* [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps
@ 2025-08-27 16:45 Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
` (6 more replies)
0 siblings, 7 replies; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 UTC (permalink / raw)
To: bpf
Cc: ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87, dxu,
deso, leon.hwang, kernel-patches-bot
This patch set introduces the BPF_F_CPU and BPF_F_ALL_CPUS flags for
percpu maps, as the requirement of BPF_F_ALL_CPUS flag for percpu_array
maps was discussed in the thread of
"[PATCH bpf-next v3 0/4] bpf: Introduce global percpu data"[1].
The goal of BPF_F_ALL_CPUS flag is to reduce data caching overhead in light
skeletons by allowing a single value to be reused to update values across all
CPUs. This avoids the M:N problem where M cached values are used to update a
map on N CPUs kernel.
The BPF_F_CPU flag is accompanied by *flags*-embedded cpu info, which
specifies the target CPU for the operation:
* For lookup operations: the flag field alongside cpu info enable querying
a value on the specified CPU.
* For update operations: the flag field alongside cpu info enable
updating value for specified CPU.
Links:
[1] https://lore.kernel.org/bpf/20250526162146.24429-1-leon.hwang@linux.dev/
Changes:
v3 -> v4:
* Address comments from Andrii:
* Remove unnecessary map_type check in bpf_map_value_size().
* Reduce code churn.
* Remove unnecessary do_delete check in
__htab_map_lookup_and_delete_batch().
* Introduce bpf_percpu_copy_to_user() and bpf_percpu_copy_from_user().
* Rename check_map_flags() to bpf_map_check_op_flags() with
extra_flags_mask.
* Add human-readable pr_warn() explanations in validate_map_op().
* Use flags in bpf_map__delete_elem() and
bpf_map__lookup_and_delete_elem().
* Drop "for alignment reasons".
v3 link: https://lore.kernel.org/bpf/20250821160817.70285-1-leon.hwang@linux.dev/
v2 -> v3:
* Address comments from Alexei:
* Use BPF_F_ALL_CPUS instead of BPF_ALL_CPUS magic.
* Introduce these two cpu flags for all percpu maps.
* Address comments from Jiri:
* Reduce some unnecessary u32 cast.
* Refactor more generic map flags check function.
* A code style issue.
v2 link: https://lore.kernel.org/bpf/20250805163017.17015-1-leon.hwang@linux.dev/
v1 -> v2:
* Address comments from Andrii:
* Embed cpu info as high 32 bits of *flags* totally.
* Use ERANGE instead of E2BIG.
* Few format issues.
RFC v2 -> v1:
* Address comments from Andrii:
* Use '&=' and '|='.
* Replace 'reuse_value' with simpler and less duplication code.
* Replace 'ASSERT_FALSE' with two 'ASSERT_OK_PTR's in self test.
RFC v1 -> RFC v2:
* Address comments from Andrii:
* Embed cpu to flags on kernel side.
* Change BPF_ALL_CPU macro to BPF_ALL_CPUS enum.
* Copy/update element within RCU protection.
* Update bpf_map_value_size() including BPF_F_CPU case.
* Use zero as default value to get cpu option.
* Update documents of APIs to be generic.
* Add size_t:0 to opts definitions.
* Update validate_map_op() including BPF_F_CPU case.
* Use LIBBPF_OPTS instead of DECLARE_LIBBPF_OPTS.
Leon Hwang (7):
bpf: Introduce internal bpf_map_check_op_flags helper function
bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_array
maps
bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and
lru_percpu_hash maps
bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for
percpu_cgroup_storage maps
libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps
selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags
include/linux/bpf-cgroup.h | 5 +-
include/linux/bpf.h | 126 +++++++++-
include/uapi/linux/bpf.h | 2 +
kernel/bpf/arraymap.c | 28 +--
kernel/bpf/hashtab.c | 95 +++++---
kernel/bpf/local_storage.c | 42 ++--
kernel/bpf/syscall.c | 64 +++--
tools/include/uapi/linux/bpf.h | 2 +
tools/lib/bpf/bpf.h | 8 +
tools/lib/bpf/libbpf.c | 33 ++-
tools/lib/bpf/libbpf.h | 21 +-
.../selftests/bpf/prog_tests/percpu_alloc.c | 224 ++++++++++++++++++
.../selftests/bpf/progs/percpu_alloc_array.c | 32 +++
13 files changed, 549 insertions(+), 133 deletions(-)
--
2.50.1
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
2025-08-27 23:17 ` Andrii Nakryiko
2025-08-27 16:45 ` [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
` (5 subsequent siblings)
6 siblings, 1 reply; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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>
---
include/linux/bpf.h | 28 ++++++++++++++++++++++++++++
kernel/bpf/syscall.c | 34 +++++++++++-----------------------
