summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/Makefile1
-rw-r--r--kernel/bpf/arraymap.c30
-rw-r--r--kernel/bpf/bpf_iter.c14
-rw-r--r--kernel/bpf/bpf_local_storage.c20
-rw-r--r--kernel/bpf/bpf_lsm.c140
-rw-r--r--kernel/bpf/bpf_struct_ops.c19
-rw-r--r--kernel/bpf/bpf_task_storage.c315
-rw-r--r--kernel/bpf/btf.c481
-rw-r--r--kernel/bpf/core.c23
-rw-r--r--kernel/bpf/cpumap.c37
-rw-r--r--kernel/bpf/devmap.c25
-rw-r--r--kernel/bpf/hashtab.c189
-rw-r--r--kernel/bpf/helpers.c13
-rw-r--r--kernel/bpf/local_storage.c44
-rw-r--r--kernel/bpf/lpm_trie.c19
-rw-r--r--kernel/bpf/queue_stack_maps.c16
-rw-r--r--kernel/bpf/reuseport_array.c12
-rw-r--r--kernel/bpf/ringbuf.c35
-rw-r--r--kernel/bpf/stackmap.c16
-rw-r--r--kernel/bpf/syscall.c316
-rw-r--r--kernel/bpf/sysfs_btf.c2
-rw-r--r--kernel/bpf/task_iter.c56
-rw-r--r--kernel/bpf/verifier.c441
-rw-r--r--kernel/fork.c7
-rw-r--r--kernel/kcov.c2
-rw-r--r--kernel/module.c36
-rw-r--r--kernel/taskstats.c2
-rw-r--r--kernel/trace/bpf_trace.c41
28 files changed, 1616 insertions, 736 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index c1b9f71ee6aa..d1249340fd6b 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_i
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
+obj-${CONFIG_BPF_LSM} += bpf_task_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_JIT) += trampoline.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c6c81eceb68f..1f8453343bf2 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -34,8 +34,8 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
int i;
for (i = 0; i < array->map.max_entries; i++) {
- ptr = __alloc_percpu_gfp(array->elem_size, 8,
- GFP_USER | __GFP_NOWARN);
+ ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8,
+ GFP_USER | __GFP_NOWARN);
if (!ptr) {
bpf_array_free_percpu(array);
return -ENOMEM;
@@ -81,11 +81,10 @@ int array_map_alloc_check(union bpf_attr *attr)
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
- int ret, numa_node = bpf_map_attr_numa_node(attr);
+ int numa_node = bpf_map_attr_numa_node(attr);
u32 elem_size, index_mask, max_entries;
bool bypass_spec_v1 = bpf_bypass_spec_v1();
- u64 cost, array_size, mask64;
- struct bpf_map_memory mem;
+ u64 array_size, mask64;
struct bpf_array *array;
elem_size = round_up(attr->value_size, 8);
@@ -126,44 +125,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
}
}
- /* make sure there is no u32 overflow later in round_up() */
- cost = array_size;
- if (percpu)
- cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
-
- ret = bpf_map_charge_init(&mem, cost);
- if (ret < 0)
- return ERR_PTR(ret);
-
/* allocate all map elements and zero-initialize them */
if (attr->map_flags & BPF_F_MMAPABLE) {
void *data;
/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
data = bpf_map_area_mmapable_alloc(array_size, numa_node);
- if (!data) {
- bpf_map_charge_finish(&mem);
+ if (!data)
return ERR_PTR(-ENOMEM);
- }
array = data + PAGE_ALIGN(sizeof(struct bpf_array))
- offsetof(struct bpf_array, value);
} else {
array = bpf_map_area_alloc(array_size, numa_node);
}
- if (!array) {
- bpf_map_charge_finish(&mem);
+ if (!array)
return ERR_PTR(-ENOMEM);
- }
array->index_mask = index_mask;
array->map.bypass_spec_v1 = bypass_spec_v1;
/* copy mandatory map attributes */
bpf_map_init_from_attr(&array->map, attr);
- bpf_map_charge_move(&array->map.memory, &mem);
array->elem_size = elem_size;
if (percpu && bpf_array_alloc_percpu(array)) {
- bpf_map_charge_finish(&array->map.memory);
bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
@@ -1018,7 +1002,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
struct bpf_array_aux *aux;
struct bpf_map *map;
- aux = kzalloc(sizeof(*aux), GFP_KERNEL);
+ aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT);
if (!aux)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 8f10e30ea0b0..5454161407f1 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -67,6 +67,15 @@ static void bpf_iter_done_stop(struct seq_file *seq)
iter_priv->done_stop = true;
}
+static bool bpf_iter_support_resched(struct seq_file *seq)
+{
+ struct bpf_iter_priv_data *iter_priv;
+
+ iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+ target_private);
+ return iter_priv->tinfo->reg_info->feature & BPF_ITER_RESCHED;
+}
+
/* maximum visited objects before bailing out */
#define MAX_ITER_OBJECTS 1000000
@@ -83,6 +92,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
struct seq_file *seq = file->private_data;
size_t n, offs, copied = 0;
int err = 0, num_objs = 0;
+ bool can_resched;
void *p;
mutex_lock(&seq->lock);
@@ -135,6 +145,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
goto done;
}
+ can_resched = bpf_iter_support_resched(seq);
while (1) {
loff_t pos = seq->index;
@@ -180,6 +191,9 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
}
break;
}
+
+ if (can_resched)
+ cond_resched();
}
stop:
offs = seq->count;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 5d3a7af9ba9b..dd5aedee99e7 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -67,7 +67,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
if (charge_mem && mem_charge(smap, owner, smap->elem_size))
return NULL;
- selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+ selem = bpf_map_kzalloc(&smap->map, smap->elem_size,
+ GFP_ATOMIC | __GFP_NOWARN);
if (selem) {
if (value)
memcpy(SDATA(selem)->data, value, smap->map.value_size);
@@ -264,7 +265,8 @@ int bpf_local_storage_alloc(void *owner,
if (err)
return err;
- storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
+ storage = bpf_map_kzalloc(&smap->map, sizeof(*storage),
+ GFP_ATOMIC | __GFP_NOWARN);
if (!storage) {
err = -ENOMEM;
goto uncharge;
@@ -543,10 +545,8 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
struct bpf_local_storage_map *smap;
unsigned int i;
u32 nbuckets;
- u64 cost;
- int ret;
- smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
+ smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
if (!smap)
return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&smap->map, attr);
@@ -555,18 +555,10 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
nbuckets = max_t(u32, 2, nbuckets);
smap->bucket_log = ilog2(nbuckets);
- cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
-
- ret = bpf_map_charge_init(&smap->map.memory, cost);
- if (ret < 0) {
- kfree(smap);
- return ERR_PTR(ret);
- }
smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
- GFP_USER | __GFP_NOWARN);
+ GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
if (!smap->buckets) {
- bpf_map_charge_finish(&smap->map.memory);
kfree(smap);
return ERR_PTR(-ENOMEM);
}
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 56cc5a915f67..70e5e0b6d69d 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -7,6 +7,7 @@
#include <linux/filter.h>
#include <linux/bpf.h>
#include <linux/btf.h>
+#include <linux/binfmts.h>
#include <linux/lsm_hooks.h>
#include <linux/bpf_lsm.h>
#include <linux/kallsyms.h>
@@ -14,6 +15,7 @@
#include <net/bpf_sk_storage.h>
#include <linux/bpf_local_storage.h>
#include <linux/btf_ids.h>
+#include <linux/ima.h>
/* For every LSM hook that allows attachment of BPF programs, declare a nop
* function where a BPF program can be attached.
@@ -51,6 +53,52 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
return 0;
}
+/* Mask for all the currently supported BPRM option flags */
+#define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC
+
+BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags)
+{
+ if (flags & ~BPF_F_BRPM_OPTS_MASK)
+ return -EINVAL;
+
+ bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC);
+ return 0;
+}
+
+BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm)
+
+const static struct bpf_func_proto bpf_bprm_opts_set_proto = {
+ .func = bpf_bprm_opts_set,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0],
+ .arg2_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size)
+{
+ return ima_inode_hash(inode, dst, size);
+}
+
+static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog)
+{
+ return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id);
+}
+
+BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode)
+
+const static struct bpf_func_proto bpf_ima_inode_hash_proto = {
+ .func = bpf_ima_inode_hash,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0],
+ .arg2_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .allowed = bpf_ima_inode_hash_allowed,
+};
+
static const struct bpf_func_proto *
bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -63,11 +111,103 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_storage_get_proto;
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
+ case BPF_FUNC_spin_lock:
+ return &bpf_spin_lock_proto;
+ case BPF_FUNC_spin_unlock:
+ return &bpf_spin_unlock_proto;
+ case BPF_FUNC_task_storage_get:
+ return &bpf_task_storage_get_proto;
+ case BPF_FUNC_task_storage_delete:
+ return &bpf_task_storage_delete_proto;
+ case BPF_FUNC_bprm_opts_set:
+ return &bpf_bprm_opts_set_proto;
+ case BPF_FUNC_ima_inode_hash:
+ return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL;
default:
return tracing_prog_func_proto(func_id, prog);
}
}
+/* The set of hooks which are called without pagefaults disabled and are allowed
+ * to "sleep" and thus can be used for sleeable BPF programs.
+ */
+BTF_SET_START(sleepable_lsm_hooks)
+BTF_ID(func, bpf_lsm_bpf)
+BTF_ID(func, bpf_lsm_bpf_map)
+BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
+BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_prog)
+BTF_ID(func, bpf_lsm_bprm_check_security)
+BTF_ID(func, bpf_lsm_bprm_committed_creds)
+BTF_ID(func, bpf_lsm_bprm_committing_creds)
+BTF_ID(func, bpf_lsm_bprm_creds_for_exec)
+BTF_ID(func, bpf_lsm_bprm_creds_from_file)
+BTF_ID(func, bpf_lsm_capget)
+BTF_ID(func, bpf_lsm_capset)
+BTF_ID(func, bpf_lsm_cred_prepare)
+BTF_ID(func, bpf_lsm_file_ioctl)
+BTF_ID(func, bpf_lsm_file_lock)
+BTF_ID(func, bpf_lsm_file_open)
+BTF_ID(func, bpf_lsm_file_receive)
+BTF_ID(func, bpf_lsm_inet_conn_established)
+BTF_ID(func, bpf_lsm_inode_create)
+BTF_ID(func, bpf_lsm_inode_free_security)
+BTF_ID(func, bpf_lsm_inode_getattr)
+BTF_ID(func, bpf_lsm_inode_getxattr)
+BTF_ID(func, bpf_lsm_inode_mknod)
+BTF_ID(func, bpf_lsm_inode_need_killpriv)
+BTF_ID(func, bpf_lsm_inode_post_setxattr)
+BTF_ID(func, bpf_lsm_inode_readlink)
+BTF_ID(func, bpf_lsm_inode_rename)
+BTF_ID(func, bpf_lsm_inode_rmdir)
+BTF_ID(func, bpf_lsm_inode_setattr)
+BTF_ID(func, bpf_lsm_inode_setxattr)
+BTF_ID(func, bpf_lsm_inode_symlink)
+BTF_ID(func, bpf_lsm_inode_unlink)
+BTF_ID(func, bpf_lsm_kernel_module_request)
+BTF_ID(func, bpf_lsm_kernfs_init_security)
+BTF_ID(func, bpf_lsm_key_free)
+BTF_ID(func, bpf_lsm_mmap_file)
+BTF_ID(func, bpf_lsm_netlink_send)
+BTF_ID(func, bpf_lsm_path_notify)
+BTF_ID(func, bpf_lsm_release_secctx)
+BTF_ID(func, bpf_lsm_sb_alloc_security)
+BTF_ID(func, bpf_lsm_sb_eat_lsm_opts)
+BTF_ID(func, bpf_lsm_sb_kern_mount)
+BTF_ID(func, bpf_lsm_sb_mount)
+BTF_ID(func, bpf_lsm_sb_remount)
+BTF_ID(func, bpf_lsm_sb_set_mnt_opts)
+BTF_ID(func, bpf_lsm_sb_show_options)
+BTF_ID(func, bpf_lsm_sb_statfs)
+BTF_ID(func, bpf_lsm_sb_umount)
+BTF_ID(func, bpf_lsm_settime)
+BTF_ID(func, bpf_lsm_socket_accept)
+BTF_ID(func, bpf_lsm_socket_bind)
+BTF_ID(func, bpf_lsm_socket_connect)
+BTF_ID(func, bpf_lsm_socket_create)
+BTF_ID(func, bpf_lsm_socket_getpeername)
+BTF_ID(func, bpf_lsm_socket_getpeersec_dgram)
+BTF_ID(func, bpf_lsm_socket_getsockname)
+BTF_ID(func, bpf_lsm_socket_getsockopt)
+BTF_ID(func, bpf_lsm_socket_listen)
+BTF_ID(func, bpf_lsm_socket_post_create)
+BTF_ID(func, bpf_lsm_socket_recvmsg)
+BTF_ID(func, bpf_lsm_socket_sendmsg)
+BTF_ID(func, bpf_lsm_socket_shutdown)
+BTF_ID(func, bpf_lsm_socket_socketpair)
+BTF_ID(func, bpf_lsm_syslog)
+BTF_ID(func, bpf_lsm_task_alloc)
+BTF_ID(func, bpf_lsm_task_getsecid)
+BTF_ID(func, bpf_lsm_task_prctl)
+BTF_ID(func, bpf_lsm_task_setscheduler)
+BTF_ID(func, bpf_lsm_task_to_inode)
+BTF_SET_END(sleepable_lsm_hooks)
+
+bool bpf_lsm_is_sleepable_hook(u32 btf_id)
+{
+ return btf_id_set_contains(&sleepable_lsm_hooks, btf_id);
+}
+
const struct bpf_prog_ops lsm_prog_ops = {
};
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 4c3b543bb33b..1a666a975416 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -548,12 +548,10 @@ static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
{
const struct bpf_struct_ops *st_ops;
- size_t map_total_size, st_map_size;
+ size_t st_map_size;
struct bpf_struct_ops_map *st_map;
const struct btf_type *t, *vt;
- struct bpf_map_memory mem;
struct bpf_map *map;
- int err;
if (!bpf_capable())
return ERR_PTR(-EPERM);
@@ -573,20 +571,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
* struct bpf_struct_ops_tcp_congestions_ops
*/
(vt->size - sizeof(struct bpf_struct_ops_value));
- map_total_size = st_map_size +
- /* uvalue */
- sizeof(vt->size) +
- /* struct bpf_progs **progs */
- btf_type_vlen(t) * sizeof(struct bpf_prog *);
- err = bpf_map_charge_init(&mem, map_total_size);
- if (err < 0)
- return ERR_PTR(err);
st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
- if (!st_map) {
- bpf_map_charge_finish(&mem);
+ if (!st_map)
return ERR_PTR(-ENOMEM);
- }
+
st_map->st_ops = st_ops;
map = &st_map->map;
@@ -597,14 +586,12 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
if (!st_map->uvalue || !st_map->progs || !st_map->image) {
bpf_struct_ops_map_free(map);
- bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
}
mutex_init(&st_map->lock);
set_vm_flush_reset_perms(st_map->image);
bpf_map_init_from_attr(map, attr);
- bpf_map_charge_move(&map->memory, &mem);
return map;
}
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
new file mode 100644
index 000000000000..4ef1959a78f2
--- /dev/null
+++ b/kernel/bpf/bpf_task_storage.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/pid.h>
+#include <linux/sched.h>
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <linux/filter.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
+#include <linux/fdtable.h>
+
+DEFINE_BPF_STORAGE_CACHE(task_cache);
+
+static struct bpf_local_storage __rcu **task_storage_ptr(void *owner)
+{
+ struct task_struct *task = owner;
+ struct bpf_storage_blob *bsb;
+
+ bsb = bpf_task(task);
+ if (!bsb)
+ return NULL;
+ return &bsb->storage;
+}
+
+static struct bpf_local_storage_data *
+task_storage_lookup(struct task_struct *task, struct bpf_map *map,
+ bool cacheit_lockit)
+{
+ struct bpf_local_storage *task_storage;
+ struct bpf_local_storage_map *smap;
+ struct bpf_storage_blob *bsb;
+
+ bsb = bpf_task(task);
+ if (!bsb)
+ return NULL;
+
+ task_storage = rcu_dereference(bsb->storage);
+ if (!task_storage)
+ return NULL;
+
+ smap = (struct bpf_local_storage_map *)map;
+ return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit);
+}
+
+void bpf_task_storage_free(struct task_struct *task)
+{
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *local_storage;
+ bool free_task_storage = false;
+ struct bpf_storage_blob *bsb;
+ struct hlist_node *n;
+
+ bsb = bpf_task(task);
+ if (!bsb)
+ return;
+
+ rcu_read_lock();
+
+ local_storage = rcu_dereference(bsb->storage);
+ if (!local_storage) {
+ rcu_read_unlock();
+ return;
+ }
+
+ /* Neither the bpf_prog nor the bpf-map's syscall
+ * could be modifying the local_storage->list now.
