env, "=%s", reg_type_str[t]);
+ verbose(env, "=%s", reg_type_str(env, t));
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
@@ -750,6 +792,26 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (state->in_async_callback_fn)
verbose(env, " async_cb");
verbose(env, "\n");
+ mark_verifier_state_clean(env);
+}
+
+static inline u32 vlog_alignment(u32 pos)
+{
+ return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
+ BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+}
+
+static void print_insn_state(struct bpf_verifier_env *env,
+ const struct bpf_func_state *state)
+{
+ if (env->prev_log_len && env->prev_log_len == env->log.len_used) {
+ /* remove new line character */
+ bpf_vlog_reset(&env->log, env->prev_log_len - 1);
+ verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' ');
+ } else {
+ verbose(env, "%d:", env->insn_idx);
+ }
+ print_verifier_state(env, state, false);
}
/* copy array src of length n * size bytes to dst. dst is reallocated if it's too
@@ -1143,8 +1205,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env,
static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
{
- switch (reg->type) {
- case PTR_TO_MAP_VALUE_OR_NULL: {
+ if (base_type(reg->type) == PTR_TO_MAP_VALUE) {
const struct bpf_map *map = reg->map_ptr;
if (map->inner_map_meta) {
@@ -1163,32 +1224,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
} else {
reg->type = PTR_TO_MAP_VALUE;
}
- break;
- }
- case PTR_TO_SOCKET_OR_NULL:
- reg->type = PTR_TO_SOCKET;
- break;
- case PTR_TO_SOCK_COMMON_OR_NULL:
- reg->type = PTR_TO_SOCK_COMMON;
- break;
- case PTR_TO_TCP_SOCK_OR_NULL:
- reg->type = PTR_TO_TCP_SOCK;
- break;
- case PTR_TO_BTF_ID_OR_NULL:
- reg->type = PTR_TO_BTF_ID;
- break;
- case PTR_TO_MEM_OR_NULL:
- reg->type = PTR_TO_MEM;
- break;
- case PTR_TO_RDONLY_BUF_OR_NULL:
- reg->type = PTR_TO_RDONLY_BUF;
- break;
- case PTR_TO_RDWR_BUF_OR_NULL:
- reg->type = PTR_TO_RDWR_BUF;
- break;
- default:
- WARN_ONCE(1, "unknown nullable register type");
+ return;
}
+
+ reg->type &= ~PTR_MAYBE_NULL;
}
static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
@@ -1546,6 +1585,7 @@ static void init_func_state(struct bpf_verifier_env *env,
state->frameno = frameno;
state->subprogno = subprogno;
init_reg_state(env, state);
+ mark_verifier_state_scratched(env);
}
/* Similar to push_stack(), but for async callbacks */
@@ -2049,7 +2089,7 @@ static int mark_reg_read(struct bpf_verifier_env *env,
break;
if (parent->live & REG_LIVE_DONE) {
verbose(env, "verifier BUG type %s var_off %lld off %d\n",
- reg_type_str[parent->type],
+ reg_type_str(env, parent->type),
parent->var_off.value, parent->off);
return -EFAULT;
}
@@ -2233,6 +2273,8 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
return -EINVAL;
}
+ mark_reg_scratched(env, regno);
+
reg = &regs[regno];
rw64 = is_reg64(env, insn, regno, reg, t);
if (t == SRC_OP) {
@@ -2337,7 +2379,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
if (insn->code == 0)
return 0;
- if (env->log.level & BPF_LOG_LEVEL) {
+ if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
verbose(env, "%d: ", idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
@@ -2591,7 +2633,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
DECLARE_BITMAP(mask, 64);
u32 history = st->jmp_history_cnt;
- if (env->log.level & BPF_LOG_LEVEL)
+ if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
for (i = last_idx;;) {
if (skip_first) {
@@ -2678,11 +2720,11 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
new_marks = true;
reg->precise = true;
}
- if (env->log.level & BPF_LOG_LEVEL) {
- print_verifier_state(env, func);
- verbose(env, "parent %s regs=%x stack=%llx marks\n",
