* [PATCH bpf-next v6 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
` (5 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
It is to unify map flags checking for lookup_elem, update_elem,
lookup_batch and update_batch APIs.
Therefore, it will be convenient to check BPF_F_CPU and BPF_F_ALL_CPUS
flags in it for these APIs in next patch.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
kernel/bpf/syscall.c | 45 ++++++++++++++++++++++----------------------
1 file changed, 22 insertions(+), 23 deletions(-)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3f178a0f8eb12..f5448e00a2e8f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -131,6 +131,17 @@ bool bpf_map_write_active(const struct bpf_map *map)
return atomic64_read(&map->writecnt) != 0;
}
+static int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
+{
+ if (flags & ~allowed_flags)
+ return -EINVAL;
+
+ if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+ return -EINVAL;
+
+ return 0;
+}
+
static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -1669,9 +1680,6 @@ static int map_lookup_elem(union bpf_attr *attr)
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
- if (attr->flags & ~BPF_F_LOCK)
- return -EINVAL;
-
CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
@@ -1679,9 +1687,9 @@ static int map_lookup_elem(union bpf_attr *attr)
if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
return -EPERM;
- if ((attr->flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK))
- return -EINVAL;
+ err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK);
+ if (err)
+ return err;
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key))
@@ -1744,11 +1752,9 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
goto err_put;
}
- if ((attr->flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
- err = -EINVAL;
+ err = bpf_map_check_op_flags(map, attr->flags, ~0);
+ if (err)
goto err_put;
- }
key = ___bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
@@ -1952,13 +1958,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
void *key, *value;
int err = 0;
- if (attr->batch.elem_flags & ~BPF_F_LOCK)
- return -EINVAL;
-
- if ((attr->batch.elem_flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
- return -EINVAL;
- }
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ if (err)
+ return err;
value_size = bpf_map_value_size(map);
@@ -2015,12 +2017,9 @@ int generic_map_lookup_batch(struct bpf_map *map,
u32 value_size, cp, max_count;
int err;
- if (attr->batch.elem_flags & ~BPF_F_LOCK)
- return -EINVAL;
-
- if ((attr->batch.elem_flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK))
- return -EINVAL;
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ if (err)
+ return err;
value_size = bpf_map_value_size(map);
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH bpf-next v6 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
2025-09-09 23:07 ` Alexei Starovoitov
2025-09-09 14:14 ` [PATCH bpf-next v6 3/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_array maps Leon Hwang
` (4 subsequent siblings)
6 siblings, 1 reply; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
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.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
include/linux/bpf.h | 22 ++++++++++++++++++
include/uapi/linux/bpf.h | 2 ++
kernel/bpf/syscall.c | 42 ++++++++++++++++++++++------------
tools/include/uapi/linux/bpf.h | 2 ++
4 files changed, 54 insertions(+), 14 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8f6e87f0f3a89..60c235836987d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3709,4 +3709,26 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char *
const char **linep, int *nump);
struct bpf_prog *bpf_prog_find_from_stack(void);
+static inline int bpf_map_check_cpu_flags(u64 flags, bool check_all_cpus_flag)
+{
+ const u64 cpu_flags = BPF_F_CPU | BPF_F_ALL_CPUS;
+ u32 cpu;
+
+ if (check_all_cpus_flag) {
+ if (unlikely((u32)flags > BPF_F_ALL_CPUS))
+ return -EINVAL;
+ if (unlikely((flags & cpu_flags) == cpu_flags))
+ return -EINVAL;
+ } else {
+ if (unlikely((u32)flags & ~BPF_F_CPU))
+ return -EINVAL;
+ }
+
+ cpu = flags >> 32;
+ if (unlikely((flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
+ return -ERANGE;
+
+ return 0;
+}
+
#endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 233de8677382e..be1fdc5042744 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1372,6 +1372,8 @@ 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 f5448e00a2e8f..db841b38f0c22 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -131,23 +131,36 @@ bool bpf_map_write_active(const struct bpf_map *map)
return atomic64_read(&map->writecnt) != 0;
}
+static bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
+{
+ return false;
+}
+
static int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
{
- if (flags & ~allowed_flags)
+ 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)) && !bpf_map_supports_cpu_flags(map->map_type))
+ return -EINVAL;
+
return 0;
}
-static u32 bpf_map_value_size(const struct bpf_map *map)
+static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
{
- 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)
+ if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS))
+ return round_up(map->value_size, 8);
+ 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);
@@ -1687,7 +1700,7 @@ 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;
@@ -1695,7 +1708,7 @@ 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);
@@ -1762,7 +1775,7 @@ 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);
@@ -1958,11 +1971,12 @@ 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)
@@ -2017,11 +2031,11 @@ 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)
@@ -2143,7 +2157,7 @@ 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 233de8677382e..be1fdc5042744 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1372,6 +1372,8 @@ 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 */
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [PATCH bpf-next v6 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-09-09 14:14 ` [PATCH bpf-next v6 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
@ 2025-09-09 23:07 ` Alexei Starovoitov
2025-09-10 2:20 ` Leon Hwang
0 siblings, 1 reply; 10+ messages in thread
From: Alexei Starovoitov @ 2025-09-09 23:07 UTC (permalink / raw)
To: Leon Hwang
Cc: bpf, Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Jiri Olsa, Yonghong Song, Song Liu, Eduard, Daniel Xu,
Daniel Müller, kernel-patches-bot
On Tue, Sep 9, 2025 at 7:14 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.