2 files changed, 39 insertions(+), 23 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8f6e87f0f3a89..512717d442c09 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3709,4 +3709,32 @@ 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_op_flags(struct bpf_map *map, u64 flags, u64 extra_flags_mask)
+{
+ if (extra_flags_mask && (flags & extra_flags_mask))
+ return -EINVAL;
+
+ if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+ return -EINVAL;
+
+ return 0;
+}
+
+static inline int bpf_map_check_update_flags(struct bpf_map *map, u64 flags)
+{
+ return bpf_map_check_op_flags(map, flags, 0);
+}
+
+#define BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK (~BPF_F_LOCK)
+
+static inline int bpf_map_check_lookup_flags(struct bpf_map *map, u64 flags)
+{
+ return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
+}
+
+static inline int bpf_map_check_batch_flags(struct bpf_map *map, u64 flags)
+{
+ return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
+}
+
#endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0fbfa8532c392..4e04b35944a2b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1669,9 +1669,6 @@ 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 +1676,9 @@ 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_lookup_flags(map, attr->flags);
+ if (err)
+ return err;
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key))
@@ -1744,11 +1741,9 @@ 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_update_flags(map, attr->flags);
+ if (err)
goto err_put;
- }
key = ___bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
@@ -1952,13 +1947,9 @@ 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_batch_flags(map, attr->batch.elem_flags);
+ if (err)
+ return err;
value_size = bpf_map_value_size(map);
@@ -2015,12 +2006,9 @@ 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_batch_flags(map, attr->batch.elem_flags);
+ if (err)
+ return err;
value_size = bpf_map_value_size(map);
--
2.50.1
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
2025-08-27 23:18 ` Andrii Nakryiko
2025-08-27 16:45 ` [PATCH bpf-next v4 3/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_array maps Leon Hwang
` (4 subsequent siblings)
6 siblings, 1 reply; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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 the following internal
helper functions for percpu maps:
* bpf_percpu_copy_to_user: For lookup_elem and lookup_batch user APIs,
copy data to user-provided value pointer.
* bpf_percpu_copy_from_user: For update_elem and update_batch user APIs,
copy data from user-provided value pointer.
* bpf_map_check_cpu_flags: Check BPF_F_CPU, BPF_F_ALL_CPUS and cpu info in
flags.
And, get the correct value size for these user APIs.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
include/linux/bpf.h | 89 ++++++++++++++++++++++++++++++++--
include/uapi/linux/bpf.h | 2 +
kernel/bpf/syscall.c | 24 ++++-----
tools/include/uapi/linux/bpf.h | 2 +
4 files changed, 103 insertions(+), 14 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 512717d442c09..a83364949b64c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -547,6 +547,56 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src
bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
}
+#ifdef CONFIG_BPF_SYSCALL
+static inline void bpf_percpu_copy_to_user(struct bpf_map *map, void __percpu *pptr, void *value,
+ u32 size, u64 flags)
+{
+ int current_cpu = raw_smp_processor_id();
+ int cpu, off = 0;
+
+ if (flags & BPF_F_CPU) {
+ cpu = flags >> 32;
+ copy_map_value_long(map, value, cpu != current_cpu ? per_cpu_ptr(pptr, cpu) :
+ this_cpu_ptr(pptr));
+ check_and_init_map_value(map, value);
+ } else {
+ 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;
+ }
+ }
+}
+
+void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
+
+static inline void bpf_percpu_copy_from_user(struct bpf_map *map, void __percpu *pptr, void *value,
+ u32 size, u64 flags)
+{
+ int current_cpu = raw_smp_processor_id();
+ int cpu, off = 0;
+ void *ptr;
+
+ if (flags & BPF_F_CPU) {
+ cpu = flags >> 32;
+ ptr = cpu == current_cpu ? this_cpu_ptr(pptr) : per_cpu_ptr(pptr, cpu);
+ copy_map_value_long(map, ptr, value);
+ bpf_obj_free_fields(map->record, ptr);
+ } else {
+ for_each_possible_cpu(cpu) {
+ copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
+ /* same user-provided value is used if
+ * BPF_F_ALL_CPUS is specified, otherwise value is
+ * an array of per-cpu values.
