summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c29
-rw-r--r--kernel/bpf/hashtab.c94
-rw-r--r--kernel/bpf/local_storage.c27
-rw-r--r--kernel/bpf/syscall.c37
4 files changed, 126 insertions, 61 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1eeb31c5b317..67e9e811de3a 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -307,7 +307,7 @@ static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key,
return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu);
}
-int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
@@ -325,11 +325,18 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
size = array->elem_size;
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value(map, value, per_cpu_ptr(pptr, cpu));
+ check_and_init_map_value(map, value);
+ goto unlock;
+ }
for_each_possible_cpu(cpu) {
copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
check_and_init_map_value(map, value + off);
off += size;
}
+unlock:
rcu_read_unlock();
return 0;
}
@@ -398,10 +405,11 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
- int cpu, off = 0;
+ void *ptr, *val;
u32 size;
+ int cpu;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & BPF_F_LOCK) || (u32)map_flags > BPF_F_ALL_CPUS))
/* unknown flags */
return -EINVAL;
@@ -422,11 +430,20 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
size = array->elem_size;
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ ptr = per_cpu_ptr(pptr, cpu);
+ copy_map_value(map, ptr, value);
+ bpf_obj_free_fields(array->map.record, ptr);
+ goto unlock;
+ }
for_each_possible_cpu(cpu) {
- copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
- bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
- off += size;
+ ptr = per_cpu_ptr(pptr, cpu);
+ val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu;
+ copy_map_value(map, ptr, val);
+ bpf_obj_free_fields(array->map.record, ptr);
}
+unlock:
rcu_read_unlock();
return 0;
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index c8a9b27f8663..441ff5bc54ac 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -932,7 +932,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
}
static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
- void *value, bool onallcpus)
+ void *value, bool onallcpus, u64 map_flags)
{
void *ptr;
@@ -943,19 +943,28 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
bpf_obj_free_fields(htab->map.record, ptr);
} else {
u32 size = round_up(htab->map.value_size, 8);
- int off = 0, cpu;
+ void *val;
+ int cpu;
+
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ ptr = per_cpu_ptr(pptr, cpu);
+ copy_map_value(&htab->map, ptr, value);
+ bpf_obj_free_fields(htab->map.record, ptr);
+ return;
+ }
for_each_possible_cpu(cpu) {
ptr = per_cpu_ptr(pptr, cpu);
- copy_map_value_long(&htab->map, ptr, value + off);
+ val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu;
+ copy_map_value(&htab->map, ptr, val);
bpf_obj_free_fields(htab->map.record, ptr);
- off += size;
}
}
}
static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
- void *value, bool onallcpus)
+ void *value, bool onallcpus, u64 map_flags)
{
/* When not setting the initial value on all cpus, zero-fill element
* values for other cpus. Otherwise, bpf program has no way to ensure
@@ -973,7 +982,7 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu));
}
} else {
- pcpu_copy_value(htab, pptr, value, onallcpus);
+ pcpu_copy_value(htab, pptr, value, onallcpus, map_flags);
}
}
@@ -985,7 +994,7 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
bool percpu, bool onallcpus,
- struct htab_elem *old_elem)
+ struct htab_elem *old_elem, u64 map_flags)
{
u32 size = htab->map.value_size;
bool prealloc = htab_is_prealloc(htab);
@@ -1043,7 +1052,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
pptr = *(void __percpu **)ptr;
}
- pcpu_init_value(htab, pptr, value, onallcpus);
+ pcpu_init_value(htab, pptr, value, onallcpus, map_flags);
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
@@ -1147,7 +1156,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
}
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
- l_old);
+ l_old, map_flags);
if (IS_ERR(l_new)) {
/* all pre-allocated elements are in use or memory exhausted */
ret = PTR_ERR(l_new);
@@ -1249,6 +1258,15 @@ err_lock_bucket:
return ret;
}
+static int htab_map_check_update_flags(bool onallcpus, u64 map_flags)
+{