>
> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
> ---
> include/linux/bpf.h | 22 ++++++++++++++++++
> include/uapi/linux/bpf.h | 2 ++
> kernel/bpf/syscall.c | 42 ++++++++++++++++++++++------------
> tools/include/uapi/linux/bpf.h | 2 ++
> 4 files changed, 54 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 8f6e87f0f3a89..60c235836987d 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -3709,4 +3709,26 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char *
> const char **linep, int *nump);
> struct bpf_prog *bpf_prog_find_from_stack(void);
>
> +static inline int bpf_map_check_cpu_flags(u64 flags, bool check_all_cpus_flag)
> +{
This function is not used in this patch. Don't add it without users.
Also I really don't like 'bool' arguments.
They make callsite hard to read.
Instead of bool use
bpf_map_check_flags(u64 flags, u64 allowed_flags)
so the callsites will look like:
bpf_map_check_flags(flags, BPF_F_CPU);
and
bpf_map_check_flags(flags, BPF_F_CPU | BPF_F_ALL_CPUS);
Also two functions that do very similar things look redundant.
This bpf_map_check_flags() vs bpf_map_check_op_flags()...
I think one should do it.
pw-bot: cr
> + const u64 cpu_flags = BPF_F_CPU | BPF_F_ALL_CPUS;
> + u32 cpu;
> +
> + if (check_all_cpus_flag) {
> + if (unlikely((u32)flags > BPF_F_ALL_CPUS))
> + return -EINVAL;
> + if (unlikely((flags & cpu_flags) == cpu_flags))
> + return -EINVAL;
> + } else {
> + if (unlikely((u32)flags & ~BPF_F_CPU))
> + return -EINVAL;
> + }
> +
> + cpu = flags >> 32;
> + if (unlikely((flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
> + return -ERANGE;
> +
> + return 0;
> +}
> +
> #endif /* _LINUX_BPF_H */
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 233de8677382e..be1fdc5042744 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -1372,6 +1372,8 @@ 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 f5448e00a2e8f..db841b38f0c22 100644
> --- a/kernel/bpf/syscall.c
> +++ b/kernel/bpf/syscall.c
> @@ -131,23 +131,36 @@ bool bpf_map_write_active(const struct bpf_map *map)
> return atomic64_read(&map->writecnt) != 0;
> }
>
> +static bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
> +{
> + return false;
> +}
> +
> static int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
> {
> - if (flags & ~allowed_flags)
> + 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)) && !bpf_map_supports_cpu_flags(map->map_type))
> + return -EINVAL;
> +
> return 0;
> }
>
> -static u32 bpf_map_value_size(const struct bpf_map *map)
> +static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
> {
> - 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)
> + if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS))
> + return round_up(map->value_size, 8);
> + 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);
> @@ -1687,7 +1700,7 @@ 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;
>
> @@ -1695,7 +1708,7 @@ 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);
> @@ -1762,7 +1775,7 @@ 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);
> @@ -1958,11 +1971,12 @@ 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)
> @@ -2017,11 +2031,11 @@ 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)
> @@ -2143,7 +2157,7 @@ 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 233de8677382e..be1fdc5042744 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
> @@ -1372,6 +1372,8 @@ 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 */
> --
> 2.50.1
>
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH bpf-next v6 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-09-09 23:07 ` Alexei Starovoitov
@ 2025-09-10 2:20 ` Leon Hwang
0 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-10 2:20 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: bpf, Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Jiri Olsa, Yonghong Song, Song Liu, Eduard, Daniel Xu,
Daniel Müller, kernel-patches-bot
On 10/9/25 07:07, Alexei Starovoitov wrote:
> On Tue, Sep 9, 2025 at 7:14 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.
>>
>> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
>> ---
>> include/linux/bpf.h | 22 ++++++++++++++++++
>> include/uapi/linux/bpf.h | 2 ++
>> kernel/bpf/syscall.c | 42 ++++++++++++++++++++++------------
>> tools/include/uapi/linux/bpf.h | 2 ++
>> 4 files changed, 54 insertions(+), 14 deletions(-)
>>
>> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>> index 8f6e87f0f3a89..60c235836987d 100644
>> --- a/include/linux/bpf.h
>> +++ b/include/linux/bpf.h
>> @@ -3709,4 +3709,26 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char *
>> const char **linep, int *nump);
>> struct bpf_prog *bpf_prog_find_from_stack(void);
>>
>> +static inline int bpf_map_check_cpu_flags(u64 flags, bool check_all_cpus_flag)
>> +{
>
> This function is not used in this patch. Don't add it without users.
>
> Also I really don't like 'bool' arguments.
> They make callsite hard to read.
Agreed. Using a bool argument here makes the call sites harder to
understand.
