[v7,bpf-next,1/2] bpf: Add bits iterator

Commit Message

Yafang Shao May 6, 2024, 3:33 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 | 140 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 140 insertions(+)

Comments

Andrii Nakryiko May 7, 2024, 3:38 a.m. UTC | #1

On Sun, May 5, 2024 at 8:35 PM 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 | 140 +++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 140 insertions(+)
>
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index 2a69a9a36c0f..83b2a02f795f 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2744,6 +2744,143 @@ __bpf_kfunc void bpf_preempt_enable(void)
>         preempt_enable();
>  }
>
> +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

typo: pointer

> + * @nr_bits: The number of bits to be iterated over. Due to the limitation of
> + * memalloc, it can't greater than (4096 * 8).

typo: can't be greater

> + *
> + * 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

s/copy/copies/

> + * 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)
> +{
> +       struct bpf_iter_bits_kern *kit = (void *)it;
> +       u32 words = BITS_TO_LONGS(nr_bits);
> +       u32 size = BITS_TO_BYTES(nr_bits);
> +       u32 left, offset;
> +       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) {
> +               /* For big-endian, we must calculate the offset */
> +               offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - size : 0;

S390 isn't the only big-endian architecture, it's wrong to hard-code just S390

there is __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ check throughout the
kernel to do this detection

> +
> +               err = bpf_probe_read_kernel_common(((char *)&kit->bits_copy) + offset,
> +                                                  size, unsafe_ptr__ign);
> +               if (err)
> +                       return -EFAULT;

I'd rewrite the above to something like (not tested, but should give
the right idea):

long bits = 0;

err = bpf_probe_read_kernel_common(&bits, size, unsafe_ptr__ign);
if (err)
    return -EFAULT;

#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
bits = __swab64(bits);
#endif

/* deal with bit mask of weird size, ensuring upper bits are zero */
bits <<= 64 - nr_bits;
bits >>= 64 - nr_bits;

kit->bits_copy = bits;


This should take care of both big-endianness, and non-multiple-of-8
sized bitmasks (I think, we need tests).

pw-bot: cr


> +
> +               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, words * sizeof(u64), unsafe_ptr__ign);
> +       if (err) {
> +               bpf_mem_free(&bpf_global_ma, kit->bits);
> +               return err;
> +       }
> +
> +       /* long-aligned */
> +       left = size & (sizeof(u64) - 1);
> +       if (!left)
> +               goto out;
> +
> +       offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - left : 0;
> +       err = bpf_probe_read_kernel_common((char *)(kit->bits + words - 1) + offset, left,
> +                                          unsafe_ptr__ign + (words - 1) * sizeof(u64));
> +       if (err) {
> +               bpf_mem_free(&bpf_global_ma, kit->bits);
> +               return err;
> +       }

tbh, I'm not sure what's the desired behavior here is. David (cc'ed),
you were dealing with cpumasks, how is the bit mask specified there?
Is it considered to be an long[] array or byte[] array? And how is
that working on big-endian, because I think it makes a difference?
Please take a look, thanks.

> +
> +out:
> +       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)
> @@ -2826,6 +2963,9 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
>  BTF_ID_FLAGS(func, bpf_wq_start)
>  BTF_ID_FLAGS(func, bpf_preempt_disable)
>  BTF_ID_FLAGS(func, bpf_preempt_enable)
> +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 = {
> --
> 2.30.1 (Apple Git-130)
>

Yafang Shao May 7, 2024, 1:32 p.m. UTC | #2

On Tue, May 7, 2024 at 11:38 AM Andrii Nakryiko
<[e-mail]> wrote:
>
> On Sun, May 5, 2024 at 8:35 PM 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 | 140 +++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 140 insertions(+)
> >
> > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> > index 2a69a9a36c0f..83b2a02f795f 100644
> > --- a/kernel/bpf/helpers.c
> > +++ b/kernel/bpf/helpers.c
> > @@ -2744,6 +2744,143 @@ __bpf_kfunc void bpf_preempt_enable(void)
> >         preempt_enable();
> >  }
> >
> > +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
>
> typo: pointer

Thanks for the fix and the other fixes.

>
> > + * @nr_bits: The number of bits to be iterated over. Due to the limitation of
> > + * memalloc, it can't greater than (4096 * 8).
>
> typo: can't be greater
>
> > + *
> > + * 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
>
> s/copy/copies/
>
> > + * 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)
> > +{
> > +       struct bpf_iter_bits_kern *kit = (void *)it;
> > +       u32 words = BITS_TO_LONGS(nr_bits);
> > +       u32 size = BITS_TO_BYTES(nr_bits);
> > +       u32 left, offset;
> > +       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) {
> > +               /* For big-endian, we must calculate the offset */
> > +               offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - size : 0;
>
> S390 isn't the only big-endian architecture, it's wrong to hard-code just S390
>
> there is __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ check throughout the
> kernel to do this detection

I missed that. will check it.