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ verbose(env, "parent %s regs=%x stack=%llx marks:",
new_marks ? "didn't have" : "already had",
reg_mask, stack_mask);
+ print_verifier_state(env, func, true);
}
if (!reg_mask && !stack_mask)
@@ -2708,9 +2750,8 @@ static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi)
static bool is_spillable_regtype(enum bpf_reg_type type)
{
- switch (type) {
+ switch (base_type(type)) {
case PTR_TO_MAP_VALUE:
- case PTR_TO_MAP_VALUE_OR_NULL:
case PTR_TO_STACK:
case PTR_TO_CTX:
case PTR_TO_PACKET:
@@ -2719,21 +2760,13 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_FLOW_KEYS:
case CONST_PTR_TO_MAP:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
- case PTR_TO_BTF_ID_OR_NULL:
- case PTR_TO_RDONLY_BUF:
- case PTR_TO_RDONLY_BUF_OR_NULL:
- case PTR_TO_RDWR_BUF:
- case PTR_TO_RDWR_BUF_OR_NULL:
+ case PTR_TO_BUF:
case PTR_TO_PERCPU_BTF_ID:
case PTR_TO_MEM:
- case PTR_TO_MEM_OR_NULL:
case PTR_TO_FUNC:
case PTR_TO_MAP_KEY:
return true;
@@ -2838,6 +2871,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
}
+ mark_stack_slot_scratched(env, spi);
if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
if (dst_reg != BPF_REG_FP) {
@@ -2959,6 +2993,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
+ mark_stack_slot_scratched(env, spi);
if (!env->allow_ptr_leaks
&& *stype != NOT_INIT
@@ -3375,11 +3410,8 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
/* We may have adjusted the register pointing to memory region, so we
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
- */
- if (env->log.level & BPF_LOG_LEVEL)
- print_verifier_state(env, state);
-
- /* The minimum value is only important with signed
+ *
+ * The minimum value is only important with signed
* comparisons where we can't assume the floor of a
* value is 0. If we are using signed variables for our
* index'es we need to make sure that whatever we use
@@ -3574,7 +3606,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
*/
*reg_type = info.reg_type;
- if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) {
+ if (base_type(*reg_type) == PTR_TO_BTF_ID) {
*btf = info.btf;
*btf_id = info.btf_id;
} else {
@@ -3642,7 +3674,7 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
}
verbose(env, "R%d invalid %s access off=%d size=%d\n",
- regno, reg_type_str[reg->type], off, size);
+ regno, reg_type_str(env, reg->type), off, size);
return -EACCES;
}
@@ -4369,15 +4401,30 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
mark_reg_unknown(env, regs, value_regno);
}
}
- } else if (reg->type == PTR_TO_MEM) {
+ } else if (base_type(reg->type) == PTR_TO_MEM) {
+ bool rdonly_mem = type_is_rdonly_mem(reg->type);
+
+ if (type_may_be_null(reg->type)) {
+ verbose(env, "R%d invalid mem access '%s'\n", regno,
+ reg_type_str(env, reg->type));
+ return -EACCES;
+ }
+
+ if (t == BPF_WRITE && rdonly_mem) {
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str(env, reg->type));
+ return -EACCES;
+ }
+
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into mem\n", value_regno);
return -EACCES;
}
+
err = check_mem_region_access(env, regno, off, size,
reg->mem_size, false);
- if (!err && t == BPF_READ && value_regno >= 0)
+ if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
@@ -4407,7 +4454,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
} else {
mark_reg_known_zero(env, regs,
value_regno);
- if (reg_type_may_be_null(reg_type))
+ if (type_may_be_null(reg_type))
regs[value_regno].id = ++env->id_gen;
/* A load of ctx field could have different
* actual load size with the one encoded in the
@@ -4415,8 +4462,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
* a sub-register.
