From: Yury Norov <ynorov@nvidia.com>
To: Yi Sun <yi.sun@unisoc.com>
Cc: yury.norov@gmail.com, akpm@linux-foundation.org,
mina86@mina86.com, akinobu.mita@gmail.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/2] lib: bitmap: add find_last_bit_range() and _find_last_bit_range()
Date: Tue, 12 May 2026 12:46:26 -0400 [thread overview]
Message-ID: <agNZYli58HtcVjBl@yury> (raw)
In-Reply-To: <20260512040659.2992142-2-yi.sun@unisoc.com>
On Tue, May 12, 2026 at 12:06:58PM +0800, Yi Sun wrote:
> In some scenarios, it's not desirable to keep searching through the
> beginning of the bitmap, but rather to search within a specific part.
> The newly added function can accomplish this quickly.
>
> Signed-off-by: Yi Sun <yi.sun@unisoc.com>
> ---
> include/linux/find.h | 35 +++++++++++++++++++++++++++++++++++
> lib/find_bit.c | 30 ++++++++++++++++++++++++++++++
> 2 files changed, 65 insertions(+)
>
> diff --git a/include/linux/find.h b/include/linux/find.h
> index 6c2be8ca615d..7126b0fffe0f 100644
> --- a/include/linux/find.h
> +++ b/include/linux/find.h
> @@ -33,6 +33,8 @@ unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned
> const unsigned long *addr3, unsigned long size);
> extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
> extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
> +extern unsigned long _find_last_bit_range(const unsigned long *addr, unsigned long size,
> + unsigned long offset);
>
> #ifdef __BIG_ENDIAN
> unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size);
> @@ -413,6 +415,39 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
> }
> #endif
>
> +#ifndef find_last_bit_range
Drop ifdefery. There's no arch implementation, so nothing to protect.
> +/**
> + * find_last_bit_range - find the last set bit in a memory region
find_last_bit_from, please. This is how the existing API named.
> + * @addr: The address to base the search on
> + * @size: The bitmap size in bits
> + * @offset: The bit number to start searching at
> + *
> + * Compared to the find_last_bit(),
> + * find_last_bit_range() has an additional parameter @offset,
> + * so it can search within a specific range of the bitmap,
> + * just like the find_next_bit().
> + *
> + * Returns the bit number of the last set bit, or size.
> + */
> +static __always_inline
> +unsigned long find_last_bit_range(const unsigned long *addr, unsigned long size,
> + unsigned long offset)
> +{
> + if (small_const_nbits(size)) {
> + unsigned long val;
> +
> + if (unlikely(offset >= size))
> + return size;
> +
> + val = *addr & GENMASK(size - 1, offset);
> +
> + return val ? __fls(val) : size;
> + }
> +
> + return _find_last_bit_range(addr, size, offset);
> +}
> +#endif
> +
> /**
> * find_next_and_bit_wrap - find the next set bit in both memory regions
> * @addr1: The first address to base the search on
> diff --git a/lib/find_bit.c b/lib/find_bit.c
> index 5ac52dfce730..bedc85053cea 100644
> --- a/lib/find_bit.c
> +++ b/lib/find_bit.c
> @@ -237,6 +237,36 @@ unsigned long _find_last_bit(const unsigned long *addr, unsigned long size)
> EXPORT_SYMBOL(_find_last_bit);
> #endif
>
> +#ifndef find_last_bit_range
> +unsigned long _find_last_bit_range(const unsigned long *addr, unsigned long size,
> + unsigned long offset)
> +{
> + unsigned long val, idx, start_idx;
> +
> + if (unlikely(offset >= size))
> + return size;
> +
> + val = BITMAP_LAST_WORD_MASK(size);
> + idx = (size - 1) / BITS_PER_LONG;
> + start_idx = offset / BITS_PER_LONG;
> +
> + do {
> + val &= addr[idx];
> +
> + if (idx == start_idx)
> + val &= BITMAP_FIRST_WORD_MASK(offset);
> +
> + if (val)
> + return idx * BITS_PER_LONG + __fls(val);
> +
> + val = ~0UL;
Can you consider handling the last bit out of the loop, so the loop
will have less code?
> + } while (idx-- > start_idx);
> +
> + return size;
> +}
> +EXPORT_SYMBOL(_find_last_bit_range);
> +#endif
> +
> unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr,
> unsigned long size, unsigned long offset)
> {
> --
> 2.34.1
next prev parent reply other threads:[~2026-05-12 16:46 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-12 4:06 [PATCH 0/2] Improve the performance of bitmap_find_next_zero_area_off() Yi Sun
2026-05-12 4:06 ` [PATCH 1/2] lib: bitmap: add find_last_bit_range() and _find_last_bit_range() Yi Sun
2026-05-12 11:31 ` Michał Nazarewicz
2026-05-12 16:46 ` Yury Norov [this message]
2026-05-12 4:06 ` [PATCH 2/2] lib: bitmap: reduce the number of goto again in bitmap_find_next_zero_area_off() Yi Sun
2026-05-12 11:32 ` Michał Nazarewicz
2026-05-12 16:51 ` Yury Norov
2026-05-12 16:34 ` [PATCH 0/2] Improve the performance of bitmap_find_next_zero_area_off() Yury Norov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=agNZYli58HtcVjBl@yury \
--to=ynorov@nvidia.com \
--cc=akinobu.mita@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mina86@mina86.com \
--cc=yi.sun@unisoc.com \
--cc=yury.norov@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox