c20351846e
This follows the ARM change from Aaro Koskinen: When unmapping N pages (e.g. shared memory) the amount of TLB flushes done can be (N*PAGE_SIZE/ZAP_BLOCK_SIZE)*N although it should be N at maximum. With PREEMPT kernel ZAP_BLOCK_SIZE is 8 pages, so there is a noticeable performance penalty when unmapping a large VMA and the system is spending its time in flush_tlb_range(). The problem is that tlb_end_vma() is always flushing the full VMA range. The subrange that needs to be flushed can be calculated by tlb_remove_tlb_entry(). This approach was suggested by Hugh Dickins, and is also used by other arches. The speed increase is roughly 3x for 8M mappings and for larger mappings even more. Bits and peices are taken from the ARM patch as well as the existing arch/um implementation that is quite similar. The end result is a significant reduction in both partial and full TLB flushes initiated through flush_tlb_range(). At the same time, the nommu implementation was broken, had a superfluous cache flush, and subsequently would have triggered a BUG_ON() if a code-path had triggered it. Tidy this up for correctness and provide a nopped-out implementation there. More background on the initial discussion can be found at: http://marc.info/?t=123609820900002&r=1&w=2 http://marc.info/?t=123660375800003&r=1&w=2 Signed-off-by: Paul Mundt <lethal@linux-sh.org> |
||
|---|---|---|
| .. | ||
| asm | ||
| cpu-common/cpu | ||
| cpu-sh2/cpu | ||
| cpu-sh2a/cpu | ||
| cpu-sh3/cpu | ||
| cpu-sh4/cpu | ||
| cpu-sh5/cpu | ||
| mach-common/mach | ||
| mach-dreamcast/mach | ||
| mach-landisk/mach | ||
| mach-se/mach | ||
| mach-sh03/mach | ||