TASK_UNMAPPED_BASE is not used with the new top down mmap layout. We can
reuse this preload slot by loading in the segment at 0x1000, where almost
all PowerPC binaries are linked at.
On a microbenchmark that bounces a token between two 64bit processes over pipes
and calls gettimeofday each iteration (to access the VDSO), both the 32bit and
64bit context switch rate improves (tested on a 4GHz POWER6):
32bit: 273k/sec - 283k/sec
64bit: 277k/sec - 284k/sec
Signed-off-by: Anton Blanchard an...@samba.org
---
Index: linux.trees.git/arch/powerpc/mm/slb.c
===
--- linux.trees.git.orig/arch/powerpc/mm/slb.c 2009-07-14 15:09:39.0
+1000
+++ linux.trees.git/arch/powerpc/mm/slb.c 2009-07-14 15:12:42.0
+1000
@@ -191,7 +191,7 @@
unsigned long slbie_data = 0;
unsigned long pc = KSTK_EIP(tsk);
unsigned long stack = KSTK_ESP(tsk);
- unsigned long unmapped_base;
+ unsigned long exec_base;
if (!cpu_has_feature(CPU_FTR_NO_SLBIE_B)
offset = SLB_CACHE_ENTRIES) {
@@ -219,14 +219,13 @@
/*
* preload some userspace segments into the SLB.
+* Almost all 32 and 64bit PowerPC executables are linked at
+* 0x1000 so it makes sense to preload this segment.
*/
- if (test_tsk_thread_flag(tsk, TIF_32BIT))
- unmapped_base = TASK_UNMAPPED_BASE_USER32;
- else
- unmapped_base = TASK_UNMAPPED_BASE_USER64;
+ exec_base = 0x1000;
if (is_kernel_addr(pc) || is_kernel_addr(stack) ||
- is_kernel_addr(unmapped_base))
+ is_kernel_addr(exec_base))
return;
slb_allocate(pc);
@@ -234,9 +233,9 @@
if (!esids_match(pc, stack))
slb_allocate(stack);
- if (!esids_match(pc, unmapped_base)
- !esids_match(stack, unmapped_base))
- slb_allocate(unmapped_base);
+ if (!esids_match(pc, exec_base)
+ !esids_match(stack, exec_base))
+ slb_allocate(exec_base);
}
static inline void patch_slb_encoding(unsigned int *insn_addr,
--
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
