[bpf-next,v4,1/2] bpf: Add bits iterator

Commit Message

Yafang Shao March 27, 2024, 11:58 a.m. UTC

Add three new kfuncs for the bits iterator:
- bpf_iter_bits_new
  Initialize a new bits iterator for a given memory area. Due to the
  limitation of bpf memalloc, the max number of bits that can be iterated
  over is limited to (4096 * 8).
- bpf_iter_bits_next
  Get the next bit in a bpf_iter_bits
- bpf_iter_bits_destroy
  Destroy a bpf_iter_bits

The bits iterator facilitates the iteration of the bits of a memory area,
such as cpumask. It can be used in any context and on any address.

Signed-off-by: Yafang Shao <[e-mail]>
---
 kernel/bpf/helpers.c | 120 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 120 insertions(+)

Comments

Andrii Nakryiko March 27, 2024, 5:41 p.m. UTC | #1

On Wed, Mar 27, 2024 at 5:00 AM Yafang Shao <[e-mail]> wrote:
>
> Add three new kfuncs for the bits iterator:
> - bpf_iter_bits_new
>   Initialize a new bits iterator for a given memory area. Due to the
>   limitation of bpf memalloc, the max number of bits that can be iterated
>   over is limited to (4096 * 8).
> - bpf_iter_bits_next
>   Get the next bit in a bpf_iter_bits
> - bpf_iter_bits_destroy
>   Destroy a bpf_iter_bits
>
> The bits iterator facilitates the iteration of the bits of a memory area,
> such as cpumask. It can be used in any context and on any address.
>
> Signed-off-by: Yafang Shao <[e-mail]>
> ---
>  kernel/bpf/helpers.c | 120 +++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 120 insertions(+)
>

LGTM

Acked-by: Andrii Nakryiko <[e-mail]>

> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index 9234174ccb21..35bd8dd08fb8 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2549,6 +2549,123 @@ __bpf_kfunc void bpf_throw(u64 cookie)
>         WARN(1, "A call to BPF exception callback should never return\n");
>  }
>
> +struct bpf_iter_bits {
> +       __u64 __opaque[2];
> +} __aligned(8);
> +
> +struct bpf_iter_bits_kern {
> +       union {
> +               unsigned long *bits;
> +               unsigned long bits_copy;
> +       };
> +       u32 nr_bits;
> +       int bit;
> +} __aligned(8);
> +
> +/**
> + * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area
> + * @it: The new bpf_iter_bits to be created
> + * @unsafe_ptr__ign: A ponter pointing to a memory area to be iterated over
> + * @nr_bits: The number of bits to be iterated over. Due to the limitation of
> + * memalloc, it can't greater than (4096 * 8).
> + *
> + * This function initializes a new bpf_iter_bits structure for iterating over
> + * a memory area which is specified by the @unsafe_ptr__ign and @nr_bits. It
> + * copy the data of the memory area to the newly created bpf_iter_bits @it for
> + * subsequent iteration operations.
> + *
> + * On success, 0 is returned. On failure, ERR is returned.
> + */
> +__bpf_kfunc int
> +bpf_iter_bits_new(struct bpf_iter_bits *it, const void *unsafe_ptr__ign, u32 nr_bits)
> +{
> +       u32 size = BITS_TO_LONGS(nr_bits) * sizeof(unsigned long);
> +       struct bpf_iter_bits_kern *kit = (void *)it;
> +       int err;
> +
> +       BUILD_BUG_ON(sizeof(struct bpf_iter_bits_kern) != sizeof(struct bpf_iter_bits));
> +       BUILD_BUG_ON(__alignof__(struct bpf_iter_bits_kern) !=
> +                    __alignof__(struct bpf_iter_bits));
> +
> +       if (!unsafe_ptr__ign || !nr_bits) {
> +               kit->bits = NULL;
> +               return -EINVAL;
> +       }
> +
> +       kit->nr_bits = 0;
> +       kit->bits_copy = 0;
> +       /* Optimization for u64/u32 mask */
> +       if (nr_bits <= 64) {
> +               err = bpf_probe_read_kernel_common(&kit->bits_copy, size, unsafe_ptr__ign);
> +               if (err)
> +                       return -EFAULT;
> +
> +               kit->nr_bits = nr_bits;
> +               kit->bit = -1;
> +               return 0;
> +       }
> +
> +       /* Fallback to memalloc */
> +       kit->bits = bpf_mem_alloc(&bpf_global_ma, size);
> +       if (!kit->bits)
> +               return -ENOMEM;
> +
> +       err = bpf_probe_read_kernel_common(kit->bits, size, unsafe_ptr__ign);
> +       if (err) {
> +               bpf_mem_free(&bpf_global_ma, kit->bits);
> +               return err;
> +       }
> +
> +       kit->nr_bits = nr_bits;
> +       kit->bit = -1;
> +       return 0;
> +}
> +
> +/**
> + * bpf_iter_bits_next() - Get the next bit in a bpf_iter_bits
> + * @it: The bpf_iter_bits to be checked
> + *
> + * This function returns a pointer to a number representing the value of the
> + * next bit in the bits.
> + *
> + * If there are no further bit available, it returns NULL.
> + */
> +__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it)
> +{
> +       struct bpf_iter_bits_kern *kit = (void *)it;
> +       u32 nr_bits = kit->nr_bits;
> +       const unsigned long *bits;
> +       int bit;
> +
> +       if (nr_bits == 0)
> +               return NULL;
> +
> +       bits = nr_bits <= 64 ? &kit->bits_copy : kit->bits;
> +       bit = find_next_bit(bits, nr_bits, kit->bit + 1);
> +       if (bit >= nr_bits) {
> +               kit->nr_bits = 0;
> +               return NULL;
> +       }
> +
> +       kit->bit = bit;
> +       return &kit->bit;
> +}
> +
> +/**
> + * bpf_iter_bits_destroy() - Destroy a bpf_iter_bits
> + * @it: The bpf_iter_bits to be destroyed
> + *
> + * Destroy the resource associated with the bpf_iter_bits.
> + */
> +__bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it)
> +{
> +       struct bpf_iter_bits_kern *kit = (void *)it;
> +
> +       if (kit->nr_bits <= 64)
> +               return;
> +       bpf_mem_free(&bpf_global_ma, kit->bits);
> +}
> +
>  __bpf_kfunc_end_defs();
>
>  BTF_KFUNCS_START(generic_btf_ids)
> @@ -2625,6 +2742,9 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null)
>  BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
>  BTF_ID_FLAGS(func, bpf_dynptr_size)
>  BTF_ID_FLAGS(func, bpf_dynptr_clone)
> +BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
> +BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
> +BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
>  BTF_KFUNCS_END(common_btf_ids)
>
>  static const struct btf_kfunc_id_set common_kfunc_set = {
> --
> 2.39.1
>