> Instead of bool use
> bpf_map_check_flags(u64 flags, u64 allowed_flags)
>
> so the callsites will look like:
> bpf_map_check_flags(flags, BPF_F_CPU);
> and
> bpf_map_check_flags(flags, BPF_F_CPU | BPF_F_ALL_CPUS);
>
> Also two functions that do very similar things look redundant.
> This bpf_map_check_flags() vs bpf_map_check_op_flags()...
> I think one should do it.
>
Yes. It would be better to consolidate this logic into
bpf_map_check_op_flags(), rather than introducing a separate but
overlapping helper. That should keep the code simpler and avoid redundancy.
Thanks,
Leon
[...]
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH bpf-next v6 3/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_array maps
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 4/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_hash and lru_percpu_hash maps Leon Hwang
` (3 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
Introduce support for the BPF_F_ALL_CPUS flag in percpu_array maps to
allow updating values for all CPUs with a single value for both
update_elem and update_batch APIs.
Introduce support for the BPF_F_CPU flag in percpu_array maps to allow:
* update value for specified CPU for both update_elem and update_batch
APIs.
* lookup value for specified CPU for both lookup_elem and lookup_batch
APIs.
The BPF_F_CPU flag is passed via:
* map_flags of lookup_elem and update_elem APIs along with embedded cpu
info.
* elem_flags of lookup_batch and update_batch APIs along with embedded
cpu info.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
include/linux/bpf.h | 2 +-
kernel/bpf/arraymap.c | 36 +++++++++++++++++++++++++++++-------
kernel/bpf/syscall.c | 9 +++++++--
3 files changed, 37 insertions(+), 10 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 60c235836987d..b5143420ea947 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2697,7 +2697,7 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
struct bpf_func_state *callee);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
-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 flags);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 3d080916faf97..aa5c17c707f1c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -295,14 +295,18 @@ 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;
+ int err, cpu, off = 0;
void __percpu *pptr;
- int cpu, off = 0;
u32 size;
+ err = bpf_map_check_cpu_flags(map_flags, false);
+ if (unlikely(err))
+ return err;
+
if (unlikely(index >= array->map.max_entries))
return -ENOENT;
@@ -313,11 +317,18 @@ 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_long(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;
}
@@ -386,13 +397,13 @@ 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;
+ int err, cpu, off = 0;
void __percpu *pptr;
- int cpu, off = 0;
u32 size;
- if (unlikely(map_flags > BPF_EXIST))
- /* unknown flags */
- return -EINVAL;
+ err = bpf_map_check_cpu_flags(map_flags, true);
+ if (unlikely(err))
+ return err;
if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
@@ -411,11 +422,22 @@ 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;
+ copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value);
+ bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
+ 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;
+ /* same user-provided value is used if BPF_F_ALL_CPUS is
+ * specified, otherwise value is an array of per-CPU values.
+ */
+ if (!(map_flags & BPF_F_ALL_CPUS))
+ off += size;
}
+unlock:
rcu_read_unlock();
return 0;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index db841b38f0c22..6d0a08d63f175 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -133,7 +133,12 @@ bool bpf_map_write_active(const struct bpf_map *map)
static bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
{
- return false;
+ switch (map_type) {
+ case BPF_MAP_TYPE_PERCPU_ARRAY:
+ return true;
+ default:
+ return false;
+ }
}
static int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
@@ -338,7 +343,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_copy(map, key, value);
} 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);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH bpf-next v6 4/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_hash and lru_percpu_hash maps
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (2 preceding siblings ...)
2025-09-09 14:14 ` [PATCH bpf-next v6 3/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_array maps Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 5/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_cgroup_storage maps Leon Hwang
` (2 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
Introduce BPF_F_ALL_CPUS flag support for percpu_hash and lru_percpu_hash
maps to allow updating values for all CPUs with a single value for both
update_elem and update_batch APIs.
Introduce BPF_F_CPU flag support for percpu_hash and lru_percpu_hash
maps to allow:
* update value for specified CPU for both update_elem and update_batch
APIs.
* lookup value for specified CPU for both lookup_elem and lookup_batch
APIs.
The BPF_F_CPU flag is passed via:
* map_flags along with embedded cpu info.
* elem_flags along with embedded cpu info.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
include/linux/bpf.h | 2 +-
kernel/bpf/hashtab.c | 105 +++++++++++++++++++++++++++++++------------
kernel/bpf/syscall.c | 4 +-
3 files changed, 80 insertions(+), 31 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b5143420ea947..7f49bb3fdaf1e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2696,7 +2696,7 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee);
-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 flags);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 71f9931ac64cd..07f4daf384776 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -937,7 +937,7 @@ 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)
{
if (!onallcpus) {
/* copy true value_size bytes */
@@ -946,15 +946,26 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
u32 size = round_up(htab->map.value_size, 8);
int off = 0, cpu;
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value);
+ return;
+ }
+
for_each_possible_cpu(cpu) {
copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off);
- off += size;
+ /* same user-provided value is used if BPF_F_ALL_CPUS
+ * is specified, otherwise value is an array of per-CPU
+ * values.
