[PATCH, v2] mm, numa: Turn 4K pte NUMA faults into effectivehugepage ones

[Ingo Molnar]

Ok, the patch withstood a bit more testing as well. Below is a 
v2 version of it, with a couple of cleanups (no functional 
changes).

Thanks,

	Ingo

----------------->
Subject: mm, numa: Turn 4K pte NUMA faults into effective hugepage ones
From: Ingo Molnar <mingo@xxxxxxxxxx>
Date: Tue Nov 20 15:48:26 CET 2012

Reduce the 4K page fault count by looking around and processing
nearby pages if possible.

To keep the logic and cache overhead simple and straightforward
we do a couple of simplifications:

 - we only scan in the HPAGE_SIZE range of the faulting address
 - we only go as far as the vma allows us

Also simplify the do_numa_page() flow while at it and fix the
previous double faulting we incurred due to not properly fixing
up freshly migrated ptes.

Suggested-by: Mel Gorman <mgorman@xxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 mm/memory.c |   99 ++++++++++++++++++++++++++++++++++++++----------------------
 1 file changed, 64 insertions(+), 35 deletions(-)

Index: linux/mm/memory.c
===================================================================
--- linux.orig/mm/memory.c
+++ linux/mm/memory.c
@@ -3455,64 +3455,93 @@ static int do_nonlinear_fault(struct mm_
 	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
-static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+static int __do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pmd_t *pmd,
-			unsigned int flags, pte_t entry)
+			unsigned int flags, pte_t entry, spinlock_t *ptl)
 {
-	struct page *page = NULL;
-	int node, page_nid = -1;
-	int last_cpu = -1;
-	spinlock_t *ptl;
-
-	ptl = pte_lockptr(mm, pmd);
-	spin_lock(ptl);
-	if (unlikely(!pte_same(*ptep, entry)))
-		goto out_unlock;
+	struct page *page;
+	int new_node;
 
 	page = vm_normal_page(vma, address, entry);
 	if (page) {
-		get_page(page);
-		page_nid = page_to_nid(page);
-		last_cpu = page_last_cpu(page);
-		node = mpol_misplaced(page, vma, address);
-		if (node != -1 && node != page_nid)
+		int page_nid = page_to_nid(page);
+		int last_cpu = page_last_cpu(page);
+
+		task_numa_fault(page_nid, last_cpu, 1);
+
+		new_node = mpol_misplaced(page, vma, address);
+		if (new_node != -1 && new_node != page_nid)
 			goto migrate;
 	}
 
-out_pte_upgrade_unlock:
+out_pte_upgrade:
 	flush_cache_page(vma, address, pte_pfn(entry));
-
 	ptep_modify_prot_start(mm, address, ptep);
 	entry = pte_modify(entry, vma->vm_page_prot);
+	if (pte_dirty(entry))
+		entry = pte_mkwrite(entry);
 	ptep_modify_prot_commit(mm, address, ptep, entry);
-
 	/* No TLB flush needed because we upgraded the PTE */
-
 	update_mmu_cache(vma, address, ptep);
-
-out_unlock:
-	pte_unmap_unlock(ptep, ptl);
-
-	if (page) {
-		task_numa_fault(page_nid, last_cpu, 1);
-		put_page(page);
-	}
 out:
 	return 0;
 
 migrate:
+	get_page(page);
 	pte_unmap_unlock(ptep, ptl);
 
-	if (migrate_misplaced_page(page, node)) {
+	migrate_misplaced_page(page, new_node); /* Drops the page reference */
+
+	/* Re-check after migration: */
+
+	ptl = pte_lockptr(mm, pmd);
+	spin_lock(ptl);
+	entry = ACCESS_ONCE(*ptep);
+
+	if (!pte_numa(vma, entry))
 		goto out;
-	}
-	page = NULL;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
-	if (!pte_same(*ptep, entry))
-		goto out_unlock;
+	goto out_pte_upgrade;
+}
+
+/*
+ * Add a simple loop to also fetch ptes within the same pmd:
+ */
+static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long addr0, pte_t *ptep0, pmd_t *pmd,
+			unsigned int flags, pte_t entry0)
+{
+	unsigned long addr0_pmd;
+	unsigned long addr_start;
+	unsigned long addr;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	addr0_pmd = addr0 & PMD_MASK;
+	addr_start = max(addr0_pmd, vma->vm_start);
 
-	goto out_pte_upgrade_unlock;
+	ptep = pte_offset_map(pmd, addr_start);
+	ptl = pte_lockptr(mm, pmd);
+	spin_lock(ptl);
+
+	for (addr = addr_start; addr < vma->vm_end; addr += PAGE_SIZE, ptep++) {
+ 		pte_t entry;
+
+		entry = ACCESS_ONCE(*ptep);
+
+		if ((addr & PMD_MASK) != addr0_pmd)
+			break;
+		if (!pte_present(entry))
+			continue;
+		if (!pte_numa(vma, entry))
+			continue;
+
+		__do_numa_page(mm, vma, addr, ptep, pmd, flags, entry, ptl);
+	}
+
+	pte_unmap_unlock(ptep, ptl);
+	
+	return 0;
 }
 
 /*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/