+ * Thus, no elem can be added-to or deleted-from the
+ * local_storage->list by the bpf_prog or by the bpf-map's syscall.
+ *
+ * It is racing with bpf_local_storage_map_free() alone
+ * when unlinking elem from the local_storage->list and
+ * the map's bucket->list.
+ */
+ raw_spin_lock_bh(&local_storage->lock);
+ hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
+ /* Always unlink from map before unlinking from
+ * local_storage.
+ */
+ bpf_selem_unlink_map(selem);
+ free_task_storage = bpf_selem_unlink_storage_nolock(
+ local_storage, selem, false);
+ }
+ raw_spin_unlock_bh(&local_storage->lock);
+ rcu_read_unlock();
+
+ /* free_task_storage should always be true as long as
+ * local_storage->list was non-empty.
+ */
+ if (free_task_storage)
+ kfree_rcu(local_storage, rcu);
+}
+
+static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_local_storage_data *sdata;
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ int fd, err;
+
+ fd = *(int *)key;
+ pid = pidfd_get_pid(fd, &f_flags);
+ if (IS_ERR(pid))
+ return ERR_CAST(pid);
+
+ /* We should be in an RCU read side critical section, it should be safe
+ * to call pid_task.
+ */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ task = pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ sdata = task_storage_lookup(task, map, true);
+ put_pid(pid);
+ return sdata ? sdata->data : NULL;
+out:
+ put_pid(pid);
+ return ERR_PTR(err);
+}
+
+static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ struct bpf_local_storage_data *sdata;
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ int fd, err;
+
+ fd = *(int *)key;
+ pid = pidfd_get_pid(fd, &f_flags);
+ if (IS_ERR(pid))
+ return PTR_ERR(pid);
+
+ /* We should be in an RCU read side critical section, it should be safe
+ * to call pid_task.
+ */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ task = pid_task(pid, PIDTYPE_PID);
+ if (!task || !task_storage_ptr(task)) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ sdata = bpf_local_storage_update(
+ task, (struct bpf_local_storage_map *)map, value, map_flags);
+
+ err = PTR_ERR_OR_ZERO(sdata);
+out:
+ put_pid(pid);
+ return err;
+}
+
+static int task_storage_delete(struct task_struct *task, struct bpf_map *map)
+{
+ struct bpf_local_storage_data *sdata;
+
+ sdata = task_storage_lookup(task, map, false);
+ if (!sdata)
+ return -ENOENT;
+
+ bpf_selem_unlink(SELEM(sdata));
+
+ return 0;
+}
+
+static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key)
+{
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ int fd, err;
+
+ fd = *(int *)key;
+ pid = pidfd_get_pid(fd, &f_flags);
+ if (IS_ERR(pid))
+ return PTR_ERR(pid);
+
+ /* We should be in an RCU read side critical section, it should be safe
+ * to call pid_task.
+ */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ task = pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ err = task_storage_delete(task, map);
+out:
+ put_pid(pid);
+ return err;
+}
+
+BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *,
+ task, void *, value, u64, flags)
+{
+ struct bpf_local_storage_data *sdata;
+
+ if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+ return (unsigned long)NULL;
+
+ /* explicitly check that the task_storage_ptr is not
+ * NULL as task_storage_lookup returns NULL in this case and
+ * bpf_local_storage_update expects the owner to have a
+ * valid storage pointer.
+ */
+ if (!task_storage_ptr(task))
+ return (unsigned long)NULL;
+
+ sdata = task_storage_lookup(task, map, true);
+ if (sdata)
+ return (unsigned long)sdata->data;
+
+ /* This helper must only be called from places where the lifetime of the task
+ * is guaranteed. Either by being refcounted or by being protected
+ * by an RCU read-side critical section.
+ */
+ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
+ sdata = bpf_local_storage_update(
+ task, (struct bpf_local_storage_map *)map, value,
+ BPF_NOEXIST);
+ return IS_ERR(sdata) ? (unsigned long)NULL :
+ (unsigned long)sdata->data;
+ }
+
+ return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
+ task)
+{
+ /* This helper must only be called from places where the lifetime of the task
+ * is guaranteed. Either by being refcounted or by being protected
+ * by an RCU read-side critical section.
+ */
+ return task_storage_delete(task, map);
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ return -ENOTSUPP;
+}
+
+static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = bpf_local_storage_map_alloc(attr);
+ if (IS_ERR(smap))
+ return ERR_CAST(smap);
+
+ smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache);
+ return &smap->map;
+}
+
+static void task_storage_map_free(struct bpf_map *map)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = (struct bpf_local_storage_map *)map;
+ bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx);
+ bpf_local_storage_map_free(smap);
+}
+
+static int task_storage_map_btf_id;
+const struct bpf_map_ops task_storage_map_ops = {
+ .map_meta_equal = bpf_map_meta_equal,
+ .map_alloc_check = bpf_local_storage_map_alloc_check,
+ .map_alloc = task_storage_map_alloc,
+ .map_free = task_storage_map_free,
+ .map_get_next_key = notsupp_get_next_key,
+ .map_lookup_elem = bpf_pid_task_storage_lookup_elem,
+ .map_update_elem = bpf_pid_task_storage_update_elem,
+ .map_delete_elem = bpf_pid_task_storage_delete_elem,
+ .map_check_btf = bpf_local_storage_map_check_btf,
+ .map_btf_name = "bpf_local_storage_map",
+ .map_btf_id = &task_storage_map_btf_id,
+ .map_owner_storage_ptr = task_storage_ptr,
+};
+
+BTF_ID_LIST_SINGLE(bpf_task_storage_btf_ids, struct, task_struct)
+
+const struct bpf_func_proto bpf_task_storage_get_proto = {
+ .func = bpf_task_storage_get,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &bpf_task_storage_btf_ids[0],
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+};
+
+const struct bpf_func_proto bpf_task_storage_delete_proto = {
+ .func = bpf_task_storage_delete,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &bpf_task_storage_btf_ids[0],
+};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ed7d02e8bc93..8d6bdb4f4d61 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -22,7 +22,8 @@
#include <linux/skmsg.h>
#include <linux/perf_event.h>
#include <linux/bsearch.h>
-#include <linux/btf_ids.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
#include <net/sock.h>
/* BTF (BPF Type Format) is the meta data format which describes
@@ -204,12 +205,19 @@ struct btf {
const char *strings;
void *nohdr_data;
struct btf_header hdr;
- u32 nr_types;
+ u32 nr_types; /* includes VOID for base BTF */
u32 types_size;
u32 data_size;
refcount_t refcnt;
u32 id;
struct rcu_head rcu;
+
+ /* split BTF support */
+ struct btf *base_btf;
+ u32 start_id; /* first type ID in this BTF (0 for base BTF) */
+ u32 start_str_off; /* first string offset (0 for base BTF) */
+ char name[MODULE_NAME_LEN];
+ bool kernel_btf;
};
enum verifier_phase {
@@ -450,14 +458,27 @@ static bool btf_type_is_datasec(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
}
+static u32 btf_nr_types_total(const struct btf *btf)
+{
+ u32 total = 0;
+
+ while (btf) {
+ total += btf->nr_types;
+ btf = btf->base_btf;
+ }
+
+ return total;
+}
+
s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
{
const struct btf_type *t;
const char *tname;
- u32 i;
+ u32 i, total;
- for (i = 1; i <= btf->nr_types; i++) {
- t = btf->types[i];
+ total = btf_nr_types_total(btf);
+ for (i = 1; i < total; i++) {
+ t = btf_type_by_id(btf, i);
if (BTF_INFO_KIND(t->info) != kind)
continue;
@@ -600,8 +621,14 @@ static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
{
- return BTF_STR_OFFSET_VALID(offset) &&
- offset < btf->hdr.str_len;
+ if (!BTF_STR_OFFSET_VALID(offset))
+ return false;
+
+ while (offset < btf->start_str_off)
+ btf = btf->base_btf;
+
+ offset -= btf->start_str_off;
+ return offset < btf->hdr.str_len;
}
static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
@@ -615,10 +642,22 @@ static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
return true;
}
+static const char *btf_str_by_offset(const struct btf *btf, u32 offset)
+{
+ while (offset < btf->start_str_off)
+ btf = btf->base_btf;
+
+ offset -= btf->start_str_off;
+ if (offset < btf->hdr.str_len)
+ return &btf->strings[offset];
+
+ return NULL;
+}
+
static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
{
/* offset must be valid */
- const char *src = &btf->strings[offset];
+ const char *src = btf_str_by_offset(btf, offset);
const char *src_limit;
if (!__btf_name_char_ok(*src, true, dot_ok))
@@ -651,27 +690,28 @@ static bool btf_name_valid_section(const struct btf *btf, u32 offset)
static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
{
+ const char *name;
+
if (!offset)
return "(anon)";
- else if (offset < btf->hdr.str_len)
- return &btf->strings[offset];
- else
- return "(invalid-name-offset)";
+
+ name = btf_str_by_offset(btf, offset);
+ return name ?: "(invalid-name-offset)";
}
const char *btf_name_by_offset(const struct btf *btf, u32 offset)
{
- if (offset < btf->hdr.str_len)
- return &btf->strings[offset];
-
- return NULL;
+ return btf_str_by_offset(btf, offset);
}
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
{
- if (type_id > btf->nr_types)
- return NULL;
+ while (type_id < btf->start_id)
+ btf = btf->base_btf;
+ type_id -= btf->start_id;
+ if (type_id >= btf->nr_types)
+ return NULL;
return btf->types[type_id];
}
@@ -1391,17 +1431,13 @@ static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t)
{
struct btf *btf = env->btf;
- /* < 2 because +1 for btf_void which is always in btf->types[0].
- * btf_void is not accounted in btf->nr_types because btf_void
- * does not come from the BTF file.