+ */
+ if (!(map_flags & BPF_F_ALL_CPUS))
+ 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
@@ -972,7 +983,7 @@ 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);
}
}
@@ -984,7 +995,7 @@ 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);
@@ -1042,7 +1053,7 @@ 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 +1158,7 @@ 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);
@@ -1263,9 +1274,15 @@ 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;
+ if (onallcpus) {
+ ret = bpf_map_check_cpu_flags(map_flags, true);
+ if (unlikely(ret))
+ return ret;
+ } else {
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+ }
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
!rcu_read_lock_bh_held());
@@ -1291,7 +1308,7 @@ 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);
@@ -1300,7 +1317,7 @@ 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;
@@ -1326,9 +1343,15 @@ 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;
+ if (onallcpus) {
+ ret = bpf_map_check_cpu_flags(map_flags, true);
+ if (unlikely(ret))
+ return ret;
+ } else {
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+ }
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
!rcu_read_lock_bh_held());
@@ -1366,10 +1389,10 @@ 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;
}
@@ -1698,9 +1721,16 @@ __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;
+ if (!do_delete && is_percpu) {
+ ret = bpf_map_check_cpu_flags(elem_map_flags, false);
+ if (ret)
+ return ret;
+ } else {
+ if ((elem_map_flags & ~BPF_F_LOCK) ||
+ ((elem_map_flags & BPF_F_LOCK) &&
+ !btf_record_has_field(map->record, BPF_SPIN_LOCK)))
+ return -EINVAL;
+ }
map_flags = attr->batch.flags;
if (map_flags)
@@ -1806,10 +1836,17 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
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_long(&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);
@@ -2365,14 +2402,17 @@ 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)
{
+ int ret, cpu, off = 0;
struct htab_elem *l;
void __percpu *pptr;
- int ret = -ENOENT;
- int cpu, off = 0;
u32 size;
+ ret = bpf_map_check_cpu_flags(map_flags, false);
+ if (unlikely(ret))
+ return ret;
+
/* per_cpu areas are zero-filled and bpf programs can only
* access 'value_size' of them, so copying rounded areas
* will not leak any kernel data
@@ -2380,18 +2420,25 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
size = round_up(map->value_size, 8);
rcu_read_lock();
l = __htab_map_lookup_elem(map, key);
- if (!l)
+ if (!l) {
+ ret = -ENOENT;
goto out;
+ }
/* 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_long(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/syscall.c b/kernel/bpf/syscall.c
index 6d0a08d63f175..d01424e0560ce 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -135,6 +135,8 @@ static bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
{
switch (map_type) {
case BPF_MAP_TYPE_PERCPU_ARRAY:
+ case BPF_MAP_TYPE_PERCPU_HASH:
+ case BPF_MAP_TYPE_LRU_PERCPU_HASH:
return true;
default:
return false;
@@ -341,7 +343,7 @@ 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, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH bpf-next v6 5/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_cgroup_storage maps
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (3 preceding siblings ...)
2025-09-09 14:14 ` [PATCH bpf-next v6 4/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_hash and lru_percpu_hash maps Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 6/7] libbpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu maps Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
6 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
Introduce BPF_F_ALL_CPUS flag support for percpu_cgroup_storage maps to
allow updating values for all CPUs with a single value for update_elem
API.
Introduce BPF_F_CPU flag support for percpu_cgroup_storage maps to
allow:
* update value for specified CPU for update_elem API.
* lookup value for specified CPU for lookup_elem API.
The BPF_F_CPU flag is passed via map_flags along with embedded cpu info.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
include/linux/bpf-cgroup.h | 4 ++--
kernel/bpf/local_storage.c | 46 +++++++++++++++++++++++++++++---------
kernel/bpf/syscall.c | 3 ++-
3 files changed, 39 insertions(+), 14 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index aedf573bdb426..013f4db9903fd 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -172,7 +172,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map);
-int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value, u64 flags);
int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
void *value, u64 flags);
@@ -467,7 +467,7 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
static inline void bpf_cgroup_storage_free(
struct bpf_cgroup_storage *storage) {}
static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key,
- void *value) {
+ void *value, u64 flags) {
return 0;
}
static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c93a756e035c0..1abfbb27449ee 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -180,18 +180,22 @@ 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;
- int cpu, off = 0;
+ int err, cpu, off = 0;
u32 size;
+ err = bpf_map_check_cpu_flags(map_flags, false);
+ if (err)
+ return err;
+
rcu_read_lock();
storage = cgroup_storage_lookup(map, key, false);
if (!storage) {
- rcu_read_unlock();
- return -ENOENT;
+ err = -ENOENT;
+ goto unlock;
}
/* per_cpu areas are zero-filled and bpf programs can only
@@ -199,13 +203,19 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
* will not leak any kernel data
*/
size = round_up(_map->value_size, 8);
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ bpf_long_memcpy(value, per_cpu_ptr(storage->percpu_buf, cpu), size);
+ goto unlock;
+ }
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off,
per_cpu_ptr(storage->percpu_buf, cpu), size);
off += size;
}
+unlock:
rcu_read_unlock();
- return 0;
+ return err;
}
int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
@@ -213,17 +223,21 @@ 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;
+ int err, cpu, off = 0;
u32 size;
- 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;
+ err = bpf_map_check_cpu_flags(map_flags, true);
+ if (err)
+ return err;
+
rcu_read_lock();
storage = cgroup_storage_lookup(map, key, false);
if (!storage) {
- rcu_read_unlock();
- return -ENOENT;
+ err = -ENOENT;
+ goto unlock;
}
/* the user space will provide round_up(value_size, 8) bytes that
@@ -233,13 +247,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
* so no kernel data leaks possible
*/
size = round_up(_map->value_size, 8);
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), value, size);
+ goto unlock;
+ }
for_each_possible_cpu(cpu) {
bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
value + off, size);
- off += size;
+ /* same user-provided value is used if BPF_F_ALL_CPUS is
+ * specified, otherwise value is an array of per-CPU values.
