bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags

Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags and check them for
following APIs:

* 'map_lookup_elem()'
* 'map_update_elem()'
* 'generic_map_lookup_batch()'
* 'generic_map_update_batch()'

And, get the correct value size for these APIs.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20260107022022.12843-2-leon.hwang@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a63e47d2109c29021e439796f8dcbd2edbaf05dc..108bab1bda9d096c3e22b9bf84b10f1fa0c502a5 100644 (file)
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3915,14 +3915,35 @@ bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image)
 }
 #endif
 
+static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
+{
+       return false;
+}
+
 static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
 {
-       if (flags & ~allowed_flags)
+       u32 cpu;
+
+       if ((u32)flags & ~allowed_flags)
                return -EINVAL;
 
        if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
                return -EINVAL;
 
+       if (!(flags & BPF_F_CPU) && flags >> 32)
+               return -EINVAL;
+
+       if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
+               if (!bpf_map_supports_cpu_flags(map->map_type))
+                       return -EINVAL;
+               if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS))
+                       return -EINVAL;
+
+               cpu = flags >> 32;
+               if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus())
+                       return -ERANGE;
+       }
+
        return 0;
 }
 

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 84ced3ed2d21e6cfa41e2aca7a42e88e6862cea2..2a2ade4be60f2c9febc38b6e427bf32cc4b15efc 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1384,6 +1384,8 @@ 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 6dd2ad2f9e812532f57e5a65badee463c6abd2c7..e8cfe9d67e64fdd13d06e65c3589b0d34129c9be 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -133,12 +133,14 @@ bool bpf_map_write_active(const struct bpf_map *map)
        return atomic64_read(&map->writecnt) != 0;
 }
 
-static u32 bpf_map_value_size(const struct bpf_map *map)
-{
-       if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
-           map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
-           map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
-           map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
+static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
+{
+       if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS))
+               return map->value_size;
+       else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+                map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+                map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+                map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
                return round_up(map->value_size, 8) * num_possible_cpus();
        else if (IS_FD_MAP(map))
                return sizeof(u32);
@@ -1729,7 +1731,7 @@ static int map_lookup_elem(union bpf_attr *attr)
        if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
                return -EPERM;
 
-       err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK);
+       err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK | BPF_F_CPU);
        if (err)
                return err;
 
@@ -1737,7 +1739,7 @@ static int map_lookup_elem(union bpf_attr *attr)
        if (IS_ERR(key))
                return PTR_ERR(key);
 
-       value_size = bpf_map_value_size(map);
+       value_size = bpf_map_value_size(map, attr->flags);
 
        err = -ENOMEM;
        value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN);
@@ -1804,7 +1806,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
                goto err_put;
        }
 
-       value_size = bpf_map_value_size(map);
+       value_size = bpf_map_value_size(map, attr->flags);
        value = kvmemdup_bpfptr(uvalue, value_size);
        if (IS_ERR(value)) {
                err = PTR_ERR(value);
@@ -2000,11 +2002,12 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
        void *key, *value;
        int err = 0;
 
-       err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+       err = bpf_map_check_op_flags(map, attr->batch.elem_flags,
+                                    BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS);
        if (err)
                return err;
 
-       value_size = bpf_map_value_size(map);
+       value_size = bpf_map_value_size(map, attr->batch.elem_flags);
 
        max_count = attr->batch.count;
        if (!max_count)
@@ -2059,11 +2062,11 @@ int generic_map_lookup_batch(struct bpf_map *map,
        u32 value_size, cp, max_count;
        int err;
 
-       err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+       err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK | BPF_F_CPU);
        if (err)
                return err;
 
-       value_size = bpf_map_value_size(map);
+       value_size = bpf_map_value_size(map, attr->batch.elem_flags);
 
        max_count = attr->batch.count;
        if (!max_count)
@@ -2185,7 +2188,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
                goto err_put;
        }
 
-       value_size = bpf_map_value_size(map);
+       value_size = bpf_map_value_size(map, 0);
 
        err = -ENOMEM;
        value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN);

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6b92b0847ec2f28a7bd65d5ffb4f08c2fecab67d..b816bc53d2e159c5f2e154eccf72929fabcd9278 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1384,6 +1384,8 @@ 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 */