- */
- if (btf->types_size - btf->nr_types < 2) {
+ if (btf->types_size == btf->nr_types) {
/* Expand 'types' array */
struct btf_type **new_types;
u32 expand_by, new_size;
- if (btf->types_size == BTF_MAX_TYPE) {
+ if (btf->start_id + btf->types_size == BTF_MAX_TYPE) {
btf_verifier_log(env, "Exceeded max num of types");
return -E2BIG;
}
@@ -1415,18 +1451,23 @@ static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t)
if (!new_types)
return -ENOMEM;
- if (btf->nr_types == 0)
- new_types[0] = &btf_void;
- else
+ if (btf->nr_types == 0) {
+ if (!btf->base_btf) {
+ /* lazily init VOID type */
+ new_types[0] = &btf_void;
+ btf->nr_types++;
+ }
+ } else {
memcpy(new_types, btf->types,
- sizeof(*btf->types) * (btf->nr_types + 1));
+ sizeof(*btf->types) * btf->nr_types);
+ }
kvfree(btf->types);
btf->types = new_types;
btf->types_size = new_size;
}
- btf->types[++(btf->nr_types)] = t;
+ btf->types[btf->nr_types++] = t;
return 0;
}
@@ -1483,6 +1524,11 @@ static void btf_free_rcu(struct rcu_head *rcu)
btf_free(btf);
}
+void btf_get(struct btf *btf)
+{
+ refcount_inc(&btf->refcnt);
+}
+
void btf_put(struct btf *btf)
{
if (btf && refcount_dec_and_test(&btf->refcnt)) {
@@ -1499,18 +1545,17 @@ static int env_resolve_init(struct btf_verifier_env *env)
u32 *resolved_ids = NULL;
u8 *visit_states = NULL;
- /* +1 for btf_void */
- resolved_sizes = kvcalloc(nr_types + 1, sizeof(*resolved_sizes),
+ resolved_sizes = kvcalloc(nr_types, sizeof(*resolved_sizes),
GFP_KERNEL | __GFP_NOWARN);
if (!resolved_sizes)
goto nomem;
- resolved_ids = kvcalloc(nr_types + 1, sizeof(*resolved_ids),
+ resolved_ids = kvcalloc(nr_types, sizeof(*resolved_ids),
GFP_KERNEL | __GFP_NOWARN);
if (!resolved_ids)
goto nomem;
- visit_states = kvcalloc(nr_types + 1, sizeof(*visit_states),
+ visit_states = kvcalloc(nr_types, sizeof(*visit_states),
GFP_KERNEL | __GFP_NOWARN);
if (!visit_states)
goto nomem;
@@ -1562,21 +1607,27 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
static bool env_type_is_resolved(const struct btf_verifier_env *env,
u32 type_id)
{
- return env->visit_states[type_id] == RESOLVED;
+ /* base BTF types should be resolved by now */
+ if (type_id < env->btf->start_id)
+ return true;
+
+ return env->visit_states[type_id - env->btf->start_id] == RESOLVED;
}
static int env_stack_push(struct btf_verifier_env *env,
const struct btf_type *t, u32 type_id)
{
+ const struct btf *btf = env->btf;
struct resolve_vertex *v;
if (env->top_stack == MAX_RESOLVE_DEPTH)
return -E2BIG;
- if (env->visit_states[type_id] != NOT_VISITED)
+ if (type_id < btf->start_id
+ || env->visit_states[type_id - btf->start_id] != NOT_VISITED)
return -EEXIST;
- env->visit_states[type_id] = VISITED;
+ env->visit_states[type_id - btf->start_id] = VISITED;
v = &env->stack[env->top_stack++];
v->t = t;
@@ -1606,6 +1657,7 @@ static void env_stack_pop_resolved(struct btf_verifier_env *env,
u32 type_id = env->stack[--(env->top_stack)].type_id;
struct btf *btf = env->btf;
+ type_id -= btf->start_id; /* adjust to local type id */
btf->resolved_sizes[type_id] = resolved_size;
btf->resolved_ids[type_id] = resolved_type_id;
env->visit_states[type_id] = RESOLVED;
@@ -1710,14 +1762,30 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type,
return __btf_resolve_size(btf, type, type_size, NULL, NULL, NULL, NULL);
}
+static u32 btf_resolved_type_id(const struct btf *btf, u32 type_id)
+{
+ while (type_id < btf->start_id)
+ btf = btf->base_btf;
+
+ return btf->resolved_ids[type_id - btf->start_id];
+}
+
/* The input param "type_id" must point to a needs_resolve type */
static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
u32 *type_id)
{
- *type_id = btf->resolved_ids[*type_id];
+ *type_id = btf_resolved_type_id(btf, *type_id);
return btf_type_by_id(btf, *type_id);
}
+static u32 btf_resolved_type_size(const struct btf *btf, u32 type_id)
+{
+ while (type_id < btf->start_id)
+ btf = btf->base_btf;
+
+ return btf->resolved_sizes[type_id - btf->start_id];
+}
+
const struct btf_type *btf_type_id_size(const struct btf *btf,
u32 *type_id, u32 *ret_size)
{
@@ -1732,7 +1800,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
if (btf_type_has_size(size_type)) {
size = size_type->size;
} else if (btf_type_is_array(size_type)) {
- size = btf->resolved_sizes[size_type_id];
+ size = btf_resolved_type_size(btf, size_type_id);
} else if (btf_type_is_ptr(size_type)) {
size = sizeof(void *);
} else {
@@ -1740,14 +1808,14 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
!btf_type_is_var(size_type)))
return NULL;
- size_type_id = btf->resolved_ids[size_type_id];
+ size_type_id = btf_resolved_type_id(btf, size_type_id);
size_type = btf_type_by_id(btf, size_type_id);
if (btf_type_nosize_or_null(size_type))
return NULL;
else if (btf_type_has_size(size_type))
size = size_type->size;
else if (btf_type_is_array(size_type))
- size = btf->resolved_sizes[size_type_id];
+ size = btf_resolved_type_size(btf, size_type_id);
else if (btf_type_is_ptr(size_type))
size = sizeof(void *);
else
@@ -3799,7 +3867,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env)
cur = btf->nohdr_data + hdr->type_off;
end = cur + hdr->type_len;
- env->log_type_id = 1;
+ env->log_type_id = btf->base_btf ? btf->start_id : 1;
while (cur < end) {
struct btf_type *t = cur;
s32 meta_size;
@@ -3826,8 +3894,8 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
return false;
if (btf_type_is_struct(t) || btf_type_is_datasec(t))
- return !btf->resolved_ids[type_id] &&
- !btf->resolved_sizes[type_id];
+ return !btf_resolved_type_id(btf, type_id) &&
+ !btf_resolved_type_size(btf, type_id);
if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
btf_type_is_var(t)) {
@@ -3847,7 +3915,7 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
return elem_type && !btf_type_is_modifier(elem_type) &&
(array->nelems * elem_size ==
- btf->resolved_sizes[type_id]);
+ btf_resolved_type_size(btf, type_id));
}
return false;
@@ -3889,7 +3957,8 @@ static int btf_resolve(struct btf_verifier_env *env,
static int btf_check_all_types(struct btf_verifier_env *env)
{
struct btf *btf = env->btf;
- u32 type_id;
+ const struct btf_type *t;
+ u32 type_id, i;
int err;
err = env_resolve_init(env);
@@ -3897,8 +3966,9 @@ static int btf_check_all_types(struct btf_verifier_env *env)
return err;
env->phase++;
- for (type_id = 1; type_id <= btf->nr_types; type_id++) {
- const struct btf_type *t = btf_type_by_id(btf, type_id);
+ for (i = btf->base_btf ? 0 : 1; i < btf->nr_types; i++) {
+ type_id = btf->start_id + i;
+ t = btf_type_by_id(btf, type_id);
env->log_type_id = type_id;
if (btf_type_needs_resolve(t) &&
@@ -3935,7 +4005,7 @@ static int btf_parse_type_sec(struct btf_verifier_env *env)
return -EINVAL;
}
- if (!hdr->type_len) {
+ if (!env->btf->base_btf && !hdr->type_len) {
btf_verifier_log(env, "No type found");
return -EINVAL;
}
@@ -3962,13 +4032,18 @@ static int btf_parse_str_sec(struct btf_verifier_env *env)
return -EINVAL;
}
- if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
- start[0] || end[-1]) {
+ btf->strings = start;
+
+ if (btf->base_btf && !hdr->str_len)
+ return 0;
+ if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || end[-1]) {
+ btf_verifier_log(env, "Invalid string section");
+ return -EINVAL;
+ }
+ if (!btf->base_btf && start[0]) {
btf_verifier_log(env, "Invalid string section");
return -EINVAL;
}
-
- btf->strings = start;
return 0;
}
@@ -4363,6 +4438,8 @@ struct btf *btf_parse_vmlinux(void)
btf->data = __start_BTF;
btf->data_size = __stop_BTF - __start_BTF;
+ btf->kernel_btf = true;
+ snprintf(btf->name, sizeof(btf->name), "vmlinux");
err = btf_parse_hdr(env);
if (err)
@@ -4388,6 +4465,81 @@ struct btf *btf_parse_vmlinux(void)
bpf_struct_ops_init(btf, log);
+ refcount_set(&btf->refcnt, 1);
+
+ err = btf_alloc_id(btf);
+ if (err)
+ goto errout;
+
+ btf_verifier_env_free(env);
+ return btf;
+
+errout:
+ btf_verifier_env_free(env);
+ if (btf) {
+ kvfree(btf->types);
+ kfree(btf);
+ }
+ return ERR_PTR(err);
+}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+
+static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size)
+{
+ struct btf_verifier_env *env = NULL;
+ struct bpf_verifier_log *log;
+ struct btf *btf = NULL, *base_btf;
+ int err;
+
+ base_btf = bpf_get_btf_vmlinux();
+ if (IS_ERR(base_btf))
+ return base_btf;
+ if (!base_btf)
+ return ERR_PTR(-EINVAL);
+
+ env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+ if (!env)
+ return ERR_PTR(-ENOMEM);
+
+ log = &env->log;
+ log->level = BPF_LOG_KERNEL;
+
+ btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
+ if (!btf) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ env->btf = btf;
+
+ btf->base_btf = base_btf;
+ btf->start_id = base_btf->nr_types;
+ btf->start_str_off = base_btf->hdr.str_len;
+ btf->kernel_btf = true;
+ snprintf(btf->name, sizeof(btf->name), "%s", module_name);
+
+ btf->data = kvmalloc(data_size, GFP_KERNEL | __GFP_NOWARN);
+ if (!btf->data) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ memcpy(btf->data, data, data_size);
+ btf->data_size = data_size;
+
+ err = btf_parse_hdr(env);
+ if (err)
+ goto errout;
+
+ btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
+ err = btf_parse_str_sec(env);
+ if (err)
+ goto errout;
+
+ err = btf_check_all_metas(env);
+ if (err)
+ goto errout;
+
btf_verifier_env_free(env);
refcount_set(&btf->refcnt, 1);
return btf;
@@ -4395,21 +4547,23 @@ struct btf *btf_parse_vmlinux(void)
errout:
btf_verifier_env_free(env);
if (btf) {
+ kvfree(btf->data);
kvfree(btf->types);
kfree(btf);
}
return ERR_PTR(err);
}
+#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */
+
struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
{
struct bpf_prog *tgt_prog = prog->aux->dst_prog;
- if (tgt_prog) {
+ if (tgt_prog)
return tgt_prog->aux->btf;
- } else {
- return btf_vmlinux;
- }
+ else
+ return prog->aux->attach_btf;
}
static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
@@ -4550,6 +4704,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
if (ctx_arg_info->offset == off) {
info->reg_type = ctx_arg_info->reg_type;
+ info->btf = btf_vmlinux;
info->btf_id = ctx_arg_info->btf_id;
return true;
}
@@ -4566,6 +4721,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg);
if (ret > 0) {
+ info->btf = btf_vmlinux;
info->btf_id = ret;
return true;
} else {
@@ -4573,6 +4729,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
}
}
+ info->btf = btf;
info->btf_id = t->type;
t = btf_type_by_id(btf, t->type);
/* skip modifiers */
@@ -4599,7 +4756,7 @@ enum bpf_struct_walk_result {
WALK_STRUCT,
};
-static int btf_struct_walk(struct bpf_verifier_log *log,
+static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
const struct btf_type *t, int off, int size,
u32 *next_btf_id)
{
@@ -4610,7 +4767,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log,
u32 vlen, elem_id, mid;
again:
- tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+ tname = __btf_name_by_offset(btf, t->name_off);
if (!btf_type_is_struct(t)) {
bpf_log(log, "Type '%s' is not a struct\n", tname);
return -EINVAL;
@@ -4627,7 +4784,7 @@ again:
goto error;
member = btf_type_member(t) + vlen - 1;
- mtype = btf_type_skip_modifiers(btf_vmlinux, member->type,
+ mtype = btf_type_skip_modifiers(btf, member->type,
NULL);
if (!btf_type_is_array(mtype))
goto error;
@@ -4643,7 +4800,7 @@ again:
/* Only allow structure for now, can be relaxed for
* other types later.
*/
- t = btf_type_skip_modifiers(btf_vmlinux, array_elem->type,
+ t = btf_type_skip_modifiers(btf, array_elem->type,
NULL);
if (!btf_type_is_struct(t))
goto error;
@@ -4701,10 +4858,10 @@ error:
/* type of the field */
mid = member->type;
- mtype = btf_type_by_id(btf_vmlinux, member->type);
- mname = __btf_name_by_offset(btf_vmlinux, member->name_off);
+ mtype = btf_type_by_id(btf, member->type);
+ mname = __btf_name_by_offset(btf, member->name_off);
- mtype = __btf_resolve_size(btf_vmlinux, mtype, &msize,
+ mtype = __btf_resolve_size(btf, mtype, &msize,
&elem_type, &elem_id, &total_nelems,
&mid);
if (IS_ERR(mtype)) {
@@ -4799,7 +4956,7 @@ error:
mname, moff, tname, off, size);
return -EACCES;
}
- stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id);
+ stype = btf_type_skip_modifiers(btf, mtype->type, &id);
if (btf_type_is_struct(stype)) {
*next_btf_id = id;
return WALK_PTR;
@@ -4825,7 +4982,7 @@ error:
return -EINVAL;
}
-int btf_struct_access(struct bpf_verifier_log *log,
+int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
const struct btf_type *t, int off, int size,
enum bpf_access_type atype __maybe_unused,
u32 *next_btf_id)
@@ -4834,7 +4991,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
u32 id;
do {
- err = btf_struct_walk(log, t, off, size, &id);
+ err = btf_struct_walk(log, btf, t, off, size, &id);
switch (err) {
case WALK_PTR:
@@ -4850,7 +5007,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
* by diving in it. At this point the offset is
* aligned with the new type, so set it to 0.
*/
- t = btf_type_by_id(btf_vmlinux, id);
+ t = btf_type_by_id(btf, id);
off = 0;
break;
default:
@@ -4866,21 +5023,37 @@ int btf_struct_access(struct bpf_verifier_log *log,
return -EINVAL;
}
+/* Check that two BTF types, each specified as an BTF object + id, are exactly
+ * the same. Trivial ID check is not enough due to module BTFs, because we can
+ * end up with two different module BTFs, but IDs point to the common type in
+ * vmlinux BTF.
+ */
+static bool btf_types_are_same(const struct btf *btf1, u32 id1,
+ const struct btf *btf2, u32 id2)
+{
+ if (id1 != id2)
+ return false;
+ if (btf1 == btf2)
+ return true;
+ return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2);
+}
+
bool btf_struct_ids_match(struct bpf_verifier_log *log,
- int off, u32 id, u32 need_type_id)
+ const struct btf *btf, u32 id, int off,
+ const struct btf *need_btf, u32 need_type_id)
{
const struct btf_type *type;
int err;
/* Are we already done? */
- if (need_type_id == id && off == 0)
+ if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id))
return true;
again:
- type = btf_type_by_id(btf_vmlinux, id);
+ type = btf_type_by_id(btf, id);
if (!type)
return false;
- err = btf_struct_walk(log, type, off, 1, &id);
+ err = btf_struct_walk(log, btf, type, off, 1, &id);
if (err != WALK_STRUCT)
return false;
@@ -4889,7 +5062,7 @@ again:
* continue the search with offset 0 in the new
* type.