+ if (unlikely(!onallcpus && map_flags > BPF_EXIST))
+ return -EINVAL;
+ if (unlikely(onallcpus && ((map_flags & BPF_F_LOCK) || (u32)map_flags > BPF_F_ALL_CPUS)))
+ return -EINVAL;
+ return 0;
+}
+
static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
void *value, u64 map_flags,
bool percpu, bool onallcpus)
@@ -1262,9 +1280,9 @@ static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
u32 key_size, hash;
int ret;
- if (unlikely(map_flags > BPF_EXIST))
- /* unknown flags */
- return -EINVAL;
+ ret = htab_map_check_update_flags(onallcpus, map_flags);
+ if (unlikely(ret))
+ return ret;
WARN_ON_ONCE(!bpf_rcu_lock_held());
@@ -1289,7 +1307,7 @@ static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
/* Update value in-place */
if (percpu) {
pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
- value, onallcpus);
+ value, onallcpus, map_flags);
} else {
void **inner_map_pptr = htab_elem_value(l_old, key_size);
@@ -1298,7 +1316,7 @@ static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
}
} else {
l_new = alloc_htab_elem(htab, key, value, key_size,
- hash, percpu, onallcpus, NULL);
+ hash, percpu, onallcpus, NULL, map_flags);
if (IS_ERR(l_new)) {
ret = PTR_ERR(l_new);
goto err;
@@ -1324,9 +1342,9 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
u32 key_size, hash;
int ret;
- if (unlikely(map_flags > BPF_EXIST))
- /* unknown flags */
- return -EINVAL;
+ ret = htab_map_check_update_flags(onallcpus, map_flags);
+ if (unlikely(ret))
+ return ret;
WARN_ON_ONCE(!bpf_rcu_lock_held());
@@ -1363,10 +1381,10 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
/* per-cpu hash map can update value in-place */
pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
- value, onallcpus);
+ value, onallcpus, map_flags);
} else {
pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
- value, onallcpus);
+ value, onallcpus, map_flags);
hlist_nulls_add_head_rcu(&l_new->hash_node, head);
l_new = NULL;
}
@@ -1678,9 +1696,9 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
u32 batch, max_count, size, bucket_size, map_id;
+ u64 elem_map_flags, map_flags, allowed_flags;
u32 bucket_cnt, total, key_size, value_size;
struct htab_elem *node_to_free = NULL;
- u64 elem_map_flags, map_flags;
struct hlist_nulls_head *head;
struct hlist_nulls_node *n;
unsigned long flags = 0;
@@ -1690,9 +1708,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
int ret = 0;
elem_map_flags = attr->batch.elem_flags;
- if ((elem_map_flags & ~BPF_F_LOCK) ||
- ((elem_map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)))
- return -EINVAL;
+ allowed_flags = BPF_F_LOCK;
+ if (!do_delete && is_percpu)
+ allowed_flags |= BPF_F_CPU;
+ ret = bpf_map_check_op_flags(map, elem_map_flags, allowed_flags);
+ if (ret)
+ return ret;
map_flags = attr->batch.flags;
if (map_flags)
@@ -1715,7 +1736,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
key_size = htab->map.key_size;
value_size = htab->map.value_size;
size = round_up(value_size, 8);
- if (is_percpu)
+ if (is_percpu && !(elem_map_flags & BPF_F_CPU))
value_size = size * num_possible_cpus();
total = 0;
/* while experimenting with hash tables with sizes ranging from 10 to
@@ -1798,10 +1819,17 @@ again_nocopy:
void __percpu *pptr;
pptr = htab_elem_get_ptr(l, map->key_size);
- for_each_possible_cpu(cpu) {
- copy_map_value_long(&htab->map, dst_val + off, per_cpu_ptr(pptr, cpu));
- check_and_init_map_value(&htab->map, dst_val + off);
- off += size;
+ if (elem_map_flags & BPF_F_CPU) {
+ cpu = elem_map_flags >> 32;
+ copy_map_value(&htab->map, dst_val, per_cpu_ptr(pptr, cpu));
+ check_and_init_map_value(&htab->map, dst_val);
+ } else {
+ for_each_possible_cpu(cpu) {
+ copy_map_value_long(&htab->map, dst_val + off,
+ per_cpu_ptr(pptr, cpu));
+ check_and_init_map_value(&htab->map, dst_val + off);
+ off += size;
+ }
}
} else {
value = htab_elem_value(l, key_size);
@@ -2357,7 +2385,7 @@ static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *k
return NULL;
}
-int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value, u64 map_flags)
{
struct htab_elem *l;
void __percpu *pptr;
@@ -2374,16 +2402,22 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
l = __htab_map_lookup_elem(map, key);
if (!l)
goto out;
+ ret = 0;
/* We do not mark LRU map element here in order to not mess up
* eviction heuristics when user space does a map walk.
