Hi all,
There is some assembler code in kernel/i2c-algo-biths.c, which prevents
i2c to be built on x86_64 machines. However, it still works on non-x86
machines, as this part of the code is only built on machines that have
rdtscl, ie x86 and x86_64 architectures.
I propose to change it by C code, as in the patch attached. Please note
that I haven't tested it "in live", as I don't have something that uses
this module. However, I have tested it in a simple C program, and I also
tested that i2c still build correctly.
Surprisingly the assembler code produced from the C code by gcc (3.3 in
my case) is always (-O0 to -O3) more efficient than the asm + C code
(see my attached file).
Bye,
Aurelien
--
.''`. Aurelien Jarno | GPG: 1024D/F1BCDB73
: :' : Debian GNU/Linux developer | Electrical Engineer
`. `' aurel32 at debian.org | aurelien at aurel32.net
`- people.debian.org/~aurel32 | www.aurel32.net
-------------- next part --------------
Index: kernel/i2c-algo-biths.c
===================================================================
RCS file: /home/cvs/i2c/kernel/i2c-algo-biths.c,v
retrieving revision 1.15
diff -u -d -p -r1.15 i2c-algo-biths.c
--- kernel/i2c-algo-biths.c 29 Dec 2004 10:12:48 -0000 1.15
+++ kernel/i2c-algo-biths.c 10 Mar 2005 00:33:56 -0000
@@ -678,13 +678,9 @@ static _HS_ATTR_ void i2c_tsc_set(struct
static _HS_ATTR_ void i2c_tsc_run(struct i2c_algo_biths_data *adap)
{
- unsigned long now, loops, xloops;
- int d0;
- xloops = adap->xloops;
- __asm__("mull %0"
- :"=d" (xloops), "=&a" (d0)
- :"1" (xloops),"0" (current_cpu_data.loops_per_jiffy));
- loops = xloops * HZ;
+ unsigned long now, loops;
+ loops = ((long long) adap->xloops * current_cpu_data.loops_per_jiffy) >> 32;
+ loops *= HZ;
do
{
rep_nop();
-------------- next part --------------
C + ASM with -O0
----------------
000014a2 <i2c_tsc_run>:
14a2: 83 ec 10 sub $0x10,%esp
14a5: 8b 44 24 14 mov 0x14(%esp),%eax
14a9: 8b 40 30 mov 0x30(%eax),%eax
14ac: 89 44 24 04 mov %eax,0x4(%esp)
14b0: 8b 44 24 04 mov 0x4(%esp),%eax
14b4: 8b 15 84 00 00 00 mov 0x84,%edx
14ba: f7 e2 mul %edx
14bc: 89 c1 mov %eax,%ecx
14be: 89 d0 mov %edx,%eax
14c0: 89 44 24 04 mov %eax,0x4(%esp)
14c4: 89 c8 mov %ecx,%eax
14c6: 89 04 24 mov %eax,(%esp)
14c9: 8b 54 24 04 mov 0x4(%esp),%edx
14cd: 89 d0 mov %edx,%eax
14cf: c1 e0 02 shl $0x2,%eax
14d2: 01 d0 add %edx,%eax
14d4: 8d 14 85 00 00 00 00 lea 0x0(,%eax,4),%edx
14db: 01 d0 add %edx,%eax
14dd: c1 e0 02 shl $0x2,%eax
