diff mbox

[08/13] vrange: Send SIGBUS when user try to access purged page

Message ID 1370916692-9576-9-git-send-email-john.stultz@linaro.org
State Superseded
Headers show

Commit Message

John Stultz June 11, 2013, 2:11 a.m. UTC 
From: Minchan Kim <minchan@kernel.org>

By vrange(2) semantic, user should see SIGBUG if he try to access
purged page without vrange(...VRANGE_NOVOLATILE).

This patch implements it.

I reused PSE bit for quick prototype without enough considering
so need time to see what's empty bit and I am surely missing
many places to handle vrange pte bit. I should investigate all of
pte handling places, especially pte_none case. TODO

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/x86/include/asm/pgtable_types.h |  2 ++
 include/asm-generic/pgtable.h        | 11 +++++++++++
 include/linux/vrange.h               |  2 ++
 mm/memory.c                          | 23 +++++++++++++++++++++--
 mm/vrange.c                          | 24 +++++++++++++++++++++++-
 5 files changed, 59 insertions(+), 3 deletions(-)
diff mbox

Patch

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index e642300..d7ea6a0 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -64,6 +64,8 @@ 
 #define _PAGE_FILE	(_AT(pteval_t, 1) << _PAGE_BIT_FILE)
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
+#define _PAGE_VRANGE	_PAGE_BIT_PSE
+
 /*
  * _PAGE_NUMA indicates that this page will trigger a numa hinting
  * minor page fault to gather numa placement statistics (see
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a59ff51..91e8f6f 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -479,6 +479,17 @@  static inline unsigned long my_zero_pfn(unsigned long addr)
 
 #ifdef CONFIG_MMU
 
+static inline pte_t pte_mkvrange(pte_t pte)
+{
+	pte = pte_set_flags(pte, _PAGE_VRANGE);
+	return pte_clear_flags(pte, _PAGE_PRESENT);
+}
+
+static inline int pte_vrange(pte_t pte)
+{
+	return ((pte_flags(pte) | _PAGE_PRESENT) == _PAGE_VRANGE);
+}
+
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_trans_huge(pmd_t pmd)
 {
diff --git a/include/linux/vrange.h b/include/linux/vrange.h
index cbb609a..75754d1 100644
--- a/include/linux/vrange.h
+++ b/include/linux/vrange.h
@@ -41,6 +41,8 @@  int discard_vpage(struct page *page);
 bool vrange_address(struct mm_struct *mm, unsigned long start,
 			unsigned long end);
 
+extern bool is_purged_vrange(struct mm_struct *mm, unsigned long address);
+
 #else
 
 static inline void vrange_init(void) {};
diff --git a/mm/memory.c b/mm/memory.c
index 6dc1882..f9bc45c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -59,6 +59,7 @@ 
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
+#include <linux/vrange.h>
 
 #include <asm/io.h>
 #include <asm/pgalloc.h>
@@ -841,7 +842,7 @@  copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	/* pte contains position in swap or file, so copy. */
 	if (unlikely(!pte_present(pte))) {
-		if (!pte_file(pte)) {
+		if (!pte_file(pte) && !pte_vrange(pte)) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
 			if (swap_duplicate(entry) < 0)
@@ -1181,7 +1182,7 @@  again:
 		if (pte_file(ptent)) {
 			if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
 				print_bad_pte(vma, addr, ptent, NULL);
-		} else {
+		} else if (!pte_vrange(ptent)) {
 			swp_entry_t entry = pte_to_swp_entry(ptent);
 
 			if (!non_swap_entry(entry))
@@ -3716,9 +3717,27 @@  int handle_pte_fault(struct mm_struct *mm,
 					return do_linear_fault(mm, vma, address,
 						pte, pmd, flags, entry);
 			}
+anon:
 			return do_anonymous_page(mm, vma, address,
 						 pte, pmd, flags);
 		}
+
+		if (unlikely(pte_vrange(entry))) {
+			if (!is_purged_vrange(mm, address)) {
+				/* zap pte */
+				ptl = pte_lockptr(mm, pmd);
+				spin_lock(ptl);
+				if (unlikely(!pte_same(*pte, entry)))
+					goto unlock;
+				flush_cache_page(vma, address, pte_pfn(*pte));
+				ptep_clear_flush(vma, address, pte);
+				pte_unmap_unlock(pte, ptl);
+				goto anon;
+			}
+
+			return VM_FAULT_SIGBUS;
+		}
+
 		if (pte_file(entry))
 			return do_nonlinear_fault(mm, vma, address,
 					pte, pmd, flags, entry);
diff --git a/mm/vrange.c b/mm/vrange.c
index 3589d10..603057e 100644
--- a/mm/vrange.c
+++ b/mm/vrange.c
@@ -477,7 +477,9 @@  int try_to_discard_one(struct page *page, struct vm_area_struct *vma,
 
 	present = pte_present(*pte);
 	flush_cache_page(vma, address, page_to_pfn(page));
-	pteval = ptep_clear_flush(vma, address, pte);
+
+	ptep_clear_flush(vma, address, pte);
+	pteval = pte_mkvrange(*pte);
 
 	update_hiwater_rss(mm);
 	dec_mm_counter(mm, MM_ANONPAGES);
@@ -491,6 +493,7 @@  int try_to_discard_one(struct page *page, struct vm_area_struct *vma,
 			BUG_ON(1);
 	}
 
+	set_pte_at(mm, address, pte, pteval);
 	pte_unmap_unlock(pte, ptl);
 	mmu_notifier_invalidate_page(mm, address);
 	ret = 1;
@@ -588,3 +591,22 @@  int discard_vpage(struct page *page)
 	return 0;
 }
 
+bool is_purged_vrange(struct mm_struct *mm, unsigned long address)
+{
+	struct vrange_root *vroot = &mm->vroot;
+	struct interval_tree_node *node;
+	struct vrange *range;
+	bool ret = false;
+
+	vrange_lock(vroot);
+	node = interval_tree_iter_first(&vroot->v_rb, address,
+						address + PAGE_SIZE - 1);
+	if (node) {
+		range = container_of(node, struct vrange, node);
+		if (range->purged)
+			ret = true;
+	}
+	vrange_unlock(vroot);
+	return ret;
+}
+