+ */
+ if (!(flags & BPF_F_ALL_CPUS))
+ off += size;
+ bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu));
+ }
+ }
+}
+#endif
+
static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src)
{
unsigned long *src_uptr, *dst_uptr;
@@ -2417,7 +2467,6 @@ struct btf_record *btf_record_dup(const struct btf_record *rec);
bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj);
-void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
struct bpf_map *bpf_map_get(u32 ufd);
@@ -3709,14 +3758,25 @@ 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 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 extra_flags_mask)
{
- if (extra_flags_mask && (flags & extra_flags_mask))
+ if (extra_flags_mask && ((u32)flags & extra_flags_mask))
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;
}
@@ -3725,7 +3785,7 @@ static inline int bpf_map_check_update_flags(struct bpf_map *map, u64 flags)
return bpf_map_check_op_flags(map, flags, 0);
}
-#define BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK (~BPF_F_LOCK)
+#define BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK (~(BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS))
static inline int bpf_map_check_lookup_flags(struct bpf_map *map, u64 flags)
{
@@ -3737,4 +3797,27 @@ static inline int bpf_map_check_batch_flags(struct bpf_map *map, u64 flags)
return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
}
+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))
+ /* unknown flags */
+ 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 4e04b35944a2b..dbd21484d7a4d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -131,12 +131,14 @@ 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 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);
@@ -1684,7 +1686,7 @@ 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);
@@ -1751,7 +1753,7 @@ 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);
@@ -1951,7 +1953,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
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)
@@ -2010,7 +2012,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
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)
@@ -2132,7 +2134,7 @@ 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] 18+ messages in thread
* [PATCH bpf-next v4 3/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_array maps
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps Leon Hwang
` (3 subsequent siblings)
6 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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 | 10 ++++++++--
kernel/bpf/arraymap.c | 28 ++++++++++++----------------
kernel/bpf/syscall.c | 2 +-
3 files changed, 21 insertions(+), 19 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a83364949b64c..bc44b72129e59 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2746,7 +2746,8 @@ 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,
@@ -3760,7 +3761,12 @@ struct bpf_prog *bpf_prog_find_from_stack(void);
static inline 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 inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 extra_flags_mask)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 3d080916faf97..42a75fbc588a1 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -295,17 +295,21 @@ 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 flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
- int cpu, off = 0;
u32 size;
+ int err;
if (unlikely(index >= array->map.max_entries))
return -ENOENT;
+ err = bpf_map_check_cpu_flags(flags, false);
+ if (unlikely(err))
+ return err;
+
/* 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
@@ -313,11 +317,7 @@ 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];
- 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;
- }
+ bpf_percpu_copy_to_user(map, pptr, value, size, flags);
rcu_read_unlock();
return 0;
}
@@ -387,12 +387,12 @@ 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;
u32 size;
+ int err;
- 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 +411,7 @@ 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];
- 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;
- }
+ bpf_percpu_copy_from_user(map, pptr, value, size, map_flags);
rcu_read_unlock();
return 0;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dbd21484d7a4d..2ee2cf5a8cedf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -316,7 +316,7 @@ 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] 18+ messages in thread
* [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (2 preceding siblings ...)
2025-08-27 16:45 ` [PATCH bpf-next v4 3/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_array maps Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
2025-08-27 23:18 ` Andrii Nakryiko
2025-08-27 16:45 ` [PATCH bpf-next v4 5/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_cgroup_storage maps Leon Hwang
` (2 subsequent siblings)
6 siblings, 1 reply; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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 | 4 +-
kernel/bpf/hashtab.c | 95 +++++++++++++++++++++++++++-----------------
kernel/bpf/syscall.c | 2 +-
3 files changed, 63 insertions(+), 38 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bc44b72129e59..c120b00448a13 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2745,7 +2745,7 @@ 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,
@@ -3763,6 +3763,8 @@ static inline 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;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 71f9931ac64cd..031a74c1b7fd7 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -937,24 +937,39 @@ 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)
{
+ int cpu = map_flags & BPF_F_CPU ? map_flags >> 32 : 0;
+ int current_cpu = raw_smp_processor_id();
+
if (!onallcpus) {
/* copy true value_size bytes */
- copy_map_value(&htab->map, this_cpu_ptr(pptr), value);
+ copy_map_value(&htab->map, (map_flags & BPF_F_CPU) && cpu != current_cpu ?
+ per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), value);
} else {
u32 size = round_up(htab->map.value_size, 8);
- int off = 0, cpu;
+ int off = 0;
+
+ if (map_flags & BPF_F_CPU) {
+ copy_map_value_long(&htab->map, cpu != current_cpu ?
+ per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), 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 +987,7 @@ 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 +999,7 @@ 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 +1057,7 @@ 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 +1162,7 @@ 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 +1278,15 @@ 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 (percpu) {
+ 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 +1312,7 @@ 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 +1321,7 @@ 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 +1347,9 @@ 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 = bpf_map_check_cpu_flags(map_flags, true);
+ if (unlikely(ret))
+ return ret;
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
!rcu_read_lock_bh_held());
@@ -1366,10 +1387,10 @@ 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 +1719,16 @@ __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_lookup_flags(map, elem_map_flags);
+ 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)
@@ -1802,15 +1830,10 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
memcpy(dst_key, l->key, key_size);
if (is_percpu) {
- int off = 0, cpu;
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;
- }
+ bpf_percpu_copy_to_user(&htab->map, pptr, dst_val, size, elem_map_flags);
} else {
value = htab_elem_value(l, key_size);
if (is_fd_htab(htab)) {
@@ -2365,13 +2388,17 @@ 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)
{
struct htab_elem *l;
void __percpu *pptr;
- int ret = -ENOENT;
- int cpu, off = 0;
u32 size;
+ int ret;
+
+ ret = bpf_map_check_cpu_flags(map_flags, false);
+ if (unlikely(ret))
+ return ret;
+ ret = -ENOENT;
/* per_cpu areas are zero-filled and bpf programs can only
* access 'value_size' of them, so copying rounded areas
@@ -2386,11 +2413,7 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
* eviction heuristics when user space does a map walk.
*/
pptr = htab_elem_get_ptr(l, map->key_size);
- 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;
- }
+ bpf_percpu_copy_to_user(map, pptr, value, size, map_flags);
ret = 0;
out:
rcu_read_unlock();
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2ee2cf5a8cedf..91ab9bdd1da38 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -314,7 +314,7 @@ 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] 18+ messages in thread
* [PATCH bpf-next v4 5/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_cgroup_storage maps
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (3 preceding siblings ...)
