Re: [PATCH 1/2] x86/bitops: implement __test_bit

[Michael S. Tsirkin]

On Mon, Aug 31, 2015 at 09:59:47AM +0200, Ingo Molnar wrote:
> 
> * Michael S. Tsirkin <mst@xxxxxxxxxx> wrote:
> 
> > On Sun, Aug 30, 2015 at 11:13:20PM -0700, H. Peter Anvin wrote:
> > > Presumably because gcc can't generate bt... whether or not it is worth it is another matter.
> > > 
> > > On August 30, 2015 11:05:49 PM PDT, Ingo Molnar <mingo@xxxxxxxxxx> wrote:
> > > >
> > > >* Michael S. Tsirkin <mst@xxxxxxxxxx> wrote:
> > > >
> > > >> +static __always_inline int __constant_test_bit(long nr, const
> > > >unsigned long *addr)
> > > >> +{
> > > >> +	return ((1UL << (nr & (BITS_PER_LONG-1))) &
> > > >> +		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
> > > >> +}
> > > >> +
> > > >> +static inline int __variable_test_bit(long nr, const unsigned long
> > > >*addr)
> > > >> +{
> > > >> +	int oldbit;
> > > >> +
> > > >> +	asm volatile("bt %2,%1\n\t"
> > > >> +		     "sbb %0,%0"
> > > >> +		     : "=r" (oldbit)
> > > >> +		     : "m" (*addr), "Ir" (nr));
> > > >> +
> > > >> +	return oldbit;
> > > >> +}
> > > >
> > > >Color me confused, why use assembly for this at all?
> > > >
> > > >Why not just use C for testing the bit (i.e. turn __constant_test_bit()
> > > >into 
> > > >__test_bit()) - that would also allow the compiler to propagate the
> > > >result, 
> > > >potentially more optimally than we can do it via SBB...
> > > >
> > > >Thanks,
> > > >
> > > >	Ingo
> > 
> > Exactly:
> > 
> > 
> > Disassembly of section .text:
> > 
> > 00000000 <__variable_test_bit>:
> > __variable_test_bit():
> >    0:   8b 54 24 08             mov    0x8(%esp),%edx
> >    4:   8b 44 24 04             mov    0x4(%esp),%eax
> >    8:   0f a3 02                bt     %eax,(%edx)
> >    b:   19 c0                   sbb    %eax,%eax
> >    d:   c3                      ret    
> >    e:   66 90                   xchg   %ax,%ax
> > 
> > 00000010 <__constant_test_bit>:
> > __constant_test_bit():
> >   10:   8b 4c 24 04             mov    0x4(%esp),%ecx
> >   14:   8b 44 24 08             mov    0x8(%esp),%eax
> >   18:   89 ca                   mov    %ecx,%edx
> >   1a:   c1 fa 04                sar    $0x4,%edx
> >   1d:   8b 04 90                mov    (%eax,%edx,4),%eax
> >   20:   d3 e8                   shr    %cl,%eax
> >   22:   83 e0 01                and    $0x1,%eax
> >   25:   c3                      ret    
> 
> But that's due to the forced interface of generating a return code. Please compare 
> it at an inlined usage site, where GCC is free to do the comparison directly and 
> use the result in flags.
> 
> Thanks,
> 
> 	Ingo

I applied this patch on top of mine:


diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 9229334..2aed985 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -323,24 +323,17 @@ static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 	return oldbit;
 }
 
-static __always_inline int __constant_test_bit(long nr, const unsigned long *addr)
+/**
+ * __test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline int __test_bit(long nr, const unsigned long *addr)
 {
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static inline int __variable_test_bit(long nr, const unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("bt %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit)
-		     : "m" (*addr), "Ir" (nr));
-
-	return oldbit;
-}
-
 #if 0 /* Fool kernel-doc since it doesn't do macros yet */
 /**
  * test_bit - Determine whether a bit is set
@@ -348,13 +341,6 @@ static inline int __variable_test_bit(long nr, const unsigned long *addr)
  * @addr: Address to start counting from
  */
 static int test_bit(int nr, const volatile unsigned long *addr);
-
-/**
- * __test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static int __test_bit(int nr, const volatile unsigned long *addr);
 #endif
 
 #define test_bit(nr, addr)			\
@@ -362,10 +348,6 @@ static int __test_bit(int nr, const volatile unsigned long *addr);
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
-#define __test_bit(nr, addr)			\
-	(__builtin_constant_p((nr))		\
-	 ? __constant_test_bit((nr), (addr))	\
-	 : __variable_test_bit((nr), (addr)))
 
 /**
  * __ffs - find first set bit in word


And the code size went up:

   134836    2997    8372  146205   23b1d arch/x86/kvm/kvm-intel.ko  ->
   134846    2997    8372  146215   23b27 arch/x86/kvm/kvm-intel.ko     

   342690   47640     441  390771   5f673 arch/x86/kvm/kvm.ko ->
   342738   47640     441  390819   5f6a3 arch/x86/kvm/kvm.ko   

I tried removing  __always_inline, this had no effect.

-- 
MST
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/