All of lore.kernel.org
 help / color / mirror / Atom feed
* sparc64: Reduce TLB flushes on hugetlb PTE change
@ 2016-03-08  2:23 Nitin Gupta
  2016-03-08  4:32 ` David Miller
  2016-03-08 14:56 ` Nitin Gupta
  0 siblings, 2 replies; 3+ messages in thread
From: Nitin Gupta @ 2016-03-08  2:23 UTC (permalink / raw)
  To: sparclinux

Flush TSB and TLB only at REAL_HPAGE_SIZE boundaries and
not at every 8K stride.

Orabug: 22643230

Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>
---
 arch/sparc/mm/hugetlbpage.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d8f625c..0f4f320 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -182,11 +182,17 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	addr &= HPAGE_MASK;
 	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		set_pte_at(mm, addr, ptep, entry);
+		*ptep = entry;
 		ptep++;
 		addr += PAGE_SIZE;
 		pte_val(entry) += PAGE_SIZE;
 	}
+
+	/* Issue TSB and TLB flush at REAL_HPAGE_SIZE boundaries */
+	flush_tsb_user_page(mm, addr, true);
+	flush_tsb_user_page(mm, addr + REAL_HPAGE_SIZE, true);
+	global_flush_tlb_page(mm, addr);
+	global_flush_tlb_page(mm, addr + REAL_HPAGE_SIZE);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-- 
2.6.4


^ permalink raw reply related	[flat|nested] 3+ messages in thread

* Re: sparc64: Reduce TLB flushes on hugetlb PTE change
  2016-03-08  2:23 sparc64: Reduce TLB flushes on hugetlb PTE change Nitin Gupta
@ 2016-03-08  4:32 ` David Miller
  2016-03-08 14:56 ` Nitin Gupta
  1 sibling, 0 replies; 3+ messages in thread
From: David Miller @ 2016-03-08  4:32 UTC (permalink / raw)
  To: sparclinux

From: Nitin Gupta <nitin.m.gupta@oracle.com>
Date: Mon,  7 Mar 2016 18:23:27 -0800

> Flush TSB and TLB only at REAL_HPAGE_SIZE boundaries and
> not at every 8K stride.
> 
> Orabug: 22643230
> 
> Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>

Is this an update to your earlier patch?

If so, why aren't you explaining what you have changed?

Also, why haven't you put a proper version indication in
the Subject line?  Like "v3" or something?

By making more and more work for me like this, you are
making it more difficult for me to process my backlog
and get to actually reviewing the content of your change
and integrating it.

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: sparc64: Reduce TLB flushes on hugetlb PTE change
  2016-03-08  2:23 sparc64: Reduce TLB flushes on hugetlb PTE change Nitin Gupta
  2016-03-08  4:32 ` David Miller
@ 2016-03-08 14:56 ` Nitin Gupta
  1 sibling, 0 replies; 3+ messages in thread
From: Nitin Gupta @ 2016-03-08 14:56 UTC (permalink / raw)
  To: sparclinux



On 03/07/2016 08:32 PM, David Miller wrote:
> From: Nitin Gupta <nitin.m.gupta@oracle.com>
> Date: Mon,  7 Mar 2016 18:23:27 -0800
>
>> Flush TSB and TLB only at REAL_HPAGE_SIZE boundaries and
>> not at every 8K stride.
>>
>> Orabug: 22643230
>>
>> Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>
> Is this an update to your earlier patch?

No, this is a separate patch.

Nitin

> If so, why aren't you explaining what you have changed?
>
> Also, why haven't you put a proper version indication in
> the Subject line?  Like "v3" or something?
>
> By making more and more work for me like this, you are
> making it more difficult for me to process my backlog
> and get to actually reviewing the content of your change
> and integrating it.
> --
> To unsubscribe from this list: send the line "unsubscribe sparclinux" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2016-03-08 14:56 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-03-08  2:23 sparc64: Reduce TLB flushes on hugetlb PTE change Nitin Gupta
2016-03-08  4:32 ` David Miller
2016-03-08 14:56 ` Nitin Gupta

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.