*/
regs[value_regno].subreg_def = DEF_NOT_SUBREG;
- if (reg_type == PTR_TO_BTF_ID ||
- reg_type == PTR_TO_BTF_ID_OR_NULL) {
+ if (base_type(reg_type) == PTR_TO_BTF_ID) {
regs[value_regno].btf = btf;
regs[value_regno].btf_id = btf_id;
}
@@ -4469,7 +4515,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
} else if (type_is_sk_pointer(reg->type)) {
if (t == BPF_WRITE) {
verbose(env, "R%d cannot write into %s\n",
- regno, reg_type_str[reg->type]);
+ regno, reg_type_str(env, reg->type));
return -EACCES;
}
err = check_sock_access(env, insn_idx, regno, off, size, t);
@@ -4485,26 +4531,32 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
} else if (reg->type == CONST_PTR_TO_MAP) {
err = check_ptr_to_map_access(env, regs, regno, off, size, t,
value_regno);
- } else if (reg->type == PTR_TO_RDONLY_BUF) {
- if (t == BPF_WRITE) {
- verbose(env, "R%d cannot write into %s\n",
- regno, reg_type_str[reg->type]);
- return -EACCES;
+ } else if (base_type(reg->type) == PTR_TO_BUF) {
+ bool rdonly_mem = type_is_rdonly_mem(reg->type);
+ const char *buf_info;
+ u32 *max_access;
+
+ if (rdonly_mem) {
+ if (t == BPF_WRITE) {
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str(env, reg->type));
+ return -EACCES;
+ }
+ buf_info = "rdonly";
+ max_access = &env->prog->aux->max_rdonly_access;
+ } else {
+ buf_info = "rdwr";
+ max_access = &env->prog->aux->max_rdwr_access;
}
+
err = check_buffer_access(env, reg, regno, off, size, false,
- "rdonly",
- &env->prog->aux->max_rdonly_access);
- if (!err && value_regno >= 0)
- mark_reg_unknown(env, regs, value_regno);
- } else if (reg->type == PTR_TO_RDWR_BUF) {
- err = check_buffer_access(env, reg, regno, off, size, false,
- "rdwr",
- &env->prog->aux->max_rdwr_access);
- if (!err && t == BPF_READ && value_regno >= 0)
+ buf_info, max_access);
+
+ if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ))
mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EACCES;
}
@@ -4578,7 +4630,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
is_sk_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
insn->dst_reg,
- reg_type_str[reg_state(env, insn->dst_reg)->type]);
+ reg_type_str(env, reg_state(env, insn->dst_reg)->type));
return -EACCES;
}
@@ -4761,8 +4813,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+ const char *buf_info;
+ u32 *max_access;
- switch (reg->type) {
+ switch (base_type(reg->type)) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
return check_packet_access(env, regno, reg->off, access_size,
@@ -4781,18 +4835,20 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return check_mem_region_access(env, regno, reg->off,
access_size, reg->mem_size,
zero_size_allowed);
- case PTR_TO_RDONLY_BUF:
- if (meta && meta->raw_mode)
- return -EACCES;
- return check_buffer_access(env, reg, regno, reg->off,
- access_size, zero_size_allowed,
- "rdonly",
- &env->prog->aux->max_rdonly_access);
- case PTR_TO_RDWR_BUF:
+ case PTR_TO_BUF:
+ if (type_is_rdonly_mem(reg->type)) {
+ if (meta && meta->raw_mode)
+ return -EACCES;
+
+ buf_info = "rdonly";
+ max_access = &env->prog->aux->max_rdonly_access;
+ } else {
+ buf_info = "rdwr";
+ max_access = &env->prog->aux->max_rdwr_access;
+ }
return check_buffer_access(env, reg, regno, reg->off,
access_size, zero_size_allowed,
- "rdwr",
- &env->prog->aux->max_rdwr_access);
+ buf_info, max_access);
case PTR_TO_STACK:
return check_stack_range_initialized(
env,
@@ -4804,9 +4860,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
register_is_null(reg))
return 0;
- verbose(env, "R%d type=%s expected=%s\n", regno,
- reg_type_str[reg->type],
- reg_type_str[PTR_TO_STACK]);
+ verbose(env, "R%d type=%s ", regno,
+ reg_type_str(env, reg->type));
+ verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK));
return -EACCES;
}
}
@@ -4817,7 +4873,7 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
if (register_is_null(reg))
return 0;
- if (reg_type_may_be_null(reg->type)) {
+ if (type_may_be_null(reg->type)) {
/* Assuming that the register contains a value check if the memory
* access is safe. Temporarily save and restore the register's state as
* the conversion shouldn't be visible to a caller.