*/
pptr = htab_elem_get_ptr(l, map->key_size);
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value(map, value, per_cpu_ptr(pptr, cpu));
+ check_and_init_map_value(map, value);
+ goto out;
+ }
for_each_possible_cpu(cpu) {
copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
check_and_init_map_value(map, value + off);
off += size;
}
- ret = 0;
out:
rcu_read_unlock();
return ret;
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c93a756e035c..1ccbf28b2ad9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -180,7 +180,7 @@ static long cgroup_storage_update_elem(struct bpf_map *map, void *key,
}
int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
- void *value)
+ void *value, u64 map_flags)
{
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
struct bpf_cgroup_storage *storage;
@@ -198,12 +198,17 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
* access 'value_size' of them, so copying rounded areas
* will not leak any kernel data
*/
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value(_map, value, per_cpu_ptr(storage->percpu_buf, cpu));
+ goto unlock;
+ }
size = round_up(_map->value_size, 8);
for_each_possible_cpu(cpu) {
- bpf_long_memcpy(value + off,
- per_cpu_ptr(storage->percpu_buf, cpu), size);
+ copy_map_value_long(_map, value + off, per_cpu_ptr(storage->percpu_buf, cpu));
off += size;
}
+unlock:
rcu_read_unlock();
return 0;
}
@@ -213,10 +218,11 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
{
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
struct bpf_cgroup_storage *storage;
- int cpu, off = 0;
+ void *val;
u32 size;
+ int cpu;
- if (map_flags != BPF_ANY && map_flags != BPF_EXIST)
+ if ((u32)map_flags & ~(BPF_ANY | BPF_EXIST | BPF_F_CPU | BPF_F_ALL_CPUS))
return -EINVAL;
rcu_read_lock();
@@ -232,12 +238,17 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
* returned or zeros which were zero-filled by percpu_alloc,
* so no kernel data leaks possible
*/
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value(_map, per_cpu_ptr(storage->percpu_buf, cpu), value);
+ goto unlock;
+ }
size = round_up(_map->value_size, 8);
for_each_possible_cpu(cpu) {
- bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
- value + off, size);
- off += size;
+ val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu;
+ copy_map_value(_map, per_cpu_ptr(storage->percpu_buf, cpu), val);
}
+unlock:
rcu_read_unlock();
return 0;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6dd2ad2f9e81..ecc0929ce462 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -133,12 +133,14 @@ bool bpf_map_write_active(const struct bpf_map *map)
return atomic64_read(&map->writecnt) != 0;
}
-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 ||
- map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
- map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
+static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
+{
+ if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS))
+ return map->value_size;
+ else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
return round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
return sizeof(u32);
@@ -314,11 +316,11 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
bpf_disable_instrumentation();
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
- err = bpf_percpu_hash_copy(map, key, value);
+ err = bpf_percpu_hash_copy(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
- err = bpf_percpu_array_copy(map, key, value);
+ err = bpf_percpu_array_copy(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
- err = bpf_percpu_cgroup_storage_copy(map, key, value);
+ err = bpf_percpu_cgroup_storage_copy(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
err = bpf_stackmap_extract(map, key, value, false);
} else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
@@ -1729,7 +1731,7 @@ static int map_lookup_elem(union bpf_attr *attr)
if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
return -EPERM;
- err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK);
+ err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK | BPF_F_CPU);
if (err)
return err;
@@ -1737,7 +1739,7 @@ static int map_lookup_elem(union bpf_attr *attr)
if (IS_ERR(key))
return PTR_ERR(key);
- value_size = bpf_map_value_size(map);
+ value_size = bpf_map_value_size(map, attr->flags);
err = -ENOMEM;
value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN);
@@ -1804,7 +1806,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
goto err_put;
}
- value_size = bpf_map_value_size(map);
+ value_size = bpf_map_value_size(map, attr->flags);
value = kvmemdup_bpfptr(uvalue, value_size);
if (IS_ERR(value)) {
err = PTR_ERR(value);
@@ -2000,11 +2002,12 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
void *key, *value;
int err = 0;
- err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags,
+ BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS);
if (err)
return err;
- value_size = bpf_map_value_size(map);
+ value_size = bpf_map_value_size(map, attr->batch.elem_flags);
max_count = attr->batch.count;
if (!max_count)
@@ -2059,11 +2062,11 @@ int generic_map_lookup_batch(struct bpf_map *map,
u32 value_size, cp, max_count;
int err;
- err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK | BPF_F_CPU);
if (err)
return err;
- value_size = bpf_map_value_size(map);
+ value_size = bpf_map_value_size(map, attr->batch.elem_flags);
max_count = attr->batch.count;
if (!max_count)
@@ -2185,7 +2188,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
goto err_put;
}
- value_size = bpf_map_value_size(map);
+ value_size = bpf_map_value_size(map, 0);
err = -ENOMEM;
value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN);
generated by cgit v1.2.3 (git 2.0.4) at 2026-02-13 19:08:36 +0000