linux-next: manual merge of the tip tree with Linus' tree

[Stephen Rothwell <sfr@canb.auug.org.au>]

[-- Attachment #1: Type: text/plain, Size: 6211 bytes --]

Hi all,

Today's linux-next merge of the tip tree got a conflict in
mm/huge_memory.c between commits d516904bd239 ("thp: merge page pre-alloc
in khugepaged_loop into khugepaged_do_scan"), e3ebcf643811 ("thp: remove
assumptions on pgtable_t type") and 46dcde735c9d ("thp: introduce
pmdp_invalidate()") from Linus' tree and commit 93c9d633bd9e ("mm/thp:
Preserve pgprot across huge page split") from the tip tree.

I fixed it up (I think - see below) and can carry the fix as necessary
(no action is required).

-- 
Cheers,
Stephen Rothwell                    sfr@canb.auug.org.au

diff --cc mm/huge_memory.c
index a863af2,5b9ab25..0000000
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@@ -1346,59 -1428,55 +1417,54 @@@ static int __split_huge_page_map(struc
  	spin_lock(&mm->page_table_lock);
  	pmd = page_check_address_pmd(page, mm, address,
  				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
- 	if (pmd) {
- 		pgtable = pgtable_trans_huge_withdraw(mm);
- 		pmd_populate(mm, &_pmd, pgtable);
- 
- 		haddr = address;
- 		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
- 			pte_t *pte, entry;
- 			BUG_ON(PageCompound(page+i));
- 			entry = mk_pte(page + i, vma->vm_page_prot);
- 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- 			if (!pmd_write(*pmd))
- 				entry = pte_wrprotect(entry);
- 			else
- 				BUG_ON(page_mapcount(page) != 1);
- 			if (!pmd_young(*pmd))
- 				entry = pte_mkold(entry);
- 			pte = pte_offset_map(&_pmd, haddr);
- 			BUG_ON(!pte_none(*pte));
- 			set_pte_at(mm, haddr, pte, entry);
- 			pte_unmap(pte);
- 		}
+ 	if (!pmd)
+ 		goto unlock;
  
- 		smp_wmb(); /* make pte visible before pmd */
- 		/*
- 		 * Up to this point the pmd is present and huge and
- 		 * userland has the whole access to the hugepage
- 		 * during the split (which happens in place). If we
- 		 * overwrite the pmd with the not-huge version
- 		 * pointing to the pte here (which of course we could
- 		 * if all CPUs were bug free), userland could trigger
- 		 * a small page size TLB miss on the small sized TLB
- 		 * while the hugepage TLB entry is still established
- 		 * in the huge TLB. Some CPU doesn't like that. See
- 		 * http://support.amd.com/us/Processor_TechDocs/41322.pdf,
- 		 * Erratum 383 on page 93. Intel should be safe but is
- 		 * also warns that it's only safe if the permission
- 		 * and cache attributes of the two entries loaded in
- 		 * the two TLB is identical (which should be the case
- 		 * here). But it is generally safer to never allow
- 		 * small and huge TLB entries for the same virtual
- 		 * address to be loaded simultaneously. So instead of
- 		 * doing "pmd_populate(); flush_tlb_range();" we first
- 		 * mark the current pmd notpresent (atomically because
- 		 * here the pmd_trans_huge and pmd_trans_splitting
- 		 * must remain set at all times on the pmd until the
- 		 * split is complete for this pmd), then we flush the
- 		 * SMP TLB and finally we write the non-huge version
- 		 * of the pmd entry with pmd_populate.
- 		 */
- 		pmdp_invalidate(vma, address, pmd);
- 		pmd_populate(mm, pmd, pgtable);
- 		ret = 1;
+ 	prot = pmd_pgprot(*pmd);
 -	pgtable = get_pmd_huge_pte(mm);
++	pgtable = pgtable_trans_huge_withdraw(mm);
+ 	pmd_populate(mm, &_pmd, pgtable);
+ 
+ 	for (i = 0, haddr = address; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+ 		pte_t *pte, entry;
+ 
+ 		BUG_ON(PageCompound(page+i));
+ 		entry = mk_pte(page + i, prot);
+ 		entry = pte_mkdirty(entry);
+ 		if (!pmd_young(*pmd))
+ 			entry = pte_mkold(entry);
+ 		pte = pte_offset_map(&_pmd, haddr);
+ 		BUG_ON(!pte_none(*pte));
+ 		set_pte_at(mm, haddr, pte, entry);
+ 		pte_unmap(pte);
  	}
+ 
+ 	smp_wmb(); /* make ptes visible before pmd, see __pte_alloc */
+ 	/*
+ 	 * Up to this point the pmd is present and huge.
+ 	 *
+ 	 * If we overwrite the pmd with the not-huge version, we could trigger
+ 	 * a small page size TLB miss on the small sized TLB while the hugepage
+ 	 * TLB entry is still established in the huge TLB.
+ 	 *
+ 	 * Some CPUs don't like that. See
+ 	 * http://support.amd.com/us/Processor_TechDocs/41322.pdf, Erratum 383
+ 	 * on page 93.
+ 	 *
+ 	 * Thus it is generally safer to never allow small and huge TLB entries
+ 	 * for overlapping virtual addresses to be loaded. So we first mark the
+ 	 * current pmd not present, then we flush the TLB and finally we write
+ 	 * the non-huge version of the pmd entry with pmd_populate.
+ 	 *
+ 	 * The above needs to be done under the ptl because pmd_trans_huge and
+ 	 * pmd_trans_splitting must remain set on the pmd until the split is
+ 	 * complete. The ptl also protects against concurrent faults due to
+ 	 * making the pmd not-present.
+ 	 */
 -	set_pmd_at(mm, address, pmd, pmd_mknotpresent(*pmd));
 -	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
++	pmdp_invalidate(vma, address, pmd);
+ 	pmd_populate(mm, pmd, pgtable);
+ 	ret = 1;
+ 
+ unlock:
  	spin_unlock(&mm->page_table_lock);
  
  	return ret;
@@@ -2279,23 -2300,30 +2345,21 @@@ static int khugepaged_has_work(void
  static int khugepaged_wait_event(void)
  {
  	return !list_empty(&khugepaged_scan.mm_head) ||
 -		!khugepaged_enabled();
 +		kthread_should_stop();
  }
  
 -static void khugepaged_do_scan(struct page **hpage)
 +static void khugepaged_do_scan(void)
  {
 +	struct page *hpage = NULL;
  	unsigned int progress = 0, pass_through_head = 0;
- 	unsigned int pages = khugepaged_pages_to_scan;
+ 	unsigned int pages = ACCESS_ONCE(khugepaged_pages_to_scan);
 +	bool wait = true;
  
- 	barrier(); /* write khugepaged_pages_to_scan to local stack */
- 
  	while (progress < pages) {
 -		cond_resched();
 -
 -#ifndef CONFIG_NUMA
 -		if (!*hpage) {
 -			*hpage = alloc_hugepage(khugepaged_defrag());
 -			if (unlikely(!*hpage)) {
 -				count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 -				break;
 -			}
 -			count_vm_event(THP_COLLAPSE_ALLOC);
 -		}
 -#else
 -		if (IS_ERR(*hpage))
 +		if (!khugepaged_prealloc_page(&hpage, &wait))
  			break;
 -#endif
 +
 +		cond_resched();
  
  		if (unlikely(kthread_should_stop() || freezing(current)))
  			break;

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]