@@ -4965,9 +5021,8 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
- return type == ARG_PTR_TO_MEM ||
- type == ARG_PTR_TO_MEM_OR_NULL ||
- type == ARG_PTR_TO_UNINIT_MEM;
+ return base_type(type) == ARG_PTR_TO_MEM ||
+ base_type(type) == ARG_PTR_TO_UNINIT_MEM;
}
static bool arg_type_is_mem_size(enum bpf_arg_type type)
@@ -5072,8 +5127,7 @@ static const struct bpf_reg_types mem_types = {
PTR_TO_MAP_KEY,
PTR_TO_MAP_VALUE,
PTR_TO_MEM,
- PTR_TO_RDONLY_BUF,
- PTR_TO_RDWR_BUF,
+ PTR_TO_BUF,
},
};
@@ -5104,31 +5158,26 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
[ARG_PTR_TO_MAP_KEY] = &map_key_value_types,
[ARG_PTR_TO_MAP_VALUE] = &map_key_value_types,
[ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types,
- [ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types,
[ARG_CONST_SIZE] = &scalar_types,
[ARG_CONST_SIZE_OR_ZERO] = &scalar_types,
[ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types,
[ARG_CONST_MAP_PTR] = &const_map_ptr_types,
[ARG_PTR_TO_CTX] = &context_types,
- [ARG_PTR_TO_CTX_OR_NULL] = &context_types,
[ARG_PTR_TO_SOCK_COMMON] = &sock_types,
#ifdef CONFIG_NET
[ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types,
#endif
[ARG_PTR_TO_SOCKET] = &fullsock_types,
- [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types,
[ARG_PTR_TO_BTF_ID] = &btf_ptr_types,
[ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types,
[ARG_PTR_TO_MEM] = &mem_types,
- [ARG_PTR_TO_MEM_OR_NULL] = &mem_types,
[ARG_PTR_TO_UNINIT_MEM] = &mem_types,
[ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types,
- [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types,
[ARG_PTR_TO_INT] = &int_ptr_types,
[ARG_PTR_TO_LONG] = &int_ptr_types,
[ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
[ARG_PTR_TO_FUNC] = &func_ptr_types,
- [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types,
+ [ARG_PTR_TO_STACK] = &stack_ptr_types,
[ARG_PTR_TO_CONST_STR] = &const_str_ptr_types,
[ARG_PTR_TO_TIMER] = &timer_types,
};
@@ -5142,12 +5191,27 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
const struct bpf_reg_types *compatible;
int i, j;
- compatible = compatible_reg_types[arg_type];
+ compatible = compatible_reg_types[base_type(arg_type)];
if (!compatible) {
verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
return -EFAULT;
}
+ /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY,
+ * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY
+ *
+ * Same for MAYBE_NULL:
+ *
+ * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
+ * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
+ *
+ * Therefore we fold these flags depending on the arg_type before comparison.
+ */
+ if (arg_type & MEM_RDONLY)
+ type &= ~MEM_RDONLY;
+ if (arg_type & PTR_MAYBE_NULL)
+ type &= ~PTR_MAYBE_NULL;
+
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
expected = compatible->types[i];
if (expected == NOT_INIT)
@@ -5157,14 +5221,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
goto found;
}
- verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+ verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type));
for (j = 0; j + 1 < i; j++)
- verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
- verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+ verbose(env, "%s, ", reg_type_str(env, compatible->types[j]));
+ verbose(env, "%s\n", reg_type_str(env, compatible->types[j]));
return -EACCES;
found:
- if (type == PTR_TO_BTF_ID) {
+ if (reg->type == PTR_TO_BTF_ID) {
if (!arg_btf_id) {
if (!compatible->btf_id) {
verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
@@ -5223,15 +5287,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
return -EACCES;
}
- if (arg_type == ARG_PTR_TO_MAP_VALUE ||
- arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
- arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
+ if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+ base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
err = resolve_map_arg_type(env, meta, &arg_type);
if (err)
return err;
}
- if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+ if (register_is_null(reg) && type_may_be_null(arg_type))
/* A NULL register has a SCALAR_VALUE type, so skip
* type checking.