+ */
+ if (!(map_flags & BPF_F_ALL_CPUS))
+ off += size;
}
+unlock:
rcu_read_unlock();
- return 0;
+ return err;
}
static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d01424e0560ce..dbb715719f40c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -137,6 +137,7 @@ static bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
case BPF_MAP_TYPE_PERCPU_ARRAY:
case BPF_MAP_TYPE_PERCPU_HASH:
case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
return true;
default:
return false;
@@ -347,7 +348,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
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_copy(map, key, value);
} else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH bpf-next v6 6/7] libbpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu maps
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (4 preceding siblings ...)
2025-09-09 14:14 ` [PATCH bpf-next v6 5/7] bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_cgroup_storage maps Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
2025-09-09 14:14 ` [PATCH bpf-next v6 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
6 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
Add libbpf support for the BPF_F_CPU flag for percpu maps by embedding the
cpu info into the high 32 bits of:
1. **flags**: bpf_map_lookup_elem_flags(), bpf_map__lookup_elem(),
bpf_map_update_elem() and bpf_map__update_elem()
2. **opts->elem_flags**: bpf_map_lookup_batch() and
bpf_map_update_batch()
And the flag can be BPF_F_ALL_CPUS, but cannot be
'BPF_F_CPU | BPF_F_ALL_CPUS'.
Behavior:
* If the flag is BPF_F_ALL_CPUS, the update is applied across all CPUs.
* If the flag is BPF_F_CPU, it updates value only to the specified CPU.
* If the flag is BPF_F_CPU, lookup value only from the specified CPU.
* lookup does not support BPF_F_ALL_CPUS.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
tools/lib/bpf/bpf.h | 8 ++++++++
tools/lib/bpf/libbpf.c | 26 ++++++++++++++++++++------
tools/lib/bpf/libbpf.h | 21 ++++++++-------------
3 files changed, 36 insertions(+), 19 deletions(-)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 7252150e7ad35..28acb15e982b3 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -286,6 +286,14 @@ LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
* Update spin_lock-ed map elements. This must be
* specified if the map value contains a spinlock.
*
+ * **BPF_F_CPU**
+ * As for percpu maps, update value on the specified CPU. And the cpu
+ * info is embedded into the high 32 bits of **opts->elem_flags**.
+ *
+ * **BPF_F_ALL_CPUS**
+ * As for percpu maps, update value across all CPUs. This flag cannot
+ * be used with BPF_F_CPU at the same time.
+ *
* @param fd BPF map file descriptor
* @param keys pointer to an array of *count* keys
* @param values pointer to an array of *count* values
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fe4fc5438678c..3d60e7a713518 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10603,7 +10603,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
}
static int validate_map_op(const struct bpf_map *map, size_t key_sz,
- size_t value_sz, bool check_value_sz)
+ size_t value_sz, bool check_value_sz, __u64 flags)
{
if (!map_is_created(map)) /* map is not yet created */
return -ENOENT;
@@ -10630,6 +10630,20 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
int num_cpu = libbpf_num_possible_cpus();
size_t elem_sz = roundup(map->def.value_size, 8);
+ if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
+ if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS)) {
+ pr_warn("map '%s': can't use BPF_F_CPU and BPF_F_ALL_CPUS at the same time\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (value_sz != elem_sz) {
+ pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %zu\n",
+ map->name, value_sz, elem_sz);
+ return -EINVAL;
+ }
+ break;
+ }
+
if (value_sz != num_cpu * elem_sz) {
pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %d * %zu = %zd\n",
map->name, value_sz, num_cpu, elem_sz, num_cpu * elem_sz);
@@ -10654,7 +10668,7 @@ int bpf_map__lookup_elem(const struct bpf_map *map,
{
int err;
- err = validate_map_op(map, key_sz, value_sz, true);
+ err = validate_map_op(map, key_sz, value_sz, true, flags);
if (err)
return libbpf_err(err);
@@ -10667,7 +10681,7 @@ int bpf_map__update_elem(const struct bpf_map *map,
{
int err;
- err = validate_map_op(map, key_sz, value_sz, true);
+ err = validate_map_op(map, key_sz, value_sz, true, flags);
if (err)
return libbpf_err(err);
@@ -10679,7 +10693,7 @@ int bpf_map__delete_elem(const struct bpf_map *map,
{
int err;
- err = validate_map_op(map, key_sz, 0, false /* check_value_sz */);
+ err = validate_map_op(map, key_sz, 0, false /* check_value_sz */, flags);
if (err)
return libbpf_err(err);
@@ -10692,7 +10706,7 @@ int bpf_map__lookup_and_delete_elem(const struct bpf_map *map,
{
int err;
- err = validate_map_op(map, key_sz, value_sz, true);
+ err = validate_map_op(map, key_sz, value_sz, true, flags);
if (err)
return libbpf_err(err);
@@ -10704,7 +10718,7 @@ int bpf_map__get_next_key(const struct bpf_map *map,
{
int err;
- err = validate_map_op(map, key_sz, 0, false /* check_value_sz */);
+ err = validate_map_op(map, key_sz, 0, false /* check_value_sz */, 0);
if (err)
return libbpf_err(err);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 2e91148d9b44d..f221dc5c6ba41 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1196,12 +1196,13 @@ LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
* @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
* @param value pointer to memory in which looked up value will be stored
* @param value_sz size in byte of value data memory; it has to match BPF map
- * definition's **value_size**. For per-CPU BPF maps value size has to be
- * a product of BPF map value size and number of possible CPUs in the system
- * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for
- * per-CPU values value size has to be aligned up to closest 8 bytes for
- * alignment reasons, so expected size is: `round_up(value_size, 8)
- * * libbpf_num_possible_cpus()`.