*/
- if (need_type_id != id) {
+ if (!btf_types_are_same(btf, id, need_btf, need_type_id)) {
off = 0;
goto again;
}
@@ -4909,7 +5082,7 @@ static int __get_type_size(struct btf *btf, u32 btf_id,
while (t && btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
if (!t) {
- *bad_type = btf->types[0];
+ *bad_type = btf_type_by_id(btf, 0);
return -EINVAL;
}
if (btf_type_is_ptr(t))
@@ -5487,7 +5660,9 @@ int btf_get_info_by_fd(const struct btf *btf,
struct bpf_btf_info info;
u32 info_copy, btf_copy;
void __user *ubtf;
- u32 uinfo_len;
+ char __user *uname;
+ u32 uinfo_len, uname_len, name_len;
+ int ret = 0;
uinfo = u64_to_user_ptr(attr->info.info);
uinfo_len = attr->info.info_len;
@@ -5504,11 +5679,37 @@ int btf_get_info_by_fd(const struct btf *btf,
return -EFAULT;
info.btf_size = btf->data_size;
+ info.kernel_btf = btf->kernel_btf;
+
+ uname = u64_to_user_ptr(info.name);
+ uname_len = info.name_len;
+ if (!uname ^ !uname_len)
+ return -EINVAL;
+
+ name_len = strlen(btf->name);
+ info.name_len = name_len;
+
+ if (uname) {
+ if (uname_len >= name_len + 1) {
+ if (copy_to_user(uname, btf->name, name_len + 1))
+ return -EFAULT;
+ } else {
+ char zero = '\0';
+
+ if (copy_to_user(uname, btf->name, uname_len - 1))
+ return -EFAULT;
+ if (put_user(zero, uname + uname_len - 1))
+ return -EFAULT;
+ /* let user-space know about too short buffer */
+ ret = -ENOSPC;
+ }
+ }
+
if (copy_to_user(uinfo, &info, info_copy) ||
put_user(info_copy, &uattr->info.info_len))
return -EFAULT;
- return 0;
+ return ret;
}
int btf_get_fd_by_id(u32 id)
@@ -5532,11 +5733,16 @@ int btf_get_fd_by_id(u32 id)
return fd;
}
-u32 btf_id(const struct btf *btf)
+u32 btf_obj_id(const struct btf *btf)
{
return btf->id;
}
+bool btf_is_kernel(const struct btf *btf)
+{
+ return btf->kernel_btf;
+}
+
static int btf_id_cmp_func(const void *a, const void *b)
{
const int *pa = a, *pb = b;
@@ -5548,3 +5754,126 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
{
return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+struct btf_module {
+ struct list_head list;
+ struct module *module;
+ struct btf *btf;
+ struct bin_attribute *sysfs_attr;
+};
+
+static LIST_HEAD(btf_modules);
+static DEFINE_MUTEX(btf_module_mutex);
+
+static ssize_t
+btf_module_read(struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buf, loff_t off, size_t len)
+{
+ const struct btf *btf = bin_attr->private;
+
+ memcpy(buf, btf->data + off, len);
+ return len;
+}
+
+static int btf_module_notify(struct notifier_block *nb, unsigned long op,
+ void *module)
+{
+ struct btf_module *btf_mod, *tmp;
+ struct module *mod = module;
+ struct btf *btf;
+ int err = 0;
+
+ if (mod->btf_data_size == 0 ||
+ (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+ goto out;
+
+ switch (op) {
+ case MODULE_STATE_COMING:
+ btf_mod = kzalloc(sizeof(*btf_mod), GFP_KERNEL);
+ if (!btf_mod) {
+ err = -ENOMEM;
+ goto out;
+ }
+ btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size);
+ if (IS_ERR(btf)) {
+ pr_warn("failed to validate module [%s] BTF: %ld\n",
+ mod->name, PTR_ERR(btf));
+ kfree(btf_mod);
+ err = PTR_ERR(btf);
+ goto out;
+ }
+ err = btf_alloc_id(btf);
+ if (err) {
+ btf_free(btf);
+ kfree(btf_mod);
+ goto out;
+ }
+
+ mutex_lock(&btf_module_mutex);
+ btf_mod->module = module;
+ btf_mod->btf = btf;
+ list_add(&btf_mod->list, &btf_modules);
+ mutex_unlock(&btf_module_mutex);
+
+ if (IS_ENABLED(CONFIG_SYSFS)) {
+ struct bin_attribute *attr;
+
+ attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+ if (!attr)
+ goto out;
+
+ sysfs_bin_attr_init(attr);
+ attr->attr.name = btf->name;
+ attr->attr.mode = 0444;
+ attr->size = btf->data_size;
+ attr->private = btf;
+ attr->read = btf_module_read;
+
+ err = sysfs_create_bin_file(btf_kobj, attr);
+ if (err) {
+ pr_warn("failed to register module [%s] BTF in sysfs: %d\n",
+ mod->name, err);
+ kfree(attr);
+ err = 0;
+ goto out;
+ }
+
+ btf_mod->sysfs_attr = attr;
+ }
+
+ break;
+ case MODULE_STATE_GOING:
+ mutex_lock(&btf_module_mutex);
+ list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+ if (btf_mod->module != module)
+ continue;
+
+ list_del(&btf_mod->list);
+ if (btf_mod->sysfs_attr)
+ sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
+ btf_put(btf_mod->btf);
+ kfree(btf_mod->sysfs_attr);
+ kfree(btf_mod);
+ break;
+ }
+ mutex_unlock(&btf_module_mutex);
+ break;
+ }
+out:
+ return notifier_from_errno(err);
+}
+
+static struct notifier_block btf_module_nb = {
+ .notifier_call = btf_module_notify,
+};
+
+static int __init btf_module_init(void)
+{
+ register_module_notifier(&btf_module_nb);
+ return 0;
+}
+
+fs_initcall(btf_module_init);
+#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 55454d2278b1..261f8692d0d2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
@@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
if (fp == NULL)
return NULL;
- aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
+ aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
if (aux == NULL) {
vfree(fp);
return NULL;
@@ -106,7 +106,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *prog;
int cpu;
@@ -138,7 +138,7 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo,
sizeof(*prog->aux->jited_linfo),
- GFP_KERNEL | __GFP_NOWARN);
+ GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!prog->aux->jited_linfo)
return -ENOMEM;
@@ -219,25 +219,17 @@ void bpf_prog_free_linfo(struct bpf_prog *prog)
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
- u32 pages, delta;
- int ret;
+ u32 pages;
size = round_up(size, PAGE_SIZE);
pages = size / PAGE_SIZE;
if (pages <= fp_old->pages)
return fp_old;
- delta = pages - fp_old->pages;
- ret = __bpf_prog_charge(fp_old->aux->user, delta);
- if (ret)
- return NULL;
-
fp = __vmalloc(size, gfp_flags);
- if (fp == NULL) {
- __bpf_prog_uncharge(fp_old->aux->user, delta);
- } else {
+ if (fp) {
memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
fp->pages = pages;
fp->aux->prog = fp;
@@ -2211,6 +2203,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak;
const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index c61a23b564aa..747313698178 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -84,8 +84,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
u32 value_size = attr->value_size;
struct bpf_cpu_map *cmap;
int err = -ENOMEM;
- u64 cost;
- int ret;
if (!bpf_capable())
return ERR_PTR(-EPERM);
@@ -97,7 +95,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
attr->map_flags & ~BPF_F_NUMA_NODE)
return ERR_PTR(-EINVAL);
- cmap = kzalloc(sizeof(*cmap), GFP_USER);
+ cmap = kzalloc(sizeof(*cmap), GFP_USER | __GFP_ACCOUNT);
if (!cmap)
return ERR_PTR(-ENOMEM);
@@ -109,26 +107,14 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
goto free_cmap;
}
- /* make sure page count doesn't overflow */
- cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
-
- /* Notice returns -EPERM on if map size is larger than memlock limit */
- ret = bpf_map_charge_init(&cmap->map.memory, cost);
- if (ret) {
- err = ret;
- goto free_cmap;
- }
-
/* Alloc array for possible remote "destination" CPUs */
cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
sizeof(struct bpf_cpu_map_entry *),
cmap->map.numa_node);
if (!cmap->cpu_map)
- goto free_charge;
+ goto free_cmap;
return &cmap->map;
-free_charge:
- bpf_map_charge_finish(&cmap->map.memory);
free_cmap:
kfree(cmap);
return ERR_PTR(err);
@@ -412,7 +398,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
}
static struct bpf_cpu_map_entry *
-__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
+__cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
+ u32 cpu)
{
int numa, err, i, fd = value->bpf_prog.fd;
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
@@ -422,13 +409,13 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
/* Have map->numa_node, but choose node of redirect target CPU */
numa = cpu_to_node(cpu);
- rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+ rcpu = bpf_map_kmalloc_node(map, sizeof(*rcpu), gfp | __GFP_ZERO, numa);
if (!rcpu)
return NULL;
/* Alloc percpu bulkq */
- rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
- sizeof(void *), gfp);
+ rcpu->bulkq = bpf_map_alloc_percpu(map, sizeof(*rcpu->bulkq),
+ sizeof(void *), gfp);
if (!rcpu->bulkq)
goto free_rcu;
@@ -438,7 +425,8 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
}
/* Alloc queue */
- rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+ rcpu->queue = bpf_map_kmalloc_node(map, sizeof(*rcpu->queue), gfp,
+ numa);
if (!rcpu->queue)
goto free_bulkq;
@@ -447,7 +435,7 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
goto free_queue;
rcpu->cpu = cpu;
- rcpu->map_id = map_id;
+ rcpu->map_id = map->id;
rcpu->value.qsize = value->qsize;
if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
@@ -455,7 +443,8 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
/* Setup kthread */
rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
- "cpumap/%d/map:%d", cpu, map_id);
+ "cpumap/%d/map:%d", cpu,
+ map->id);
if (IS_ERR(rcpu->kthread))
goto free_prog;
@@ -571,7 +560,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
rcpu = NULL; /* Same as deleting */
} else {
/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
- rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id);
+ rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
if (!rcpu)
return -ENOMEM;
rcpu->cmap = cmap;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2b5ca93c17de..f6e9c68afdd4 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -109,8 +109,6 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
{
u32 valsize = attr->value_size;
- u64 cost = 0;
- int err;
/* check sanity of attributes. 2 value sizes supported:
* 4 bytes: ifindex
@@ -135,21 +133,13 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
if (!dtab->n_buckets) /* Overflow check */
return -EINVAL;
- cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets;
- } else {
- cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
}
- /* if map size is larger than memlock limit, reject it */
- err = bpf_map_charge_init(&dtab->map.memory, cost);
- if (err)
- return -EINVAL;
-
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
dtab->map.numa_node);
if (!dtab->dev_index_head)
- goto free_charge;
+ return -ENOMEM;
spin_lock_init(&dtab->index_lock);
} else {
@@ -157,14 +147,10 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
sizeof(struct bpf_dtab_netdev *),
dtab->map.numa_node);
if (!dtab->netdev_map)
- goto free_charge;
+ return -ENOMEM;
}
return 0;
-
-free_charge:
- bpf_map_charge_finish(&dtab->map.memory);
- return -ENOMEM;
}
static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
@@ -175,7 +161,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
if (!capable(CAP_NET_ADMIN))
return ERR_PTR(-EPERM);
- dtab = kzalloc(sizeof(*dtab), GFP_USER);
+ dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT);
if (!dtab)
return ERR_PTR(-ENOMEM);
@@ -602,8 +588,9 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
struct bpf_prog *prog = NULL;
struct bpf_dtab_netdev *dev;
- dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
- dtab->map.numa_node);
+ dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev),
+ GFP_ATOMIC | __GFP_NOWARN,
+ dtab->map.numa_node);
if (!dev)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 1fccba6e88c4..7e848200cd26 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -86,6 +86,9 @@ struct bucket {
};
};
+#define HASHTAB_MAP_LOCK_COUNT 8
+#define HASHTAB_MAP_LOCK_MASK (HASHTAB_MAP_LOCK_COUNT - 1)
+
struct bpf_htab {
struct bpf_map map;
struct bucket *buckets;
@@ -99,6 +102,8 @@ struct bpf_htab {
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
u32 hashrnd;
+ struct lock_class_key lockdep_key;
+ int __percpu *map_locked[HASHTAB_MAP_LOCK_COUNT];
};
/* each htab element is struct htab_elem + key + value */
@@ -138,33 +143,53 @@ static void htab_init_buckets(struct bpf_htab *htab)
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
- if (htab_use_raw_lock(htab))
+ if (htab_use_raw_lock(htab)) {
raw_spin_lock_init(&htab->buckets[i].raw_lock);
- else
+ lockdep_set_class(&htab->buckets[i].raw_lock,
+ &htab->lockdep_key);
+ } else {
spin_lock_init(&htab->buckets[i].lock);
+ lockdep_set_class(&htab->buckets[i].lock,
+ &htab->lockdep_key);
+ }
}
}
-static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab,
- struct bucket *b)
+static inline int htab_lock_bucket(const struct bpf_htab *htab,
+ struct bucket *b, u32 hash,
+ unsigned long *pflags)
{
unsigned long flags;
+ hash = hash & HASHTAB_MAP_LOCK_MASK;
+
+ migrate_disable();
+ if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
+ __this_cpu_dec(*(htab->map_locked[hash]));
+ migrate_enable();
+ return -EBUSY;
+ }
+
if (htab_use_raw_lock(htab))
raw_spin_lock_irqsave(&b->raw_lock, flags);
else
spin_lock_irqsave(&b->lock, flags);
- return flags;
+ *pflags = flags;
+
+ return 0;
}
static inline void htab_unlock_bucket(const struct bpf_htab *htab,
- struct bucket *b,
+ struct bucket *b, u32 hash,
unsigned long flags)
{
+ hash = hash & HASHTAB_MAP_LOCK_MASK;
if (htab_use_raw_lock(htab))
raw_spin_unlock_irqrestore(&b->raw_lock, flags);
else
spin_unlock_irqrestore(&b->lock, flags);
+ __this_cpu_dec(*(htab->map_locked[hash]));
+ migrate_enable();
}
static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -199,7 +224,7 @@ static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
{
- return (struct htab_elem *) (htab->elems + i * htab->elem_size);
+ return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size);
}
static void htab_free_elems(struct bpf_htab *htab)
@@ -255,7 +280,7 @@ static int prealloc_init(struct bpf_htab *htab)
if (!htab_is_percpu(htab) && !htab_is_lru(htab))
num_entries += num_possible_cpus();
- htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries,
+ htab->elems = bpf_map_area_alloc((u64)htab->elem_size * num_entries,
htab->map.numa_node);
if (!htab->elems)
return -ENOMEM;
@@ -267,7 +292,8 @@ static int prealloc_init(struct bpf_htab *htab)
u32 size = round_up(htab->map.value_size, 8);
void __percpu *pptr;
- pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN);
+ pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
+ GFP_USER | __GFP_NOWARN);
if (!pptr)
goto free_elems;
htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
@@ -321,8 +347,8 @@ static int alloc_extra_elems(struct bpf_htab *htab)
struct pcpu_freelist_node *l;
int cpu;
- pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8,
- GFP_USER | __GFP_NOWARN);
+ pptr = bpf_map_alloc_percpu(&htab->map, sizeof(struct htab_elem *), 8,
+ GFP_USER | __GFP_NOWARN);
if (!pptr)
return -ENOMEM;
@@ -390,17 +416,11 @@ static int htab_map_alloc_check(union bpf_attr *attr)
attr->value_size == 0)
return -EINVAL;
- if (attr->key_size > MAX_BPF_STACK)
- /* eBPF programs initialize keys on stack, so they cannot be
- * larger than max stack size
- */
- return -E2BIG;
-
- if (attr->value_size >= KMALLOC_MAX_SIZE -
- MAX_BPF_STACK - sizeof(struct htab_elem))
- /* if value_size is bigger, the user space won't be able to
- * access the elements via bpf syscall. This check also makes
- * sure that the elem_size doesn't overflow and it's
+ if ((u64)attr->key_size + attr->value_size >= KMALLOC_MAX_SIZE -
+ sizeof(struct htab_elem))
+ /* if key_size + value_size is bigger, the user space won't be
+ * able to access the elements via bpf syscall. This check
+ * also makes sure that the elem_size doesn't overflow and it's
* kmalloc-able later in htab_map_update_elem()
*/
return -E2BIG;
@@ -422,13 +442,14 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
struct bpf_htab *htab;
- u64 cost;
- int err;
+ int err, i;
- htab = kzalloc(sizeof(*htab), GFP_USER);
+ htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT);
if (!htab)
return ERR_PTR(-ENOMEM);
+ lockdep_register_key(&htab->lockdep_key);
+
bpf_map_init_from_attr(&htab->map, attr);
if (percpu_lru) {
@@ -459,26 +480,21 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
htab->n_buckets > U32_MAX / sizeof(struct bucket))
goto free_htab;
- cost = (u64) htab->n_buckets * sizeof(struct bucket) +
- (u64) htab->elem_size * htab->map.max_entries;
-
- if (percpu)
- cost += (u64) round_up(htab->map.value_size, 8) *
- num_possible_cpus() * htab->map.max_entries;
- else
- cost += (u64) htab->elem_size * num_possible_cpus();
-
- /* if map size is larger than memlock limit, reject it */
- err = bpf_map_charge_init(&htab->map.memory, cost);
- if (err)
- goto free_htab;
-
err = -ENOMEM;
htab->buckets = bpf_map_area_alloc(htab->n_buckets *
sizeof(struct bucket),
htab->map.numa_node);
if (!htab->buckets)
- goto free_charge;
+ goto free_htab;
+
+ for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
+ htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map,
+ sizeof(int),
+ sizeof(int),
+ GFP_USER);
+ if (!htab->map_locked[i])
+ goto free_map_locked;
+ }
if (htab->map.map_flags & BPF_F_ZERO_SEED)
htab->hashrnd = 0;
@@ -490,7 +506,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
if (prealloc) {
err = prealloc_init(htab);
if (err)
- goto free_buckets;
+ goto free_map_locked;
if (!percpu && !lru) {
/* lru itself can remove the least used element, so
@@ -506,11 +522,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
free_prealloc:
prealloc_destroy(htab);
-free_buckets:
+free_map_locked:
+ for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
+ free_percpu(htab->map_locked[i]);
bpf_map_area_free(htab->buckets);
-free_charge:
- bpf_map_charge_finish(&htab->map.memory);
free_htab:
+ lockdep_unregister_key(&htab->lockdep_key);
kfree(htab);
return ERR_PTR(err);
}
@@ -687,12 +704,15 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
struct hlist_nulls_node *n;
unsigned long flags;
struct bucket *b;
+ int ret;
tgt_l = container_of(node, struct htab_elem, lru_node);
b = __select_bucket(htab, tgt_l->hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags);
+ if (ret)
+ return false;
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
if (l == tgt_l) {
@@ -700,7 +720,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
break;
}
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, tgt_l->hash, flags);
return l == tgt_l;
}
@@ -891,8 +911,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new = ERR_PTR(-E2BIG);
goto dec_count;
}
- l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
- htab->map.numa_node);
+ l_new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
+ GFP_ATOMIC | __GFP_NOWARN,
+ htab->map.numa_node);
if (!l_new) {
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
@@ -908,8 +929,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
pptr = htab_elem_get_ptr(l_new, key_size);
} else {
/* alloc_percpu zero-fills */
- pptr = __alloc_percpu_gfp(size, 8,
- GFP_ATOMIC | __GFP_NOWARN);
+ pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
+ GFP_ATOMIC | __GFP_NOWARN);
if (!pptr) {
kfree(l_new);
l_new = ERR_PTR(-ENOMEM);
@@ -998,7 +1019,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
*/
}
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
@@ -1039,7 +1062,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
return ret;
}
@@ -1077,7 +1100,9 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
return -ENOMEM;
memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
@@ -1096,7 +1121,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
if (ret)
bpf_lru_push_free(&htab->lru, &l_new->lru_node);
@@ -1131,7 +1156,9 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
b = __select_bucket(htab, hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
@@ -1154,7 +1181,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
return ret;
}
@@ -1194,7 +1221,9 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
return -ENOMEM;
}
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
@@ -1216,7 +1245,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
if (l_new)
bpf_lru_push_free(&htab->lru, &l_new->lru_node);
return ret;
@@ -1244,7 +1273,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
struct htab_elem *l;
unsigned long flags;
u32 hash, key_size;
- int ret = -ENOENT;
+ int ret;
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
@@ -1254,17 +1283,20 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l = lookup_elem_raw(head, hash, key, key_size);
if (l) {
hlist_nulls_del_rcu(&l->hash_node);
free_htab_elem(htab, l);
- ret = 0;
+ } else {
+ ret = -ENOENT;
}
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
return ret;
}
@@ -1276,7 +1308,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
struct htab_elem *l;
unsigned long flags;
u32 hash, key_size;
- int ret = -ENOENT;
+ int ret;
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
@@ -1286,16 +1318,18 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l = lookup_elem_raw(head, hash, key, key_size);
- if (l) {
+ if (l)
hlist_nulls_del_rcu(&l->hash_node);
- ret = 0;
- }
+ else
+ ret = -ENOENT;
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
if (l)
bpf_lru_push_free(&htab->lru, &l->lru_node);
return ret;
@@ -1321,6 +1355,7 @@ static void delete_all_elements(struct bpf_htab *htab)
static void htab_map_free(struct bpf_map *map)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ int i;
/* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback.
