Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags and check them for
following APIs:
* 'map_lookup_elem()'
* 'map_update_elem()'
* 'generic_map_lookup_batch()'
* 'generic_map_update_batch()'
And, get the correct value size for these APIs.
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
v10 -> v11:
- Use '(BPF_F_ALL_CPUS << 1) - 1' as allowed_flags in map_update_elem().
- Add BPF_EXIST to allowed_flags in generic_map_update_batch().
---
include/linux/bpf.h | 23 +++++++++++++++++++++-
include/uapi/linux/bpf.h | 2 ++
kernel/bpf/syscall.c | 36 ++++++++++++++++++++--------------
tools/include/uapi/linux/bpf.h | 2 ++
4 files changed, 47 insertions(+), 16 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6498be4c44f8..d84af3719b59 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3829,14 +3829,35 @@ bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image)
}
#endif
+static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
+{
+ return false;
+}
+
static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
{
- if (flags & ~allowed_flags)
+ u32 cpu;
+
+ if ((u32)flags & ~allowed_flags)
return -EINVAL;
if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
return -EINVAL;
+ if (!(flags & BPF_F_CPU) && flags >> 32)
+ return -EINVAL;
+
+ if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
+ if (!bpf_map_supports_cpu_flags(map->map_type))
+ return -EINVAL;
+ if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS))
+ return -EINVAL;
+
+ cpu = flags >> 32;
+ if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus())
+ return -ERANGE;
+ }
+
return 0;
}
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f5713f59ac10..8b6279ca6e66 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1373,6 +1373,8 @@ enum {
BPF_NOEXIST = 1, /* create new element if it didn't exist */
BPF_EXIST = 2, /* update existing element */
BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */
+ BPF_F_CPU = 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+ BPF_F_ALL_CPUS = 16, /* update value across all CPUs for percpu maps */
};
/* flags for BPF_MAP_CREATE command */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cef8963d69f9..3c3e3b4095b9 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);
@@ -1732,7 +1734,7 @@ 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;
@@ -1740,7 +1742,7 @@ 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);
@@ -1781,6 +1783,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel);
struct bpf_map *map;
void *key, *value;
+ u64 allowed_flags;
u32 value_size;
int err;
@@ -1797,7 +1800,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
goto err_put;
}
- err = bpf_map_check_op_flags(map, attr->flags, ~0);
+ allowed_flags = (BPF_F_ALL_CPUS << 1) - 1;
+ err = bpf_map_check_op_flags(map, attr->flags, allowed_flags);
if (err)
goto err_put;
@@ -1807,7 +1811,7 @@ 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);
@@ -2001,13 +2005,15 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
void __user *keys = u64_to_user_ptr(attr->batch.keys);
u32 value_size, cp, max_count;
void *key, *value;
+ u64 allowed_flags;
int err = 0;
- err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ allowed_flags = BPF_EXIST | BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS;
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags, allowed_flags);
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)
@@ -2062,11 +2068,11 @@ 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)
@@ -2188,7 +2194,7 @@ 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);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f5713f59ac10..8b6279ca6e66 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1373,6 +1373,8 @@ enum {
BPF_NOEXIST = 1, /* create new element if it didn't exist */
BPF_EXIST = 2, /* update existing element */
BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */
+ BPF_F_CPU = 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+ BPF_F_ALL_CPUS = 16, /* update value across all CPUs for percpu maps */
};
/* flags for BPF_MAP_CREATE command */
--
2.51.2On Tue, Nov 25, 2025 at 6:59 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags and check them for
> following APIs:
>
> * 'map_lookup_elem()'
> * 'map_update_elem()'
> * 'generic_map_lookup_batch()'
> * 'generic_map_update_batch()'
>
> And, get the correct value size for these APIs.
>
> Acked-by: Andrii Nakryiko <andrii@kernel.org>
> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
> ---
> v10 -> v11:
> - Use '(BPF_F_ALL_CPUS << 1) - 1' as allowed_flags in map_update_elem().
> - Add BPF_EXIST to allowed_flags in generic_map_update_batch().
It should be mentioned in the commit log.
Lines after --- don't stay in the log.
> ---
> include/linux/bpf.h | 23 +++++++++++++++++++++-
> include/uapi/linux/bpf.h | 2 ++
> kernel/bpf/syscall.c | 36 ++++++++++++++++++++--------------
> tools/include/uapi/linux/bpf.h | 2 ++
> 4 files changed, 47 insertions(+), 16 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 6498be4c44f8..d84af3719b59 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -3829,14 +3829,35 @@ bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image)
> }
> #endif
>
> +static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
> +{
> + return false;
> +}
> +
> static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
> {
> - if (flags & ~allowed_flags)
> + u32 cpu;
> +
> + if ((u32)flags & ~allowed_flags)
> return -EINVAL;
>
> if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
> return -EINVAL;
>
> + if (!(flags & BPF_F_CPU) && flags >> 32)
> + return -EINVAL;
> +
> + if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
> + if (!bpf_map_supports_cpu_flags(map->map_type))
> + return -EINVAL;
> + if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS))
> + return -EINVAL;
> +
> + cpu = flags >> 32;
> + if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus())
> + return -ERANGE;
> + }
> +
> return 0;
> }
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index f5713f59ac10..8b6279ca6e66 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -1373,6 +1373,8 @@ enum {
> BPF_NOEXIST = 1, /* create new element if it didn't exist */
> BPF_EXIST = 2, /* update existing element */
> BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */
> + BPF_F_CPU = 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
> + BPF_F_ALL_CPUS = 16, /* update value across all CPUs for percpu maps */
> };
>
> /* flags for BPF_MAP_CREATE command */
> diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> index cef8963d69f9..3c3e3b4095b9 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);
> @@ -1732,7 +1734,7 @@ 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;
>
> @@ -1740,7 +1742,7 @@ 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);
> @@ -1781,6 +1783,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
> bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel);
> struct bpf_map *map;
> void *key, *value;
> + u64 allowed_flags;
> u32 value_size;
> int err;
>
> @@ -1797,7 +1800,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
> goto err_put;
> }
>
> - err = bpf_map_check_op_flags(map, attr->flags, ~0);
> + allowed_flags = (BPF_F_ALL_CPUS << 1) - 1;
This is cryptic.
Use
allowed_flags = BPF_NOEXIST | BPF_EXIST | BPF_F_LOCK | BPF_F_CPU |
BPF_F_ALL_CPUS;
© 2016 - 2025 Red Hat, Inc.