*/
@@ -5300,10 +5363,11 @@ skip_type_check:
err = check_helper_mem_access(env, regno,
meta->map_ptr->key_size, false,
NULL);
- } else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
- (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
- !register_is_null(reg)) ||
- arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+ } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+ base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+ if (type_may_be_null(arg_type) && register_is_null(reg))
+ return 0;
+
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
@@ -6025,9 +6089,9 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "caller:\n");
- print_verifier_state(env, caller);
+ print_verifier_state(env, caller, true);
verbose(env, "callee:\n");
- print_verifier_state(env, callee);
+ print_verifier_state(env, callee, true);
}
return 0;
}
@@ -6242,9 +6306,9 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
*insn_idx = callee->callsite + 1;
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
- print_verifier_state(env, callee);
+ print_verifier_state(env, callee, true);
verbose(env, "to caller at %d:\n", *insn_idx);
- print_verifier_state(env, caller);
+ print_verifier_state(env, caller, true);
}
/* clear everything in the callee */
free_func_state(callee);
@@ -6410,13 +6474,11 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
static int check_get_func_ip(struct bpf_verifier_env *env)
{
- enum bpf_attach_type eatype = env->prog->expected_attach_type;
enum bpf_prog_type type = resolve_prog_type(env->prog);
int func_id = BPF_FUNC_get_func_ip;
if (type == BPF_PROG_TYPE_TRACING) {
- if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT &&
- eatype != BPF_MODIFY_RETURN) {
+ if (!bpf_prog_has_trampoline(env->prog)) {
verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n",
func_id_name(func_id), func_id);
return -ENOTSUPP;
@@ -6435,6 +6497,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
int *insn_idx_p)
{
const struct bpf_func_proto *fn = NULL;
+ enum bpf_return_type ret_type;
+ enum bpf_type_flag ret_flag;
struct bpf_reg_state *regs;
struct bpf_call_arg_meta meta;
int insn_idx = *insn_idx_p;
@@ -6574,13 +6638,14 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
/* update return register (already marked as written above) */
- if (fn->ret_type == RET_INTEGER) {
+ ret_type = fn->ret_type;
+ ret_flag = type_flag(fn->ret_type);
+ if (ret_type == RET_INTEGER) {
/* sets type to SCALAR_VALUE */
mark_reg_unknown(env, regs, BPF_REG_0);
- } else if (fn->ret_type == RET_VOID) {
+ } else if (ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
- } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
- fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ } else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) {
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
@@ -6594,28 +6659,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
regs[BPF_REG_0].map_uid = meta.map_uid;
- if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
- if (map_value_has_spin_lock(meta.map_ptr))
- regs[BPF_REG_0].id = ++env->id_gen;
- } else {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag;
+ if (!type_may_be_null(ret_type) &&
+ map_value_has_spin_lock(meta.map_ptr)) {
+ regs[BPF_REG_0].id = ++env->id_gen;
}
- } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
+ } else if (base_type(ret_type) == RET_PTR_TO_SOCKET) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
- } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag;
+ } else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
- } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag;
+ } else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
- } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag;
+ } else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = meta.mem_size;
- } else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
- fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
+ } else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) {
const struct btf_type *t;
mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -6633,29 +6695,30 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
tname, PTR_ERR(ret));
return -EINVAL;
}
- regs[BPF_REG_0].type =
- fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
- PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = tsize;
} else {
- regs[BPF_REG_0].type =
- fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
- PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
+ /* MEM_RDONLY may be carried from ret_flag, but it
+ * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+ * it will confuse the check of PTR_TO_BTF_ID in
+ * check_mem_access().
+ */
+ ret_flag &= ~MEM_RDONLY;
+
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
regs[BPF_REG_0].btf = meta.ret_btf;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
- } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
- fn->ret_type == RET_PTR_TO_BTF_ID) {
+ } else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
int ret_btf_id;
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
- PTR_TO_BTF_ID :
- PTR_TO_BTF_ID_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
ret_btf_id = *fn->ret_btf_id;
if (ret_btf_id == 0) {
- verbose(env, "invalid return type %d of func %s#%d\n",
- fn->ret_type, func_id_name(func_id), func_id);
+ verbose(env, "invalid return type %u of func %s#%d\n",
+ base_type(ret_type), func_id_name(func_id),
+ func_id);
return -EINVAL;
}
/* current BPF helper definitions are only coming from
@@ -6664,12 +6727,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].btf = btf_vmlinux;
regs[BPF_REG_0].btf_id = ret_btf_id;