+ * definition's **value_size**. For per-CPU BPF maps, value size can be
+ * `round_up(value_size, 8)` if **BPF_F_CPU** or **BPF_F_ALL_CPUS** is
+ * specified in **flags**, otherwise a product of BPF map value size and number
+ * of possible CPUs in the system (could be fetched with
+ * **libbpf_num_possible_cpus()**). Note else that for per-CPU values value
+ * size has to be aligned up to closest 8 bytes, so expected size is:
+ * `round_up(value_size, 8) * libbpf_num_possible_cpus()`.
* @flags extra flags passed to kernel for this operation
* @return 0, on success; negative error, otherwise
*
@@ -1219,13 +1220,7 @@ LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map,
* @param key pointer to memory containing bytes of the key
* @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
* @param value pointer to memory containing bytes of the value
- * @param value_sz size in byte of value data memory; it has to match BPF map
- * definition's **value_size**. For per-CPU BPF maps value size has to be
- * a product of BPF map value size and number of possible CPUs in the system
- * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for
- * per-CPU values value size has to be aligned up to closest 8 bytes for
- * alignment reasons, so expected size is: `round_up(value_size, 8)
- * * libbpf_num_possible_cpus()`.
+ * @param value_sz refer to **bpf_map__lookup_elem**'s description.'
* @flags extra flags passed to kernel for this operation
* @return 0, on success; negative error, otherwise
*
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH bpf-next v6 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-09-09 14:14 [PATCH bpf-next v6 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (5 preceding siblings ...)
2025-09-09 14:14 ` [PATCH bpf-next v6 6/7] libbpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu maps Leon Hwang
@ 2025-09-09 14:14 ` Leon Hwang
6 siblings, 0 replies; 10+ messages in thread
From: Leon Hwang @ 2025-09-09 14:14 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
Add test coverage for the new BPF_F_CPU and BPF_F_ALL_CPUS flags support
in percpu maps. The following APIs are exercised:
* bpf_map_update_batch()
* bpf_map_lookup_batch()
* bpf_map_update_elem()
* bpf_map__update_elem()
* bpf_map_lookup_elem_flags()
* bpf_map__lookup_elem()
cd tools/testing/selftests/bpf/
./test_progs -t percpu_alloc
253/13 percpu_alloc/cpu_flag_percpu_array:OK
253/14 percpu_alloc/cpu_flag_percpu_hash:OK
253/15 percpu_alloc/cpu_flag_lru_percpu_hash:OK
253/16 percpu_alloc/cpu_flag_percpu_cgroup_storage:OK
253 percpu_alloc:OK
Summary: 1/16 PASSED, 0 SKIPPED, 0 FAILED
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
.../selftests/bpf/prog_tests/percpu_alloc.c | 233 ++++++++++++++++++
.../selftests/bpf/progs/percpu_alloc_array.c | 32 +++
2 files changed, 265 insertions(+)
diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index 343da65864d6d..a130d164d4209 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include "cgroup_helpers.h"
#include "percpu_alloc_array.skel.h"
#include "percpu_alloc_cgrp_local_storage.skel.h"
#include "percpu_alloc_fail.skel.h"
@@ -115,6 +116,230 @@ static void test_failure(void) {
RUN_TESTS(percpu_alloc_fail);
}
+static void test_percpu_map_op_cpu_flag(struct bpf_map *map, void *keys, size_t key_sz,
+ u32 max_entries, bool test_batch)
+{
+ int i, j, cpu, map_fd, value_size, nr_cpus, err;
+ u64 *values = NULL, batch = 0, flags;
+ const u64 value = 0xDEADC0DE;
+ size_t value_sz = sizeof(u64);
+ u32 count;
+ LIBBPF_OPTS(bpf_map_batch_opts, batch_opts);
+
+ nr_cpus = libbpf_num_possible_cpus();
+ if (!ASSERT_GT(nr_cpus, 0, "libbpf_num_possible_cpus"))
+ return;
+
+ value_size = value_sz * nr_cpus;
+ values = calloc(max_entries, value_size);
+ if (!ASSERT_OK_PTR(values, "calloc values"))