2025-08-27 16:45 ` [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
6 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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 | 5 +++--
include/linux/bpf.h | 1 +
kernel/bpf/local_storage.c | 42 ++++++++++++++++++++------------------
kernel/bpf/syscall.c | 2 +-
4 files changed, 27 insertions(+), 23 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index aedf573bdb426..1cb28660aa866 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -172,7 +172,8 @@ 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 +468,7 @@ 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/include/linux/bpf.h b/include/linux/bpf.h
index c120b00448a13..2d67af3e7f870 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3765,6 +3765,7 @@ static inline 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;
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c93a756e035c0..31b146cf8f48e 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;
u32 size;
+ int err;
+
+ 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 +203,10 @@ 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);
- for_each_possible_cpu(cpu) {
- bpf_long_memcpy(value + off,
- per_cpu_ptr(storage->percpu_buf, cpu), size);
- off += size;
- }
+ bpf_percpu_copy_to_user(_map, storage->percpu_buf, value, size, map_flags);
+unlock:
rcu_read_unlock();
- return 0;
+ return err;
}
int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
@@ -213,17 +214,21 @@ 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;
u32 size;
+ int err;
- 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 +238,10 @@ 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);
- for_each_possible_cpu(cpu) {
- bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
- value + off, size);
- off += size;
- }
+ bpf_percpu_copy_from_user(_map, storage->percpu_buf, value, size, map_flags);
+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 91ab9bdd1da38..0c88d7f6f1491 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -318,7 +318,7 @@ 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] 18+ messages in thread
* [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (4 preceding siblings ...)
2025-08-27 16:45 ` [PATCH bpf-next v4 5/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_cgroup_storage maps Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
2025-08-27 23:18 ` Andrii Nakryiko
2025-08-27 16:45 ` [PATCH bpf-next v4 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
6 siblings, 1 reply; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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 | 33 +++++++++++++++++++++++++++------
tools/lib/bpf/libbpf.h | 21 ++++++++-------------
3 files changed, 43 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..e6a6341da861a 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;
@@ -10629,6 +10629,27 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: {
int num_cpu = libbpf_num_possible_cpus();
size_t elem_sz = roundup(map->def.value_size, 8);
+ __u32 cpu;
+
+ 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;
+ }
+ cpu = flags >> 32;
+ if (cpu >= num_cpu) {
+ pr_warn("map '%s': cpu %u in flags cannot be GE num cpus %d\n",
+ map->name, cpu, num_cpu);
+ return -ERANGE;
+ }
+ 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",
@@ -10654,7 +10675,7 @@ 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 +10688,7 @@ 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 +10700,7 @@ 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 +10713,7 @@ 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 +10725,7 @@ 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] 18+ messages in thread
* [PATCH bpf-next v4 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
` (5 preceding siblings ...)
2025-08-27 16:45 ` [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
@ 2025-08-27 16:45 ` Leon Hwang
6 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-08-27 16:45 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 | 224 ++++++++++++++++++
.../selftests/bpf/progs/percpu_alloc_array.c | 32 +++
2 files changed, 256 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..98b6e8cc7ae60 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 +116,221 @@ 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 = (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_opts -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_opts -ERANGE"))
+ goto out;
+
+ err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+ if (!ASSERT_EQ(err, -ERANGE, "bpf_map_lookup_elem_opts -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_opts -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"))
+ 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 +341,12 @@ 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] 18+ messages in thread
* Re: [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function
2025-08-27 16:45 ` [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
@ 2025-08-27 23:17 ` Andrii Nakryiko
2025-09-03 14:39 ` Leon Hwang
0 siblings, 1 reply; 18+ messages in thread
From: Andrii Nakryiko @ 2025-08-27 23:17 UTC (permalink / raw)
To: Leon Hwang
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> 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>
> ---
> include/linux/bpf.h | 28 ++++++++++++++++++++++++++++
> kernel/bpf/syscall.c | 34 +++++++++++-----------------------
> 2 files changed, 39 insertions(+), 23 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 8f6e87f0f3a89..512717d442c09 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -3709,4 +3709,32 @@ 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_op_flags(struct bpf_map *map, u64 flags, u64 extra_flags_mask)
> +{
> + if (extra_flags_mask && (flags & extra_flags_mask))
doh, Leon... when extra_flags_mask == 0, `flags & extra_flags_mask` is
always false, so just:
if (flags & extra_flags_mask)
return -EINVAL;
But it feels more natural to reverse the meaning of this and treat it
as extra *allowed flags*. So zero would mean no extra flags should be
there (most strict case) and ~0 would mean "we don't care or will
check later". And so in the code you'd have
if (flags & ~extra_flags) /* check for any unsupported flags */
return -EINVAL;
But I need someone else to do a reality check on me here at this point.
> + return -EINVAL;
> +
> + if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
> + return -EINVAL;
> +
> + return 0;
> +}
> +
> +static inline int bpf_map_check_update_flags(struct bpf_map *map, u64 flags)
> +{
> + return bpf_map_check_op_flags(map, flags, 0);
> +}
> +
> +#define BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK (~BPF_F_LOCK)
> +
> +static inline int bpf_map_check_lookup_flags(struct bpf_map *map, u64 flags)
> +{
> + return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
> +}
> +
> +static inline int bpf_map_check_batch_flags(struct bpf_map *map, u64 flags)
> +{
> + return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
> +}
> +
> #endif /* _LINUX_BPF_H */
[...]