} else {
- verbose(env, "unknown return type %d of func %s#%d\n",
- fn->ret_type, func_id_name(func_id), func_id);
+ verbose(env, "unknown return type %u of func %s#%d\n",
+ base_type(ret_type), func_id_name(func_id), func_id);
return -EINVAL;
}
- if (reg_type_may_be_null(regs[BPF_REG_0].type))
+ if (type_may_be_null(regs[BPF_REG_0].type))
regs[BPF_REG_0].id = ++env->id_gen;
if (is_ptr_cast_function(func_id)) {
@@ -6878,25 +6941,25 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env,
if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
verbose(env, "math between %s pointer and %lld is not allowed\n",
- reg_type_str[type], val);
+ reg_type_str(env, type), val);
return false;
}
if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
verbose(env, "%s pointer offset %d is not allowed\n",
- reg_type_str[type], reg->off);
+ reg_type_str(env, type), reg->off);
return false;
}
if (smin == S64_MIN) {
verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
- reg_type_str[type]);
+ reg_type_str(env, type));
return false;
}
if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
verbose(env, "value %lld makes %s pointer be out of bounds\n",
- smin, reg_type_str[type]);
+ smin, reg_type_str(env, type));
return false;
}
@@ -7273,11 +7336,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
return -EACCES;
}
- switch (ptr_reg->type) {
- case PTR_TO_MAP_VALUE_OR_NULL:
+ if (ptr_reg->type & PTR_MAYBE_NULL) {
verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
- dst, reg_type_str[ptr_reg->type]);
+ dst, reg_type_str(env, ptr_reg->type));
return -EACCES;
+ }
+
+ switch (base_type(ptr_reg->type)) {
case CONST_PTR_TO_MAP:
/* smin_val represents the known value */
if (known && smin_val == 0 && opcode == BPF_ADD)
@@ -7285,14 +7350,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
fallthrough;
case PTR_TO_PACKET_END:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
- dst, reg_type_str[ptr_reg->type]);
+ dst, reg_type_str(env, ptr_reg->type));
return -EACCES;
default:
break;
@@ -8265,12 +8327,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
/* Got here implies adding two SCALAR_VALUEs */
if (WARN_ON_ONCE(ptr_reg)) {
- print_verifier_state(env, state);
+ print_verifier_state(env, state, true);
verbose(env, "verifier internal error: unexpected ptr_reg\n");
return -EINVAL;
}
if (WARN_ON(!src_reg)) {
- print_verifier_state(env, state);
+ print_verifier_state(env, state, true);
verbose(env, "verifier internal error: no src_reg\n");
return -EINVAL;
}
@@ -9015,7 +9077,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
struct bpf_reg_state *reg, u32 id,
bool is_null)
{
- if (reg_type_may_be_null(reg->type) && reg->id == id &&
+ if (type_may_be_null(reg->type) && reg->id == id &&
!WARN_ON_ONCE(!reg->id)) {
/* Old offset (both fixed and variable parts) should
* have been known-zero, because we don't allow pointer
@@ -9393,7 +9455,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
*/
if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
- reg_type_may_be_null(dst_reg->type)) {
+ type_may_be_null(dst_reg->type)) {
/* Mark all identical registers in each branch as either
* safe or unknown depending R == 0 or R != 0 conditional.
*/
@@ -9409,7 +9471,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return -EACCES;
}
if (env->log.level & BPF_LOG_LEVEL)
- print_verifier_state(env, this_branch->frame[this_branch->curframe]);
+ print_insn_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
@@ -9448,7 +9510,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->type = aux->btf_var.reg_type;
- switch (dst_reg->type) {
+ switch (base_type(dst_reg->type)) {
case PTR_TO_MEM:
dst_reg->mem_size = aux->btf_var.mem_size;
break;
@@ -9647,7 +9709,7 @@ static int check_return_code(struct bpf_verifier_env *env)
/* enforce return zero from async callbacks like timer */
if (reg->type != SCALAR_VALUE) {
verbose(env, "In async callback the register R0 is not a known value (%s)\n",
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -9661,7 +9723,7 @@ static int check_return_code(struct bpf_verifier_env *env)
if (is_subprog) {
if (reg->type != SCALAR_VALUE) {
verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EINVAL;
}
return 0;
@@ -9725,7 +9787,7 @@ static int check_return_code(struct bpf_verifier_env *env)
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -10582,7 +10644,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
return true;
if (rcur->type == NOT_INIT)
return false;
- switch (rold->type) {
+ switch (base_type(rold->type)) {
case SCALAR_VALUE:
if (env->explore_alu_limits)
return false;
@@ -10604,6 +10666,22 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
}
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
+ /* a PTR_TO_MAP_VALUE could be safe to use as a
+ * PTR_TO_MAP_VALUE_OR_NULL into the same map.
+ * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
+ * checked, doing so could have affected others with the same
+ * id, and we can't check for that because we lost the id when
+ * we converted to a PTR_TO_MAP_VALUE.
+ */
+ if (type_may_be_null(rold->type)) {
+ if (!type_may_be_null(rcur->type))
+ return false;
+ if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
+ return false;
+ /* Check our ids match any regs they're supposed to */
+ return check_ids(rold->id, rcur->id, idmap);
+ }
+
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
* 'id' is not compared, since it's only used for maps with
@@ -10615,20 +10693,6 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
- case PTR_TO_MAP_VALUE_OR_NULL:
- /* a PTR_TO_MAP_VALUE could be safe to use as a
- * PTR_TO_MAP_VALUE_OR_NULL into the same map.
- * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
- * checked, doing so could have affected others with the same
- * id, and we can't check for that because we lost the id when
- * we converted to a PTR_TO_MAP_VALUE.
- */
- if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
- return false;
- if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
- return false;
- /* Check our ids match any regs they're supposed to */
- return check_ids(rold->id, rcur->id, idmap);
case PTR_TO_PACKET_META:
case PTR_TO_PACKET:
if (rcur->type != rold->type)
@@ -10657,11 +10721,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
case PTR_TO_PACKET_END:
case PTR_TO_FLOW_KEYS:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
/* Only valid matches are exact, which memcmp() above
* would have accepted
@@ -11187,17 +11248,13 @@ next:
/* Return true if it's OK to have the same insn return a different type. */
static bool reg_type_mismatch_ok(enum bpf_reg_type type)
{
- switch (type) {
+ switch (base_type(type)) {
case PTR_TO_CTX:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
- case PTR_TO_BTF_ID_OR_NULL:
return false;
default:
return true;
@@ -11277,16 +11334,12 @@ static int do_check(struct bpf_verifier_env *env)
if (need_resched())
cond_resched();
- if (env->log.level & BPF_LOG_LEVEL2 ||
- (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
- if (env->log.level & BPF_LOG_LEVEL2)
- verbose(env, "%d:", env->insn_idx);
- else
- verbose(env, "\nfrom %d to %d%s:",
- env->prev_insn_idx, env->insn_idx,
- env->cur_state->speculative ?
- " (speculative execution)" : "");
- print_verifier_state(env, state->frame[state->curframe]);
+ if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) {
+ verbose(env, "\nfrom %d to %d%s:",
+ env->prev_insn_idx, env->insn_idx,
+ env->cur_state->speculative ?
+ " (speculative execution)" : "");
+ print_verifier_state(env, state->frame[state->curframe], true);
do_print_state = false;
}
@@ -11297,9 +11350,15 @@ static int do_check(struct bpf_verifier_env *env)
.private_data = env,
};
+ if (verifier_state_scratched(env))
+ print_insn_state(env, state->frame[state->curframe]);
+
verbose_linfo(env, env->insn_idx, "; ");
+ env->prev_log_len = env->log.len_used;
verbose(env, "%d: ", env->insn_idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
+ env->prev_insn_print_len = env->log.len_used - env->prev_log_len;
+ env->prev_log_len = env->log.len_used;
}
if (bpf_prog_is_dev_bound(env->prog->aux)) {
@@ -11421,7 +11480,7 @@ static int do_check(struct bpf_verifier_env *env)
if (is_ctx_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
insn->dst_reg,
- reg_type_str[reg_state(env, insn->dst_reg)->type]);
+ reg_type_str(env, reg_state(env, insn->dst_reg)->type));
return -EACCES;
}
@@ -11508,6 +11567,7 @@ static int do_check(struct bpf_verifier_env *env)
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);
@@ -11673,7 +11733,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
err = -EINVAL;
goto err_put;
}
- aux->btf_var.reg_type = PTR_TO_MEM;
+ aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY;
aux->btf_var.mem_size = tsize;
} else {
aux->btf_var.reg_type = PTR_TO_BTF_ID;
@@ -11833,6 +11893,9 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
break;
case BPF_MAP_TYPE_RINGBUF:
+ case BPF_MAP_TYPE_INODE_STORAGE:
+ case BPF_MAP_TYPE_SK_STORAGE:
+ case BPF_MAP_TYPE_TASK_STORAGE:
break;
default:
verbose(env,
@@ -13016,6 +13079,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env,
static int do_misc_fixups(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
+ enum bpf_attach_type eatype = prog->expected_attach_type;
bool expect_blinding = bpf_jit_blinding_enabled(prog);
enum bpf_prog_type prog_type = resolve_prog_type(prog);
struct bpf_insn *insn = prog->insnsi;
@@ -13386,11 +13450,79 @@ patch_map_ops_generic:
continue;
}
+ /* Implement bpf_get_func_arg inline. */
+ if (prog_type == BPF_PROG_TYPE_TRACING &&
+ insn->imm == BPF_FUNC_get_func_arg) {
+ /* Load nr_args from ctx - 8 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+ insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6);
+ insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3);
+ insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1);
+ insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0);
+ insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0);
+ insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0);
+ insn_buf[7] = BPF_JMP_A(1);
+ insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL);
+ cnt = 9;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ /* Implement bpf_get_func_ret inline. */
+ if (prog_type == BPF_PROG_TYPE_TRACING &&
+ insn->imm == BPF_FUNC_get_func_ret) {
+ if (eatype == BPF_TRACE_FEXIT ||
+ eatype == BPF_MODIFY_RETURN) {
+ /* Load nr_args from ctx - 8 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+ insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
+ insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
+ insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0);
+ insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0);
+ insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0);
+ cnt = 6;
+ } else {
+ insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP);
