| 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
| ||
|
Message-ID: <20080311151719.GA15313@mailshack.com>
Date: Tue, 11 Mar 2008 16:17:19 +0100
From: Alexander van Heukelum <heukelum@...lshack.com>
To: Ingo Molnar <mingo@...e.hu>
Cc: Alexander van Heukelum <heukelum@...tmail.fm>,
Andi Kleen <andi@...stfloor.org>,
Thomas Gleixner <tglx@...utronix.de>,
"H. Peter Anvin" <hpa@...or.com>,
LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH] x86: Optimize find_next_(zero_)bit for small constant-size bitmaps
x86: Optimize find_next_(zero_)bit for small constant-size bitmaps.
This moves an optimization for searching constant-sized small
bitmaps form x86_64-specific to generic code.
On an i386 defconfig (the x86#testing one), the size of vmlinux hardly
changes with this applied. I have observed only four places where this
optimization avoids a call into find_next_bit:
In the functions return_unused_surplus_pages, alloc_fresh_huge_page,
and adjust_pool_surplus, this patch avoids a call for a 1-bit bitmap.
In __next_cpu a call is avoided for a 32-bit bitmap. That's it.
On x86_64, 52 locations are optimized with a minimal increase in
code size:
Current #testing defconfig:
146 x bsf, 27 x find_next_*bit
text data bss dec hex filename
5392637 846592 724424 6963653 6a41c5 vmlinux
After removing the x86_64 specific optimization for find_next_*bit:
94 x bsf, 79 x find_next_*bit
text data bss dec hex filename
5392358 846592 724424 6963374 6a40ae vmlinux
After this patch (making the optimization generic):
146 x bsf, 27 x find_next_*bit
text data bss dec hex filename
5392396 846592 724424 6963412 6a40d4 vmlinux
---
Hi Ingo,
I have now tested (in user-space) the one-long-versions of the
find_next_(zero_)bit in the patch. They give the expected
results.
> > +#ifdef CONFIG_GENERIC_FIND_NEXT_BIT
> > +unsigned long __find_next_bit(const unsigned long *addr,
> > + unsigned long size, unsigned long offset);
> > +
> > +static __always_inline unsigned long
> > +find_next_bit(const unsigned long *addr, unsigned long size,
> > + unsigned long offset)
>
> > +#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
>
> there should be an #else here i think, which maps find_next_bit to
> __find_next_bit / etc.
No, that is intentional: architectures are expected to either set
CONFIG_GENERIC_FIND_NEXT_BIT, or provide their own implementation
of find_next_bit.
An alternative would be to have all architectures providing
__find_next_bit/__find_next_zero_bit and do the optimization
unconditionally.
> > +unsigned long __find_next_bit(const unsigned long *addr,
> > + unsigned long size, unsigned long offset);
>
> should be explicitly "extern", so that we see that it's a prototype
> declaration.
ok.
This version runs fine on qemu.
Greetings,
Alexander
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index 7fbf93a..1a23ce1 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -312,12 +312,6 @@ static int test_bit(int nr, const volatile unsigned long *addr);
#undef ADDR
-unsigned long find_next_bit(const unsigned long *addr,
- unsigned long size, unsigned long offset);
-unsigned long find_next_zero_bit(const unsigned long *addr,
- unsigned long size, unsigned long offset);
-
-
#ifdef CONFIG_X86_32
# include "bitops_32.h"
#else
diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h
index 40bf0f8..87e1a17 100644
--- a/include/asm-x86/bitops_64.h
+++ b/include/asm-x86/bitops_64.h
@@ -20,21 +20,11 @@ static inline long __scanbit(unsigned long val, unsigned long max)
(__scanbit(*(unsigned long *)addr,(size))) : \
find_first_bit(addr,size)))
-#define find_next_bit(addr,size,off) \
-((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \
- ((off) + (__scanbit((*(unsigned long *)addr) >> (off),(size)-(off)))) : \
- find_next_bit(addr,size,off)))
-
#define find_first_zero_bit(addr,size) \
((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \
(__scanbit(~*(unsigned long *)addr,(size))) : \
find_first_zero_bit(addr,size)))
-#define find_next_zero_bit(addr,size,off) \
-((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? \
- ((off)+(__scanbit(~(((*(unsigned long *)addr)) >> (off)),(size)-(off)))) : \
- find_next_zero_bit(addr,size,off)))
-
static inline void set_bit_string(unsigned long *bitmap, unsigned long i,
int len)
{
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 69c1edb..15360f9 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -72,4 +72,81 @@ static inline unsigned fls_long(unsigned long l)
return fls64(l);
}
+#ifdef __KERNEL__
+#ifdef CONFIG_GENERIC_FIND_NEXT_BIT
+extern unsigned long __find_next_bit(const unsigned long *addr,
+ unsigned long size, unsigned long offset);
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+static __always_inline unsigned long
+find_next_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ unsigned long value;
+
+ /* Avoid a function call if the bitmap size is a constant */
+ /* and not bigger than BITS_PER_LONG. */
+
+ /* insert a sentinel so that __ffs returns size if there */
+ /* are no set bits in the bitmap */
+ if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+ value = (*addr) & ((~0ul) << offset);
+ value |= (1ul << size);
+ return __ffs(value);
+ }
+
+ /* the result of __ffs(0) is undefined, so it needs to be */
+ /* handled separately */
+ if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
+ value = (*addr) & ((~0ul) << offset);
+ return (value == 0) ? BITS_PER_LONG : __ffs(value);
+ }
+
+ /* size is not constant or too big */
+ return __find_next_bit(addr, size, offset);
+}
+
+extern unsigned long __find_next_zero_bit(const unsigned long *addr,
+ unsigned long size, unsigned long offset);
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+static __always_inline unsigned long
+find_next_zero_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ unsigned long value;
+
+ /* Avoid a function call if the bitmap size is a constant */
+ /* and not bigger than BITS_PER_LONG. */
+
+ /* insert a sentinel so that __ffs returns size if there */
+ /* are no set bits in the bitmap */
+ if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+ value = (~(*addr)) & ((~0ul) << offset);
+ value |= (1ul << size);
+ return __ffs(value);
+ }
+
+ /* the result of __ffs(0) is undefined, so it needs to be */
+ /* handled separately */
+ if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
+ value = (~(*addr)) & ((~0ul) << offset);
+ return (value == 0) ? BITS_PER_LONG : __ffs(value);
+ }
+
+ /* size is not constant or too big */
+ return __find_next_zero_bit(addr, size, offset);
+}
+#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
+#endif /* __KERNEL__ */
#endif
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index 5820e07..ce94c4c 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -15,17 +15,12 @@
#include <asm/byteorder.h>
#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
-#undef find_next_bit
-#undef find_next_zero_bit
-
-/**
- * find_next_bit - find the next set bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
+
+/*
+ * Find the next set bit in a memory region.
*/
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
- unsigned long offset)
+unsigned long __find_next_bit(const unsigned long *addr,
+ unsigned long size, unsigned long offset)
{
const unsigned long *p = addr + BITOP_WORD(offset);
unsigned long result = offset & ~(BITS_PER_LONG-1);
@@ -62,15 +57,14 @@ found_first:
found_middle:
return result + __ffs(tmp);
}
-
-EXPORT_SYMBOL(find_next_bit);
+EXPORT_SYMBOL(__find_next_bit);
/*
* This implementation of find_{first,next}_zero_bit was stolen from
* Linus' asm-alpha/bitops.h.
*/
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
- unsigned long offset)
+unsigned long __find_next_zero_bit(const unsigned long *addr,
+ unsigned long size, unsigned long offset)
{
const unsigned long *p = addr + BITOP_WORD(offset);
unsigned long result = offset & ~(BITS_PER_LONG-1);
@@ -107,8 +101,7 @@ found_first:
found_middle:
return result + ffz(tmp);
}
-
-EXPORT_SYMBOL(find_next_zero_bit);
+EXPORT_SYMBOL(__find_next_zero_bit);
#ifdef __BIG_ENDIAN
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists