[RFC][PATCH 3/6] mm: VMA sequence count

[Peter Zijlstra]

Wrap the VMA modifications (vma_adjust/unmap_page_range) with sequence
counts such that we can easily test if a VMA is changed.

The unmap_page_range() one allows us to make assumptions about
page-tables; when we find the seqcount hasn't changed we can assume
page-tables are still valid.

The flip side is that we cannot distinguish between a vma_adjust() and
the unmap_page_range() -- where with the former we could have
re-checked the vma bounds against the address.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 include/linux/mm_types.h |    2 ++
 mm/memory.c              |    2 ++
 mm/mmap.c                |   13 +++++++++++++
 3 files changed, 17 insertions(+)

--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -13,6 +13,7 @@
 #include <linux/page-debug-flags.h>
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
+#include <linux/seqlock.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 
@@ -308,6 +309,7 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
+	seqcount_t vm_sequence;
 };
 
 struct core_thread {
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1293,6 +1293,7 @@ static void unmap_page_range(struct mmu_
 		details = NULL;
 
 	BUG_ON(addr >= end);
+	write_seqcount_begin(&vma->vm_sequence);
 	tlb_start_vma(tlb, vma);
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
@@ -1302,6 +1303,7 @@ static void unmap_page_range(struct mmu_
 		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
+	write_seqcount_end(&vma->vm_sequence);
 }
 
 
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -596,6 +596,8 @@ void __vma_link_rb(struct mm_struct *mm,
 	else
 		mm->highest_vm_end = vma->vm_end;
 
+	seqcount_init(&vma->vm_sequence);
+
 	/*
 	 * vma->vm_prev wasn't known when we followed the rbtree to find the
 	 * correct insertion point for that vma. As a result, we could not
@@ -715,6 +717,10 @@ int vma_adjust(struct vm_area_struct *vm
 	long adjust_next = 0;
 	int remove_next = 0;
 
+	write_seqcount_begin(&vma->vm_sequence);
+	if (next)
+		write_seqcount_begin_nested(&next->vm_sequence, SINGLE_DEPTH_NESTING);
+
 	if (next && !insert) {
 		struct vm_area_struct *exporter = NULL;
 
@@ -880,7 +886,10 @@ again:			remove_next = 1 + (end > next->
 		 * we must remove another next too. It would clutter
 		 * up the code too much to do both in one go.
 		 */
+		write_seqcount_end(&next->vm_sequence);
 		next = vma->vm_next;
+		write_seqcount_begin_nested(&next->vm_sequence, SINGLE_DEPTH_NESTING);
+
 		if (remove_next == 2)
 			goto again;
 		else if (next)
@@ -891,6 +900,10 @@ again:			remove_next = 1 + (end > next->
 	if (insert && file)
 		uprobe_mmap(insert);
 
+	if (next)
+		write_seqcount_end(&next->vm_sequence);
+	write_seqcount_end(&vma->vm_sequence);
+
 	validate_mm(mm);
 
 	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/