linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Lobakin <aleksander.lobakin@intel.com>
To: Yury Norov <yury.norov@gmail.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	Rasmus Villemoes <linux@rasmusvillemoes.dk>,
	Alexander Potapenko <glider@google.com>,
	Jakub Kicinski <kuba@kernel.org>,
	Eric Dumazet <edumazet@google.com>,
	David Ahern <dsahern@kernel.org>,
	Przemek Kitszel <przemyslaw.kitszel@intel.com>,
	Simon Horman <simon.horman@corigine.com>,
	netdev@vger.kernel.org, linux-btrfs@vger.kernel.org,
	dm-devel@redhat.com, ntfs3@lists.linux.dev,
	linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 08/13] bitmap: introduce generic optimized bitmap_size()
Date: Mon, 16 Oct 2023 18:52:42 +0200	[thread overview]
Message-ID: <20231016165247.14212-9-aleksander.lobakin@intel.com> (raw)
In-Reply-To: <20231016165247.14212-1-aleksander.lobakin@intel.com>

The number of times yet another open coded
`BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge.
Some generic helper is long overdue.

Add one, bitmap_size(), but with one detail.
BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both
divident and divisor are compile-time constants or when the divisor
is not a pow-of-2. When it is however, the compilers sometimes tend
to generate suboptimal code (GCC 13):

48 83 c0 3f          	add    $0x3f,%rax
48 c1 e8 06          	shr    $0x6,%rax
48 8d 14 c5 00 00 00 00	lea    0x0(,%rax,8),%rdx

%BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does
full division of `nbits + 63` by it and then multiplication by 8.
Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC:

8d 50 3f             	lea    0x3f(%rax),%edx
c1 ea 03             	shr    $0x3,%edx
81 e2 f8 ff ff 1f    	and    $0x1ffffff8,%edx

Now it divides `nbits + 63` by 8 and then masks bits[2:0].
bloat-o-meter:

add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617)

Clang does it better and generates the same code before/after starting
from -O1, except that with the ALIGN() approach it uses %edx and thus
still saves some bytes:

add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520)

Note that we can't expand DIV_ROUND_UP() by adding a check and using
this approach there, as it's used in array declarations where
expressions are not allowed.
Add this helper to tools/ as well.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Acked-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 drivers/md/dm-clone-metadata.c | 5 -----
 drivers/s390/cio/idset.c       | 2 +-
 include/linux/bitmap.h         | 8 +++++---
 include/linux/cpumask.h        | 2 +-
 lib/math/prime_numbers.c       | 2 --
 tools/include/linux/bitmap.h   | 8 +++++---
 6 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c
index c43d55672bce..47c1fa7aad8b 100644
--- a/drivers/md/dm-clone-metadata.c
+++ b/drivers/md/dm-clone-metadata.c
@@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd)
 
 /*---------------------------------------------------------------------------*/
 
-static size_t bitmap_size(unsigned long nr_bits)
-{
-	return BITS_TO_LONGS(nr_bits) * sizeof(long);
-}
-
 static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words,
 			    unsigned long nr_regions)
 {
diff --git a/drivers/s390/cio/idset.c b/drivers/s390/cio/idset.c
index 0a1105a483bf..e5f28370a903 100644
--- a/drivers/s390/cio/idset.c
+++ b/drivers/s390/cio/idset.c
@@ -18,7 +18,7 @@ struct idset {
 
 static inline unsigned long idset_bitmap_size(int num_ssid, int num_id)
 {
-	return BITS_TO_LONGS(num_ssid * num_id) * sizeof(unsigned long);
+	return bitmap_size(size_mul(num_ssid, num_id));
 }
 
 static struct idset *idset_new(int num_ssid, int num_id)
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index c413e2ecb628..2020cb534ed7 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -241,9 +241,11 @@ extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
 
+#define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = 0;
@@ -253,7 +255,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 
 static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = ~0UL;
@@ -264,7 +266,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 			unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = *src;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index f10fb87d49db..dbdbf1451cad 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -821,7 +821,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  */
 static inline unsigned int cpumask_size(void)
 {
-	return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long);
+	return bitmap_size(large_cpumask_bits);
 }
 