* bpf_free_used_maps() is called after bpf prog is no longer executing.
@@ -1338,6 +1373,9 @@ static void htab_map_free(struct bpf_map *map)
free_percpu(htab->extra_elems);
bpf_map_area_free(htab->buckets);
+ for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
+ free_percpu(htab->map_locked[i]);
+ lockdep_unregister_key(&htab->lockdep_key);
kfree(htab);
}
@@ -1374,7 +1412,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val;
void __user *uvalues = u64_to_user_ptr(attr->batch.values);
void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
- void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
+ void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
u32 batch, max_count, size, bucket_size;
struct htab_elem *node_to_free = NULL;
u64 elem_map_flags, map_flags;
@@ -1441,8 +1479,11 @@ again_nocopy:
b = &htab->buckets[batch];
head = &b->head;
/* do not grab the lock unless need it (bucket_cnt > 0). */
- if (locked)
- flags = htab_lock_bucket(htab, b);
+ if (locked) {
+ ret = htab_lock_bucket(htab, b, batch, &flags);
+ if (ret)
+ goto next_batch;
+ }
bucket_cnt = 0;
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
@@ -1459,7 +1500,7 @@ again_nocopy:
/* Note that since bucket_cnt > 0 here, it is implicit
* that the locked was grabbed, so release it.
*/
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, batch, flags);
rcu_read_unlock();
bpf_enable_instrumentation();
goto after_loop;
@@ -1470,7 +1511,7 @@ again_nocopy:
/* Note that since bucket_cnt > 0 here, it is implicit
* that the locked was grabbed, so release it.
*/
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, batch, flags);
rcu_read_unlock();
bpf_enable_instrumentation();
kvfree(keys);
@@ -1523,7 +1564,7 @@ again_nocopy:
dst_val += value_size;
}
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, batch, flags);
locked = false;
while (node_to_free) {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index deda1185237b..bd8a3183d030 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
.ret_type = RET_INTEGER,
};
+BPF_CALL_0(bpf_ktime_get_coarse_ns)
+{
+ return ktime_get_coarse_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = {
+ .func = bpf_ktime_get_coarse_ns,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+};
+
BPF_CALL_0(bpf_get_current_pid_tgid)
{
struct task_struct *task = current;
@@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_ringbuf_output:
return &bpf_ringbuf_output_proto;
case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 571bb351ed3b..2d4f9ac12377 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -164,10 +164,10 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
return 0;
}
- new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
- map->value_size,
- __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
- map->numa_node);
+ new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) +
+ map->value_size,
+ __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
+ map->numa_node);
if (!new)
return -ENOMEM;
@@ -287,8 +287,6 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
{
int numa_node = bpf_map_attr_numa_node(attr);
struct bpf_cgroup_storage_map *map;
- struct bpf_map_memory mem;
- int ret;
if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) &&
attr->key_size != sizeof(__u64))
@@ -308,18 +306,10 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
/* max_entries is not used and enforced to be 0 */
return ERR_PTR(-EINVAL);
- ret = bpf_map_charge_init(&mem, sizeof(struct bpf_cgroup_storage_map));
- if (ret < 0)
- return ERR_PTR(ret);
-
map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map),
- __GFP_ZERO | GFP_USER, numa_node);
- if (!map) {
- bpf_map_charge_finish(&mem);
+ __GFP_ZERO | GFP_USER | __GFP_ACCOUNT, numa_node);
+ if (!map)
return ERR_PTR(-ENOMEM);
- }
-
- bpf_map_charge_move(&map->map.memory, &mem);
/* copy mandatory map attributes */
bpf_map_init_from_attr(&map->map, attr);
@@ -496,9 +486,9 @@ static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages)
struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
enum bpf_cgroup_storage_type stype)
{
+ const gfp_t gfp = __GFP_ZERO | GFP_USER;
struct bpf_cgroup_storage *storage;
struct bpf_map *map;
- gfp_t flags;
size_t size;
u32 pages;
@@ -508,23 +498,19 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
size = bpf_cgroup_storage_calculate_size(map, &pages);
- if (bpf_map_charge_memlock(map, pages))
- return ERR_PTR(-EPERM);
-
- storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
- __GFP_ZERO | GFP_USER, map->numa_node);
+ storage = bpf_map_kmalloc_node(map, sizeof(struct bpf_cgroup_storage),
+ gfp, map->numa_node);
if (!storage)
goto enomem;
- flags = __GFP_ZERO | GFP_USER;
-
if (stype == BPF_CGROUP_STORAGE_SHARED) {
- storage->buf = kmalloc_node(size, flags, map->numa_node);
+ storage->buf = bpf_map_kmalloc_node(map, size, gfp,
+ map->numa_node);
if (!storage->buf)
goto enomem;
check_and_init_map_lock(map, storage->buf->data);
} else {
- storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags);
+ storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp);
if (!storage->percpu_buf)
goto enomem;
}
@@ -534,7 +520,6 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
return storage;
enomem:
- bpf_map_uncharge_memlock(map, pages);
kfree(storage);
return ERR_PTR(-ENOMEM);
}
@@ -561,16 +546,11 @@ void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
{
enum bpf_cgroup_storage_type stype;
struct bpf_map *map;
- u32 pages;
if (!storage)
return;
map = &storage->map->map;
-
- bpf_cgroup_storage_calculate_size(map, &pages);
- bpf_map_uncharge_memlock(map, pages);
-
stype = cgroup_storage_type(map);
if (stype == BPF_CGROUP_STORAGE_SHARED)
call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu);
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 00e32f2ec3e6..cec792a17e5f 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -282,8 +282,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
if (value)
size += trie->map.value_size;
- node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN,
- trie->map.numa_node);
+ node = bpf_map_kmalloc_node(&trie->map, size, GFP_ATOMIC | __GFP_NOWARN,
+ trie->map.numa_node);
if (!node)
return NULL;
@@ -540,8 +540,6 @@ out:
static struct bpf_map *trie_alloc(union bpf_attr *attr)
{
struct lpm_trie *trie;
- u64 cost = sizeof(*trie), cost_per_node;
- int ret;
if (!bpf_capable())
return ERR_PTR(-EPERM);
@@ -557,7 +555,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
attr->value_size > LPM_VAL_SIZE_MAX)
return ERR_PTR(-EINVAL);
- trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN);
+ trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
if (!trie)
return ERR_PTR(-ENOMEM);
@@ -567,20 +565,9 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
offsetof(struct bpf_lpm_trie_key, data);
trie->max_prefixlen = trie->data_size * 8;
- cost_per_node = sizeof(struct lpm_trie_node) +
- attr->value_size + trie->data_size;
- cost += (u64) attr->max_entries * cost_per_node;
-
- ret = bpf_map_charge_init(&trie->map.memory, cost);
- if (ret)
- goto out_err;
-
spin_lock_init(&trie->lock);
return &trie->map;
-out_err:
- kfree(trie);
- return ERR_PTR(ret);
}
static void trie_free(struct bpf_map *map)
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 0ee2347ba510..f9c734aaa990 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -66,29 +66,21 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr)
static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
{
- int ret, numa_node = bpf_map_attr_numa_node(attr);
- struct bpf_map_memory mem = {0};
+ int numa_node = bpf_map_attr_numa_node(attr);
struct bpf_queue_stack *qs;
- u64 size, queue_size, cost;
+ u64 size, queue_size;
size = (u64) attr->max_entries + 1;
- cost = queue_size = sizeof(*qs) + size * attr->value_size;
-
- ret = bpf_map_charge_init(&mem, cost);
- if (ret < 0)
- return ERR_PTR(ret);
+ queue_size = sizeof(*qs) + size * attr->value_size;
qs = bpf_map_area_alloc(queue_size, numa_node);
- if (!qs) {
- bpf_map_charge_finish(&mem);
+ if (!qs)
return ERR_PTR(-ENOMEM);
- }
memset(qs, 0, sizeof(*qs));
bpf_map_init_from_attr(&qs->map, attr);
- bpf_map_charge_move(&qs->map.memory, &mem);
qs->size = size;
raw_spin_lock_init(&qs->lock);
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index a55cd542f2ce..4838922f723d 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -150,9 +150,8 @@ static void reuseport_array_free(struct bpf_map *map)
static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
{
- int err, numa_node = bpf_map_attr_numa_node(attr);
+ int numa_node = bpf_map_attr_numa_node(attr);
struct reuseport_array *array;
- struct bpf_map_memory mem;
u64 array_size;
if (!bpf_capable())
@@ -161,20 +160,13 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
array_size = sizeof(*array);
array_size += (u64)attr->max_entries * sizeof(struct sock *);
- err = bpf_map_charge_init(&mem, array_size);
- if (err)
- return ERR_PTR(err);
-
/* allocate all map elements and zero-initialize them */
array = bpf_map_area_alloc(array_size, numa_node);
- if (!array) {
- bpf_map_charge_finish(&mem);
+ if (!array)
return ERR_PTR(-ENOMEM);
- }
/* copy mandatory map attributes */
bpf_map_init_from_attr(&array->map, attr);
- bpf_map_charge_move(&array->map.memory, &mem);
return &array->map;
}
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 31cb04a4dd2d..f25b719ac786 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -48,7 +48,6 @@ struct bpf_ringbuf {
struct bpf_ringbuf_map {
struct bpf_map map;
- struct bpf_map_memory memory;
struct bpf_ringbuf *rb;
};
@@ -60,8 +59,8 @@ struct bpf_ringbuf_hdr {
static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
{
- const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN |
- __GFP_ZERO;
+ const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL |
+ __GFP_NOWARN | __GFP_ZERO;
int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES;
int nr_data_pages = data_sz >> PAGE_SHIFT;
int nr_pages = nr_meta_pages + nr_data_pages;
@@ -88,10 +87,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
* user-space implementations significantly.
*/
array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages);
- if (array_size > PAGE_SIZE)
- pages = vmalloc_node(array_size, numa_node);
- else
- pages = kmalloc_node(array_size, flags, numa_node);
+ pages = bpf_map_area_alloc(array_size, numa_node);
if (!pages)
return NULL;
@@ -134,7 +130,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
rb = bpf_ringbuf_area_alloc(data_sz, numa_node);
if (!rb)
- return ERR_PTR(-ENOMEM);
+ return NULL;
spin_lock_init(&rb->spinlock);
init_waitqueue_head(&rb->waitq);
@@ -150,8 +146,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
{
struct bpf_ringbuf_map *rb_map;
- u64 cost;
- int err;
if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
@@ -167,32 +161,19 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
return ERR_PTR(-E2BIG);
#endif
- rb_map = kzalloc(sizeof(*rb_map), GFP_USER);
+ rb_map = kzalloc(sizeof(*rb_map), GFP_USER | __GFP_ACCOUNT);
if (!rb_map)
return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&rb_map->map, attr);
- cost = sizeof(struct bpf_ringbuf_map) +
- sizeof(struct bpf_ringbuf) +
- attr->max_entries;
- err = bpf_map_charge_init(&rb_map->map.memory, cost);
- if (err)
- goto err_free_map;
-
rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node);
- if (IS_ERR(rb_map->rb)) {
- err = PTR_ERR(rb_map->rb);
- goto err_uncharge;
+ if (!rb_map->rb) {
+ kfree(rb_map);
+ return ERR_PTR(-ENOMEM);
}
return &rb_map->map;
-
-err_uncharge:
- bpf_map_charge_finish(&rb_map->map.memory);
-err_free_map:
- kfree(rb_map);
- return ERR_PTR(err);
}
static void bpf_ringbuf_free(struct bpf_ringbuf *rb)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 599041cd0c8a..aea96b638473 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -90,7 +90,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
{
u32 value_size = attr->value_size;
struct bpf_stack_map *smap;
- struct bpf_map_memory mem;
u64 cost, n_buckets;
int err;
@@ -119,15 +118,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
- err = bpf_map_charge_init(&mem, cost);
- if (err)
- return ERR_PTR(err);
-
smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
- if (!smap) {
- bpf_map_charge_finish(&mem);
+ if (!smap)
return ERR_PTR(-ENOMEM);
- }
bpf_map_init_from_attr(&smap->map, attr);
smap->map.value_size = value_size;
@@ -135,20 +128,17 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
err = get_callchain_buffers(sysctl_perf_event_max_stack);
if (err)
- goto free_charge;
+ goto free_smap;
err = prealloc_elems_and_freelist(smap);
if (err)
goto put_buffers;
- bpf_map_charge_move(&smap->map.memory, &mem);
-
return &smap->map;
put_buffers:
put_callchain_buffers();
-free_charge:
- bpf_map_charge_finish(&mem);
+free_smap:
bpf_map_area_free(smap);
return ERR_PTR(err);
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8f50c9c19f1b..287be337d5f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -31,6 +31,7 @@
#include <linux/poll.h>
#include <linux/bpf-netns.h>
#include <linux/rcupdate_trace.h>
+#include <linux/memcontrol.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -127,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
-static u32 bpf_map_value_size(struct bpf_map *map)
+static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
@@ -267,6 +268,10 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
return err;
}
+/* Please, do not use this function outside from the map creation path
+ * (e.g. in map update path) without taking care of setting the active
+ * memory cgroup (see at bpf_map_kmalloc_node() for example).