+ goto out;
+ memset(values, 0, value_size * max_entries);
+
+ map_fd = bpf_map__fd(map);
+ flags = BPF_F_CPU | BPF_F_ALL_CPUS;
+ err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+ if (!ASSERT_ERR(err, "bpf_map_lookup_elem_flags err"))
+ goto out;
+
+ err = bpf_map_update_elem(map_fd, keys, values, flags);
+ if (!ASSERT_ERR(err, "bpf_map_update_elem err"))
+ goto out;
+
+ flags = (u64)nr_cpus << 32 | BPF_F_CPU;
+ err = bpf_map_update_elem(map_fd, keys, values, flags);
+ if (!ASSERT_EQ(err, -ERANGE, "bpf_map_update_elem -ERANGE"))
+ goto out;
+
+ err = bpf_map__update_elem(map, keys, key_sz, values, value_sz, flags);
+ if (!ASSERT_EQ(err, -ERANGE, "bpf_map__update_elem -ERANGE"))
+ goto out;
+
+ err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+ if (!ASSERT_EQ(err, -ERANGE, "bpf_map_lookup_elem_flags -ERANGE"))
+ goto out;
+
+ err = bpf_map__lookup_elem(map, keys, key_sz, values, value_sz, flags);
+ if (!ASSERT_EQ(err, -ERANGE, "bpf_map__lookup_elem -ERANGE"))
+ goto out;
+
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ /* clear value on all cpus */
+ values[0] = 0;
+ flags = BPF_F_ALL_CPUS;
+ for (i = 0; i < max_entries; i++) {
+ err = bpf_map__update_elem(map, keys + i * key_sz, key_sz, values,
+ value_sz, flags);
+ if (!ASSERT_OK(err, "bpf_map__update_elem all_cpus"))
+ goto out;
+ }
+
+ /* update value on specified cpu */
+ for (i = 0; i < max_entries; i++) {
+ values[0] = value;
+ flags = (u64)cpu << 32 | BPF_F_CPU;
+ err = bpf_map__update_elem(map, keys + i * key_sz, key_sz, values,
+ value_sz, flags);
+ if (!ASSERT_OK(err, "bpf_map__update_elem specified cpu"))
+ goto out;
+
+ /* lookup then check value on CPUs */
+ for (j = 0; j < nr_cpus; j++) {
+ flags = (u64)j << 32 | BPF_F_CPU;
+ err = bpf_map__lookup_elem(map, keys + i * key_sz, key_sz, values,
+ value_sz, flags);
+ if (!ASSERT_OK(err, "bpf_map__lookup_elem specified cpu"))
+ goto out;
+ if (!ASSERT_EQ(values[0], j != cpu ? 0 : value,
+ "bpf_map__lookup_elem value on specified cpu"))
+ goto out;
+ }
+ }
+ }
+
+ if (!test_batch)
+ goto out;
+
+ batch_opts.elem_flags = (u64)nr_cpus << 32 | BPF_F_CPU;
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &batch_opts);
+ if (!ASSERT_EQ(err, -ERANGE, "bpf_map_update_batch -ERANGE"))
+ goto out;
+
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ memset(values, 0, max_entries * value_size);
+
+ /* clear values across all CPUs */
+ batch_opts.elem_flags = BPF_F_ALL_CPUS;
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &batch_opts);
+ if (!ASSERT_OK(err, "bpf_map_update_batch all_cpus"))
+ goto out;
+
+ /* update values on specified CPU */
+ for (i = 0; i < max_entries; i++)
+ values[i] = value;
+
+ batch_opts.elem_flags = (u64)cpu << 32 | BPF_F_CPU;
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &batch_opts);
+ if (!ASSERT_OK(err, "bpf_map_update_batch specified cpu"))
+ goto out;
+
+ /* lookup values on specified CPU */
+ memset(values, 0, max_entries * value_sz);
+ err = bpf_map_lookup_batch(map_fd, NULL, &batch, keys, values, &count, &batch_opts);
+ if (!ASSERT_TRUE(!err || err == -ENOENT, "bpf_map_lookup_batch specified cpu"))
+ goto out;
+
+ for (i = 0; i < max_entries; i++)
+ if (!ASSERT_EQ(values[i], value, "value on specified cpu"))
+ goto out;
+
+ /* lookup values from all CPUs */
+ batch_opts.elem_flags = 0;
+ memset(values, 0, max_entries * value_size);
+ err = bpf_map_lookup_batch(map_fd, NULL, &batch, keys, values, &count, &batch_opts);
+ if (!ASSERT_TRUE(!err || err == -ENOENT, "bpf_map_lookup_batch all_cpus"))
+ goto out;
+
+ for (i = 0; i < max_entries; i++) {
+ for (j = 0; j < nr_cpus; j++) {
+ if (!ASSERT_EQ(values[i*nr_cpus + j], j != cpu ? 0 : value,
+ "value on specified cpu"))
+ goto out;
+ }
+ }
+ }
+
+out:
+ if (values)
+ free(values);
+}