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-08-27 16:45 ` [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
@ 2025-08-27 23:18 ` Andrii Nakryiko
2025-09-03 14:26 ` Leon Hwang
0 siblings, 1 reply; 18+ messages in thread
From: Andrii Nakryiko @ 2025-08-27 23:18 UTC (permalink / raw)
To: Leon Hwang
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags and the following internal
> helper functions for percpu maps:
>
> * bpf_percpu_copy_to_user: For lookup_elem and lookup_batch user APIs,
> copy data to user-provided value pointer.
> * bpf_percpu_copy_from_user: For update_elem and update_batch user APIs,
> copy data from user-provided value pointer.
> * bpf_map_check_cpu_flags: Check BPF_F_CPU, BPF_F_ALL_CPUS and cpu info in
> flags.
>
> And, get the correct value size for these user APIs.
>
> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
> ---
> include/linux/bpf.h | 89 ++++++++++++++++++++++++++++++++--
> include/uapi/linux/bpf.h | 2 +
> kernel/bpf/syscall.c | 24 ++++-----
> tools/include/uapi/linux/bpf.h | 2 +
> 4 files changed, 103 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 512717d442c09..a83364949b64c 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -547,6 +547,56 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src
> bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
> }
>
> +#ifdef CONFIG_BPF_SYSCALL
> +static inline void bpf_percpu_copy_to_user(struct bpf_map *map, void __percpu *pptr, void *value,
> + u32 size, u64 flags)
> +{
> + int current_cpu = raw_smp_processor_id();
> + int cpu, off = 0;
> +
> + if (flags & BPF_F_CPU) {
> + cpu = flags >> 32;
> + copy_map_value_long(map, value, cpu != current_cpu ? per_cpu_ptr(pptr, cpu) :
> + this_cpu_ptr(pptr));
> + check_and_init_map_value(map, value);
I'm not sure it's the question to you, but why would we
"check_and_init_map_value" when copying data to user space?... this is
so confusing...
> + } else {
> + 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;
> + }
> + }
> +}
> +
> +void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
> +
> +static inline void bpf_percpu_copy_from_user(struct bpf_map *map, void __percpu *pptr, void *value,
> + u32 size, u64 flags)
> +{
> + int current_cpu = raw_smp_processor_id();
> + int cpu, off = 0;
> + void *ptr;
> +
> + if (flags & BPF_F_CPU) {
> + cpu = flags >> 32;
> + ptr = cpu == current_cpu ? this_cpu_ptr(pptr) : per_cpu_ptr(pptr, cpu);
> + copy_map_value_long(map, ptr, value);
> + bpf_obj_free_fields(map->record, ptr);
> + } else {
> + for_each_possible_cpu(cpu) {
> + copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
> + /* same user-provided value is used if
> + * BPF_F_ALL_CPUS is specified, otherwise value is
> + * an array of per-cpu values.
> + */
> + if (!(flags & BPF_F_ALL_CPUS))
> + off += size;
> + bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu));
> + }
> + }
> +}
> +#endif
hm... these helpers are just here with no way to validate that they
generalize existing logic correctly... Do a separate patch where you
introduce this helper before adding per-CPU flags *and* make use of
them in existing code? Then we can check that you didn't introduce any
subtle differences? Then in this patch you can adjust helpers to
handle BPF_F_CPU and BPF_F_ALL_CPUS?
pw-bot: cr
[...]
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps
2025-08-27 16:45 ` [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps Leon Hwang
@ 2025-08-27 23:18 ` Andrii Nakryiko
2025-09-03 14:30 ` Leon Hwang
0 siblings, 1 reply; 18+ messages in thread
From: Andrii Nakryiko @ 2025-08-27 23:18 UTC (permalink / raw)
To: Leon Hwang
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> 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 | 4 +-
> kernel/bpf/hashtab.c | 95 +++++++++++++++++++++++++++-----------------
> kernel/bpf/syscall.c | 2 +-
> 3 files changed, 63 insertions(+), 38 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index bc44b72129e59..c120b00448a13 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -2745,7 +2745,7 @@ 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,
> @@ -3763,6 +3763,8 @@ static inline 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;
> diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
> index 71f9931ac64cd..031a74c1b7fd7 100644
> --- a/kernel/bpf/hashtab.c
> +++ b/kernel/bpf/hashtab.c
> @@ -937,24 +937,39 @@ 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)
> {
> + int cpu = map_flags & BPF_F_CPU ? map_flags >> 32 : 0;
> + int current_cpu = raw_smp_processor_id();
> +
> if (!onallcpus) {
> /* copy true value_size bytes */
> - copy_map_value(&htab->map, this_cpu_ptr(pptr), value);
> + copy_map_value(&htab->map, (map_flags & BPF_F_CPU) && cpu != current_cpu ?
> + per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), value);
FWIW, I still feel like this_cpu_ptr() micro-optimization is
unnecessary and is just a distraction. This code is called when
user-space updates/looks up per-CPU value, it's not a hot path by any
means where this_cpu_ptr() vs per_cpu_ptr() makes any measurable
difference
> } else {
> u32 size = round_up(htab->map.value_size, 8);
> - int off = 0, cpu;
> + int off = 0;
> +
> + if (map_flags & BPF_F_CPU) {
> + copy_map_value_long(&htab->map, cpu != current_cpu ?
> + per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), 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;
> }
> }
this couldn't have been replaced by bpf_percpu_copy_to_user?.. (and I
just want to emphasize how hard did you make it to review all this by
putting those bpf_percpu_copy_to_user and bpf_percpu_copy_from_user on
its own in patch #2, instead of having a proper refactoring patch...)
[...]
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps
2025-08-27 16:45 ` [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
@ 2025-08-27 23:18 ` Andrii Nakryiko
2025-09-03 14:33 ` Leon Hwang
0 siblings, 1 reply; 18+ messages in thread
From: Andrii Nakryiko @ 2025-08-27 23:18 UTC (permalink / raw)
To: Leon Hwang
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Wed, Aug 27, 2025 at 9:46 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> 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 | 33 +++++++++++++++++++++++++++------
> tools/lib/bpf/libbpf.h | 21 ++++++++-------------
> 3 files changed, 43 insertions(+), 19 deletions(-)
>
[...]
> @@ -10629,6 +10629,27 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
> case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: {
> int num_cpu = libbpf_num_possible_cpus();
> size_t elem_sz = roundup(map->def.value_size, 8);
> + __u32 cpu;
> +
> + 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;
> + }
> + cpu = flags >> 32;
> + if (cpu >= num_cpu) {
only check this if BPF_F_CPU is set
> + pr_warn("map '%s': cpu %u in flags cannot be GE num cpus %d\n",
"GE"? maybe "CPU #%d is not valid"... (or don't even check cpu value
itself, it's unlikely user using BPF_F_CPU will get it so wrong)
[...]
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-08-27 23:18 ` Andrii Nakryiko
@ 2025-09-03 14:26 ` Leon Hwang
2025-09-03 23:53 ` Andrii Nakryiko
0 siblings, 1 reply; 18+ messages in thread
From: Leon Hwang @ 2025-09-03 14:26 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Thu Aug 28, 2025 at 7:18 AM +08, Andrii Nakryiko wrote:
> On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>
[...]
>>
>> +#ifdef CONFIG_BPF_SYSCALL
>> +static inline void bpf_percpu_copy_to_user(struct bpf_map *map, void __percpu *pptr, void *value,
>> + u32 size, u64 flags)
>> +{
>> + int current_cpu = raw_smp_processor_id();
>> + int cpu, off = 0;
>> +
>> + if (flags & BPF_F_CPU) {
>> + cpu = flags >> 32;
>> + copy_map_value_long(map, value, cpu != current_cpu ? per_cpu_ptr(pptr, cpu) :
>> + this_cpu_ptr(pptr));
>> + check_and_init_map_value(map, value);
>
> I'm not sure it's the question to you, but why would we
> "check_and_init_map_value" when copying data to user space?... this is
> so confusing...
>
After reading its code, I think it's to hide some kernel details from
user space, e.g. refcount, list nodes, rb nodes.
>> + } else {
>> + 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;
>> + }
>> + }
>> +}
>> +
>> +void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
>> +
>> +static inline void bpf_percpu_copy_from_user(struct bpf_map *map, void __percpu *pptr, void *value,
>> + u32 size, u64 flags)
>> +{
[...]
>> +}
>> +#endif
>
> hm... these helpers are just here with no way to validate that they
> generalize existing logic correctly... Do a separate patch where you
> introduce this helper before adding per-CPU flags *and* make use of
> them in existing code? Then we can check that you didn't introduce any
> subtle differences? Then in this patch you can adjust helpers to
> handle BPF_F_CPU and BPF_F_ALL_CPUS?
>
Get it.
I'll send a separate patch later.
Thanks,
Leon
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps
2025-08-27 23:18 ` Andrii Nakryiko
@ 2025-09-03 14:30 ` Leon Hwang
0 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-09-03 14:30 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Thu Aug 28, 2025 at 7:18 AM +08, Andrii Nakryiko wrote:
> On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>
[...]
>> diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
>> index 71f9931ac64cd..031a74c1b7fd7 100644
>> --- a/kernel/bpf/hashtab.c
>> +++ b/kernel/bpf/hashtab.c
>> @@ -937,24 +937,39 @@ 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)
>> {
>> + int cpu = map_flags & BPF_F_CPU ? map_flags >> 32 : 0;
>> + int current_cpu = raw_smp_processor_id();
>> +
>> if (!onallcpus) {
>> /* copy true value_size bytes */
>> - copy_map_value(&htab->map, this_cpu_ptr(pptr), value);
>> + copy_map_value(&htab->map, (map_flags & BPF_F_CPU) && cpu != current_cpu ?
>> + per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), value);
>
> FWIW, I still feel like this_cpu_ptr() micro-optimization is
> unnecessary and is just a distraction. This code is called when
> user-space updates/looks up per-CPU value, it's not a hot path by any
> means where this_cpu_ptr() vs per_cpu_ptr() makes any measurable
> difference
>
OK.
I'll remove it in next revision.
>> } else {
>> u32 size = round_up(htab->map.value_size, 8);
>> - int off = 0, cpu;
>> + int off = 0;
>> +
>> + if (map_flags & BPF_F_CPU) {
>> + copy_map_value_long(&htab->map, cpu != current_cpu ?
>> + per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), 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;
>> }
>> }
>
> this couldn't have been replaced by bpf_percpu_copy_to_user?.. (and I
> just want to emphasize how hard did you make it to review all this by
> putting those bpf_percpu_copy_to_user and bpf_percpu_copy_from_user on
> its own in patch #2, instead of having a proper refactoring patch...)
>
Sorry about this.
I will use 'bpf_percpu_copy_from_user()' here in next revision.
Thanks,
Leon
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps
2025-08-27 23:18 ` Andrii Nakryiko
@ 2025-09-03 14:33 ` Leon Hwang
0 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-09-03 14:33 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Thu Aug 28, 2025 at 7:18 AM +08, Andrii Nakryiko wrote:
> On Wed, Aug 27, 2025 at 9:46 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>
>> 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 | 33 +++++++++++++++++++++++++++------
>> tools/lib/bpf/libbpf.h | 21 ++++++++-------------
>> 3 files changed, 43 insertions(+), 19 deletions(-)
>>
>
> [...]
>
>> @@ -10629,6 +10629,27 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
>> case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: {
>> int num_cpu = libbpf_num_possible_cpus();
>> size_t elem_sz = roundup(map->def.value_size, 8);
>> + __u32 cpu;
>> +
>> + 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;
>> + }
>> + cpu = flags >> 32;
>> + if (cpu >= num_cpu) {
>
> only check this if BPF_F_CPU is set
>
>> + pr_warn("map '%s': cpu %u in flags cannot be GE num cpus %d\n",
>
> "GE"? maybe "CPU #%d is not valid"... (or don't even check cpu value
> itself, it's unlikely user using BPF_F_CPU will get it so wrong)
>
Let's remove it instead.
Thanks,
Leon
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function
2025-08-27 23:17 ` Andrii Nakryiko
@ 2025-09-03 14:39 ` Leon Hwang
0 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-09-03 14:39 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Thu Aug 28, 2025 at 7:17 AM +08, Andrii Nakryiko wrote:
> On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>
>> 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>
>> ---
>> include/linux/bpf.h | 28 ++++++++++++++++++++++++++++
>> kernel/bpf/syscall.c | 34 +++++++++++-----------------------
>> 2 files changed, 39 insertions(+), 23 deletions(-)
>>
>> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>> index 8f6e87f0f3a89..512717d442c09 100644
>> --- a/include/linux/bpf.h
>> +++ b/include/linux/bpf.h
>> @@ -3709,4 +3709,32 @@ 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_op_flags(struct bpf_map *map, u64 flags, u64 extra_flags_mask)
>> +{
>> + if (extra_flags_mask && (flags & extra_flags_mask))
>
> doh, Leon... when extra_flags_mask == 0, `flags & extra_flags_mask` is
> always false, so just:
>
> if (flags & extra_flags_mask)
> return -EINVAL;
>
> But it feels more natural to reverse the meaning of this and treat it
> as extra *allowed flags*. So zero would mean no extra flags should be
> there (most strict case) and ~0 would mean "we don't care or will
> check later". And so in the code you'd have
>
> if (flags & ~extra_flags) /* check for any unsupported flags */
> return -EINVAL;
>
> But I need someone else to do a reality check on me here at this point.
>
It seems clearer to handle this as additional *allowed flags*. That would
make it more understandable.
Thanks,
Leon
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-09-03 14:26 ` Leon Hwang
@ 2025-09-03 23:53 ` Andrii Nakryiko
2025-09-04 2:36 ` Leon Hwang
0 siblings, 1 reply; 18+ messages in thread
From: Andrii Nakryiko @ 2025-09-03 23:53 UTC (permalink / raw)
To: Leon Hwang
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On Wed, Sep 3, 2025 at 7:27 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> On Thu Aug 28, 2025 at 7:18 AM +08, Andrii Nakryiko wrote:
> > On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
> >>
>
> [...]
>
> >>
> >> +#ifdef CONFIG_BPF_SYSCALL
> >> +static inline void bpf_percpu_copy_to_user(struct bpf_map *map, void __percpu *pptr, void *value,
> >> + u32 size, u64 flags)
> >> +{
> >> + int current_cpu = raw_smp_processor_id();
> >> + int cpu, off = 0;
> >> +
> >> + if (flags & BPF_F_CPU) {
> >> + cpu = flags >> 32;
> >> + copy_map_value_long(map, value, cpu != current_cpu ? per_cpu_ptr(pptr, cpu) :
> >> + this_cpu_ptr(pptr));
> >> + check_and_init_map_value(map, value);
> >
> > I'm not sure it's the question to you, but why would we
> > "check_and_init_map_value" when copying data to user space?... this is
> > so confusing...