+ */
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
{
/* We really just want to fail instead of triggering OOM killer
@@ -279,7 +284,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
* __GFP_RETRY_MAYFAIL to avoid such situations.
*/
- const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO;
+ const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT;
unsigned int flags = 0;
unsigned long align = 1;
void *area;
@@ -341,77 +346,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
map->numa_node = bpf_map_attr_numa_node(attr);
}
-static int bpf_charge_memlock(struct user_struct *user, u32 pages)
-{
- unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
- if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
- atomic_long_sub(pages, &user->locked_vm);
- return -EPERM;
- }
- return 0;
-}
-
-static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
-{
- if (user)
- atomic_long_sub(pages, &user->locked_vm);
-}
-
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
-{
- u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
- struct user_struct *user;
- int ret;
-
- if (size >= U32_MAX - PAGE_SIZE)
- return -E2BIG;
-
- user = get_current_user();
- ret = bpf_charge_memlock(user, pages);
- if (ret) {
- free_uid(user);
- return ret;
- }
-
- mem->pages = pages;
- mem->user = user;
-
- return 0;
-}
-
-void bpf_map_charge_finish(struct bpf_map_memory *mem)
-{
- bpf_uncharge_memlock(mem->user, mem->pages);
- free_uid(mem->user);
-}
-
-void bpf_map_charge_move(struct bpf_map_memory *dst,
- struct bpf_map_memory *src)
-{
- *dst = *src;
-
- /* Make sure src will not be used for the redundant uncharging. */
- memset(src, 0, sizeof(struct bpf_map_memory));
-}
-
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
-{
- int ret;
-
- ret = bpf_charge_memlock(map->memory.user, pages);
- if (ret)
- return ret;
- map->memory.pages += pages;
- return ret;
-}
-
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
-{
- bpf_uncharge_memlock(map->memory.user, pages);
- map->memory.pages -= pages;
-}
-
static int bpf_map_alloc_id(struct bpf_map *map)
{
int id;
@@ -456,17 +390,74 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
__release(&map_idr_lock);
}
+#ifdef CONFIG_MEMCG_KMEM
+static void bpf_map_save_memcg(struct bpf_map *map)
+{
+ map->memcg = get_mem_cgroup_from_mm(current->mm);
+}
+
+static void bpf_map_release_memcg(struct bpf_map *map)
+{
+ mem_cgroup_put(map->memcg);
+}
+
+void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
+ int node)
+{
+ struct mem_cgroup *old_memcg;
+ void *ptr;
+
+ old_memcg = set_active_memcg(map->memcg);
+ ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node);
+ set_active_memcg(old_memcg);
+
+ return ptr;
+}
+
+void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
+{
+ struct mem_cgroup *old_memcg;
+ void *ptr;
+
+ old_memcg = set_active_memcg(map->memcg);
+ ptr = kzalloc(size, flags | __GFP_ACCOUNT);
+ set_active_memcg(old_memcg);
+
+ return ptr;
+}
+
+void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
+ size_t align, gfp_t flags)
+{
+ struct mem_cgroup *old_memcg;
+ void __percpu *ptr;
+
+ old_memcg = set_active_memcg(map->memcg);
+ ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT);
+ set_active_memcg(old_memcg);
+
+ return ptr;
+}
+
+#else
+static void bpf_map_save_memcg(struct bpf_map *map)
+{
+}
+
+static void bpf_map_release_memcg(struct bpf_map *map)
+{
+}
+#endif
+
/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
- struct bpf_map_memory mem;
- bpf_map_charge_move(&mem, &map->memory);
security_bpf_map_free(map);
+ bpf_map_release_memcg(map);
/* implementation dependent freeing */
map->ops->map_free(map);
- bpf_map_charge_finish(&mem);
}
static void bpf_map_put_uref(struct bpf_map *map)
@@ -527,6 +518,19 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
}
#ifdef CONFIG_PROC_FS
+/* Provides an approximation of the map's memory footprint.
+ * Used only to provide a backward compatibility and display
+ * a reasonable "memlock" info.
+ */
+static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
+{
+ unsigned long size;
+
+ size = round_up(map->key_size + bpf_map_value_size(map), 8);
+
+ return round_up(map->max_entries * size, PAGE_SIZE);
+}
+
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_map *map = filp->private_data;
@@ -545,7 +549,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
"value_size:\t%u\n"
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
- "memlock:\t%llu\n"
+ "memlock:\t%lu\n"
"map_id:\t%u\n"
"frozen:\t%u\n",
map->map_type,
@@ -553,7 +557,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
map->value_size,
map->max_entries,
map->map_flags,
- map->memory.pages * 1ULL << PAGE_SHIFT,
+ bpf_map_memory_footprint(map),
map->id,
READ_ONCE(map->frozen));
if (type) {
@@ -773,7 +777,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
map->map_type != BPF_MAP_TYPE_ARRAY &&
map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
map->map_type != BPF_MAP_TYPE_SK_STORAGE &&
- map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
+ map->map_type != BPF_MAP_TYPE_INODE_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
return -ENOTSUPP;
if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
map->value_size) {
@@ -795,7 +800,6 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
static int map_create(union bpf_attr *attr)
{
int numa_node = bpf_map_attr_numa_node(attr);
- struct bpf_map_memory mem;
struct bpf_map *map;
int f_flags;
int err;
@@ -874,6 +878,8 @@ static int map_create(union bpf_attr *attr)
if (err)
goto free_map_sec;
+ bpf_map_save_memcg(map);
+
err = bpf_map_new_fd(map, f_flags);
if (err < 0) {
/* failed to allocate fd.
@@ -892,9 +898,7 @@ free_map_sec:
security_bpf_map_free(map);
free_map:
btf_put(map->btf);
- bpf_map_charge_move(&mem, &map->memory);
map->ops->map_free(map);
- bpf_map_charge_finish(&mem);
return err;
}
@@ -1628,51 +1632,6 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
audit_log_end(ab);
}
-int __bpf_prog_charge(struct user_struct *user, u32 pages)
-{
- unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- unsigned long user_bufs;
-
- if (user) {
- user_bufs = atomic_long_add_return(pages, &user->locked_vm);
- if (user_bufs > memlock_limit) {
- atomic_long_sub(pages, &user->locked_vm);
- return -EPERM;
- }
- }
-
- return 0;
-}
-
-void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
-{
- if (user)
- atomic_long_sub(pages, &user->locked_vm);
-}
-
-static int bpf_prog_charge_memlock(struct bpf_prog *prog)
-{
- struct user_struct *user = get_current_user();
- int ret;
-
- ret = __bpf_prog_charge(user, prog->pages);
- if (ret) {
- free_uid(user);
- return ret;
- }
-
- prog->aux->user = user;
- return 0;
-}
-
-static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
-{
- struct user_struct *user = prog->aux->user;
-
- __bpf_prog_uncharge(user, prog->pages);
- free_uid(user);
-}
-
static int bpf_prog_alloc_id(struct bpf_prog *prog)
{
int id;
@@ -1722,7 +1681,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
kvfree(aux->func_info);
kfree(aux->func_info_aux);
- bpf_prog_uncharge_memlock(aux->prog);
+ free_uid(aux->user);
security_bpf_prog_free(aux);
bpf_prog_free(aux->prog);
}
@@ -1732,6 +1691,8 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
bpf_prog_kallsyms_del_all(prog);
btf_put(prog->aux->btf);
bpf_prog_free_linfo(prog);
+ if (prog->aux->attach_btf)
+ btf_put(prog->aux->attach_btf);
if (deferred) {
if (prog->aux->sleepable)
@@ -1965,12 +1926,16 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
static int
bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type,
- u32 btf_id, u32 prog_fd)
+ struct btf *attach_btf, u32 btf_id,
+ struct bpf_prog *dst_prog)
{
if (btf_id) {
if (btf_id > BTF_MAX_TYPE)
return -EINVAL;
+ if (!attach_btf && !dst_prog)
+ return -EINVAL;
+
switch (prog_type) {
case BPF_PROG_TYPE_TRACING:
case BPF_PROG_TYPE_LSM:
@@ -1982,7 +1947,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
}
}
- if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING &&
+ if (attach_btf && (!btf_id || dst_prog))
+ return -EINVAL;
+
+ if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING &&
prog_type != BPF_PROG_TYPE_EXT)
return -EINVAL;
@@ -2099,7 +2067,8 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
{
enum bpf_prog_type type = attr->prog_type;
- struct bpf_prog *prog;
+ struct bpf_prog *prog, *dst_prog = NULL;
+ struct btf *attach_btf = NULL;
int err;
char license[128];
bool is_gpl;
@@ -2141,47 +2110,73 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
if (is_perfmon_prog_type(type) && !perfmon_capable())
return -EPERM;
+ /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
+ * or btf, we need to check which one it is
+ */
+ if (attr->attach_prog_fd) {
+ dst_prog = bpf_prog_get(attr->attach_prog_fd);
+ if (IS_ERR(dst_prog)) {
+ dst_prog = NULL;
+ attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd);
+ if (IS_ERR(attach_btf))
+ return -EINVAL;
+ if (!btf_is_kernel(attach_btf)) {
+ /* attaching through specifying bpf_prog's BTF
+ * objects directly might be supported eventually
+ */
+ btf_put(attach_btf);
+ return -ENOTSUPP;
+ }
+ }
+ } else if (attr->attach_btf_id) {
+ /* fall back to vmlinux BTF, if BTF type ID is specified */
+ attach_btf = bpf_get_btf_vmlinux();
+ if (IS_ERR(attach_btf))
+ return PTR_ERR(attach_btf);
+ if (!attach_btf)
+ return -EINVAL;
+ btf_get(attach_btf);
+ }
+
bpf_prog_load_fixup_attach_type(attr);
if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
- attr->attach_btf_id,
- attr->attach_prog_fd))
+ attach_btf, attr->attach_btf_id,
+ dst_prog)) {
+ if (dst_prog)
+ bpf_prog_put(dst_prog);
+ if (attach_btf)
+ btf_put(attach_btf);
return -EINVAL;
+ }
/* plain bpf_prog allocation */
prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
- if (!prog)
+ if (!prog) {
+ if (dst_prog)
+ bpf_prog_put(dst_prog);
+ if (attach_btf)
+ btf_put(attach_btf);
return -ENOMEM;
+ }
prog->expected_attach_type = attr->expected_attach_type;
+ prog->aux->attach_btf = attach_btf;
prog->aux->attach_btf_id = attr->attach_btf_id;
- if (attr->attach_prog_fd) {
- struct bpf_prog *dst_prog;
-
- dst_prog = bpf_prog_get(attr->attach_prog_fd);
- if (IS_ERR(dst_prog)) {
- err = PTR_ERR(dst_prog);
- goto free_prog_nouncharge;
- }
- prog->aux->dst_prog = dst_prog;
- }
-
+ prog->aux->dst_prog = dst_prog;
prog->aux->offload_requested = !!attr->prog_ifindex;
prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
err = security_bpf_prog_alloc(prog->aux);
if (err)
- goto free_prog_nouncharge;
-
- err = bpf_prog_charge_memlock(prog);
- if (err)
- goto free_prog_sec;
+ goto free_prog;
+ prog->aux->user = get_current_user();
prog->len = attr->insn_cnt;
err = -EFAULT;
if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
bpf_prog_insn_size(prog)) != 0)
- goto free_prog;
+ goto free_prog_sec;
prog->orig_prog = NULL;
prog->jited = 0;
@@ -2192,19 +2187,19 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
if (bpf_prog_is_dev_bound(prog->aux)) {
err = bpf_prog_offload_init(prog, attr);
if (err)
- goto free_prog;
+ goto free_prog_sec;
}
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
- goto free_prog;
+ goto free_prog_sec;
prog->aux->load_time = ktime_get_boottime_ns();
err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
sizeof(attr->prog_name));
if (err < 0)
- goto free_prog;
+ goto free_prog_sec;
/* run eBPF verifier */
err = bpf_check(&prog, attr, uattr);
@@ -2249,11 +2244,12 @@ free_used_maps:
*/
__bpf_prog_put_noref(prog, prog->aux->func_cnt);
return err;
-free_prog:
- bpf_prog_uncharge_memlock(prog);
free_prog_sec:
+ free_uid(prog->aux->user);
security_bpf_prog_free(prog->aux);
-free_prog_nouncharge:
+free_prog:
+ if (prog->aux->attach_btf)
+ btf_put(prog->aux->attach_btf);
bpf_prog_free(prog);
return err;
}
@@ -2611,7 +2607,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
goto out_put_prog;
}
- key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+ key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id);
}
link = kzalloc(sizeof(*link), GFP_USER);
@@ -3588,7 +3584,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
}
if (prog->aux->btf)
- info.btf_id = btf_id(prog->aux->btf);
+ info.btf_id = btf_obj_id(prog->aux->btf);
ulen = info.nr_func_info;
info.nr_func_info = prog->aux->func_info_cnt;
@@ -3691,7 +3687,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
memcpy(info.name, map->name, sizeof(map->name));
if (map->btf) {
- info.btf_id = btf_id(map->btf);
+ info.btf_id = btf_obj_id(map->btf);
info.btf_key_type_id = map->btf_key_type_id;
info.btf_value_type_id = map->btf_value_type_id;
}
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 11b3380887fa..ef6911aee3bb 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -26,7 +26,7 @@ static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
.read = btf_vmlinux_read,
};
-static struct kobject *btf_kobj;
+struct kobject *btf_kobj;
static int __init btf_vmlinux_init(void)
{
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 5b6af30bfbcd..0458a40edf10 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -136,8 +136,7 @@ struct bpf_iter_seq_task_file_info {
};
static struct file *
-task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info,
- struct task_struct **task, struct files_struct **fstruct)
+task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)
{
struct pid_namespace *ns = info->common.ns;
u32 curr_tid = info->tid, max_fds;
@@ -150,14 +149,17 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info,
* Otherwise, it does not hold any reference.
