The test program:
/*
* This test aims to provoke VHPT misses.
*
* In order to maximize the number of the TLB entries needed for the virtually mapped
* PTE pages, only one valid PTE / page will be used (, and a single byte per data page).
* The TLB pressure will me multiplied by "N" in order not to leave any
* practical chance for a TLB hit.
*
* Remember to allow to over-commit memory: "sysctl -w vm.overcommit_memory=1".
*
* ...there is no control over the physical addresses of the user pages... there will
* be some variation of the results from run to run due to some address aliases...
*
* ...the interrupts are enabled...
*/
#include <sys/types.h>
#include <stdio.h>
#include <sys/mman.h>
#define N 8 // TLB pressure multiplier
#define N_RUNS 10
#define N_EXTERNAL_LOOPS 10
#define N_INTERNAL_LOOPS 1000
#define CACHE_BYTES 128
#define N_TLB_ENTRIES 128
// Not counting the kernel's DTRs...
#define N_PTE_PAGE_U_PAGE_PAIRS (N_TLB_ENTRIES / 2 * N)
#define PTE_PER_CACHE_BYTES (CACHE_BYTES / sizeof(unsigned long))
unsigned int pagesize;
#define PTES_PER_PAGE (pagesize / sizeof(void *))
#define VA_RANGE_PER_PTE_PAGE (PTES_PER_PAGE * pagesize)
/*
* Cache line "coloring" in order to reduce cache alias problems.
* (Yet as there is no control over the physical addresses of the user pages...)
* The i-th element touched by the innermost loop will be at the offset in the page:
* (i * 2 + 1) * CACHE_BYTES
* The PTE mapping this test data will be at the offset in its page:
* i * 2 * CACHE_BYTES
*/
#define OFFSET (VA_RANGE_PER_PTE_PAGE + \
2 * PTE_PER_CACHE_BYTES * pagesize + \
2 * CACHE_BYTES)
unsigned int offset;
#define TEST_VA_RANGE ((unsigned long) VA_RANGE_PER_PTE_PAGE * \
N_PTE_PAGE_U_PAGE_PAIRS + \
/* Cache line "coloring": */ \
2 * N_PTE_PAGE_U_PAGE_PAIRS * \
PTE_PER_CACHE_BYTES * pagesize + \
2 * N_PTE_PAGE_U_PAGE_PAIRS * CACHE_BYTES)
#define MEM_PROT (PROT_READ | PROT_WRITE)
#define MEM_TYPE (MAP_PRIVATE | MAP_ANONYMOUS)
#define GET_ITC() \
({ \
unsigned long ia64_intri_res; \
\
asm volatile ("mov %0=ar.itc" : "=r"(ia64_intri_res)); \
ia64_intri_res; \
})
inline unsigned long test(char *p0, unsigned int n)
{
int i, j;
char *p;
unsigned long itc0 = GET_ITC();
for (j = 0; j < n; j++)
for (i = 0, p = p0 + CACHE_BYTES; // Cache line "coloring"
i < N_PTE_PAGE_U_PAGE_PAIRS; i++, p += offset)
*p = i;
return GET_ITC() - itc0;
}
void main_test(void)
{
void *p;
int loop;
unsigned long tmp, sum = 0;
p = mmap(NULL, TEST_VA_RANGE, MEM_PROT, MEM_TYPE, -1, 0);
if (p == MAP_FAILED){
perror("mmap");
fprintf(stderr, "Have you allowed to over-commit memory? "
"Try: \"sysctl -w vm.overcommit_memory=1\"\n");
exit(1);
}
(void) test(p, 1); // Warm up...
for (loop = 0; loop < N_EXTERNAL_LOOPS; loop++)
sum += test(p, N_INTERNAL_LOOPS);
(void) munmap(p, TEST_VA_RANGE);
printf("ITC ticks: %ld,%03ld,%03ld,",
sum / 1000000, sum / 1000 % 1000, sum % 1000);
tmp = (unsigned long) N_EXTERNAL_LOOPS * N_INTERNAL_LOOPS *
N_PTE_PAGE_U_PAGE_PAIRS;
printf(" # user accesses: %ld,%03ld,%03ld, ITC ticks / access: %ld\n",
tmp / 1000000, tmp / 1000 % 1000, tmp % 1000, sum / tmp);
}
int main(int argc, char *argv[])
{
int run;
unsigned long tmp;
pagesize = getpagesize();
offset = OFFSET; // Depends on "getpagesize()"
printf("Page size =\t\t\t%12d\n", pagesize);
printf("PTEs / page =\t\t\t%12d\n", PTES_PER_PAGE);
printf("VA range / PTE page =\t\t%12d (%d Mbytes)\n",
VA_RANGE_PER_PTE_PAGE, VA_RANGE_PER_PTE_PAGE >> 20);
printf("# PTE-page / user-page pairs =\t%12d\n", N_PTE_PAGE_U_PAGE_PAIRS);
printf("Test VA range =\t\t\t%12ld (%ld Gbytes)\n",
TEST_VA_RANGE, TEST_VA_RANGE >> 30);
tmp = N_PTE_PAGE_U_PAGE_PAIRS * pagesize;
printf("Resident user memory =\t\t%12ld (%ld Mbytes)\n", tmp, tmp >> 20);
printf("# PTE + user cache lines =\t%12d (%d Kbytes)\n",
N_PTE_PAGE_U_PAGE_PAIRS * 2,
N_PTE_PAGE_U_PAGE_PAIRS * 2 * CACHE_BYTES >> 10);
printf("\n");
for (run = 0; run < N_RUNS; run++)
main_test();
return 0;
}
-
: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|