summaryrefslogtreecommitdiff
path: root/arch/arc
diff options
context:
space:
mode:
authorVineet Gupta <vgupta@synopsys.com>2013-04-05 18:38:31 +0530
committerVineet Gupta <vgupta@synopsys.com>2013-05-07 13:44:00 +0530
commit8d56bec2f2945b7e500b413d1bdc24e7dca12877 (patch)
tree6a777ae12a5661959b055b3f47b77badc59a2a31 /arch/arc
parenta92a5d0dce5b02fa34792e313b5fe3d7d317b17b (diff)
ARC: [mm] optimize needless full mm TLB flush on munmap
munmap ends up calling tlb_flush() which for ARC was flushing the entire TLB unconditionally (by moving the MMU to a new ASID) do_munmap unmap_region unmap_vmas unmap_single_vma unmap_page_range tlb_start_vma zap_pud_range tlb_end_vma() tlb_finish_mmu tlb_flush() ---> unconditional flush_tlb_mm() So even a single page munmap, a frequent operation when uClibc dynamic linker (ldso) is loading the dependent shared libraries, would move the the ASID multiple times - needlessly invalidating the pre-faulted TLB entries (and increasing the rate of ASID wraparound + full TLB flush). This is now optimised to only be called if tlb->full_mm (which means for exit/execve) cases only. And for those cases, flush_tlb_mm() is already optimised to be a no-op for mm->mm_users == 0. So essentially there are no mmore full mm flushes - except for fork which anyhow needs it for properly COW'ing parent address space. munmap now needs to do TLB range flush, which is implemented with tlb_end_vma() Results ------- 1. ASID now consistenly moves by 4 during a simple ls (as opposed to 5 or 7 before). 2. LMBench microbenchmark also shows improvements Basic system parameters ------------------------------------------------------------------------------ Host OS Description Mhz tlb cache mem scal pages line par load bytes --------- ------------- ----------------------- ---- ----- ----- ------ ---- 3.9-rc5-0 Linux 3.9.0-r 3.9-rc5-0404-gcc-4.4-ba 80 8 64 1.1000 1 3.9-rc5-0 Linux 3.9.0-r 3.9-rc5-0405-avoid-full 80 8 64 1.1200 1 Processor, Processes - times in microseconds - smaller is better ------------------------------------------------------------------------------ Host OS Mhz null null open slct sig sig fork exec sh call I/O stat clos TCP inst hndl proc proc proc --------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- 3.9-rc5-0 Linux 3.9.0-r 80 4.81 8.69 68.6 118. 239. 8.53 31.6 4839 13.K 34.K 3.9-rc5-0 Linux 3.9.0-r 80 4.46 8.36 53.8 91.3 223. 8.12 24.2 4725 13.K 33.K File & VM system latencies in microseconds - smaller is better ------------------------------------------------------------------------------- Host OS 0K File 10K File Mmap Prot Page 100fd Create Delete Create Delete Latency Fault Fault selct --------- ------------- ------ ------ ------ ------ ------- ----- ------- ----- 3.9-rc5-0 Linux 3.9.0-r 314.7 223.2 1054.9 390.2 3615.0 1.590 20.1 126.6 3.9-rc5-0 Linux 3.9.0-r 265.8 183.8 1014.2 314.1 3193.0 6.910 18.8 110.4 Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Diffstat (limited to 'arch/arc')
-rw-r--r--arch/arc/include/asm/tlb.h16
1 files changed, 12 insertions, 4 deletions
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
index 3eb2ce0bdfa3..fe91719866a5 100644
--- a/arch/arc/include/asm/tlb.h
+++ b/arch/arc/include/asm/tlb.h
@@ -21,20 +21,28 @@
#ifndef __ASSEMBLY__
-#define tlb_flush(tlb) local_flush_tlb_mm((tlb)->mm)
+#define tlb_flush(tlb) \
+do { \
+ if (tlb->fullmm) \
+ flush_tlb_mm((tlb)->mm); \
+} while (0)
/*
* This pair is called at time of munmap/exit to flush cache and TLB entries
* for mappings being torn down.
* 1) cache-flush part -implemented via tlb_start_vma( ) can be NOP (for now)
* as we don't support aliasing configs in our VIPT D$.
- * 2) tlb-flush part - implemted via tlb_end_vma( ) can be NOP as well-
- * albiet for difft reasons - its better handled by moving to new ASID
+ * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range
*
* Note, read http://lkml.org/lkml/2004/1/15/6
*/
#define tlb_start_vma(tlb, vma)
-#define tlb_end_vma(tlb, vma)
+
+#define tlb_end_vma(tlb, vma) \
+do { \
+ if (!tlb->fullmm) \
+ flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
+} while (0)
#define __tlb_remove_tlb_entry(tlb, ptep, address)