 /*
diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c
index d42cebf7407f..d3b64b10da1c 100644
--- a/lib/math/prime_numbers.c
+++ b/lib/math/prime_numbers.c
@@ -6,8 +6,6 @@
 #include <linux/prime_numbers.h>
 #include <linux/slab.h>
 
-#define bitmap_size(nbits) (BITS_TO_LONGS(nbits) * sizeof(unsigned long))
-
 struct primes {
 	struct rcu_head rcu;
 	unsigned long last, sz;
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index f3566ea0f932..81a2299ace15 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -2,6 +2,7 @@
 #ifndef _TOOLS_LINUX_BITMAP_H
 #define _TOOLS_LINUX_BITMAP_H
 
+#include <linux/align.h>
 #include <string.h>
 #include <linux/bitops.h>
 #include <linux/find.h>
@@ -25,13 +26,14 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
 
+#define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = 0UL;
 	else {
-		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-		memset(dst, 0, len);
+		memset(dst, 0, bitmap_size(nbits));
 	}
 }
 
@@ -83,7 +85,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
  */
 static inline unsigned long *bitmap_zalloc(int nbits)
 {
-	return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long));
+	return calloc(1, bitmap_size(nbits));
 }
 
 /*
-- 
2.41.0


  parent reply	other threads:[~2023-10-16 17:21 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-16 16:52 [PATCH v2 00/13] ip_tunnel: convert __be16 tunnel flags to bitmaps Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 01/13] bitops: add missing prototype check Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 02/13] bitops: make BYTES_TO_BITS() treewide-available Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 03/13] bitops: let the compiler optimize {__,}assign_bit() Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 04/13] linkmode: convert linkmode_{test,set,clear,mod}_bit() to macros Alexander Lobakin
2023-10-19  0:27   ` Jakub Kicinski
2023-10-16 16:52 ` [PATCH v2 05/13] s390/cio: rename bitmap_size() -> idset_bitmap_size() Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 06/13] fs/ntfs3: add prefix to bitmap_size() and use BITS_TO_U64() Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 07/13] btrfs: rename bitmap_set_bits() -> btrfs_bitmap_set_bits() Alexander Lobakin
2023-10-16 16:52 ` Alexander Lobakin [this message]
2023-10-16 16:52 ` [PATCH v2 09/13] bitmap: make bitmap_{get,set}_value8() use bitmap_{read,write}() Alexander Lobakin
2023-10-16 17:48   ` Yury Norov
2023-10-16 16:52 ` [PATCH v2 10/13] ip_tunnel: use a separate struct to store tunnel params in the kernel Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 11/13] ip_tunnel: convert __be16 tunnel flags to bitmaps Alexander Lobakin
2023-10-19  0:27   ` Jakub Kicinski
2023-10-20  7:41     ` Alexander Potapenko
2023-10-20 12:30       ` Yury Norov
2023-11-02 11:48         ` Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 12/13] lib/bitmap: add compile-time test for __assign_bit() optimization Alexander Lobakin
2023-10-16 16:52 ` [PATCH v2 13/13] lib/bitmap: add tests for IP tunnel flags conversion helpers Alexander Lobakin
2023-10-16 17:54 ` [PATCH v2 00/13] ip_tunnel: convert __be16 tunnel flags to bitmaps Yury Norov
2023-10-20 12:46   ` 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=20231016165247.14212-9-aleksander.lobakin@intel.com \
    --to=aleksander.lobakin@intel.com \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=dm-devel@redhat.com \
    --cc=dsahern@kernel.org \
    --cc=edumazet@google.com \
    --cc=glider@google.com \
    --cc=kuba@kernel.org \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=netdev@vger.kernel.org \
    --cc=ntfs3@lists.linux.dev \
    --cc=przemyslaw.kitszel@intel.com \
    --cc=simon.horman@corigine.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;
as well as URLs for NNTP newsgroup(s).