aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorAnton Blanchard <anton@samba.org>2009-09-21 12:52:35 -0400
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2009-09-24 01:31:44 -0400
commit8bbde7a7062facf8af35bcc9a64cbafe8f36f3cf (patch)
tree4d41cfa5b9a65a39f46933f650e930019346201c /arch
parent738ef42e32fe95553a424c04016b936c9f6c9afb (diff)
powerpc: Move 64bit heap above 1TB on machines with 1TB segments
If we are using 1TB segments and we are allowed to randomise the heap, we can put it above 1TB so it is backed by a 1TB segment. Otherwise the heap will be in the bottom 1TB which always uses 256MB segments and this may result in a performance penalty. This functionality is disabled when heap randomisation is turned off: echo 1 > /proc/sys/kernel/randomize_va_space which may be useful when trying to allocate the maximum amount of 16M or 16G pages. On a microbenchmark that repeatedly touches 32GB of memory with a stride of 256MB + 4kB (designed to stress 256MB segments while still mapping nicely into the L1 cache), we see the improvement: Force malloc to use heap all the time: # export MALLOC_MMAP_MAX_=0 MALLOC_TRIM_THRESHOLD_=-1 Disable heap randomization: # echo 1 > /proc/sys/kernel/randomize_va_space # time ./test 12.51s Enable heap randomization: # echo 2 > /proc/sys/kernel/randomize_va_space # time ./test 1.70s Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/kernel/process.c17
1 files changed, 16 insertions, 1 deletions
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 0a3216433051..1168c5f440ab 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1165,7 +1165,22 @@ static inline unsigned long brk_rnd(void)
1165 1165
1166unsigned long arch_randomize_brk(struct mm_struct *mm) 1166unsigned long arch_randomize_brk(struct mm_struct *mm)
1167{ 1167{
1168 unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd()); 1168 unsigned long base = mm->brk;
1169 unsigned long ret;
1170
1171#ifdef CONFIG_PPC64
1172 /*
1173 * If we are using 1TB segments and we are allowed to randomise
1174 * the heap, we can put it above 1TB so it is backed by a 1TB
1175 * segment. Otherwise the heap will be in the bottom 1TB
1176 * which always uses 256MB segments and this may result in a
1177 * performance penalty.
1178 */
1179 if (!is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T))
1180 base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T);
1181#endif
1182
1183 ret = PAGE_ALIGN(base + brk_rnd());
1169 1184
1170 if (ret < mm->brk) 1185 if (ret < mm->brk)
1171 return mm->brk; 1186 return mm->brk;