All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yury Norov <yury.norov@gmail.com>
To: linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	"David S . Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Rasmus Villemoes <linux@rasmusvillemoes.dk>,
	Yury Norov <yury.norov@gmail.com>
Subject: [PATCH 6/7] lib/find: optimize for_each() macros
Date: Mon, 19 Sep 2022 14:05:58 -0700	[thread overview]
Message-ID: <20220919210559.1509179-7-yury.norov@gmail.com> (raw)
In-Reply-To: <20220919210559.1509179-1-yury.norov@gmail.com>

Moving an iterator of the macros inside conditional part of for-loop
helps to generate a better code. It had been first implemented in commit
7baac8b91f9871ba ("cpumask: make for_each_cpu_mask a bit smaller").

Now that cpumask for-loops are the aliases to bitmap loops, it's worth
to optimize them the same way.

Bloat-o-meter says:
add/remove: 8/12 grow/shrink: 147/592 up/down: 4876/-24416 (-19540)

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/find.h | 56 ++++++++++++++++++++------------------------
 1 file changed, 25 insertions(+), 31 deletions(-)

diff --git a/include/linux/find.h b/include/linux/find.h
index 3b746a183216..0cdfab9734a6 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -458,31 +458,25 @@ unsigned long find_next_bit_le(const void *addr, unsigned
 #endif
 
 #define for_each_set_bit(bit, addr, size) \
-	for ((bit) = find_next_bit((addr), (size), 0);		\
-	     (bit) < (size);					\
-	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+	for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
 
 #define for_each_and_bit(bit, addr1, addr2, size) \
-	for ((bit) = find_next_and_bit((addr1), (addr2), (size), 0);		\
-	     (bit) < (size);							\
-	     (bit) = find_next_and_bit((addr1), (addr2), (size), (bit) + 1))
+	for ((bit) = 0;									\
+	     (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
+	     (bit)++)
 
 /* same as for_each_set_bit() but use bit as value to start with */
 #define for_each_set_bit_from(bit, addr, size) \
-	for ((bit) = find_next_bit((addr), (size), (bit));	\
-	     (bit) < (size);					\
-	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+	for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
 
 #define for_each_clear_bit(bit, addr, size) \
-	for ((bit) = find_next_zero_bit((addr), (size), 0);	\
-	     (bit) < (size);					\
-	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+	for ((bit) = 0;									\
+	     (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size);		\
+	     (bit)++)
 
 /* same as for_each_clear_bit() but use bit as value to start with */
 #define for_each_clear_bit_from(bit, addr, size) \
-	for ((bit) = find_next_zero_bit((addr), (size), (bit));	\
-	     (bit) < (size);					\
-	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+	for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
 
 /**
  * for_each_set_bitrange - iterate over all set bit ranges [b; e)
@@ -492,11 +486,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @size: bitmap size in number of bits
  */
 #define for_each_set_bitrange(b, e, addr, size)			\
-	for ((b) = find_next_bit((addr), (size), 0),		\
-	     (e) = find_next_zero_bit((addr), (size), (b) + 1);	\
+	for ((b) = 0;						\
+	     (b) = find_next_bit((addr), (size), b),		\
+	     (e) = find_next_zero_bit((addr), (size), (b) + 1),	\
 	     (b) < (size);					\
-	     (b) = find_next_bit((addr), (size), (e) + 1),	\
-	     (e) = find_next_zero_bit((addr), (size), (b) + 1))
+	     (b) = (e) + 1)
 
 /**
  * for_each_set_bitrange_from - iterate over all set bit ranges [b; e)
@@ -506,11 +500,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @size: bitmap size in number of bits
  */
 #define for_each_set_bitrange_from(b, e, addr, size)		\
-	for ((b) = find_next_bit((addr), (size), (b)),		\
-	     (e) = find_next_zero_bit((addr), (size), (b) + 1);	\
+	for (;							\
+	     (b) = find_next_bit((addr), (size), (b)),		\
+	     (e) = find_next_zero_bit((addr), (size), (b) + 1),	\
 	     (b) < (size);					\
-	     (b) = find_next_bit((addr), (size), (e) + 1),	\
-	     (e) = find_next_zero_bit((addr), (size), (b) + 1))
+	     (b) = (e) + 1)
 
 /**
  * for_each_clear_bitrange - iterate over all unset bit ranges [b; e)
@@ -520,11 +514,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @size: bitmap size in number of bits
  */
 #define for_each_clear_bitrange(b, e, addr, size)		\
-	for ((b) = find_next_zero_bit((addr), (size), 0),	\
-	     (e) = find_next_bit((addr), (size), (b) + 1);	\
+	for ((b) = 0;						\
+	     (b) = find_next_zero_bit((addr), (size), (b)),	\
+	     (e) = find_next_bit((addr), (size), (b) + 1),	\
 	     (b) < (size);					\
-	     (b) = find_next_zero_bit((addr), (size), (e) + 1),	\
-	     (e) = find_next_bit((addr), (size), (b) + 1))
+	     (b) = (e) + 1)
 
 /**
  * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e)
@@ -534,11 +528,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @size: bitmap size in number of bits
  */
 #define for_each_clear_bitrange_from(b, e, addr, size)		\
-	for ((b) = find_next_zero_bit((addr), (size), (b)),	\
-	     (e) = find_next_bit((addr), (size), (b) + 1);	\
+	for (;							\
+	     (b) = find_next_zero_bit((addr), (size), (b)),	\
+	     (e) = find_next_bit((addr), (size), (b) + 1),	\
 	     (b) < (size);					\
-	     (b) = find_next_zero_bit((addr), (size), (e) + 1),	\
-	     (e) = find_next_bit((addr), (size), (b) + 1))
+	     (b) = (e) + 1)
 
 /**
  * for_each_set_bit_wrap - iterate over all set bits starting from @start, and
-- 
2.34.1


  parent reply	other threads:[~2022-09-19 21:07 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-19 21:05 [PATCH 0/7] cpumask: repair cpumask_check() Yury Norov
2022-09-19 21:05 ` [PATCH 1/7] cpumask: fix checking valid cpu range Yury Norov
2022-09-28 12:18   ` Valentin Schneider
2022-09-28 14:49     ` Yury Norov
2022-09-30 17:04       ` Valentin Schneider
2022-10-01  2:02         ` Yury Norov
2022-09-19 21:05 ` [PATCH 2/7] net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and} Yury Norov
2022-09-26 17:34   ` Jakub Kicinski
2022-09-26 17:47     ` Yury Norov
2022-09-19 21:05 ` [PATCH 3/7] cpumask: switch for_each_cpu{,_not} to use for_each_bit() Yury Norov
2022-09-19 21:05 ` [PATCH 4/7] lib/find_bit: add find_next{,_and}_bit_wrap Yury Norov
2022-09-19 21:05 ` [PATCH 5/7] lib/bitmap: introduce for_each_set_bit_wrap() macro Yury Norov
2022-09-19 21:05 ` Yury Norov [this message]
2022-09-19 21:05 ` [PATCH 7/7] lib/bitmap: add tests for for_each() loops Yury Norov
2022-09-25 15:47 ` [PATCH 0/7] cpumask: repair cpumask_check() Yury Norov
2022-09-26 15:09   ` Jakub Kicinski
2022-09-26 16:27     ` 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=20220919210559.1509179-7-yury.norov@gmail.com \
    --to=yury.norov@gmail.com \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.