> >
>
> After reading its code, I think it's to hide some kernel details from
> user space, e.g. refcount, list nodes, rb nodes.
we don't copy those details, so there is nothing to hide, so no, I
think it's just weird that we do this, unless there is some
non-obvious reasoning behind this
>
> >> + } else {
> >> + 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;
> >> + }
> >> + }
> >> +}
> >> +
> >> +void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
> >> +
> >> +static inline void bpf_percpu_copy_from_user(struct bpf_map *map, void __percpu *pptr, void *value,
> >> + u32 size, u64 flags)
> >> +{
>
> [...]
>
> >> +}
> >> +#endif
> >
> > hm... these helpers are just here with no way to validate that they
> > generalize existing logic correctly... Do a separate patch where you
> > introduce this helper before adding per-CPU flags *and* make use of
> > them in existing code? Then we can check that you didn't introduce any
> > subtle differences? Then in this patch you can adjust helpers to
> > handle BPF_F_CPU and BPF_F_ALL_CPUS?
> >
>
> Get it.
>
> I'll send a separate patch later.
separate patch as part of the patch set to show the value of this refactoring :)
>
> Thanks,
> Leon
^ permalink raw reply [flat|nested] 18+ messages in thread
* Re: [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
2025-09-03 23:53 ` Andrii Nakryiko
@ 2025-09-04 2:36 ` Leon Hwang
0 siblings, 0 replies; 18+ messages in thread
From: Leon Hwang @ 2025-09-04 2:36 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, ast, andrii, daniel, jolsa, yonghong.song, song, eddyz87,
dxu, deso, kernel-patches-bot
On 4/9/25 07:53, Andrii Nakryiko wrote:
> On Wed, Sep 3, 2025 at 7:27 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>
>> On Thu Aug 28, 2025 at 7:18 AM +08, Andrii Nakryiko wrote:
>>> On Wed, Aug 27, 2025 at 9:45 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>>>
>>
>> [...]
>>
>>>>
>>>> +#ifdef CONFIG_BPF_SYSCALL
>>>> +static inline void bpf_percpu_copy_to_user(struct bpf_map *map, void __percpu *pptr, void *value,
>>>> + u32 size, u64 flags)
>>>> +{
>>>> + int current_cpu = raw_smp_processor_id();
>>>> + int cpu, off = 0;
>>>> +
>>>> + if (flags & BPF_F_CPU) {
>>>> + cpu = flags >> 32;
>>>> + copy_map_value_long(map, value, cpu != current_cpu ? per_cpu_ptr(pptr, cpu) :
>>>> + this_cpu_ptr(pptr));
>>>> + check_and_init_map_value(map, value);
>>>
>>> I'm not sure it's the question to you, but why would we
>>> "check_and_init_map_value" when copying data to user space?... this is
>>> so confusing...
>>>
>>
>> After reading its code, I think it's to hide some kernel details from
>> user space, e.g. refcount, list nodes, rb nodes.
>
> we don't copy those details, so there is nothing to hide, so no, I
> think it's just weird that we do this, unless there is some
> non-obvious reasoning behind this
>
Ack.
check_and_init_map_value() is useless here.
>>
>>>> + } else {
>>>> + 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;
>>>> + }
>>>> + }
>>>> +}
>>>> +
>>>> +void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
>>>> +
>>>> +static inline void bpf_percpu_copy_from_user(struct bpf_map *map, void __percpu *pptr, void *value,
>>>> + u32 size, u64 flags)
>>>> +{
>>
>> [...]
>>
>>>> +}
>>>> +#endif
>>>
>>> hm... these helpers are just here with no way to validate that they
>>> generalize existing logic correctly... Do a separate patch where you
>>> introduce this helper before adding per-CPU flags *and* make use of
>>> them in existing code? Then we can check that you didn't introduce any
>>> subtle differences? Then in this patch you can adjust helpers to
>>> handle BPF_F_CPU and BPF_F_ALL_CPUS?
>>>
>>
>> Get it.
>>
>> I'll send a separate patch later.
>
> separate patch as part of the patch set to show the value of this refactoring :)
>
Sorry for my misunderstanding. :/
Thanks,
Leon
^ permalink raw reply [flat|nested] 18+ messages in thread
end of thread, other threads:[~2025-09-04 2:36 UTC | newest]
Thread overview: 18+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-08-27 16:45 [PATCH bpf-next v4 0/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 1/7] bpf: Introduce internal bpf_map_check_op_flags helper function Leon Hwang
2025-08-27 23:17 ` Andrii Nakryiko
2025-09-03 14:39 ` Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 2/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
2025-08-27 23:18 ` Andrii Nakryiko
2025-09-03 14:26 ` Leon Hwang
2025-09-03 23:53 ` Andrii Nakryiko
2025-09-04 2:36 ` Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 3/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_array maps Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 4/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps Leon Hwang
2025-08-27 23:18 ` Andrii Nakryiko
2025-09-03 14:30 ` Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 5/7] bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_cgroup_storage maps Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 6/7] libbpf: Support BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps Leon Hwang
2025-08-27 23:18 ` Andrii Nakryiko
2025-09-03 14:33 ` Leon Hwang
2025-08-27 16:45 ` [PATCH bpf-next v4 7/7] selftests/bpf: Add cases to test BPF_F_CPU and BPF_F_ALL_CPUS flags Leon Hwang
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.