Patch

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9234174ccb21..35bd8dd08fb8 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2549,6 +2549,123 @@  __bpf_kfunc void bpf_throw(u64 cookie)
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
+struct bpf_iter_bits {
+	__u64 __opaque[2];
+} __aligned(8);
+
+struct bpf_iter_bits_kern {
+	union {
+		unsigned long *bits;
+		unsigned long bits_copy;
+	};
+	u32 nr_bits;
+	int bit;
+} __aligned(8);
+
+/**
+ * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area
+ * @it: The new bpf_iter_bits to be created
+ * @unsafe_ptr__ign: A ponter pointing to a memory area to be iterated over
+ * @nr_bits: The number of bits to be iterated over. Due to the limitation of
+ * memalloc, it can't greater than (4096 * 8).
+ *
+ * This function initializes a new bpf_iter_bits structure for iterating over
+ * a memory area which is specified by the @unsafe_ptr__ign and @nr_bits. It
+ * copy the data of the memory area to the newly created bpf_iter_bits @it for
+ * subsequent iteration operations.
+ *
+ * On success, 0 is returned. On failure, ERR is returned.
+ */
+__bpf_kfunc int
+bpf_iter_bits_new(struct bpf_iter_bits *it, const void *unsafe_ptr__ign, u32 nr_bits)
+{
+	u32 size = BITS_TO_LONGS(nr_bits) * sizeof(unsigned long);
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	int err;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_bits_kern) != sizeof(struct bpf_iter_bits));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_bits_kern) !=
+		     __alignof__(struct bpf_iter_bits));
+
+	if (!unsafe_ptr__ign || !nr_bits) {
+		kit->bits = NULL;
+		return -EINVAL;
+	}
+
+	kit->nr_bits = 0;
+	kit->bits_copy = 0;
+	/* Optimization for u64/u32 mask */
+	if (nr_bits <= 64) {
+		err = bpf_probe_read_kernel_common(&kit->bits_copy, size, unsafe_ptr__ign);
+		if (err)
+			return -EFAULT;
+
+		kit->nr_bits = nr_bits;
+		kit->bit = -1;
+		return 0;
+	}
+
+	/* Fallback to memalloc */
+	kit->bits = bpf_mem_alloc(&bpf_global_ma, size);
+	if (!kit->bits)
+		return -ENOMEM;
+
+	err = bpf_probe_read_kernel_common(kit->bits, size, unsafe_ptr__ign);
+	if (err) {
+		bpf_mem_free(&bpf_global_ma, kit->bits);
+		return err;
+	}
+
+	kit->nr_bits = nr_bits;
+	kit->bit = -1;
+	return 0;
+}
+
+/**
+ * bpf_iter_bits_next() - Get the next bit in a bpf_iter_bits
+ * @it: The bpf_iter_bits to be checked
+ *
+ * This function returns a pointer to a number representing the value of the
+ * next bit in the bits.
+ *
+ * If there are no further bit available, it returns NULL.
+ */
+__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	u32 nr_bits = kit->nr_bits;
+	const unsigned long *bits;
+	int bit;
+
+	if (nr_bits == 0)
+		return NULL;
+
+	bits = nr_bits <= 64 ? &kit->bits_copy : kit->bits;
+	bit = find_next_bit(bits, nr_bits, kit->bit + 1);
+	if (bit >= nr_bits) {
+		kit->nr_bits = 0;
+		return NULL;
+	}
+
+	kit->bit = bit;
+	return &kit->bit;
+}
+
+/**
+ * bpf_iter_bits_destroy() - Destroy a bpf_iter_bits
+ * @it: The bpf_iter_bits to be destroyed
+ *
+ * Destroy the resource associated with the bpf_iter_bits.
+ */
+__bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+
+	if (kit->nr_bits <= 64)
+		return;
+	bpf_mem_free(&bpf_global_ma, kit->bits);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
@@ -2625,6 +2742,9 @@  BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
 BTF_ID_FLAGS(func, bpf_dynptr_size)
 BTF_ID_FLAGS(func, bpf_dynptr_clone)
+BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
+BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {