Patchwork [7/8] mm: thp: Use more portable PMD clearing sequenece in zap_huge_pmd().

login
register
mail settings
Submitter David Miller
Date Oct. 2, 2012, 10:27 p.m.
Message ID <20121002.182741.650740858374403508.davem@davemloft.net>
Download mbox | patch
Permalink /patch/188671/
State RFC
Delegated to: David Miller
Headers show

Comments

David Miller - Oct. 2, 2012, 10:27 p.m.
Invalidation sequences are handled in various ways on various
architectures.

One way, which sparc64 uses, is to let the set_*_at() functions
accumulate pending flushes into a per-cpu array.  Then the
flush_tlb_range() et al. calls process the pending TLB flushes.

In this regime, the __tlb_remove_*tlb_entry() implementations are
essentially NOPs.

The canonical PTE zap in mm/memory.c is:

			ptent = ptep_get_and_clear_full(mm, addr, pte,
							tlb->fullmm);
			tlb_remove_tlb_entry(tlb, pte, addr);

With a subsequent tlb_flush_mmu() if needed.

Mirror this in the THP PMD zapping using:

		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
		page = pmd_page(orig_pmd);
		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);

And we properly accomodate TLB flush mechanims like the one described
above.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 mm/huge_memory.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
Andrea Arcangeli - Oct. 2, 2012, 10:58 p.m.
On Tue, Oct 02, 2012 at 06:27:41PM -0400, David Miller wrote:
> 
> Invalidation sequences are handled in various ways on various
> architectures.
> 
> One way, which sparc64 uses, is to let the set_*_at() functions
> accumulate pending flushes into a per-cpu array.  Then the
> flush_tlb_range() et al. calls process the pending TLB flushes.
> 
> In this regime, the __tlb_remove_*tlb_entry() implementations are
> essentially NOPs.
> 
> The canonical PTE zap in mm/memory.c is:
> 
> 			ptent = ptep_get_and_clear_full(mm, addr, pte,
> 							tlb->fullmm);
> 			tlb_remove_tlb_entry(tlb, pte, addr);
> 
> With a subsequent tlb_flush_mmu() if needed.
> 
> Mirror this in the THP PMD zapping using:
> 
> 		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
> 		page = pmd_page(orig_pmd);
> 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
> 
> And we properly accomodate TLB flush mechanims like the one described
> above.

Thanks for the explanation.

Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
--
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

Patch

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5d44785..f9d8461 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1025,9 +1025,10 @@  int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
 		struct page *page;
 		pgtable_t pgtable;
+		pmd_t orig_pmd;
 		pgtable = get_pmd_huge_pte(tlb->mm);
-		page = pmd_page(*pmd);
-		pmd_clear(pmd);
+		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
+		page = pmd_page(orig_pmd);
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		page_remove_rmap(page);
 		VM_BUG_ON(page_mapcount(page) < 0);