*/
again:
- if (*task) {
- curr_task = *task;
- curr_files = *fstruct;
+ if (info->task) {
+ curr_task = info->task;
+ curr_files = info->files;
curr_fd = info->fd;
} else {
curr_task = task_seq_get_next(ns, &curr_tid, true);
- if (!curr_task)
+ if (!curr_task) {
+ info->task = NULL;
+ info->files = NULL;
return NULL;
+ }
curr_files = get_files_struct(curr_task);
if (!curr_files) {
@@ -167,9 +169,8 @@ again:
goto again;
}
- /* set *fstruct, *task and info->tid */
- *fstruct = curr_files;
- *task = curr_task;
+ info->files = curr_files;
+ info->task = curr_task;
if (curr_tid == info->tid) {
curr_fd = info->fd;
} else {
@@ -199,8 +200,8 @@ again:
rcu_read_unlock();
put_files_struct(curr_files);
put_task_struct(curr_task);
- *task = NULL;
- *fstruct = NULL;
+ info->task = NULL;
+ info->files = NULL;
info->fd = 0;
curr_tid = ++(info->tid);
goto again;
@@ -209,21 +210,13 @@ again:
static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
{
struct bpf_iter_seq_task_file_info *info = seq->private;
- struct files_struct *files = NULL;
- struct task_struct *task = NULL;
struct file *file;
- file = task_file_seq_get_next(info, &task, &files);
- if (!file) {
- info->files = NULL;
- info->task = NULL;
- return NULL;
- }
-
- if (*pos == 0)
+ info->task = NULL;
+ info->files = NULL;
+ file = task_file_seq_get_next(info);
+ if (file && *pos == 0)
++*pos;
- info->task = task;
- info->files = files;
return file;
}
@@ -231,24 +224,11 @@ static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct bpf_iter_seq_task_file_info *info = seq->private;
- struct files_struct *files = info->files;
- struct task_struct *task = info->task;
- struct file *file;
++*pos;
++info->fd;
fput((struct file *)v);
- file = task_file_seq_get_next(info, &task, &files);
- if (!file) {
- info->files = NULL;
- info->task = NULL;
- return NULL;
- }
-
- info->task = task;
- info->files = files;
-
- return file;
+ return task_file_seq_get_next(info);
}
struct bpf_iter__task_file {
@@ -337,6 +317,7 @@ static const struct bpf_iter_seq_info task_seq_info = {
static struct bpf_iter_reg task_reg_info = {
.target = "task",
+ .feature = BPF_ITER_RESCHED,
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
@@ -354,6 +335,7 @@ static const struct bpf_iter_seq_info task_file_seq_info = {
static struct bpf_iter_reg task_file_reg_info = {
.target = "task_file",
+ .feature = BPF_ITER_RESCHED,
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task_file, task),
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 53fe6ef6d931..17270b8404f1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,7 +238,9 @@ struct bpf_call_arg_meta {
u64 msize_max_value;
int ref_obj_id;
int func_id;
+ struct btf *btf;
u32 btf_id;
+ struct btf *ret_btf;
u32 ret_btf_id;
};
@@ -556,10 +558,9 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env,
return cur->frame[reg->frameno];
}
-const char *kernel_type_name(u32 id)
+static const char *kernel_type_name(const struct btf* btf, u32 id)
{
- return btf_name_by_offset(btf_vmlinux,
- btf_type_by_id(btf_vmlinux, id)->name_off);
+ return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
}
static void print_verifier_state(struct bpf_verifier_env *env,
@@ -589,7 +590,7 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (t == PTR_TO_BTF_ID ||
t == PTR_TO_BTF_ID_OR_NULL ||
t == PTR_TO_PERCPU_BTF_ID)
- verbose(env, "%s", kernel_type_name(reg->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))
verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
@@ -1381,7 +1382,8 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
static void mark_btf_ld_reg(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno,
- enum bpf_reg_type reg_type, u32 btf_id)
+ enum bpf_reg_type reg_type,
+ struct btf *btf, u32 btf_id)
{
if (reg_type == SCALAR_VALUE) {
mark_reg_unknown(env, regs, regno);
@@ -1389,6 +1391,7 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env,
}
mark_reg_known_zero(env, regs, regno);
regs[regno].type = PTR_TO_BTF_ID;
+ regs[regno].btf = btf;
regs[regno].btf_id = btf_id;
}
@@ -2737,7 +2740,9 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
regno);
return -EACCES;
}
- err = __check_mem_access(env, regno, off, size, reg->range,
+
+ err = reg->range < 0 ? -EINVAL :
+ __check_mem_access(env, regno, off, size, reg->range,
zero_size_allowed);
if (err) {
verbose(env, "R%d offset is outside of the packet\n", regno);
@@ -2760,7 +2765,7 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
/* check access to 'struct bpf_context' fields. Supports fixed offsets only */
static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
enum bpf_access_type t, enum bpf_reg_type *reg_type,
- u32 *btf_id)
+ struct btf **btf, u32 *btf_id)
{
struct bpf_insn_access_aux info = {
.reg_type = *reg_type,
@@ -2778,10 +2783,12 @@ 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 (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) {
+ *btf = info.btf;
*btf_id = info.btf_id;
- else
+ } else {
env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+ }
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
@@ -3293,8 +3300,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
int value_regno)
{
struct bpf_reg_state *reg = regs + regno;
- const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id);
- const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
+ const char *tname = btf_name_by_offset(reg->btf, t->name_off);
u32 btf_id;
int ret;
@@ -3315,23 +3322,23 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
}
if (env->ops->btf_struct_access) {
- ret = env->ops->btf_struct_access(&env->log, t, off, size,
- atype, &btf_id);
+ ret = env->ops->btf_struct_access(&env->log, reg->btf, t,
+ off, size, atype, &btf_id);
} else {
if (atype != BPF_READ) {
verbose(env, "only read is supported\n");
return -EACCES;
}
- ret = btf_struct_access(&env->log, t, off, size, atype,
- &btf_id);
+ ret = btf_struct_access(&env->log, reg->btf, t, off, size,
+ atype, &btf_id);
}
if (ret < 0)
return ret;
if (atype == BPF_READ && value_regno >= 0)
- mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+ mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id);
return 0;
}
@@ -3381,12 +3388,12 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
return -EACCES;
}
- ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+ ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id);
if (ret < 0)
return ret;
if (value_regno >= 0)
- mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+ mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id);
return 0;
}
@@ -3462,6 +3469,7 @@ 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_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
+ struct btf *btf = NULL;
u32 btf_id = 0;
if (t == BPF_WRITE && value_regno >= 0 &&
@@ -3474,7 +3482,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (err < 0)
return err;
- err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf_id);
+ err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf, &btf_id);
if (err)
verbose_linfo(env, insn_idx, "; ");
if (!err && t == BPF_READ && value_regno >= 0) {
@@ -3496,8 +3504,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
*/
regs[value_regno].subreg_def = DEF_NOT_SUBREG;
if (reg_type == PTR_TO_BTF_ID ||
- reg_type == PTR_TO_BTF_ID_OR_NULL)
+ reg_type == PTR_TO_BTF_ID_OR_NULL) {
+ regs[value_regno].btf = btf;
regs[value_regno].btf_id = btf_id;
+ }
}
regs[value_regno].type = reg_type;
}
@@ -3757,7 +3767,8 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
goto mark;
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
- state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
+ (state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
+ env->allow_ptr_leaks)) {
__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
state->stack[spi].slot_type[j] = STACK_MISC;
@@ -4114,11 +4125,11 @@ found:
arg_btf_id = compatible->btf_id;
}
- if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
- *arg_btf_id)) {
+ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
+ btf_vmlinux, *arg_btf_id)) {
verbose(env, "R%d is of type %s but %s is expected\n",
- regno, kernel_type_name(reg->btf_id),
- kernel_type_name(*arg_btf_id));
+ regno, kernel_type_name(reg->btf, reg->btf_id),
+ kernel_type_name(btf_vmlinux, *arg_btf_id));
return -EACCES;
}
@@ -4240,6 +4251,7 @@ skip_type_check:
verbose(env, "Helper has invalid btf_id in R%d\n", regno);
return -EACCES;
}
+ meta->ret_btf = reg->btf;
meta->ret_btf_id = reg->btf_id;
} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
if (meta->func_id == BPF_FUNC_spin_lock) {
@@ -4467,6 +4479,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_inode_storage_delete)
goto error;
break;
+ case BPF_MAP_TYPE_TASK_STORAGE:
+ if (func_id != BPF_FUNC_task_storage_get &&
+ func_id != BPF_FUNC_task_storage_delete)
+ goto error;
+ break;
default:
break;
}
@@ -4545,6 +4562,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
goto error;
break;
+ case BPF_FUNC_task_storage_get:
+ case BPF_FUNC_task_storage_delete:
+ if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
+ goto error;
+ break;
default:
break;
}
@@ -4685,6 +4707,32 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
__clear_all_pkt_pointers(env, vstate->frame[i]);
}
+enum {
+ AT_PKT_END = -1,
+ BEYOND_PKT_END = -2,
+};
+
+static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open)
+{
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *reg = &state->regs[regn];
+
+ if (reg->type != PTR_TO_PACKET)
+ /* PTR_TO_PACKET_META is not supported yet */
+ return;
+
+ /* The 'reg' is pkt > pkt_end or pkt >= pkt_end.
+ * How far beyond pkt_end it goes is unknown.
+ * if (!range_open) it's the case of pkt >= pkt_end
+ * if (range_open) it's the case of pkt > pkt_end
+ * hence this pointer is at least 1 byte bigger than pkt_end
+ */
+ if (range_open)
+ reg->range = BEYOND_PKT_END;
+ else
+ reg->range = AT_PKT_END;
+}
+
static void release_reg_references(struct bpf_verifier_env *env,
struct bpf_func_state *state,
int ref_obj_id)
@@ -5152,16 +5200,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
const struct btf_type *t;
mark_reg_known_zero(env, regs, BPF_REG_0);
- t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL);
+ t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL);
if (!btf_type_is_struct(t)) {
u32 tsize;
const struct btf_type *ret;
const char *tname;
/* resolve the type size of ksym. */
- ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+ ret = btf_resolve_size(meta.ret_btf, t, &tsize);
if (IS_ERR(ret)) {
- tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ tname = btf_name_by_offset(meta.ret_btf, t->name_off);
verbose(env, "unable to resolve the size of type '%s': %ld\n",
tname, PTR_ERR(ret));
return -EINVAL;
@@ -5174,19 +5222,27 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
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;
+ 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) {
+ } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
+ fn->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 = PTR_TO_BTF_ID_OR_NULL;
+ regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
+ PTR_TO_BTF_ID :
+ PTR_TO_BTF_ID_OR_NULL;
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);
return -EINVAL;
}
+ /* current BPF helper definitions are only coming from
+ * built-in code with type IDs from vmlinux BTF
+ */
+ 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",
@@ -5586,7 +5642,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
- dst_reg->raw = 0;
+ memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
}
break;
case BPF_SUB:
@@ -5651,7 +5707,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
- dst_reg->raw = 0;
+ memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
}
break;
case BPF_AND:
@@ -6695,7 +6751,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
static void __find_good_pkt_pointers(struct bpf_func_state *state,
struct bpf_reg_state *dst_reg,
- enum bpf_reg_type type, u16 new_range)
+ enum bpf_reg_type type, int new_range)
{
struct bpf_reg_state *reg;
int i;
@@ -6720,8 +6776,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
enum bpf_reg_type type,
bool range_right_open)
{
- u16 new_range;
- int i;
+ int new_range, i;
if (dst_reg->off < 0 ||
(dst_reg->off == 0 && range_right_open))
@@ -6972,6 +7027,67 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
return is_branch64_taken(reg, val, opcode);
}
+static int flip_opcode(u32 opcode)
+{
+ /* How can we transform "a <op> b" into "b <op> a"? */
+ static const u8 opcode_flip[16] = {
+ /* these stay the same */
+ [BPF_JEQ >> 4] = BPF_JEQ,
+ [BPF_JNE >> 4] = BPF_JNE,
+ [BPF_JSET >> 4] = BPF_JSET,
+ /* these swap "lesser" and "greater" (L and G in the opcodes) */
+ [BPF_JGE >> 4] = BPF_JLE,
+ [BPF_JGT >> 4] = BPF_JLT,
+ [BPF_JLE >> 4] = BPF_JGE,
+ [BPF_JLT >> 4] = BPF_JGT,
+ [BPF_JSGE >> 4] = BPF_JSLE,
+ [BPF_JSGT >> 4] = BPF_JSLT,
+ [BPF_JSLE >> 4] = BPF_JSGE,
+ [BPF_JSLT >> 4] = BPF_JSGT
+ };
+ return opcode_flip[opcode >> 4];
+}
+
+static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg,
+ u8 opcode)
+{
+ struct bpf_reg_state *pkt;
+
+ if (src_reg->type == PTR_TO_PACKET_END) {
+ pkt = dst_reg;
+ } else if (dst_reg->type == PTR_TO_PACKET_END) {
+ pkt = src_reg;
+ opcode = flip_opcode(opcode);
+ } else {
+ return -1;
+ }
+
+ if (pkt->range >= 0)
+ return -1;
+
+ switch (opcode) {
+ case BPF_JLE:
+ /* pkt <= pkt_end */
+ fallthrough;
+ case BPF_JGT:
+ /* pkt > pkt_end */
+ if (pkt->range == BEYOND_PKT_END)
+ /* pkt has at last one extra byte beyond pkt_end */
+ return opcode == BPF_JGT;
+ break;
+ case BPF_JLT:
+ /* pkt < pkt_end */
+ fallthrough;
+ case BPF_JGE:
+ /* pkt >= pkt_end */
+ if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END)
+ return opcode == BPF_JGE;
+ break;
+ }
+ return -1;
+}
+
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
@@ -7135,23 +7251,7 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
u64 val, u32 val32,
u8 opcode, bool is_jmp32)
{
- /* How can we transform "a <op> b" into "b <op> a"? */
- static const u8 opcode_flip[16] = {
- /* these stay the same */
- [BPF_JEQ >> 4] = BPF_JEQ,
- [BPF_JNE >> 4] = BPF_JNE,
- [BPF_JSET >> 4] = BPF_JSET,
- /* these swap "lesser" and "greater" (L and G in the opcodes) */
- [BPF_JGE >> 4] = BPF_JLE,
- [BPF_JGT >> 4] = BPF_JLT,
- [BPF_JLE >> 4] = BPF_JGE,
- [BPF_JLT >> 4] = BPF_JGT,
- [BPF_JSGE >> 4] = BPF_JSLE,
- [BPF_JSGT >> 4] = BPF_JSLT,
- [BPF_JSLE >> 4] = BPF_JSGE,
- [BPF_JSLT >> 4] = BPF_JSGT
- };
- opcode = opcode_flip[opcode >> 4];
+ opcode = flip_opcode(opcode);
/* This uses zero as "not present in table"; luckily the zero opcode,
* BPF_JA, can't get here.