>
> > +
> > +               err = bpf_probe_read_kernel_common(((char *)&kit->bits_copy) + offset,
> > +                                                  size, unsafe_ptr__ign);
> > +               if (err)
> > +                       return -EFAULT;
>
> I'd rewrite the above to something like (not tested, but should give
> the right idea):
>
> long bits = 0;
>
> err = bpf_probe_read_kernel_common(&bits, size, unsafe_ptr__ign);
> if (err)
>     return -EFAULT;
>
> #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
> bits = __swab64(bits);
> #endif
>
> /* deal with bit mask of weird size, ensuring upper bits are zero */
> bits <<= 64 - nr_bits;
> bits >>= 64 - nr_bits;
>
> kit->bits_copy = bits;
>
>
> This should take care of both big-endianness, and non-multiple-of-8
> sized bitmasks (I think, we need tests).

looks good, will change it.

>
> pw-bot: cr
>
>
> > +
> > +               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, words * sizeof(u64), unsafe_ptr__ign);
> > +       if (err) {
> > +               bpf_mem_free(&bpf_global_ma, kit->bits);
> > +               return err;
> > +       }
> > +
> > +       /* long-aligned */
> > +       left = size & (sizeof(u64) - 1);
> > +       if (!left)
> > +               goto out;
> > +
> > +       offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - left : 0;
> > +       err = bpf_probe_read_kernel_common((char *)(kit->bits + words - 1) + offset, left,
> > +                                          unsafe_ptr__ign + (words - 1) * sizeof(u64));
> > +       if (err) {
> > +               bpf_mem_free(&bpf_global_ma, kit->bits);
> > +               return err;
> > +       }
>
> tbh, I'm not sure what's the desired behavior here is. David (cc'ed),
> you were dealing with cpumasks, how is the bit mask specified there?
> Is it considered to be an long[] array or byte[] array? And how is
> that working on big-endian, because I think it makes a difference?
> Please take a look, thanks.

The function find_next_bit() requires the pointer to be of type
"unsigned long *", hence, we must ensure consistency by converting it
here as well. As cpumask represents a bitmap and is always of type
"unsigned long *", it remains unaffected by endianness considerations.

>
> > +
> > +out:
> > +       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)
> > @@ -2826,6 +2963,9 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
> >  BTF_ID_FLAGS(func, bpf_wq_start)
> >  BTF_ID_FLAGS(func, bpf_preempt_disable)
> >  BTF_ID_FLAGS(func, bpf_preempt_enable)
> > +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 = {
> > --
> > 2.30.1 (Apple Git-130)
> >

