linux-kernel - [RFC] bitops/non-atomic: make @nr unsigned to avoid any DIV

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu,  5 Aug 2021 12:14:08 -0700
From:   Vineet Gupta <Vineet.Gupta1@...opsys.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Will Deacon <will@...nel.org>, Arnd Bergmann <arnd@...db.de>,
        Mark Rutland <mark.rutland@....com>
Cc:     linux-kernel@...r.kernel.org, linux-arch@...r.kernel.org,
        linux-snps-arc@...ts.infradead.org,
        Vineet Gupta <Vineet.Gupta1@...opsys.com>
Subject: [RFC] bitops/non-atomic: make @nr unsigned to avoid any DIV

signed math causes generation of costlier instructions such as DIV when
they could be done by barrerl shifter.

Worse part is this is not caught by things like bloat-o-meter since
instruction length / symbols are typically same size.

e.g.

stock (signed math)
__________________

919b4614 <test_taint>:
919b4614:	div	r2,r0,0x20
                ^^^
919b4618:	add2	r2,0x920f6050,r2
919b4620:	ld_s	r2,[r2,0]
919b4622:	lsr	r0,r2,r0
919b4626:	j_s.d	[blink]
919b4628:	bmsk_s	r0,r0,0
919b462a:	nop_s

(patched) unsigned math
__________________

919b4614 <test_taint>:
919b4614:	lsr	r2,r0,0x5  @nr/32
                ^^^
919b4618:	add2	r2,0x920f6050,r2
919b4620:	ld_s	r2,[r2,0]
919b4622:	lsr	r0,r2,r0     #test_bit()
919b4626:	j_s.d	[blink]
919b4628:	bmsk_s	r0,r0,0
919b462a:	nop_s

Signed-off-by: Vineet Gupta <vgupta@...opsys.com>
---
This is an RFC for feeback, I understand this impacts every arch,
but as of now it is only buld/run tested on ARC.
---
---
 include/asm-generic/bitops/non-atomic.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 7e10c4b50c5d..c5a7d8eb9c2b 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -13,7 +13,7 @@
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static inline void __set_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -21,7 +21,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
 	*p  |= mask;
 }
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static inline void __clear_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -38,7 +38,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static inline void __change_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -55,7 +55,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_set_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -74,7 +74,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_clear_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -85,7 +85,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
+static inline int __test_and_change_bit(unsigned int nr,
 					    volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
@@ -101,7 +101,7 @@ static inline int __test_and_change_bit(int nr,
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
+static inline int test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
-- 
2.25.1