*/
@@ -7333,6 +7433,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, false);
+ mark_pkt_end(other_branch, insn->dst_reg, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7340,6 +7441,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_end > pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, true);
+ mark_pkt_end(this_branch, insn->src_reg, false);
} else {
return false;
}
@@ -7352,6 +7454,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, true);
+ mark_pkt_end(this_branch, insn->dst_reg, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7359,6 +7462,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_end < pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, false);
+ mark_pkt_end(other_branch, insn->src_reg, true);
} else {
return false;
}
@@ -7371,6 +7475,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, true);
+ mark_pkt_end(other_branch, insn->dst_reg, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7378,6 +7483,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, false);
+ mark_pkt_end(this_branch, insn->src_reg, true);
} else {
return false;
}
@@ -7390,6 +7496,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, false);
+ mark_pkt_end(this_branch, insn->dst_reg, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7397,6 +7504,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, true);
+ mark_pkt_end(other_branch, insn->src_reg, false);
} else {
return false;
}
@@ -7496,6 +7604,10 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
src_reg->var_off.value,
opcode,
is_jmp32);
+ } else if (reg_is_pkt_pointer_any(dst_reg) &&
+ reg_is_pkt_pointer_any(src_reg) &&
+ !is_jmp32) {
+ pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
}
if (pred >= 0) {
@@ -7504,7 +7616,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
*/
if (!__is_pointer_value(false, dst_reg))
err = mark_chain_precision(env, insn->dst_reg);
- if (BPF_SRC(insn->code) == BPF_X && !err)
+ if (BPF_SRC(insn->code) == BPF_X && !err &&
+ !__is_pointer_value(false, src_reg))
err = mark_chain_precision(env, insn->src_reg);
if (err)
return err;
@@ -7646,6 +7759,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
break;
case PTR_TO_BTF_ID:
case PTR_TO_PERCPU_BTF_ID:
+ dst_reg->btf = aux->btf_var.btf;
dst_reg->btf_id = aux->btf_var.btf_id;
break;
default:
@@ -7960,6 +8074,11 @@ static void init_explored_state(struct bpf_verifier_env *env, int idx)
env->insn_aux_data[idx].prune_point = true;
}
+enum {
+ DONE_EXPLORING = 0,
+ KEEP_EXPLORING = 1,
+};
+
/* t, w, e - match pseudo-code above:
* t - index of current instruction
* w - next instruction
@@ -7972,10 +8091,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
int *insn_state = env->cfg.insn_state;
if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
- return 0;
+ return DONE_EXPLORING;
if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
- return 0;
+ return DONE_EXPLORING;
if (w < 0 || w >= env->prog->len) {
verbose_linfo(env, t, "%d: ", t);
@@ -7994,10 +8113,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
if (env->cfg.cur_stack >= env->prog->len)
return -E2BIG;
insn_stack[env->cfg.cur_stack++] = w;
- return 1;
+ return KEEP_EXPLORING;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
if (loop_ok && env->bpf_capable)
- return 0;
+ return DONE_EXPLORING;
verbose_linfo(env, t, "%d: ", t);
verbose_linfo(env, w, "%d: ", w);
verbose(env, "back-edge from insn %d to %d\n", t, w);
@@ -8009,7 +8128,74 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
verbose(env, "insn state internal bug\n");
return -EFAULT;
}
- return 0;
+ return DONE_EXPLORING;
+}
+
+/* Visits the instruction at index t and returns one of the following:
+ * < 0 - an error occurred
+ * DONE_EXPLORING - the instruction was fully explored
+ * KEEP_EXPLORING - there is still work to be done before it is fully explored
+ */
+static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env)
+{
+ struct bpf_insn *insns = env->prog->insnsi;
+ int ret;
+
+ /* All non-branch instructions have a single fall-through edge. */
+ if (BPF_CLASS(insns[t].code) != BPF_JMP &&
+ BPF_CLASS(insns[t].code) != BPF_JMP32)
+ return push_insn(t, t + 1, FALLTHROUGH, env, false);
+
+ switch (BPF_OP(insns[t].code)) {
+ case BPF_EXIT:
+ return DONE_EXPLORING;
+
+ case BPF_CALL:
+ ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+ if (ret)
+ return ret;
+
+ if (t + 1 < insn_cnt)
+ init_explored_state(env, t + 1);
+ if (insns[t].src_reg == BPF_PSEUDO_CALL) {
+ init_explored_state(env, t);
+ ret = push_insn(t, t + insns[t].imm + 1, BRANCH,
+ env, false);
+ }
+ return ret;
+
+ case BPF_JA:
+ if (BPF_SRC(insns[t].code) != BPF_K)
+ return -EINVAL;
+
+ /* unconditional jump with single edge */
+ ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env,
+ true);
+ if (ret)
+ return ret;
+
+ /* unconditional jmp is not a good pruning point,
+ * but it's marked, since backtracking needs
+ * to record jmp history in is_state_visited().
+ */
+ init_explored_state(env, t + insns[t].off + 1);
+ /* tell verifier to check for equivalent states
+ * after every call and jump
+ */
+ if (t + 1 < insn_cnt)
+ init_explored_state(env, t + 1);
+
+ return ret;
+
+ default:
+ /* conditional jump with two edges */
+ init_explored_state(env, t);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+ if (ret)
+ return ret;
+
+ return push_insn(t, t + insns[t].off + 1, BRANCH, env, true);
+ }
}
/* non-recursive depth-first-search to detect loops in BPF program
@@ -8017,11 +8203,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
*/
static int check_cfg(struct bpf_verifier_env *env)
{
- struct bpf_insn *insns = env->prog->insnsi;
int insn_cnt = env->prog->len;
int *insn_stack, *insn_state;
int ret = 0;
- int i, t;
+ int i;
insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
@@ -8037,92 +8222,32 @@ static int check_cfg(struct bpf_verifier_env *env)
insn_stack[0] = 0; /* 0 is the first instruction */
env->cfg.cur_stack = 1;
-peek_stack:
- if (env->cfg.cur_stack == 0)
- goto check_state;
- t = insn_stack[env->cfg.cur_stack - 1];
-
- if (BPF_CLASS(insns[t].code) == BPF_JMP ||
- BPF_CLASS(insns[t].code) == BPF_JMP32) {
- u8 opcode = BPF_OP(insns[t].code);
-
- if (opcode == BPF_EXIT) {
- goto mark_explored;
- } else if (opcode == BPF_CALL) {
- ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
- if (ret == 1)
- goto peek_stack;
- else if (ret < 0)
- goto err_free;
- if (t + 1 < insn_cnt)
- init_explored_state(env, t + 1);
- if (insns[t].src_reg == BPF_PSEUDO_CALL) {
- init_explored_state(env, t);
- ret = push_insn(t, t + insns[t].imm + 1, BRANCH,
- env, false);
- if (ret == 1)
- goto peek_stack;
- else if (ret < 0)
- goto err_free;
- }
- } else if (opcode == BPF_JA) {
- if (BPF_SRC(insns[t].code) != BPF_K) {
- ret = -EINVAL;
- goto err_free;
- }
- /* unconditional jump with single edge */
- ret = push_insn(t, t + insns[t].off + 1,
- FALLTHROUGH, env, true);
- if (ret == 1)
- goto peek_stack;
- else if (ret < 0)
- goto err_free;
- /* unconditional jmp is not a good pruning point,
- * but it's marked, since backtracking needs
- * to record jmp history in is_state_visited().
- */
- init_explored_state(env, t + insns[t].off + 1);
- /* tell verifier to check for equivalent states
- * after every call and jump
- */
- if (t + 1 < insn_cnt)
- init_explored_state(env, t + 1);
- } else {
- /* conditional jump with two edges */
- init_explored_state(env, t);
- ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
- if (ret == 1)
- goto peek_stack;
- else if (ret < 0)
- goto err_free;
+ while (env->cfg.cur_stack > 0) {
+ int t = insn_stack[env->cfg.cur_stack - 1];
- ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true);
- if (ret == 1)
- goto peek_stack;
- else if (ret < 0)
- goto err_free;
- }
- } else {
- /* all other non-branch instructions with single
- * fall-through edge
- */
- ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
- if (ret == 1)
- goto peek_stack;
- else if (ret < 0)
+ ret = visit_insn(t, insn_cnt, env);
+ switch (ret) {
+ case DONE_EXPLORING:
+ insn_state[t] = EXPLORED;
+ env->cfg.cur_stack--;
+ break;
+ case KEEP_EXPLORING:
+ break;
+ default:
+ if (ret > 0) {
+ verbose(env, "visit_insn internal bug\n");
+ ret = -EFAULT;
+ }
goto err_free;
+ }
}
-mark_explored:
- insn_state[t] = EXPLORED;
- if (env->cfg.cur_stack-- <= 0) {
+ if (env->cfg.cur_stack < 0) {
verbose(env, "pop stack internal bug\n");
ret = -EFAULT;
goto err_free;
}
- goto peek_stack;
-check_state:
for (i = 0; i < insn_cnt; i++) {
if (insn_state[i] != EXPLORED) {
verbose(env, "unreachable insn %d\n", i);
@@ -9642,6 +9767,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
if (percpu) {
aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
+ aux->btf_var.btf = btf_vmlinux;
aux->btf_var.btf_id = type;
} else if (!btf_type_is_struct(t)) {
const struct btf_type *ret;
@@ -9660,6 +9786,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
aux->btf_var.mem_size = tsize;
} else {
aux->btf_var.reg_type = PTR_TO_BTF_ID;
+ aux->btf_var.btf = btf_vmlinux;
aux->btf_var.btf_id = type;
}
return 0;
@@ -9731,11 +9858,21 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
}
- if ((is_tracing_prog_type(prog_type) ||
- prog_type == BPF_PROG_TYPE_SOCKET_FILTER) &&
- map_value_has_spin_lock(map)) {
- verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
- return -EINVAL;
+ if (map_value_has_spin_lock(map)) {
+ if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
+ verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
+
+ if (is_tracing_prog_type(prog_type)) {
+ verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
+
+ if (prog->aux->sleepable) {
+ verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
@@ -11466,20 +11603,6 @@ static int check_attach_modify_return(unsigned long addr, const char *func_name)
return -EINVAL;
}
-/* non exhaustive list of sleepable bpf_lsm_*() functions */
-BTF_SET_START(btf_sleepable_lsm_hooks)
-#ifdef CONFIG_BPF_LSM
-BTF_ID(func, bpf_lsm_bprm_committed_creds)
-#else
-BTF_ID_UNUSED
-#endif
-BTF_SET_END(btf_sleepable_lsm_hooks)
-
-static int check_sleepable_lsm_hook(u32 btf_id)
-{
- return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id);
-}
-
/* list of non-sleepable functions that are otherwise on
* ALLOW_ERROR_INJECTION list
*/
@@ -11516,7 +11639,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
bpf_log(log, "Tracing programs must provide btf_id\n");
return -EINVAL;
}
- btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux;
+ btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf;
if (!btf) {
bpf_log(log,
"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
@@ -11701,7 +11824,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
/* LSM progs check that they are attached to bpf_lsm_*() funcs.
* Only some of them are sleepable.
*/
- if (check_sleepable_lsm_hook(btf_id))
+ if (bpf_lsm_is_sleepable_hook(btf_id))
ret = 0;
break;
default:
@@ -11792,7 +11915,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return ret;
}
- key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+ key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id);
tr = bpf_trampoline_get(key, &tgt_info);
if (!tr)
return -ENOMEM;
diff --git a/kernel/fork.c b/kernel/fork.c
index d61fa86eaaad..7425b3224891 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -404,9 +404,10 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
/*
- * If memcg_kmem_charge_page() fails, page->mem_cgroup
- * pointer is NULL, and memcg_kmem_uncharge_page() in
- * free_thread_stack() will ignore this page.
+ * If memcg_kmem_charge_page() fails, page's
+ * memory cgroup pointer is NULL, and
+ * memcg_kmem_uncharge_page() in free_thread_stack()
+ * will ignore this page.
*/
ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
0);
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 6b8368be89c8..80bfe71bbe13 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -1023,6 +1023,8 @@ EXPORT_SYMBOL(kcov_remote_stop);
/* See the comment before kcov_remote_start() for usage details. */
u64 kcov_common_handle(void)
{
+ if (!in_task())
+ return 0;
return current->kcov_handle;
}
EXPORT_SYMBOL(kcov_common_handle);
diff --git a/kernel/module.c b/kernel/module.c
index a4fa44a652a7..c3a9e972d3b2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -380,6 +380,35 @@ static void *section_objs(const struct load_info *info,
return (void *)info->sechdrs[sec].sh_addr;
}
+/* Find a module section: 0 means not found. Ignores SHF_ALLOC flag. */
+static unsigned int find_any_sec(const struct load_info *info, const char *name)
+{
+ unsigned int i;
+
+ for (i = 1; i < info->hdr->e_shnum; i++) {
+ Elf_Shdr *shdr = &info->sechdrs[i];
+ if (strcmp(info->secstrings + shdr->sh_name, name) == 0)
+ return i;
+ }
+ return 0;
+}
+
+/*
+ * Find a module section, or NULL. Fill in number of "objects" in section.
+ * Ignores SHF_ALLOC flag.
+ */
+static __maybe_unused void *any_section_objs(const struct load_info *info,
+ const char *name,
+ size_t object_size,
+ unsigned int *num)
+{
+ unsigned int sec = find_any_sec(info, name);
+
+ /* Section 0 has sh_addr 0 and sh_size 0. */
+ *num = info->sechdrs[sec].sh_size / object_size;
+ return (void *)info->sechdrs[sec].sh_addr;
+}
+
/* Provided by the linker */
extern const struct kernel_symbol __start___ksymtab[];
extern const struct kernel_symbol __stop___ksymtab[];
@@ -3250,6 +3279,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
sizeof(*mod->bpf_raw_events),
&mod->num_bpf_raw_events);
#endif
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ mod->btf_data = any_section_objs(info, ".BTF", 1, &mod->btf_data_size);
+#endif
#ifdef CONFIG_JUMP_LABEL
mod->jump_entries = section_objs(info, "__jump_table",
sizeof(*mod->jump_entries),
@@ -3677,6 +3709,10 @@ static noinline int do_init_module(struct module *mod)
mod->init_layout.ro_size = 0;
mod->init_layout.ro_after_init_size = 0;
mod->init_layout.text_size = 0;
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */
+ mod->btf_data = NULL;
+#endif
/*
* We want to free module_init, but be aware that kallsyms may be
* walking this with preempt disabled. In all the failure paths, we
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index a2802b6ff4bb..2b4898b4752e 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -346,7 +346,7 @@ static int parse(struct nlattr *na, struct cpumask *mask)
data = kmalloc(len, GFP_KERNEL);
if (!data)
return -ENOMEM;
- nla_strlcpy(data, na, len);
+ nla_strscpy(data, na, len);
ret = cpulist_parse(data, mask);
kfree(data);
return ret;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 852226dd4b11..ebadaa83502c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -16,6 +16,9 @@
#include <linux/syscalls.h>
#include <linux/error-injection.h>
#include <linux/btf_ids.h>
+#include <linux/bpf_lsm.h>
+
+#include <net/bpf_sk_storage.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/btf.h>
@@ -1032,6 +1035,20 @@ const struct bpf_func_proto bpf_get_current_task_proto = {
.ret_type = RET_INTEGER,
};
+BPF_CALL_0(bpf_get_current_task_btf)
+{
+ return (unsigned long) current;
+}
+
+BTF_ID_LIST_SINGLE(bpf_get_current_btf_ids, struct, task_struct)
+
+static const struct bpf_func_proto bpf_get_current_task_btf_proto = {
+ .func = bpf_get_current_task_btf,
+ .gpl_only = true,
+ .ret_type = RET_PTR_TO_BTF_ID,
+ .ret_btf_id = &bpf_get_current_btf_ids[0],
+};
+
BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
@@ -1174,7 +1191,11 @@ BTF_SET_END(btf_allowlist_d_path)
static bool bpf_d_path_allowed(const struct bpf_prog *prog)
{
- return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id);
+ if (prog->type == BPF_PROG_TYPE_LSM)
+ return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id);
+
+ return btf_id_set_contains(&btf_allowlist_d_path,
+ prog->aux->attach_btf_id);
}
BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path)
@@ -1269,12 +1290,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_tail_call:
return &bpf_tail_call_proto;
case BPF_FUNC_get_current_pid_tgid:
return &bpf_get_current_pid_tgid_proto;
case BPF_FUNC_get_current_task:
return &bpf_get_current_task_proto;
+ case BPF_FUNC_get_current_task_btf:
+ return &bpf_get_current_task_btf_proto;
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
case BPF_FUNC_get_current_comm:
@@ -1729,6 +1754,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_skc_to_tcp_request_sock_proto;
case BPF_FUNC_skc_to_udp6_sock:
return &bpf_skc_to_udp6_sock_proto;
+ case BPF_FUNC_sk_storage_get:
+ return &bpf_sk_storage_get_tracing_proto;
+ case BPF_FUNC_sk_storage_delete:
+ return &bpf_sk_storage_delete_tracing_proto;
+ case BPF_FUNC_sock_from_file:
+ return &bpf_sock_from_file_proto;
#endif
case BPF_FUNC_seq_printf:
return prog->expected_attach_type == BPF_TRACE_ITER ?
@@ -2041,10 +2072,12 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
{
- struct module *mod = __module_address((unsigned long)btp);
+ struct module *mod;
- if (mod)
- module_put(mod);
+ preempt_disable();
+ mod = __module_address((unsigned long)btp);
+ module_put(mod);
+ preempt_enable();
}
static __always_inline