+ cnt = 1;
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ /* Implement get_func_arg_cnt inline. */
+ if (prog_type == BPF_PROG_TYPE_TRACING &&
+ insn->imm == BPF_FUNC_get_func_arg_cnt) {
+ /* Load nr_args from ctx - 8 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
+ if (!new_prog)
+ return -ENOMEM;
+
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
/* Implement bpf_get_func_ip inline. */
if (prog_type == BPF_PROG_TYPE_TRACING &&
insn->imm == BPF_FUNC_get_func_ip) {
- /* Load IP address from ctx - 8 */
- insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+ /* Load IP address from ctx - 16 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16);
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
if (!new_prog)
@@ -13504,7 +13636,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
mark_reg_known_zero(env, regs, i);
else if (regs[i].type == SCALAR_VALUE)
mark_reg_unknown(env, regs, i);
- else if (regs[i].type == PTR_TO_MEM_OR_NULL) {
+ else if (base_type(regs[i].type) == PTR_TO_MEM) {
const u32 mem_size = regs[i].mem_size;
mark_reg_known_zero(env, regs, i);
@@ -14099,6 +14231,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
}
}
+ mark_verifier_state_clean(env);
+
if (IS_ERR(btf_vmlinux)) {
/* Either gcc or pahole or kernel are broken. */
verbose(env, "in-kernel BTF is malformed\n");
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 919194de39c8..cd4c23f7e3df 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -30,6 +30,7 @@
#include "cgroup-internal.h"
+#include <linux/bpf-cgroup.h>
#include <linux/cred.h>
#include <linux/errno.h>
#include <linux/init_task.h>
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 083be6af29d7..d7ed1dffa426 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -33,6 +33,7 @@
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/kmemleak.h>
+#include <linux/filter.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 623dd0684429..21aa30644219 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
@@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
.func = bpf_trace_printk,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
};
@@ -450,9 +450,9 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = {
.func = bpf_trace_vprintk,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
- .arg3_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -492,9 +492,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
- .arg4_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -509,7 +509,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -533,7 +533,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -694,7 +694,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1004,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_MEM,
.arg2_type = ARG_CONST_SIZE,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
@@ -1012,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx)
{
/* This helper call is inlined by verifier. */
- return ((u64 *)ctx)[-1];
+ return ((u64 *)ctx)[-2];
}
static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
@@ -1091,6 +1091,53 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
};
+BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value)
+{
+ /* This helper call is inlined by verifier. */
+ u64 nr_args = ((u64 *)ctx)[-1];
+
+ if ((u64) n >= nr_args)
+ return -EINVAL;
+ *value = ((u64 *)ctx)[n];
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_proto = {
+ .func = get_func_arg,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
+{
+ /* This helper call is inlined by verifier. */
+ u64 nr_args = ((u64 *)ctx)[-1];
+
+ *value = ((u64 *)ctx)[nr_args];
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_ret_proto = {
+ .func = get_func_ret,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_1(get_func_arg_cnt, void *, ctx)
+{
+ /* This helper call is inlined by verifier. */
+ return ((u64 *)ctx)[-1];
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
+ .func = get_func_arg_cnt,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static const struct bpf_func_proto *
bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -1287,7 +1334,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1509,7 +1556,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1563,7 +1610,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -1629,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
NULL;
case BPF_FUNC_d_path:
return &bpf_d_path_proto;
+ case BPF_FUNC_get_func_arg:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL;
+ case BPF_FUNC_get_func_ret:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL;
+ case BPF_FUNC_get_func_arg_cnt:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL;
default:
fn = raw_tp_prog_func_proto(func_id, prog);
if (!fn && prog->expected_attach_type == BPF_TRACE_ITER)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 33272a7b6912..4e1257f50aa3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
+#include <linux/bpf-cgroup.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index f5f0039d31e5..4f35514a48f3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_uprobe: " fmt
+#include <linux/bpf-cgroup.h>
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/module.h>
generated by cgit (git 2.34.1) at 2024-06-22 00:03:27 +0000