14e0: 89 44 24 08 mov %eax,0x8(%esp)
14e4: f3 90 pause
14e6: 0f 31 rdtsc
14e8: 89 44 24 0c mov %eax,0xc(%esp)
14ec: 8b 44 24 14 mov 0x14(%esp),%eax
14f0: 8b 50 2c mov 0x2c(%eax),%edx
14f3: 8b 44 24 0c mov 0xc(%esp),%eax
14f7: 29 d0 sub %edx,%eax
14f9: 3b 44 24 08 cmp 0x8(%esp),%eax
14fd: 72 e5 jb 14e4 <i2c_tsc_run+0x42>
14ff: 83 c4 10 add $0x10,%esp
1502: c3 ret
C only with -O0
---------------
000014a2 <i2c_tsc_run>:
14a2: 83 ec 08 sub $0x8,%esp
14a5: 8b 54 24 0c mov 0xc(%esp),%edx
14a9: a1 84 00 00 00 mov 0x84,%eax
14ae: f7 62 30 mull 0x30(%edx)
14b1: 89 d0 mov %edx,%eax
14b3: 89 c2 mov %eax,%edx
14b5: c1 fa 1f sar $0x1f,%edx
14b8: 89 04 24 mov %eax,(%esp)
14bb: 8b 14 24 mov (%esp),%edx
14be: 89 d0 mov %edx,%eax
14c0: c1 e0 02 shl $0x2,%eax
14c3: 01 d0 add %edx,%eax
14c5: 8d 14 85 00 00 00 00 lea 0x0(,%eax,4),%edx
14cc: 01 d0 add %edx,%eax
14ce: c1 e0 02 shl $0x2,%eax
14d1: 89 04 24 mov %eax,(%esp)
14d4: f3 90 pause
14d6: 0f 31 rdtsc
14d8: 89 44 24 04 mov %eax,0x4(%esp)
14dc: 8b 44 24 0c mov 0xc(%esp),%eax
14e0: 8b 50 2c mov 0x2c(%eax),%edx
14e3: 8b 44 24 04 mov 0x4(%esp),%eax
14e7: 29 d0 sub %edx,%eax
14e9: 3b 04 24 cmp (%esp),%eax
14ec: 72 e6 jb 14d4 <i2c_tsc_run+0x32>
14ee: 83 c4 08 add $0x8,%esp
14f1: c3 ret
C + ASM with -O2
----------------
00000f10 <i2c_tsc_run>:
f10: 56 push %esi
f11: 8b 35 84 00 00 00 mov 0x84,%esi
f17: 53 push %ebx
f18: 8b 5c 24 0c mov 0xc(%esp),%ebx
f1c: 89 f2 mov %esi,%edx
f1e: 8b 4b 30 mov 0x30(%ebx),%ecx
f21: 89 c8 mov %ecx,%eax
f23: f7 e2 mul %edx
f25: 8d 04 92 lea (%edx,%edx,4),%eax
f28: 8d 04 80 lea (%eax,%eax,4),%eax
f2b: 8d 0c 85 00 00 00 00 lea 0x0(,%eax,4),%ecx
f32: 8d b4 26 00 00 00 00 lea 0x0(%esi),%esi
f39: 8d bc 27 00 00 00 00 lea 0x0(%edi),%edi
f40: f3 90 pause
f42: 0f 31 rdtsc
f44: 8b 73 2c mov 0x2c(%ebx),%esi
f47: 29 f0 sub %esi,%eax
f49: 39 c8 cmp %ecx,%eax
f4b: 72 f3 jb f40 <i2c_tsc_run+0x30>
f4d: 5b pop %ebx
f4e: 5e pop %esi
f4f: c3 ret
C only with -O2
---------------
00000f10 <i2c_tsc_run>:
f10: 53 push %ebx
f11: a1 84 00 00 00 mov 0x84,%eax
f16: 8b 5c 24 08 mov 0x8(%esp),%ebx
f1a: f7 63 30 mull 0x30(%ebx)
f1d: 8d 04 92 lea (%edx,%edx,4),%eax
f20: 8d 04 80 lea (%eax,%eax,4),%eax
f23: 8d 0c 85 00 00 00 00 lea 0x0(,%eax,4),%ecx
f2a: 8d b6 00 00 00 00 lea 0x0(%esi),%esi
f30: f3 90 pause
f32: 0f 31 rdtsc
f34: 8b 53 2c mov 0x2c(%ebx),%edx
f37: 29 d0 sub %edx,%eax
f39: 39 c8 cmp %ecx,%eax
f3b: 72 f3 jb f30 <i2c_tsc_run+0x20>
f3d: 5b pop %ebx
f3e: c3 ret
f3f: 90 nop
