lkml.org 
[lkml]   [2003]   [Jul]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: 2.5.74-mm1
On Thu, 3 Jul 2003, William Lee Irwin III wrote:

> On Thu, Jul 03, 2003 at 02:15:08PM -0700, Andrew Morton wrote:
> > ok. If you're feeling keen could you please revert the cpumask_t patch.
> > And please send the .config, thanks.
>
> Zwane reproduced this and when I compiled an identical kernel for him
> it went away; the only difference wsa the compiler version.

This is definitely a compiler issue, i rebuilt with;

zwane@montezuma linux-2.5.74-cpumask {0:0} gcc296 -v
Reading specs from /usr/lib/gcc-lib/i386-redhat-linux7/2.96/specs
gcc version 2.96 20000731 (Red Hat Linux 7.3 2.96-118)
And that works with NR_CPUS = 3 (it also explains why my 8way test box
with RH7.3 worked)

Also i ended up writing a userspace test case. I then narrowed it down to
-O2 with gcc 3.2 (native RH9 compiler) which causes failure;

e.g.

zwane@montezuma linux-2.5.74-cpumask {0:0} gcc -v
Reading specs from /usr/lib/gcc-lib/i386-redhat-linux/3.2.2/specs
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man
--infodir=/usr/share/info --enable-shared --enable-threads=posix
--disable-checking --with-system-zlib --enable-__cxa_atexit
--host=i386-redhat-linux
Thread model: posix
gcc version 3.2.2 20030222 (Red Hat Linux 3.2.2-5)
zwane@montezuma linux-2.5.74-cpumask {0:0} gcc -O2 test.c -o test-gcc3.2
zwane@montezuma linux-2.5.74-cpumask {0:0} ./test-gcc3.2
main: tmp 1
main: phys_cpu_present_map before 0
main: phys_cpu_present_map after 0
main: tmp 8
main: phys_cpu_present_map before 0
main: phys_cpu_present_map after 0
main: tmp 10
main: phys_cpu_present_map before 0
main: phys_cpu_present_map after 0
zwane@montezuma linux-2.5.74-cpumask {0:0} gcc -O1 test.c -o test-gcc3.2
zwane@montezuma linux-2.5.74-cpumask {0:0} ./test-gcc3.2
main: tmp 1
main: phys_cpu_present_map before 0
main: phys_cpu_present_map after 1
main: tmp 8
main: phys_cpu_present_map before 1
main: phys_cpu_present_map after 9
main: tmp 10
main: phys_cpu_present_map before 9
main: phys_cpu_present_map after 19
The second one is correct. So one definite failing piece of code was in
the cpus_or() path, i'm not so sure about the others. I have attached the
test case. Bill says his gcc 3.3 works...

Andrew?

--
function.linuxpower.ca#include <stdio.h>
#include <linux/bitops.h>
#define BITS_PER_LONG 32
#define NR_CPUS 3
#define printk(x...) printf(x)

#define BITS_TO_LONGS(bits) \
(((bits)+BITS_PER_LONG-1)/BITS_PER_LONG)
#define DECLARE_BITMAP(name,bits) \
unsigned long name[BITS_TO_LONGS(bits)]
#define CLEAR_BITMAP(name,bits) \
memset(name, 0, BITS_TO_LONGS(bits)*sizeof(unsigned long))

static inline void bitmap_or(volatile unsigned long *dst, const volatile unsigned long *bitmap1,
const volatile unsigned long *bitmap2, int bits)
{
int k;
for (k = 0; k < BITS_TO_LONGS(bits); ++k)
dst[k] = bitmap1[k] | bitmap2[k];
}
#define cpu_set(cpu, map) set_bit(cpu, (map).mask)
#define cpus_or(dst,src1,src2) bitmap_or((dst).mask, (src1).mask, (src2).mask, NR_CPUS)
#define cpus_coerce(map) ((map).mask[0])

#define CPU_ARRAY_SIZE BITS_TO_LONGS(NR_CPUS)

#define CPU_MASK_ALL { {[0 ... CPU_ARRAY_SIZE-1] = ~0UL} }
#define CPU_MASK_NONE { {[0 ... CPU_ARRAY_SIZE-1] = 0UL} }
#define cpumask_of_cpu(cpu) ({ cpumask_t __cpu_mask = CPU_MASK_NONE;\
cpu_set(cpu, __cpu_mask); \
__cpu_mask; \
})
struct cpumask
{
unsigned long mask[CPU_ARRAY_SIZE];
};
typedef struct cpumask cpumask_t;
static inline cpumask_t apicid_to_cpu_present(int phys_apicid)
{
return cpumask_of_cpu(phys_apicid);
}
int main(int argc, char **argv)
{
int bios_apicids[] = { 0, 3, 4, -1}, i, apicid;
cpumask_t phys_cpu_present_map = CPU_MASK_NONE, tmp;
for (i = 0; bios_apicids[i] != -1; i++) {
apicid = bios_apicids[i];
tmp = apicid_to_cpu_present(apicid);
printk("%s: tmp %lx\n", __FUNCTION__, cpus_coerce(tmp));
printk("%s: phys_cpu_present_map before %lx\n",
__FUNCTION__, cpus_coerce(phys_cpu_present_map));
cpus_or(phys_cpu_present_map, phys_cpu_present_map, tmp);
printk("%s: phys_cpu_present_map after %lx\n",
__FUNCTION__, cpus_coerce(phys_cpu_present_map));
}
return 0;
}
\
 
 \ /
  Last update: 2005-03-22 13:46    [from the cache]
©2003-2011 Jasper Spaans