Andrii Nakryiko May 7, 2024, 5:09 p.m. UTC | #3

On Tue, May 7, 2024 at 6:32 AM Yafang Shao <[e-mail]> wrote:
>
> On Tue, May 7, 2024 at 11:38 AM Andrii Nakryiko
> <[e-mail]> wrote:
> >
> > On Sun, May 5, 2024 at 8:35 PM 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 | 140 +++++++++++++++++++++++++++++++++++++++++++
> > >  1 file changed, 140 insertions(+)
> > >
> > > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> > > index 2a69a9a36c0f..83b2a02f795f 100644
> > > --- a/kernel/bpf/helpers.c
> > > +++ b/kernel/bpf/helpers.c
> > > @@ -2744,6 +2744,143 @@ __bpf_kfunc void bpf_preempt_enable(void)
> > >         preempt_enable();
> > >  }
> > >
> > > +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
> >
> > typo: pointer
>
> Thanks for the fix and the other fixes.
>
> >
> > > + * @nr_bits: The number of bits to be iterated over. Due to the limitation of
> > > + * memalloc, it can't greater than (4096 * 8).
> >
> > typo: can't be greater
> >
> > > + *
> > > + * 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
> >
> > s/copy/copies/
> >
> > > + * 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)
> > > +{
> > > +       struct bpf_iter_bits_kern *kit = (void *)it;
> > > +       u32 words = BITS_TO_LONGS(nr_bits);
> > > +       u32 size = BITS_TO_BYTES(nr_bits);
> > > +       u32 left, offset;
> > > +       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) {
> > > +               /* For big-endian, we must calculate the offset */
> > > +               offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - size : 0;
> >
> > S390 isn't the only big-endian architecture, it's wrong to hard-code just S390
> >
> > there is __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ check throughout the
> > kernel to do this detection
>
> I missed that. will check it.
>
> >
> > > +
> > > +               err = bpf_probe_read_kernel_common(((char *)&kit->bits_copy) + offset,
> > > +                                                  size, unsafe_ptr__ign);
> > > +               if (err)
> > > +                       return -EFAULT;
> >
> > I'd rewrite the above to something like (not tested, but should give
> > the right idea):
> >
> > long bits = 0;
> >
> > err = bpf_probe_read_kernel_common(&bits, size, unsafe_ptr__ign);
> > if (err)
> >     return -EFAULT;
> >
> > #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
> > bits = __swab64(bits);
> > #endif
> >
> > /* deal with bit mask of weird size, ensuring upper bits are zero */
> > bits <<= 64 - nr_bits;
> > bits >>= 64 - nr_bits;
> >
> > kit->bits_copy = bits;
> >
> >
> > This should take care of both big-endianness, and non-multiple-of-8
> > sized bitmasks (I think, we need tests).
>
> looks good, will change it.
>
> >
> > pw-bot: cr
> >
> >
> > > +
> > > +               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, words * sizeof(u64), unsafe_ptr__ign);
> > > +       if (err) {
> > > +               bpf_mem_free(&bpf_global_ma, kit->bits);
> > > +               return err;
> > > +       }
> > > +
> > > +       /* long-aligned */
> > > +       left = size & (sizeof(u64) - 1);
> > > +       if (!left)
> > > +               goto out;
> > > +
> > > +       offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - left : 0;
> > > +       err = bpf_probe_read_kernel_common((char *)(kit->bits + words - 1) + offset, left,
> > > +                                          unsafe_ptr__ign + (words - 1) * sizeof(u64));
> > > +       if (err) {
> > > +               bpf_mem_free(&bpf_global_ma, kit->bits);
> > > +               return err;
> > > +       }
> >
> > tbh, I'm not sure what's the desired behavior here is. David (cc'ed),
> > you were dealing with cpumasks, how is the bit mask specified there?
> > Is it considered to be an long[] array or byte[] array? And how is
> > that working on big-endian, because I think it makes a difference?
> > Please take a look, thanks.
>
> The function find_next_bit() requires the pointer to be of type
> "unsigned long *", hence, we must ensure consistency by converting it
> here as well. As cpumask represents a bitmap and is always of type
> "unsigned long *", it remains unaffected by endianness considerations.
>

Right, but the question is whether this iterator should make the same
simplifying assumption or not? I think the motivation for this
iterator was the ability to iterate over CPU masks, so I'm asking (and
that's why I cc'ed David) what we should do to make it work well for
CPU masks.

> >
> > > +
> > > +out:
> > > +       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)
> > > @@ -2826,6 +2963,9 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
> > >  BTF_ID_FLAGS(func, bpf_wq_start)
> > >  BTF_ID_FLAGS(func, bpf_preempt_disable)
> > >  BTF_ID_FLAGS(func, bpf_preempt_enable)
> > > +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 = {
> > > --
> > > 2.30.1 (Apple Git-130)
> > >
>
>
>
> --
> Regards
> Yafang

Patch

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 2a69a9a36c0f..83b2a02f795f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2744,6 +2744,143 @@  __bpf_kfunc void bpf_preempt_enable(void)
 	preempt_enable();
 }
 
+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)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	u32 words = BITS_TO_LONGS(nr_bits);
+	u32 size = BITS_TO_BYTES(nr_bits);
+	u32 left, offset;
+	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) {
+		/* For big-endian, we must calculate the offset */
+		offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - size : 0;
+
+		err = bpf_probe_read_kernel_common(((char *)&kit->bits_copy) + offset,
+						   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, words * sizeof(u64), unsafe_ptr__ign);
+	if (err) {
+		bpf_mem_free(&bpf_global_ma, kit->bits);
+		return err;
+	}
+
+	/* long-aligned */
+	left = size & (sizeof(u64) - 1);
+	if (!left)
+		goto out;
+
+	offset = IS_ENABLED(CONFIG_S390) ? sizeof(u64) - left : 0;
+	err = bpf_probe_read_kernel_common((char *)(kit->bits + words - 1) + offset, left,
+					   unsafe_ptr__ign + (words - 1) * sizeof(u64));
+	if (err) {
+		bpf_mem_free(&bpf_global_ma, kit->bits);
+		return err;
+	}
+
+out:
+	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)
@@ -2826,6 +2963,9 @@  BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
 BTF_ID_FLAGS(func, bpf_wq_start)
 BTF_ID_FLAGS(func, bpf_preempt_disable)
 BTF_ID_FLAGS(func, bpf_preempt_enable)
+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 = {