+
+static void test_percpu_map_cpu_flag(enum bpf_map_type map_type)
+{
+ struct percpu_alloc_array *skel;
+ size_t key_sz = sizeof(int);
+ int *keys = NULL, i, err;
+ struct bpf_map *map;
+ u32 max_entries;
+
+ skel = percpu_alloc_array__open();
+ if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open"))
+ return;
+
+ map = skel->maps.percpu;
+ bpf_map__set_type(map, map_type);
+
+ err = percpu_alloc_array__load(skel);
+ if (!ASSERT_OK(err, "test_percpu_alloc__load"))
+ goto out;
+
+ max_entries = bpf_map__max_entries(map);
+ keys = calloc(max_entries, key_sz);
+ if (!ASSERT_OK_PTR(keys, "calloc keys"))
+ goto out;
+
+ for (i = 0; i < max_entries; i++)
+ keys[i] = i;
+
+ test_percpu_map_op_cpu_flag(map, keys, key_sz, max_entries, true);
+out:
+ if (keys)
+ free(keys);
+ percpu_alloc_array__destroy(skel);
+}
+
+static void test_percpu_array_cpu_flag(void)
+{
+ test_percpu_map_cpu_flag(BPF_MAP_TYPE_PERCPU_ARRAY);
+}
+
+static void test_percpu_hash_cpu_flag(void)
+{
+ test_percpu_map_cpu_flag(BPF_MAP_TYPE_PERCPU_HASH);
+}
+
+static void test_lru_percpu_hash_cpu_flag(void)
+{
+ test_percpu_map_cpu_flag(BPF_MAP_TYPE_LRU_PERCPU_HASH);
+}
+
+static void test_percpu_cgroup_storage_cpu_flag(void)
+{
+ struct bpf_cgroup_storage_key key;
+ struct percpu_alloc_array *skel;
+ int cgroup = -1, prog_fd, err;
+ struct bpf_map *map;
+
+ skel = percpu_alloc_array__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open_and_load"))
+ return;
+
+ cgroup = create_and_get_cgroup("/cg_percpu");
+ if (!ASSERT_GE(cgroup, 0, "create_and_get_cgroup"))
+ goto out;
+
+ err = join_cgroup("/cg_percpu");
+ if (!ASSERT_OK(err, "join_cgroup"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs.cgroup_egress);
+ err = bpf_prog_attach(prog_fd, cgroup, BPF_CGROUP_INET_EGRESS, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach"))
+ goto out;
+
+ map = skel->maps.percpu_cgroup_storage;
+ err = bpf_map_get_next_key(bpf_map__fd(map), NULL, &key);
+ if (!ASSERT_OK(err, "bpf_map_get_next_key"))
+ goto out;
+
+ test_percpu_map_op_cpu_flag(map, &key, sizeof(key), 1, false);
+out:
+ bpf_prog_detach2(-1, cgroup, BPF_CGROUP_INET_EGRESS);
+ close(cgroup);
+ cleanup_cgroup_environment();
+ percpu_alloc_array__destroy(skel);
+}
+
void test_percpu_alloc(void)
{
if (test__start_subtest("array"))
@@ -125,4 +350,12 @@ void test_percpu_alloc(void)
test_cgrp_local_storage();
if (test__start_subtest("failure_tests"))
test_failure();
+ if (test__start_subtest("cpu_flag_percpu_array"))
+ test_percpu_array_cpu_flag();
+ if (test__start_subtest("cpu_flag_percpu_hash"))
+ test_percpu_hash_cpu_flag();
+ if (test__start_subtest("cpu_flag_lru_percpu_hash"))
+ test_lru_percpu_hash_cpu_flag();
+ if (test__start_subtest("cpu_flag_percpu_cgroup_storage"))
+ test_percpu_cgroup_storage_cpu_flag();
}
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
index 37c2d2608ec0b..427301909c349 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -187,4 +187,36 @@ int BPF_PROG(test_array_map_10)
return 0;
}
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(max_entries, 2);
+ __type(key, int);
+ __type(value, u64);
+} percpu SEC(".maps");
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test_percpu_array, int x)
+{
+ u64 value = 0xDEADC0DE;
+ int key = 0;
+
+ bpf_map_update_elem(&percpu, &key, &value, BPF_ANY);
+ return 0;
+}
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+ __type(key, struct bpf_cgroup_storage_key);
+ __type(value, u64);
+} percpu_cgroup_storage SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int cgroup_egress(struct __sk_buff *skb)
+{
+ u64 *val = bpf_get_local_storage(&percpu_cgroup_storage, 0);
+
+ __sync_fetch_and_add(val, 1);
+ return 1;
+}
+
char _license[] SEC("license") = "GPL";
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread